WO2019000469A1 - 应用控制方法、装置、存储介质及电子设备 - Google Patents

应用控制方法、装置、存储介质及电子设备 Download PDF

Info

Publication number
WO2019000469A1
WO2019000469A1 PCT/CN2017/091381 CN2017091381W WO2019000469A1 WO 2019000469 A1 WO2019000469 A1 WO 2019000469A1 CN 2017091381 W CN2017091381 W CN 2017091381W WO 2019000469 A1 WO2019000469 A1 WO 2019000469A1
Authority
WO
WIPO (PCT)
Prior art keywords
application
weight
items
prediction result
item
Prior art date
Application number
PCT/CN2017/091381
Other languages
English (en)
French (fr)
Inventor
曾元清
Original Assignee
广东欧珀移动通信有限公司
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 广东欧珀移动通信有限公司 filed Critical 广东欧珀移动通信有限公司
Priority to PCT/CN2017/091381 priority Critical patent/WO2019000469A1/zh
Priority to CN201780090733.0A priority patent/CN110914802A/zh
Publication of WO2019000469A1 publication Critical patent/WO2019000469A1/zh

Links

Images

Classifications

    • 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

Definitions

  • the present invention relates to the field of computer communication technologies, and in particular, to an application control method, apparatus, storage medium, and electronic device.
  • Embodiments of the present invention provide an application control method, apparatus, storage medium, and electronic device, which can more accurately predict an application that a user is about to select to open.
  • an embodiment of the present invention provides an application control method, which is applied to an electronic device, and includes:
  • the weights of the plurality of weighting items are adjusted to improve the accuracy of the target prediction result according to the actually opened application.
  • an embodiment of the present invention further provides an application control apparatus, including:
  • An obtaining module configured to acquire historical state information and current weights of multiple weight items in the electronic device
  • a calculation module configured to calculate, according to the historical state information of the multiple weight items, a probability that each weight item individually corresponds to each application being opened, to obtain an independent prediction result corresponding to each weight item;
  • a prediction module configured to predict, according to the independent prediction result and the weight of the current weight, an application to be opened to obtain a target prediction result
  • An adjustment module configured to adjust weights of the plurality of weight items according to an application that is actually opened In order to improve the accuracy of the target prediction results.
  • an embodiment of the present invention further provides a storage medium having a computer program stored thereon, the computer program being invoked by a processor to execute an application control method according to any of the embodiments of the present invention.
  • an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, where the processor calls the computer stored in the memory A program for executing an application control method according to any of the embodiments of the present invention.
  • FIG. 1 is a schematic diagram of interaction between an electronic device and a user according to an embodiment of the present invention.
  • FIG. 2 is a schematic flowchart diagram of an application control method according to an embodiment of the present invention.
  • FIG. 3 is another schematic flowchart of an application control method according to an embodiment of the present invention.
  • FIG. 4 is a historical state information record table of an application control method according to an embodiment of the present invention.
  • FIG. 5 is a related record table of an application control method according to an embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of an application control apparatus according to an embodiment of the present invention.
  • FIG. 7 is another schematic structural diagram of an application control apparatus according to an embodiment of the present invention.
  • FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
  • Embodiments of the present invention provide an application control method, apparatus, storage medium, and electronic device. The details will be described separately below.
  • An execution body of an application control method provided by an embodiment of the present invention may be an application control device provided by an embodiment of the present invention, or an electronic device integrated with the application control device.
  • the computer, the notebook, the palmtop, the tablet, the smart phone, etc., the application control device can be implemented by hardware or software.
  • FIG. 1 is a schematic diagram of interaction between an electronic device and a user according to an embodiment of the present invention.
  • the electronic device includes a data collection and statistics system and a prediction system with feedback adjustment.
  • the data collection and statistics system is configured to collect data of each weight item corresponding to a user when opening an application, and perform corresponding statistics.
  • the prediction system predicts an application that the user will open, the prediction system calculates various prediction results according to each weight item data and the current weight of each weight item.
  • the prediction system analyzes the result of the prediction and the application that the user finally selects to open, and adjusts the weight of each weight item according to the analysis result feedback. After multiple feedback adjustments, the weights of the weighting items of the prediction system finally converge, so that the prediction result is closer to the application that the user actually selects to open, and the accuracy of the prediction result is improved.
  • FIG. 2 is a schematic flowchart diagram of an application control method according to an embodiment of the present invention. The method includes:
  • Step S101 Acquire historical state information and current weights of multiple weight items in the electronic device.
  • each user has different usage habits and usage preferences for applications on the electronic device.
  • the user's usage habits on the application on the electronic device will still follow a certain rule, which is traceable. Therefore, the embodiment of the present invention searches for the usage rule of the user for the application based on the historical usage of the user.
  • the data collection and statistics system acquires historical state information of a plurality of weight items in the electronic device based on a pre-stated user history of the application on the electronic device.
  • the weight items may include, but are not limited to, the current time when the user starts an application, the current location where the user opens an application, the logical order between applications, the duration of the application switching, the headset status of the electronic device, the working status of various sensors of the electronic device, and the like.
  • the prediction system obtains the current weight of each weight item based on the initial weights of the respective weight items and the degree of influence of each weight item in the historical prediction results.
  • Step S102 Calculate, according to the historical state information of the plurality of weight items, a probability that each weight item individually corresponds to each application being opened, to obtain an independent prediction result corresponding to each weight item.
  • each weight item has different degrees of influence on different applications, so each weight item has a corresponding independent prediction result for each application.
  • Step S103 predicting an application to be opened according to the independent prediction result and the weighting of the current weight to obtain a target prediction result.
  • the target prediction result is a probability that is ultimately given based on the influence of the weight of the ownership on the application, and needs to be combined with the weight calculated by the separately calculated probability and the corresponding current weight of the application corresponding to each weight item. To determine the final probability that each app is turned on, to predict which app is about to be opened.
  • Step S104 Adjust the weights of the plurality of weight items according to the actually opened application to improve the accuracy of the target prediction result.
  • the electronic device reversely returns the weight of each weight item according to the final selection result.
  • the weights of the weighting items of the prediction system finally converge, so that the prediction result is closer to the application that the user actually selects to open, and the accuracy of the prediction result is improved.
  • the weighting of the plurality of weighting items is adjusted according to an actually opened application to improve accuracy of the target prediction result, including:
  • the weight of the independent prediction result that predicts that the actually opened application is turned on is greater than the first threshold Value
  • the calculating, according to the historical state information of the plurality of weight items, each probability item corresponding to the probability that each application is turned on, to obtain an independent prediction result corresponding to each weight item includes:
  • each weighting item individually corresponds to a probability that each application is turned on, to obtain a corresponding weight item Independent prediction results.
  • the predicting an application to be opened according to the independent prediction result and the weighting of the current weight to obtain a target prediction result includes:
  • An application that reaches a second threshold in the plurality of applications is predicted to be an application to be opened to obtain a target prediction result.
  • the method before the obtaining the historical state information of the plurality of weight items in the electronic device and the current weight, the method further includes:
  • the state information corresponding to each weight item in the plurality of weight items when the user starts the application in the historical period is collected to collect historical state information of the plurality of weight items.
  • the state information corresponding to each weight item of the plurality of weight items when the user opens the application in the collection history period, to collect historical state information of the plurality of weight items including:
  • the device status includes a headset status and a sensor status.
  • the method before the adjusting the weights of the plurality of weighting items to improve the accuracy of the target prediction result according to the actually opened application, the method further includes:
  • the application that is predicted to be opened is preloaded.
  • the method before the preloading process is performed on the application that is predicted to be opened, the method further includes:
  • Detecting device resources in the electronic device where the device resources include a memory resource and a remaining power.
  • the embodiment of the present invention calculates the historical state information of the plurality of weight items in the electronic device and the current weight, and calculates, according to the historical state information of the plurality of weight items, the probability that each weight item individually corresponds to the opening of each application.
  • the weights of the plurality of weight items are adjusted to improve the accuracy of the target prediction result, so as to provide the user with a more accurate prediction of the user to open the application, so that the electronic device gradually adapts to the user's usage habits and improves the convenience of use. .
  • FIG. 3 is another schematic flowchart of an application control method according to an embodiment of the present invention
  • FIG. 4 is a historical state information record table of an application control method according to an embodiment of the present invention
  • Step S201 Collect state information corresponding to each weight item in the plurality of weight items when the user starts the application in the historical period, to collect historical state information of the plurality of weight items.
  • each user has different usage habits and usage preferences for applications on the electronic device.
  • the user's usage habits on the application on the electronic device will still follow a certain rule, which is traceable. Therefore, the embodiment of the present invention searches for the usage rule of the user for the application based on the historical usage of the user.
  • the multiple weighting items are respective impact factors in the electronic device that affect the application or the application is turned on, and each impact factor has different degrees of influence on different applications, and the impact degree can be weighted. Said.
  • the plurality of weighting items may include time, location, inter-application logic order, application switching duration, and device status.
  • the device status includes a headset status and a sensor status.
  • a data collection and statistics system may be set in the electronic device for collecting state information of each weight item in each of the opened applications when the user opens the application, and corresponding statistics are performed. .
  • the data acquisition system can collect the following information and record accordingly:
  • the state information corresponding to the time weight item when the user starts the application in the historical period is collected to collect the historical state information corresponding to the time weight item.
  • the time may include a week and a time of day. For example, by collecting the time when the WeChat application is opened in the past month, it is counted that the WeChat application is turned on from 7:00 to 23:00 every day.
  • the location weighting item when the user opens the application in the historical period can be collected by the global positioning system on the electronic device, or the base station information connected by the electronic device, or the service set identifier of the wireless network connection of the electronic device.
  • Corresponding state information to collect historical state information of the location weight item For example, by collecting the location where the QQ application is opened in the past month, the location where the WeChat application is opened is counted as the way between the home, the company, the home, and the company.
  • the state information corresponding to the headset state weight item when the user starts the application in the historical period is collected to collect the historical state information of the headset state weight item.
  • the headset state is in a plugged and unplugged state, and the headset state mainly affects the probability that the user opens the video and audio application.
  • the state information corresponding to the sensor state weight item when the user starts the application in the historical period is collected to collect the historical state information of the sensor state weight item.
  • the sensor may include a fingerprint sensor, a proximity sensor, an infrared sensor, a gravity sensor, a triaxial acceleration sensor, and the like. There are certain logical relationships between different sensor states in an electronic device and different open applications. For example, when the user opens the Need for Speed application, it will trigger a gravity sensor or a three-axis acceleration sensor to achieve dynamic effects during the game.
  • Step S202 Acquire historical state information and current weights of multiple weight items in the electronic device.
  • the data collection and statistics system acquires historical state information of a plurality of weight items in the electronic device based on a pre-stated user history of the application on the electronic device.
  • the weight items may include, but are not limited to, the current time when the user starts an application, the current location where the user opens an application, the logical order between applications, the duration of the application switching, the headset status of the electronic device, the working status of various sensors of the electronic device, and the like.
  • the prediction system obtains the current weight of each weight item based on the initial weights of the respective weight items and the degree of influence of each weight item in the historical prediction results.
  • the historical state information of the plurality of weight items is derived from state information of each of the pre-acquired weight items in the history opening.
  • the current weight is derived from the initial state of the electronic device to the extent that each weight item affects the opened application during use.
  • the weight of each weighting terms may be administered according to the a priori knowledge of the value of a 11, a 21, to a m1, wherein a m1 to m represents the m-th weighting terms, a m1 represents the m-th The initial weight of the weight item.
  • the weight is compensated or corrected.
  • the initial weight of the headphone weight item is set slightly higher than the initial weight of the other weight item.
  • the weight may be adjusted in each iteration so that the current weight obtained in the next prediction is closer to the actual usage habit of the user. For example, if there are 10 weighting items, the initial weight of each weight item can be set to 10%. In the subsequent iterations, the system slowly adjusts, and finally approaches the user's actual usage habits.
  • a feedback adjustment prediction system can be set in the electronic device, in the prediction system Before the system needs to predict the application that the user is about to be opened at the next moment, it needs to obtain the historical state information of the multiple weight items in the electronic device and the current weight, in preparation for the upcoming prediction behavior. It can be understood that the triggering timing of the predicted behavior can be triggered based on the current time, or the current location, or a change in the current device state.
  • Step S203 calculating, according to all the historical state information that each of the plurality of weighting items occurs when each application history is turned on, calculating a probability that each weighting item is individually corresponding to each application being turned on, to obtain each The independent prediction result corresponding to the weight item.
  • each weight item has different degrees of influence on different applications, so each weight item has a corresponding independent prediction result for each application.
  • the historical state information of the first to n-1th times of each of the m weighting items may be used, Calculating, at the nth time, each weight item individually corresponds to a probability that each application is turned on, to obtain independent prediction results corresponding to the m weight items respectively being r 1n to r mn ;
  • n and n are both positive integers greater than or equal to 1.
  • r 1n refers to the independent prediction result of the first factor in the nth prediction
  • r mn refers to the independent prediction result of the mth factor in the nth prediction.
  • Step S204 predicting an application to be started according to the independent prediction result and the weighting of the current weight to obtain a target prediction result.
  • the target prediction result is a probability that is ultimately given based on the influence of the weight of the ownership on the application, and needs to be combined with the weight calculated by the separately calculated probability and the corresponding current weight of the application corresponding to each weight item. To determine the final probability that each app is turned on, to predict which app is about to be opened.
  • step S204 can be implemented by performing step S2041 to step S2042, specifically:
  • Step S2041 Calculate, according to the independent prediction result corresponding to the plurality of weight items and the weighting of the current weight, a probability that each application of the plurality of applications is turned on under the influence of the plurality of weight items.
  • the current weights corresponding to the m weighting items are a 1n to a mn respectively .
  • the independent prediction results corresponding to the m weighting items and the weighting of the current weights may be used. Calculating a probability r n that each application of the plurality of applications is turned on under the influence of the m weight items, wherein the r n is equal to the independent prediction result r 1n corresponding to the first weight item multiplied by the current weight a 1n to The independent prediction result r mn corresponding to the m- th weight term is multiplied by the sum of the current weights a mn , and the calculation formula of r n is as follows:
  • r n a 1n * r 1n + a 2n * r 2n + ... + a mn * r mn .
  • the first weight term is time, assuming that the forecast is only 60% of the independent forecast calculated from the time weight term, the weight of the time weight term is 30%, and the second weight is the location.
  • a prediction only considers the location weight item to calculate the independent prediction result is 30%
  • the location weight item weight is 30%
  • the third weight item is the headset status, assuming that a prediction is only considered by the location headset item.
  • the independent prediction result is 90%
  • the weight of the headphone state weighting item is 40%
  • the probability that the music application is turned on is 63%
  • the probability that the phone application is turned on is 23%
  • the probability that the WeC application is turned on is 67%.
  • Step S2042 The application that reaches the second threshold in the plurality of applications is predicted to be an application to be opened to obtain a target prediction result.
  • the music application with the probability of being turned on is 51% and the WeChat application with the probability of being turned on being 67% predicted to be the application to be opened, and the target prediction result is obtained.
  • WeChat and music applications are set to 50%, the music application with the probability of being turned on is 51% and the WeChat application with the probability of being turned on being 67% predicted to be the application to be opened, and the target prediction result is obtained.
  • the first to nth target prediction results are recorded in the table, and the application information that is actually opened and the weight corresponding to the actually opened application information after each prediction is performed. Status information related to the item.
  • the application that is predicted to be opened may include an application in the form of software, such as various client applications, and may also include hardware modules existing in the electronic device, such as fingerprints. Sensor, proximity sensor, etc.
  • Step S205 Perform preload processing on the application that is predicted to be turned on.
  • resource preloading may be performed on the application in the target prediction result to shorten the time when the application is actually opened.
  • the device resources in the electronic device may be detected before the pre-loading process is performed on the application that is predicted to be turned on. For example, detecting whether the memory resource of the electronic device meets the storage space requirement required for the application preloading, and when satisfied, performing preload processing on the application that is predicted to be opened. For example, detecting whether the remaining power of the electronic device is greater than a preset power, and if so, performing preload processing on the application that is predicted to be turned on.
  • Step S206 Adjust the weights of the plurality of weight items according to the actually opened application to improve the accuracy of the target prediction result.
  • the prediction system with feedback adjustment in the electronic device adjusts the weight of each weight item according to the final selection result. After a plurality of feedback adjustments, the weights of the weighting items of the prediction system finally converge, so that the prediction result is closer to the application that the user actually selects to open, and the accuracy of the prediction result is improved.
  • the weighting items affecting multiple applications in an electronic device include time, location, and headset status.
  • the independent prediction result calculated by considering only the time weight item is 60%
  • the weight of the time weight item is 30%
  • the independent prediction result calculated by considering only the location weight item is 30%.
  • the weight of the weight item is 30%.
  • the independent prediction result calculated by considering only the location headset item is 90%
  • the weight of the headset status weight item is 40%.
  • the application to be opened is predicted to be a music application
  • the actually opened application is a music application
  • the first threshold is set to 50%
  • the probability of predicting that the music application is turned on in the independent prediction result is increased.
  • Greater than 50% of the weighting item corresponding to the weight that is, increasing the time weight item and the headset status
  • the weight corresponding to the weight item for example, the corresponding increase of 1%
  • the weight of the time weight item is adjusted to 31%
  • the weight of the headphone state weight item is adjusted to 41%
  • the probability that the actually opened application is opened is predicted.
  • the weights corresponding to other weight items smaller than the first threshold may not be adjusted, for example, the weight of the location weight item remains at 30%.
  • the actually opened application is the same as the application that is predicted to be turned on, reducing a probability that the actual predicted application is turned on is lower than the first threshold in the independent prediction result.
  • the weight corresponding to the weight item is lower than the first threshold in the independent prediction result.
  • the application to be opened is predicted to be a music application
  • the actually opened application is a video application
  • the first threshold is set to 50%
  • reducing the probability that the independent prediction result predicts that the music application is turned on The weight corresponding to the weight item less than 50%, that is, the weight of the time weight item is reduced, for example, the corresponding reduction is 1%, for example, the weight of the location weight item is reduced to 29%.
  • the embodiment of the present invention calculates the historical state information of the plurality of weight items in the electronic device and the current weight, and calculates, according to the historical state information of the plurality of weight items, the probability that each weight item individually corresponds to the opening of each application.
  • the electronic device is gradually adapted to the user's usage habits, and preloads the application that is predicted to be opened, shortens the time when the application is opened, and improves the convenience of use.
  • FIG. 6 is a schematic structural diagram of an application control device according to an embodiment of the present invention.
  • the application control device 30 includes an acquisition module 32, a calculation module 33, a prediction module 34, and an adjustment module 36.
  • the obtaining module 32 is configured to acquire historical state information and current weights of multiple weight items in the electronic device.
  • the obtaining module 32 acquires historical state information of multiple weighting items in the application based on a pre-stated historical opening situation of the application on the electronic device by the user.
  • the weighting items may include, but are not limited to, the current time when the user starts an application, the current location where the user opens an application, the logical sequence between applications, the duration of the application switching, the headset status of the electronic device, and the various sensors of the electronic device. State, etc.
  • the obtaining module 32 obtains the current weights of the respective weight items based on the initial weights of the respective weight items and the degree of influence of the respective weight items in the historical prediction results.
  • the historical state information of the plurality of weight items is derived from state information of each of the pre-acquired weight items in the history opening.
  • the current weight is derived from the initial state of the electronic device to the extent that each weight item affects the opened application during use.
  • the calculating module 33 is configured to calculate, according to the historical state information of the multiple weight items, a probability that each weight item is individually corresponding to each application being turned on, to obtain an independent prediction result corresponding to each weight item.
  • each weight item has different degrees of influence on different applications, so each weight item has a corresponding independent prediction result for each application.
  • the prediction module 34 is configured to predict an application to be started according to the independent prediction result and the weight of the current weight to obtain a target prediction result.
  • the target prediction result is based on the probability that the weight of the ownership item is finally given, and the prediction module 34 needs to combine the probability calculated separately from the application corresponding to each weight item with the corresponding current right.
  • the weighted value of the value to determine the final probability that each application is turned on to predict the application to be opened.
  • the adjusting module 36 is configured to adjust weights of the plurality of weight items according to an actually opened application to improve accuracy of the target prediction result.
  • the adjustment module 36 reversely returns the weight of each weight item according to the final selection result. After repeated feedback adjustments, the weights of the respective weighting items are finally converged, so that the prediction result is closer to the application that the user actually selects to open, and the accuracy of the prediction result is improved.
  • FIG. 7 is another schematic structural diagram of an application control apparatus according to an embodiment of the present invention.
  • the application control device 30 includes an acquisition module 31, an acquisition module 32, a calculation module 33, a prediction module 34, a preload module 35, and an adjustment module 36.
  • the collecting module 31 is configured to collect state information corresponding to each weight item of the plurality of weight items when the user opens the application in the historical period, to collect historical state information of the plurality of weight items.
  • each user has different usage habits and usage preferences for applications on the electronic device.
  • the user's usage habits on the application on the electronic device will still follow a certain rule, which is traceable. Therefore, the embodiment of the present invention searches for the usage rule of the user for the application based on the historical usage of the user.
  • the multiple weighting items are respective impact factors in the electronic device that affect the application or the application is turned on, and each impact factor has different degrees of influence on different applications, and the impact degree can be weighted. Said.
  • the plurality of weighting items may include time, location, inter-application logic order, application switching duration, and device status.
  • the device status includes a headset status and a sensor status.
  • the collecting module 31 collects state information corresponding to the time weight item when the user starts the application in the historical period, to collect historical state information corresponding to the time weight item.
  • the time may include a week and a time of day.
  • the collection module 31 may be opened by the global positioning system on the electronic device, or the base station information connected by the electronic device, or the service set identifier of the wireless network connection of the electronic device.
  • the status information corresponding to the location weight item is used to calculate the historical status information of the location weight item.
  • the collection module 31 collects state information corresponding to the headset state weight item when the user starts the application in the historical period, to collect historical state information of the headset state weight item.
  • the headset state is in a plugged and unplugged state, and the headset state mainly affects the probability that the user opens the video and audio application.
  • the collecting module 31 collects state information corresponding to the sensor state weight item when the user starts the application in the historical period to collect historical state information of the sensor state weight item.
  • the sensor may include a fingerprint sensor, a proximity sensor, an infrared sensor, a gravity sensor, a triaxial acceleration sensor, and the like. There are certain logical relationships between different sensor states in an electronic device and different open applications.
  • the obtaining module 32 is configured to acquire historical state information and current weights of multiple weight items in the electronic device.
  • the historical opening situation is used to obtain historical state information of multiple weight items in the electronic device.
  • the weight items may include, but are not limited to, the current time when the user starts an application, the current location where the user opens an application, the logical order between applications, the duration of the application switching, the headset status of the electronic device, the working status of various sensors of the electronic device, and the like.
  • the obtaining module 32 obtains the current weights of the respective weight items based on the initial weights of the respective weight items and the degree of influence of the respective weight items in the historical prediction results.
  • the historical state information of the plurality of weight items is derived from state information of each of the pre-acquired weight items in the history opening.
  • the current weight is derived from the initial state of the electronic device to the extent that each weight item affects the opened application during use.
  • the weight of each weighting terms may be administered according to the a priori knowledge of the value of a 11, a 21, to a m1, wherein a m1 to m represents the m-th weighting terms, a m1 represents the m-th The initial weight of the weight item.
  • the weight is compensated or corrected.
  • the initial weight of the headphone weight item is set slightly higher than the initial weight of the other weight item.
  • the weight may be adjusted in each iteration so that the current weight obtained in the next prediction is closer to the actual usage habit of the user.
  • the obtaining module 32 needs to acquire historical state information and current weights of multiple weight items in the electronic device, and perform for the upcoming prediction behavior. ready. It can be understood that the triggering timing of the predicted behavior can be triggered based on the current time, or the current location, or a change in the current device state.
  • the calculating module 33 is configured to calculate, according to all historical state information that each of the plurality of weighting items occurs when each application history is turned on, calculate a probability that each weight item individually corresponds to each application being opened To get the independent prediction result corresponding to each weight item.
  • each weight item has different degrees of influence on different applications, so each weight item has a corresponding independent prediction result for each application.
  • the calculating module 33 is configured to calculate, according to all historical state information that each of the plurality of weighting items occurs when each application history is turned on, each weighting item individually corresponds to each The probability that an application is turned on to obtain an independent prediction result corresponding to each weight item.
  • the calculating module 33 may be based on the first to n-1th times of each of the m weighting items.
  • n and n are both positive integers greater than or equal to 1.
  • r 1n refers to the independent prediction result of the first factor in the nth prediction
  • r mn refers to the independent prediction result of the mth factor in the nth prediction.
  • r 1n is calculated based on the actual opening results of the previous 1st to the n-1th.
  • the prediction module 34 is configured to predict an application to be started according to the independent prediction result and the weight of the current weight to obtain a target prediction result.
  • the target prediction result is based on the probability that the weight of the ownership item is finally given, and the prediction module 34 needs to combine the probability calculated separately from the application corresponding to each weight item with the corresponding current right.
  • the weighted value of the value to determine the final probability that each application is turned on to predict the application to be opened.
  • the prediction module 34 further includes a calculation sub-module 341 and a prediction sub-module 342.
  • the calculation sub-module 341 is configured to calculate, according to the independent prediction result corresponding to the multiple weight items and the weight of the current weight, each application of the multiple applications is affected by the multiple weight items The probability of opening.
  • the current weights corresponding to the m weight items are a 1n to a mn respectively .
  • the calculation submodule 341 may respectively perform independent prediction results corresponding to the m weight items and Weighting of current weights, calculating a probability r n that each application of the plurality of applications is turned on under the influence of the m weight items, wherein the r n is equal to the independent prediction result r 1n corresponding to the first weight item multiplied by The independent prediction result r mn corresponding to the current weight a 1n to the mth weight item is multiplied by the sum of the current weights a mn , and the calculation formula of r n is as follows:
  • r n a 1n * r 1n + a 2n * r 2n + ... + a mn * r mn .
  • the prediction sub-module 342 is configured to predict, by the application that the corresponding opened probability of the multiple applications reaches the second threshold, that the application is to be opened, to obtain the target prediction result.
  • the application that is predicted to be opened may include an application in the form of software, such as various client applications, and may also include hardware modules existing in the electronic device, such as fingerprints. Sensor, proximity sensor, etc.
  • the preloading module 35 is configured to perform preload processing on the application that is predicted to be turned on.
  • the pre-loading module 35 may perform resource pre-loading on the application in the target prediction result to shorten the application. The time that was really opened.
  • the device resources in the electronic device may be detected before the pre-loading process is performed on the application that is predicted to be turned on. For example, detecting whether the memory resource of the electronic device meets the storage space requirement required for the application preloading, and when satisfied, the preloading module 35 performs preload processing on the application that is predicted to be opened. For example, detecting whether the remaining power of the electronic device is greater than a preset power, and if so, the preloading module 35 performs preload processing on the application that is predicted to be turned on.
  • the adjusting module 36 is configured to adjust weights of the plurality of weight items according to an actually opened application to improve accuracy of the target prediction result.
  • the adjustment module 36 reversely returns the weight of each weight item according to the final selection result.
  • the weights of the weighting items of the prediction system are finally converged, so that the prediction result is closer to the application that the user actually selects to open, and the accuracy of the prediction result is improved.
  • the adjusting module 36 is configured to: when the actually opened application is the same as the application that is predicted to be turned on, improve the prediction that the actually opened application is predicted by the independent prediction result.
  • the probability of opening is greater than the weight corresponding to the weighting term of the first threshold.
  • the adjusting module 36 is configured to: when the actually opened application is the same as the application that is predicted to be turned on, reduce the prediction that the actually opened application is predicted in the independent prediction result.
  • the probability of being turned on is less than the weight corresponding to the weight term of the first threshold.
  • An embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor calling the computer program stored in the memory, executing the program An application control method according to any of the embodiments of the invention.
  • the electronic device can be a device such as a smartphone or a tablet.
  • the electronic device 400 includes a processor 401 having one or more processing cores, and having one or more computers.
  • a memory 402 of the storage medium and a computer program stored on the memory 402 and operable on the processor 401 are read.
  • the processor 401 is electrically connected to the memory 402. It will be understood by those skilled in the art that the electronic device structure illustrated in FIG. 8 does not constitute a limitation to the electronic device, and may include more or less components than those illustrated, or a combination of certain components, or different component arrangements.
  • the processor 401 is a control center of the electronic device 400, which connects various parts of the entire electronic device using various interfaces and lines, executes the electronic by running or loading an application stored in the memory 402, and calling data stored in the memory 402.
  • the various functions and processing data of the device enable overall monitoring of the electronic device.
  • the processor 401 in the electronic device 400 loads the instructions corresponding to the process of one or more applications into the memory 402 according to the following steps, and is stored in the memory by the processor 401.
  • the application in 402 to implement various functions:
  • the weights of the plurality of weighting items are adjusted to improve the accuracy of the target prediction result according to the actually opened application.
  • the processor 401 is configured to adjust, according to the actually opened application, the weights of the multiple weight items to improve the accuracy of the target prediction result, including:
  • the weight of the independent prediction result that predicts that the actually opened application is turned on is greater than the first threshold And decreasing a weight corresponding to the weight item in the independent prediction result that predicts that the probability that the actually opened application is turned on is less than the first threshold.
  • the processor 401 is configured to calculate, according to the historical state information of the multiple weight items, each probability item individually corresponding to a probability that each application is turned on, to obtain each weight item pair.
  • Independent forecast results should include:
  • each weighting item individually corresponds to a probability that each application is turned on, to obtain a corresponding weight item Independent prediction results.
  • the processor 401 is configured to: according to the independent prediction result and the weight of the current weight, predict an application to be started to obtain a target prediction result, including:
  • An application that reaches a second threshold in the plurality of applications is predicted to be an application to be opened to obtain a target prediction result.
  • the processor 401 is configured to: before acquiring the historical state information of the multiple weight items in the electronic device and the current weight, further comprising:
  • the state information corresponding to each weight item in the plurality of weight items when the user starts the application in the historical period is collected to collect historical state information of the plurality of weight items.
  • the plurality of weighting items include time, location, inter-application logic order, application switching duration, and device status.
  • the processor 401 is configured to collect state information corresponding to each weight item of the plurality of weight items when the user starts the application in the collecting historical period, to collect historical state information of the multiple weight items.
  • the processor 401 for the device state includes a headset state and a sensor state.
  • the processor 401 is configured to: before the adjusting, according to the actually opened application, the weights of the multiple weight items to improve the accuracy of the target prediction result, the method further includes:
  • the application that is predicted to be opened is preloaded.
  • the processor 401 is configured to enter the application that is about to be opened for the prediction. Before the line preload processing, it also includes:
  • Detecting device resources in the electronic device where the device resources include a memory resource and a remaining power.
  • the electronic device 400 may further include a display screen, a wireless fidelity (WiFi) module, a radio frequency circuit, an input unit, an audio circuit, a sensor including a camera, a Bluetooth module, and a power source. Let me repeat.
  • WiFi wireless fidelity
  • the application control device belongs to the same concept as the application control method in the foregoing embodiment, and any method provided in the embodiment of the application control method may be run on the application control device.
  • the specific implementation process is described in the application control method embodiment, and details are not described herein again.
  • the computer program can be stored in a computer readable storage medium, such as in a memory of the computer device, and executed by at least one processor within the computer device, and can include, as described, application control during execution The flow of an embodiment of the method.
  • the storage medium may be a magnetic disk, an optical disk, a read only memory (ROM), a random access memory (RAM), or the like.
  • each functional module may be integrated into one processing chip, or each module may exist physically separately, or two or more modules may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated module if implemented in the form of a software functional module and sold or used as a standalone product, may also be stored in a computer readable storage medium, such as a read only memory, a magnetic disk or an optical disk, etc. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种应用控制方法、应用控制装置、存储介质及电子设备，所述方法包括：获取电子设备中多个权重项的历史状态信息以及当前权值，根据历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果，根据独立预测结果以及当前权值的加权，预测即将被开启的应用，根据实际被开启的应用，对多个权重项的权值进行调整以提高预测即将被开启的应用的准确性。

Description

应用控制方法、装置、存储介质及电子设备 技术领域
本发明涉及计算机通信技术领域，尤其涉及一种应用控制方法、装置、存储介质及电子设备。
背景技术
随着智能电子设备上应用数量的井喷式发展，每个电子设备上可能都安装了数十甚至上百个应用。在如此众多的应用中，如何准确地判断用户即将要开启的应用，并对这些应用进行资源预加载，已经越来越受到业界的普遍关注。
发明内容
本发明实施例提供一种应用控制方法、装置、存储介质及电子设备，可以更加精确地预测用户即将选择开启的应用。
第一方面，本发明实施例提供一种应用控制方法，应用于电子设备中，包括：
获取电子设备中多个权重项的历史状态信息以及当前权值；
根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果；
根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果；
根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性。
第二方面，本发明实施例还提供了一种应用控制装置，包括：
获取模块，用于获取电子设备中多个权重项的历史状态信息以及当前权值；
计算模块，用于根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果；
预测模块，用于根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果；
调整模块，用于根据实际被开启的应用，对所述多个权重项的权值进行调 整以提高所述目标预测结果的准确性。
第三方面，本发明实施例还提供一种存储介质，其上存储有计算机程序，所述计算机程序被处理器调用以执行本发明任一实施例所述的应用控制方法。
第四方面，本发明实施例还提供一种电子设备，包括存储器，处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器调用所述存储器中存储的所述计算机程序，执行本发明任一实施例所述的应用控制方法。
附图说明
为了更清楚地说明本发明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发明的一些实施例，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为本发明实施例提供的电子设备与用户间的交互示意图。
图2为本发明实施例提供的应用控制方法的流程示意图。
图3为本发明实施例提供的应用控制方法的另一流程示意图。
图4为本发明实施例提供的应用控制方法的历史状态信息记录表。
图5为本发明实施例提供的应用控制方法的相关记录表。
图6为本发明实施例提供的应用控制装置的结构示意图。
图7为本发明实施例提供的应用控制装置的另一结构示意图。
图8为本发明实施例提供的电子设备的结构示意图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明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发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，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，都属于本发明保护的范围。
本发明实施例提供一种应用控制方法、装置、存储介质及电子设备。以下将分别进行详细说明。
本发明实施例提供的一种应用控制方法的执行主体，可以为本发明实施例提供的一种应用控制装置，或者集成了所述应用控制装置的电子设备(譬如台 式电脑、笔记本、掌上电脑、平板电脑、智能手机等)，所述应用控制装置可以采用硬件或者软件的方式实现。
请参阅图1，图1为本发明实施例提供的电子设备与用户间的交互示意图。其中，电子设备包括数据采集统计***与带回馈调整的预测***。所述数据采集统计***用于采集用户开启某应用时对应的各权重项数据，并做出相应的统计。在所述预测***预测用户将即开启的应用时，所述预测***根据各权重项数据与各权重项的当前权值计算出各种预测结果。在用户最终选择开启某应用后，所述预测***对预测结果和用户最终选择开启的应用进行结果分析，并根据分析结果反馈调整各权重项的权值。经过多次反馈调整后，所述预测***的各个权重项的权值最终收敛，使得预测结果更接近于用户实际选择开启的应用，提升预测结果的准确性。
请参阅图2，图2为本发明实施例提供的一种应用控制方法的流程示意图。所述方法包括：
步骤S101，获取电子设备中多个权重项的历史状态信息以及当前权值。
可以理解的是，每个用户对电子设备上的应用的使用习惯以及使用偏好各不相同。但是具体到一个用户时，该用户对电子设备上的应用的使用习惯仍然会遵循一定规律，是有迹可循的。因此，本发明实施例基于用户的历史使用情况寻找该用户对应用的使用规律。
在一些实施例中，数据采集统计***基于预先统计的用户对电子设备上的应用的历史开启情况，来获取电子设备中多个权重项的历史状态信息。权重项可以包括但不限于用户开启某应用的当前时间、用户开启某应用的当前地点、应用间逻辑顺序、应用切换时长、电子设备的耳机状态、电子设备的各种传感器的工作状态等。
在一些实施例中，预测***基于各权重项的初始权值、以及各个权重项在历史预测结果中的影响程度，来获取各权重项的当前权值。
步骤S102，根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
可以理解的是，针对不同的应用，每个权重项对不同的应用的影响程度是不同的，因此每个权重项针对每一应用都会存在一个对应的独立预测结果。
步骤S103，根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果。
可以理解的是，所述目标预测结果是基于所有权重项对应用的影响最终给出的概率，需结合每个权重项对应的应用中单独计算出来的概率与对应的当前权值的加权值，来确定每个应用被开启的最终概率，以此来预测即将被开启的应用。
步骤S104，根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性。
比如，在用户做出最终选择，对电子设备中的应用程序进行实际开启之后，电子设备会根据最终选择结果，反向回馈调整各个权重项的权值。经过多次的反馈调整后，所述预测***的各个权重项的权值最终收敛，使得预测结果更接近于用户实际选择开启的应用，提升预测结果的准确性。
在一些实施例中，所述根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性，包括：
当所述实际被开启的应用与所述预测即将被开启的应用相同时，提高所述独立预测结果中预测所述实际被开启的应用被开启的概率大于第一阈值的权重项所对应的权值；或者
降低所述独立预测结果中预测所述实际被开启的应用被开启的概率小于第一阈值的权重项所对应的权值。
在一些实施例中，所述根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果，包括：
根据所述多个权重项中每一权重项在每个应用历史被开启时发生的所有历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
在一些实施例中，所述根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果，包括：
根据所述多个权重项分别对应的独立预测结果以及当前权值的加权，计算多个应用中每个应用在所述多个权重项的影响下被开启的概率；
将所述多个应用中对应的被开启的概率达到第二阈值的应用预测为即将被开启的应用，以得到目标预测结果。
在一些实施例中，在所述获取电子设备中多个权重项的历史状态信息以及当前权值之前，还包括：
采集历史时段内用户在开启应用时多个权重项中的每一权重项对应的状态信息，以统计所述多个权重项的历史状态信息。
在一些实施例中，所述采集历史时段内用户在开启应用时多个权重项中的每一权重项对应的状态信息，以统计所述多个权重项的历史状态信息，包括：
通过所述电子设备上的全球定位***、或者所述电子设备连接的基站信息、或者所述电子设备的无线网络连接的服务集标识，采集历史时段内用户在开启应用时地点权重项对应的状态信息，以统计所述地点权重项的历史状态信息。
在一些实施例中，所述设备状态包括耳机状态以及传感器状态。
在一些实施例中，在所述根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性之前，还包括：
对所述预测即将被开启的应用进行预加载处理。
在一些实施例中，在所述对所述预测即将被开启的应用进行预加载处理之前，还包括：
对所述电子设备中的设备资源进行检测，其中所述设备资源包括内存资源与剩余电量。
上述所有可选技术方案，可以采用任意结合形成本发明的可选实施例，在此不再一一赘述。
本发明实施例通过获取电子设备中多个权重项的历史状态信息以及当前权值，根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果，根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果，根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性，以向用户提供更加精准的用户开启应用的预测，从而使得电子设备渐渐适配于用户的使用习惯，提升使用便利性。
请参阅图3至图5，图3为本发明实施例提供的一种应用控制方法的另一流程示意图，图4为本发明实施例提供的应用控制方法的历史状态信息记录表，图5为本发明实施例提供的应用控制方法的相关记录表。所述方法包括：
步骤S201，采集历史时段内用户在开启应用时多个权重项中的每一权重项对应的状态信息，以统计所述多个权重项的历史状态信息。
可以理解的是，每个用户对电子设备上的应用的使用习惯以及使用偏好各不相同。但是具体到一个用户时，该用户对电子设备上的应用的使用习惯仍然会遵循一定规律，是有迹可循的。因此，本发明实施例基于用户的历史使用情况寻找该用户对应用的使用规律。
可以理解的是，所述多个权重项为电子设备中影响应用或者应用程序被开启的各个影响因子，且每个影响因子针对不同的应用的影响程度不一样，所述影响程度可以用权重来表示。
在一些实施例中，所述多个权重项可以包括时间、地点、应用间逻辑顺序、应用切换时长以及设备状态。其中，所述设备状态包括耳机状态以及传感器状态。
比如，可以在所述电子设备中设置一数据采集统计***，用于采集用户在开启应用时各个权重项中的每一权重项在各个被开启的应用中的状态信息，并做出相应的统计。
例如，如图4中显示的表格所示，在用户每开启一个应用时，所述数据采集***可以采集以下信息并做相应记录：
比如，采集历史时段内用户开启应用时时间权重项对应的状态信息，以统计所述时间权重项对应的历史状态信息。所述时间可以包括星期以及时刻。比如通过采集过去一个月内微信应用被打开的时间，以统计出微信应用被开启的时间为每天的7：00至23：00。
比如，可以通过所述电子设备上的全球定位***、或者所述电子设备连接的基站信息、或者所述电子设备的无线网络连接的服务集标识，采集历史时段内用户在开启应用时地点权重项对应的状态信息，以统计所述地点权重项的历史状态信息。比如通过采集过去一个月内QQ应用被打开的地点，以统计出微信应用被开启的地点为家、公司、家与公司之间的途中。
比如，采集历史时段内用户在开启应用时耳机状态权重项对应的状态信息，以统计所述耳机状态权重项的历史状态信息。所述耳机状态为插接和未插接两种状态，所述耳机状态主要影响到用户打开视频、音频类应用的概率。比如，采集历史时段内用户在开启应用时传感器状态权重项对应的状态信息，以统计所述传感器状态权重项的历史状态信息。其中，所述传感器可以包括指纹传感器、接近传感器、红外传感器、重力传感器、三轴加速度传感器等。电子设备中不同的传感器状态与不同的被开启的应用间会存在一定的逻辑关系。比如，用户在开启极品飞车应用时，会触发重力传感器或者三轴加速度传感器，以此来实现游戏过程中的动态效果。
步骤S202，获取电子设备中多个权重项的历史状态信息以及当前权值。
在一些实施例中，数据采集统计***基于预先统计的用户对电子设备上的应用的历史开启情况，来获取电子设备中多个权重项的历史状态信息。权重项可以包括但不限于用户开启某应用的当前时间、用户开启某应用的当前地点、应用间逻辑顺序、应用切换时长、电子设备的耳机状态、电子设备的各种传感器的工作状态等。
在一些实施例中，预测***基于各权重项的初始权值、以及各个权重项在历史预测结果中的影响程度，来获取各权重项的当前权值。
其中，所述多个权重项的历史状态信息来源于预先采集的各权重项在历史开启中的状态信息。所述当前权值来源于电子设备的初始状态至目前为止各个权重项在使用过程中对被开启应用的影响程度。比如在初始状态下，各个权重项的权值可以根据先验知识给予的一些经典值a11，a21，至am1，其中am1的m表示第m个权重项，am1表示第m个权重项的初始权值。随着用户在开启应用的过程中，各权重项在被开启应用中的状态变化，对权值进行补偿或修正。比如，在初始状态下，针对视频或音频类的应用，将耳机权重项的初始权值设置的比其他权重项的初始权值略高。在用户开启应用的过程中，可以在每次迭代中调整权值，以使下一次预测时获取到的当前权值更贴近用户实际使用习惯。比如，有10个权重项，可以将每个权重项的初始权值都定成10％，后续每次迭代中***慢慢调整，最终趋近用户实际使用习惯。
比如，可以在所述电子设备中设置一回馈调整的预测***，在所述预测系 统需要预测用户下一时刻即将被开启的应用之前，需要获取电子设备中多个权重项的历史状态信息以及当前权值，为即将进行的预测行为做准备。可以理解的是，预测行为的触发时机可以基于当前时间，或者当前地点，或者当前设备状态的变化进行触发。
步骤S203，根据所述多个权重项中每一权重项在每个应用历史被开启时发生的所有历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
可以理解的是，针对不同的应用，每个权重项对不同的应用的影响程度是不同的，因此每个权重项针对每一应用都会存在一个对应的独立预测结果。
在一些实施例中，根据所述多个权重项中每一权重项在每个应用历史被开启时发生的所有历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
比如，其中所述多个权重项包括m个权重项，在第n次预测之前，可以根据所述m个权重项中每一权重项的第1次至第n-1次的历史状态信息，在第n次计算每一权重项单独对应于每个应用被开启的概率，以得到所述m个权重项分别对应的独立预测结果为r1n至rmn；
其中，m与n均为大于或等于1的正整数。
可以理解的是，r1n是指第1个因子在第n次预测的独立预测结果，rmn是指第m个因子在第n次预测的独立预测结果。比如，r1n是基于之前的第1次到第n-1次的实际开启结果统计出来的。例如，计算某个音乐应用的耳机状态权重项时，n＝11，所述音乐应用之前被打开的10次中，耳机状态为插接状态的有9次，耳机状态为未插接状态的有1次，则可以根据所述耳机状态权重项前10次的历史状态信息计算出r1n等于90％。
步骤S204，根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果。
可以理解的是，所述目标预测结果是基于所有权重项对应用的影响最终给出的概率，需结合每个权重项对应的应用中单独计算出来的概率与对应的当前权值的加权值，来确定每个应用被开启的最终概率，以此来预测即将被开启的应用。
在一些实施例中，所述步骤S204可以通过执行步骤S2041至步骤S2042来实现，具体为：
步骤S2041，根据所述多个权重项分别对应的独立预测结果以及当前权值的加权，计算多个应用中每个应用在所述多个权重项的影响下被开启的概率。
比如，所述m个权重项分别对应的当前权值为a1n至amn，当进行第n次预测时，可以根据所述m个权重项分别对应的独立预测结果以及当前权值的加权，计算多个应用中每个应用在所述m个权重项的影响下被开启的概率rn，其中所述rn等于第1权重项对应的独立预测结果r1n乘以当前权值a1n至第m权重项对应的独立预测结果rmn乘以当前权值amn之和，rn的计算公式如下：
rn＝a1n*r1n+a2n*r2n+...+amn*rmn。
例如，m＝3，第一个权重项是时间，假设某次预测只考虑时间权重项计算出来的独立预测结果是60％，时间权重项的权值是30％，第二个权重项是地点，假设某次预测只考虑地点权重项计算出来的独立预测结果是30％，地点权重项的权值是30％，第三个权重项是耳机状态，假设某次预测只考虑地点耳机项计算出来的独立预测结果是90％，耳机状态权重项的权值是40％，rn＝60％*30％+30％*30％+90％*40％＝63％。
比如，在第n次预测时，计算出音乐应用被开启的概率为63％，电话应用被开启的概率为23％，微信应用被开启的概率为67％。
步骤S2042，将所述多个应用中对应的被开启的概率达到第二阈值的应用预测为即将被开启的应用，以得到目标预测结果。
比如，所述第二阈值设置为50％，则可以将被开启的概率为51％的音乐应用以及被开启的概率为67％的微信应用预测为即将被开启的应用，则得到目标预测结果为微信和音乐应用。
例如，如图5所示，表中记录了第1次至第n次的目标预测结果，以及每次进行预测之后，实际被开启的应用信息以及所述实际被开启的应用信息所对应的权重项相关的状态信息。
在一些实施例中，所述预测即将被开启的应用可以包括软件形式的应用程序，比如各类客户端应用，也可以包括电子设备内存在的硬件模组，比如指纹 传感器，接近传感器等。
步骤S205，对所述预测即将被开启的应用进行预加载处理。
可以理解的是，在得到目标预测结果之后，当所述目标预测结果为即将被打开的应用时，可以对所述目标预测结果中的应用进行资源预加载，以缩短应用真正被打开的时间。
在一些实施例中，可以在所述对所述预测即将被开启的应用进行预加载处理之前，对所述电子设备中的设备资源进行检测。比如检测所述电子设备的内存资源是否满足应用预加载时所需的存储空间需求，当满足时，对所述预测即将被开启的应用进行预加载处理。比如检测所述电子设备的剩余电量是否大于预设电量，若是，则对所述预测即将被开启的应用进行预加载处理。
步骤S206，根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性。
比如，在用户做出最终选择，对电子设备中的应用程序进行实际开启之后，电子设备中带回馈调整的预测***会根据最终选择结果，反向回馈调整各个权重项的权值。经过多次的反馈调整后，所述预测***的各个权重项的权值最终收敛，使得预测结果更接近于用户实际选择开启的应用，提升预测结果的准确性。
在一些实施例中，当所述实际被开启的应用与所述预测即将被开启的应用相同时，提高所述独立预测结果中预测所述实际被开启的应用被开启的概率大于第一阈值的权重项所对应的权值。
比如，某一电子设备中影响多个应用的权重项包括时间、地点、耳机状态。比如，针对音乐应用，本次预测只考虑时间权重项计算出来的独立预测结果是60％，时间权重项的权值是30％，只考虑地点权重项计算出来的独立预测结果是30％，地点权重项的权值是30％，只考虑地点耳机项计算出来的独立预测结果是90％，耳机状态权重项的权值是40％，则结合所有权重项，则预测音乐应用即将被开启的概率＝60％*30％+30％*30％+90％*40％＝63％。
若预测即将被开启的应用为音乐应用，当实际被开启的应用为音乐应用时，且当第一阈值设定为50％时，提高所述独立预测结果中预测所述音乐应用被开启的概率大于50％的权重项所对应的权值，即提高时间权重项和耳机状态 权重项所对应的权值，比如对应提高1％，将时间权重项的权值调整为31％，耳机状态权重项的权值调整为41％，预测所述实际被开启的应用被开启的概率小于第一阈值的其他权重项所对应的权值可以不做调整，比如地点权重项的权值保持为30％。
在一些实施例中，当所述实际被开启的应用与所述预测即将被开启的应用相同时，降低所述独立预测结果中预测所述实际被开启的应用被开启的概率小于第一阈值的权重项所对应的权值。
若预测即将被开启的应用为音乐应用，当实际被开启的应用为视频应用时，且当第一阈值设定为50％时，降低所述独立预测结果中预测所述音乐应用被开启的概率小于50％的权重项所对应的权值，即降低时间权重项的权值，比如对应降低1％，比如地点权重项的权值降低为29％。
本发明实施例通过获取电子设备中多个权重项的历史状态信息以及当前权值，根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果，根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果，并对所述预测即将被开启的应用进行预加载处理，根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性，以向用户提供更加精准的用户开启应用的预测，从而使得电子设备渐渐适配于用户的使用习惯，并且对预测即将被开启的应用进行预加载，缩短应用被开启的时间，提升使用便利性。
本发明实施例还提供一种应用控制装置，如图6所示，图6为本发明实施例提供的一种应用控制装置的结构示意图。所述应用控制装置30包括获取模块32，计算模块33，预测模块34，以及调整模块36。
其中，所述获取模块32，用于获取电子设备中多个权重项的历史状态信息以及当前权值。
可以理解的是，所述获取模块32基于预先统计的用户对电子设备上的应用的历史开启情况，来获取应用中多个权重项的历史状态信息。权重项可以包括但不限于用户开启某应用的当前时间、用户开启某应用的当前地点、应用间逻辑顺序、应用切换时长、电子设备的耳机状态、电子设备的各种传感器的工 作状态等。
在一些实施例中，所述获取模块32基于各权重项的初始权值、以及各个权重项在历史预测结果中的影响程度，来获取各权重项的当前权值。
其中，所述多个权重项的历史状态信息来源于预先采集的各权重项在历史开启中的状态信息。所述当前权值来源于电子设备的初始状态至目前为止各个权重项在使用过程中对被开启应用的影响程度。
所述计算模块33，用于根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
可以理解的是，针对不同的应用，每个权重项对不同的应用的影响程度是不同的，因此每个权重项针对每一应用都会存在一个对应的独立预测结果。
所述预测模块34，用于根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果。
可以理解的是，所述目标预测结果是基于所有权重项对应用的影响最终给出的概率，所述预测模块34需结合每个权重项对应的应用中单独计算出来的概率与对应的当前权值的加权值，来确定每个应用被开启的最终概率，以此来预测即将被开启的应用。
所述调整模块36，用于根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性。
比如，在用户做出最终选择，对电子设备中的应用程序进行实际开启之后，所述调整模块36会根据最终选择结果，反向回馈调整各个权重项的权值。经过多次的反馈调整后，使得各个权重项的权值最终收敛，使得预测结果更接近于用户实际选择开启的应用，提升预测结果的准确性。
请参阅图7，图7为本发明实施例提供的一种应用控制装置的另一结构示意图。所述应用控制装置30包括采集模块31，获取模块32，计算模块33，预测模块34，预加载模块35，以及调整模块36。
其中，所述采集模块31，用于采集历史时段内用户在开启应用时多个权重项中的每一权重项对应的状态信息，以统计所述多个权重项的历史状态信息。
可以理解的是，每个用户对电子设备上的应用的使用习惯以及使用偏好各不相同。但是具体到一个用户时，该用户对电子设备上的应用的使用习惯仍然会遵循一定规律，是有迹可循的。因此，本发明实施例基于用户的历史使用情况寻找该用户对应用的使用规律。
可以理解的是，所述多个权重项为电子设备中影响应用或者应用程序被开启的各个影响因子，且每个影响因子针对不同的应用的影响程度不一样，所述影响程度可以用权重来表示。
在一些实施例中，所述多个权重项可以包括时间、地点、应用间逻辑顺序、应用切换时长以及设备状态。其中，所述设备状态包括耳机状态以及传感器状态。
比如，所述采集模块31采集历史时段内用户开启应用时时间权重项对应的状态信息，以统计所述时间权重项对应的历史状态信息。所述时间可以包括星期以及时刻。
比如，所述采集模块31可以通过所述电子设备上的全球定位***、或者所述电子设备连接的基站信息、或者所述电子设备的无线网络连接的服务集标识，采集历史时段内用户在开启应用时地点权重项对应的状态信息，以统计所述地点权重项的历史状态信息。
比如，所述采集模块31采集历史时段内用户在开启应用时耳机状态权重项对应的状态信息，以统计所述耳机状态权重项的历史状态信息。所述耳机状态为插接和未插接两种状态，所述耳机状态主要影响到用户打开视频、音频类应用的概率。
比如，所述采集模块31采集历史时段内用户在开启应用时传感器状态权重项对应的状态信息，以统计所述传感器状态权重项的历史状态信息。其中，所述传感器可以包括指纹传感器、接近传感器、红外传感器、重力传感器、三轴加速度传感器等。电子设备中不同的传感器状态与不同的被开启的应用间会存在一定的逻辑关系。
所述获取模块32，用于获取电子设备中多个权重项的历史状态信息以及当前权值。
可以理解的是，所述获取模块32基于预先统计的用户对电子设备上的应 用的历史开启情况，来获取电子设备中多个权重项的历史状态信息。权重项可以包括但不限于用户开启某应用的当前时间、用户开启某应用的当前地点、应用间逻辑顺序、应用切换时长、电子设备的耳机状态、电子设备的各种传感器的工作状态等。
在一些实施例中，所述获取模块32基于各权重项的初始权值、以及各个权重项在历史预测结果中的影响程度，来获取各权重项的当前权值。
其中，所述多个权重项的历史状态信息来源于预先采集的各权重项在历史开启中的状态信息。所述当前权值来源于电子设备的初始状态至目前为止各个权重项在使用过程中对被开启应用的影响程度。比如在初始状态下，各个权重项的权值可以根据先验知识给予的一些经典值a11，a21，至am1，其中am1的m表示第m个权重项，am1表示第m个权重项的初始权值。随着用户在开启应用的过程中，各权重项在被开启应用中的状态变化，对权值进行补偿或修正。比如，在初始状态下，针对视频或音频类的应用，将耳机权重项的初始权值设置的比其他权重项的初始权值略高。在用户开启应用的过程中，可以在每次迭代中调整权值，以使下一次预测时获取到的当前权值更贴近用户实际使用习惯。
比如，在所述预测***需要预测用户下一时刻即将被开启的应用之前，所述获取模块32需要获取电子设备中多个权重项的历史状态信息以及当前权值，为即将进行的预测行为做准备。可以理解的是，预测行为的触发时机可以基于当前时间，或者当前地点，或者当前设备状态的变化进行触发。
所述计算模块33，用于根据所述多个权重项中每一权重项在每个应用历史被开启时发生的所有历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
可以理解的是，针对不同的应用，每个权重项对不同的应用的影响程度是不同的，因此每个权重项针对每一应用都会存在一个对应的独立预测结果。
在一些实施例中，所述计算模块33，用于根据所述多个权重项中每一权重项在每个应用历史被开启时发生的所有历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
比如，其中所述多个权重项包括m个权重项，在第n次预测之前，所述计算模块33可以根据所述m个权重项中每一权重项的第1次至第n-1次的历 史状态信息，在第n次计算每一权重项单独对应于每个应用被开启的概率，以得到所述m个权重项分别对应的独立预测结果为r1n至rmn；
其中，m与n均为大于或等于1的正整数。
可以理解的是，r1n是指第1个因子在第n次预测的独立预测结果，rmn是指第m个因子在第n次预测的独立预测结果。比如，r1n是基于之前的第1次到第n-1次的实际开启结果统计出来的。
所述预测模块34，用于根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果。
可以理解的是，所述目标预测结果是基于所有权重项对应用的影响最终给出的概率，所述预测模块34需结合每个权重项对应的应用中单独计算出来的概率与对应的当前权值的加权值，来确定每个应用被开启的最终概率，以此来预测即将被开启的应用。
在一些实施例中，所述预测模块34还包括计算子模块341和预测子模块342。
其中，所述计算子模块341，用于根据所述多个权重项分别对应的独立预测结果以及当前权值的加权，计算多个应用中每个应用在所述多个权重项的影响下被开启的概率。
比如，所述m个权重项分别对应的当前权值为a1n至amn，当进行第n次预测时，所述计算子模块341可以根据所述m个权重项分别对应的独立预测结果以及当前权值的加权，计算多个应用中每个应用在所述m个权重项的影响下被开启的概率rn，其中所述rn等于第1权重项对应的独立预测结果r1n乘以当前权值a1n至第m权重项对应的独立预测结果rmn乘以当前权值amn之和，rn的计算公式如下：
rn＝a1n*r1n+a2n*r2n+...+amn*rmn。
所述预测子模块342，用于将所述多个应用中对应的被开启的概率达到第二阈值的应用预测为即将被开启的应用，以得到目标预测结果。
在一些实施例中，所述预测即将被开启的应用可以包括软件形式的应用程序，比如各类客户端应用，也可以包括电子设备内存在的硬件模组，比如指纹 传感器，接近传感器等。
所述预加载模块35，用于对所述预测即将被开启的应用进行预加载处理。
可以理解的是，在得到目标预测结果之后，当所述目标预测结果为即将被打开的应用时，所述预加载模块35可以对所述目标预测结果中的应用进行资源预加载，以缩短应用真正被打开的时间。
在一些实施例中，可以在所述对所述预测即将被开启的应用进行预加载处理之前，对所述电子设备中的设备资源进行检测。比如检测所述电子设备的内存资源是否满足应用预加载时所需的存储空间需求，当满足时，所述预加载模块35对所述预测即将被开启的应用进行预加载处理。比如检测所述电子设备的剩余电量是否大于预设电量，若是，则所述预加载模块35对所述预测即将被开启的应用进行预加载处理。
所述调整模块36，用于根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性。
比如，在用户做出最终选择，对电子设备中的应用程序进行实际开启之后，所述调整模块36会根据最终选择结果，反向回馈调整各个权重项的权值。经过多次的反馈调整后，使得所述预测***的各个权重项的权值最终收敛，使得预测结果更接近于用户实际选择开启的应用，提升预测结果的准确性。
在一些实施例中，所述调整模块36，用于当所述实际被开启的应用与所述预测即将被开启的应用相同时，提高所述独立预测结果中预测所述实际被开启的应用被开启的概率大于第一阈值的权重项所对应的权值。
在一些实施例中，所述调整模块36，用于当所述实际被开启的应用与所述预测即将被开启的应用相同时，降低所述独立预测结果中预测所述实际被开启的应用被开启的概率小于第一阈值的权重项所对应的权值。
本发明实施例还提供一种电子设备，包括存储器，处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器调用所述存储器中存储的所述计算机程序，执行本发明任一实施例所述的应用控制方法。
该电子设备可以是智能手机、平板电脑等设备。如图8所示，电子设备400包括有一个或者一个以上处理核心的处理器401、有一个或一个以上计算机可 读存储介质的存储器402及存储在存储器402上并可在处理器401上运行的计算机程序。其中，处理器401与存储器402电性连接。本领域技术人员可以理解，图8中示出的电子设备结构并不构成对电子设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
处理器401是电子设备400的控制中心，利用各种接口和线路连接整个电子设备的各个部分，通过运行或加载存储在存储器402内的应用程序，以及调用存储在存储器402内的数据，执行电子设备的各种功能和处理数据，从而对电子设备进行整体监控。
在本发明实施例中，电子设备400中的处理器401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402中，并由处理器401来运行存储在存储器402中的应用程序，从而实现各种功能：
获取电子设备中多个权重项的历史状态信息以及当前权值；
根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果；
根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果；
根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性。
在一些实施例中，处理器401用于所述根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性，包括：
当所述实际被开启的应用与所述预测即将被开启的应用相同时，提高所述独立预测结果中预测所述实际被开启的应用被开启的概率大于第一阈值的权重项所对应的权值；或者降低所述独立预测结果中预测所述实际被开启的应用被开启的概率小于第一阈值的权重项所对应的权值。
在一些实施例中，处理器401用于所述根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对 应的独立预测结果，包括：
根据所述多个权重项中每一权重项在每个应用历史被开启时发生的所有历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
在一些实施例中，处理器401用于所述根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果，包括：
根据所述多个权重项分别对应的独立预测结果以及当前权值的加权，计算多个应用中每个应用在所述多个权重项的影响下被开启的概率；
将所述多个应用中对应的被开启的概率达到第二阈值的应用预测为即将被开启的应用，以得到目标预测结果。
在一些实施例中，处理器401用于在所述获取电子设备中多个权重项的历史状态信息以及当前权值之前，还包括：
采集历史时段内用户在开启应用时多个权重项中的每一权重项对应的状态信息，以统计所述多个权重项的历史状态信息。
在一些实施例中，所述多个权重项包括时间、地点、应用间逻辑顺序、应用切换时长以及设备状态。
在一些实施例中，处理器401用于所述采集历史时段内用户在开启应用时多个权重项中的每一权重项对应的状态信息，以统计所述多个权重项的历史状态信息，包括：
通过所述电子设备上的全球定位***、或者所述电子设备连接的基站信息、或者所述电子设备的无线网络连接的服务集标识，采集历史时段内用户在开启应用时地点权重项对应的状态信息，以统计所述地点权重项的历史状态信息。
在一些实施例中，处理器401用于所述设备状态包括耳机状态以及传感器状态。
在一些实施例中，处理器401用于在所述根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性之前，还包括：
对所述预测即将被开启的应用进行预加载处理。
在一些实施例中，处理器401用于在所述对所述预测即将被开启的应用进 行预加载处理之前，还包括：
对所述电子设备中的设备资源进行检测，其中所述设备资源包括内存资源与剩余电量。
尽管图8中未示出，电子设备400还可以包括显示屏、无线保真(WiFi，Wireless Fidelity)模块、射频电路、输入单元、音频电路、传感器括摄像头、蓝牙模块以及电源等，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
本发明实施例中，所述应用控制装置与上文实施例中的一种应用控制方法属于同一构思，在所述应用控制装置上可以运行所述应用控制方法实施例中提供的任一方法，其具体实现过程详见所述应用控制方法实施例，此处不再赘述。
需要说明的是，对本发明所述应用控制方法而言，本领域普通测试人员可以理解实现本发明实施例所述应用控制方法的全部或部分流程，是可以通过计算机程序来控制相关的硬件来完成，所述计算机程序可存储于一计算机可读取存储介质中，如存储在计算机设备的存储器中，并被该计算机设备内的至少一个处理器执行，在执行过程中可包括如所述应用控制方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储器(ROM，Read Only Memory)、随机存取记忆体(RAM，Random Access Memory)等。
对本发明实施例的所述应用控制装置而言，其各功能模块可以集成在一个处理芯片中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中，所述存储介质譬如为只读存储器，磁盘或光盘等。
以上对本发明实施例所提供的一种应用控制方法、装置、存储介质及电子设备进行了详细介绍，本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的技术方案及其核心思想；本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技 术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例的技术方案的范围。

Claims (20)

  1. 一种应用控制方法，应用于电子设备中，其包括：
    获取所述电子设备中多个权重项的历史状态信息以及当前权值；
    根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果；
    根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果；
    根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性。
  2. 如权利要求1所述的应用控制方法，其中所述根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性，包括：
    当所述实际被开启的应用与所述预测即将被开启的应用相同时，提高所述独立预测结果中预测所述实际被开启的应用被开启的概率大于第一阈值的权重项所对应的权值；或者
    降低所述独立预测结果中预测所述实际被开启的应用被开启的概率小于第一阈值的权重项所对应的权值。
  3. 如权利要求1所述的应用控制方法，其中所述根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果，包括：
    根据所述多个权重项中每一权重项在每个应用历史被开启时发生的所有历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
  4. 如权利要求3所述的应用控制方法，其中所述根据所述独立预测结果以及所述当前权值的加权，预测即将被开启的应用，以得到目标预测结果，包括：
    根据所述多个权重项分别对应的独立预测结果以及当前权值的加权，计算多个应用中每个应用在所述多个权重项的影响下被开启的概率；
    将所述多个应用中对应的被开启的概率达到第二阈值的应用预测为即将被开启的应用，以得到目标预测结果。
  5. 如权利要求1所述的应用控制方法，其中在所述获取电子设备中多个权重项的历史状态信息以及当前权值之前，还包括：
    采集历史时段内用户在开启应用时多个权重项中的每一权重项对应的状态信息，以统计所述多个权重项的历史状态信息。
  6. 如权利要求5所述的应用控制方法，其中所述多个权重项包括时间、地点、应用间逻辑顺序、应用切换时长以及设备状态。
  7. 如权利要求6所述的应用控制方法，其中所述采集历史时段内用户在开启应用时多个权重项中的每一权重项对应的状态信息，以统计所述多个权重项的历史状态信息，包括：
    通过所述电子设备上的全球定位***、或者所述电子设备连接的基站信息、或者所述电子设备的无线网络连接的服务集标识，采集历史时段内用户在开启应用时地点权重项对应的状态信息，以统计所述地点权重项的历史状态信息。
  8. 如权利要求6所述的应用控制方法，其中所述设备状态包括耳机状态以及传感器状态。
  9. 如权利要求1所述的应用控制方法，其中在所述根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性之前，还包括：
    对所述预测即将被开启的应用进行预加载处理。
  10. 如权利要求9所述的应用控制方法，其中在所述对所述预测即将被开启的应用进行预加载处理之前，还包括：
    对所述电子设备中的设备资源进行检测，其中所述设备资源包括内存资源与剩余电量。
  11. 一种应用控制装置，其包括：
    获取模块，用于获取电子设备中多个权重项的历史状态信息以及当前权值；
    计算模块，用于根据所述多个权重项的历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果；
    预测模块，用于根据所述独立预测结果以及所述当前权值的加权，预测即 将被开启的应用，以得到目标预测结果；
    调整模块，用于根据实际被开启的应用，对所述多个权重项的权值进行调整以提高所述目标预测结果的准确性。
  12. 如权利要求11所述的应用控制装置，其中所述调整模块，用于当所述实际被开启的应用与所述预测即将被开启的应用相同时，提高所述独立预测结果中预测所述实际被开启的应用被开启的概率大于第一阈值的权重项所对应的权值；或者
    降低所述独立预测结果中预测所述实际被开启的应用被开启的概率小于第一阈值的权重项所对应的权值。
  13. 如权利要求11所述的应用控制装置，其中所述计算模块，用于根据所述多个权重项中每一权重项在每个应用历史被开启时发生的所有历史状态信息，计算每一权重项单独对应于每个应用被开启的概率，以得到每一权重项对应的独立预测结果。
  14. 如权利要求13所述的应用控制装置，其中所述预测模块，包括：
    计算子模块，用于根据所述多个权重项分别对应的独立预测结果以及当前权值的加权，计算多个应用中每个应用在所述多个权重项的影响下被开启的概率；
    预测子模块，用于将所述多个应用中对应的被开启的概率达到第二阈值的应用预测为即将被开启的应用，以得到目标预测结果。
  15. 如权利要求11所述的应用控制装置，其中所述装置还包括：
    采集模块，用于采集历史时段内用户在开启应用时多个权重项中的每一权重项对应的状态信息，以统计所述多个权重项的历史状态信息。
  16. 如权利要求15所述的应用控制装置，其中所述多个权重项包括时间、地点、应用间逻辑顺序、应用切换时长以及设备状态。
  17. 如权利要求16所述的应用控制装置，其中所述采集模块，用于通过所述电子设备上的全球定位***、或者所述电子设备连接的基站信息、或者所述电子设备的无线网络连接的服务集标识，采集历史时段内用户在开启应用时地点权重项对应的状态信息，以统计所述地点权重项的历史状态信息。
  18. 如权利要求11所述的应用控制装置，其中所述装置还包括：
    预加载模块，用于对所述预测即将被开启的应用进行预加载处理。
  19. 一种存储介质，其上存储有计算机程序，其中所述计算机程序被处理器调用以执行如权利要求1-10任一项所述的应用控制方法。
  20. 一种电子设备，包括存储器，处理器及存储在存储器上并可在处理器上运行的计算机程序，其中所述处理器调用所述存储器中存储的所述计算机程序，执行如权利要求1-10任一项所述的应用控制方法。
PCT/CN2017/091381 2017-06-30 2017-06-30 应用控制方法、装置、存储介质及电子设备 WO2019000469A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2017/091381 WO2019000469A1 (zh) 2017-06-30 2017-06-30 应用控制方法、装置、存储介质及电子设备
CN201780090733.0A CN110914802A (zh) 2017-06-30 2017-06-30 应用控制方法、装置、存储介质及电子设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/091381 WO2019000469A1 (zh) 2017-06-30 2017-06-30 应用控制方法、装置、存储介质及电子设备

Publications (1)

Publication Number Publication Date
WO2019000469A1 true WO2019000469A1 (zh) 2019-01-03

Family

ID=64741900

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/091381 WO2019000469A1 (zh) 2017-06-30 2017-06-30 应用控制方法、装置、存储介质及电子设备

Country Status (2)

Country Link
CN (1) CN110914802A (zh)
WO (1) WO2019000469A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105893609A (zh) * 2016-04-26 2016-08-24 南通大学 一种基于加权混合的移动app推荐方法
CN106021337A (zh) * 2016-05-09 2016-10-12 房加科技（北京）有限公司 一种基于大数据分析的智能推荐方法及***
US20160357808A1 (en) * 2015-06-05 2016-12-08 Apple Inc. Systems and methods for proactively providing recommendations to a user of a computing device
CN106775755A (zh) * 2016-12-30 2017-05-31 维沃移动通信有限公司 一种应用推荐方法及移动终端

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE69429204T2 (de) * 1993-03-26 2002-07-25 Cabletron Systems Inc Ablaufssteuerungsverfahren und -gerät für ein Kommunikationsnetzwerk
US20120324481A1 (en) * 2011-06-16 2012-12-20 Samsung Electronics Co. Ltd. Adaptive termination and pre-launching policy for improving application startup time
CN103019737B (zh) * 2012-12-27 2016-10-26 小米科技有限责任公司 一种应用程序快捷方式的显示方法和装置
CN103235799B (zh) * 2013-04-15 2015-12-02 百度在线网络技术（北京）有限公司 调整移动终端的互联网内容项的展现顺序的方法和***
CN103440167B (zh) * 2013-09-04 2016-06-29 福州大学 Hadoop多作业环境下自学习反馈的任务调度方法
CN104516897B (zh) * 2013-09-29 2018-03-02 国际商业机器公司 一种针对应用对象进行排序的方法和装置
CN105653655A (zh) * 2015-12-25 2016-06-08 Tcl集团股份有限公司 应用推送方法及装置
CN105939416A (zh) * 2016-05-30 2016-09-14 努比亚技术有限公司 移动终端及其应用预启动方法
CN106775068B (zh) * 2016-11-29 2020-07-14 中气电力装备有限公司 一种触控区域控制方法及智能终端

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160357808A1 (en) * 2015-06-05 2016-12-08 Apple Inc. Systems and methods for proactively providing recommendations to a user of a computing device
CN105893609A (zh) * 2016-04-26 2016-08-24 南通大学 一种基于加权混合的移动app推荐方法
CN106021337A (zh) * 2016-05-09 2016-10-12 房加科技（北京）有限公司 一种基于大数据分析的智能推荐方法及***
CN106775755A (zh) * 2016-12-30 2017-05-31 维沃移动通信有限公司 一种应用推荐方法及移动终端

Also Published As

Publication number Publication date
CN110914802A (zh) 2020-03-24

Similar Documents

Publication Publication Date Title
US10785039B2 (en) Blockchain consensus method and device
EP3502880B1 (en) Method for preloading application, storage medium, and terminal device
US10664289B2 (en) Loading sub-applications for a terminal application
US11849399B2 (en) Method for reducing power consumption of terminal, and terminal
EP3502878B1 (en) Method for preloading application and terminal device
US11164097B2 (en) Method for preloading application, storage medium, and terminal device
CN105264456B (zh) 运动围栏
US9465622B2 (en) Application defined computing component configuration
AU2018284487B2 (en) Application control method and application control device
WO2015081801A1 (en) Method, server, and system for information push
US10187516B2 (en) Systems, non-transitory computer-readable media and methods for voice quality enhancement
CN107885545B (zh) 应用管理方法、装置、存储介质及电子设备
Han et al. E3: Energy-efficient engine for frame rate adaptation on smartphones
JP7272694B2 (ja) 端末の電力消費を低減するための方法、および端末
CN107728772B (zh) 应用程序的处理方法、装置、存储介质及电子设备
CN114461481A (zh) 电子设备的功耗确定方法、装置、存储介质及电子设备
WO2020133408A1 (zh) 应用程序的优先级调整方法、装置、存储介质及电子设备
CN107797832B (zh) 应用清理方法、装置、存储介质及电子设备
WO2019072179A1 (zh) 应用程序运行控制方法及装置
CN108293197A (zh) 一种资源统计方法、装置及终端
WO2019000469A1 (zh) 应用控制方法、装置、存储介质及电子设备
CN108377162A (zh) 天线控制方法、装置、存储介质及电子设备
CN113918757A (zh) 应用推荐方法、装置、电子设备及存储介质
CN113056756B (zh) 睡眠识别方法、装置、存储介质及电子设备
CN114546910A (zh) 访问控制方法、装置、存储介质及电子装置

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: 17915840

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: 17915840

Country of ref document: EP

Kind code of ref document: A1