WO2019062317A1 - 应用程序管控方法及电子设备 - Google Patents

应用程序管控方法及电子设备 Download PDF

Info

Publication number
WO2019062317A1
WO2019062317A1 PCT/CN2018/097907 CN2018097907W WO2019062317A1 WO 2019062317 A1 WO2019062317 A1 WO 2019062317A1 CN 2018097907 W CN2018097907 W CN 2018097907W WO 2019062317 A1 WO2019062317 A1 WO 2019062317A1
Authority
WO
WIPO (PCT)
Prior art keywords
application
function
sample vector
training model
gaussian kernel
Prior art date
Application number
PCT/CN2018/097907
Other languages
English (en)
French (fr)
Inventor
梁昆
Original Assignee
Oppo广东移动通信有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Publication of WO2019062317A1 publication Critical patent/WO2019062317A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/445Program loading or initiating
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/48Program initiating; Program switching, e.g. by interrupt
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]

Definitions

  • the present application relates to the field of electronic device terminals, and in particular, to an application management method and an electronic device.
  • the embodiment of the present application provides an application management method and an electronic device to intelligently close an application.
  • An application management method is applied to an electronic device, and the application management and control method includes:
  • sample vector set of the application in a preset historical time period, wherein the sample vector in the sample vector set includes historical feature information x i of a plurality of dimensions of the application at a plurality of time points within a preset historical time period ;
  • the sample vector set is calculated by a nonlinear support vector machine algorithm to generate a training model.
  • An embodiment of the present application provides an electronic device, where the electronic device includes a processor and a memory, in which an application is stored, the processor runs the application, and the processor further performs:
  • sample vector set of the application in a preset historical time period, wherein the sample vector in the sample vector set includes historical feature information x i of a plurality of dimensions of the application at a plurality of time points within a preset historical time period ;
  • the sample vector set is calculated by a nonlinear support vector machine algorithm to generate a training model.
  • An embodiment of the present application provides an electronic device, where the electronic device includes a processor and a memory, in which an application is stored, the processor runs the application, and the processor further performs:
  • sample vector set of the application in a preset historical time period, wherein the sample vector in the sample vector set includes historical feature information x i of a plurality of dimensions of the application at a plurality of time points within a preset historical time period ;
  • the sample vector set is calculated by a nonlinear support vector machine algorithm to generate a training model.
  • the processor closes the application and releases the cache space occupied by the application.
  • the application management method and the electronic device provided by the application obtain the historical feature information x i by detecting the application into the background, and generate a training model by using a nonlinear support vector machine algorithm, thereby bringing the current feature information s of the application into the training.
  • the model determines whether the application needs to be closed, and intelligently closes the application.
  • FIG. 1 is a schematic diagram of a system of an application management device according to an embodiment of the present application.
  • FIG. 2 is a schematic diagram of an application scenario of an application management and control device according to an embodiment of the present disclosure.
  • FIG. 3 is a schematic flowchart of an application management and control method according to an embodiment of the present application.
  • FIG. 4 is another schematic flowchart of an application management and control method according to an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of an apparatus according to an embodiment of the present application.
  • FIG. 6 is another schematic structural diagram of an apparatus according to an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
  • FIG. 8 is another schematic structural diagram of an electronic device according to an embodiment of the present application.
  • An application management method is applied to an electronic device, and the application management and control method includes:
  • sample vector set of the application in a preset historical time period, wherein the sample vector in the sample vector set includes historical feature information x i of a plurality of dimensions of the application at a plurality of time points within a preset historical time period ;
  • the sample vector set is calculated by a nonlinear support vector machine algorithm to generate a training model.
  • the nonlinear support vector machine algorithm is used to calculate a sample vector set
  • the generated training model includes:
  • the training model is obtained by defining a Gaussian kernel function.
  • the kernel function is a Gaussian kernel function
  • K(x, x i ) is the Euclidean distance between any point x in space to a certain center x i
  • is the width parameter of the Gaussian kernel function
  • the Gaussian kernel function is defined, and the model function and the classification decision function are defined according to the Gaussian kernel function, and the training model is obtained by defining a Gaussian kernel function, defining a model function and a classification decision according to a Gaussian kernel function.
  • a target optimization function is defined by a model function and a classification decision function, and an optimal solution of the target optimization function is obtained by a sequence minimum optimization algorithm to obtain a training model, wherein the target optimization function is Wherein the target optimization function is to find a minimum value on the parameters ( ⁇ 1 , ⁇ 2, ..., ⁇ i ), one ⁇ i corresponds to one sample (x i , y i ), and the total number of variables is equal to the training sample Capacity m.
  • the optimal solution is
  • the training model is
  • the g(x) is the training model output value.
  • the determining whether the application needs to be closed further includes:
  • the application management method in the determining whether the application needs to be closed, when it is determined that the application needs to be closed, the application is closed, when it is determined that the application needs to be retained, The application is then retained.
  • the method further includes:
  • An embodiment of the present application provides an electronic device, where the electronic device includes a processor and a memory, in which an application is stored, the processor runs the application, and the processor further performs:
  • sample vector set of the application in a preset historical time period, wherein the sample vector in the sample vector set includes historical feature information x i of a plurality of dimensions of the application at a plurality of time points within a preset historical time period ;
  • the sample vector set is calculated by a nonlinear support vector machine algorithm to generate a training model.
  • the processor in the calculating a sample vector set by using a nonlinear support vector machine algorithm to generate a training model, the processor further performs:
  • the training model is obtained by defining a Gaussian kernel function.
  • the kernel function is a Gaussian kernel function
  • K(x, x i ) is the Euclidean distance between any point x in space to a certain center x i
  • is the width parameter of the Gaussian kernel function
  • the processor obtains a training model by defining a Gaussian kernel function, defining a model function and a classification decision function according to a Gaussian kernel function, and the model is obtained.
  • a model function and a classification decision function are defined according to a Gaussian kernel function by defining a Gaussian kernel function
  • the processor defines a model function and a classification according to a Gaussian kernel function by defining a Gaussian kernel function.
  • the decision function defines the target optimization function through the model function and the classification decision function, and obtains the optimal solution of the target optimization function through the sequence minimum optimization algorithm to obtain a training model, wherein the target optimization function is Wherein the target optimization function is to find a minimum value on the parameters ( ⁇ 1 , ⁇ 2, ..., ⁇ i ), one ⁇ i corresponds to one sample (x i , y i ), and the total number of variables is equal to the training sample Capacity m.
  • the optimal solution is
  • the training model is
  • the g(x) is the training model output value.
  • the processor in the determining whether the application needs to be shut down, the processor further executes:
  • the processor when it is determined whether the application needs to be closed, when it is determined that the application needs to be closed, the processor closes the application, and when it is determined that the application needs to be retained, the The processor retains the application.
  • the processor further executes:
  • An embodiment of the present application provides an electronic device, where the electronic device includes a processor and a memory, in which an application is stored, and the processor runs the application, wherein the processor further performs:
  • sample vector set of the application in a preset historical time period, wherein the sample vector in the sample vector set includes historical feature information x i of a plurality of dimensions of the application at a plurality of time points within a preset historical time period ;
  • the sample vector set is calculated by a nonlinear support vector machine algorithm to generate a training model.
  • the processor closes the application and releases the cache space occupied by the application.
  • the processor in the calculating a sample vector set by using a nonlinear support vector machine algorithm to generate a training model, the processor further performs:
  • the training model is obtained by defining a Gaussian kernel function.
  • the application management method provided by the present application is mainly applied to electronic devices such as a wristband, a smart phone, a tablet based on an Apple system or an Android system, or a smart mobile electronic device such as a Windows or Linux based notebook computer.
  • the application may be a chat application, a video application, a music application, a shopping application, a shared bicycle application, or a mobile banking application.
  • FIG. 1 is a schematic diagram of a system for controlling an application program according to an embodiment of the present application.
  • the application management device is mainly configured to: obtain historical feature information x i of the application from a database, and then calculate the historical feature information x i by an algorithm to obtain a training model, and secondly, the current feature information of the application.
  • the training model is input for calculation, and the calculation result is used to judge whether the application can be closed to control the preset application, such as closing, or freezing, thereby releasing the buffer space of the electronic device and saving power.
  • FIG. 2 is a schematic diagram of an application scenario of an application management and control method according to an embodiment of the present application.
  • the application management device acquires the historical feature information x i of the application from the database when detecting that the application enters the background of the electronic device, and then calculates the historical feature information x i through an algorithm to obtain
  • the training model is followed by inputting the current feature information s of the application into the training model for calculation, and judging whether the application can be closed by the calculation result.
  • the application control device detects that the application a enters the background of the electronic device, the historical feature information x i of the application a is obtained from the database, and then the historical feature information x i is calculated by an algorithm to obtain a training model.
  • the current feature information s of the application is input into the training model for calculation, and the calculation result determines that the application a can be closed and the application a is closed;
  • the historical feature information x i of the application b is obtained from the database, and then the historical feature information x i is calculated by an algorithm to obtain a training model.
  • the current feature information s of the application b is input into the training model for calculation, and the calculation is performed.
  • the application b is retained, thereby saving the electronic device cache space occupied by the application b when it is in the background and saving the consumption of the electronic device when the application b is in the background.
  • the embodiment of the present application provides an application management method, and the execution entity of the application management method may be an application management device provided by an embodiment of the present invention, or an electronic device of the application management device, where the application The control device can be implemented in hardware or software.
  • FIG. 3 is a schematic flowchart diagram of an application management and control method according to an embodiment of the present application.
  • the application management and control method provided by the embodiment of the present application is applied to an electronic device, and the specific process may be as follows:
  • Step 101 Acquire a sample vector set of the application in a preset historical time period, where the sample vector in the sample vector set includes historical features of multiple dimensions of the application at a plurality of time points within a preset historical time period.
  • Information x i is a sample vector set of the application in a preset historical time period, where the sample vector in the sample vector set includes historical features of multiple dimensions of the application at a plurality of time points within a preset historical time period.
  • a sample vector includes historical feature information x i of a plurality of dimensions of the application at a certain point in time within a preset historical time period.
  • the preset historical time period is a time period before a time point when the application enters the background is detected.
  • the preset historical time period may be one week before the time point when the application is in the background is detected.
  • an application is detected entering the background at 8:15 am on August 15, 2017, and the historical feature information x i of the week before 8:15 am on August 15, 2017 is obtained, that is, Obtain historical characteristic information x i between 8:15 am on August 8, 2017 and 8:15 am on August 15, 2017.
  • the preset historical time period may also be three days before the time point when the application is in the background is detected.
  • an application is detected entering the background to obtain historical feature information x i for three days before 6:20 pm on August 13, 2017. That is, the historical feature information x i between 6:20 pm on August 10, 2017 and 6:20 pm on August 13, 2017 is obtained.
  • the feature information of the multiple dimensions may refer to Table 1.
  • the feature information of the ten dimensions shown in Table 1 above is only one of the embodiments in the present application, but the application is not limited to the feature information of the ten dimensions shown in Table 1, and may also be One of them, or at least two of them, or all of them, may also include feature information of other dimensions, for example, whether it is currently charging, current power, or whether WiFi is currently connected.
  • Step 102 Calculate a sample vector set by using a nonlinear support vector machine algorithm to generate a training model.
  • FIG. 4 is a schematic flowchart diagram of an application management and control method according to an embodiment of the present application.
  • the step 102 may include:
  • Step 1021 label the sample vectors in the sample vector set to generate a label result y i of each sample vector
  • Step 1022 Obtain a training model by defining a Gaussian kernel function.
  • step 1021 the sample vectors in the sample vector set are labeled to generate a labeled result y i for each sample vector.
  • a training model is obtained by defining a Gaussian kernel function.
  • the kernel function is a Gaussian kernel function
  • K(x, x i ) is the Euclidean distance between any point x in space to a certain center x i
  • is the width parameter of the Gaussian kernel function
  • the training model may be defined by defining a Gaussian kernel function and defining a model function and a classification decision function according to a Gaussian kernel function.
  • the target optimization function is defined by the model function and the classification decision function, and the optimal solution of the target optimization function is obtained by the sequence minimum optimization algorithm to obtain a training model, and the target optimization function is Wherein the target optimization function is to find a minimum value on the parameters ( ⁇ 1 , ⁇ 2, ..., ⁇ i ), one ⁇ i corresponds to one sample (x i , y i ), and the total number of variables is equal to the training sample Capacity m.
  • the optimal solution can be written as The training model is
  • the g(x) is the training model output value.
  • Step 103 Input current feature information s of the application into the training model for calculation.
  • the step 103 may include:
  • Step 1031 Collect current feature information s of the application.
  • Step 1032 Bring the current feature information s into the training model for calculation.
  • the current feature information s of the application is collected, and the current feature information s is brought into the formula calculation.
  • the acquired dimension of the current feature information s of the application is the same as the dimension of the collected historical feature information x i of the application.
  • step 104 it is determined whether the application needs to be closed.
  • the application management and control method provided by the application obtains the historical feature information x i by detecting the application entering the background, and generates a training model by using a nonlinear support vector machine algorithm, thereby bringing the current feature information s of the application into the training model, and further Determine if the application needs to be closed and intelligently close the application.
  • FIG. 5 is a schematic structural diagram of an application program management apparatus according to an embodiment of the present application.
  • the application management device 30 includes an acquisition module 31, a generation module 32, a calculation module 33, and a determination module 34.
  • the application may be a chat application, a video application, a music application, a shopping application, a shared bicycle application, or a mobile banking application.
  • the obtaining module 31 is configured to acquire a sample vector set of the application in a preset historical time period, where the sample vector in the sample vector set includes multiple time points of the application in a preset historical time period. Historical feature information x i of the dimension.
  • FIG. 6 is a schematic structural diagram of an application program management apparatus according to an embodiment of the present application.
  • the application management device 30 further includes a detection module 35 for detecting that the application enters the background.
  • the application management device 30 may further include a first preset module 36 and a storage module 37.
  • the first preset module 36 is configured to preset a historical time period.
  • the storage module 37 is configured to store feature information of an application.
  • the obtaining module 31 acquires the historical feature information x i in the preset historical time period from the storage module 37 according to the preset historical time period set by the first preset module 36.
  • a sample vector includes historical feature information x i of a plurality of dimensions of the application at a certain point in time within a preset historical time period.
  • the preset historical time period is a time period before a time point when the application enters the background is detected.
  • the preset historical time period may be one week before the time point when the application is in the background is detected.
  • an application is detected entering the background at 8:15 am on August 15, 2017, and the historical feature information x i of the week before 8:15 am on August 15, 2017 is obtained, that is, Obtain historical characteristic information x i between 8:15 am on August 8, 2017 and 8:15 am on August 15, 2017.
  • the preset historical time period may also be three days before the time point when the application is in the background is detected.
  • an application is detected entering the background to obtain historical feature information x i for three days before 6:20 pm on August 13, 2017. That is, the historical feature information x i between 6:20 pm on August 10, 2017 and 6:20 pm on August 13, 2017 is obtained.
  • the feature information of the multiple dimensions may refer to Table 2.
  • the feature information of the ten dimensions shown in Table 2 above is only one of the embodiments in the present application, but the application is not limited to the feature information of the ten dimensions shown in Table 1, and may also be One of them, or at least two of them, or all of them, may also include feature information of other dimensions, for example, whether it is currently charging, current power, or whether WiFi is currently connected.
  • the generating module 32 is configured to calculate a sample vector set by using a nonlinear support vector machine algorithm to generate a training model.
  • the generating module 32 trains the historical feature information x i acquired by the obtaining module 31, and inputs the historical feature information x i in a nonlinear support vector machine algorithm.
  • the generating module 32 includes a training module 321 and a solving module 322 .
  • the training module 321 is configured to mark the sample vectors in the sample vector set to generate a label result of each sample vector.
  • the solving module 322 is configured to obtain a training model by defining a Gaussian kernel function.
  • the kernel function is a Gaussian kernel function
  • K(x, x i ) is the Euclidean distance between any point x in space to a certain center x i
  • is the width parameter of the Gaussian kernel function
  • the solving module 322 can be used to define a model function and a classification decision function according to a Gaussian kernel function by defining a Gaussian kernel function, define a target optimization function through a model function and a classification decision function, and optimize the sequence by minimum
  • the algorithm obtains the optimal solution of the target optimization function, and obtains a training model, and the target optimization function is
  • the target optimization function is to find a minimum value on the parameters ( ⁇ 1 , ⁇ 2, ..., ⁇ i ), one ⁇ i corresponds to one sample (x i , y i ), and the total number of variables is equal to the training sample Capacity m.
  • the optimal solution can be written as The training model is
  • the g(x) is the training model output value.
  • the calculation module 33 is configured to input the current feature information s of the application into the training model for calculation.
  • the calculation module 33 may include an acquisition module 331 and an operation module 332 .
  • the collecting module 331 is configured to collect current feature information s of the application.
  • the operation module 332 is configured to bring the current feature information s into the training model for calculation.
  • the current feature information s of the application is collected, and the current feature information s is brought into the formula calculation.
  • the acquired dimension of the current feature information s of the application is the same as the dimension of the collected historical feature information x i of the application.
  • the collecting module 331 is configured to collect the current feature information s according to the predetermined acquisition time, and store the current feature information s in the storage module 37.
  • the collecting module 331 is further configured to collect and detect the application.
  • the current feature information s corresponding to the time point entering the background is used, and the current feature information s is input into the operation module 332 for being brought into the training model for calculation.
  • the determining module 34 is configured to determine whether the application needs to be closed.
  • the application management device 30 further includes a second preset module 38.
  • the second preset module 38 is configured to preset a future time period.
  • the determining module 34 determines the probability that the application is applied in the preset future time period according to the result calculated by the calculating module 33.
  • the preset future time period may be 5 minutes, 10 minutes, or 15 minutes after detecting the time point when the application is in the background.
  • the application management device 30 can also include a shutdown module 39 for shutting down the application when it is determined that the application needs to be closed.
  • the device for the application management and control method provided by the application obtains the historical feature information x i by detecting the application entering the background, and generates a training model by using a nonlinear support vector machine algorithm, thereby bringing the current feature information s of the application into Train the model to determine if the application needs to be closed and intelligently close the application.
  • FIG. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • the electronic device 500 includes a processor 501 and a memory 502.
  • the processor 501 is electrically connected to the memory 502.
  • the processor 501 is a control center of the electronic device 500, and connects various parts of the entire electronic device 500 by various interfaces and lines, by running or loading an application stored in the memory 502, and calling data stored in the memory 502, executing The various functions of the electronic device and the processing of the data enable overall monitoring of the electronic device 500.
  • the processor 501 in the electronic device 500 loads the instructions corresponding to the process of one or more applications into the memory 502 according to the following steps, and is stored and stored in the memory 502 by the processor 501.
  • the application thus implementing various functions:
  • sample vector set of the application in a preset historical time period, wherein the sample vector in the sample vector set includes historical feature information x i of a plurality of dimensions of the application at a plurality of time points within a preset historical time period ;
  • the sample vector set is calculated by a nonlinear support vector machine algorithm to generate a training model.
  • the application may be a chat application, a video application, a music application, a shopping application, a shared bicycle application, or a mobile banking application.
  • a sample vector includes historical feature information x i of a plurality of dimensions of the application at a certain point in time within a preset historical time period.
  • the preset historical time period is a time period before a time point when the application enters the background is detected.
  • the preset historical time period may be one week before the time point when the application is in the background is detected.
  • an application is detected entering the background at 8:15 am on August 15, 2017, and the historical feature information x i of the week before 8:15 am on August 15, 2017 is obtained, that is, Obtain historical characteristic information x i between 8:15 am on August 8, 2017 and 8:15 am on August 15, 2017.
  • the preset historical time period may also be three days before the time point when the application is in the background is detected.
  • an application is detected entering the background to obtain historical feature information x i for three days before 6:20 pm on August 13, 2017. That is, the historical feature information x i between 6:20 pm on August 10, 2017 and 6:20 pm on August 13, 2017 is obtained.
  • the feature information of the multiple dimensions may refer to Table 3.
  • the feature information of the ten dimensions shown in Table 3 above is only one of the embodiments in the present application, but the application is not limited to the feature information of the ten dimensions shown in Table 1, and may also be One of them, or at least two of them, or all of them, may also include feature information of other dimensions, for example, whether it is currently charging, current power, or whether WiFi is currently connected.
  • the processor 501 calculates a sample vector set by using a nonlinear support vector machine algorithm, and the generating the training model further includes:
  • the training model is obtained by defining a Gaussian kernel function.
  • the kernel function is a Gaussian kernel function
  • K(x, x i ) is the Euclidean distance between any point x in space to a certain center x i
  • is the width parameter of the Gaussian kernel function
  • the training model is obtained by defining a Gaussian kernel function, defining a model function and a classification decision function according to a Gaussian kernel function
  • the model function and the classification decision function define a target optimization function
  • the optimal solution of the target optimization function is obtained by the sequence minimum optimization algorithm to obtain a training model
  • the target optimization function is
  • the target optimization function is to find a minimum value on the parameters ( ⁇ 1 , ⁇ 2, ..., ⁇ i ), one ⁇ i corresponds to one sample (x i , y i ), and the total number of variables is equal to the training sample Capacity m.
  • the optimal solution can be written as The training model is
  • the g(x) is the training model output value.
  • the processor 501 inputs the current feature information s of the application into the training model for calculation, and further includes:
  • the current feature information s is brought into the training model for calculation.
  • the processor 501 collects current feature information s of the application, and brings the current feature information s into a formula calculation.
  • the dimension of the current feature information s of the application collected by the processor 501 is the same as the dimension of the collected historical feature information x i of the application.
  • the processor 501 determines if the application needs to be shut down. When g(s) > 0, the processor 501 determines that the application needs to be turned off; when g(s) ⁇ 0, the processor 501 determines that the application needs to be reserved.
  • Memory 502 can be used to store applications and data.
  • the program stored in the memory 502 contains instructions executable in the processor.
  • the program can constitute various functional modules.
  • the processor 501 executes various function applications and data processing by running a program stored in the memory 502.
  • FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • the electronic device 500 further includes a radio frequency circuit 503, a display screen 504, a control circuit 505, an input unit 506, an audio circuit 507, a sensor 508, and a power source 509.
  • the processor 501 is electrically connected to the radio frequency circuit 503, the display screen 504, the control circuit 505, the input unit 506, the audio circuit 507, the sensor 508, and the power source 509, respectively.
  • the radio frequency circuit 503 is configured to transceive radio frequency signals to communicate with a server or other electronic device over a wireless communication network.
  • the display screen 504 can be used to display information entered by the user or information provided to the user as well as various graphical user interfaces of the terminal, which can be composed of images, text, icons, video, and any combination thereof.
  • the control circuit 505 is electrically connected to the display screen 504 for controlling the display screen 504 to display information.
  • the input unit 506 can be configured to receive input digits, character information, or user characteristic information (eg, fingerprints), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function controls.
  • user characteristic information eg, fingerprints
  • the audio circuit 507 can provide an audio interface between the user and the terminal through a speaker and a microphone.
  • Sensor 508 is used to collect external environmental information.
  • Sensor 508 can include one or more of ambient brightness sensors, acceleration sensors, gyroscopes, and the like.
  • Power source 509 is used to power various components of electronic device 500.
  • the power supply 509 can be logically coupled to the processor 501 through a power management system to enable functions such as managing charging, discharging, and power management through the power management system.
  • the electronic device 500 may further include a camera, a Bluetooth module, and the like, and details are not described herein again.
  • the electronic device provided by the application enters the background by detecting the application program, acquires the historical feature information x i , and generates a training model by using a nonlinear support vector machine algorithm, thereby bringing the current feature information s of the application into the training model, thereby judging the Whether the application needs to be closed, intelligently close the application.
  • the embodiment of the present invention further provides a medium in which a plurality of instructions are stored, the instructions being adapted to be loaded by a processor to execute the application management method described in any of the above embodiments.
  • the program may be stored in a computer readable storage medium, and the storage medium may include: Read Only Memory (ROM), Random Access Memory (RAM), disk or optical disk.
  • ROM Read Only Memory
  • RAM Random Access Memory

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Stored Programmes (AREA)

Abstract

本申请提供了一种应用程序管控方法及电子设备,通过检测应用程序进入后台,获取历史特征信息x i,采用非线性支持向量机算法生成训练模型,从而将应用程序的当前特征信息s带入训练模型,进而判断所述应用程序是否需要关闭,智能关闭应用程序。

Description

应用程序管控方法及电子设备
本申请要求于2017年09月30日提交中国专利局、申请号为201710919669.4、申请名称为“应用程序管控方法、装置、介质及电子设备”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及电子设备终端领域,具体涉及一种应用程序管控方法及电子设备。
背景技术
终端用户每天会使用大量应用,通常一个应用被推到后台后,如果及时不清理会占用宝贵的***缓存资源,并且会影响***功耗。因此,有必要提供一种应用程序管控方法及电子设备。
发明内容
本申请实施例提供一种应用程序管控方法及电子设备,以智能关闭应用程序。
本申请实施例提供一种应用程序管控方法,应用于电子设备,所述应用程序管控方法包括:
获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
判断所述应用程序是否需要关闭。
本申请实施例提供一种电子设备,所述电子设备包括处理器和存储器,在所述存储器中存储有应用程序,所述处理器运行所述应用程序,所述处理器还执行:
获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
判断所述应用程序是否需要关闭。
本申请实施例提供一种电子设备,所述电子设备包括处理器和存储器,在所述存储器中存储有应用程序,所述处理器运行所述应用程序,所述处理器还执行:
获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
当判断所述应用程序需要关闭时,所述处理器关闭所述应用程序,释放所述应用程序占用的缓存空间。
本申请所提供的应用程序管控方法及电子设备,通过检测应用程序进入后台,获取历史特征信息x i,采用非线性支持向量机算法生成训练模型,从而将应用程序的当前特征信息s带入训练模型,进而判断所述应用程序是否需要关闭,智能关闭应用程序。
附图说明
为了更清楚地说明本申请实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的应用程序管控装置的一种***示意图。
图2为本申请实施例提供的应用程序管控装置的应用场景示意图。
图3为本申请实施例提供的应用程序管控方法的一种流程示意图。
图4为本申请实施例提供的应用程序管控方法的另一种流程示意图。
图5为本申请实施例提供的装置的一种结构示意图。
图6为本申请实施例提供的装置的另一种结构示意图。
图7为本申请实施例提供的电子设备的一种结构示意图。
图8为本申请实施例提供的电子设备的另一种结构示意图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述。显然,所描述的实施例仅仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
本申请实施例提供一种应用程序管控方法,应用于电子设备,所述应用程序管控方法包括:
获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
判断所述应用程序是否需要关闭。
在所述的应用程序管控方法中,所述采用非线性支持向量机算法对样本向量集进行计算,生成训练模型包括:
对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果y i;以及
通过定义高斯核函数,得到训练模型。
在所述的应用程序管控方法中,所述核函数为高斯核函数为
Figure PCTCN2018097907-appb-000001
其中,K(x,x i)为空间中任一点x到某一中心x i之间欧氏距离,σ为高斯核函数的宽度参数。
在所述的应用程序管控方法中,所述通过定义高斯核函数,得到训练模型为通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型,所述模型函数为
Figure PCTCN2018097907-appb-000002
所述分类决策函数为
Figure PCTCN2018097907-appb-000003
其中,f(x)为分类决策值,α i是拉格朗日因子,b为偏置系数,当f(x)=1时,代表所述应用程序“可清理”,当f(x)=-1时,代表所述应用程序“不可清理”。
在所述的应用程序管控方法中,所述通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型为通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,通过模型函数和分类决策函数定义目标最优化函数,通过序列最小优化算法得到目标优化函数的最优解,得到训练模型,所述目标优化函数为
Figure PCTCN2018097907-appb-000004
其中,所述目标最优化函数为在参数(α 12,…,α i)上求最小值,一个α i对应于一个样本(x i,y i),变量的总数等于训练样本的容量m。
在所述的应用程序管控方法中,所述最优解记为
Figure PCTCN2018097907-appb-000005
所述训练模型为
Figure PCTCN2018097907-appb-000006
所述g(x)为训练模型输出值。
在所述的应用程序管控方法中,所述判断应用程序是否需要关闭还包括:
当g(s)>0,判定所述应用程序需要关闭;以及
当g(s)<0,判定所述应用程序需要保留。
在所述的应用程序管控方法中,在所述判断所述应用程序是否需要关闭中,当判断所述应用程序需要关闭时,则关闭所述应用程序,当判断所述应用程序需要保留时,则保留所述应用程序。
在所述的应用程序管控方法中,在所述获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i之前,还包括:
检测所述应用程序是否进入后台;
如果是,则执行获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
如果否,则重复执行检测所述应用程序是否进入后台。
本申请实施例提供一种电子设备,所述电子设备包括处理器和存储器,在所述存储器中存储有应用程序,所述处理器运行所述应用程序,所述处理器还执行:
获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用 程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
判断所述应用程序是否需要关闭。
在所述电子设备中,在所述采用非线性支持向量机算法对样本向量集进行计算,生成训练模型中,所述处理器还执行:
对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果y i;以及
通过定义高斯核函数,得到训练模型。
在所述电子设备中,所述核函数为高斯核函数为
Figure PCTCN2018097907-appb-000007
其中,K(x,x i)为空间中任一点x到某一中心x i之间欧氏距离,σ为高斯核函数的宽度参数。
在所述电子设备中,在所述通过定义高斯核函数,得到训练模型中,所述处理器通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型,所述模型函数为
Figure PCTCN2018097907-appb-000008
所述分类决策函数为
Figure PCTCN2018097907-appb-000009
其中,f(x)为分类决策值,α i是拉格朗日因子,b为偏置系数,当f(x)=1时,代表所述应用程序“可清理”,当f(x)=-1时,代表所述应用程序“不可清理”。
在所述电子设备中,在通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型中,所述处理器通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,通过模型函数和分类决策函数定义目标最优化函数,通过序列最小优化算法得到目标优化函数的最优解,得到训练模型,所述目标优化函数为
Figure PCTCN2018097907-appb-000010
其中,所述目标最优化函数为在参数(α 12,…,α i)上求最小值,一个α i对应于一个样本(x i,y i),变量的总数等于训练样本的容量m。
在所述电子设备中,所述最优解记为
Figure PCTCN2018097907-appb-000011
所述训练模型为
Figure PCTCN2018097907-appb-000012
所述g(x)为训练模型输出值。
在所述电子设备中,在所述判断应用程序是否需要关闭中,所述处理器还执行:
当g(s)>0,判定所述应用程序需要关闭;以及
当g(s)<0,判定所述应用程序需要保留。
在所述电子设备中,在所述判断应用程序是否需要关闭中,当判断所述应用程序需要关闭时,所述处理器关闭所述应用程序,当判断所述应用程序需要保留时,所述处理器保留所述应用程序。
在所述电子设备中,在所述获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i之前,所述处理器还执行:
检测所述应用程序是否进入后台;
如果是,则执行获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
如果否,则重复执行检测所述应用程序是否进入后台。
本申请实施例提供一种电子设备,所述电子设备包括处理器和存储器,在所述存储器中存储有应用程序,所述处理器运行所述应用程序,其中,所述处理器还执行:
获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
当判断所述应用程序需要关闭时,所述处理器关闭所述应用程序,释放所述应用程序占用的缓存空间。
在所述电子设备中,在所述采用非线性支持向量机算法对样本向量集进行计算,生成训练模型中,所述处理器还执行:
对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果y i;以及
通过定义高斯核函数,得到训练模型。
本申请提供的应用程序管控方法,主要应用于电子设备,如:手环、智能手机、基于苹果***或安卓***的平板电脑、或基于Windows或Linux***的笔记本电脑等智能移动电子设备。需要说明的是,所述应用程序可以为聊天应用程序、视频应用程序、音乐应用程序、购物应用程序、共享单车应用程序或手机银行应用程序等。
请参阅图1,图1为本申请实施例提供的应用程序管控装置的***示意图。所述应用程序管控装置主要用于:从数据库中获取应用程序的历史特征信息x i,然后,将历史特征信息x i通过算法进行计算,得到训练模型,其次,将应用程序的当前特征信息s输入训练模型进行计算,通过计算结果判断应用程序是否可关闭,以对预设应用程序进行管控,例如关闭、或者冻结等,从而释放电子设备的缓存空间以 及节省电量。
具体的,请参阅图2,图2为本申请实施例提供的应用程序管控方法的应用场景示意图。在一种实施例中,应用程序管控装置在检测到应用程序进入电子设备的后台时,从数据库中获取应用程序的历史特征信息x i,然后,将历史特征信息x i通过算法进行计算,得到训练模型,其次,将应用程序的当前特征信息s输入训练模型进行计算,通过计算结果判断应用程序是否可关闭。比如,应用程序管控装置在检测到应用程序a进入电子设备的后台时,从数据库中获取应用程序a的历史特征信息x i,然后,将历史特征信息x i通过算法进行计算,得到训练模型,其次,将应用程序的当前特征信息s输入训练模型进行计算,通过计算结果判断应用程序a可关闭,并将应用程序a关闭;应用程序管控装置在检测到应用程序b进入电子设备的后台时,从数据库中获取应用程序b的历史特征信息x i,然后,将历史特征信息x i通过算法进行计算,得到训练模型,其次,将应用程序b的当前特征信息s输入训练模型进行计算,通过计算结果判断应用程序b需要保留,并将应用程序b保留,从而节省了应用程序b处于后台时占用的电子设备缓存空间和节省了应用程序b处于后台时对电子设备电量的消耗。
本申请实施例提供一种应用程序管控方法,所述应用程序管控方法的执行主体可以是本发明实施例提供的应用程序管控装置,或者成了该应用程序管控装置的电子设备,其中该应用程序管控装置可以采用硬件或者软件的方式实现。
请参阅图3,图3为本申请实施例提供的应用程序管控方法的流程示意图。本申请实施例提供的应用程序管控方法应用于电子设备,具体流程可以如下:
步骤101,获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
比如,当检测到应用程序进入后台时,获取应用程序的多个样本向量,所述多个样本向量形成样本向量集。一个样本向量包括应用程序在预设历史时段内的某一时间点的多个维度的历史特征信息x i
其中,所述预设历史时段为检测到应用程序进入后台的时间点之前的时间段。
例如,所述预设历史时段可以为检测到应用程序处于后台的时间点之前的一周。在一种实施例中,2017年8月15日上午8点15分检测到某一应用程序进入后台,获取2017年8月15日上午8点15分之前一周的历史特征信息x i,也即获取2017年8月8日上午8点15分至2017年8月15日上午8点15分之间的历史特征信息x i
例如,在所述预设历史时段还可以为检测到应用程序处于后台的时间点之前的三天。在一种实施例中,2017年8月13日下午6点20分检测到某一应用程序进入后台,获取2017年8月13日下午6点20分之前三天的历史特征信息x i,也即获取2017年8月10日下午6点20分至2017年8月13日下午6点20分之间的历史 特征信息x i
其中,所述多个维度的特征信息可以参考表1。
Figure PCTCN2018097907-appb-000013
表1
需要说明的是,以上表1示出的10个维度的特征信息仅为本申请实施例中的一种,但是本申请并不局限于表1示出的10个维度的特征信息,也可以为其中之一、或者其中至少两个,或者全部,亦或者还可以包括其他维度的特征信息,例如,当前是否在充电、当前的电量或者当前是否连接WiFi等。
步骤102,采用非线性支持向量机算法对样本向量集进行计算,生成训练模型。
请参阅图4,图4为本申请实施例提供的应用程序管控方法的流程示意图。在一种实施例中,所述步骤102可以包括:
步骤1021:对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果y i;以及
步骤1022:通过定义高斯核函数,得到训练模型。
在步骤1021中,对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果y i
比如,可以对样本向量集中的样本向量进行标记,在非线性支持向量机算法中输入样本向量,生成每个样本向量的标记结果y i,形成样本向量结果集T={(x 1,y 1),(x 2,y 2),...,(x m,y m)},输入样本向量x i∈R n,y i∈{+1,-1},i=1,2,3,...,n,R n表示样本向量所在的输入空间,n表示输入空间的维数,y i表示输入样本向量对应的标记结果。
在步骤1022中,通过定义高斯核函数,得到训练模型。
在一种实施例中,所述核函数为高斯核函数为
Figure PCTCN2018097907-appb-000014
其中,K(x,x i)为空间中任一点x到某一中心x i之间欧氏距离,σ为高斯核函数的宽度参数。
在一种实施例中,所述通过定义高斯核函数,得到训练模型可以为通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型,所述模型函数为
Figure PCTCN2018097907-appb-000015
所述分类决策函数为
Figure PCTCN2018097907-appb-000016
其中,f(x)为分类决策值,α i是拉格朗日因子,b为偏置系数,当f(x)=1时,代表所述应用程序“可清理”,当f(x)=-1时,代表所述应用程序“不可清理”。
在一种实施例中,所述通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型可以为通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,通过模型函数和分类决策函数定义目标最优化函数,通过序列最小优化算法得到目标优化函数的最优解,得到训练模型,所述目标优化函数为
Figure PCTCN2018097907-appb-000017
其中,所述目标最优化函数为在参数(α 12,…,α i)上求最小值,一个α i对应于一个样本(x i,y i),变量的总数等于训练样本的容量m。
在一种实施例中,所述最优解可以记为
Figure PCTCN2018097907-appb-000018
所述训练模型为
Figure PCTCN2018097907-appb-000019
所述g(x)为训练模型输出值。
步骤103,将所述应用程序的当前特征信息s输入所述训练模型进行计算。
请参阅图4,在一种实施例中,所述步骤103可以包括:
步骤1031:采集所述应用程序的当前特征信息s;以及
步骤1032:将当前特征信息s带入训练模型进行计算。
在一种实施例中,采集所述应用程序的当前特征信息s,将当前特征信息s带入公式计算
Figure PCTCN2018097907-appb-000020
在一种实施方式中,采集的所述应用程序的当前特征信息s的维度与采集的所述应用程序的历史特征信息x i的维度相同。
步骤104,判断所述应用程序是否需要关闭。
需要说明的是,当g(s)>0,判定应用程序需要关闭;当g(s)<0,判定应用程序需要保留。
本申请所提供的应用程序管控方法,通过检测应用程序进入后台,获取历史特征信息x i,采用非线性支持向量机算法生成训练模型,从而将应用程序的当前特征信息s带入训练模型,进而判断所述应用程序是否需要关闭,智能关闭应用程序。
请参阅图5,图5为本申请实施例提供的应用程序管控装置的结构示意图。所述应用程序管控装置30包括获取模块31,生成模块32、计算模块33和判断模块34。
需要说明的是,所述应用程序可以为聊天应用程序、视频应用程序、音乐应用程序、购物应用程序、共享单车应用程序或手机银行应用程序等。
所述获取模块31用于获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
请参阅图6,图6为本申请实施例提供的应用程序管控装置的结构示意图。所述应用程序管控装置30还包括检测模块35,用于检测所述应用程序进入后台。
所述应用程序管控装置30还可以包括第一预设模块36和储存模块37。所述第一预设模块36用于预设历史时段。所述储存模块37用于储存应用程序的特征信息。所述获取模块31根据所述第一预设模块36设定的预设历史时段,从储存模块37中获取预设历史时段内历史特征信息x i
比如,当检测到应用程序进入后台时,获取应用程序的多个样本向量,所述多个样本向量形成样本向量集。一个样本向量包括应用程序在预设历史时段内的某一时间点的多个维度的历史特征信息x i
其中,所述预设历史时段为检测到应用程序进入后台的时间点之前的时间段。
例如,所述预设历史时段可以为检测到应用程序处于后台的时间点之前的一周。在一种实施例中,2017年8月15日上午8点15分检测到某一应用程序进入后台,获取2017年8月15日上午8点15分之前一周的历史特征信息x i,也即获取2017年8月8日上午8点15分至2017年8月15日上午8点15分之间的历史特征信息x i
例如,在所述预设历史时段还可以为检测到应用程序处于后台的时间点之前的三天。在一种实施例中,2017年8月13日下午6点20分检测到某一应用程序进入后台,获取2017年8月13日下午6点20分之前三天的历史特征信息x i,也即获取2017年8月10日下午6点20分至2017年8月13日下午6点20分之间的历史特征信息x i
其中,所述多个维度的特征信息可以参考表2。
Figure PCTCN2018097907-appb-000021
表2
需要说明的是,以上表2示出的10个维度的特征信息仅为本申请实施例中的一种,但是本申请并不局限于表1示出的10个维度的特征信息,也可以为其中之一、或者其中至少两个,或者全部,亦或者还可以包括其他维度的特征信息,例如,当前是否在充电、当前的电量或者当前是否连接WiFi等。
所述生成模块32用于采用非线性支持向量机算法对样本向量集进行计算,生成训练模型。
所述生成模块32训练所述获取模块31获取的历史特征信息x i,在非线性支持向量机算法中输入所述历史特征信息x i
请参阅图6,所述生成模块32包括训练模块321和求解模块322。
所述训练模块321用于对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果。
比如,可以对样本向量集中的样本向量进行标记,在非线性支持向量机算法中输入样本向量,生成每个样本向量的标记结果y i,形成样本向量结果集T={(x 1,y 1),(x 2,y 2),...,(x m,y m)},输入样本向量x i∈R n,y i∈{+1,-1},i=1,2,3,...,n,R n表示样本向量所在的输入空间,n表示输入空间的维数,y i表示输入样本向量对应的标记结果。
所述求解模块322用于通过定义高斯核函数,得到训练模型。
在一种实施例中,所述核函数为高斯核函数为
Figure PCTCN2018097907-appb-000022
其中,K(x,x i)为空间中任一点x到某一中心x i之间欧氏距离,σ为高斯核函数的宽度参数。
在一种实施例中,所述求解模块322可以用于通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型,所述模型函数为
Figure PCTCN2018097907-appb-000023
所述分类决策函数为
Figure PCTCN2018097907-appb-000024
其中,f(x)为分类决策值,α i是拉格朗日因子,b为偏置系数,当f(x)=1时,代表所述应用程序“可清理”,当f(x)=-1时,代表所述应用程序“不可清理”。
在一种实施例中,所述求解模块322可以用于通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,通过模型函数和分类决策函数定义目标最优化函数,通过序列最小优化算法得到目标优化函数的最优解,得到训练模型,所述目标优化函数为
Figure PCTCN2018097907-appb-000025
其中,所述目标最优化函数为在参数(α 12,…,α i)上求最小值,一个α i对应于一个样本(x i,y i),变量的总数等于训练样本的容量m。
在一种实施例中,所述最优解可以记为
Figure PCTCN2018097907-appb-000026
所述训练模型为
Figure PCTCN2018097907-appb-000027
所述g(x)为训练模型输出值。
所述计算模块33用于将所述应用程序的当前特征信息s输入所述训练模型进行计算。
请参阅图6,在一种实施例中,所述计算模块33可以包括采集模块331和运算模块332。
所述采集模块331用于采集所述应用程序的当前特征信息s。
所述运算模块332用于当前特征信息s带入训练模型进行计算。
在一种实施例中,采集所述应用程序的当前特征信息s,将当前特征信息s带入公式计算
Figure PCTCN2018097907-appb-000028
在一种实施方式中,采集的所述应用程序的当前特征信息s的维度与采集的所述应用程序的历史特征信息x i的维度相同。
在一种实施例中,所述采集模块331用于根据预定采集时间定时采集当前特征信息s,并将当前特征信息s存入储存模块37,所述采集模块331还用于采集检测到应用程序进入后台的时间点对应的当前特征信息s,并将该当前特征信息s输入运算模块332用于带入训练模型进行计算。
所述判断模块34用于判断所述应用程序是否需要关闭。
需要说明的是,当g(s)>0,判定应用程序需要关闭;当g(s)<0,判定应用程序需要保留。
所述应用程序管控装置30还包括一第二预设模块38。所述第二预设模块38用于预设未来时段。所述判断模块34根据所述计算模块33计算的结果判断应用程序在预设未来时段应用的概率。所述预设的未来时段可以是从检测到应用程序处于后台的时间点之后5分钟、10分钟或者15分钟。
所述应用程序管控装置30还可以包括关闭模块39,用于当判断应用程序需要关闭时,将所述应用程序关闭。
本申请所提供的用于应用程序管控方法的装置,通过检测应用程序进入后台,获取历史特征信息x i,采用非线性支持向量机算法生成训练模型,从而将应用程序的当前特征信息s带入训练模型,进而判断所述应用程序是否需要关闭,智能关闭应用程序。
请参阅图7,图7为本申请实施例提供的电子设备的结构示意图。所述电子设备500包括:处理器501和存储器502。其中,处理器501与存储器502电性连接。
处理器501是电子设备500的控制中心,利用各种接口和线路连接整个电子设备500的各个部分,通过运行或加载存储在存储器502内的应用程序,以及调用存储在存储器502内的数据,执行电子设备的各种功能和处理数据,从而对电子设备500进行整体监控。
在本实施例中,电子设备500中的处理器501会按照如下的步骤,将一个或一个以上的应用程序的进程对应的指令加载到存储器502中,并由处理器501来运行存储在存储器502中的应用程序,从而实现各种功能:
获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
判断所述应用程序是否需要关闭。
需要说明的是,所述应用程序可以为聊天应用程序、视频应用程序、音乐应用程序、购物应用程序、共享单车应用程序或手机银行应用程序等。
比如,当检测到应用程序进入后台时,获取应用程序的多个样本向量,所述多个样本向量形成样本向量集。一个样本向量包括应用程序在预设历史时段内的某一时间点的多个维度的历史特征信息x i
其中,所述预设历史时段为检测到应用程序进入后台的时间点之前的时间段。
例如,所述预设历史时段可以为检测到应用程序处于后台的时间点之前的一周。在一种实施例中,2017年8月15日上午8点15分检测到某一应用程序进入后台,获取2017年8月15日上午8点15分之前一周的历史特征信息x i,也即获取2017年8月8日上午8点15分至2017年8月15日上午8点15分之间的历史特征信息x i
例如,在所述预设历史时段还可以为检测到应用程序处于后台的时间点之前的三天。在一种实施例中,2017年8月13日下午6点20分检测到某一应用程序进入后台,获取2017年8月13日下午6点20分之前三天的历史特征信息x i,也即获取2017年8月10日下午6点20分至2017年8月13日下午6点20分之间的历史特征信息x i
其中,所述多个维度的特征信息可以参考表3。
Figure PCTCN2018097907-appb-000029
Figure PCTCN2018097907-appb-000030
表3
需要说明的是,以上表3示出的10个维度的特征信息仅为本申请实施例中的一种,但是本申请并不局限于表1示出的10个维度的特征信息,也可以为其中之一、或者其中至少两个,或者全部,亦或者还可以包括其他维度的特征信息,例如,当前是否在充电、当前的电量或者当前是否连接WiFi等。
在一种实施例中,所述处理器501采用非线性支持向量机算法对样本向量集进行计算,生成训练模型还包括:
对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果y i;以及
通过定义高斯核函数,得到训练模型。
在一种实施例中,可以对样本向量集中的样本向量进行标记,在非线性支持向量机算法中输入样本向量,生成每个样本向量的标记结果y i,形成样本向量结果集T={(x 1,y 1),(x 2,y 2),...,(x m,y m)},输入样本向量x i∈R n,y i∈{+1,-1},i=1,2,3,...,n,R n表示样本向量所在的输入空间,n表示输入空间的维数,y i表示输入样本向量对应的标记结果。
在一种实施例中,所述核函数为高斯核函数为
Figure PCTCN2018097907-appb-000031
其中,K(x,x i)为空间中任一点x到某一中心x i之间欧氏距离,σ为高斯核函数的宽度参数。
在一种实施例中,所述通过定义高斯核函数,得到训练模型为通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型,所述模型函数为
Figure PCTCN2018097907-appb-000032
所述分类 决策函数为
Figure PCTCN2018097907-appb-000033
其中,f(x)为分类决策值,α i是拉格朗日因子,b为偏置系数,当f(x)=1时,代表所述应用程序“可清理”,当f(x)=-1时,代表所述应用程序“不可清理”。
在一种实施例中,所述通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型为通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,通过模型函数和分类决策函数定义目标最优化函数,通过序列最小优化算法得到目标优化函数的最优解,得到训练模型,所述目标优化函数为
Figure PCTCN2018097907-appb-000034
其中,所述目标最优化函数为在参数(α 12,…,α i)上求最小值,一个α i对应于一个样本(x i,y i),变量的总数等于训练样本的容量m。
在一种实施例中,所述最优解可以记为
Figure PCTCN2018097907-appb-000035
所述训练模型为
Figure PCTCN2018097907-appb-000036
所述g(x)为训练模型输出值。
在一种实施例中,所述处理器501将所述应用程序的当前特征信息s输入所述训练模型进行计算还包括:
采集所述应用程序的当前特征信息s;以及
将当前特征信息s带入训练模型进行计算。
在一种实施例中,所述处理器501采集所述应用程序的当前特征信息s,将当前特征信息s带入公式计算
Figure PCTCN2018097907-appb-000037
在一种实施方式中,所述处理器501采集的所述应用程序的当前特征信息s的维度与采集的所述应用程序的历史特征信息x i的维度相同。
在一种实施方式中,所述处理器501判断所述应用程序是否需要关闭。当g(s)>0,所述处理器501判定应用程序需要关闭;当g(s)<0,所述处理器501判定应用程序需要保留。
存储器502可用于存储应用程序和数据。存储器502存储的程序中包含有可在处理器中执行的指令。所述程序可以组成各种功能模块。处理器501通过运行存储在存储器502的程序,从而执行各种功能应用以及数据处理。
在一些实施例中,如图8所示,图8为本申请实施例提供的电子设备的结构示意图。所述电子设备500还包括:射频电路503、显示屏504、控制电路505、输入单元506、音频电路507、传感器508以及电源509。其中,处理器501分别与射频电路503、显示屏504、控制电路505、输入单元506、音频 电路507、传感器508以及电源509电性连接。
射频电路503用于收发射频信号,以通过无线通信网络与服务器或其他电子设备进行通信。
显示屏504可用于显示由用户输入的信息或提供给用户的信息以及终端的各种图形用户接口,这些图形用户接口可以由图像、文本、图标、视频和其任意组合来构成。
控制电路505与显示屏504电性连接,用于控制显示屏504显示信息。
输入单元506可用于接收输入的数字、字符信息或用户特征信息(例如指纹),以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入。
音频电路507可通过扬声器、传声器提供用户与终端之间的音频接口。
传感器508用于采集外部环境信息。传感器508可以包括环境亮度传感器、加速度传感器、陀螺仪等传感器中的一种或多种。
电源509用于给电子设备500的各个部件供电。在一些实施例中,电源509可以通过电源管理***与处理器501逻辑相连,从而通过电源管理***实现管理充电、放电、以及功耗管理等功能。
尽管图8中未示出,电子设备500还可以包括摄像头、蓝牙模块等,在此不再赘述。
本申请所提供的电子设备,通过检测应用程序进入后台,获取历史特征信息x i,采用非线性支持向量机算法生成训练模型,从而将应用程序的当前特征信息s带入训练模型,进而判断所述应用程序是否需要关闭,智能关闭应用程序。
本发明实施例还提供一种介质,该介质中存储有多条指令,该指令适于由处理器加载以执行上述任一实施例所述的应用程序管控方法。
本发明实施例提供的应用程序管控方法及电子设备属于同一构思,其具体实现过程详见说明书全文,此处不再赘述。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,该程序可以存储于一计算机可读存储介质中,存储介质可以包括:只读存储器(ROM,Read Only Memory)、随机存取记忆体(RAM,Random Access Memory)、磁盘或光盘等。
以上对本申请实施例提供的应用程序管控方法及电子设备进行了详细介绍,本文中应用了具体个例对本申请的原理及实施例进行了阐述,以上实施例的说明只是用于帮助理解本申请。同时,对于本领域的技术人员,依据本申请的思想,在具体实施例及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本申请的限制。

Claims (20)

  1. 一种应用程序管控方法,应用于电子设备,其中,所述应用程序管控方法包括:
    获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
    采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
    将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
    判断所述应用程序是否需要关闭。
  2. 如权利要求1所述的应用程序管控方法,其中,所述采用非线性支持向量机算法对样本向量集进行计算,生成训练模型包括:
    对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果y i;以及
    通过定义高斯核函数,得到训练模型。
  3. 如权利要求2所述的应用程序管控方法,其中,所述核函数为高斯核函数为
    Figure PCTCN2018097907-appb-100001
    其中,K(x,x i)为空间中任一点x到某一中心x i之间欧氏距离,σ为高斯核函数的宽度参数。
  4. 如权利要求3所述的应用程序管控方法,其中,所述通过定义高斯核函数,得到训练模型为通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型,所述模型函数为
    Figure PCTCN2018097907-appb-100002
    所述分类决策函数为
    Figure PCTCN2018097907-appb-100003
    其中,f(x)为分类决策值,α i是拉格朗日因子,b为偏置系数,当f(x)=1时,代表所述应用程序“可清理”,当f(x)=-1时,代表所述应用程序“不可清理”。
  5. 如权利要求4所述的应用程序管控方法,其中,所述通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型为通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,通过模型函数和分类决策函数定义目标最优化函数,通过序列最小优化算法得到目标优化函数的最优解,得到训练模型,所述目标优化函数为
    Figure PCTCN2018097907-appb-100004
    其中,所述目标最优化函数为在参数(α 12,…,α i)上求最小值,一个α i对应于一个样本(x i,y i),变量的总数等于训练样本的容量m。
  6. 如权利要求5所述的应用程序管控方法,其中,所述最优解记为
    Figure PCTCN2018097907-appb-100005
    所述训 练模型为
    Figure PCTCN2018097907-appb-100006
    所述g(x)为训练模型输出值。
  7. 如权利要求6所述的应用程序管控方法,其中,所述判断应用程序是否需要关闭还包括:
    当g(s)>0,判定所述应用程序需要关闭;以及
    当g(s)<0,判定所述应用程序需要保留。
  8. 如权利要求1所述的应用程序管控方法,其中,在所述判断所述应用程序是否需要关闭中,当判断所述应用程序需要关闭时,则关闭所述应用程序,当判断所述应用程序需要保留时,则保留所述应用程序。
  9. 如权利要求1所述的应用程序管控方法,其中,在所述获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i之前,还包括:
    检测所述应用程序是否进入后台;
    如果是,则执行获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
    如果否,则重复执行检测所述应用程序是否进入后台。
  10. 一种电子设备,所述电子设备包括处理器和存储器,在所述存储器中存储有应用程序,所述处理器运行所述应用程序,其中,所述处理器还执行:
    获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
    采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
    将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
    判断所述应用程序是否需要关闭。
  11. 如权利要求10所述电子设备,其中,在所述采用非线性支持向量机算法对样本向量集进行计算,生成训练模型中,所述处理器还执行:
    对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果y i;以及
    通过定义高斯核函数,得到训练模型。
  12. 如权利要求11所述电子设备,其中,所述核函数为高斯核函数为
    Figure PCTCN2018097907-appb-100007
    其中,K(x,x i)为空间中任一点x到某一中心x i之间欧氏距离,σ为高斯核函数的宽度参数。
  13. 如权利要求12所述电子设备,其中,在所述通过定义高斯核函数,得到训练模型中,所述处理器通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型,所述模型函数为
    Figure PCTCN2018097907-appb-100008
    所述分类决策函数为
    Figure PCTCN2018097907-appb-100009
    其中,f(x)为分类决策值,α i是拉格朗日因子,b为偏置系数,当f(x)=1时,代表所述应用程序“可清理”,当f(x)=-1时,代表所述应用程序“不可清理”。
  14. 如权利要求13所述电子设备,其中,在通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,得到训练模型中,所述处理器通过定义高斯核函数,根据高斯核函数定义模型函数和分类决策函数,通过模型函数和分类决策函数定义目标最优化函数,通过序列最小优化算法得到目标优化函数的最优解,得到训练模型,所述目标优化函数为
    Figure PCTCN2018097907-appb-100010
    其中,所述目标最优化函数为在参数(α 12,…,α i)上求最小值,一个α i对应于一个样本(x i,y i),变量的总数等于训练样本的容量m。
  15. 如权利要求14所述电子设备,其中,所述最优解记为
    Figure PCTCN2018097907-appb-100011
    所述训练模型为
    Figure PCTCN2018097907-appb-100012
    所述g(x)为训练模型输出值。
  16. 如权利要求15所述电子设备,其中,在所述判断应用程序是否需要关闭中,所述处理器还执行:
    当g(s)>0,判定所述应用程序需要关闭;以及
    当g(s)<0,判定所述应用程序需要保留。
  17. 如权利要求10所述电子设备,其中,在所述判断应用程序是否需要关闭中,当判断所述应用程序需要关闭时,所述处理器关闭所述应用程序,当判断所述应用程序需要保留时,所述处理器保留所述应用程序。
  18. 如权利要求/0所述电子设备,其中,在所述获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i之前,所述处理器还执行:
    检测所述应用程序是否进入后台;
    如果是,则执行获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
    如果否,则重复执行检测所述应用程序是否进入后台。
  19. 一种电子设备,所述电子设备包括处理器和存储器,在所述存储器中存储有应用程序,所述处理器运行所述应用程序,其中,所述处理器还执行:
    获取所述应用程序在预设历史时段内的样本向量集,其中该样本向量集中的样本向量包括所述应用程序在预设历史时间段内的若干时间点的多个维度的历史特征信息x i
    采用非线性支持向量机算法对样本向量集进行计算,生成训练模型;
    将所述应用程序的当前特征信息s输入所述训练模型进行计算;以及
    当判断所述应用程序需要关闭时,所述处理器关闭所述应用程序,释放所述应用程序占用的缓存空间。
  20. 如权利要求19所述电子设备,其中,在所述采用非线性支持向量机算法对样本向量集进行计算,生成训练模型中,所述处理器还执行:
    对样本向量集中的样本向量进行标记,生成每个样本向量的标记结果y i;以及
    通过定义高斯核函数,得到训练模型。
PCT/CN2018/097907 2017-09-30 2018-08-01 应用程序管控方法及电子设备 WO2019062317A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710919669.4A CN107643948B (zh) 2017-09-30 2017-09-30 应用程序管控方法、装置、介质及电子设备
CN201710919669.4 2017-09-30

Publications (1)

Publication Number Publication Date
WO2019062317A1 true WO2019062317A1 (zh) 2019-04-04

Family

ID=61123198

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/097907 WO2019062317A1 (zh) 2017-09-30 2018-08-01 应用程序管控方法及电子设备

Country Status (2)

Country Link
CN (1) CN107643948B (zh)
WO (1) WO2019062317A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110502269A (zh) * 2019-07-24 2019-11-26 深圳壹账通智能科技有限公司 应用程序优化方法、设备、存储介质及装置
CN111241688A (zh) * 2020-01-15 2020-06-05 北京百度网讯科技有限公司 复合生产工艺过程监控方法及装置
CN111797861A (zh) * 2019-04-09 2020-10-20 Oppo广东移动通信有限公司 信息处理方法、装置、存储介质及电子设备
CN115913699A (zh) * 2022-11-11 2023-04-04 南方电网数字电网研究院有限公司 配电网横向访问检测方法、装置、计算机设备和存储介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107643948B (zh) * 2017-09-30 2020-06-02 Oppo广东移动通信有限公司 应用程序管控方法、装置、介质及电子设备
CN107608748B (zh) * 2017-09-30 2019-09-13 Oppo广东移动通信有限公司 应用程序管控方法、装置、存储介质及终端设备
CN107678845B (zh) * 2017-09-30 2020-03-10 Oppo广东移动通信有限公司 应用程序管控方法、装置、存储介质及电子设备
CN107885544B (zh) * 2017-10-31 2020-04-10 Oppo广东移动通信有限公司 应用程序管控方法、装置、介质及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015009023A1 (ko) * 2013-07-15 2015-01-22 삼성전자 주식회사 휴대 단말기의 사용 로그를 활용하는 방법 및 이를 이용한 장치
CN106055399A (zh) * 2016-05-31 2016-10-26 宇龙计算机通信科技(深圳)有限公司 一种控制应用程序的方法及终端
CN107133094A (zh) * 2017-06-05 2017-09-05 努比亚技术有限公司 应用管理方法、移动终端及计算机可读存储介质
CN107608748A (zh) * 2017-09-30 2018-01-19 广东欧珀移动通信有限公司 应用程序管控方法、装置、存储介质及终端设备
CN107643948A (zh) * 2017-09-30 2018-01-30 广东欧珀移动通信有限公司 应用程序管控方法、装置、介质及电子设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104573740B (zh) * 2014-12-22 2018-07-03 山东鲁能软件技术有限公司 一种基于svm分类模型的设备故障诊断方法
CN105912370B (zh) * 2016-05-03 2020-02-14 Oppo广东移动通信有限公司 移动终端的后台应用程序的控制方法、装置及移动终端
CN106155777A (zh) * 2016-06-30 2016-11-23 宇龙计算机通信科技(深圳)有限公司 一种后台应用管理装置、终端及后台应用管理方法
CN106971091B (zh) * 2017-03-03 2020-08-28 江苏大学 一种基于确定性粒子群优化和支持向量机的肿瘤识别方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015009023A1 (ko) * 2013-07-15 2015-01-22 삼성전자 주식회사 휴대 단말기의 사용 로그를 활용하는 방법 및 이를 이용한 장치
CN106055399A (zh) * 2016-05-31 2016-10-26 宇龙计算机通信科技(深圳)有限公司 一种控制应用程序的方法及终端
CN107133094A (zh) * 2017-06-05 2017-09-05 努比亚技术有限公司 应用管理方法、移动终端及计算机可读存储介质
CN107608748A (zh) * 2017-09-30 2018-01-19 广东欧珀移动通信有限公司 应用程序管控方法、装置、存储介质及终端设备
CN107643948A (zh) * 2017-09-30 2018-01-30 广东欧珀移动通信有限公司 应用程序管控方法、装置、介质及电子设备

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111797861A (zh) * 2019-04-09 2020-10-20 Oppo广东移动通信有限公司 信息处理方法、装置、存储介质及电子设备
CN110502269A (zh) * 2019-07-24 2019-11-26 深圳壹账通智能科技有限公司 应用程序优化方法、设备、存储介质及装置
CN111241688A (zh) * 2020-01-15 2020-06-05 北京百度网讯科技有限公司 复合生产工艺过程监控方法及装置
CN111241688B (zh) * 2020-01-15 2023-08-25 北京百度网讯科技有限公司 复合生产工艺过程监控方法及装置
CN115913699A (zh) * 2022-11-11 2023-04-04 南方电网数字电网研究院有限公司 配电网横向访问检测方法、装置、计算机设备和存储介质
CN115913699B (zh) * 2022-11-11 2024-06-25 南方电网数字电网研究院有限公司 配电网横向访问检测方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN107643948B (zh) 2020-06-02
CN107643948A (zh) 2018-01-30

Similar Documents

Publication Publication Date Title
WO2019062317A1 (zh) 应用程序管控方法及电子设备
WO2019062358A1 (zh) 应用程序管控方法及终端设备
US11169827B2 (en) Resource loading at application startup using attributes of historical data groups
WO2019085749A1 (zh) 应用程序管控方法、装置、介质及电子设备
CN105512685B (zh) 物体识别方法和装置
WO2019120019A1 (zh) 用户性别预测方法、装置、存储介质及电子设备
WO2019062413A1 (zh) 应用程序管控方法、装置、存储介质及电子设备
WO2019085750A1 (zh) 应用程序管控方法、装置、介质及电子设备
US11249645B2 (en) Application management method, storage medium, and electronic apparatus
US20140269643A1 (en) Systems and methods for geo-fencing
US20140038674A1 (en) Two-phase power-efficient activity recognition system for mobile devices
WO2020048392A1 (zh) 应用程序的病毒检测方法、装置、计算机设备及存储介质
WO2019062405A1 (zh) 应用程序的处理方法、装置、存储介质及电子设备
US11423880B2 (en) Method for updating a speech recognition model, electronic device and storage medium
CN107659717B (zh) 状态检测方法、装置和存储介质
US9471873B1 (en) Automating user patterns on a user device
CN113284142A (zh) 图像检测方法、装置、计算机可读存储介质及计算机设备
JP2021530047A (ja) 画像処理方法及び装置、電子機器、並びに記憶媒体
CN111326146A (zh) 语音唤醒模板的获取方法、装置、电子设备及计算机可读存储介质
CN109726726B (zh) 视频中的事件检测方法及装置
WO2022016650A1 (zh) 智能笔图像处理方法、装置及电子设备
CN115618232A (zh) 数据预测方法、装置、存储介质及电子设备
CN109040427A (zh) 分屏处理方法、装置、存储介质和电子设备
CN114298403A (zh) 预测作品的关注度的方法和装置
US11567822B2 (en) Method of monitoring closed system, apparatus thereof and monitoring device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18862747

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18862747

Country of ref document: EP

Kind code of ref document: A1