CN107943266A - power consumption control method, device and equipment - Google Patents
power consumption control method, device and equipment Download PDFInfo
- Publication number
- CN107943266A CN107943266A CN201711159364.4A CN201711159364A CN107943266A CN 107943266 A CN107943266 A CN 107943266A CN 201711159364 A CN201711159364 A CN 201711159364A CN 107943266 A CN107943266 A CN 107943266A
- Authority
- CN
- China
- Prior art keywords
- terminal
- operation data
- data
- model
- power consumption
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
- G06F1/329—Power saving characterised by the action undertaken by task scheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44594—Unloading
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mobile Radio Communication Systems (AREA)
- Power Sources (AREA)
- Telephone Function (AREA)
Abstract
The disclosure is directed to a kind of power consumption control method, device and equipment, this method includes:Obtain operation data of the terminal under screen state of currently going out;The operation data are handled using data model, obtain prediction result, the data model carries out multiple operation data of multiple terminals under screen state of going out for server on the model of model training generation, and the prediction result is used to judge whether the terminal is sleep pattern;Determine whether the terminal is sleep pattern under the current screen state of going out according to the prediction result;If the terminal is sleep pattern under the current screen state of going out, power consumption control is carried out to the terminal according to default power consumption strategies, so as to achieve the purpose that terminal power saving during sleep, reduces the power consumption of terminal.
Description
Technical field
This disclosure relates to the communication technology, more particularly to a kind of power consumption control method, device and equipment.
Background technology
With the improvement of living standards, the terminal device such as mobile phone, notebook, ipad, computer, smart television and intelligent watch
Become commonly used equipment, and requirement of the user to its energy consumption is also higher and higher.
In general, in order to reduce the energy consumption of terminal device, in the case where terminal device is not operated for a long time, terminal device
The screen that can go out automatically enters holding state, so as to reduce the energy consumption of terminal device.However, go out screen shape of the terminal device in the long period
Under state, the service such as the third party application (Application, App) of part or rice shaddock (MIUI) can also continue on backstage
Operation, for example, mobile phone is in the case of the screen that goes out, some App still can pushed information etc..
The content of the invention
To overcome problem present in correlation technique, the disclosure provides a kind of power consumption control method, device and equipment.
According to the first aspect of the embodiment of the present disclosure, there is provided a kind of power consumption control method, including:
Obtain operation data of the terminal under screen state of currently going out;
The operation data are handled using data model, obtain prediction result, the data model is server
Multiple operation data of multiple terminals under screen state of going out are carried out with the model of model training generation, the prediction result is used to sentence
Whether the terminal of breaking is sleep pattern;
Determine whether the terminal is sleep pattern under the current screen state of going out according to the prediction result;
If the terminal is sleep pattern under the current screen state of going out, according to default power consumption strategies to the end
End carries out power consumption control.
It is described that the operation data are handled using data model in one embodiment, obtain prediction result, bag
Include:
Feature extraction is carried out to the operation data, obtains feature vector;
Described eigenvector is inputted into the data model, obtains the prediction result.
In one embodiment, the method further includes:
The prediction result is sent to server, so that the server optimizes the data according to the prediction result
Model.
In one embodiment, the default power consumption strategies include at least one in following strategy:
Close or pause at all application program App of the running background of the terminal;
The App in the running background of the terminal is controlled to close partial function;
According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
According to the second aspect of the embodiment of the present disclosure, there is provided a kind of power consumption control method, including:
Obtain multiple operation data of multiple terminals under screen state of going out;
Model training generation data model is carried out to multiple operation data;
The data model is sent to each terminal so that each terminal under screen state of going out according to the data
Model determines whether each terminal is sleep pattern, and carries out power consumption control according to the sleep pattern.
In one embodiment, it is described that model training generation data model is carried out to multiple operation data, including:
Feature extraction is carried out to multiple operation data, obtains feature vector;
Model training is carried out to described eigenvector using machine learning algorithm, generates the data model.
In one embodiment, it is described that model training is carried out to described eigenvector using machine learning algorithm, generate institute
Data model is stated, including:
Successive ignition is carried out to described eigenvector according to default iterative algorithm, generates the model data, the mould
The accuracy rate of type data is more than predetermined threshold value.
In one embodiment, it is described to it is multiple it is described operation data carry out model trainings generation data models before, institute
The method of stating further includes:
Each operation data are carried out with format check, the format check is used for the form for examining the operation data
It is whether correct;
If the format error of the operation data, abandons the operation data.
In one embodiment, it is described to it is multiple it is described operation data carry out model trainings generation data models before, institute
The method of stating further includes:
Each operation data are carried out with completeness check, the completeness check is for examining the operation data
It is no that there are absent field;
If the operation data are there are absent field, the absent field in operation data described in completion.
In one embodiment, the method further includes:
The prediction result that multiple terminals are sent is received, the prediction result uses the data mould for each terminal
Type is to the result that is obtained after the operation data processing under screen state of currently going out;
The data model is optimized according to the prediction result.
In one embodiment, the default power consumption strategies include at least one in following strategy:
Close or pause at all application program App of the running background of the terminal;
The App in the running background of the terminal is controlled to close partial function;
According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
According to the third aspect of the embodiment of the present disclosure, there is provided a kind of power consumption control apparatus, including:
Acquisition module, is configured as obtaining operation data of the terminal under screen state of currently going out;
Processing module, is configured as handling the operation data using data model, obtains prediction result, described
Data model carries out multiple operation data of multiple terminals under screen state of going out for server the model of model training generation, institute
Prediction result is stated to be used to judge whether the terminal is sleep pattern;
Determining module, be configured as according to the prediction result determine the terminal under the current screen state of going out whether
For sleep pattern;
Control module, if it is sleep pattern to be configured as the terminal under the current screen state of going out, according to default
Power consumption strategies to the terminal carry out power consumption control.
In one embodiment, the processing module, including:
Extracting sub-module, is configured as carrying out feature extraction to the operation data, obtains feature vector;
Acquisition submodule, is configured as described eigenvector inputting the data model, obtains the prediction result.
In one embodiment, described device further includes:
Sending module, is configured as the prediction result being sent to server, so that the server is according to described pre-
Survey data model described in result optimizing.
In one embodiment, the default power consumption strategies include at least one in following strategy:
Close or pause at all application program App of the running background of the terminal;
The App in the running background of the terminal is controlled to close partial function;
According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
According to the fourth aspect of the embodiment of the present disclosure, there is provided a kind of power consumption control apparatus, including:
Acquisition module, is configured as obtaining multiple operation data of multiple terminals under screen state of going out;
Generation module, is configured as carrying out model training generation data model to multiple operation data;
Sending module, is configured as the data model being sent to each terminal, so that each terminal is in the screen that goes out
Determine whether each terminal is sleep pattern according to the data model under state, and power consumption is carried out according to the sleep pattern
Control.
In one embodiment, the generation module, including:
Extracting sub-module, is configured as carrying out feature extraction to multiple operation data, obtains feature vector;
Submodule is generated, is configured as carrying out model training to described eigenvector using machine learning algorithm, generates institute
State data model.
In one embodiment, the generation submodule, including:
Iteration submodule, is configured as carrying out described eigenvector successive ignition, generation according to default iterative algorithm
The model data, the accuracy rate of the model data are more than predetermined threshold value.
In one embodiment, described device further includes:
First correction verification module, is configured as carrying out format check to each operation data, the format check is used for
Examine the form of the operation data whether correct;
Discard module, if being configured as the format error of the operation data, abandons the operation data.
In one embodiment, described device further includes:
Second correction verification module, is configured as carrying out completeness check, the completeness check to each operation data
For examining the operation data to whether there is absent field;
Completion module, if being configured as the operation data there are absent field, lacking in operation data described in completion
Lose field.
In one embodiment, described device further includes:
Receiving module, is configured as receiving the prediction result that multiple terminals are sent, the prediction result is each described
Terminal is using the data model to the result that is obtained after the operation data processing under screen state of currently going out;
Optimization module, is configured as optimizing the data model according to the prediction result.
In one embodiment, the default power consumption strategies include at least one in following strategy:
Close or pause at all application program App of the running background of the terminal;
The App in the running background of the terminal is controlled to close partial function;
According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
According to a fifth aspect of the embodiments of the present disclosure, there is provided a kind of equipment, including:
Memory, processor and computer program, the processor run the computer program and perform following methods:
Obtain operation data of the terminal under screen state of currently going out;
The operation data are handled using data model, obtain prediction result, the data model is server
Multiple operation data of multiple terminals under screen state of going out are carried out with the model of model training generation, the prediction result is used to sentence
Whether the terminal of breaking is sleep pattern;
Determine whether the terminal is sleep pattern under the current screen state of going out according to the prediction result;
If the terminal is sleep pattern under the current screen state of going out, according to default power consumption strategies to the end
End carries out power consumption control.
According to the 6th of the embodiment of the present disclosure the aspect, there is provided a kind of equipment, including:
Memory, processor and computer program, the processor run the computer program and perform following methods:
Obtain multiple operation data of multiple terminals under screen state of going out;
Model training generation data model is carried out to multiple operation data;
The data model is sent to each terminal so that each terminal under screen state of going out according to the data
Model determines whether each terminal is sleep pattern, and carries out power consumption control according to the sleep pattern.
According to the 7th of the embodiment of the present disclosure the aspect, there is provided a kind of computer-readable recording medium, is stored thereon with calculating
The step of machine program, which realizes each embodiment the method for first aspect when being executed by processor.
According to the eighth aspect of the embodiment of the present disclosure, there is provided a kind of computer-readable recording medium, is stored thereon with calculating
The step of machine program, which realizes each embodiment the method for second aspect when being executed by processor.
The technical scheme provided by this disclosed embodiment can include the following benefits:
In one embodiment, operation data of the terminal under screen state of currently going out are obtained;Using data model to running number
According to being handled, prediction result is obtained, determines whether terminal is sleep pattern under current screen state of going out according to prediction result, if
Terminal is sleep pattern under current screen state of going out, then power consumption control is carried out to terminal according to default power consumption strategies, so as to reach
To the purpose of terminal power saving during sleep, reduce the power consumption of terminal.
In one embodiment, feature extraction is carried out to operation data, feature vector is obtained, by feature vector input data mould
Type, obtains prediction result, and performs corresponding optimised power consumption measure according to current predictive result, so as to reach terminal in sleep period
Between power saving purpose, and obstacle will not be caused to the use of user.
In one embodiment, terminal uses operation data processing of the data model to terminal under screen state of currently going out
Afterwards, prediction result is obtained, which is fed back to server by terminal, and server can be according to the prediction result to data mould
Type optimizes, and a closed loop is formed, so that data model is more accurate.
In one embodiment, default power consumption strategies can include a variety of optimised power consumption strategies, terminal in a sleep mode,
It can be controlled to running App in terminal, to achieve the purpose that to save power consumption, flexibility is high.
In one embodiment, multiple operation data of multiple terminals under screen state of going out are obtained;To it is multiple operation data into
Row model training generates data model;Data model is sent to each terminal so that each terminal under screen state of going out according to data
Model determines whether each terminal is sleep pattern, and corresponding optimised power consumption strategy is performed according to sleep pattern, from reduction terminal
Power consumption.
In one embodiment, feature extraction is carried out to multiple operation data, feature vector is obtained, using machine learning algorithm
Model training is carried out to feature vector, generates data model so that the terminal loads data model, and by under terminal current state
Operation data be input to the parametric form of feature vector in data model and obtain predicted value, and held according to current predictive result
The corresponding optimised power consumption measure of row, so as to achieve the purpose that terminal power saving during sleep, and will not cause the use of user
Obstacle.
In one embodiment, successive ignition is carried out to feature vector according to default iterative algorithm, generates model data, mould
The accuracy rate of type data is more than predetermined threshold value, so that data model reaches certain evaluation index, can improve definite terminal and sleep
The accuracy of sleep mode, preferably carries out energy consumption control.
In one embodiment, format check is carried out to each operation data, if the format error of operation data, abandons fortune
Row data, ensure that the accuracy and reliability of the data model generated according to operation data.
In one embodiment, completeness check is carried out to each operation data, if operation data are mended there are absent field
Absent field in row data for the national games, ensure that the accuracy and reliability of the data model generated according to operation data.
In one embodiment, terminal uses operation data processing of the data model to terminal under screen state of currently going out
Afterwards, prediction result is obtained, which is fed back to server by terminal, and server can be according to the prediction result to data mould
Type optimizes, and a closed loop is formed, so that data model is more accurate.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
The disclosure can be limited.
Brief description of the drawings
Attached drawing herein is merged in specification and forms the part of this specification, shows the implementation for meeting the present invention
Example, and for explaining the principle of the present invention together with specification.
Fig. 1 is a kind of flow chart of power consumption control method according to an exemplary embodiment;
Fig. 2 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment;
Fig. 3 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment;
Fig. 4 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment;
Fig. 5 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment;
Fig. 6 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment;
Fig. 7 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment;
Fig. 8 is a kind of block diagram of power consumption control apparatus according to an exemplary embodiment;
Fig. 9 is a kind of block diagram of the power consumption control apparatus shown according to another exemplary embodiment;
Figure 10 is a kind of block diagram of the power consumption control apparatus shown according to another exemplary embodiment;
Figure 11 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment;
Figure 12 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment;
Figure 13 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment;
Figure 14 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment;
Figure 15 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment;
Figure 16 is a kind of block diagram of equipment according to an exemplary embodiment;
Figure 17 is a kind of block diagram of device for power consumption control according to an exemplary embodiment;
Figure 18 is a kind of block diagram of the device for power consumption control shown according to another exemplary embodiment.
Embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During attached drawing, unless otherwise indicated, the same numbers in different attached drawings represent the same or similar key element.Following exemplary embodiment
Described in embodiment do not represent and the consistent all embodiments of the present invention.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects being described in detail in claims, of the invention.
Fig. 1 is a kind of flow chart of power consumption control method according to an exemplary embodiment.The execution master of this method
Body is terminal, and terminal can be the equipment such as mobile phone, computer, ipad, game machine, intelligent TV set, as shown in Figure 1, this method bag
Include following steps:
In step s 11, operation data of the terminal under screen state of currently going out are obtained.
In the embodiments of the present disclosure, it is data of the terminal under screen state of currently going out to run data, for example, when terminal is gone out screen
Afterwards, current operation data can be obtained in real time.Operation data can include what sensing data, foreground and backstage used
App bags name, Bluetooth status information, Wi-Fi network connection state information etc..
In step s 12, operation data are handled using data model, obtains prediction result, data model is clothes
Business device carries out multiple operation data of multiple terminals under screen state of going out on the model of model training generation, and prediction result is used to sentence
Whether disconnected terminal is sleep pattern.
In the embodiments of the present disclosure, terminal loads data model, and data input data model will be run, obtain output
Prediction result.
Wherein, data model is to be generated by server end and then be loaded into terminal, and server can select engineering
Practise multiple operation data that algorithm reports each terminal to carry out model training and obtain trained data model, for example, service
Device is using decision tree, logistic regression, support vector machines (Support Vector Machine, SVM) scheduling algorithm to multiple operations
Data are handled, and generate data model.The data model includes the logic and rule of complexity, exports as prediction result, in advance
Survey result to be used to judge whether terminal is sleep pattern, e.g., data model can be predicted by the real-time parameter of input terminal works as
Before go out screen whether be maximum duration the screen that goes out, if so, then terminal is sleep pattern.If for example, by mobile phone under screen state of going out
Real-time parameter input the data model, according to the output result of data model, it can be determined that the duration of the current screen that goes out is
It is no to have exceeded maximum time threshold value, if exceeding maximum time threshold value, it is determined that the terminal is sleep mould under current screen state of going out
Formula.
In step s 13, determine whether terminal is sleep pattern under current screen state of going out according to prediction result.
In the embodiments of the present disclosure, terminal can determine whether terminal is sleep pattern according to prediction result, if so, then holding
The corresponding optimised power consumption measure of row.For example, including "Yes" in the prediction result, then terminal is sleep mould under current screen state of going out
Formula, if including "No" in prediction result, terminal is non-sleep pattern under current screen state of going out.
In step S14, if terminal is sleep pattern under current screen state of going out, according to default power consumption strategies to end
End carries out power consumption control.
In the embodiments of the present disclosure, can be according to default work(if terminal is sleep pattern under current screen state of going out
Consumption strategy optimizes the power consumption of terminal, to save energy consumption, for example, the App being currently running in whole or in part is closed, or
Person, closes terminal or runs partial function of App etc..
The power consumption control method that the embodiment of the present disclosure provides, obtains operation data of the terminal under screen state of currently going out;Adopt
Operation data are handled with data model, obtain prediction result, determine terminal in current screen state of going out according to prediction result
Under whether be sleep pattern, if terminal is sleep pattern under current screen state of going out, according to default power consumption strategies to terminal
Power consumption control is carried out, so as to achieve the purpose that terminal power saving during sleep, reduces the power consumption of terminal.
Fig. 2 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment.In implementation shown in Fig. 2
On the basis of example, as shown in Fig. 2, the reality of step S12 " being handled using data model operation data, obtain prediction result "
Existing mode may comprise steps of:
In the step s 21, feature extraction is carried out to operation data, obtains feature vector.
In the embodiments of the present disclosure, since data model is the model that machine learning obtains, therefore, it is necessary to running data
Feature extraction is carried out, data will be run and be transformed to the feature vector form that machine learning algorithm can use.
In step S22, by feature vector input data model, prediction result is obtained.
In the present embodiment, using the feature vector got in last step as in parameter input data model, obtain
The prediction result of output.The prediction result can represent sleep pattern and non-sleep pattern with the form of "Yes" and "No",
Sleep pattern and non-sleep pattern, or other modes, this public affairs can be represented with the form of digital " 1 " and " 0 "
It is not any limitation as in opening.
Operation data are carried out feature extraction, obtain feature vector by the power consumption control method that the embodiment of the present disclosure provides, will
Feature vector input data model, obtains prediction result, and performs corresponding optimised power consumption measure according to current predictive result, from
And achieve the purpose that terminal power saving during sleep, and obstacle will not be caused to the use of user.
Alternatively, on the basis of Fig. 1 or embodiment illustrated in fig. 2, after step S14, this method can also include:Will be pre-
Survey result and be sent to server, so that server optimizes data model according to prediction result.
In the embodiments of the present disclosure, terminal using the data model to terminal at operation data under screen state of currently going out
After reason, prediction result is obtained, which is fed back to server by terminal, and server can be according to the prediction result to data
Model optimizes, and a closed loop is formed, so that data model is more accurate.
Alternatively, default power consumption strategies include at least one in following strategy:
Close or pause at all application program App of the running background of terminal;
The App in the running background of terminal is controlled to close partial function;
According to the priority of App, the part App of the running background of terminal is closed or paused at.
In the embodiments of the present disclosure, if terminal is sleep pattern under current screen state of going out, according to default power consumption plan
Slightly power consumption of the terminal under screen state of currently going out is optimized.Wherein, default power consumption strategies can be controlled at terminal
The App of running background closes partial function, for example, preventing the message push for the App that part is currently running, prompting message, automatically
Some functions such as loading, automatic positioning, alternatively, default power consumption strategies can be the priority according to App, close or pause at
The part App of the running background of terminal, for example, according to the priority height of each App, closes the relatively low App of some priority,
Alternatively, default power consumption strategies, which can be all App being currently running of control, enters resting state, for example, control is currently running
All App also enter resting state, work again when screen is lighted etc.;Alternatively, default power consumption strategies can be closed
Or all application program App of the running background of terminal are paused at, for example, the App just in running background is directly suspended fortune
OK, when terminal screen is lit, these App bring into operation.
The power consumption control method that the embodiment of the present disclosure provides, default power consumption strategies can include a variety of optimised power consumption plans
Slightly, terminal in a sleep mode, can be controlled to running App in terminal, to achieve the purpose that to save power consumption, flexibility
It is high.
Fig. 3 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment.The execution of this method
Main body is server or Data Analysis Platform, as shown in figure 3, this method comprises the following steps:
In step S31, multiple operation data of multiple terminals under screen state of going out are obtained.
In the embodiments of the present disclosure, each terminal is collected from the operation data under screen state of going out, and these are run
Data are uploaded to Data Analysis Platform or server according to certain form according to the default time cycle.
Wherein, run data can include sensing data, foreground and backstage use App bags name, Bluetooth status information,
Wireless Fidelity (WIreless-Fidelity, Wi-Fi) network connection state information etc..Terminal can be mobile phone, computer, ipad,
The equipment such as game machine, intelligent TV set.
In step s 32, model training generation data model is carried out to multiple operation data.
In the embodiments of the present disclosure, multiple operation data that machine learning algorithm reports each terminal can be selected to carry out mould
Type training simultaneously obtains trained data model, for example, using decision tree, logistic regression, support vector machines (Support
Vector Machine, SVM) scheduling algorithm to it is multiple operation data handle, generate data model.The data model includes
Complicated logic and rule, the output of data model is prediction result, which is used to judge whether terminal is sleep mould
Formula, e.g., data model can be predicted by the real-time parameter of input terminal it is current go out screen whether be maximum duration the screen that goes out, if
It is that then terminal is sleep pattern.If for example, the real-time parameter under screen state of going out of mobile phone is inputted the data model, according to
The output result of data model, it can be determined that whether the duration of the current screen that goes out has exceeded maximum time threshold value, if more than most
Big time threshold, it is determined that the terminal is sleep pattern under current screen state of going out.
In step S33, data model is sent to each terminal so that each terminal under screen state of going out according to data model
Determine whether each terminal is sleep pattern, and power consumption control is carried out according to sleep pattern.
In the embodiments of the present disclosure, by data model loading terminal so that the data model can be run in the terminal.Eventually
End is processed into feature vector form under screen state of going out, by the operation data currently gone out under screen state, and loading data model simultaneously will
Feature vector is input in model in the form of parameter, and model returns to current prediction result, and terminal can be according to prediction result
Determine whether terminal is sleep pattern, if so, then performing corresponding optimised power consumption measure.For example, included in the prediction result
"Yes", then terminal is sleep pattern under current screen state of going out, if including "No" in prediction result, terminal is in the current screen shape that goes out
It is non-sleep pattern under state, if sleep pattern, some functions for the App that closing that terminal can be suitably is currently running, so that
Achieve the purpose that to reduce power consumption.
The power consumption control method that the embodiment of the present disclosure provides, obtains multiple operation numbers of multiple terminals under screen state of going out
According to;Model training generation data model is carried out to multiple operation data;Data model is sent to each terminal, so that each terminal exists
Determine whether each terminal is sleep pattern according to data model under screen state of going out, and corresponding power consumption is performed according to sleep pattern
Optimisation strategy, from the power consumption for reducing terminal.
Alternatively, on the basis of embodiment illustrated in fig. 3, default power consumption strategies include at least one in following strategy
It is a:
Close or pause at all application program App of the running background of terminal;
The App in the running background of terminal is controlled to close partial function;
According to the priority of App, the part App of the running background of terminal is closed or paused at.
In the embodiments of the present disclosure, if terminal is sleep pattern under current screen state of going out, according to default power consumption plan
Slightly power consumption of the terminal under screen state of currently going out is optimized.Wherein, default power consumption strategies can be controlled at terminal
The App of running background closes partial function, for example, preventing the message push for the App that part is currently running, prompting message, automatically
Some functions such as loading, automatic positioning, alternatively, default power consumption strategies can be the priority according to App, close or pause at
The part App of the running background of terminal, for example, according to the priority height of each App, closes the relatively low App of some priority,
Alternatively, default power consumption strategies, which can be all App being currently running of control, enters resting state, for example, control is currently running
All App also enter resting state, work again when screen is lighted etc.;Alternatively, default power consumption strategies can be closed
Or all application program App of the running background of terminal are paused at, for example, the App just in running background is directly suspended fortune
OK, when terminal screen is lit, these App bring into operation.
The power consumption control method that the embodiment of the present disclosure provides, default power consumption strategies can include a variety of optimised power consumption plans
Slightly, terminal in a sleep mode, can be controlled to running App in terminal, to achieve the purpose that to save power consumption, flexibility
It is high.
Fig. 4 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment.In implementation shown in Fig. 3
On the basis of example, as shown in figure 4, the realization side of step S32 " carrying out model training generation data model to multiple operation data "
Formula may comprise steps of:
In step S41, feature extraction is carried out to multiple operation data, obtains feature vector.
In the embodiments of the present disclosure, calculated to use machine learning algorithm, it is necessary to which operation data are processed into machine learning
The feature vector form that method can use obtains corresponding feature vector, it is necessary to each operation data progress feature extraction.
In step S42, model training is carried out to feature vector using machine learning algorithm, generates data model.
In the embodiments of the present disclosure, the suitable machine learning such as trade-off decision tree, logistic regression, SVM according to the actual requirements
Algorithm, carries out model training using algorithm by the feature vector handled well in step S41, obtains trained data model.
Alternatively, step S42 " model training being carried out to feature vector using machine learning algorithm, generate data model " bag
Include:Successive ignition is carried out to feature vector according to default iterative algorithm, generates model data, the accuracy rate of model data is more than
Predetermined threshold value.
In the present embodiment, predetermined threshold value can be set according to the actual requirements, for example, predetermined threshold value can be 70%,
80%th, the numerical value such as 85%, 90%.Default iterative algorithm can be the machine learning algorithms such as decision tree, logistic regression, SVM, root
Successive ignition is carried out to feature vector according to default iterative algorithm, so that data model reaches certain evaluation index, for example, most
Throughout one's life into data model accuracy rate be more than 80%.
In the present embodiment, successive ignition is carried out to feature vector according to default iterative algorithm, generates model data, mould
The accuracy rate of type data is more than predetermined threshold value, so that data model reaches certain evaluation index, can improve definite terminal and sleep
The accuracy of sleep mode, preferably carries out energy consumption control.
The embodiment of the present disclosure provide power consumption control method, to it is multiple operation data carry out feature extractions, obtain feature to
Amount, carries out model training to feature vector using machine learning algorithm, generates data model so that the terminal loads data mould
Type, and the operation data under terminal current state are input in data model with the parametric form of feature vector and are predicted
Value, and corresponding optimised power consumption measure is performed according to current predictive result, so that achieve the purpose that terminal power saving during sleep,
And obstacle will not be caused to the use of user.
Fig. 5 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment.In Fig. 3 or Fig. 4 institutes
On the basis of showing embodiment, as shown in figure 5, in step S32 " carrying out model training generation data model to multiple operation data "
Before, this method further includes:
In step s 51, each operation data are carried out with format check, format check is used for the form for examining operation data
It is whether correct.
In the embodiments of the present disclosure, it is necessary to which the every operation data reported to terminal carry out format check, for example, can be right
The fields such as the start bits of data, data bit, parity check bit, stop position are run to be verified.Its method of calibration can use existing
The method of calibration of some data formats, details are not described herein again.
In step S52, if the format error of operation data, operation data are abandoned.
In the embodiments of the present disclosure, if mistake occurs in the form of operation data, the operation data are abandoned.If for example, fortune
There is mistake in any one field such as start bit, data bit, parity check bit, stop position in row data, then abandons the operation
Data.
Each operation data are carried out format check, if operation data by the power consumption control method that the embodiment of the present disclosure provides
Format error, then abandon operation data, ensure that according to operation data generate data model accuracy and reliability.
Fig. 6 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment.In Fig. 3 or Fig. 4 institutes
On the basis of showing embodiment, as shown in fig. 6, in step S12 " carrying out model training generation data model to multiple operation data "
Before, this method further includes:
In step S61, each operation data are carried out with completeness check, completeness check, which is used for inspection operation data, is
It is no that there are absent field.
In the embodiments of the present disclosure, it is necessary to which the every operation data reported to terminal carry out completeness check, it is somebody's turn to do with checking
Whether operation data have shortage of data.Even-odd check method, cyclic redundancy check code (Cyclic Redundancy can be used
Check, CRC) check addition, Message Digest Algorithm 5 (Message Digest Algorithm 5, MD5) check addition, Kazakhstan
The methods of uncommon algorithm, verifies the integrality for running data.
In step S62, if operation data there are absent field, the absent field in completion operation data.
In the present embodiment, if there are absent field, it is necessary to the field of missing be supplemented complete in operation data.
Each operation data are carried out completeness check, if operation number by the power consumption control method that the embodiment of the present disclosure provides
According to there are absent field, then the absent field in completion operation data, ensure that according to the data model for running data generation
Accuracy and reliability.
Fig. 7 is a kind of flow chart of the power consumption control method shown according to another exemplary embodiment.It is any in Fig. 3-Fig. 6
The basis of embodiment, as shown in fig. 7, this method is further comprising the steps of:
In step S71, the prediction result that multiple terminals are sent is received, prediction result uses data model pair for each terminal
The result that terminal obtains after the operation data processing under screen state of currently going out.
In step S72, data model is optimized according to prediction result.
In the embodiments of the present disclosure, terminal using the data model to terminal at operation data under screen state of currently going out
After reason, prediction result is obtained, which is fed back to server by terminal, and server can be according to the prediction result to data
Model optimizes, and a closed loop is formed, so that data model is more accurate.
Fig. 8 is a kind of block diagram of power consumption control apparatus according to an exemplary embodiment.As shown in figure 8, the device
Including:
Acquisition module 11 is configured as obtaining operation data of the terminal under screen state of currently going out.
Processing module 12 is configured as handling operation data using data model, obtains prediction result, data mould
Type carries out multiple operation data of multiple terminals under screen state of going out for server the model of model training generation, prediction result
For judging whether terminal is sleep pattern.
Determining module 13 is configured as determining whether terminal is sleep pattern under current screen state of going out according to prediction result.
It is sleep pattern that if control module 14, which is configured as terminal under current screen state of going out, according to default power consumption plan
Power consumption control slightly is carried out to terminal.
Fig. 9 is a kind of block diagram of the power consumption control apparatus shown according to another exemplary embodiment.In embodiment illustrated in fig. 8
On the basis of, as shown in figure 9, processing module 12 includes:
Extracting sub-module 121 is configured as carrying out feature extraction to operation data, obtains feature vector.
Acquisition submodule 122 is configured as, by feature vector input data model, obtaining prediction result.
Figure 10 is a kind of block diagram of the power consumption control apparatus shown according to another exemplary embodiment.Shown in Fig. 8 or Fig. 9
On the basis of embodiment, as shown in Figure 10, which further includes:
Sending module 15 is configured as prediction result being sent to server, so that server optimizes number according to prediction result
According to model.
Alternatively, default power consumption strategies include at least one in following strategy:
Close or pause at all application program App of the running background of terminal;
The App in the running background of terminal is controlled to close partial function;
According to the priority of App, the part App of the running background of terminal is closed or paused at.
On the device in the various embodiments described above, wherein modules perform the concrete mode of operation in the related party
It is described in detail in the embodiment of method, explanation will be not set forth in detail herein.
Figure 11 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment.As shown in figure 11, should
Device includes:
Acquisition module 21 is configured as obtaining multiple operation data of multiple terminals under screen state of going out.
Generation module 22 is configured as carrying out model training generation data model to multiple operation data.
Sending module 23 is configured as data model being sent to each terminal so that each terminal under screen state of going out according to number
Determine whether each terminal is sleep pattern according to model, and power consumption control is carried out according to sleep pattern.
Figure 12 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment.In implementation shown in Figure 11
On the basis of example, as shown in figure 12, generation module 22 includes:
Extracting sub-module 221 is configured as carrying out feature extraction to multiple operation data, obtains feature vector.
Generation submodule 222 is configured as carrying out model training to feature vector using machine learning algorithm, generates data
Model.
Alternatively, as shown in figure 12, generation submodule 222 includes:
Iteration submodule 223 is configured as carrying out successive ignition to feature vector according to default iterative algorithm, generates mould
Type data, the accuracy rate of model data are more than predetermined threshold value.
Figure 13 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment.In Figure 11 or Figure 12 institutes
On the basis of showing embodiment, as shown in figure 13, which further includes:
First correction verification module 24 is configured as carrying out format check to each operation data, and format check, which is used to examine, to be run
Whether the form of data is correct.
If discard module 25 is configured as the format error of operation data, operation data are abandoned.
Figure 14 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment.Appoint in Figure 11-Figure 13
On the basis of one illustrated embodiment, as shown in figure 14, which further includes:
Second correction verification module 26 is configured as carrying out completeness check to each operation data, and completeness check is used to examine
Operation data whether there is absent field.
If completion module 27 is configured as operation data there are absent field, the absent field in completion operation data.
Figure 15 is a kind of block diagram of power consumption control apparatus according to another exemplary embodiment.Appoint in Figure 11-Figure 14
On the basis of one illustrated embodiment, as shown in figure 15, device further includes:
Receiving module 28 is configured as receiving the prediction result that multiple terminals are sent, and prediction result uses data for each terminal
Model is to the result that is obtained after the operation data processing under screen state of currently going out;
Optimization module 29 is configured as optimizing data model according to prediction result.
Alternatively, default power consumption strategies include at least one in following strategy:
Close or pause at all application program App of the running background of terminal;
The App in the running background of terminal is controlled to close partial function;
According to the priority of App, the part App of the running background of terminal is closed or paused at.
On the device in the various embodiments described above, wherein modules perform the concrete mode of operation in the related party
It is described in detail in the embodiment of method, explanation will be not set forth in detail herein.
Figure 16 is a kind of block diagram of equipment according to an exemplary embodiment.As shown in figure 16, which includes:
Memory 31, processor 32 and computer program 33, processor 32 run computer program 33 and perform with lower section
Method:
Obtain operation data of the terminal under screen state of currently going out;
Operation data are handled using data model, obtain prediction result, data model is server to multiple ends
Hold multiple operation data under screen state of going out to carry out the model of model training generation, prediction result be used to judging terminal whether be
Sleep pattern;
Determine whether terminal is sleep pattern under current screen state of going out according to prediction result;
If terminal is sleep pattern under current screen state of going out, power consumption control is carried out to terminal according to default power consumption strategies
System.
On the device in above-described embodiment, wherein modules perform the concrete mode of operation in related this method
Embodiment in be described in detail, explanation will be not set forth in detail herein.
The embodiment of the present disclosure also provides another equipment, and the structure of the equipment is identical with the structure described in Figure 16, including:
Memory 31, processor 32 and computer program 33, processor 32 run computer program 33 and perform with lower section
Method:
Obtain multiple operation data of multiple terminals under screen state of going out;
Model training generation data model is carried out to multiple operation data;
Data model is sent to each terminal, so that each terminal determines that each terminal is under screen state of going out according to data model
No is sleep pattern, and carries out power consumption control according to sleep pattern.
On the device in above-described embodiment, wherein modules perform the concrete mode of operation in related this method
Embodiment in be described in detail, explanation will be not set forth in detail herein.
The embodiment of the present disclosure also provides a kind of computer-readable recording medium, is stored thereon with computer program, the program
The step of method shown in above-mentioned Fig. 1 or Fig. 2 is realized when being executed by processor.
The embodiment of the present disclosure also provides a kind of computer-readable recording medium, is stored thereon with computer program, the program
The step of method shown in above-mentioned Fig. 3-Fig. 7 is realized when being executed by processor.
Figure 17 is a kind of block diagram of device for power consumption control according to an exemplary embodiment.For example, device
800 can be mobile phone, computer, digital broadcast terminal, messaging devices, game console, tablet device, and medical treatment is set
It is standby, body-building equipment, personal digital assistant etc..
With reference to Figure 17, device 800 can include following one or more assemblies:Processing component 802, memory 804, electric power
Component 806, multimedia component 808, audio component 810, the interface 812 of input/output (I/O), sensor component 814, and
Communication component 816.
The integrated operation of the usual control device 800 of processing component 802, such as with display, call, data communication, phase
The operation that machine operates and record operation is associated.Processing component 802 can refer to including one or more processors 820 to perform
Order, to complete all or part of step of above-mentioned method.In addition, processing component 802 can include one or more modules, just
Interaction between processing component 802 and other assemblies.For example, processing component 802 can include multi-media module, it is more to facilitate
Interaction between media component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in equipment 800.These data are shown
Example includes the instruction of any application program or method for being operated on device 800, and contact data, telephone book data, disappears
Breath, picture, video etc..Memory 804 can be by any kind of volatibility or non-volatile memory device or their group
Close and realize, as static RAM (SRAM), electrically erasable programmable read-only memory (EEPROM) are erasable to compile
Journey read-only storage (EPROM), programmable read only memory (PROM), read-only storage (ROM), magnetic memory, flash
Device, disk or CD.
Electric power assembly 806 provides electric power for the various assemblies of device 800.Electric power assembly 806 can include power management system
System, one or more power supplys, and other components associated with generating, managing and distributing electric power for device 800.
Multimedia component 808 is included in the screen of one output interface of offer between described device 800 and user.One
In a little embodiments, screen can include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch-screen, to receive input signal from the user.Touch panel includes one or more touch sensings
Device is to sense the gesture on touch, slip and touch panel.The touch sensor can not only sense touch or sliding action
Border, but also detect and the duration and pressure associated with the touch or slide operation.In certain embodiments, more matchmakers
Body component 808 includes a front camera and/or rear camera.When equipment 800 is in operator scheme, such as screening-mode or
During video mode, front camera and/or rear camera can receive exterior multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 810 is configured as output and/or input audio signal.For example, audio component 810 includes a Mike
Wind (MIC), when device 800 is in operator scheme, during such as call model, logging mode and speech recognition mode, microphone by with
It is set to reception external audio signal.The received audio signal can be further stored in memory 804 or via communication set
Part 816 is sent.In certain embodiments, audio component 810 further includes a loudspeaker, for exports audio signal.
I/O interfaces 812 provide interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include but be not limited to:Home button, volume button, start button and lock
Determine button.
Sensor component 814 includes one or more sensors, and the state for providing various aspects for device 800 is commented
Estimate.For example, sensor component 814 can detect opening/closed mode of equipment 800, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 800, and sensor component 814 can be with 800 1 components of detection device 800 or device
Position change, the existence or non-existence that user contacts with device 800,800 orientation of device or acceleration/deceleration and device 800
Temperature change.Sensor component 814 can include proximity sensor, be configured to detect without any physical contact
Presence of nearby objects.Sensor component 814 can also include optical sensor, such as CMOS or ccd image sensor, for into
As being used in application.In certain embodiments, which can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between device 800 and other equipment.Device
800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G, or combinations thereof.In an exemplary implementation
In example, communication component 816 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 816 further includes near-field communication (NFC) module, to promote junction service.Example
Such as, in NFC module radio frequency identification (RFID) technology can be based on, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 800 can be believed by one or more application application-specific integrated circuit (ASIC), numeral
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for performing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instructing, example are additionally provided
Such as include the memory 804 of instruction, above-metioned instruction can be performed to complete the above method by the processor 820 of device 800.For example,
The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk
With optical data storage devices etc..
Figure 18 is a kind of block diagram of the device for power consumption control shown according to another exemplary embodiment.For example, dress
Put 1900 and may be provided as a server.With reference to Figure 18, device 1900 includes processing component 1922, it further comprises one
Or multiple processors, and as the memory resource representated by memory 1932, can holding by processing component 1922 for storing
Capable instruction, such as application program.The application program stored in memory 1932 can include one or more each
A module for corresponding to one group of instruction.In addition, processing component 1922 is configured as execute instruction, to perform above-mentioned Fig. 3-Fig. 7 institutes
The method shown.
Device 1900 can also include a power supply module 1926 and be configured as the power management of executive device 1900, one
Wired or wireless network interface 1950 is configured as device 1900 being connected to network, and input and output (I/O) interface
1958.Device 1900 can be operated based on the operating system for being stored in memory 1932, such as Windows ServerTM, Mac
OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of mobile terminal
When device performs so that mobile terminal is able to carry out a kind of power consumption control method, the described method includes:
Obtain operation data of the terminal under screen state of currently going out;
The operation data are handled using data model, obtain prediction result, the data model is server
Multiple operation data of multiple terminals under screen state of going out are carried out with the model of model training generation, the prediction result is used to sentence
Whether the terminal of breaking is sleep pattern;
Determine whether the terminal is sleep pattern under the current screen state of going out according to the prediction result;
If the terminal is sleep pattern under the current screen state of going out, according to default power consumption strategies to the end
End carries out power consumption control.
Wherein, it is described that the operation data are handled using data model, prediction result is obtained, including:
Feature extraction is carried out to the operation data, obtains feature vector;
Described eigenvector is inputted into the data model, obtains the prediction result.
Wherein, the method further includes:
The prediction result is sent to server, so that the server optimizes the data according to the prediction result
Model.
Wherein, the default power consumption strategies include at least one in following strategy:
Close or pause at all application program App of the running background of the terminal;
The App in the running background of the terminal is controlled to close partial function;
According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of mobile terminal
When device performs so that mobile terminal is able to carry out a kind of power consumption control method, the described method includes:
Obtain multiple operation data of multiple terminals under screen state of going out;
Model training generation data model is carried out to multiple operation data;
The data model is sent to each terminal so that each terminal under screen state of going out according to the data
Model determines whether each terminal is sleep pattern, and carries out power consumption control according to the sleep pattern.
Wherein, it is described that model training generation data model is carried out to multiple operation data, including:
Feature extraction is carried out to multiple operation data, obtains feature vector;
Model training is carried out to described eigenvector using machine learning algorithm, generates the data model.
Wherein, it is described that model training is carried out to described eigenvector using machine learning algorithm, the data model is generated,
Including:
Successive ignition is carried out to described eigenvector according to default iterative algorithm, generates the model data, the mould
The accuracy rate of type data is more than predetermined threshold value.
Wherein, it is described to it is multiple it is described operation data carry out model trainings generation data models before, the method is also wrapped
Include:
Each operation data are carried out with format check, the format check is used for the form for examining the operation data
It is whether correct;
If the format error of the operation data, abandons the operation data.
Wherein, it is described to it is multiple it is described operation data carry out model trainings generation data models before, the method is also wrapped
Include:
Each operation data are carried out with completeness check, the completeness check is for examining the operation data
It is no that there are absent field;
If the operation data are there are absent field, the absent field in operation data described in completion.
Wherein, the method further includes:
The prediction result that multiple terminals are sent is received, the prediction result uses the data mould for each terminal
Type is to the result that is obtained after the operation data processing under screen state of currently going out;
The data model is optimized according to the prediction result.
Wherein, the default power consumption strategies include at least one in following strategy:
Close or pause at all application program App of the running background of the terminal;
The App in the running background of the terminal is controlled to close partial function;
According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
Those skilled in the art will readily occur to the present invention its after considering specification and putting into practice invention disclosed herein
Its embodiment.This application is intended to cover the present invention any variations, uses, or adaptations, these modifications, purposes or
Person's adaptive change follows the general principle of the present invention and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.Description and embodiments are considered only as exemplary, and true scope and spirit of the invention are by following
Claims are pointed out.
It should be appreciated that the invention is not limited in the precision architecture for being described above and being shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is only limited by appended claims
System.
Claims (26)
- A kind of 1. power consumption control method, it is characterised in that including:Obtain operation data of the terminal under screen state of currently going out;The operation data are handled using data model, obtain prediction result, the data model is server to more Multiple operation data of a terminal under screen state of going out carry out the model of model training generation, and the prediction result is used to judge institute State whether terminal is sleep pattern;Determine whether the terminal is sleep pattern under the current screen state of going out according to the prediction result;If the terminal is sleep pattern under the current screen state of going out, according to default power consumption strategies to the terminal into Row power consumption control.
- 2. according to the method described in claim 1, it is characterized in that, described run at data using data model to described Reason, obtains prediction result, including:Feature extraction is carried out to the operation data, obtains feature vector;Described eigenvector is inputted into the data model, obtains the prediction result.
- 3. method according to claim 1 or 2, it is characterised in that the method further includes:The prediction result is sent to server, so that the server optimizes the data mould according to the prediction result Type.
- 4. method according to claim 1 or 2, it is characterised in that the default power consumption strategies are included in following strategy It is at least one:Close or pause at all application program App of the running background of the terminal;The App in the running background of the terminal is controlled to close partial function;According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
- A kind of 5. power consumption control method, it is characterised in that including:Obtain multiple operation data of multiple terminals under screen state of going out;Model training generation data model is carried out to multiple operation data;The data model is sent to each terminal so that each terminal under screen state of going out according to the data model Determine whether each terminal is sleep pattern, and power consumption control is carried out according to the sleep pattern.
- 6. according to the method described in claim 5, it is characterized in that, described carry out model training life to multiple operation data Into data model, including:Feature extraction is carried out to multiple operation data, obtains feature vector;Model training is carried out to described eigenvector using machine learning algorithm, generates the data model.
- 7. according to the method described in claim 6, it is characterized in that, it is described using machine learning algorithm to described eigenvector into Row model training, generates the data model, including:Successive ignition is carried out to described eigenvector according to default iterative algorithm, generates the model data, the pattern number According to accuracy rate be more than predetermined threshold value.
- 8. according to claim 5-7 any one of them methods, it is characterised in that described to carry out mould to multiple operation data Before type training generation data model, the method further includes:Format check is carried out to each operation data, the format check is used to whether examine the form for running data Correctly;If the format error of the operation data, abandons the operation data.
- 9. according to claim 5-7 any one of them methods, it is characterised in that described to carry out mould to multiple operation data Before type training generation data model, the method further includes:Each operation data are carried out with completeness check, the completeness check is used to examine whether the operation data deposit In absent field;If the operation data are there are absent field, the absent field in operation data described in completion.
- 10. according to claim 5-7 any one of them methods, it is characterised in that the method further includes:The prediction result that multiple terminals are sent is received, the prediction result uses the data model pair for each terminal The result obtained after the current operation data processing gone out under screen state;The data model is optimized according to the prediction result.
- 11. according to claim 5-7 any one of them methods, it is characterised in that the default power consumption strategies include following It is at least one in strategy:Close or pause at all application program App of the running background of the terminal;The App in the running background of the terminal is controlled to close partial function;According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
- A kind of 12. power consumption control apparatus, it is characterised in that including:Acquisition module, is configured as obtaining operation data of the terminal under screen state of currently going out;Processing module, is configured as handling the operation data using data model, obtains prediction result, the data Model carries out multiple operation data of multiple terminals under screen state of going out for server on the model of model training generation, described pre- Result is surveyed to be used to judge whether the terminal is sleep pattern;Determining module, is configured as determining whether the terminal is to sleep under the current screen state of going out according to the prediction result Sleep mode;Control module, if it is sleep pattern to be configured as the terminal under the current screen state of going out, according to default work( Consumption strategy carries out power consumption control to the terminal.
- 13. device according to claim 12, it is characterised in that the processing module, including:Extracting sub-module, is configured as carrying out feature extraction to the operation data, obtains feature vector;Acquisition submodule, is configured as described eigenvector inputting the data model, obtains the prediction result.
- 14. the device according to claim 12 or 13, it is characterised in that described device further includes:Sending module, is configured as the prediction result being sent to server, so that the server is tied according to the prediction Fruit optimizes the data model.
- 15. the device according to claim 12 or 13, it is characterised in that the default power consumption strategies include following strategy In it is at least one:Close or pause at all application program App of the running background of the terminal;The App in the running background of the terminal is controlled to close partial function;According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
- A kind of 16. power consumption control apparatus, it is characterised in that including:Acquisition module, is configured as obtaining multiple operation data of multiple terminals under screen state of going out;Generation module, is configured as carrying out model training generation data model to multiple operation data;Sending module, is configured as the data model being sent to each terminal, so that each terminal is in screen state of going out It is lower to determine whether each terminal is sleep pattern according to the data model, and power consumption control is carried out according to the sleep pattern System.
- 17. device according to claim 16, it is characterised in that the generation module, including:Extracting sub-module, is configured as carrying out feature extraction to multiple operation data, obtains feature vector;Submodule is generated, is configured as carrying out model training to described eigenvector using machine learning algorithm, generates the number According to model.
- 18. device according to claim 17, it is characterised in that the generation submodule, including:Iteration submodule, is configured as carrying out successive ignition to described eigenvector according to default iterative algorithm, described in generation Model data, the accuracy rate of the model data are more than predetermined threshold value.
- 19. according to claim 16-18 any one of them devices, it is characterised in that described device further includes:First correction verification module, is configured as carrying out format check to each operation data, the format check is used to examine Whether the form of the operation data is correct;Discard module, if being configured as the format error of the operation data, abandons the operation data.
- 20. according to claim 16-18 any one of them devices, it is characterised in that described device further includes:Second correction verification module, is configured as carrying out completeness check to each operation data, the completeness check is used for The operation data are examined to whether there is absent field;Completion module, if being configured as the operation data there are absent field, the missing word in operation data described in completion Section.
- 21. according to claim 16-18 any one of them devices, it is characterised in that described device further includes:Receiving module, is configured as receiving the prediction result that multiple terminals are sent, the prediction result is each terminal Using the data model to the result that is obtained after the operation data processing under screen state of currently going out;Optimization module, is configured as optimizing the data model according to the prediction result.
- 22. according to claim 16-18 any one of them devices, it is characterised in that the default power consumption strategies include with It is at least one in lower strategy:Close or pause at all application program App of the running background of the terminal;The App in the running background of the terminal is controlled to close partial function;According to the priority of the App, the part App of the running background of the terminal is closed or paused at.
- A kind of 23. equipment, it is characterised in that including:Memory, processor and computer program, the processor run the computer program and perform following methods:Obtain operation data of the terminal under screen state of currently going out;The operation data are handled using data model, obtain prediction result, the data model is server to more Multiple operation data of a terminal under screen state of going out carry out the model of model training generation, and the prediction result is used to judge institute State whether terminal is sleep pattern;Determine whether the terminal is sleep pattern under the current screen state of going out according to the prediction result;If the terminal is sleep pattern under the current screen state of going out, according to default power consumption strategies to the terminal into Row power consumption control.
- A kind of 24. equipment, it is characterised in that including:Memory, processor and computer program, the processor run the computer program and perform following methods:Obtain multiple operation data of multiple terminals under screen state of going out;Model training generation data model is carried out to multiple operation data;The data model is sent to each terminal so that each terminal under screen state of going out according to the data model Determine whether each terminal is sleep pattern, and power consumption control is carried out according to the sleep pattern.
- 25. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The step of any one of claim 1-4 the method is realized during execution.
- 26. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The step of any one of claim 5-11 the method is realized during execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711159364.4A CN107943266A (en) | 2017-11-20 | 2017-11-20 | power consumption control method, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711159364.4A CN107943266A (en) | 2017-11-20 | 2017-11-20 | power consumption control method, device and equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107943266A true CN107943266A (en) | 2018-04-20 |
Family
ID=61930335
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711159364.4A Pending CN107943266A (en) | 2017-11-20 | 2017-11-20 | power consumption control method, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107943266A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110505679A (en) * | 2019-08-15 | 2019-11-26 | Oppo广东移动通信有限公司 | A kind of power consumption control method of communication terminal, device and storage medium |
CN110742580A (en) * | 2019-09-18 | 2020-02-04 | 华为技术有限公司 | Sleep state identification method and device |
WO2020168448A1 (en) * | 2019-02-18 | 2020-08-27 | 深圳市欢太科技有限公司 | Sleep prediction method and apparatus, and storage medium and electronic device |
CN111722693A (en) * | 2020-05-29 | 2020-09-29 | 北京小米松果电子有限公司 | Power consumption adjusting method and device, storage medium, server and terminal |
CN113055984A (en) * | 2019-12-26 | 2021-06-29 | Oppo广东移动通信有限公司 | Terminal control method and device, mobile terminal and storage medium |
CN113051464A (en) * | 2019-12-27 | 2021-06-29 | Oppo广东移动通信有限公司 | Policy pushing method, policy execution method, device, equipment and medium |
CN113050783A (en) * | 2019-12-26 | 2021-06-29 | Oppo广东移动通信有限公司 | Terminal control method and device, mobile terminal and storage medium |
CN113439253A (en) * | 2019-04-12 | 2021-09-24 | 深圳市欢太科技有限公司 | Application cleaning method and device, storage medium and electronic equipment |
CN117077812A (en) * | 2023-09-13 | 2023-11-17 | 荣耀终端有限公司 | Network training method, sleep state evaluation method and related equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100100716A1 (en) * | 2008-10-22 | 2010-04-22 | Microsoft Corporation | Conserving Power Using Predictive Modelling and Signaling |
CN103327162A (en) * | 2012-03-21 | 2013-09-25 | 华为技术有限公司 | Contextual model setting method and terminal device |
CN104125335A (en) * | 2014-06-24 | 2014-10-29 | 小米科技有限责任公司 | Method, device and system for managing authority |
CN104423532A (en) * | 2013-09-06 | 2015-03-18 | ***通信集团公司 | Power supply management method, device and system of mobile terminal |
CN105902257A (en) * | 2016-06-27 | 2016-08-31 | 安徽华米信息科技有限公司 | Sleep state analysis method and device and intelligent wearable equipment |
CN106125896A (en) * | 2016-06-29 | 2016-11-16 | 宇龙计算机通信科技(深圳)有限公司 | A kind of application program freezing method and mobile terminal |
CN106211084A (en) * | 2016-09-07 | 2016-12-07 | 中国人民解放军国防科学技术大学 | Environment perception method based on GSM signal |
CN106502371A (en) * | 2016-11-08 | 2017-03-15 | 珠海市魅族科技有限公司 | A kind of electricity-saving control method and device |
CN106648023A (en) * | 2016-10-02 | 2017-05-10 | 上海青橙实业有限公司 | Mobile terminal and power-saving method of mobile terminal based on neural network |
-
2017
- 2017-11-20 CN CN201711159364.4A patent/CN107943266A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100100716A1 (en) * | 2008-10-22 | 2010-04-22 | Microsoft Corporation | Conserving Power Using Predictive Modelling and Signaling |
CN103327162A (en) * | 2012-03-21 | 2013-09-25 | 华为技术有限公司 | Contextual model setting method and terminal device |
CN104423532A (en) * | 2013-09-06 | 2015-03-18 | ***通信集团公司 | Power supply management method, device and system of mobile terminal |
CN104125335A (en) * | 2014-06-24 | 2014-10-29 | 小米科技有限责任公司 | Method, device and system for managing authority |
CN105902257A (en) * | 2016-06-27 | 2016-08-31 | 安徽华米信息科技有限公司 | Sleep state analysis method and device and intelligent wearable equipment |
CN106125896A (en) * | 2016-06-29 | 2016-11-16 | 宇龙计算机通信科技(深圳)有限公司 | A kind of application program freezing method and mobile terminal |
CN106211084A (en) * | 2016-09-07 | 2016-12-07 | 中国人民解放军国防科学技术大学 | Environment perception method based on GSM signal |
CN106648023A (en) * | 2016-10-02 | 2017-05-10 | 上海青橙实业有限公司 | Mobile terminal and power-saving method of mobile terminal based on neural network |
CN106502371A (en) * | 2016-11-08 | 2017-03-15 | 珠海市魅族科技有限公司 | A kind of electricity-saving control method and device |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020168448A1 (en) * | 2019-02-18 | 2020-08-27 | 深圳市欢太科技有限公司 | Sleep prediction method and apparatus, and storage medium and electronic device |
CN113439253A (en) * | 2019-04-12 | 2021-09-24 | 深圳市欢太科技有限公司 | Application cleaning method and device, storage medium and electronic equipment |
CN113439253B (en) * | 2019-04-12 | 2023-08-22 | 深圳市欢太科技有限公司 | Application cleaning method and device, storage medium and electronic equipment |
CN110505679A (en) * | 2019-08-15 | 2019-11-26 | Oppo广东移动通信有限公司 | A kind of power consumption control method of communication terminal, device and storage medium |
CN110505679B (en) * | 2019-08-15 | 2022-08-16 | Oppo广东移动通信有限公司 | Power consumption control method and device of communication terminal and storage medium |
CN110742580A (en) * | 2019-09-18 | 2020-02-04 | 华为技术有限公司 | Sleep state identification method and device |
CN113055984B (en) * | 2019-12-26 | 2022-11-15 | Oppo广东移动通信有限公司 | Terminal control method and device, mobile terminal and storage medium |
CN113050783A (en) * | 2019-12-26 | 2021-06-29 | Oppo广东移动通信有限公司 | Terminal control method and device, mobile terminal and storage medium |
CN113055984A (en) * | 2019-12-26 | 2021-06-29 | Oppo广东移动通信有限公司 | Terminal control method and device, mobile terminal and storage medium |
CN113050783B (en) * | 2019-12-26 | 2023-08-08 | Oppo广东移动通信有限公司 | Terminal control method and device, mobile terminal and storage medium |
CN113051464A (en) * | 2019-12-27 | 2021-06-29 | Oppo广东移动通信有限公司 | Policy pushing method, policy execution method, device, equipment and medium |
CN111722693A (en) * | 2020-05-29 | 2020-09-29 | 北京小米松果电子有限公司 | Power consumption adjusting method and device, storage medium, server and terminal |
CN117077812A (en) * | 2023-09-13 | 2023-11-17 | 荣耀终端有限公司 | Network training method, sleep state evaluation method and related equipment |
CN117077812B (en) * | 2023-09-13 | 2024-03-08 | 荣耀终端有限公司 | Network training method, sleep state evaluation method and related equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107943266A (en) | power consumption control method, device and equipment | |
CN105426200B (en) | Communication module group firmware and plug-in unit generation method and device | |
WO2020088069A1 (en) | Hand gesture keypoints detection method and apparatus, electronic device, and storage medium | |
CN107423106A (en) | The method and apparatus for supporting more frame grammars | |
CN107582028A (en) | Sleep monitor method and device | |
CN107527059A (en) | Character recognition method, device and terminal | |
CN106098060A (en) | The correction processing method of voice and device, the device of correction process for voice | |
CN104639745B (en) | Phonetic prompt method and device | |
CN105093980B (en) | Control the method and device of smart machine start and stop | |
CN107944447A (en) | Image classification method and device | |
CN106792448A (en) | Bluetooth connecting method and device, system | |
CN105279499A (en) | Age recognition method and device | |
CN107527024A (en) | Face face value appraisal procedure and device | |
CN104601204B (en) | trigger condition detection method and device | |
CN107194464A (en) | The training method and device of convolutional neural networks model | |
CN108665889A (en) | The Method of Speech Endpoint Detection, device, equipment and storage medium | |
CN107748867A (en) | The detection method and device of destination object | |
CN107544802A (en) | device identification method and device | |
CN105353938A (en) | Suspended short message display method and apparatus | |
CN106330864B (en) | The processing method of verification information, apparatus and system | |
CN108764283A (en) | A kind of the loss value-acquiring method and device of disaggregated model | |
CN107948278A (en) | A kind of information transferring method, terminal device and system | |
CN107566750A (en) | Control method, device and the storage medium of flash lamp | |
CN106445148A (en) | Method and device for triggering terminal application | |
CN106301946B (en) | device identification method and device |
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 |