Application control method and related apparatus

Abstract

Embodiments of the present application provide an application control method and related device, and relate to the technical field of terminals. The method is applied to an electronic device, and includes: in a first time period of a t-th day, a background of the electronic device runs M applications, and a first application list is used to kill the M applications; in a second time period of the t-th day, a background of the electronic device runs N applications, and a second application list is used to kill the N applications, an application quantity in the second application list is different from an application quantity in the first application list, the first time period is different from the second time period, and the M and the N are integers. In this way, the probability that an application not used by a user is killed can be improved, and thus the power consumption of the electronic device can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of terminal, and in particular, to an application (APP) control method and related device. BACKGROUND

[0002] A plurality of applications can be installed on some electronic devices to provide a plurality of application services to users. The user can start a plurality of applications. One of the plurality of started applications can run in the foreground, and the remaining applications of the plurality of started applications can run in the background.

[0003] In order to save power consumption, the electronic device can kill some of the applications running in the background. The killed applications will terminate running, and the applications that are not killed are keep-alive applications that remain running.

[0004] However, the above implementation has the problem of short battery life of the electronic device. SUMMARY

[0005] Embodiments of the present application provide an application control method and related device, applied to the technical field of terminal. In response to a recommendation operation, the electronic device adopts an application list corresponding to a time period to which a recommendation operation time belongs to kill applications running in the background. The number of applications in the application list corresponding to different time periods is different. In this way, the probability that an application that will not be used by the user is killed can be improved, and the power consumption of the electronic device can be reduced.

[0006] In a first aspect, embodiments of the present application provide an application control method applied to an electronic device, the method comprising: in a first time period of the tth day, there are M applications running in the background of the electronic device, and a first application list is adopted to kill the M applications. In a second time period of the tth day, there are N applications running in the background of the electronic device, and a second application list is adopted to kill the N applications. The number of applications in the second application list is different from the number of applications in the first application list. The first time period is different from the second time period. M and N are integers.

[0007] In this way, the application list corresponding to different time periods can be obtained, and the number of applications in the application list corresponding to different time periods is different. The application list corresponding to different time periods is adopted to kill the applications running in the background, which can improve the probability that an application that will not be used by the user is killed, thereby reducing the power consumption of the electronic device, and can also reduce the probability that an application that will be used by the user is killed, thereby improving the user experience.

[0008] In a possible implementation, the first application list is obtained in the following manner: at the first time period of the t-th day, a first predicted application list of the first time period of the t-th day is predicted by using a preset model. A target number of applications in the first predicted application list are selected to obtain the first application list. The preset model is configured to output the first predicted application list under the condition that application usage data of the first time period in the L days before the t-th day is input, and application usage data of R times of using applications before a first recommendation operation time is input. The first recommendation operation time is the time when the first time period of the t-th day is reached. The application usage data includes a start time of running in the foreground of the application and an application identifier. The target number is related to one or more of the following: an application usage number of the first time period in the L days before the t-th day, an application usage number of the first time period in the K days before the t-th day, an application usage number of Q time periods before the first time period of the t-th day, and the Q time periods are not the first time period.

[0009] In this way, the preset model considers the order of the probability of the possible application usage of the user in the first time period. The first application list composed of the target number of applications selected from the first predicted application list output by the preset model also considers the possible application usage number of the user in the first time period, improves the accuracy of the first application list, and can improve the probability that the application that will not be used by the user in the first time period is killed, so as to reduce the power consumption of the electronic device.

[0010] In a possible implementation, the target number is positively related to one or more of the following: an application usage number of the first time period in the L days before the t-th day, an application usage number of the first time period in the K days before the t-th day, and an application usage number of Q time periods before the first time period of the t-th day.

[0011] In this way, the target number of the first time period is predicted based on the application usage number of the first time period in the L days before the t-th day, the application usage number of the first time period in the K days before the t-th day, and the application usage number of the Q time periods before the first time period of the t-th day, which can improve the prediction accuracy of the target number of the first time period.

[0012] In one possible implementation, if day t is a workday, the target quantity is related to one or more of the following: the application usage during the first time slot of workdays in the L days prior to day t, the application usage during the first time slot of the K workdays prior to day t, and the application usage during the Q time slots belonging to workdays prior to the first time slot of day t. If day t is a public holiday, the target quantity is related to one or more of the following: the application usage during the first time slot of public holidays in the L days prior to day t, the application usage during the first time slot of the K public holidays prior to day t, and the application usage during the Q time slots belonging to public holidays prior to the first time slot of day t.

[0013] In this way, since users' habits of using the application on weekdays may be different from those on holidays, distinguishing the date type of day t can further improve the accuracy of predicting the target quantity in the first time period.

[0014] In one possible implementation, the first time segment of day t is the s-th time segment of day t. The target number N ts Satisfy the following formula:

[0015]

[0016] Where, N ti,s N represents the application usage count during the s-th time period of the i-th target day prior to day t, where the interval between the i-th target day prior to day t is i-1 target days. t,sj The app usage count is the number of times the app is used in the j-th time period before the s-th time period on day t. The interval between the j-th time period before the s-th time period on day t and the s-th time period on day t is j-1 time periods belonging to the target day. γ1 is a weighting coefficient, γ2 is a weighting coefficient, γ3 is a weighting coefficient, and σ is a weighting coefficient. tsL 2 The variance of the number of applications used in the s-th time period of the target day in the L days prior to day t, σ tsL 2 *γ3 represents the variance σ tsL 2 The weighted average of the values ​​indicates that the target date satisfies the following conditions: if day t is a working day, the target date is a working day; if day t is a public holiday, the target date is a public holiday. * represents multiplication.

[0017] Thus, based on the application usage in the s-th time period among the K target days prior to day t (e.g. ), application usage of the Q time periods belonging to the target day before the s-th time period on day t (e.g. ) and the stability of user habits in using the application during the s-th time period of the target day (e.g., σ)tsL 2 predicting the target number N of the first time period of the t-th day ts The accuracy of the predicted target number of the first time period of the t-th day can be further improved.

[0018] In a possible implementation, the plurality of applications in the first prediction list are arranged in descending order of the application usage probabilities. The target number of applications are selected from the first prediction application list to obtain the first application list, including: the first application list is composed of the first N ts applications in the first prediction application list. ts The target number is N.

[0019] In this way, the applications in the first application list are also arranged in descending order of the application usage probabilities. In the case that the electronic device adopts the first application list to kill the background running applications, if the background running applications whose application identifiers are in the first application list need to be killed in order to make the electronic device have sufficient available memory, the electronic device can preferentially kill the applications at the tail of the first application list. It should be understood that the usage probability of the application at the tail of the first application list is smaller than the usage probability of the application at the top of the first application list, so as to reduce the probability that the application to be used by the user is killed.

[0020] In a possible implementation, before the M applications are killed by using the first application list, the method further includes: determining whether a first similarity corresponding to the first time period of the t-th day is greater than a similarity threshold, and / or whether a first dispersion corresponding to the first time period of the t-th day is greater than a dispersion threshold. The first similarity represents the similarity between the application usage number of the first time period of the t-th day and the application usage number of the time period before the first time period of the t-th day, and the first dispersion represents the difference between the application usage number of the first time period of the t-th day and the application usage number of the first time period of the day before the t-th day. The M applications are killed by using the first application list, including: in the case that the first similarity is less than or equal to the similarity threshold, and / or the first dispersion is less than or equal to the dispersion threshold, the M applications are killed by using the first application list.

[0021] In this way, if the first similarity is less than or equal to the similarity threshold, and / or the first dispersion is less than or equal to the dispersion threshold, it can be indicated that the user's habit of using the application in the first time period is stable, and the killing by using the first application list can improve the probability that the application which will not be used by the user in the first time period of the t-th day is killed, thereby reducing the power consumption of the electronic device.

[0022] In a possible implementation, the second time period of the t-th day belongs to the time period of the t-th day. The second application list comprises a second predicted application list, which is predicted by using a preset model when the second time period of the t-th day is reached. The preset model is further configured to output the second predicted application list under the condition that the application usage data in the second time period of the L days before the t-th day is input, and the application usage data of the R times of using the application before the second recommended operation time is input. The second recommended operation time is the time when the second time period of the t-th day is reached. Before the N applications are killed by using the second application list, the method further comprises: determining whether a second similarity corresponding to the second time period of the t-th day is greater than a similarity threshold, and / or whether a second dispersion corresponding to the second time period of the t-th day is greater than a dispersion threshold. The second similarity represents the similarity between the application usage quantity of the second time period of the t-th day and the application usage quantity of the time period before the second time period of the t-th day, and the second dispersion represents the difference between the application usage quantity of the second time period of the t-th day and the application usage quantity of the second time period of the days before the t-th day. The N applications are killed by using the second application list, comprising: the N applications are killed by using the second predicted application list in the case that the second similarity is greater than the similarity threshold, and / or the second dispersion is greater than the dispersion threshold.

[0023] In this way, if the second similarity is greater than the similarity threshold, and / or the second dispersion is greater than the dispersion threshold, it can be indicated that the user's habit of using the application in the second time period is unstable, and the second predicted application list is used for killing, which can reduce the probability that the application used by the user in the second time period of the t-th day is killed, and improve the user experience.

[0024] In a possible implementation, the first dispersion comprises a first variance or a first standard deviation. The first variance is the variance of the application usage quantity in the first time period of the L days before the t-th day. The first standard deviation is the standard deviation of the application usage quantity in the first time period of the L days before the t-th day. The first similarity is related to the application usage quantity in the first time period of the K days before the t-th day and the application usage quantity of the first Q time periods of the t-th day.

[0025] In this way, based on the variance or the standard deviation of the application usage quantity in the first time period of the L days before the t-th day, the habit stability of the user using the application in the first time period can be determined, and accurate determination of the habit stability of the user using the application can be realized. Based on the first similarity, the habit stability of the user using the application in the first time period can be determined. The first similarity is determined based on the application usage quantity in the first time period of the K days before the t-th day and the application usage quantity of the first Q time periods of the t-th day, and thus accurate determination of the habit stability of the user using the application can be realized.

[0026] In a possible implementation, in a case where the day t is a weekday, the first variance is a variance of the application usage quantity of the first time period of the weekdays in the L days before the day t, and the first standard deviation is a standard deviation of the application usage quantity of the first time period of the weekdays in the L days before the day t. The first similarity degree is related to the application usage quantity of the first time period in the K weekdays before the day t and the application usage quantity of the Q time periods before the first time period of the day t. In a case where the day t is a holiday, the first variance is a variance of the application usage quantity of the first time period of the holidays in the L days before the day t, and the first standard deviation is a standard deviation of the application usage quantity of the first time period of the holidays in the L days before the day t. The first similarity degree is related to the application usage quantity of the first time period in the K holidays before the day t and the application usage quantity of the Q time periods before the first time period of the day t.

[0027] In this way, the date type of the day t is distinguished, and the accuracy of the habit stability of the user using the application can be further improved.

[0028] In a possible implementation, the first time period of the day t is the s-th time period of the day t. The first similarity degree N wts The following formula is met:

[0029] N wts =max[N w,ti,s ,N w,t,sj ]

[0030] N w,ti,s =N ti,s -A s , N w,t , sj =N t,sj -A s , N ti,s is the application usage quantity of the s-th time period of the i-th target day before the day t, the i-th target day is spaced apart from the day t by i-1 target days, N t,sj is the application usage quantity of the j-th time period before the s-th time period of the day t, the j-th time period is spaced apart from the s-th time period of the day t by j-1 time periods belonging to target days, A s is the number of applications used in both the s-th time period and the j-th time period of the i-th target day, i=1, 2,..., K, and j=1, 2,..., Q, and the target day meets: in a case where the day t is a weekday, the target day is a weekday, and in a case where the day t is a holiday, the target day is a holiday.

[0031] Thus, the application usage of the user in the first time period of the tth day is affected by the application usage in the first time period in the K days before the tth day and the application usage in the first time period of the tth day in the first Q time periods. Thus, the first similarity is obtained based on the application usage quantity in the first time period in the K days before the tth day, the application usage quantity in the first time period of the tth day in the first Q time periods, and the quantity of the application used by the user in the first time period in the K days before the tth day and in the first Q time periods of the tth day, and the habit stability of the user in using the application in the first time period of the tth day is judged based on the first similarity, so that the accuracy of the judgment can be improved.

[0032] In a possible implementation, the first time period of the tth day is the s th time period of the tth day. The first variance σ tsL 2 and the first standard deviation σ tsL satisfies the following formula:

[0033]

[0034] wherein x ts , p is the application usage quantity in the s th time period of the p th target day in the L days before the tth day, and n is the quantity of the target day in the L days before the tth day. The target day satisfies: the target day is a weekday if the tth day is a weekday, and the target day is a holiday if the tth day is a holiday.

[0035] Thus, in the case of judging the habit stability of the user in using the application in the first time period by using the first variance or the first standard deviation, the accuracy of the judgment can be improved.

[0036] In one possible implementation, the first time period on day t is the s-th time period on day t, and the preset model is a multi-path recall model. The preset model is used to predict the first predicted application list for the first time period, including obtaining the first data corresponding to the first time period. The first data includes first long-term data, first recent data, and first real-time data. The first long-term data includes application usage data for the s-th time period of the target day in the L days prior to day t; the recent data includes application usage data for the s-th time period of the U target days prior to day t; and the real-time data includes application usage data for the R applications used before the first recommended operation time. The multi-path recall model processes the first data as follows to obtain the first predicted application list: the classification and regression tree (CART) algorithm in the multi-path recall model is used to calculate the first weight of each application corresponding to the long-term data. The recent popular recall algorithm in the multi-path recall model is used to calculate the second weight of each application corresponding to the recent data. The time decay algorithm in the multi-path recall model is also used to calculate the third weight of each application corresponding to the real-time data. The applications corresponding to the first data are sorted according to their fourth weight to obtain a first sorted list. The fourth weight of an application is the sum of its first, second, and third weights. The fourth weight is related to the application's first usage probability. The top N0 applications from the first sorted list constitute the first predicted application list, where N0 is a preset value, and N0 is greater than the target number.

[0037] Thus, as Figure 4 As shown in S402, the multi-path recall model can employ three recall paths to learn users' long-term, recent, and real-time application (APP) usage habits respectively. It also uses recall weights for each path to achieve multi-path recall fusion and ranking. The multi-path recall model comprehensively considers users' long-term, recent, and real-time application usage habits. By considering long-term, recent, and real-time data, the accuracy of the predicted application list output by the multi-path recall model, sorted by usage probability, can be improved.

[0038] In one possible implementation, day t contains forty-eight time segments, with no overlap between adjacent segments and all segments having the same duration. Understandably, since day t contains forty-eight time segments, each segment can be 30 minutes long. Thus, upon receiving a recommended action, the electronic device can obtain a list of applications within the time segment containing the recommended action. The device can then use this list to detect and eliminate applications running in the background, achieving accurate detection while reducing power consumption.

[0039] In a second aspect, an embodiment of the present application provides an application control apparatus. The application control apparatus can be an electronic device, or a chip or chip system in the electronic device. The application control apparatus can include a display unit and a processing unit. When the application control apparatus is an electronic device, the processing unit can be a processor. The application control apparatus can further include a storage unit, which can be a memory. The storage unit is configured to store instructions, and the processing unit is configured to execute the instructions stored in the storage unit, so that the electronic device implements an application control method described in the first aspect or any possible implementation of the first aspect. When the application control apparatus is a chip or chip system in the electronic device, the processing unit can be a processor. The processing unit is configured to execute the instructions stored in the storage unit, so that the electronic device implements an application control method described in the first aspect or any possible implementation of the first aspect. The storage unit can be a storage unit (e.g., a register, a cache, etc.) in the chip, or a storage unit (e.g., a read-only memory, a random access memory, etc.) outside the chip in the electronic device.

[0040] In a third aspect, an embodiment of the present application provides an electronic device. The electronic device includes a processor and a memory. The memory is configured to store code instructions, and the processor is configured to execute the code instructions to perform the method described in the first aspect or any possible implementation of the first aspect.

[0041] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program or instructions. When the computer program or instructions are executed on a computer, the computer is caused to perform the method described in the first aspect or any possible implementation of the first aspect.

[0042] In a fifth aspect, an embodiment of the present application provides a computer program product including a computer program. When the computer program is executed on a computer, the computer is caused to perform the method described in the first aspect or any possible implementation of the first aspect.

[0043] In a sixth aspect, an embodiment of the present application provides a chip or chip system. The chip or chip system includes at least one processor and a communication interface. The communication interface and the at least one processor are interconnected through a line. The at least one processor is configured to execute a computer program or instructions to perform the method described in the first aspect or any possible implementation of the first aspect. The communication interface in the chip can be an input / output interface, a pin, or a circuit, etc.

[0044] In a possible implementation, the chip or the chip system described above in the application further includes at least one memory in which instructions are stored. The memory can be a storage unit inside the chip, for example, a register, a cache, etc., or a storage unit of the chip (for example, a read-only memory, a random access memory, etc.).

[0045] It should be understood that the second aspect to the sixth aspect of the application correspond to the technical solutions of the first aspect of the application, and the beneficial effects obtained by each aspect and the corresponding feasible implementation manners are similar, which will not be described again. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 A scene schematic diagram provided for an embodiment of the application;

[0047] Figure 2 A structural schematic diagram of an electronic device provided for an embodiment of the application;

[0048] Figure 3 A software architecture schematic diagram of an electronic device provided for an embodiment of the application;

[0049] Figure 4 An application control method flow schematic diagram provided for an embodiment of the application;

[0050] Figure 5 An architecture schematic diagram of a multi-path recall model provided for an embodiment of the application. DETAILED DESCRIPTION

[0051] In order to clearly describe the technical solutions of the embodiments of the application, the following briefly introduces some terms and technologies involved in the embodiments of the application:

[0052] 1. Decision tree algorithm

[0053] The decision tree algorithm is widely used in classification and regression task models, and is a tree structure describing the classification of instances. It is a typical classification method, which first processes data, generates readable rules and decision trees using inductive algorithms, and then analyzes new data using decisions. Essentially, decision trees are a process of classifying data through a series of rules.

[0054] Common decision tree algorithms can include the classification and regression tree (CART) algorithm, and can also include the ID3 decision tree or C4.5 algorithm. Among them, the CART algorithm supports binary classification problems. The calculation results of the CART algorithm are all probability values, and in the case of classification, the Gini index minimization criterion is often used.

[0055] 2. Other terms

[0056] In the embodiments of the present application, the terms "first", "second", and the like are used to distinguish between similar or identical items or items with substantially the same function and effect. For example, the first chip and the second chip are merely used to distinguish between different chips, and do not limit the order. Those skilled in the art can understand that the terms "first", "second", and the like do not limit the number and execution order, and the terms "first", "second", and the like do not necessarily mean different.

[0057] It should be noted that in the embodiments of the present application, the words "exemplary" or "for example" are used to represent an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner.

[0058] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The association relationship between the associated objects is described by "and / or", which means that there can be three kinds of relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single item or multiple items. For example, at least one of a, b, or c, can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0059] A user can open multiple applications on an electronic device. One of the opened multiple applications can run in the foreground, and the remaining applications of the opened multiple applications can run in the background.

[0060] For ease of understanding, the following describes the embodiments of the present application with reference to the accompanying drawings. Figure 1 The scenario in which one application runs in the foreground and the remaining applications run in the background is described. Figure 1 A scenario diagram provided by an embodiment of the present application is shown.

[0061] Taking the case that a file management application, a message application, a video application, a WeChat application, a TikTok application, a map application, and a Taobao application on an electronic device are opened, the file management application runs in the foreground, and the message application, the video application, the WeChat application, the TikTok application, the map application, and the Taobao application run in the background, for example, in the case where the file management application runs in the foreground, the electronic device can display Figure 1The image 'a' shows the interface of a file management application. For example... Figure 1 The interface shown in Figure 'a' displays a virtual navigation bar 101 at the bottom of the screen. The virtual navigation bar 101 contains multiple virtual controls, such as a back control, a home control, and function controls 102.

[0062] In electronic device display Figure 1 In the interface shown in Figure a, the user can click on the function control 102. In response to the user's click on the function control 102, the electronic device can display as shown in Figure a. Figure 1 The recent tasks screen 103 is shown as b in the diagram. The recent tasks screen 103 may contain previews of applications running in the background. Figure 1 The recent tasks interface 103 shown in Figure b only displays previews of the file management application, the SMS application, and the video application. (This is in contrast to the previews displayed on electronic devices.) Figure 1 In the case of the interface shown in b, the user can swipe the screen left or right, so that the preview interface of other applications running in the background can be displayed on the recent tasks interface 103.

[0063] In electronic device display Figure 1 In the interface shown in b, the user can click on the blank area, and the electronic device can display... Figure 1 The 'c' in the diagram represents the interface of the desktop application. For example... Figure 1 The interface shown in 'c' includes the icon 104 for recommended apps.

[0064] In electronic device display Figure 1 In the scenario shown in 'c', the user can make recommendations. A recommendation is, for example, clicking on icon 104. In response to a recommendation, the electronic device can obtain a set of applications the user might use within the time period corresponding to the recommendation.

[0065] In some implementations, in response to a recommendation, the electronic device uses a predictive model to predict the applications the user might use within the time period corresponding to the recommendation, resulting in a predicted application list. This list contains applications the user is likely to use. The electronic device then uses this predicted application list to detect and remove multiple applications running in the background.

[0066] The number of applications in the predicted application list is a preset fixed value. The prediction model is used to sort the applications used by the user before the recommendation operation time in order of the size of the use probability, and then truncate part of the applications according to the preset fixed value to obtain the predicted application list. The preset fixed value is the maximum value of the number of applications used in each time period in a day. Therefore, the number of applications in the predicted application list corresponding to different time periods obtained by the prediction model is the same. The applications in the predicted application list corresponding to different time periods can be as shown in Table 1.

[0067] Table 1 Applications in the predicted application list corresponding to different time periods

[0068]

[0069] It should be understood that the time periods shown in Table 1 can be time periods belonging to the same day. The time periods shown in Table 1 can also be time periods belonging to different days.

[0070] Table 1 shows the applications and the number of applications in the predicted application list corresponding to the first time period, the second time period, the third time period and the fourth time period respectively. As shown in Table 1, the electronic device can obtain the predicted application list corresponding to different time periods by using the prediction model, and the number of applications in the predicted application list corresponding to different time periods is the same.

[0071] When the electronic device uses the predicted application list for killing, the number of applications running in the background after killing in different time periods is the same. However, the number of applications used by the user in different time periods can be different. If the predicted application list is used to kill the applications running in the background, the applications that will not be used by the user will not be killed, thereby causing the problem of large power consumption of the electronic device and short battery life of the electronic device.

[0072] Therefore, an application control method is provided. In response to a recommendation operation, the electronic device uses the application list corresponding to the time period to which the recommendation operation time belongs to kill the applications running in the background. The number of applications in the application list corresponding to different time periods is different. In this way, the probability of killing the applications that will not be used by the user can be improved, thereby reducing the power consumption of the electronic device.

[0073] The electronic device of the embodiments of the present application can include a handheld device, a vehicle-mounted device, etc. with an application recommendation function. For example, some electronic devices are: a mobile phone, a tablet computer, a palm computer, a notebook computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with a wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a 5G network, or a terminal device in a future evolved public land mobile network (PLMN), etc. The embodiments of the present application are not limited thereto.

[0074] By way of example and not limitation, in the embodiments of the present application, the electronic device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes, etc. The wearable device is a portable device that is directly worn on the body or integrated into the clothes or accessories of the user. The wearable device is not only a hardware device, but also a device that realizes powerful functions through software support and data interaction and cloud interaction. The general wearable smart device includes a device with full functions and large size, which can realize complete or partial functions without relying on a smart phone, such as a smart watch or smart glasses, etc., and a device that focuses on a certain application function and needs to be used in cooperation with other devices, such as a smart phone, such as various smart wristbands and smart jewelry for monitoring vital signs, etc.

[0075] In addition, in the embodiments of the present application, the electronic device can also be a terminal device in an Internet of Things (IoT) system. The IoT is an important part of future information technology development, and its main technical feature is to connect objects through communication technology and network, so as to realize the intelligent network of man-machine interconnection and object-object interconnection.

[0076] The electronic device in the embodiments of the present application can also be referred to as a terminal device, a user equipment (UE), a mobile station (MS), a mobile terminal (MT), an access terminal, a subscriber unit, a subscriber station, a mobile station, a mobile terminal, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user apparatus, etc.

[0077] In the embodiments of the present application, the electronic device or each network device includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system layer. The hardware layer includes a central processing unit (CPU), a memory management unit (MMU), and a memory (also known as main memory), etc. The operating system can be any one or more computer operating systems that implement business processing through processes, such as a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a windows operating system, etc. The application layer includes a browser, an address book, word processing software, instant messaging software, etc.

[0078] Figure 2 A structure schematic diagram of an electronic device provided by the embodiments of the present application is shown.

[0079] As Figure 2As shown, the electronic device 200 can include a processor 210, an external memory interface 220, an internal memory 221, a universal serial bus (USB) interface 230, a charging management module 240, a power management module 241, a battery 242, an antenna 1, an antenna 2, a mobile communication module 250, a wireless communication module 260, an audio module 270, a speaker 270A, a receiver 270B, a microphone 270C, a headset jack 270D, a sensor module 280, a key 290, a motor 291, an indicator 292, a camera 293, a display screen 294, and a subscriber identification module (SIM) card interface 295, etc. The sensor module 280 can include a pressure sensor 280A, a gyroscope sensor 280B, a barometric pressure sensor 280C, a magnetic sensor 280D, an acceleration sensor 280E, a distance sensor 280F, a proximity light sensor 280G, a fingerprint sensor 280H, a temperature sensor 280J, a touch sensor 280K, an ambient light sensor 280L, a bone conduction sensor 280M, etc.

[0080] It can be understood that the structure shown in the embodiments of the present application does not constitute a specific limitation on the electronic device 200. In other embodiments of the present application, the electronic device 200 can include more or fewer components than shown, or combine certain components, or split certain components, or different arrangement of components. The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0081] Exemplarily, in the first time period, the electronic device has M applications running in the background. The processor 210 of the electronic device receives a first recommended operation through the sensor module 280. In response to the first recommended operation, the processor 210 can obtain a first application list corresponding to the first time period to which the first recommended operation belongs. The processor 210 can use the first application list to kill the M applications, so that the application whose application identifier is not in the first application list among the M applications is killed. In this way, the power consumption and memory occupation of the electronic device can be reduced.

[0082] In the second time period, the electronic device has N applications running in the background. The processor 210 of the electronic device receives a second recommended operation through the sensor module 280. In response to the second recommended operation, the processor 210 can obtain a second application list corresponding to the second time period to which the second recommended operation belongs. The processor 210 can use the second application list to kill the N applications, so that the application whose application identifier is not in the second application list among the N applications is killed. In this way, the power consumption and memory occupation of the electronic device can be reduced.

[0083] The number of applications in the second application list is different from the number of applications in the first application list. The first time period is different from the second time period. M and N are integers.

[0084] As shown in the first application list corresponding to the first time period and the second application list corresponding to the second time period, the number of applications in the application list corresponding to different time periods is different, so that the probability that the application not used by the user is killed can be improved, and the power consumption of the electronic device is reduced.

[0085] The software system of the electronic device 200 can adopt a layered architecture, an event-driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture. Embodiments of the present application take the Android system with a layered architecture as an example to exemplarily illustrate the software structure of the electronic device 100.

[0086] Figure 3 A software architecture schematic diagram of the electronic device provided by the embodiments of the present application is shown.

[0087] The layered architecture divides the software into several layers, and each layer has a clear role and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom, the application layer, the application framework layer, the Android runtime and the system library, and the kernel layer.

[0088] The application layer can include a series of application packages.

[0089] As shown in Figure 3 , the application package can include desktop management, perception, recommendation, camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message, and the like. Among them, the recommendation application can be used for application recommendation. In some implementations, the recommendation application is referred to as an application recommendation application, and the application recommendation application is referred to as an application recommendation.

[0090] The application framework layer provides the application program interface (API) and the programming framework for the application program of the application layer. The application framework layer includes some pre-defined functions.

[0091] As shown in Figure 3 , the application framework layer can include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, a location manager (LBS), and the like.

[0092] The position manager can be used to acquire the current position of the electronic device. For example, acquiring current global positioning system (GPS) data, (wireless fidelity, Wi-Fi) positioning data and cell base station positioning data.

[0093] The Android runtime includes a core library and a virtual machine. The Android runtime is responsible for scheduling and managing the Android system.

[0094] The core library contains two parts: one is the function function that the java language needs to call, and the other is the core library of Android.

[0095] The application layer and the application framework layer run in the virtual machine. The virtual machine executes the java file of the application layer and the application framework layer into a binary file. The virtual machine is used to perform functions such as management of object life cycle, stack management, thread management, security and exception management, and garbage collection.

[0096] The system library can include multiple functional modules. For example: surface manager, media library, three-dimensional graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL) and the like.

[0097] The kernel layer is the layer between hardware and software. The kernel layer at least contains display driver, camera driver, audio driver, sensor driver.

[0098] Exemplarily, in the case that the user clicks on an application, the desktop management application can send an application click event to the perception application. Based on the application click event, the perception application can collect the current time and the application corresponding to the application click event, and generate application usage data.

[0099] Among them, the application usage data can include the start time of the application running in the foreground and the application identifier. The application identifier can be the application name. The start time of the application running in the foreground can be the time when the user clicks on the application to start the application, or the time when the user clicks on the application to convert the application from background running to foreground running. The application usage data includes the application usage quantity. The application usage quantity can be the same as the number of application running in the foreground start time points. For example, there are 5 application running in the foreground start time points in the application usage data of the X time period, and the application usage quantity of the X time period is 5.

[0100] At the first time, the user can perform a first recommendation operation. The first recommendation operation is, for example, an operation in which the user clicks the recommendation application. The desktop management application can send an application click event to the recommendation application. The application click event includes a timestamp representing the first time. The recommendation application can identify that the first time belongs to a first time period. The recommendation application can obtain application usage data corresponding to the first time period from the perception application. The recommendation application can transmit the application usage data corresponding to the first time period to the application framework layer.

[0101] The application framework layer can input the application usage data transmitted by the recommendation application into a preset model. The preset model can output a first predicted application list corresponding to the first time period to which the first time belongs. The application framework layer can select a target number of applications of the first time period to which the first time belongs from the first predicted application list to obtain a first application list. The application framework layer can transmit the first application list to the recommendation application. The recommendation application can transmit the first application list to a killing module for killing background running applications. The killing module can use the first application list to kill the applications running in the background.

[0102] The target number of the first time period to which the first time belongs is the predicted number of applications of the first time period to which the first time belongs. The killing module can be located in the application program layer or the application framework layer. The killing module is not shown in Figure 3 .

[0103] At a second time, the user can perform a second recommendation operation. The second recommendation operation is, for example, the user clicking the recommendation application. The second time belongs to a second time period. The first time period is different from the second time period. In response to the second recommendation operation, the recommendation application can obtain a second application list corresponding to the second time period to which the second time belongs, which is transmitted by the application framework layer. The recommendation application can transmit the second application list to the killing module. The killing module can use the second application list to kill the applications running in the background.

[0104] The specific implementation principle of the recommendation application obtaining the second application list is similar to that of the recommendation application obtaining the first application list, and will not be described here. The target number used by the application framework layer to obtain the second application list is the predicted number of applications of the second time period to which the second time belongs. The number of applications in the second application list is different from the number of applications in the first application list. In this way, the number of applications in the application list corresponding to each time period can be different, and the killing module uses the application list corresponding to the time period to which the recommendation operation time belongs to kill the applications running in the background, which can improve the probability that the applications not used by the user are killed, and thus can reduce the power consumption of the electronic device.

[0105] Figure 4A flowchart of an application control method is shown.

[0106] As shown in Figure 4 , the method comprises:

[0107] S401, the electronic device obtains a training set model feature corresponding to a prediction period.

[0108] Exemplarily, taking the first time period as the prediction period for example. The electronic device can receive a first recommended operation. In the case of receiving the first recommended operation, the electronic device can identify the first time period to which the first recommended operation time belongs, and obtain the first data corresponding to the first time period to which the first recommended operation time belongs. Since the feature type in the first data is the same as the training set model feature type, the first data can also be referred to as the training set model feature corresponding to the first time period to which the first recommended operation time belongs. The first data can also be referred to as the training set model feature corresponding to the first recommended operation time.

[0109] Exemplarily, taking the first recommended operation time belonging to the tth day and the first time period belonging to the s th time period of the tth day for example, the first data can include first long-term data, first recent data and first real-time data.

[0110] The first long-term data includes application usage data in the s th time period L days before the tth day. L can be 90, or 60 or 30 or other numerical values.

[0111] The first recent data includes application usage data in the s th time period U days before the tth day. L>U. U can be 3, or 5 or 7 or other numerical values.

[0112] The first real-time data includes application usage data of R times of using the application before the first recommended operation time. R can be 5, or 7, 10 or 12 or other numerical values. R times of using the application can be understood as R starting time points of the application running in the foreground, or the sum of the operation times of opening the application and the operation times of converting the application from running in the background to running in the foreground is R.

[0113] Taking the first recommended operation time as 10:10 on December 14, L as 90, U as 3 and R as 5 for example, the first data can be as shown in Table 2.

[0114] Table 2 shows the first data

[0115]

[0116] As shown in Table 2, the first long-term data can include application usage data of the s-th time period of each day in the 90 days before the t-th day. The first recent data can include application usage data of the s-th time period of each day in the 3 days before the t-th day. The first real-time data can include application usage data of the 5 times of using the application before the first recommended operation moment of the t-th day (e.g., 10:10 on December 14). The format of the application usage data can refer to the format of the application usage data of the 5 times of using the application before the first recommended operation moment of the t-th day shown in Table 2. Wherein, "12.13 24:00, application A" indicates that the application with the application name of application A is running in the foreground, and the start time is 24:00 on December 13.

[0117] It can be understood that the t-1-th day means a day before the t-th day and adjacent to the t-th day. The t-2-th day means a day before the t-1-th day and adjacent to the t-1-th day. The t-3-th day means a day before the t-2-th day and adjacent to the t-2-th day. The t-4-th day means a day before the t-3-th day and adjacent to the t-3-th day. The t-5-th day means a day before the t-4-th day and adjacent to the t-4-th day. The t-88-th day means a day before the t-87-th day and adjacent to the t-87-th day. The t-89-th day means a day before the t-88-th day and adjacent to the t-88-th day. The t-90-th day means a day before the t-89-th day and adjacent to the t-89-th day.

[0118] Optionally, still taking the first recommended operation moment belonging to the t-th day and the first time period belonging to the s-th time period of the t-th day as an example. If the t-th day is a weekday, the first long-term data can include application usage data of the s-th time period of the weekday in the L days before the t-th day. The first recent data can include application usage data of the s-th time period of the weekday in the U days before the t-th day. The first real-time data can include application usage data of the R times of using the application before the first recommended operation moment of the t-th day. Wherein, the time of the R times of using the application before the first recommended operation moment of the t-th day all belong to the time of the weekday.

[0119] Optionally, still taking the first recommended operation moment belonging to the t-th day and the first time period belonging to the s-th time period of the t-th day as an example. If the t-th day is a holiday, the first long-term data can include application usage data of the s-th time period of the holiday in the L days before the t-th day. The first recent data can include application usage data of the s-th time period of the holiday in the U days before the t-th day. The first real-time data can include application usage data of the R times of using the application before the first recommended operation moment of the t-th day. Wherein, the time of the R times of using the application before the first recommended operation moment of the t-th day all belong to the time of the holiday.

[0120] S402, the electronic device performs model prediction inference to obtain a prediction application list corresponding to a prediction period.

[0121] Illustratively, the electronic device can input the first data into a preset model, and the preset model can output a first prediction application list corresponding to a first time period.

[0122] Illustratively, the preset model can be a multi-path recall model. The multi-path recall model can include a recall layer and a sorting layer. The recall layer can include a first path recall, a second path recall, and a third path recall. The first path recall adopts a classification and regression tree (CART) algorithm. The second path recall adopts a recently popular recall algorithm. The third path recall adopts a time decay algorithm. The recall layer is used to quickly screen a candidate (or feature) set of the order of ten million to obtain a feature set of the order of thousands or even hundreds. The sorting layer is used to uniformly score and sort the results of the multi-path recall in the recall layer, and select the top k. Figure 5 An architecture diagram of the multi-path recall model is shown, for ease of understanding, Figure 5 The subsequent description is made.

[0123] The electronic device can input the first long-term data into the classification and regression tree (CART) of the multi-path recall model to obtain a first probability value of each application in the first long-term data. Based on the first probability value of each application and a first path recall weight, the electronic device can calculate a first weight of each application.

[0124] The first path recall weight represents the proportion of the first path recall in all path sorting, and the first path recall weight can be preset. The first weight of the application can be obtained by multiplying the first probability value of the application by the first path recall weight, for example, the first weight of the application A can be obtained by multiplying the first probability value of the application A by the first path recall weight.

[0125] The electronic device can input the first recent data into the recently popular recall algorithm to obtain a second probability value of each application in the first recent data. Based on the second probability value of each application and a second path recall weight, the electronic device can calculate a second weight of each application. Illustratively, the recently popular recall algorithm can determine the proportion of the number of uses of each application in the first recent data to the sum of the number of uses of the applications in the first recent data as the first probability of each application. For example, the number of uses of the applications in the first recent data is 60, of which the memo is used 12 times, the video is used 6 times, the email is used 6 times, the setting is used 5 times, the weather is used 3 times, and the clock is used 3 times. It can be determined that the second probability value of the memo is 0.2, the second probability value of the video is 0.1, the second probability value of the email is 0.1, the second probability value of the setting is 0.083, the second probability value of the weather is 0.05, and the second probability value of the clock is 0.05.

[0126] wherein the second road recall weight represents a proportion of the second road recall in all road sorting, and the second road recall weight can also be preset. The second weight of the application can be obtained by multiplying the second probability value of the application by the second road recall weight.

[0127] The electronic device can input the first real-time data into a time decay algorithm to obtain a third probability value of each application in the first real-time data. Based on the third probability value of each application and a third road recall weight, the electronic device can calculate a third weight of each application.

[0128] wherein the third probability value of the ythapplication in the first real-time data satisfies the formula: δ(T) y is a decay value of the ythapplication with a time interval of T y . T y is a time difference between the time when the ythapplication starts running in the foreground and the first recommended operation time. ε0is an initial decay value. θ is an exponential decay constant. l is a translation amount indicating left, so that the value does not have to decay from ε0, but continues to decay from any position. ε0, θ and l can all be values trained in advance by the electronic device. The third road recall weight represents a proportion of the third road recall in all road sorting, and the third road recall weight can also be preset. The third weight of the application can be obtained by multiplying the third probability value of the application by the third road recall weight.

[0129] Based on the first weight, the second weight and the third weight of each application, the electronic device can obtain a fourth weight of each application. The electronic device can sort the plurality of applications corresponding to the first data in the order of the fourth weight of the application to obtain a first sorting list. The fourth weight of the application is the sum of the first weight of the application, the second weight of the application and the third weight of the application. For example, the fourth weight of application A is the sum of the first weight of application A, the second weight of application A and the third weight of application A. The fourth weight of the application is related to the first use probability of the application. In this way, the sorting of the application in the first sorting list is in the order of the size of the use probability of the application.

[0130] The electronic device can intercept the first N0applications in the first sorting list to form a first predicted application list. Wherein N0is a preset value, and N0may be the maximum value of the application use quantity in the respective application use quantity of each time period. N0is greater than the target quantity corresponding to the first time period.

[0131] It should be understood that, since the sorting of the application in the first sorting list is in the order of the size of the use probability of the application, the plurality of applications in the first predicted application list are sorted in the order of the size of the use probability of the application.

[0132] In this way, in the case that the electronic device adopts the first predicted application list to kill the background running application, if the background running application identified in the first predicted application list needs to be killed in order to make the electronic device have sufficient available memory, the electronic device can preferentially kill the application located at the tail of the first predicted application list. It should be understood that the use probability of the application located at the tail of the first predicted application list is less than the use probability of the application located at the top of the first predicted application list, so as to reduce the probability that the application to be used by the user is killed.

[0133] It should be understood that the first predicted application list obtained in step S402 can also be referred to as a predicted application list corresponding to a first recommended operation time. As shown in S401-S402, the first real-time data contained in the training set model feature corresponding to the first recommended operation time is associated with the first recommended operation time.

[0134] As shown in the above first data, the first real-time data is the application usage data of R times of using the application before the first recommended operation time. The real-time data contained in the training set model feature corresponding to the vth recommended operation time can be the application usage data of R times of using the application before the vth recommended operation time. In the case that the first recommended operation time and the vth recommended operation time both belong to the s time period of the t day, if the first real-time data is different from the real-time data contained in the training set model feature corresponding to the vth recommended operation time, the first training data is different from the training set model feature corresponding to the vth recommended operation time, and then the first predicted application list is different from the predicted application list corresponding to the vth recommended operation time.

[0135] Optionally, each of the first, second and third recall weights can be dynamically calculated by using the recall rate of each path.

[0136] The multi-path recall model shown above learns the habits of the user in long-term, recent and real-time use of the application (APP) by using three paths of recall, and also uses the recall weight of each path to realize the fusion and sorting of multi-path recall. In this way, the multi-path recall model of the embodiments of the present application comprehensively considers the habits of the user in long-term, recent and real-time use of the application. In the case that the long-term, recent and real-time data are all considered, the accuracy of the order of the predicted application list according to the size of the use probability can be high.

[0137] Since the number of applications in the predicted application list of the prediction time period obtained by the multi-path recall model is determined according to the preset value N0, the multi-path recall model does not consider the change of the number of application uses of the user at different time periods, and therefore, it is necessary to accurately determine the application list corresponding to the prediction time based on the predicted application list of the prediction time period to kill the background running application in the case where the habit of the user using the application is stable, so as to reduce the power consumption of the electronic device. Therefore, S403 and S404 shown subsequently in the embodiments of the present application can judge the stability of the habit of the user using the application. Based on the judgment result of steps S403 and / or S404, the electronic device can determine whether to execute S405 or S407 subsequently.

[0138] S403, the electronic device can judge whether the dispersion of the prediction time period is greater than the dispersion threshold value.

[0139] Exemplarily, the electronic device can judge whether the first dispersion corresponding to the first time period of the tth day is greater than the dispersion threshold value.

[0140] If the first dispersion is greater than the dispersion threshold value, it indicates that the habit of the user using the application in the first time period of the tth day is greatly different from the habit of the user using the application in the first time period before the tth day, and in order to reduce the probability of the application used by the user in the first time period of the tth day being killed, the electronic device can execute step S407.

[0141] If the first dispersion is less than or equal to the dispersion threshold value, it can indicate that the habit of the user using the application in the first time period of the tth day is less different from the habit of the user using the application in the first time period before the tth day, or it indicates that the habit of the user using the application in the first time period is stable, and in order to further judge whether the habit of the user using the application in the first time period is stable, the electronic device can execute step S404.

[0142] The first dispersion can also indicate the difference between the number of application uses of the first time period of the tth day and the number of application uses of the first time period of the days before the tth day.

[0143] Optionally, if the first dispersion is less than or equal to the dispersion threshold value, the electronic device can execute step S405.

[0144] Exemplarily, the first dispersion can include a first variance or a first standard deviation. The dispersion threshold value can include a variance threshold value or a standard deviation threshold value.

[0145] The first variance is the variance of the number of application uses in the first time period in the L days before the tth day.

[0146] The first standard deviation is the standard deviation of the number of application uses in the first time period in the L days before the tth day.

[0147] If the first variance is greater than the variance threshold, or the first standard deviation is greater than the standard deviation threshold, it can be indicated that the habit of the user using the application in the first time period on the tth day is greatly different from the habit of the user using the application in the first time period before the tth day, so as to reduce the probability of the application used by the user in the first time period on the tth day being killed, the electronic device can execute step S407.

[0148] If the first variance is less than or equal to the variance threshold, or the first standard deviation is less than or equal to the standard deviation threshold, it can be indicated that the habit of the user using the application in the first time period on the tth day is less different from the habit of the user using the application in the first time period before the tth day, or it is indicated that the habit of the user using the application in the first time period is stable, and the electronic device can execute step S404 or S405.

[0149] Exemplarily, in the case that the tth day is a weekday, the first variance is the variance of the application usage quantity in the first time period of the weekdays in the L days before the tth day, and the first standard deviation is the standard deviation of the application usage quantity in the first time period of the weekdays in the L days before the tth day.

[0150] In the case that the tth day is a holiday, the first variance is the variance of the application usage quantity in the first time period of the holidays in the L days before the tth day, and the first standard deviation is the standard deviation of the application usage quantity in the first time period of the holidays in the L days before the tth day.

[0151] In this way, in the case of using the first variance or the first standard deviation to judge the stability of the habit of the user using the application in the first time period, the accuracy of the judgment can be improved.

[0152] Exemplarily, the first variance σ tsL 2 and the first standard deviation σ tsL satisfies the following formula (1):

[0153]

[0154] wherein x ts , p is the application usage quantity in the s th time period of the p th target day in the L days before the t th day, and n is the number of target days in the L days before the t th day. The target day satisfies: in the case that the t th day is a weekday, the target day is a weekday, and in the case that the t th day is a holiday, the target day is a holiday.

[0155] S404, the electronic device can judge whether the similarity of the prediction period is greater than a similarity threshold.

[0156] Exemplarily, the electronic device can determine whether the first similarity corresponding to the first time period of the t-th day is greater than a similarity threshold. The similarity threshold can be 0, 1, 2, or the like.

[0157] If the first similarity is greater than the similarity threshold, it indicates that the user's habit of using the application in the first time period of the t-th day is greatly different from the user's habit of using the application in the first time period before the t-th day. In order to reduce the probability that the application that the user will use in the first time period of the t-th day is killed, the electronic device can perform step S407.

[0158] If the first similarity is less than or equal to the similarity threshold, it can indicate that the user's habit of using the application in the first time period of the t-th day is less different from the user's habit of using the application in the first time period before the t-th day, or that the user's habit of using the application in the first time period is stable. In order to improve the probability that the application that the user will not use in the first time period of the t-th day is killed, the electronic device can perform step S405.

[0159] The first similarity can also represent the similarity between the number of applications used in the first time period and the number of applications used in the time period before the first time period.

[0160] Exemplarily, the first similarity is related to the number of applications used in the first time period of the t-th day and the number of applications used in the first time period of the t-th day.

[0161] K can be an integer greater than or equal to 2. Q can be an integer greater than or equal to 2. K and Q can be the same or different.

[0162] Exemplarily, in the case that the t-th day is a weekday, the first similarity is related to the number of applications used in the first time period of the K weekdays before the t-th day and the number of applications used in the first time period of the Q time periods before the t-th day.

[0163] In the case that the t-th day is a holiday, the first similarity is related to the number of applications used in the first time period of the K holidays before the t-th day and the number of applications used in the first time period of the Q time periods before the t-th day.

[0164] Exemplarily, the first similarity N wts Satisfies the following formula (2):

[0165] N wts = max[N w,ti,s , N w,t,sj ] (2)

[0166] N w,ti,s = N ti,s -A s . Nw,t,sj = N t , sj - A s . N ti,s is the application usage quantity of the s-th time period of the i-th target day before the t-th day. The i-th target day before the t-th day is spaced i-1 target days from the t-th day. t,sj is the application usage quantity of the j-th time period before the s-th time period of the t-th day. The j-th time period before the s-th time period of the t-th day is spaced j-1 time periods belonging to target days from the s-th time period of the t-th day. s is the application usage quantity of both the s-th time period of the i-th target day before the t-th day and the j-th time period before the s-th time period of the t-th day. i = 1, 2, …, K. j = 1, 2, …, Q. The target day satisfies: working day if the t-th day is a working day, holiday if the t-th day is a holiday.

[0167] Exemplarily, with 48 time periods in a day, and the s-th time period being 10:00-10:30, K = Q = 2, the first time period of the t-th day or the s-th time period of the t-th day being 10:00-10:30 on December 14, December 14 being a working day and being Tuesday, and the similarity threshold being 2, N ti , s and N t , sj may be determined or composed as shown in Table 3.

[0168] Table 3 N ti , s and N t , sj application usage quantity

[0169]

[0170] As shown in Table 3, the s-th time period of the 1st target day before the t-th day is 10:00-10:30 on December 13. The s-th time period of the 2nd target day before the t-th day is 10:00-10:30 on December 10. The 1st time period before the s-th time period of the t-th day is 09:30-10:00 on December 13. The 2nd time period before the s-th time period of the t-th day is 09:00-09:30 on December 13.

[0171] It can be understood that if the first recommended operation time is 10:00, 10:00 is the starting time point of the time period 10:00-10:30, the electronic device can determine that the first recommended operation time belongs to the time period 10:00-10:30, and the first recommended operation time does not belong to the time period 09:30-10:00.

[0172] As shown in Table 3, the application use quantity N t1 , s of the s time period of the first target day before the t day is 4. The application use quantity N t2 , s of the s time period of the second target day before the t day is 5. The application use quantity N t , s1 of the first time period before the s time period of the t day is 4. The application use quantity N t , s2 of the second time period before the s time period of the t day is 3. Take N t1 , s for example, N t1 , s is determined as follows: the number of starting time points of the application running in the foreground in the s time period of the first target day before the t day is added to obtain N t1，s .

[0173] As shown in Table 3, in the s time period of the i target day before the t day and the j time period before the s time period of the t day, there are 1 starting time point of the application B running in the foreground, 1 starting time point of the application C running in the foreground, and 1 starting time point of the application D running in the foreground, which indicates that the number of applications used in the s time period of the i target day before the t day and the j time period before the s time period of the t day is 1+1+1=3, that is, A s =3. Then, N w,t1,s =N t1，s -A s =4-3=1; N w,t2,s =N t2，s -A s =5-3=2; N w,t,s1 =N t，s1 -A s =4-3=1; N w,t,s2 =N t，s2 -A s =3-3=0.

[0174] Therefore, N wts =max[N w,ti,s ,N w,t,sj ]=max[Nw,t1,s N w,t2,s N w,t,s1 N w,t,s2 ] = max[1,2,1,0] = 2.

[0175] Since the similarity threshold is 2, the electronic device can execute S405.

[0176] It is understandable that if the s-th time period before the i-th target day and the j-th time period before the s-th time period on day t both contain 2 start times for application B running in the foreground, 1 start time for application C running in the foreground, and 1 start time for application D running in the foreground, then the number of applications used in the s-th time period before the i-th target day and the j-th time period before the s-th time period on day t can be 2+1+1=4.

[0177] The application usage data in the first time period during the K days prior to day t and the application usage data in the preceding Q time periods of the first time period on day t will affect the user's application usage in the first time period on day t. Therefore, based on the number of applications used in the first time period during the K days prior to day t, the number of applications used in the preceding Q time periods of the first time period on day t, and the number of applications used by the user in both the first time period during the K days prior to day t and the preceding Q time periods of the first time period on day t, a first similarity score is obtained. Using the first similarity score to judge the stability of the user's application usage habits in the first time period on day t can improve the accuracy of the judgment.

[0178] The first similarity score takes into account various factors.

[0179] S405. Electronic devices can acquire the number of targets for a predicted time period.

[0180] For example, an electronic device can obtain a target quantity for the first time period on day t. The target quantity for the first time period on day t is related to one or more of the following: the application usage quantity in the first time period over the L days prior to day t, the application usage quantity in the first time period over the K days prior to day t, and the application usage quantity over the Q time periods prior to the first time period on day t. The Q time periods are not part of the first time period.

[0181] For example, the target number for the first time period on day t is positively correlated with one or more of the following: the number of times the application was used in the first time period in the L days prior to day t, the number of times the application was used in the first time period in the K days prior to day t, and the number of times the application was used in the Q time periods prior to the first time period on day t.

[0182] Exemplarily, if holidays and workdays are not distinguished, the target number N ts0 satisfies the following formula (3):

[0183]

[0184] wherein N t-i,s is the application usage number of the s-th time period on the t-i-th day before the t-th day. N t,s-j is the application usage number of the s-j-th time period before the s-th time period on the t-th day. The s-j-th time period before the s-th time period on the t-th day is separated from the s-th time period on the t-th day by j-1 time periods. The length of the s-j-th time period can be the same as the length of the s-th time period. γ1 is a weight coefficient. γ2 is a weight coefficient. γ3 is a weight coefficient, and γ3 can be 0.005. σ tsL0 2 is the variance of the application usage number of the s-th time period on the t-i-th day before the t-th day, σ tsL0 2 *γ3 represents the weighting of the variance σ tsL0 2 . γ1 can be greater than γ3, and γ2 can be greater than γ3.

[0185] The user's use of the application in the first time period on the t-th day can be affected by the user's habit of using the application in the first time period, the application usage in the s-th time period on the t-i-th day before the t-th day, and the application usage in the s-j-th time period before the s-th time period on the t-th day. Therefore, as shown in formula (3), based on the application usage in the s-th time period on the t-i-th day before the t-th day (such as σ ), the application usage in the Q time periods before the s-th time period on the t-th day (such as σ ), and the stability of the user's habit of using the application in the s-th time period (such as σ tsL0 2 , the target number N ts0 of the first time period on the t-th day is predicted, which can improve the accuracy of the predicted target number of the first time period on the t-th day.

[0186] Exemplarily, if holidays and workdays are distinguished, in the case that the t-th day is a workday, the target number of the first time period on the t-th day is related to one or more of the following: the application usage number of the first time period on the workday among the L days before the t-th day, the application usage number in the first time period on the K workdays before the t-th day, and the application usage number in the Q time periods belonging to workdays before the first time period on the t-th day.

[0187] In the case that the tth day is a holiday, the target number of the first time period of the tth day is related to one or more of the following: the application usage number of the first time period of the holiday in the L days before the tth day, the application usage number in the first time period in the K holidays before the tth day, the application usage number of the Q time periods belonging to holidays before the first time period of the tth day.

[0188] Exemplarily, the target number N ts satisfies the following formula (4):

[0189]

[0190] wherein N ti,s is the application usage number of the s th time period of the i th target day before the t th day. The i th target day before the t th day is spaced i-1 target days from the t th day. N t,sj is the application usage number of the j th time period before the s th time period of the t th day. The j th time period before the s th time period of the t th day is spaced j-1 time periods belonging to target days from the s th time period of the t th day. The length of the j th time period can be the same as the length of the s th time period. γ1 is a weight coefficient. γ2 is a weight coefficient. γ3 is a weight coefficient, and γ3 can be 0.005. σ tsL 2 is the variance of the application usage number of the s th time period of the target day in the L days before the t th day. σ tsL 2 *γ3 represents the weighting of the variance σ tsL 2 . The target day satisfies: in the case that the t th day is a working day, the target day is a working day; in the case that the t th day is a holiday, the target day is a holiday. * is a multiplication sign. For example, σ tsL 2 *γ3 represents σ tsL 2 ×γ3.

[0191] Since the habit of the user using the application on a working day can be different from the habit of the user using the application on a holiday, as shown in formula (4), based on the application usage in the s th time period in the K target days before the t th day (such as ), the application usage of the Q time periods belonging to target days before the s th time period of the t th day (such as ), and the habit stability of the user using the application in the s th time period of the target day (such as σ tsL 2 , the target number N ts of the first time period of the t th day can be predicted, which can further improve the accuracy of the predicted target number of the first time period of the t th day.

[0192] S406, based on the prediction application list corresponding to the prediction period and the target number of the prediction period, obtaining the target application list corresponding to the prediction period, and using the target application list corresponding to the prediction period to kill the application running in the background.

[0193] For example, based on the first prediction application list and the target number N ts of the first time period of the t-th day, the first target application list corresponding to the first time period of the t-th day is obtained, and the first target application list is used to kill the application running in the background. The first target application list can also be referred to as the target application list corresponding to the first recommended operation time.

[0194] For example, in the case of obtaining the first prediction application list and the target number of the first time period of the t-th day, the electronic device can intercept the first N ts applications from the first prediction application list to form the first target application list, and use the first target application list to kill the application running in the background. Since N ts <N0, in the case that the user's habit of using the application in the first time period is stable, compared with using the first prediction application list to kill the application running in the background, using the first target application list to kill the application running in the background can improve the probability that the application not used by the user in the first time period is killed, and thus can reduce the power consumption of the electronic device.

[0195] Alternatively, the target number of the first time period of the t-th day can also be N ts0 , and N ts0 <N0. The specific implementation principles and technical effects in the case that the target number of the first time period of the t-th day is N ts0 are similar to those in the case that the target number of the first time period of the t-th day is N ts , which will not be described here.

[0196] S407, using the prediction application list corresponding to the prediction period to kill the application running in the background.

[0197] For example, in the case that the first variance is greater than the variance threshold, or the first standard deviation is greater than the standard deviation threshold, using the first prediction application list to kill the application running in the background can reduce the probability of killing the application that will be used by the user in the first time period, and can improve the user experience.

[0198] Optionally, in a case where the first standard deviation is greater than the standard deviation threshold and the first similarity is greater than the similarity threshold, or in a case where the first standard deviation is greater than the standard deviation threshold and the first similarity is greater than the similarity threshold, the first prediction application list is used to kill the application running in the background, which can reduce the probability that the application to be used by the user in the first time period is killed, and can improve the user experience.

[0199] The application control method provided in the embodiments of the present application can obtain first data corresponding to a first time period to which a first recommendation operation moment belongs in a case where the first recommendation operation is received, input the first data into a multi-path recall model, and obtain a first prediction application list. In a case where it is judged that the habit of the user using the application in the first time period is stable, the electronic device can predict the number of applications that the user is likely to use in the first time period to which the first recommendation operation moment belongs, obtain a target number (such as N ts ) of the first time period to which the first recommendation operation moment belongs, and obtain a first target application list composed of the first N ts applications in the first prediction application list. The electronic device can use the first target application list to kill the application running in the background, which can improve the probability that the application not to be used by the user in the first time period to which the first recommendation operation moment belongs is killed, and further can reduce the power consumption of the electronic device and reduce the probability that the endurance time of the electronic device is short. In a case where it is judged that the habit of the user using the application in the first time period is not stable, the electronic device can use the first prediction application list to kill the application running in the background, which can reduce the probability that the application to be used by the user in the first time period to which the first recommendation operation moment belongs is killed, and further can improve the user experience.

[0200] Figure 5 An architecture schematic diagram of the multi-path recall model provided in the embodiments of the present application is shown.

[0201] As shown in Figure 5 , the multi-path recall model includes a recall layer and a ranking layer. The recall layer can include a first path recall using a classification and regression tree (CART) algorithm, a second path recall using a recent hot recall algorithm, and a third path recall using a time decay algorithm. The first path recall can be referred to as a CART decision tree recall. The second path recall can be referred to as a recent hot recall. The third path recall can be referred to as a recent use recall.

[0202] In possible implementation manners, the electronic device can be in a cold start phase or can be in a normal phase.

[0203] Exemplarily, still taking the time of the first recommended operation moment belonging to the first time period of the t-th day as an example, if the sum β of the application usage quantities of the first time period of the L days before the t-th day satisfies 201≤β≤800, it indicates that the electronic device belongs to the cold start stage. Exemplarily, the number of days from the date when the user first uses the electronic device to the t-th day is less than or equal to U, which can also indicate that the electronic device is in the cold start stage.

[0204] If the sum β of the application usage quantities of the first time period of the L days before the t-th day satisfies 800<β, it indicates that the electronic device belongs to the cold start stage. Exemplarily, the number of days from the date when the user first uses the electronic device to the t-th day is greater than U, which can also indicate that the electronic device is in the normal stage.

[0205] Optionally, the manner in which the electronic device in the normal stage obtains the predicted application list of the prediction period can be different from the manner in which the electronic device in the cold start stage obtains the predicted application list of the prediction period.

[0206] Exemplarily, still taking the time of the first recommended operation moment belonging to the first time period of the t-th day as an example.

[0207] For the scenario in which the electronic device is in the normal stage, in the case that the electronic device receives the first recommended operation, the electronic device can Figure 4 In the embodiment shown as S402, the electronic device can process the first long-term data, the first recent data and the first real-time data by using the three-way recall in the multi-way recall model, and process and sort the results of the three-way recall to obtain the first predicted application list. Exemplarily, the first data obtained by the electronic device can include a data set representing the first long-term data, a data set representing the first recent data and a data set representing the first real-time data. In the case that the electronic device obtains the first data, if the electronic device identifies that the dates corresponding to the first long-term data in the first data are different from the dates corresponding to the first recent data, or the number of dates corresponding to the first long-term data is greater than the number of dates corresponding to the first recent data, it can indicate that the electronic device is in the normal stage, and the electronic device can mark the data set representing the first long-term data as a first identifier, mark the data set representing the first recent data as a second identifier, and mark the data set representing the first real-time data as a third identifier. In the case that the electronic device inputs the first data into the preset model, the first-way recall can process the data set of the first identifier, the second-way recall can process the data set of the second identifier, and the third-way recall can process the data set of the third identifier.

[0208] In a scenario where the electronic device is in a cold start stage, in a case where the electronic device receives a first recommended operation, since the number of days from the first use of the electronic device by the user to the t-th day is less than or equal to U. In a case where the electronic device obtains first data, if the electronic device identifies that the dates corresponding to the first long-term data in the first data are the same as the dates corresponding to the first recent data, or the number of dates corresponding to the first long-term data in the first data is the same as the number of dates corresponding to the first recent data, it can be indicated that the electronic device is in a cold start stage, or the first long-term data and the first recent data in the first data are the same, the electronic device can clear the data set representing the first long-term data, mark the data set representing the first recent data as a second identifier, and mark the data set representing the first real-time data as a third identifier.

[0209] In a case where the electronic device inputs the first data into the preset model, the second recall can process the data set of the second identifier to obtain the second weight of each application corresponding to the first recent data. The third recall can process the data set of the third identifier to obtain the third weight of each application corresponding to the first real-time data.

[0210] The ranking layer in the multi-recall model obtains the fifth weight of each application based on the second weight and the third weight of each application. The ranking layer in the multi-recall model ranks the plurality of applications corresponding to the first data in order of the fifth weight of the application to obtain a first ranking list. The electronic device can intercept the first N0 applications in the first ranking list to form a first predicted application list.

[0211] The specific implementation principle of the second weight of the application can be referred to the specific implementation principle of the second weight of the application in S402 in Figure 4 The specific implementation principle of the third weight of the application can be referred to the specific implementation principle of the third weight of the application in S402 in Figure 4 The fifth weight of the application is the sum of the second weight of the application and the third weight of the application. For example, the fifth weight of the application A is the sum of the second weight of the application A and the third weight of the application A.

[0212] Since the first recall has a requirement on the data volume of the data to be processed, if the data volume of the data processed by the first recall is less than or equal to the data volume of the data processed by the second recall, the accuracy of the processing result obtained by the first recall processing can be poor. The data volume of the first long-term data when the electronic device is in the cold start stage is the same as the data volume of the first recent data, and the data volume of the first long-term data does not reach the data volume requirement of the data to be processed by the first recall. Therefore, in the scenario that the electronic device is in the cold start stage, the first long-term data is cleared, and the multi-recall model processes and sorts the first recent data and the first real-time data, which can reduce the influence of the processing result with low accuracy obtained by the first recall processing on the accuracy of the first prediction application list, and further an accurate first prediction application list can be obtained.

[0213] The embodiment of the present application also provides an application control method applied to an electronic device, the method comprising:

[0214] In the first time period of the t-th day, the electronic device has M applications running in the background, and the M applications are killed by using a first application list.

[0215] In the second time period of the t-th day, the electronic device has N applications running in the background, and the N applications are killed by using a second application list, the number of applications in the second application list is different from the number of applications in the first application list, the first time period is different from the second time period, and M and N are integers.

[0216] Exemplarily, taking the first application list obtained by the electronic device in response to a first recommendation operation as an example, the first recommendation operation time belongs to the s-th time period of the t-th day, the first application list can be a first target application list. For example, in response to the first recommendation operation, the electronic device can execute S401-S406 in Figure 4 , or execute S401-S403, S405 and S406 in Figure 4 , or execute S401-S402 and S404-S406 in Figure 4 , so that the electronic device kills the M applications by using the first target application list in the first time period, which can improve the probability that the applications not to be used by the user in the first time period of the t-th day are killed, and further reduce the power consumption of the electronic device.

[0217] It can be understood that the first application list can also be a first prediction application list. For example, in response to the first recommendation operation, the electronic device can execute S401-S403 and S407 in Figure 4 , so that the electronic device kills the M applications by using the first prediction application list in the first time period, which can reduce the probability that the applications to be used by the user in the first time period of the t-th day are killed.

[0218] Exemplarily, taking the second application list obtained by the electronic device in response to the second recommendation operation as an example, the second recommendation operation time belongs to the second time period of the t-th day, the second application list can be a second predicted application list. For example, in response to the second recommendation operation, the electronic device can process the training set model features corresponding to the second time period of the t-th day by using the multi-path recall model to obtain the second predicted application list. In the case where it is judged that the user's habit of using the application in the second time period is unstable, the electronic device uses the second predicted application list to kill N applications. The specific implementation principle and technical effect of the electronic device using the multi-path recall model to process the training set model features corresponding to the second time period of the t-th day to obtain the second predicted application list are similar to those of the electronic device using the multi-path recall model to process the first data to obtain the first predicted application list, and will not be described here.

[0219] The specific implementation principle and technical effect of the electronic device using the second predicted application list to kill N applications in the second time period of the t-th day are similar to those of the electronic device using the first predicted application list to kill M applications in the first time period of the t-th day, and will not be described here.

[0220] It can be understood that the second application list can also be a second target application list. For example, in response to the second recommendation operation, the electronic device can obtain the second predicted application list. In the case where it is judged that the user's habit of using the application in the second time period is stable, the electronic device can intercept the target number of applications in the second time period of the t-th day from the second predicted application list to form a second target application list, and use the second target application list to kill N applications.

[0221] The specific implementation principle of the electronic device obtaining the target number of applications in the second time period of the t-th day is similar to that of the electronic device obtaining the target number of applications in the first time period of the t-th day. The specific implementation principle of the electronic device judging whether the user's habit of using the application in the second time period is stable is similar to that of the electronic device judging whether the user's habit of using the application in the first time period is stable, and will not be described here.

[0222] It can be understood that the specific implementation principle and technical effect of the electronic device using the second target application list to kill N applications in the second time period of the t-th day are similar to those of the electronic device using the first target application list to kill M applications in the first time period of the t-th day, and will not be described here.

[0223] Exemplarily, as shown in Table 4, the application control method provided by the embodiments of the present application can obtain application lists for killing background applications in different time periods.

[0224] Table 4 Application in application list corresponding to different time period

[0225]

[0226] It should be understood that the time periods shown in Table 4 can be time periods belonging to the same day. The time periods shown in Table 4 can also belong to different days. The application list of each time period shown in Table 4 is the application list corresponding to one time point in the time period. The application list corresponding to different time points in a time period can be different. For example, the application list corresponding to the first time period is the application list corresponding to one time point in the first time period.

[0227] As shown in Table 4, the application control method provided by the embodiments of the present application can obtain application lists corresponding to different time periods, and the number of applications in the application lists corresponding to different time periods is different. The application control method provided by the embodiments of the present application can kill the applications running in the background by using the corresponding application list in different time periods, which can improve the probability that the applications not used by the user are killed, thereby reducing the power consumption of the electronic device, and can also reduce the probability that the applications used by the user are killed, thereby improving the user experience.

[0228] Next, the application control method provided by the embodiments of the present application will be described by taking the first application list as the first target application list and the second application list as the second predicted application list as an example.

[0229] Optionally, the first application list is obtained by the following method:

[0230] When the first time period of the t-th day is reached, a first predicted application list of the first time period of the t-th day is obtained by using a preset model. A target number of applications in the first predicted application list are selected to obtain the first application list.

[0231] The preset model is used to output the first predicted application list under the condition that the application usage data of the first time period in the L days before the t-th day is input, and the application usage data of the R times of using the application before the first recommended operation time point is input. The first recommended operation time point is the time point when the first time period of the t-th day is reached. The application usage data includes the start time of the application running in the foreground and the application identifier. The target number is related to one or more of the following: the number of applications used in the first time period in the L days before the t-th day, the number of applications used in the first time period in the K days before the t-th day, the number of applications used in the Q time periods before the first time period of the t-th day, and the Q time periods do not belong to the first time period. It can be understood that the first application list can be the application list corresponding to the first recommended operation time point.

[0232] Exemplarily, the preset model can be Figure 3The multi-path recall model shown in the embodiment. In the embodiment of the application, the first prediction application list of the first time period is obtained by using a preset model, a target number of applications are selected from the first prediction application list, and the specific implementation principle of obtaining the first application list is similar to Figure 3 The specific implementation principle of obtaining the first target application list by the electronic device in the embodiment is similar, and will not be described here.

[0233] In this way, the preset model considers the size order of the possible application use probability of the user in the first time period. The first application list composed of the target number of applications selected from the first prediction application list output by the preset model also considers the possible application use quantity of the user in the first time period, improves the accuracy of the first application list, and can improve the probability that the application that will not be used by the user in the first time period is killed, so as to reduce the power consumption of the electronic device.

[0234] Optionally, the target number of the first time period is positively correlated with one or more of the following: the application use quantity in the first time period in the L days before the t-th day, the application use quantity in the first time period in the K days before the t-th day, and the application use quantity in the Q time periods before the first time period of the t-th day.

[0235] Exemplarily, the target number of the first time period is positively correlated with one or more of the following, and the target number of the first time period can satisfy Figure 4 Formula (3) in the embodiment.

[0236] In this way, the target number of the first time period is predicted based on the application use quantity in the first time period in the L days before the t-th day, the application use quantity in the first time period in the K days before the t-th day, and the application use quantity in the Q time periods before the first time period of the t-th day, which can improve the prediction accuracy of the target number of the first time period.

[0237] Optionally, in the case that the t-th day is a weekday, the target number is related to one or more of the following: the application use quantity in the first time period of the weekday in the L days before the t-th day, the application use quantity in the first time period in the K weekdays before the t-th day, and the application use quantity in the Q time periods belonging to the weekday before the first time period of the t-th day.

[0238] In the case that the t-th day is a holiday, the target number is related to one or more of the following: the application use quantity in the first time period of the holiday in the L days before the t-th day, the application use quantity in the first time period in the K holidays before the t-th day, and the application use quantity in the Q time periods belonging to the holiday before the first time period of the t-th day.

[0239] In this way, since the habits of the user using the application on weekdays can be different from the habits of the user using the application on holidays, distinguishing the date type of the t-th day can further improve the prediction accuracy of the target number of the first time period.

[0240] Optionally, the first time period of the t-th day is the s-th time period of the t-th day. The target number N ts satisfies formula (4).

[0241] In this way, based on the application usage in the s-th time period of the K target days before the t-th day (such as ), the application usage in the Q time periods belonging to the target days before the s-th time period of the t-th day (such as ), and the habit stability of the user using the application in the s-th time period of the target day (such as tsL 2 ), the target number N ts of the first time period of the t-th day is predicted, which can further improve the accuracy of the prediction of the target number of the first time period of the t-th day.

[0242] Optionally, the plurality of applications in the first prediction list are arranged in order of the size of the application usage probability.

[0243] Selecting the target number of applications in the first prediction application list to obtain a first application list, comprising: cutting off the first N ts applications from the first prediction application list to form the first application list. N ts is the target number of the first time period of the t-th day.

[0244] In this way, the applications in the first application list can also be arranged in order of the size of the application usage probability. In the case that the electronic device adopts the first application list to kill the background running applications, if the background running applications whose application identifiers are in the first application list need to be killed in order to make the electronic device have enough available memory, the electronic device can preferentially kill the applications at the tail of the first application list. It should be understood that the usage probability of the applications at the tail of the first application list is smaller than the usage probability of the applications at the top of the first application list, so as to reduce the probability that the applications that the user will use are killed.

[0245] Optionally, before the M applications are killed by using the first application list, the method further comprises:

[0246] determine whether the first similarity corresponding to the first time period of the t-th day is greater than a similarity threshold value, and / or whether the first dispersion corresponding to the first time period of the t-th day is greater than a dispersion threshold value. The first similarity represents a similarity between the application usage quantity of the first time period of the t-th day and the application usage quantity of a time period before the first time period of the t-th day, and the first dispersion represents a difference between the application usage quantity of the first time period of the t-th day and the application usage quantity of the first time period of a plurality of days before the t-th day.

[0247] The first application list is used to kill the M applications, including:

[0248] In a case where the first similarity is less than or equal to the similarity threshold value, and / or the first dispersion is less than or equal to the dispersion threshold value, the first application list is used to kill the M applications.

[0249] In this way, if the first similarity is less than or equal to the similarity threshold value, and / or the first dispersion is less than or equal to the dispersion threshold value, it can be indicated that the user's habit of using the application in the first time period is stable, and the first application list is used for killing, which can improve the probability that an application that will not be used by the user in the first time period of the t-th day is killed, and reduce the power consumption of the electronic device.

[0250] Optionally, the second time period of the t-th day belongs to the time periods of the t-th day. The second application list includes a second predicted application list, which is obtained by using a preset model when the second time period of the t-th day is reached. The preset model is also used to output the second predicted application list when the application usage data in the second time period of the L days before the t-th day and the application usage data of the R times of using the application before the second recommended operation time are input. The second recommended operation time is a time when the second time period of the t-th day is reached.

[0251] Before the N applications are killed by using the second application list, the method further includes:

[0252] determine whether the second similarity corresponding to the second time period of the t-th day is greater than a similarity threshold value, and / or whether the second dispersion corresponding to the second time period of the t-th day is greater than a dispersion threshold value. The second similarity represents a similarity between the application usage quantity of the second time period of the t-th day and the application usage quantity of a time period before the second time period of the t-th day, and the second dispersion represents a difference between the application usage quantity of the second time period of the t-th day and the application usage quantity of the second time period of a plurality of days before the t-th day.

[0253] The second application list is used to kill the N applications, including:

[0254] In a case where the second similarity is greater than the similarity threshold and / or the second dispersion is greater than the dispersion threshold, the second predicted application list is used to kill the N applications.

[0255] In this way, if the second similarity is greater than the similarity threshold and / or the second dispersion is greater than the dispersion threshold, it can be indicated that the user's habit of using applications in the second time period is unstable, and using the second predicted application list for killing can reduce the probability that the applications that the user will use in the second time period on the tth day are killed, thereby improving the user experience.

[0256] Optionally, the first dispersion includes a first variance or a first standard deviation. The first variance is a variance of the number of applications used in the first time period in the L days before the tth day. The first standard deviation is a standard deviation of the number of applications used in the first time period in the L days before the tth day.

[0257] The first similarity is related to the number of applications used in the first time period in the K days before the tth day and the number of applications used in the first time period in the Q time periods before the tth day.

[0258] In this way, based on the variance or the standard deviation of the number of applications used in the first time period in the L days before the tth day, the habit stability of the user in using applications in the first time period can be determined, and accurate determination of the habit stability of the user in using applications can be achieved. Based on the first similarity, the habit stability of the user in using applications in the first time period can be determined. The first similarity can be determined based on the number of applications used in the first time period in the K days before the tth day and the number of applications used in the first time period in the Q time periods before the tth day, and accurate determination of the habit stability of the user in using applications can be achieved.

[0259] Optionally, in a case where the tth day is a weekday, the first variance is a variance of the number of applications used in the first time period on weekdays in the L days before the tth day, and the first standard deviation is a standard deviation of the number of applications used in the first time period on weekdays in the L days before the tth day. The first similarity is related to the number of applications used in the first time period in the K weekdays and the number of applications used in the first time period in the Q time periods before the tth day.

[0260] In a case where the tth day is a holiday, the first variance is a variance of the number of applications used in the first time period on holidays in the L days before the tth day, and the first standard deviation is a standard deviation of the number of applications used in the first time period on holidays in the L days before the tth day. The first similarity is related to the number of applications used in the first time period in the K holidays and the number of applications used in the first time period in the Q time periods before the tth day.

[0261] In this way, by distinguishing the date type of the tth day, the accuracy of the determination of the habit stability of the user in using applications can be further improved.

[0262] Optionally, the first time period of the tth day is the s th time period of the tth day. The first similarity N wts The formula (2) is satisfied.

[0263] The application usage of the user in the first time period of the tth day is influenced by the application usage in the first time period of the K days before the tth day and the application usage in the first time period of the Q days before the tth day. In this way, based on the number of applications used in the first time period of the K days before the tth day, the number of applications used in the first time period of the Q days before the tth day, and the number of applications used by the user in the first time period of the K days before the tth day and the first time period of the Q days before the tth day, the first similarity is obtained, and the first similarity is used to judge the habit stability of the user in the first time period of the tth day, which can improve the accuracy of the judgment.

[0264] Optionally, the first time period of the tth day is the s th time period of the tth day. The first variance σ tsL 2 The first standard deviation σ tsL The formula (1) is satisfied.

[0265] In this way, in the case of using the first variance or the first standard deviation to judge the habit stability of the user in the first time period, the accuracy of the judgment can be improved.

[0266] Optionally, the first time period of the tth day is the s th time period of the tth day, and the preset model is a multi-path recall model.

[0267] The first prediction application list of the first time period is obtained by using the preset model, and the first prediction application list includes:

[0268] The first data corresponding to the first time period is obtained. The first data includes first long-term data, first recent data, and first real-time data. The first long-term data includes application usage data of the s th time period of the target day in the L days before the tth day, the recent data includes application usage data of the s th time period of the U target days before the tth day, and the real-time data includes application usage data of R times of using the application before the first recommendation operation time.

[0269] The first data is processed by using the multi-path recall model in the following manner to obtain the first prediction application list:

[0270] The classification and regression tree (CART) algorithm in the multi-path recall model is used to calculate the long-term data to obtain the first weight of each application corresponding to the long-term data. The recently popular recall algorithm in the multi-path recall model is used to calculate the recent data to obtain the second weight of each application corresponding to the recent data. The time decay algorithm in the multi-path recall model is used to calculate the real-time data to obtain the third weight of each application corresponding to the real-time data.

[0271] The first data corresponding to the plurality of applications are sorted according to the fourth weight of the application in descending order to obtain a first sorting list. The fourth weight of the application is the sum of the first weight of the application, the second weight of the application and the third weight of the application. The fourth weight of the application is related to the first use probability of the application.

[0272] The first N0 applications in the first sorting list are obtained to form a first prediction application list, where N0 is a preset value, and N0 is greater than the target number.

[0273] Exemplarily, the specific implementation principle of the embodiment of the present application can be referred to Figure 4 the specific implementation principle of S402 in the embodiment of the present application.

[0274] In this way, the multi-path recall model learns the habits of users in using applications (APPs) in the long term, the recent term and the real time, respectively, by using three-path recall, and also uses the weight of each path recall to realize multi-path recall fusion sorting. The multi-path recall model comprehensively considers the habits of users in using applications in the long term, the recent term and the real time. In the case that the long-term, recent and real-time data are all considered, the accuracy of the prediction application list output by the multi-path recall model can be improved in the order of the size of the use probability.

[0275] Optionally, the tth day contains forty-eight time periods, and adjacent two time periods in the forty-eight time periods do not overlap in time, and the time length of each time period in the forty-eight time periods is the same.

[0276] It can be understood that the tth day contains forty-eight time periods, and the time length of each time period can be 30 minutes (min). In this way, in the case that the recommendation operation is received, the electronic device can obtain the application list of the time period in which the recommendation operation time point is located, and the electronic device can use the application list to kill the application running in the background, so as to reduce the power consumption of the electronic device in the case of accurate killing.

[0277] It should be noted that the module names involved in the embodiments of the present application can be defined as other names, as long as the functions of the modules can be realized, and the names of the modules are not limited specifically.

[0278] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0279] The application control method of the embodiments of the present application has been described above, and the device for executing the above method provided by the embodiments of the present application will be described below. Those skilled in the art can understand that the method and the device can be combined and referred to each other, and the related device provided by the embodiments of the present application can execute the steps in the above application control method.

[0280] The application control method provided by the embodiments of the present application can be applied in an electronic device with communication function. The electronic device includes a terminal device, and the specific device form of the terminal device can refer to the above related description, which will not be described here.

[0281] The embodiments of the present application provide an electronic device, which includes a processor and a memory. The memory stores computer execution instructions. The processor executes the computer execution instructions stored in the memory, so that the electronic device executes the above method.

[0282] The embodiments of the present application provide a chip. The chip includes a processor, which is used to call a computer program in a memory to execute the technical solutions in the above embodiments. The implementation principle and technical effects are similar to those of the above related embodiments, which will not be described here.

[0283] The embodiments of the present application provide a chip system. The chip system includes at least one processor and a communication interface, the communication interface and the at least one processor are interconnected through a line, and the at least one processor is used to run a computer program or instructions to execute the above method.

[0284] The embodiments of the present application also provide a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by the processor to realize the above method. The method described in the above embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. If realized in software, the functions can be stored as one or more instructions or codes on a computer readable medium or transmitted on a computer readable medium. The computer readable medium can include computer storage medium and communication medium, and can also include any medium that can transfer computer programs from one place to another. The storage medium can be any target medium accessible by a computer.

[0285] In a possible implementation, the computer readable medium can include a RAM, a ROM, a compact disc read-only memory (CD-ROM) or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that is suitable for storing desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray® disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer readable media.

[0286] The embodiment of the present application provides a computer program product, which comprises a computer program, and when the computer program is executed, the computer executes the above method.

[0287] The embodiment of the present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiment of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices generate a device for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The device for implementing the functions specified in one flow or multiple flows and / or blocks Figure 1 The device for implementing the functions specified in one flow or multiple flows and / or blocks

[0288] The above detailed description further describes the purpose, technical scheme, and beneficial effects of the present application. It should be understood that the above is only a specific embodiment of the present application, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made on the basis of the technical scheme of the present application should be included in the protection scope of the present application.

Claims

1. An application control method, characterized in that, Applied to electronic devices, the method includes: During the first time period of day t, M applications are running in the background of the electronic device. The first application list is used to detect and kill the M applications. During the second time period on day t, N applications are running in the background of the electronic device. The N applications are detected and killed using a second application list. The number of applications in the second application list is different from the number of applications in the first application list. The first time period is different from the second time period. M and N are both integers. The first application list is obtained in the following way: When the first time period of the t-th day is reached, the first prediction application list of the first time period of the t-th day is obtained by using a preset model; Select the target number of applications from the first predicted application list to obtain the first application list; The target quantity is related to one or more of the following: the number of times the application was used in the first time period during the L days prior to day t, the number of times the application was used in the first time period during the K days prior to day t, the number of times the application was used in the Q time periods prior to the first time period on day t, wherein the Q time periods do not belong to the first time period; and the values ​​of L and K are different.

2. The method according to claim 1, characterized in that, The preset model is used to output the first predicted application list when given application usage data in the first time period during the L days prior to day t, and application usage data of the application used R times before the first recommended operation time; the first recommended operation time is the time when the first time period of day t is reached; the application usage data includes the start time of the application running in the foreground and the application identifier.

3. The method according to claim 2, characterized in that, The target quantity is positively correlated with one or more of the following: the number of times the application was used in the first time period during the L days prior to day t, the number of times the application was used in the first time period during the K days prior to day t, and the number of times the application was used in the Q time periods prior to the first time period on day t.

4. The method according to claim 2 or 3, characterized in that, When day t is a workday, the target quantity is related to one or more of the following: the application usage quantity during the first time period on workdays in the L days prior to day t, the application usage quantity during the first time period in the K workdays prior to day t, and the application usage quantity during the Q time periods belonging to workdays prior to the first time period on day t. If day t is a holiday, the target quantity is related to one or more of the following: the application usage quantity during the first time period of the holidays in the L days prior to day t, the application usage quantity during the first time period of the K holidays prior to day t, and the application usage quantity during the Q time periods that are holidays prior to the first time period of day t.

5. The method according to claim 2 or 3, characterized in that, The first time period on day t is the s-th time period on day t; the target quantity Satisfy the following formula: in, The application usage count is the number of times the application occurs during the s-th time period on the i-th target day prior to the t-th day, where the i-th target day prior to the t-th day is separated from the t-th day by an interval of i-1 target days. The number of times the application is used in the j-th time period before the s-th time period on day t, where the j-th time period before the s-th time period on day t is separated from the s-th time period on day t by a time interval of j-1 time periods belonging to the target day. These are the weighting coefficients. These are the weighting coefficients. These are the weighting coefficients. The variance of the number of applications used in the s-th time period of the target day in the L days prior to the t-th day. Variance The target day is a working day if the t-th day is a working day, and a public holiday if the t-th day is a public holiday.

6. The method according to claim 2 or 3, characterized in that, The multiple applications in the first predicted application list are arranged in order of their application usage probability; The step of selecting a target number of applications from the first predicted application list to obtain the first application list includes: Extracting from the first list of predictive applications The first application list consists of [number] applications; The target quantity.

7. The method according to claim 2 or 3, characterized in that, Before scanning and removing the M applications using the first application list, the method further includes: Determine whether the first similarity corresponding to the first time period on day t is greater than a similarity threshold, and / or whether the first dispersion corresponding to the first time period on day t is greater than a dispersion threshold; The first similarity represents the similarity between the number of applications used in the first time period on day t and the number of applications used in the time periods preceding the first time period on day t; the first dispersion represents the difference between the number of applications used in the first time period on day t and the number of applications used in the first time period on the previous days. The step of scanning and eliminating the M applications using the first application list includes: If the first similarity is less than or equal to the similarity threshold, and the first dispersion is less than or equal to the dispersion threshold, and it is determined that the user's application usage habits are stable during the first time period on day t, then the first application list is used to detect and remove the M applications.

8. The method according to claim 7, characterized in that, The second time period on day t belongs to the time period on day t; the method further includes: When the second time period of the t-th day is reached, the preset model is used to predict and obtain the second predicted application list for the second time period of the t-th day; wherein, the preset model is also used to output the second predicted application list when inputting application usage data in the second time period in the L days before the t-th day, and application usage data of the R times the application is used before the second recommended operation time; the second recommended operation time is the time when the second time period of the t-th day is reached; Before using the second application list to detect and remove the N applications, the method further includes: Determine whether the second similarity corresponding to the second time period on day t is greater than the similarity threshold, and / or whether the second dispersion corresponding to the second time period on day t is greater than the dispersion threshold; The second similarity represents the similarity between the number of applications used in the second time period on day t and the number of applications used in the time periods preceding the second time period on day t; the second dispersion represents the difference between the number of applications used in the second time period on day t and the number of applications used in the second time period on the previous days. The step of using a second application list to detect and remove the N applications includes: If the second similarity is greater than the similarity threshold and / or the second dispersion is greater than the dispersion threshold, it is determined that the user's application usage habits during the second time period on day t are unstable. In this case, the second predicted application list is used as the second application list to detect and eliminate the N applications.

9. The method according to claim 8, characterized in that, The first dispersion includes a first variance or a first standard deviation; the first variance is the variance of the number of applications used in the first time period during the L days prior to day t; the first standard deviation is the standard deviation of the number of applications used in the first time period during the L days prior to day t. The first similarity is related to the number of times the application was used in the first time period in the K days prior to day t and the number of times the application was used in the Q time periods preceding the first time period on day t.

10. The method according to claim 9, characterized in that, When day t is a workday, the first variance is the variance of the number of applications used in the first time period during the workdays in the L days prior to day t, and the first standard deviation is the standard deviation of the number of applications used in the first time period during the workdays in the L days prior to day t; the first similarity is related to the number of applications used in the first time period during the K workdays prior to day t and the number of applications used in the Q time periods prior to the first time period on day t. When day t is a holiday, the first variance is the variance of the number of applications used in the first time period during the holidays in the L days prior to day t, and the first standard deviation is the standard deviation of the number of applications used in the first time period during the holidays in the L days prior to day t; the first similarity is related to the number of applications used in the first time period during the K holidays prior to day t and the number of applications used in the Q time periods prior to the first time period on day t.

11. The method according to claim 10, characterized in that, The first time period on day t is the s-th time period on day t; the first similarity Satisfy the following formula: in, , The application usage count is the number of times the application occurs during the s-th time period prior to the ith target day, where the ith target day is separated from the ith target day by an interval of i-1 target days. The number of times the application is used in the j-th time period before the s-th time period on the t-th day, where the j-th time period is separated from the s-th time period on the t-th day by a time interval of j-1 time periods belonging to the target day. Let i = 1, 2, ..., K, and j = 1, 2, ..., Q, where i is the number of applications used in both the s-th and j-th time periods of the i-th target day, and j is the number of applications used in both the s-th and j-th time periods of the i-th target day. The target day satisfies the following conditions: the target day is a working day if the t-th day is a working day, and the target day is a public holiday if the t-th day is a public holiday. K is the number of days, used to indicate the K days preceding the t-th day. Q is the number of time periods, used to indicate the Q time periods preceding the first time period of the t-th day.

12. The method according to any one of claims 9-11, characterized in that, The first time period on day t is the s-th time period on day t; the first variance and the first standard deviation Satisfy the following formula: in, The number of times the application is used during the s-th time period of the p-th target day in the L days prior to the t-th day, where n is the number of target days in the L days prior to the t-th day. The target day satisfies the following conditions: if day t is a working day, the target day is a working day; if day t is a public holiday, the target day is a public holiday.

13. The method according to any one of claims 2-3 and 8-11, characterized in that, The first time period of day t is the s-th time period of day t, and the preset model is a multi-path recall model; The first prediction application list obtained by using a preset model for the first time period includes: Obtain the first data corresponding to the first time period; the first data includes first long-term data, first recent data and first real-time data, the first long-term data includes the application usage data of the s-th time period of the target day in the L days before the t-th day, the recent data includes the application usage data of the s-th time period of the U target days before the t-th day, and the real-time data includes the application usage data of the application used R times before the first recommended operation time; The first data is processed using a multi-path recall model as follows to obtain the first prediction application list: The classification and regression tree CART algorithm in the multi-path recall model is used to calculate the first weight of each application corresponding to the long-term data; the recent popular recall algorithm in the multi-path recall model is used to calculate the second weight of each application corresponding to the recent data; and the time decay algorithm in the multi-path recall model is used to calculate the third weight of each application corresponding to the real-time data. The applications corresponding to the first data are sorted according to their fourth weight to obtain a first sorted list; the fourth weight of an application is the sum of its first weight, second weight, and third weight; the fourth weight of an application is related to its first usage probability. The first N0 applications from the first sorted list are used to form the first predicted application list, where N0 is a preset value and is greater than the target number.

14. The method according to any one of claims 1-3 and 8-11, characterized in that, The t-th day contains forty-eight time periods, with no overlap between adjacent time periods, and all time periods having the same duration.

15. An electronic device, characterized in that, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the electronic device to perform the method as described in any one of claims 1-14.

16. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-14.

17. A chip system, characterized in that, It includes at least one processor and a communication interface, the communication interface and the at least one processor being interconnected via a line, the at least one processor being configured to run a computer program or instructions to perform the method as described in any one of claims 1-14.

18. A computer program product, characterized in that, Includes a computer program that, when run, causes a computer to perform the method as described in any one of claims 1-14.

Images