CN109858548A - The judgment method and device of abnormal power consumption, storage medium, communication terminal - Google Patents
The judgment method and device of abnormal power consumption, storage medium, communication terminal Download PDFInfo
- Publication number
- CN109858548A CN109858548A CN201910087102.4A CN201910087102A CN109858548A CN 109858548 A CN109858548 A CN 109858548A CN 201910087102 A CN201910087102 A CN 201910087102A CN 109858548 A CN109858548 A CN 109858548A
- Authority
- CN
- China
- Prior art keywords
- power consumption
- gray level
- level image
- characteristic
- eigenmatrix
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Image Analysis (AREA)
Abstract
This disclosure relates to field of communication technology, and in particular to a kind of judgment method of exception power consumption, a kind of judgment means, a kind of computer-readable medium and a kind of communication terminal of abnormal power consumption.The described method includes: extracting the characteristic in predetermined period in power consumption log；The characteristic is handled by preset rules to obtain corresponding gray level image；The gray level image is inputted into abnormal power consumption identification model, to obtain the power consumption anomalous identification result of the predetermined period.The case where disclosure can be read out and identify to the gray level image using the abnormal power consumption identification model trained, and whether there is abnormal power consumption to judge terminal device in the predetermined period.
Description
Technical field
This disclosure relates to field of communication technology, and in particular to a kind of judgment method of exception power consumption, a kind of abnormal power consumption
Judgment means, a kind of computer-readable medium and a kind of communication terminal.
Background technique
With the fast development of intelligent mobile terminal and development of Mobile Internet technology, the data-handling capacity of intelligent mobile terminal
More and more by force, screen size is increasing, resolution ratio is higher and higher.It is corresponding, power consumption of the intelligent mobile terminal in use process
Amount is also increasing, and stand-by time is easy to cause to shorten, and accelerates cell decay.Therefore, intelligent mobile terminal was being used
The identification and analysis of power consumption exception in journey just become more and more important.
When the prior art identifies intelligent mobile terminal progress abnormal power consumption, preparatory write comprising for possible is needed mostly
Then the program of the decision logic of existing every case is carried out to terminal device according to the collected data with the presence or absence of abnormal
Power consumption carries out knowing judgement and analysis.But it is big due to the generation power consumption of intelligent mobile terminal in actual use is abnormal
Mostly relative complex, the reason of generating abnormal power consumption, there may be tens hundreds of possibilities, and generated abnormal multiple of power consumption
There is likely to be certain relevances between reason.Therefore, the prior art writes abnormal power consumption determining program and needs to expend largely
Time and manpower, need lasting maintenance code；And judgment mechanism is also inflexible.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
A kind of judgment method for being designed to provide abnormal power consumption of the disclosure, a kind of judgment means of abnormal power consumption, one
Kind computer-readable medium, a kind of communication terminal avoid to provide a kind of new abnormal power consumption judgment mode to code
Maintenance, saves time and human cost, to overcome the limitation and defect of the relevant technologies to a certain extent.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the disclosure in a first aspect, providing a kind of judgment method of abnormal power consumption, comprising:
Extract the characteristic in predetermined period in power consumption log；
The characteristic is handled by preset rules to obtain corresponding gray level image；
The gray level image is inputted into abnormal power consumption identification model, to obtain the power consumption anomalous identification knot of the predetermined period
Fruit.
According to the second aspect of the disclosure, a kind of judgment means of abnormal power consumption are provided, comprising:
Characteristic extraction module, for extracting the characteristic in predetermined period in power consumption log；
Gray level image generation module, for handling the characteristic by preset rules to obtain corresponding gray level image；
Recognition result generation module, it is described pre- to obtain for the gray level image to be inputted abnormal power consumption identification model
If the power consumption anomalous identification result in period.
According to the third aspect of the disclosure, a kind of computer-readable medium is provided, is stored thereon with computer program, it is described
The judgment method of above-mentioned abnormal power consumption is realized when computer program is executed by processor.
According to the fourth aspect of the disclosure, a kind of communication terminal is provided, comprising:
One or more processors；
Storage device, for storing one or more programs, when one or more of programs are one or more of
When processor executes, so that one or more of processors realize the judgement of above-mentioned abnormal power consumption.
In the judgment method of exception power consumption provided by a kind of embodiment of the disclosure, by will be in predetermined period duration
Characteristic included in power consumption log is converted to the gray level image with corresponding data characteristic, has trained so as to utilization
Abnormal power consumption identification model the gray level image is read out and is identified, with judge terminal device in the predetermined period whether
The case where there are abnormal power consumptions.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 schematically shows a kind of schematic diagram of the judgment method of exception power consumption in disclosure exemplary embodiment；
Fig. 2 schematically shows a kind of showing for method for converting characteristic to grayscale image in disclosure exemplary embodiment
It is intended to；
Fig. 3 schematically shows a kind of signal of feature object arrangement mode in eigenmatrix in disclosure exemplary embodiment
Figure；
Fig. 4 schematically shows in disclosure exemplary embodiment showing for feature object arrangement mode in another eigenmatrix
It is intended to；
Fig. 5 schematically shows a kind of schematic diagram of gray level image in disclosure exemplary embodiment；
Fig. 6 schematically shows a kind of composition schematic diagram of Wireless network connection equipment in disclosure exemplary embodiment；
Fig. 7 schematically shows a kind of structure of the computer system of wireless telecom equipment in disclosure exemplary embodiment and shows
It is intended to.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
It is existing in the intelligent mobile terminal equipment in use judgment method of abnormal power consumption condition there are still
Some problem and shortage, such as: it needs that complicated decision logic is arranged by code, judgment mechanism is also inflexible.In addition, by
In generate abnormal power consumption the case where may be multiple application programs or due to synthesis cause, and may be used also between multiple reasons
There can be certain relevance, it is understood that there may be the case where abnormal power consumption cannot be accurately identified.
The shortcomings that for the above-mentioned prior art and deficiency provide a kind of sentencing for abnormal power consumption in this example embodiment
Disconnected method, can be applied to the terminal devices such as mobile phone, tablet computer and laptop.With reference to shown in Fig. 1, above-mentioned is different
The judgment method of normal power consumption may comprise steps of:
S11 extracts the characteristic in predetermined period in power consumption log；
S12 handles the characteristic by preset rules to obtain corresponding gray level image；
The gray level image is inputted abnormal power consumption identification model by S13, is known extremely with obtaining the power consumption of the predetermined period
Other result.
In the judgment method of exception power consumption provided by this example embodiment, history power consumption daily record data instruction is advanced with
Practice exception power consumption identification model.When being identified and judgeed to abnormal power consumption, by by the power consumption day in predetermined period duration
Characteristic included in will is converted to corresponding gray level image, so that gray level image has the corresponding feature of power consumption log,
Data are expressed by the number of greyscale levels of pixel each in gray level image.So as to utilize the abnormal power consumption identification model pair trained
The case where gray level image is read out and identifies, whether there is abnormal power consumption to judge terminal device in the predetermined period.
In the following, accompanying drawings and embodiments will be combined to each step of the judgment method of the abnormal power consumption in this example embodiment
Suddenly it is described in detail.
For above-mentioned intelligent terminal, power consumption details when it should be understood that system is run, or to power consumption
When amount is analyzed, detailed power consumption can be obtained by checking, analyzing power consumption log or the electricity statistical log of battery
Data.
Step S11 extracts the characteristic in predetermined period in power consumption log.
In this example embodiment, it generally may include: runing time, bright screen time in electricity statistical log, go out when shielding
Between and the classifications such as electricity consumption value under different hardware module or different conditions parameter.By being read to electricity statistical log
It reads, it can be determined that the problem of going out in current electricity statistical log with the presence or absence of abnormal power consumption, but can not also directly interpret and provide
The abnormal power consumption period of body and corresponding abnormal power consumption reason.Therefore, part and power consumption in electricity statistical log can be chosen
Data basis of the characteristic of strong correlation as abnormal power consumption analysis.
Use duration as cycle length in addition, above-mentioned predetermined period can be using certain, or with certain electricity
Length of the amount consumption as the period.For example, the length that the period can be set is that terminal device uses five minutes, ten minutes or 60
The durations such as minute；It can also configure using the length in 1%, 2% or 5% as period of terminal device electric quantity consumption.
The characteristic being selected may include multiple with the feature object of power consumption strong correlation and corresponding parameter, example
Such as: screen use state, screen intensity, CPU use state, volume, Web vector graphic state, talking state, signal strength, network
Wake-up times, using wakeup frequency, foreground application state, CPU wake-up times and camera use state etc..
It for example, is 1% as cycle length using intelligent terminal power consumption, above-mentioned screen state can be with
It is percentage of the bright screen total time in current period in predetermined period；For example, terminal is in the corresponding use of current period
A length of 50 minutes, the total duration of bright screen was 20 minutes in the period in this prior, then accounting of the bright screen time in current period is
40%.Above-mentioned screen intensity can be average brightness value when screen is waken up in current period.CPU use state can be with
It is the average dedicated percentage of CPU in current period.It is called that volume can be loudspeaker, earpiece and microphone in current week
When average volume size.Above-mentioned Web vector graphic state can refer to the total duration of terminal device in a network in current period
Or the accounting in the net time.Above-mentioned talking state can refer to specific call total duration.Signal strength can be current
Average signal strength in period.Above-mentioned foreground application state then can be different grades of according to what is used in current period
The corresponding average load of multiple application programs indicates.Above-mentioned camera status, which can use the specific of camera in current period, to be made
It is indicated with duration.
Certainly, in other exemplary embodiments of the disclosure, above-mentioned feature object is also possible to the number of background application
Amount and the accounting of application total quantity or the duration of background application etc..
Step S12 handles the characteristic by preset rules to obtain corresponding gray level image.
In this example embodiment, the characteristic in predetermined period can be converted to corresponding gray scale figure, and make
The gray level image has the characteristic of characteristic in the period.Specifically, refering to what is shown in Fig. 2, the above method may include:
Step S121 generates the eigenmatrix of default dimension according to the quantity of feature object.
In this example embodiment, characteristic may include the parameter of multiple feature objects and feature object.Specifically
For, step S121 may include:
Step S1211 is normalized feature object parameter so that each feature object parameter configuration is pre-
Setting parameter range；
Step S1212 is arranged to generate eigenmatrix the feature object parameter after normalized by preset order.
For example, different number can be chosen according to the different demands analyzed power consumption or the feature object of type is raw special
Levy matrix.For example, refering to what is shown in Fig. 3,12 feature objects that can be chosen in above-mentioned example generate the feature that dimension is 3 × 4
Matrix.
Certainly, in other exemplary embodiments of the disclosure, in order to facilitate each spy in calculating and balance characteristics matrix
The attribute and parameter of object are levied, can also configuring matrix be according to actual needs other dimensions, and choose other feature pair
As.For example, refering to what is shown in Fig. 4, the eigenmatrix that 9 feature objects in above-mentioned example generate 3 × 3 can also be chosen；Or
Choose the eigenmatrix that 8 feature objects generate 4 × 2.The disclosure does not do particular determination to the concrete form of eigenmatrix.
After determining the form of eigenmatrix, the corresponding parameter of each feature object in current period can be extracted, and right
Each feature object parameter is normalized, and makes the numerical value between feature object parameter processing 0-255, with gray level image
Number of greyscale levels can be corresponded to effectively, the conversion convenient for the later period to gray level image.
Step S122 converts corresponding gray level image by preset rules for the eigenmatrix.
It, can be according to the generation pair of the dimension of the eigenmatrix after obtaining eigenmatrix in this example embodiment
The gray level image of size is answered, and respective pixel in the gray level image is configured according to the numerical value of each element in the eigenmatrix
Number of greyscale levels.It can be by a block of pixels in each of matrix element corresponding grey scale image.For example, for Fig. 3
Shown in 4 × 3 matrix, corresponding gray level image is as shown in Figure 5.
The gray level image is inputted abnormal power consumption identification model by step S13, different with the power consumption for obtaining the predetermined period
Normal recognition result.
In this example embodiment, it is different to obtain that history power consumption daily record data training neural network module can be advanced with
Normal power consumption identification model, then using gray level image as input parameter, gray level image is carried out using the exception power consumption identification model
Identification and analysis, the case where judgement in each period with the presence or absence of abnormal power consumption.
Specifically, the abnormal power consumption identification model of training may include:
Step S211 extracts history power consumption log, and extracts characteristic by predetermined period to the history power consumption log.
The power consumption log of intelligent terminal or electricity statistical log generally may include normal power consumption log and exception
Power consumption log.Wherein, normal power consumption log refer to intelligent terminal in use no exceptions power consumption when it is produced
Electricity statistical log；And abnormal power consumption log refers to that intelligent terminal is produced in the presence of abnormal power consumption behavior in use
Raw electricity statistical log can be marked determining power consumption extremely in abnormal power consumption log.
After the abnormal power consumption log for extracting intelligent terminal, daily record data can be carried out by the preset period first
It divides, such as using power consumption 1% as cycle length.And extract the characteristic in each period, for example, characteristic
It may include 8,9 or 12 feature objects and the corresponding design parameter in above-described embodiment.
Step S212 handles the characteristic by preset rules and generates corresponding gray level image, according to the gray scale
Image generates sample data；Wherein, the sample data includes positive sample set and negative sample set.
In an exemplary embodiment of the disclosure, since acquisition positive sample can be relatively easy in normal power consumption log
Data, and by carrying out being converted to negative sample data to positive sample data.It therefore, can be raw using only normal power consumption log
At sample data.Specifically, when generating sample data according to normal power consumption log, above-mentioned step S212 may include:
Step S311 is generated according to the quantity for the feature object for including in the corresponding characteristic of the normal power consumption log
The positive sample eigenmatrix of default dimension；
Step S312 converts corresponding gray level image by preset rules for the positive sample eigenmatrix, in order to root
Positive sample set is generated according to the gray level image；And
Step S313 carries out random matrix conversion to the positive sample eigenmatrix to obtain negative sample eigenmatrix；
Step S314 converts corresponding gray level image by preset rules for the negative sample eigenmatrix, in order to root
Negative sample set is generated according to the gray level image.
After characteristic in obtaining the normal power consumption log of history in each period, can to each feature object parameter into
Row normalized, and according to the positive sample eigenmatrix of treated data generate corresponding default dimension, further according to positive sample
Eigen matrix generates corresponding gray level image, to obtain positive sample set.Further, it is also possible to each positive sample eigenmatrix
Carry out conversion process.For example, can be carried out to positive sample eigenmatrix any in transposition, rotation, conjugation or conjugate transposition
A kind of or any a variety of operations.To obtain corresponding negative sample matrix.
Certainly, in other exemplary embodiments of the disclosure, one and positive sample eigenmatrix dimension phase also can be set
Same transition matrix, after making positive sample eigenmatrix and the transition matrix carry out single or multiple additions, subtraction
Obtain negative sample eigenmatrix.Or one or more transforming numericals also can be set, by making positive sample eigenmatrix and one
A or multiple transforming numericals carry out one or many scale multiplications and obtain corresponding negative sample eigenmatrix.The disclosure is to matrix
Conversion method does not do particular determination.
In another exemplary embodiment of the present disclosure, history power consumption log also may include abnormal power consumption log.Specifically
For, above-mentioned method can also include:
Step S321 extracts characteristic by predetermined period to the history exception power consumption log；
Step S322 generates the negative sample eigenmatrix of default dimension according to the characteristic；
Step S323 converts corresponding gray level image by preset rules for the negative sample eigenmatrix, in order to root
Negative sample set is generated according to the gray level image.
After characteristic in obtaining the power consumption log of history exception in each period, hair can be screened by artificial mode
The period of raw exception power consumption, and each feature object parameter in those periods is normalized, and according to treated
Data generate the negative sample eigenmatrix of corresponding default dimension, generate corresponding grayscale image further according to negative sample eigenmatrix
Picture, to obtain negative sample set.
Step S213 obtains the abnormal power consumption identification as training neural network model is inputted using the sample data
Model.
It, can be by sample data after obtaining positive sample set and negative sample set in this example embodiment
Neural network model is inputted, neural network model is trained, to obtain abnormal power consumption identification model.For example, refreshing
Convolutional neural networks model or full convolutional neural networks model etc. can be used through network model, the disclosure is to neural network model
Structure do not do particular determination.
Based on above content, in other exemplary embodiments of the disclosure, after obtaining sample data, or utilize different
It, can also be wrong with the presence or absence of exception or data to each gray level image of acquisition when normal power consumption identification model carries out abnormal power consumption identification
Accidentally carry out judgement screening.For example, may include:
Whether step S331 judges the number of greyscale levels of each pixel in the gray level image in corresponding preset threshold range；
Step S332, if judging, the number of greyscale levels of pixel in the gray level image is not being corresponded in preset threshold range,
Determine that the gray level image is abnormal images to delete and/or mark the gray level image.
In this exemplary embodiment, the numberical range of each feature object in eigenmatrix can be pre-configured with.For example, setting
The numberical range of volume is 0-100, and the numberical range of camera use state is in 0-60 etc..It is special for being generated according to characteristic
Matrix is levied, or after being converted into gray level image according to eigenmatrix, the number of greyscale levels of each pixel can be read out, is judged
The case where with the presence or absence of error in data.If there are error in data for one or more gray level images in judgement sample data, can
To delete or mark the gray level image, to improve the validity of sample data.If sentencing during abnormal power consumption identification
Breaking, there are mistakes to gray level image, then can be marked, so that convenient generate gray level image to the period again.
Method provided by the embodiment of the present disclosure, by extracting the characteristic in each period, and it is raw using characteristic
At corresponding gray level image, the data characteristics that each period has, Bu Huiyin can complete in gray level image, be accurately shown
The conversion of data makes initial data fail.In addition, by being identified using power consumption abnormal conditions of the gray level image to each period,
The training difficulty of neural network model can be reduced, and effectively promotes the accuracy of identification, it can be accurately to abnormal power consumption
The time of generation is positioned.And then the original for generating abnormal power consumption can be accurately analyzed according to the period corresponding characteristic
Cause.The prior art is avoided to need to write complicated decision logic when analyzing abnormal power consumption, save time cost and manpower at
This.Also, with increasing for identification number, the accuracy rate of recognition result will be stepped up
It should be noted that above-mentioned attached drawing is only showing for processing included by method according to an exemplary embodiment of the present invention
Meaning property explanation, rather than limit purpose.It can be readily appreciated that it is above-mentioned it is shown in the drawings processing do not indicate or limit these processing when
Between sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Further, refering to what is shown in Fig. 6, also providing a kind of judgment means of abnormal power consumption in this exemplary embodiment
60, comprising: characteristic extraction module 601, gray level image generation module 602 and recognition result generation module 603.Wherein:
The characteristic extraction module 601 can be used for extracting the characteristic in predetermined period in power consumption log.
The gray level image generation module 602 can be used for handling the characteristic by preset rules corresponding to obtain
Gray level image.
The recognition result generation module 603 can be used for inputting the gray level image into abnormal power consumption identification model, with
Obtain the power consumption anomalous identification result of the predetermined period.
In a kind of example of the disclosure, the gray level image generation module 602 may include: matrix generation module and figure
As conversion module (not shown).Wherein,
The matrix generation module can be used for generating the eigenmatrix of default dimension according to the quantity of feature object.
Described image conversion module can be used for converting corresponding gray level image by preset rules for the eigenmatrix.
In a kind of example of the disclosure, the matrix generation module includes: parameter processing module and parameter arrangement module
(not shown).Wherein,
The parameter processing module can be used for that feature object parameter is normalized so that each feature pair
As parameter configuration is in preset parameter range.
Parameter arrangement module can be used for the feature object parameter after normalized by preset order arrange with
Generate eigenmatrix.
In a kind of example of the disclosure, described image conversion module may include: that image configurations module (is not shown in figure
Out).
Described image configuration module can be used for generating the gray level image of correspondingly-sized according to the dimension of the eigenmatrix,
And the number of greyscale levels of respective pixel in the gray level image is configured according to the numerical value of each element in the eigenmatrix.
In a kind of example of the disclosure, described device further include: model training module (not shown).Wherein,
The model training module can be used for training the abnormal power consumption identification model in advance；Include:
History log data extraction module can be used for extracting history power consumption log, and press to the history power consumption log
Predetermined period extracts characteristic.
Sample data generation module can be used for handling the corresponding grayscale image of the characteristic generation by preset rules
Picture, to generate sample data according to the gray level image；Wherein, the sample data includes positive sample set and negative sample collection
It closes.
Training execution module can be used for described to obtain using the sample data as training neural network model is inputted
Abnormal power consumption identification model.
In a kind of example of the disclosure, the history power consumption log includes normal power consumption log；The sample data is raw
It may include: positive sample eigenmatrix generation module, positive sample set generation module, sample conversion module and first at module
Negative sample set generation module (not shown).
Wherein,
The positive sample eigenmatrix generation module can be used for according to the corresponding characteristic of the normal power consumption log
In include the quantity of feature object generate the positive sample eigenmatrix of default dimension.
The positive sample set generation module can be used for converting the positive sample eigenmatrix to pair by preset rules
The gray level image answered, in order to generate positive sample set according to the gray level image.
The sample conversion module can be used for carrying out the positive sample eigenmatrix random matrix conversion negative to obtain
Sample characteristics matrix.
The first negative sample set generation module can be used for converting the negative sample eigenmatrix by preset rules
For corresponding gray level image, in order to generate negative sample set according to the gray level image.
In a kind of example of the disclosure, the history power consumption log further includes abnormal power consumption log, the sample data
Generation module may include: negative sample data extraction module, negative sample eigenmatrix generation module and the second negative sample set
Generation module (not shown).Wherein,
The negative sample data extraction module can be used for extracting the history exception power consumption log by predetermined period special
Levy data.
The negative sample eigenmatrix generation module can be used for generating the negative sample of default dimension according to the characteristic
Eigen matrix.
The second negative sample set generation module can be used for converting the negative sample eigenmatrix by preset rules
For corresponding gray level image, in order to generate negative sample set according to the gray level image.
In a kind of example of the disclosure, above-mentioned device can also include: data checking module and image processing module
(not shown).Wherein,
Whether the data checking module can be used for judging the number of greyscale levels of each pixel in the gray level image in correspondence
In preset threshold range.
If described image processing module can be used for judging the number of greyscale levels of pixel in the gray level image not corresponding pre-
If in threshold range, then determining that the gray level image is abnormal images to delete and/or mark the gray level image.
The detail of each module is in the judgement of corresponding abnormal power consumption in the judgment means of above-mentioned abnormal power consumption
It is described in detail in method, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
Fig. 7 shows the structural representation for being suitable for the computer system for the wireless telecom equipment for being used to realize the embodiment of the present invention
Figure.
It should be noted that the computer system 700 of the electronic equipment shown in Fig. 7 is only an example, it should not be to this hair
The function and use scope of bright embodiment bring any restrictions.
As shown in fig. 7, computer system 700 includes central processing unit (Central Processing Unit, CPU)
701, it can be according to the program being stored in read-only memory (Read-Only Memory, ROM) 702 or from storage section
708 programs being loaded into random access storage device (Random Access Memory, RAM) 703 and execute various appropriate
Movement and processing.In RAM 703, it is also stored with various programs and data needed for system operatio.CPU 701, ROM702 with
And RAM 703 is connected with each other by bus 704.Input/output (Input/Output, I/O) interface 705 is also connected to bus
704。
I/O interface 705 is connected to lower component: the importation 706 including keyboard, mouse etc.；It is penetrated including such as cathode
Spool (Cathode Ray Tube, CRT), liquid crystal display (Liquid Crystal Display, LCD) etc. and loudspeaker
Deng output par, c 707；Storage section 708 including hard disk etc.；And including such as LAN (Local Area Network, office
Domain net) card, modem etc. network interface card communications portion 709.Communications portion 709 via such as internet network
Execute communication process.Driver 710 is also connected to I/O interface 705 as needed.Detachable media 711, such as disk, CD,
Magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 710, in order to from the computer journey read thereon
Sequence is mounted into storage section 708 as needed.
Particularly, according to an embodiment of the invention, may be implemented as computer below with reference to the process of flow chart description
Software program.For example, the embodiment of the present invention includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 709, and/or from detachable media
711 are mounted.When the computer program is executed by central processing unit (CPU) 701, executes and limited in the system of the application
Various functions.
It should be noted that computer-readable medium shown in the embodiment of the present invention can be computer-readable signal media
Or computer readable storage medium either the two any combination.Computer readable storage medium for example can be with
System, device or the device of --- but being not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than
Combination.The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires
Electrical connection, portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type are programmable
Read-only memory (Erasable Programmable Read Only Memory, EPROM), flash memory, optical fiber, Portable, compact
Disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In the present invention, computer readable storage medium can be it is any include or storage program
Tangible medium, which can be commanded execution system, device or device use or in connection.And in this hair
In bright, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer-readable medium other than storage medium, the computer-readable medium can send, propagate or transmit for by
Instruction execution system, device or device use or program in connection.The journey for including on computer-readable medium
Sequence code can transmit with any suitable medium, including but not limited to: wireless, wired etc. or above-mentioned is any appropriate
Combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in unit involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part realizes that described unit also can be set in the processor.Wherein, the title of these units is in certain situation
Under do not constitute restriction to the unit itself.
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in electronic equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when the electronics is set by one for said one or multiple programs
When standby execution, so that method described in electronic equipment realization as the following examples.For example, the electronic equipment can be real
Each step now as shown in Figures 1 to 5.
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the attached claims.
Claims (11)
1. a kind of judgment method of exception power consumption characterized by comprising
Extract the characteristic in predetermined period in power consumption log；
The characteristic is handled by preset rules to obtain corresponding gray level image；
The gray level image is inputted into abnormal power consumption identification model, to obtain the power consumption anomalous identification result of the predetermined period.
2. the method according to claim 1, wherein the characteristic includes multiple feature objects and feature pair
As corresponding parameter；It is described to include: to obtain corresponding gray level image by the preset rules processing characteristic
The eigenmatrix of default dimension is generated according to the quantity of feature object；
Corresponding gray level image is converted by preset rules by the eigenmatrix.
3. according to the method described in claim 2, it is characterized in that, described generate default dimension according to the feature object parameter
Eigenmatrix include:
Feature object parameter is normalized so that each feature object parameter configuration is in preset parameter range；
Feature object parameter after normalized is arranged by preset order to generate eigenmatrix.
4. according to the method described in claim 3, it is characterized in that, described converted the eigenmatrix to pair by preset rules
The gray level image answered includes:
The gray level image of correspondingly-sized is generated according to the dimension of the eigenmatrix, and according to each element in the eigenmatrix
Numerical value configures the number of greyscale levels of respective pixel in the gray level image.
5. the method according to claim 1, wherein the method also includes:
The abnormal power consumption identification model is trained in advance, comprising:
History power consumption log is extracted, and characteristic is extracted by predetermined period to the history power consumption log；
The characteristic is handled by preset rules and generates corresponding gray level image, to generate sample number according to the gray level image
According to；Wherein, the sample data includes positive sample set and negative sample set；
The abnormal power consumption identification model is obtained as training neural network model is inputted using the sample data.
6. according to the method described in claim 5, it is characterized in that, the history power consumption log includes normal power consumption log；Institute
It states and handles the corresponding gray level image of the characteristic generation by preset rules, to generate sample data according to the gray level image
Include:
Default dimension is being generated just according to the quantity for the feature object for including in the corresponding characteristic of the normal power consumption log
Sample characteristics matrix；
Corresponding gray level image is converted by preset rules by the positive sample eigenmatrix, in order to according to the gray level image
Generate positive sample set；And
Random matrix conversion is carried out to obtain negative sample eigenmatrix to the positive sample eigenmatrix；
Corresponding gray level image is converted by preset rules by the negative sample eigenmatrix, in order to according to the gray level image
Generate negative sample set.
7. according to the method described in claim 6, it is characterized in that, the history power consumption log further includes abnormal power consumption log；
The method also includes:
Characteristic is extracted by predetermined period to the history exception power consumption log；
The negative sample eigenmatrix of default dimension is generated according to the characteristic；
Corresponding gray level image is converted by preset rules by the negative sample eigenmatrix, in order to according to the gray level image
Generate negative sample set.
8. according to the method described in claim 5, it is characterized in that, the method also includes:
Judge the number of greyscale levels of each pixel in the gray level image whether in corresponding preset threshold range；
If judging, the number of greyscale levels of pixel in the gray level image not in corresponding preset threshold range, determines the grayscale image
As being abnormal images to delete and/or mark the gray level image.
9. a kind of judgment means of exception power consumption characterized by comprising
Characteristic extraction module, for extracting the characteristic in predetermined period in power consumption log；
Gray level image generation module, for handling the characteristic by preset rules to obtain corresponding gray level image；
Recognition result generation module, for the gray level image to be inputted abnormal power consumption identification model, to obtain the default week
The power consumption anomalous identification result of phase.
10. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that the computer program is located
Manage the judgment method realized when device executes such as abnormal power consumption described in any item of the claim 1 to 8.
11. a kind of communication terminal characterized by comprising
One or more processors；
Storage device, for storing one or more programs, when one or more of programs are by one or more of processing
When device executes, so that one or more of processors realize sentencing such as abnormal power consumption described in any item of the claim 1 to 8
Disconnected method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910087102.4A CN109858548B (en) | 2019-01-29 | 2019-01-29 | Method and device for judging abnormal power consumption, storage medium and communication terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910087102.4A CN109858548B (en) | 2019-01-29 | 2019-01-29 | Method and device for judging abnormal power consumption, storage medium and communication terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109858548A true CN109858548A (en) | 2019-06-07 |
| CN109858548B CN109858548B (en) | 2023-04-18 |
Family
ID=66896792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910087102.4A Active CN109858548B (en) | 2019-01-29 | 2019-01-29 | Method and device for judging abnormal power consumption, storage medium and communication terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858548B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111221736A (en) * | 2020-01-08 | 2020-06-02 | 北京金山安全软件有限公司 | Equipment power consumption method and device and electronic equipment |
| CN111722993A (en) * | 2020-06-16 | 2020-09-29 | 广东小天才科技有限公司 | Method and system for monitoring abnormal power consumption of communication terminal, terminal device and storage medium |
| CN113051128A (en) * | 2019-12-27 | 2021-06-29 | Oppo广东移动通信有限公司 | Power consumption detection method and device, electronic equipment and storage medium |
| CN114860535A (en) * | 2022-04-18 | 2022-08-05 | 地平线征程(杭州)人工智能科技有限公司 | Data evaluation model generation method and device and abnormal data monitoring method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017094263A1 (en) * | 2015-12-04 | 2017-06-08 | 日本電気株式会社 | Log analysis system, method, and program |
| CN107330731A (en) * | 2017-06-30 | 2017-11-07 | 北京京东尚科信息技术有限公司 | It is a kind of to recognize that advertisement position clicks on abnormal method and apparatus |
| JP2017224051A (en) * | 2016-06-13 | 2017-12-21 | 株式会社リコー | Information processing apparatus, information processing method, and program |
| CN107809331A (en) * | 2017-10-25 | 2018-03-16 | 北京京东尚科信息技术有限公司 | The method and apparatus for identifying abnormal flow |
| CN108520063A (en) * | 2018-04-11 | 2018-09-11 | Oppo广东移动通信有限公司 | Processing method, device and the terminal device of event log |
| CN109101527A (en) * | 2018-06-21 | 2018-12-28 | 中国科学院信息工程研究所 | A kind of magnanimity security log information filter method and device |
-
2019
- 2019-01-29 CN CN201910087102.4A patent/CN109858548B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017094263A1 (en) * | 2015-12-04 | 2017-06-08 | 日本電気株式会社 | Log analysis system, method, and program |
| JP2017224051A (en) * | 2016-06-13 | 2017-12-21 | 株式会社リコー | Information processing apparatus, information processing method, and program |
| CN107330731A (en) * | 2017-06-30 | 2017-11-07 | 北京京东尚科信息技术有限公司 | It is a kind of to recognize that advertisement position clicks on abnormal method and apparatus |
| CN107809331A (en) * | 2017-10-25 | 2018-03-16 | 北京京东尚科信息技术有限公司 | The method and apparatus for identifying abnormal flow |
| CN108520063A (en) * | 2018-04-11 | 2018-09-11 | Oppo广东移动通信有限公司 | Processing method, device and the terminal device of event log |
| CN109101527A (en) * | 2018-06-21 | 2018-12-28 | 中国科学院信息工程研究所 | A kind of magnanimity security log information filter method and device |
Non-Patent Citations (1)
| Title |
|---|
| 夏玉明等: "基于卷积神经网络的网络攻击检测方法研究", 《信息网络安全》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113051128A (en) * | 2019-12-27 | 2021-06-29 | Oppo广东移动通信有限公司 | Power consumption detection method and device, electronic equipment and storage medium |
| CN111221736A (en) * | 2020-01-08 | 2020-06-02 | 北京金山安全软件有限公司 | Equipment power consumption method and device and electronic equipment |
| CN111722993A (en) * | 2020-06-16 | 2020-09-29 | 广东小天才科技有限公司 | Method and system for monitoring abnormal power consumption of communication terminal, terminal device and storage medium |
| CN114860535A (en) * | 2022-04-18 | 2022-08-05 | 地平线征程(杭州)人工智能科技有限公司 | Data evaluation model generation method and device and abnormal data monitoring method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109858548B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858548A (en) | The judgment method and device of abnormal power consumption, storage medium, communication terminal | |
| CN109345553A (en) | A kind of palm and its critical point detection method, apparatus and terminal device | |
| WO2019062462A1 (en) | Application control method and apparatus, storage medium and electronic device | |
| EP4113376A1 (en) | Image classification model training method and apparatus, computer device, and storage medium | |
| CN113011646A (en) | Data processing method and device and readable storage medium | |
| CN110659817A (en) | Data processing method and device, machine readable medium and equipment | |
| CN109447787A (en) | Reference report automatically parses method, apparatus, computer equipment and storage medium | |
| CN106845434A (en) | A kind of image-type computer room water leakage monitoring method based on SVMs | |
| CN112364744A (en) | TensorRT-based accelerated deep learning image recognition method, device and medium | |
| CN114708539A (en) | Image type identification method and device, equipment, medium and product thereof | |
| CN107728772B (en) | Application processing method and device, storage medium and electronic equipment | |
| CN111538852A (en) | Multimedia resource processing method, device, storage medium and equipment | |
| CN109345371A (en) | Personal reference report backtracking method and system | |
| CN116229188B (en) | Image processing display method, classification model generation method and equipment thereof | |
| CN113538629A (en) | Detection method and device | |
| CN113052246A (en) | Method and related device for training classification model and image classification | |
| EP4149111A1 (en) | Method for determining video coding test sequence, related apparatus and computer program product | |
| CN108830664A (en) | Difference electronics indigo plant ticket generation method, equipment and computer readable storage medium | |
| CN109062644B (en) | The method and apparatus of processing information for terminal | |
| CN110060183A (en) | Client intelligent matching process, device, computer equipment and storage medium | |
| CN115223221A (en) | Face detection method and device, electronic equipment and storage medium | |
| CN115454755A (en) | Test method for terminal system and related equipment | |
| CN108776959A (en) | Image processing method, device and terminal device | |
| CN111611117B (en) | Hard disk fault prediction method, device, equipment and computer readable storage medium | |
| CN113077251A (en) | Abnormal behavior monitoring method and device in prepaid transaction scene |
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 |