CN115061740A

CN115061740A - Application program processing method and device

Info

Publication number: CN115061740A
Application number: CN202111401532.2A
Authority: CN
Inventors: 陈贵龙; 赵杰
Original assignee: Honor Device Co Ltd
Current assignee: Honor Device Co Ltd
Priority date: 2021-11-19
Filing date: 2021-11-19
Publication date: 2022-09-16
Anticipated expiration: 2041-11-19
Also published as: CN116627534B; CN116627534A; CN115061740B

Abstract

The application provides an application processing method and device, wherein the method comprises the following steps: the method comprises the steps that an electronic device displays a recent task list, wherein the recent task list displays first content, and the first content comprises tasks which are started by a user in the electronic device; after the memory clearing operation of the user is acquired, the latest task list is switched from displaying the first content to second content, and the second content is used for indicating that the electronic equipment does not start a task; after a first starting operation of a user is acquired, displaying a first task; switching from displaying the first task to displaying a desktop; and after a second starting operation of the user is acquired, displaying a second task, wherein the second task is different from the first task, and the loading time length of the second task is different from the loading time length of the first task.

Description

Application program processing method and device

Technical Field

The present application relates to the field of computer technologies, and in particular, to an application processing method and apparatus.

Background

Smart mobile phone, computer and intelligent household electrical appliances become essential electronic equipment in user's daily life gradually, and in order to satisfy the different demands of user, the Application (APP) of installation is more and more in the electronic equipment, and required resource is also more and more when corresponding APP moves in operation to it is long to increase application start-up time, reduces user experience.

Disclosure of Invention

The application provides an application program processing method and device, and aims to solve the problems that application starting time is long and user experience is reduced.

In order to achieve the above object, the present application provides the following technical solutions:

in a first aspect, the present application provides an application processing method, applied to an electronic device, the method including: the electronic equipment displays a recent task list, wherein the recent task list displays first content, and the first content comprises tasks started by a user in the electronic equipment; after the memory clearing operation of the user is acquired, the latest task list is switched from displaying first content to second content, and the second content is used for indicating that the electronic equipment does not start a task; after a first starting operation of a user is acquired, displaying a first task; switching from displaying the first task to displaying the desktop; and after a second starting operation of the user is acquired, displaying a second task, wherein the second task is different from the first task, the loading time of the second task is different from the loading time of the first task, and if the loading time of the second task is longer than the loading time of the first task.

In this embodiment, different tasks are displayed when a user performs different opening operations, and the loading durations of the two tasks are different, and the loading duration of the first task is shorter than that of the second task, which indicates that the electronic device has preloaded the first task before the user opens the first task, and shortens the starting duration of the first task, so that the first task is started more quickly.

In a second aspect, the present application provides an application processing method, applied to an electronic device, the method including: the electronic equipment displays a floating mark, the floating mark displays third content, and the third content is at least one task which is started by a user in the electronic equipment; after the memory clearing operation of the user is acquired, the display content of the suspension mark is empty; after a first starting operation of a user is acquired, a first task is displayed, and related content of the first task can be displayed in a suspension mark; switching from displaying the first task to displaying the desktop; and after a second starting operation of the user is acquired, displaying a second task, wherein the second task is different from the first task, the loading time of the second task is different from the loading time of the first task, and if the loading time of the second task is longer than the loading time of the first task.

Optionally, when applied to an electronic device, the method further includes: acquiring the starting operation of a user on the suspension mark; and responding to the starting operation, and controlling the suspension mark to be continuously displayed on the interface of the electronic equipment. The user can control the on and off of the floating mark, if the user performs an on operation, the floating mark can be displayed on an interface of the electronic device all the time in the using process of the electronic device, and the user can know the pre-loaded first task in real time through the floating mark.

Optionally, the method further comprises: when responding to the memory clearing operation of a user, storing a picture of a task started by the user; after the first opening operation of the user is acquired, displaying the first task comprises: and after the first starting operation of the user is acquired, displaying a picture of the first task, wherein the picture of the first task is acquired when the response is made to the memory clearing operation in the historical use process of the first task. In this embodiment, in the history use process of the first task, if the user performs the memory clearing operation, the electronic device may acquire the picture of the first task, so that the picture of the first task may be directly displayed after the first start operation is acquired, the process of generating the picture of the first task is omitted, and the efficiency is improved.

Optionally, the picture of the first task is an interface thumbnail of the first task, and the interface thumbnail is a thumbnail of an interface displayed when the first task responds to the memory clearing operation, for example, a thumbnail of a last interface displayed by the first task when responding to the memory clearing operation, for example, for a video, the thumbnail may be a last playing interface. The electronic equipment can load the resources required by the interface thumbnail in advance, and can directly display the interface pointed by the interface thumbnail after the first task is started.

Optionally, the method further comprises: acquiring starting operation of a user on a first task; and responding to the starting operation, and displaying an interface thumbnail of the first task on the electronic equipment.

Optionally, the method further comprises: the first task and the second task are displayed in the recent task list, a starting mark is displayed at the display position of the first task, the starting mark is used for indicating that the first task is preloaded to a background when a user does not perform starting operation on the first task, and the starting mark can be used for enabling the user to know which tasks are preloaded and which are started by the user, so that the tasks can be distinguished through the starting mark.

Optionally, after obtaining the first opening operation of the user, displaying the first task includes: after a first starting operation is acquired in a first scene, displaying a first task matched with the first scene; and after the first starting operation is acquired in the second scene, displaying a first task matched with the second scene, wherein the first task matched with the second scene is different from the first task matched with the first scene.

In this embodiment, the first scene and the second scene are two different scenes, and when the same first starting operation of the user is obtained in different scenes, the electronic device may display the first task matched with the scenes in different scenes, so as to implement personalized recommendation in different scenes.

Optionally, the first scene is a first time of the current date, and the second scene is a second time, the first time and the second time of the current date; and/or the first scene is a first geographical position, the second scene is a second geographical position, and the first geographical position and the second geographical position are different. The first scene and the second scene can be different times on the same date, different predicted tasks are automatically started at different times, and the requirements of users for using different tasks at different times are met while personalized loading is carried out. For example, during work, users generally use office applications and communication applications, and after work, users generally use entertainment applications, shopping applications, and the like; further, the user often uses a taxi taking application and a ticket buying application when going off duty, uses a news application before sleeping, and the like, and is distinguished by different times so as to automatically start different applications at different times.

The first scene and the second scene can be different geographic positions, different predicted tasks are automatically started under the different geographic positions, and the requirements of different tasks used under different geographic positions of a user are met while personalized loading is carried out. For example, when a user is at a station, the user generally uses a bus application (such as a bus code) and a ticket purchasing application; users are in companies, generally using a card punching application and an office application; users typically use payment applications and coupon applications at a store. The different geographic positions are distinguished so as to self-start different applications in different geographic positions.

Optionally, the first task is a predicted task obtained in response to a predicted trigger operation of the user, and the predicted task is obtained according to historical usage of a plurality of tasks related to the predicted trigger operation. Generally, a plurality of tasks related to the predicted triggering operation are tasks which are possibly started after the predicted triggering operation, the electronic equipment starts at least one task in the tasks which are possibly started, the predicted task obtained from the tasks is also a task which is possibly started after the predicted triggering operation, the accuracy can be improved, the predicted task is started in advance, the resources of the predicted task are loaded in advance, and the starting of the predicted task can be accelerated when a user starts the predicted task.

The historical use conditions of the tasks related to the predicted trigger operation can be changed according to the use of the user to the tasks after the predicted trigger operation, namely the historical use conditions of the tasks can be changed along with the use habits of the user, the corresponding tasks related to the predicted trigger operation can be changed along with the use of the tasks by the user, and the predicted tasks can also be changed along with the change of the historical use conditions, so that the predicted tasks can accord with the use habits of the user, the predicted tasks can be obtained from the tasks matched with the predicted trigger operation along with the use habits of the user, and the accuracy of the predicted tasks is improved.

In this embodiment, the predicted task may be displayed on the floating mark, and if the predicted task changes, the content displayed on the floating mark may also change, so as to display the current predicted task in real time through the floating mark. The predicted task matching the predicted trigger operation may be a plurality of tasks, the floating mark may display one of the plurality of predicted tasks, and the one predicted task displayed by the floating mark is the task most likely to be opened after the predicted trigger operation. Of course, the floating mark may also display a plurality of predicted tasks, but may block the currently displayed content of the electronic device, and for this purpose, the floating mark may poll and display the plurality of predicted tasks, that is, the floating mark may display the plurality of predicted tasks of the same prediction trigger operation at different times.

Or the floating mark can have an expansion function and a contraction function, the contraction function is a default function, the floating mark is mainly the contraction function when the electronic equipment starts to display the floating mark, and the predicted task which is most probably opened after the prediction trigger operation is displayed; if the user clicks the suspension mark, the unfolding function of the suspension mark takes effect, and the suspension mark is unfolded; the floating mark displays a plurality of predicted tasks, the user clicks the floating mark again, the contraction function of the floating mark is effective, and the floating mark is contracted. The user may also initiate the predicted task by clicking on the hover flag, in which case the operation of initiating the predicted task is to be distinguished from the operation of controlling the hover flag to expand and contract. For example, the click positions of the two operations may be different, or one click and one double click may be used.

Optionally, the prediction trigger operation includes at least one of opening an application, opening a service, and unlocking by a bright screen; the predicted task includes at least one of a predicted application and a predicted service. The electronic equipment can set different prediction trigger operations, predict application programs and/or services for users, and provide diversified use so as to meet different use requirements of the users.

Optionally, the method further comprises: determining a plurality of fourth tasks related to the predicted trigger operation from all the third tasks in the historical time period based on the start time of each third task in the historical time period and the stop time of the predicted trigger operation; the predicted task is obtained according to the historical use condition of a plurality of tasks related to the prediction trigger operation, and the predicted task comprises the following steps: obtaining a gain score of each fourth task, wherein the gain score is used for indicating the transfer condition from the prediction trigger operation to the fourth task in the historical time period, and the gain score removes the influence of the use condition of the fourth task in a plurality of fourth tasks in the historical time period; the predicted task is derived from the plurality of fourth tasks based on the gain score of each fourth task.

In this embodiment, after monitoring one predicted triggering operation, the electronic device may obtain a plurality of fourth tasks related to the predicted triggering operation based on the time correlation between the predicted triggering operation and the third task, and then select the predicted task from the plurality of fourth tasks based on a transfer condition from the predicted triggering operation to the fourth task. The case of the transition from the predicted triggering operation to the fourth task may be that the predicted triggering operation triggers the use of the fourth task, and also indicates the probability of being triggered (or using the fourth task), and so on, so that the fourth task is a task that is used after the predicted triggering operation is monitored in a historical time period, and the accuracy can be improved by selecting the predicted task from the fourth tasks. And the gain score removes the influence of the use condition of the fourth task in a plurality of fourth tasks in the historical time period, removes the influence of the use probability of the fourth task on the transfer condition of the fourth task, and improves the accuracy of the gain score of each fourth task.

The electronic equipment can obtain the predicted tasks in a simple calculation mode, and a model training process is omitted, so that the electronic equipment side can omit calculation of a large amount of complex model training data, the data volume used by the electronic equipment side is reduced, and the memory and the power consumption are saved.

Optionally, obtaining the gain score of each fourth task includes: obtaining a first basic probability of each fourth task based on the number of usage times of each fourth task and the total number of usage times of the plurality of fourth tasks in the historical time period, wherein the first basic probability of the fourth task is used for indicating the usage condition of the fourth task in the plurality of fourth tasks in the historical time period; obtaining a first transition probability of each fourth task based on the number of transitions from the predicted trigger operation to the fourth task and the total number of transitions of the plurality of fourth tasks within the historical time period; and subtracting the first basic probability of the fourth task from the first transfer probability of the fourth task to obtain a gain score of the fourth task.

Optionally, the method further comprises: obtaining geographic location gain scores for a plurality of fifth tasks used at the current geographic location; the predicted task is obtained according to the historical use condition of a plurality of tasks related to the prediction trigger operation, and the method further comprises the following steps: if the duration of the electronic equipment at the current geographic position is less than or equal to the threshold, obtaining a comprehensive gain score of each task in the fourth task and the fifth task based on the geographic position gain score of the fifth task and the gain score of the fourth task; obtaining a predicted task from a plurality of fourth tasks and a plurality of fifth tasks based on the comprehensive gain scores of the tasks; and if the duration of the electronic equipment at the current geographic position is greater than the threshold value, obtaining the predicted task from the plurality of fourth tasks based on the gain score of each fourth task.

Because the tasks used by the user in different geographic positions may be different, in this embodiment, the geographic position gain score of the task is introduced on the basis of considering the gain scores from the prediction trigger operation to the tasks, and the predicted task is selected from two aspects, so that different predicted tasks can be selected in different geographic positions. Further considering the duration of the user at the current geographic position when selecting the predicted task; if the duration is greater than the threshold, indicating that the user has reached the current geographic location for a period of time, the likelihood that the user will turn on a task associated with the geographic location is reduced, at which point the geographic location gain score may be ignored.

The electronic equipment can obtain the predicted tasks in a simple calculation mode, and a model training process is omitted, so that the electronic equipment side can omit calculation of a large amount of complex model training data, the data volume used by the electronic equipment side is reduced, and the memory and the power consumption are saved. And the geographic position and the historical use condition of the task can not be provided for the cloud, so that the privacy of the user is protected.

Optionally, obtaining the geographic position gain scores of the plurality of fifth tasks used in the current geographic position includes: obtaining a second base probability of using each fifth task at the current geographic position based on the number of use times of using each fifth task at the current geographic position in the historical time period and the total number of use times of the plurality of fifth tasks, wherein the second base probability of using each fifth task at the current geographic position in the historical time period is used for indicating the use condition of the fifth task in the plurality of fifth tasks at the current geographic position in the historical time period; obtaining a second transition probability of using each fifth task at the current geographic position based on the number of transitions from the current geographic position to the fifth task and the total number of transitions of the plurality of fifth tasks within the historical time period; and subtracting the second basic probability of the fifth task from the second transition probability of the fifth task to obtain the geographic position gain score of the fifth task.

Optionally, the method further comprises: loading the predicted task at a first preset loading opportunity; the first preset loading opportunity is obtained based on the use duration of the task pointed by the predicted trigger operation in the historical time period each time, and the fourth time is obtained based on the interval time between the task pointed by the predicted trigger operation in the historical time period and the predicted task, so that the predicted task is started after the predicted trigger operation is started, a proper pre-loading opportunity is provided, the loading timeliness of the predicted task is improved, the pre-loading time of the predicted task can be delayed, and the waste of resources and power consumption is reduced.

Optionally, the obtaining, by the predicted task, according to historical usage of a plurality of tasks related to the prediction trigger operation includes: acquiring a related task path corresponding to the predicted trigger operation, wherein the related task path takes a task pointed by the predicted trigger operation as a last task and is obtained based on a task executed before the predicted trigger operation; obtaining a historical associated task path in a historical time period; obtaining a historical associated task path matched with the associated task path based on the feature vector of the associated task path and the feature vector of the historical associated task path; and obtaining the predicted task based on the matched historical associated task path.

In this embodiment, an associated task path can be obtained for the prediction trigger operation, the predicted task is obtained through the relationship between the associated task path and the historical associated task path, and the predicted task can be obtained in this way for the prediction trigger operation which has a small occurrence number but a periodic usage rule, so that the prediction mechanism is improved. The characteristic vectors can be provided by the cloud, so that the power consumption of the electronic equipment is saved.

Optionally, obtaining a historical associated task path matched with the associated task path based on the feature vector of the associated task path and the feature vector of the historical associated task path includes: selecting a first historical associated task path from all historical associated task paths in a historical time period, wherein the first historical associated task path is a historical associated task path containing a preset number of tasks in the associated task path; selecting a second history associated task path from all the first history associated task paths, wherein the second history associated task path is the first history associated task path with the occurrence frequency smaller than a preset frequency threshold; selecting a sub-path from the second historical associated task path, wherein the sub-path is the same as the number of tasks in the associated task path in the second historical associated task path; obtaining sub-paths matched with the associated task paths based on the feature vectors of each sub-path and the feature vectors of the associated task paths; based on the matched historical associated task path, obtaining the predicted task comprises: the predicted task is derived based on the tasks that occur after the matched sub-path.

Before the predicted task is obtained, the embodiment may compare the associated task path with the historical associated task path, obtain a sub-path related to the associated task path from the historical associated task path, and match the feature vector of the sub-path with the feature vector of the associated task path, thereby reducing the data amount and improving the efficiency.

Optionally, the method further comprises: loading the predicted task at a second preset loading opportunity; the second preset loading opportunity is a second preset time after the start time of the task pointed by the trigger operation is predicted, the second preset time is the sum of a fourth time and a fifth time, the fourth time is obtained based on the use time of the last task in the matched sub-path in the historical time period, the fifth time is obtained based on the interval time from the last task to the next task in the matched sub-path in the historical time period, the predicted task is started after the start of the trigger operation is predicted, the proper preloading opportunity is provided, the timeliness of loading of the predicted task is improved, the preloading time of the predicted task can be delayed, and waste of resources and power consumption is reduced.

In a third aspect, the present application provides an application processing apparatus, applied to an electronic device, the apparatus including: a display unit for displaying a recent task list, the recent task list displaying first content, the first content including a task that has been started by a user in an electronic device; the control unit is used for controlling the latest task list to be switched from displaying the first content to displaying the second content after the memory clearing operation of the user is acquired, and the second content is used for indicating that the electronic equipment does not start a task; after a first starting operation of a user is acquired, displaying a first task; and after a second starting operation of the user is acquired, displaying a second task, wherein the second task is different from the first task, and the loading time of the second task is longer than that of the first task.

In a fourth aspect, the present application provides an application processing apparatus, applied to an electronic device, the apparatus including: the display unit is used for displaying a floating mark, the floating mark displays third content, and the third content is at least one task started by a user in the electronic equipment; the control unit is used for controlling the display content of the suspension mark to be empty after the memory emptying operation of the user is acquired; after a first starting operation of a user is acquired, a first task is displayed, and related content of the first task can be displayed in a suspension mark; and after a second starting operation of the user is acquired, displaying a second task, wherein the second task is different from the first task, and the loading time of the second task is longer than that of the first task. .

In a fifth aspect, the present application provides an electronic device, including a memory and a processor, where the memory is used to store instructions executable by the processor, and the processor executes the instructions to make the electronic device execute the application processing method.

In a sixth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor of an electronic device, causes the electronic device to execute the above-mentioned application processing method.

It should be appreciated that the description of technical features, solutions, benefits, or similar language throughout this application does not imply that all of the features and advantages may be realized in any single embodiment. Rather, it is to be understood that the description of a feature or advantage is intended to include the specific features, aspects or advantages in at least one embodiment. Therefore, descriptions of technical features, technical solutions or advantages in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and advantages described in the present embodiments may also be combined in any suitable manner. One skilled in the relevant art will recognize that an embodiment may be practiced without one or more of the specific features, aspects, or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments.

Drawings

Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure;

fig. 2 is a schematic diagram of a software architecture of an electronic device according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a UI jump in a scenario where prediction is triggered when an application is opened according to an embodiment of the present application;

FIG. 4 is a diagram of UI interface jump in the scenario corresponding to FIG. 3 without prediction and preloading;

FIG. 5 is a schematic diagram of a UI jump in a scenario where prediction is triggered when a system desktop is returned according to an embodiment of the present application;

FIG. 6 is a diagram of UI interface jump in the scenario corresponding to FIG. 5 without prediction and preloading;

FIG. 7 is a schematic diagram of a UI jump in a scene where prediction is triggered when a screen is unlocked according to an embodiment of the present application;

FIG. 8 is a diagram of UI interface jumps in the scenario corresponding to FIG. 7 without prediction and preloading;

fig. 9 is a timing diagram of an application processing method according to an embodiment of the present application;

FIG. 10 is a flowchart of an application processing method according to an embodiment of the present application;

FIG. 11 is a timing diagram illustrating another method for processing an application according to an embodiment of the present application;

FIG. 12 is a schematic diagram of a path alignment provided in an embodiment of the present application;

fig. 13 is a timing diagram illustrating a further method for processing an application according to an embodiment of the present application;

FIG. 14 is a flowchart of another application processing method provided by an embodiment of the present application;

FIG. 15 is a diagrammatic illustration of the application processing method of FIG. 14;

FIG. 16 is a schematic diagram of a UI interface for setting a floating window provided by an embodiment of the application;

fig. 17 is a UI schematic diagram of an icon of a hover ball display prediction APP at a trigger opportunity according to an embodiment of the present application;

fig. 18 is a UI diagram of an icon of a hover ball display prediction APP at another trigger opportunity according to the embodiment of the present application;

fig. 19 is a UI diagram of an icon for showing a predicted service in a hover ball according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. The terminology used in the following examples is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of this application and the appended claims, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, such as "one or more", unless the context clearly indicates otherwise. It should also be understood that in the embodiments of the present application, "one or more" means one, two, or more than two; "and/or" describes the association relationship of the associated objects, indicating that three relationships may exist; for example, a and/or B, may represent: a alone, both A and B, and B alone, where A, B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise. The words "one/some implementations," "exemplary," "for example," and the like are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.

The embodiments of the present application relate to a plurality of numbers greater than or equal to two. It should be noted that, in the description of the embodiments of the present application, the terms "first", "second", and the like are used for distinguishing the description, and are not to be construed as indicating or implying relative importance or order.

In this embodiment, the electronic device may predict an application program that may be started by the user, and load a resource required for starting the predicted application program into a memory of the electronic device, where a manner for the electronic device to predict the application program may be that the electronic device counts APPs that are commonly used within a user history time period, and the commonly used APPs are used as the predicted APPs. For example, the APP that is frequently used may be the APP that is used the most frequently in the historical period; for example, the APP that is commonly used may be an APP that has been used more than a threshold number of times within the historical period of time. The history time period may be history week, history month, or the like, and the history time period is not limited in this embodiment.

The APP predicted based on the number of times of use in the history period is an APP frequently used by the user, and the APP frequently used by the user is not necessarily an APP that the user is about to use. For example, APPs frequently used by users include: panning, wechat, beauty groups, video, and ride tools; after the user arrives at a company to work, the user is about to use a card punching APP and an office APP, the APP about to be used by the user is inconsistent with the APP predicted based on the use times in the historical time period, and therefore the accuracy of the APP predicted by the electronic equipment based on the use times is low.

In order to improve the accuracy of the predicted APP, the embodiment provides an application processing method, where the application processing method may obtain the association between the APP and the trigger action based on the historical usage data of the APP; after the electronic device currently monitors a trigger action, predicting an APP matched with the current trigger action based on the association between the APP and the trigger action.

Wherein the trigger action may include: opening APPs, returning from one APP to a desktop, unlocking a screen, changing the user's geographic location, which may be the user arriving at a particular location, such as a station, a company, a mall, etc. There may be some difference in the APP that the user will open when the user arrives at different locations. For example, when a user arrives at a station, the APP to be opened by the user may be a bus APP (such as a bus number) and a ticket purchasing APP; for another example, when the user arrives at a company, the APP to be opened by the user may be a card punching APP and an office APP; also for example, when the user arrives at a store, the APP that the user is going to open may be a payment APP and a coupon APP.

The APPs opened by the user in different geographic positions can be recorded in the historical usage data of the APPs, that is, the association between the APPs and the geographic positions is recorded in the historical usage data of the APPs, for example, the card punching APP is associated with a company, and the payment APP is associated with a shopping mall. During the process of using the electronic device by the user, after the electronic device is located at the position of the user, the electronic device may extract an APP associated with the current geographic position from historical usage data of the APP, and then predict an APP matching the current geographic position based on the APP associated with the current geographic position, for example, take the APP associated with the current geographic position as the predicted APP. The APP predicted by the electronic device based on the association between the APP and the geographic location is more likely to be used by the user, so that the accuracy of the predicted APP can be improved.

According to the above, after monitoring any trigger action, the electronic device can predict the APP matched with the current trigger action based on the association between the APP and the trigger action, so that the predicted APP is related to the trigger action, the predicted APP is more likely to be opened, and the accuracy of the predicted APP is improved.

In some embodiments, after predicting the APPs, the electronic device selects TopN APPs from all the predicted APPs, and preloads the TopN APPs, where N is a positive integer greater than or equal to 1. The TopN APPs may be APPs with the use probability of the first N bits in all the APPs, and the loading timing of the TopN APPs may be at least one of when the trigger action is monitored, after the trigger action is completed, and after the trigger action is started. The triggering action is used for opening the APPs, and the loading time of the TopN APPs can be at least one of the time when the APPs are opened, the time when the APPs are closed and the running process of the APPs.

Referring to fig. 1, a schematic structural diagram of an electronic device provided in an embodiment of the present application is shown, where the electronic device is configured to run an application processing method provided in the present application. In some embodiments, the electronic device may be a cell phone, a tablet, a desktop, a laptop, a notebook, an Ultra-mobile Personal Computer (UMPC), a handheld Computer, a netbook, a Personal Digital Assistant (PDA), a wearable electronic device, a smart watch, or the like. The specific form of the electronic device is not particularly limited in the present application.

As shown in fig. 1, the electronic device may include: the mobile terminal comprises a processor, an external memory interface, an internal memory, a Universal Serial Bus (USB) interface, a charging management module, a power management module, a battery, an antenna 1, an antenna 2, a mobile communication module, a wireless communication module, a sensor module, a positioning module, a key, a motor, an indicator, a camera, a display screen, a Subscriber Identity Module (SIM) card interface and the like. Wherein the audio module may include a speaker, a receiver, a microphone, an earphone interface, etc., and the sensor module may include a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, a bone conduction sensor, etc.

It is to be understood that the illustrated structure of the present embodiment does not constitute a specific limitation to the electronic device. In other embodiments, an electronic device may include more or fewer components than shown, or some components may be combined, some components may be split, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

The processor may include one or more processing units, such as: the processor 110 may include an Application Processor (AP), a modem processor, a Graphics Processing Unit (GPU), an Image Signal Processor (ISP), a controller, a video codec, a Digital Signal Processor (DSP), a baseband processor, and/or a neural-Network Processing Unit (NPU), etc. The different processing units may be separate devices or may be integrated into one or more processors. The processor is a nerve center and a command center of the electronic equipment, and the controller can generate an operation control signal according to the instruction operation code and the time sequence signal to finish the control of instruction fetching and instruction execution.

The display screen is used for displaying images, videos, a series of Graphical User Interfaces (GUIs), and the like, such as pre-loaded TopN APPs.

The positioning module is used for positioning the geographic position of the electronic device, and the positioning module can adopt a Beidou satellite navigation system, a Global Positioning System (GPS) and the like.

The external memory interface can be used for connecting an external memory card, such as a Micro SD card, so as to expand the storage capability of the electronic device. The external memory card communicates with the processor through the external memory interface to realize the data storage function. For example, files such as music, video, etc. are saved in an external memory card. The internal memory may be used to store computer-executable program code, which includes instructions. The processor executes various functional applications of the electronic device and data processing by executing instructions stored in the internal memory. For example, in the present application, the processor causes the electronic device to execute the application processing method provided in the present application by executing the instructions stored in the internal memory.

The

antennas

1 and 2 are used for transmitting and receiving electromagnetic wave signals. Each antenna in an electronic device may be used to cover a single or multiple communication bands. Different antennas can also be multiplexed to improve the utilization of the antennas. For example: the antenna 1 may be multiplexed as a diversity antenna of a wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

The mobile communication module can provide a solution including 2G/3G/4G/5G wireless communication applied to the electronic equipment. The wireless communication module may provide solutions for wireless communication applied to electronic devices, including Wireless Local Area Networks (WLANs) (e.g., wireless fidelity (Wi-Fi) networks), Bluetooth (BT), Global Navigation Satellite System (GNSS), Frequency Modulation (FM), Near Field Communication (NFC), Infrared (IR), and the like.

The operating system of the electronic device may employ a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. The embodiment of the application takes an Android system with a layered architecture as an example, and exemplarily illustrates a software structure of an electronic device. Fig. 2 is a block diagram of a software structure of the electronic device. The layered architecture divides the software into several layers, each layer having a clear role and division of labor. The layers communicate with each other through a software interface. Taking the Android system as an example, in some embodiments, the Android system is divided into four layers, which are an application layer, an application Framework layer (Framework), a class library layer, and a system Kernel layer (Kernel) from top to bottom.

Wherein the application layer may include a series of application packages. As shown in fig. 2, the application packages may include APPs such as cameras, galleries, calendars, conversations, maps, navigation, WLAN, bluetooth, music, video, short messages, etc. The application framework layer provides an Application Programming Interface (API) and a programming framework for the application program of the application layer. The application framework layer includes a number of predefined functions. As shown in FIG. 2, the application framework layers may include a window manager, content provider, view system, phone manager, resource manager, notification manager, and the like. In fig. 2, the application framework layer may include a data collection module, a data preservation module, an algorithm module, a prediction module, and a system process manager.

The data acquisition module is used for sensing the running state of the APP, such as events of application opening/closing, foreground and background switching, installation/uninstallation and the like. And the data storage module is used for storing the time for opening and closing the APP by the user, namely the APP opening time and the APP closing time. The algorithm module is used for calculating the using probability of the APP based on historical using data of the APP, and the prediction module is used for predicting the APP to be used based on the using probability of the APP after the triggering action occurs. If the prediction module can predict TopN APPs, the APP identifications of the TopN APPs are transmitted to the system process manager.

The predicted trigger actions of the APP may include the following:

(1) when an APP is turned on, triggering APP prediction;

(2) when the desktop is opened, APP prediction is triggered, for example, when the desktop returns from an interface of an APP, APP prediction is triggered;

(3) when the screen unlocking operation is detected, an APP prediction event is triggered.

The APP prediction may be set according to actual needs, and include other trigger occasions besides the above three trigger occasions, for example, trigger APP prediction according to a preset time interval, and the like, which is not described in detail herein.

The system process manager is used for loading the starting resource of at least one APP in the TopN APPs to the system memory, so that when a user opens the APP, the user can directly display the UI interface of the APP when opening the APP because the resource loading process of the APP is completed in advance before opening the APP, and zero waiting of the user is realized.

The system library may include a plurality of functional modules. For example: surface managers (surface managers), Media Libraries (Media Libraries), three-dimensional graphics processing Libraries (e.g., OpenGL ES), 2D graphics engines (e.g., SGL), and the like.

The kernel layer is a layer between hardware and software. The inner core layer at least comprises a display driver, a camera driver, an audio driver and a sensor driver. For example, after predicting TopN APPs, the prediction module may send APP identifiers of the predicted TopN APPs to the display driver, and the display driver may drive the display screen to display at least one APP identifier, and the display screen may display the APP identifiers in a form of a floating ball.

Under a scene, behind the electronic equipment preloading APP, the foreground interface of electronic equipment remains unchanged, and when the user opened the pre-loaded APP of intelligence, electronic equipment can show the UI interface of pre-loaded APP, and in some examples, electronic equipment can also show the interface of pre-loaded APP when last quitting.

In another scenario, the electronic device presents an icon of a preloaded APP within the hover ball. And clicking the icon displayed in the floating ball by the user to directly display the preloaded APP UI.

Example one

In this embodiment, a prediction process and a preloading process of an application program are performed in a scenario where a foreground interface of an electronic device is maintained after the electronic device preloads an APP.

First, a change process of the UI interface and prediction of APP performed under different trigger events is described with reference to fig. 3 to 8.

(1) Triggering APP prediction when APP is turned on

For example, as shown in fig. 3, after the user clicks the icon of the WeChat APP, the UI of the WeChat APP is displayed, and meanwhile, the electronic device monitors the operation that the icon of the WeChat APP is triggered, and starts to perform APP prediction by using the opening of the WeChat APP as a trigger event. If the historical use data of the electronic equipment based on the APP is found, the association between the video APP and the WeChat APP is very large, the electronic equipment can predict that the user may open the video APP next, the electronic equipment intelligently loads the starting resource corresponding to the video APP at the background, therefore, when the user opens the video APP, namely, the user clicks the icon of the video APP as shown in (3) in fig. 3, the display screen directly shows the UI interface of the video APP, so that the intelligent preloading application program is realized, the starting resource preloading process of the video APP is completed before the user opens the video APP, the time for the user to wait for the starting of the video APP is reduced to zero, and the user experience is improved.

As shown in fig. 3, before the user clicks the icon of the WeChat APP, the APP running in the background of the electronic device does not run, and after the user opens the WeChat APP, the APPs running in the background of the electronic device include the WeChat APP and the video APP.

Fig. 4 shows a scenario in which the electronic device does not perform APP prediction and preloading, as shown in (1) in fig. 4, the user opens the WeChat APP operation without triggering APP prediction, so that the electronic device does not predict that the user will open the video APP next time, and does not preload the start resource of the video APP. When the user opens the video APP, if the user clicks an icon of the video APP, the electronic device first loads a starting resource required by the video APP, in the process of waiting for resource loading, the display screen displays an interface waiting for starting, as shown in (5) in fig. 4, and after the loading is completed, the display screen displays a UI (user interface) of the video APP.

Compared with the method shown in fig. 4, when the user opens the video APP in fig. 3, the electronic device does not wait for the process of loading the video APP, and waits for the APP start time of the user to be zero, so that the user experience is improved.

In addition, in some embodiments, the system background may directly preload a page corresponding to the last use of the video APP by the user, in this case, the page corresponding to the last exit of the video APP by the user may be directly displayed on the display screen, as shown in (4) in fig. 3, and a play interface corresponding to the last video watched by the user is directly displayed.

In other embodiments, the background of the electronic device may preload page resources of a first page corresponding to an APP. The page resource of the preloaded APP can be set according to the requirements of the user, and the method and the device are not limited in this respect.

(2) Triggering APP prediction when desktop is opened

Fig. 5 illustrates predicting APPs at the desktop, which are preloaded, thus reducing latency when the predicted APPs are opened, either from one APP back to the desktop or unlocking the electronic device into the desktop. As shown in (1) in fig. 5, when a user opens a desktop, APP prediction is triggered, it is predicted that the user may open a video APP next, and a corresponding start resource of the video APP is loaded in the background. As shown in (2) in fig. 5, when the user clicks the video APP icon, the display screen directly displays the UI interface of the video APP.

Returning to the desktop from the UI interface of the video APP, the electronic device may predict the APP again, and if the photo APP is opened after the desktop is opened, the electronic device may display the interface of the photo APP after waiting for a while when the photo APP is opened, as shown in (4) to (7) of fig. 5, because the photo APP is not preloaded.

Fig. 6 shows that there is no prediction at the desktop, there is no preloading process for APP, and the user needs to wait for the electronic device to load the resources of the video APP when the user opens the video APP. Compared with the process shown in fig. 6, in the process shown in fig. 5, before the user opens the video APP, the electronic device preloads the starting resource of the video APP, so that when the user opens the video APP, the UI interface of the video APP can be directly displayed, and the user does not need to wait for the video APP to load the starting resource.

(3) Triggering APP prediction during screen unlocking operation

When the user unlocks the screen (an unlocking operation is shown as (1) in fig. 7), it is predicted that the user may open the video APP next, and the starting resource of the video APP is preloaded intelligently in the background. As shown in (2) in fig. 7, when the user clicks the icon of the video APP, the UI interface of the video APP is directly presented, and the presentation of the UI interface is shown in (3) in fig. 7.

Compared with the process shown in fig. 8 in which APP prediction and preloading are not performed, the process shown in fig. 7 saves the time for the user to wait for the video APP to load and start the resource, reduces the time for the user to wait for the APP to start to zero, and improves the user experience.

As can be seen from the above, in order to implement zero latency when a user starts an APP, the electronic device may accurately predict the APP that the user may open in a future period of time based on the association between the APP and the trigger event, and load the predicted resources required by the APP into the memory in advance. The process of predicting APPs is described below with reference to the accompanying drawings, where fig. 9 illustrates an application processing method provided in this embodiment, and the application processing method illustrated in fig. 9 takes APP open as a trigger event, and predicting APPs based on associations between APPs may include the following steps:

s101, a data acquisition module acquires the starting time and the closing time of the APP. When a user opens, exits (namely closes), switches between the front/background and installs and unloads the APP, corresponding events are generated, such as an APP opening event, an APP exiting event, an APP background switching event and the like, the data acquisition module can sense the events and determine the running state of the APP by sensing the events.

For example, after an event that an APP is turned on or exited is sensed, the data acquisition module may record the turn-on time of the APP and the turn-off time of the APP.

S102, the data acquisition module sends the starting time and the closing time of the APP to the data storage module.

S103, the data storage module stores the starting time and the closing time of the APP, and adds one to the using times of the APP.

The data saving module may add one to the number of usage times of the APP each time the start time and the close time of receiving the APP to count the total number of usage times of the APP. The data storage module may record time information of each APP used by the user according to a time sequence, and the time information of the same APP may be recorded in the same area, such as in the same table.

In this embodiment, the data acquisition module can perceive the relevant event of APP at the APP operation in-process, records the time of occurrence of the relevant event of APP, like recording the opening time and closing time of APP, these time messages can be sent to the data storage module, the time message of APP is preserved by the data storage module, and can add an operation to the number of times of using of APP, in order to count out the total number of times of using of APP, thereby realize the real-time monitoring to the APP use.

S104, the algorithm module obtains the starting time of the APP, the closing time of the APP and the using times of the APP from the data storage module.

In some examples, the algorithm module may obtain historical usage data of the APP from the data saving module at preset time intervals; in other examples, the algorithm module may obtain historical usage data of the APP from the data retention module on an irregular basis. The historical usage data of an APP includes a start time, a close time, and a number of uses of the APP within a historical period, where the number of uses is a total number of uses within the historical period. The algorithm module can actively acquire the historical use data of the APP from the data storage module, and the data storage module can also actively send the historical use data of the APP to the algorithm module.

The historical time period may be selected according to actual needs, for example, the last month, or the last 20 days, or the last two weeks, and the algorithm module may obtain historical usage data of all APPs used in the historical time period. If the historical time period is the last month, the algorithm module acquires all the APPs used by the user every day in the last month and corresponding time information. All the APPs used each day are arranged in turn according to the turn-on time.

In this embodiment, the algorithm module may obtain historical usage data of the APP in two historical time periods, where, for example, the two historical time periods are a first historical time period and a second historical time period respectively, a duration of the first historical time period is greater than a duration of the second historical time period, historical usage data of the APP in the first historical time period reflects a habit of the user in using the APP for a long time, and historical usage data of the APP in the second historical time period reflects a habit of the user in using the APP for a short time, so as to take into account the long-term usage habit and the recent usage habit when predicting the APP.

For example, the first historical period of time may be a full time window, e.g., the first historical period of time may be a period of time since the electronic device began use; the second historical period of time may be a partial time window, e.g., the second historical period of time may be the last two weeks, etc.

S105, the algorithm module takes an APP in the historical time period as a source APP, and takes an APP with the starting time later than the closing time of the source APP as a standby APP.

After obtaining the historical use data of all the APPs in the historical time period, the algorithm module takes one APP in the historical time period as a source APP, and takes an APP with the starting time later than the closing time of the source APP as an alternative APP, and the alternative APP can be regarded as the next opened APP after the source APP is opened by the user, so that the source APP and the alternative APP can be two APPs with an association relationship.

In this embodiment, a causal association APP sequence represents an association relationship between a source APP and an alternative APP, after APP (a1) is turned off, a new APP (a2) is turned on within a certain time range, and it can be considered that a1 → a2 is an ordered causal association APP sequence, where a1 is the source APP or the source APP, a2 is the effect APP or the alternative APP, and the source APP and the alternative APP in the causal association APP sequence can be represented by APP identifiers.

Where a2 is not necessarily the next one, but rather reflects the APP that may be turned on in the short future. For example, the electronic device sets a preset interval, and the APP that is turned on during the interval after the source APP (a1) is turned off may be referred to as a 2. For example, a user used 5 APPs a day in the morning, specifically, APP1 was opened at 7:00 and the ratio of APP to APP was changed at 7: 10 turns off APP1, 7:30 turns on APP2, 8:00 turns on APP3, 11:00 turns on APP4 and at 11: 20 turn off APP4, 11:30 turn on APP5, and the preset interval time is 30 minutes, then based on the turn-on time and the turn-off time of 5 APPs, there may be the following relationship between the 5 APPs:

APP1→APP2、APP4→APP5。

if 7: 40 opens APP6, then APP1 and APP6 are also APPs with an association relationship, that is, APP1 → APP6, that is, for each source APP, all APPs opened during the interval of closing each source APP may be the candidate APPs for that source APP, and all candidate APPs for that source APP are not necessarily the next APPs opened after that source APP.

In addition, in this embodiment, it may also be determined whether two APPs have an association relationship according to the start times of the two APPs, that is, whether a causal association APP sequence is formed, and the same electronic device also sets a preset interval time, and if the interval time is also 30 minutes, the following association relationship exists between the above 5 APPs:

APP1 → APP2, APP2 → APP3, APP4 → APP 5. Likewise when causally related APP sequences are derived with an open time, all alternative APPs of a source APP are not necessarily the next APP to open after that source APP.

S106, the algorithm module calculates the basic probability of each alternative APP and the transition probability of each alternative APP based on the using times of the alternative APPs.

AlternativesThe using times of the APPs are the total using times of the alternative APPs in the historical time period and represent the times of opening the alternative APPs by the user, and the basic probability of each alternative APP is used for representing the probability of the alternative APP being used in the historical time period. The algorithm module may calculate the base probability of each alternative APP based on the number of uses of the alternative APP and the number of uses of all the alternative APPs in units of each alternative APP. In particular, the base probability D of each alternative APP _{base_prob} ＝D _{base_no} /D _{base_no_all} ，D _{base_no} Is the number of uses of alternative APP, D _{base_no_all} Is the sum of the number of uses of all alternative APPs.

The transition probability of each alternative APP is used for representing the probability of transition from one source APP to the alternative APP in the historical time period, and the transition from the source APP to the alternative APP represents that the user opens the alternative APP after opening the source APP. If a plurality of source APPs are possible to be transferred to one alternative APP, for the transfer from each source APP to the alternative APP, the algorithm module respectively calculates the probability of transferring from different source APPs to the alternative APPs. The transition probability of the alternative APP can be obtained based on the number of transitions from the source APP to the alternative APP, the causal association APP sequence indicates the transition from the source APP to the alternative APP, the algorithm module can initialize the number of transitions to 1 after obtaining the causal association APP sequence from one source APP to one alternative APP, if the same causal association APP sequence is obtained again, the number of transitions is added by one to obtain the total number of transitions D of the causal association APP sequence in the history period _{transfer_no} 。

The algorithm module may calculate the transition probability of each alternative APP based on the transition times of the alternative APPs and the transition times of all the alternative APPs in units of each alternative APP. In particular, the transition probability D of each alternative APP _{transfer_prob} ＝D _{transfer_no} /D _{transfer_no_all} ，D _{transfer_no_all} Is the sum of the transition times of all alternative APPs.

And S107, the algorithm module subtracts the basic probability from the transition probability of the same alternative APP to obtain the gain score of the alternative APP. The reason why the gain score is obtained by subtracting the basic probability of the alternative APP from the transition probability of the alternative APP is that the basic probability of a certain alternative APP is very high, so that the transition probability of the alternative APP is difficult to objectively reflect that the alternative APP is opened due to the opening of one source APP, and the basic probability of the alternative APP is subtracted to objectively reflect the improvement of the possibility that the alternative APP is opened due to the opening of the source APP.

For example, the transition probability of general APP → WeChat is high, because the basic probability of WeChat is high, and the increase of the possibility of WeChat opening caused by general APP opening is reflected after the subtraction.

The above steps S104 to S107 are preprocessing stages, and the algorithm module may calculate the gain score of each alternative APP in advance before predicting the APP. If the algorithm module obtains historical usage data of the APPs in the two historical time periods, the algorithm module may calculate a gain score of each alternative APP for the two historical time periods, respectively. For example, the algorithm module may calculate the gain score of each APP in the full time window and the gain score of each alternative APP in the last two weeks, based on the historical usage data of the APPs in the full time window and the historical usage data of the APPs in the last two weeks.

And S108, the data acquisition module sends the APP identification to the prediction module. In this embodiment, the data acquisition module senses that a certain APP is running (if the certain APP is turned on), the data acquisition module sends an APP identifier of the APP to the prediction module, the prediction module is triggered to perform APP prediction, the APP identifier serves as an identity identifier of the APP and is used for distinguishing the APP identifier from other APPs, and the APP identifier may be the name of the APP and the like in this embodiment.

Besides using the APP operation trigger prediction module to perform APP prediction, the embodiment may also use other methods for triggering, for example, after detecting an unlocking operation of a user, triggering the APP prediction, or when detecting that the electronic device returns to a desktop from an interface of an APP, triggering the APP prediction, or triggering the APP prediction at a preset time interval, which is not described in detail herein.

S109, the prediction module obtains the gain score of the alternative APP associated with the APP identification from the algorithm module.

The prediction module can send the APP identifications to the algorithm module, the algorithm module can search the causal association APP sequences using the APP identifications as source APPs from all the causal association APP sequences, and the alternative APPs in the searched causal association APP sequences are alternative APPs associated with the APP identifications. And the algorithm module has already calculated the gain score of the alternative APP associated with the APP identity, the algorithm module may send the gain score of the alternative APP associated with the APP identity to the prediction module.

S110, selecting target APPs with gain values sequenced at the top N positions from alternative APPs associated with the APP identifications by a prediction module. And the target APP with the gain scores sequenced in the first N bits is the first N bits candidate APP with the maximum gain score in all the candidate APPs.

If the algorithm module calculates the gain scores of the two alternative APPs in the two historical time periods, the prediction module can obtain the two gain scores of one alternative APP, the prediction module can perform weighting processing or average processing on the two gain scores of one alternative APP to obtain the target gain score of the alternative APP, and the target APPs ranked in the top N positions are selected based on the target gain scores of the alternative APPs. Certainly, the prediction module may also select, as the target APP, an alternative APP with a gain score larger than a time threshold, or select, as the target APP, an alternative APP with a gain score within a certain range.

S111, the prediction module sends the target APP with the first N bits to the system process manager.

S112, the system process manager preloads the target APP with the first N bits.

The system process manager can pre-load the resources needed by starting one or more target APP. For example, only the resources of the next open target APP may be preloaded; in another example, resources of multiple target APPs may be preloaded, such as 3 target APPs are predicted, and the system process manager may preload resources of the 3 target APPs.

In this embodiment, the system process manager may preload the target APP based on the number of APPs that run in the background, where the number of APPs that can run in the background is M, P APPs that have currently run, and (M-P) APPs that can run in the background may be further executed. If (M-P) is greater than or equal to N, the system process manager can preload N target APPs; if (M-P) is less than N, the system process manager may preload (M-P) target APPs, where (M-P) target APPs may be the largest gain scores among the N target APPs, or the system process manager may close some APPs currently running in the background and then preload the N target APPs. M is an integer greater than 1, P is an integer greater than or equal to 1, and M is greater than P.

In this embodiment, the specific process of preloading and the loaded resource are not limited, for example, corresponding hardware resources are allocated to the APP, and relevant data required for starting the APP is loaded based on the hardware resources, which may include process starting, service starting, memory allocation, file content reading, network data acquisition, UI interface rendering, and the like. The following description is made with reference to an example, and when the data acquisition module detects that the user clicks WeChat, the prediction module is triggered to perform APP prediction. The prediction module acquires the gain scores of the alternative APPs related to the WeChat from the algorithm module, for example, the gain scores of the alternative APPs such as known, Baidu, Taobao, Payment Bao, and tremble are acquired.

The prediction module determines known, hundred and pan target APPs from the alternative APPs, and the prediction module can send the known, hundred and pan APP identifications to the system process manager for preloading.

For example, the system process management module may preload the known corresponding starting resource, and if the user opens the known starting resource within 30 minutes in the future, the known starting resource is already preloaded to the memory, so that the starting resource loading process does not need to be waited, the known UI interface is directly displayed, and zero waiting for the user is realized.

As another example, the system process manager preloads the first three APPs in the sequence, namely the known, Baidu and Taobao start resources. Thus, if the user opens any one of APP in the options of know, Baidu and Taobao within 30min in the future, the UI interface of the APP is directly displayed without waiting for starting resource loading.

In the application program processing method, after monitoring the opened APP, the data acquisition module can select a target APP from the alternative APPs associated with the currently opened APP based on the gain value of the alternative APPs associated with the currently opened APP; the alternative APP associated with the currently opened APP is an APP having an association relationship with the currently opened APP in the historical time period, that is, an APP that may be opened after the APP is opened in the historical time period. Because the APP usage habit of a user has a certain rule, other APPs that are opened in a historical period of time may still be opened after the current APP is opened, which means that the probability that a target APP selected based on the gain score of the associated candidate APP is opened is higher, and the accuracy of the predicted APP is improved. And the APP opened currently is different, the target APP predicted by the prediction module may also be different, the influence of the APP opened currently is reflected, and the possibility of counting the change of the APP commonly used is low.

In addition, the application program processing method can predict the APP based on the gain value of the alternative APP calculated by the algorithm module based on the historical use data of the APP in the historical time period, such as the opening time, the closing time and the use times, and saves the collection and storage of a large amount of model training data in the whole APP prediction process.

Before performing APP prediction with a complex machine model, the complex machine model is trained with a large amount of model training data, such as model training data constructed by historical usage data, geographic location, weather, time, etc. of APP, and the model training data may include: the utility model discloses a machine model of this embodiment, including APP number of times, the working day, non-working day, the current time, electronic equipment's electric quantity, WiFi, APP commonly used in the most recent X hour (like an hour), user age and state, these model training data are stored with q-d pair form, memory space doubles, therefore for the relatively poor electronic equipment of performance make it also difficult to train complicated machine model because of collection and memory capacity are limited, in the process of gathering and storing a large amount of model training data, electronic equipment's consumption is improved and the data bulk of model training data is difficult to train out machine model when not enough, this embodiment is improving the degree of accuracy of the APP of prediction simultaneously for machine model prediction APP, memory and power consumption reduce.

In addition, in the application processing method shown in fig. 9, the algorithm module may calculate the gain score of the alternative APP in advance, so that the prediction module may directly use the gain score of the alternative APP in the algorithm module after obtaining the APP identifier, thereby improving efficiency. The embodiment may also adopt other forms, for example, after the prediction module obtains the APP identifier, the prediction module triggers the algorithm module to search for the alternative APP associated with the APP identifier, and calculates the gain score of the alternative APP. Although the obtaining duration of the gain scores is prolonged by the prediction module, the algorithm module can omit the calculation of the gain scores of all the alternative APPs, and the workload of the algorithm module is reduced.

Example two

The use habit of the user to the APP may also be related to the geographical position of the user, for example, when the user arrives at a station, the probability that the user opens the riding APP (such as a riding code) and the ticket purchasing APP is high; for example, when the user arrives at a company, the probability that the user opens the card punching APP and the office APP is high; for another example, when the user arrives at a shopping mall, the probability that the user opens the payment APP and the coupon APP is high.

In this embodiment, the prediction module may comprehensively consider the geographic location of the user and the currently opened APP, the process is shown in fig. 10, the data acquisition module may monitor the currently used APP, and the positioning module may obtain the current geographic location; the algorithm module can calculate a gain score of an alternative APP associated with the currently used APP and a geographic gain score of the alternative APP used at the current geographic position; the prediction module can judge whether the duration of the user at the current geographic position is greater than a threshold value, and if the duration is less than the threshold value, the prediction module can calculate a comprehensive gain score based on the gain score and the geographic gain score of the alternative APP and predict the APP by utilizing the comprehensive gain score; if the duration is greater than or equal to the threshold, the prediction module may use the gain score of the alternative APP for APP prediction.

Detailed process referring to fig. 11, fig. 11 shows a timing chart of another application processing method provided in this embodiment, which may include the following steps:

s201, the data acquisition module acquires the starting time of the APP, the closing time of the APP and the geographic position.

S202, the data acquisition module sends the starting time of the APP, the closing time of the APP and the geographic position to the data storage module.

S203, the data storage module stores the starting time of the APP, the closing time of the APP and the geographic position, and the number of using times of the APP is increased by one.

S204, the algorithm module obtains the starting time of the APP, the closing time of the APP, the geographic position and the using times of the APP from the data storage module.

S205, the algorithm module takes an APP in a historical time period as a source APP, and takes an APP with the starting time later than the closing time of the source APP as a standby APP; and taking the geographic position as a source object, and taking the APP used in the geographic position as an alternative APP.

S206, the algorithm module calculates the basic probability of each alternative APP, the transition probability of each alternative APP and the geographic position transition probability of each APP based on the using times of the alternative APPs.

S207, the algorithm module subtracts the basic probability from the transition probability of the same alternative APP to obtain a gain score of the alternative APP; and subtracting the basic probability from the geographic position transition probability of the same alternative APP to obtain a geographic position gain score.

And S208, the data acquisition module sends the geographic position, the APP identification and the geographic position duration to the prediction module.

S209, the prediction module obtains the gain score and the geographic position gain score of the alternative APP associated with the APP identification from the algorithm module.

S210, the prediction module judges whether the duration of the geographic position is greater than a threshold value, if so, the step S211 is executed, and if not, the step S212 is executed.

S211, the prediction module selects target APPs with gain scores sequenced at the top N bits from alternative APPs associated with the APP identifications.

S212, the prediction module selects target APPs ranked at the top N from alternative APPs associated with the APP identification and alternative APPs associated with the geographic position based on the gain scores of the alternative APPs and the gain scores of the geographic position.

S213, the prediction module sends the target APP with the first N bits to the system process manager.

S214, the system process manager preloads the target APP with the first N bits.

The difference with respect to the application processing method shown in fig. 9 is that the application processing method shown in fig. 11 introduces a parameter of a geographic location, because the geographic location of the user may be different, which may cause different APPs opened by the user, so that the data acquisition module also obtains the geographic location of the user when monitoring the APP operation, the geographic location of the user may be obtained by the positioning module, and the positioning module may be integrated in the data acquisition module, or may be an independent module, and sends the geographic location of the user to the data acquisition module.

The data acquisition module further sends the geographic position of the user to the data storage module, namely the historical use data of the APP sent by the data acquisition module comprises the geographic position of the user, and the geographic position is the geographic position where the user opens the APP; the algorithm module also calculates the geographical position gain score of the alternative APP when calculating the gain score of the alternative APP; the prediction module can comprehensively consider the gain scores of the alternative APPs and the geographic position gain scores to predict the APPs. The calculation of the geographical position gain score of the alternative APP by the algorithm module is explained as follows:

after obtaining the historical use data of all APPs in the historical time period, the algorithm module extracts the APP identification and the geographic position where the user opens the APP from the historical use data of the APP to obtain a geographic cause and effect association sequence from the geographic position to the APP, and the geographic cause and effect association sequence is marked as a place → APP, so that the probability that the user opens the APP at the place is determined to be high. Like home → smart home, it shows that the user is very likely to turn on the smart home APP at home.

When obtaining the geographical causal association sequence, the algorithm module may refer to a duration of the user at the geographical location when opening the APP, and if the duration is less than or equal to a threshold, obtain the geographical causal association sequence from the geographical location to the APP, that is, APP a1 opened by the user within a period of time after reaching a certain geographical location LOC, consider LOC → a1 as the geographical causal association sequence, otherwise ignore the geographical location LOC. Note that the alternative APP in the geo-causal association sequence may be the first APP that the user turns on at the arrival at the geographic location, or may be all APPs that turn on for a duration.

In the process of obtaining the geographic causal association sequence, the algorithm module may calculate the number of geographic transitions from the same geographic location to the same alternative APP, and then calculate the geographic location transition probability based on the number of geographic transitions.

In particular, the probability D of the geographical position transition for each alternative APP _{transfer_loc_prob} ＝D _{transfer_loc_no} /D _{transfer_loc_no_all} ，D _{transfer_loc_no} Is the number of geographical transitions, D _{transfer_loc_no_all} Is the sum of all geographical transition times to represent by the geographical transition probability the probability of opening an alternative APP at one geographical location within a historical period of time. And subtracting the basic probability from the geographic position transition probability of the same alternative APP to obtain a geographic position gain score, wherein the influence of high basic probability of a certain alternative APP on the geographic position gain score is also considered.

When the prediction module performs APP prediction, firstly, whether the duration of the APP at the geographic location is greater than a threshold value is determined, if so, the user is said to have reached the geographic location for a period of time, and since the APP associated with the geographic location is not opened during the period of time, the possibility that the user opens the APP is reduced, so that the APP associated with the geographic location can be ignored as the preloading object in this case. For example, if the user has arrived at the office and the time elapsed after the arrival exceeds the card punching time, the card punching APP is no longer used as the pre-loading object. At this time, the prediction module ignores the gain score of the geographic location, and performs APP prediction directly based on the gain score of the alternative APP, and the process is described with reference to fig. 9. If the duration is less than or equal to the threshold, the prediction module may consider the gain score of the alternative APP and the geographic location gain score in combination.

One way is that: and the prediction module obtains a comprehensive gain score based on the gain scores of the alternative APPs and the geographic position gain score, and selects the target APPs ranked at the top N from the alternative AAP associated with the APP identification and the alternative APPs associated with the geographic position.

If the prediction module calculates the average value of the gain scores of the alternative APP and the geographic position gain scores, and the average value is used as a comprehensive gain score; for another example, the prediction module performs weighting processing on the gain scores of the alternative APPs and the geographic position gain scores, and the weighting processing may allocate a weight to the gain scores of the alternative APPs and the geographic position gain scores respectively to obtain a comprehensive gain score in a weighted summation manner. The weight can be randomly assigned to a value, or the weight of the geographic position gain score is greater than the gain score of the alternative APP, because when the duration is less than or equal to the threshold, the possibility of opening the alternative APP associated with the geographic position is high, and the occupation ratio of the alternative APP in the comprehensive gain score is improved by assigning a greater weight. For example, in a home, a company, or a shopping mall, the possibility that the smart home APP, the card punching APP, the conference APP, the payment APP, and the dining APP are opened is high, and the weight of the geographic gain score of the alternative APP in these geographic locations can be appropriately increased.

In some examples, the alternative APP associated with the geographic location may be at least part of the alternative APP associated with the APP identity, such as the alternative APP associated with the geographic location may be an APP used at the geographic location with a start time later than the off time of the source APP, the source APP being the APP to which the APP identity points; in other examples, after candidate APPs associated with APP identities are determined, geographic position gain scores of the candidate APPs are obtained from an algorithm module, and a prediction module selects target APPs ranked in the top N bits from candidate AAPs associated with APP identities based on the gain scores and the geographic position gain scores of the candidate APPs; in other examples, the prediction module may obtain, from the algorithm module, the gain score of the candidate APP associated with the APP identifier and the geographic position gain score of the candidate APP associated with the geographic position with reference to the APP identifier and the geographic position, respectively, and select the target APP from the candidate APP associated with the APP identifier and the candidate APP associated with the geographic position.

For example, APP id points to APP1, and alternative APPs associated with APP id include: APP2, APP3, APP4 and APP5, alternative APPs of geographic location association including: APP4, APP5, APP6, and APP7, the prediction module may obtain gain scores of APP2 to APP5 from the algorithm module, obtain geographic position gain scores of APP4 to APP7, and calculate comprehensive gain scores for APP2 to APP7, where the geographic position gain scores of APP2 and APP3 may be 0, and the gain scores of the same APP6 and APP7 may be 0. The prediction module selects a target APP from APPs 2-7 based on the composite gain score.

The following description is made with reference to an example, and when the data acquisition module detects that the user clicks WeChat, the prediction module is triggered to perform APP prediction. The prediction module obtains the gain scores of the alternative APPs associated with the WeChat from the algorithm module, for example, obtains the gain scores of the alternative APPs such as Mei Tuo, Taobao, Paobao (further, what you are hungry in Paobao), trembling and the like. And the prediction module knows that the current position of the user is a market, and the prediction module acquires the geographic position gain scores of alternative APPs such as Mei Tuo, Pay Bao (further, how hungry the Pay Bao) and dripping which are associated with WeChat from the algorithm module.

The prediction module determines that the time of the user arriving at the shopping mall is short, then the prediction module can calculate a comprehensive gain score based on the geographic position gain score and the gain score of the alternative APP, wherein the comprehensive gain score of the Mei Tuo and the Pay Bao is the highest, and the prediction module can push the Mei Tuo and the Pay Bao to the system process management module.

In the application processing method, after monitoring that the APP is opened, the data acquisition module can trigger the prediction module to predict the APP based on the current opened APP and the geographic position of the current user, so that the prediction module can consider the influence of the geographic position on the APP to be opened on the basis of considering the influence of the current opened APP on the APP to be opened. Because the APPs that the user turns on in different geographic locations differ, introducing a geographic location may improve the accuracy of the predicted APP. Moreover, the electronic equipment can perform APP prediction based on the current geographic position of the user, the electronic equipment omits sending the geographic position of the user to the cloud server, the privacy of the user is protected from being revealed, and the privacy safety is improved.

EXAMPLE III

The prediction module in the first embodiment may perform APP prediction based on the gain scores of the alternative APPs, and the prediction module in the second embodiment may introduce the gain scores of the geographic locations based on the first embodiment, but the first embodiment and the second embodiment predict APPs that are commonly used by the user and have an association relationship with a certain APP or a geographic location, that is, the first embodiment and the second embodiment described above are directed to APP usage habits that are relatively commonly used by the user. For the APP using habit that the number of times of use of a user is small but a periodic using rule exists, prediction is difficult to perform through the first embodiment and the second embodiment.

For example, when wages are issued every month 15, the user opens a bank APP (card issuer of wage card) to check whether wages are issued, then opens a house loan APP (another bank APP to which house loan is issued) to check the amount of house loan still, opens a public deposit APP to check the balance of the public deposit, and after the house loan is completed, the user may go to shopping or enjoy food, the user opens a shopping APP/food APP, etc., but since the user only performs the above operations every month 15, the above operations are rarely performed in other time periods, so the number of times of occurrence of the association relationship between the above APPs in the history time period is small, and if APP prediction is performed according to embodiment one and embodiment two, prediction is difficult. For different users, the APP use habits of the periodic use rules are different, if some users are six months at the end of a month, three weeks at night, and some users can also pass a memorial day, for example, a certain memorial day in one year, the memorial days without the users are possibly different, and for the situations, the prediction by adopting the first embodiment and the second embodiment has certain difficulty.

To this end, the present embodiment illustrates another application processing method, which performs APP prediction based on the relationship between the current causal link path and the historical causal link path. The current causal association path and the historical causal association path are obtained by a plurality of causal association APP sequences, fig. 12 shows the current causal association path (dashed line) and the historical causal association path (solid line), as can be seen from fig. 12, the current causal association path overlaps with a part of the segments in the historical causal association path, although the application 5 and the application 6 are not completely identical, but the two applications are of the same type, it can be seen that the current causal association path is similar to a part of the segments in the historical causal association path (called sub-paths), the historical causal association path is of a periodic usage rule, as the historical causal association path in fig. 12 can be obtained at 15 th month, so that when the current causal association path is similar to the sub-paths in the historical causal association path, the prediction module can perform APP prediction based on the similar sub-paths, such as the prediction module may target the application 7 as a target APP. Detailed flow referring to fig. 13, the method may include the following steps:

s301, the data acquisition module acquires the starting time and the closing time of the APP.

S302, the data acquisition module sends the starting time and the closing time of the APP to the data storage module.

S303, the data storage module stores the starting time and the closing time of the APP.

S304, the algorithm module obtains the starting time and the closing time of the APP used in the historical time period from the data storage module.

S305, the algorithm module takes an APP in the historical time period as a source APP, and takes an APP with the starting time later than the closing time of the source APP as a standby APP.

S306, the algorithm module determines that a historical causal association path with a periodic usage rule exists in the historical time period based on the source APP and the alternative APP.

In this embodiment, the historical causal association path is a directed sequence composed of a plurality of APPs. After the algorithm module obtains the source APP and the alternative APPs, the source APP and the alternative APPs are an APP group, the alternative APP in one APP group may be a source APP in another APP group, and the source APP in the same APP group may be an alternative APP in another APP group, so that the algorithm module can link the APPs in different groups through the source APP and the alternative APPs in different APP groups to obtain a historical causal association path.

For example, one APP group includes: APP1 and APP2, APP1 being the source APP, APP2 being the alternative APP; another group of APPs includes: APP2 and APP3, APP2 being the source APP, APP3 being the alternative APP; yet another group of APPs comprises: APP3 and APP4, APP3 being the source APP, APP4 being the target APP; yet another group of APPs comprises: APP4 and APP5, APP4 being the source APP, APP5 being the target APP; the algorithm module may obtain a historical causal association path: APP1 → APP2 → APP3 → APP4 → APP 5.

The algorithm module can also determine whether the historical causal association path has a periodic usage rule or not based on the start time and the close time of the APP in the historical causal association path; and if the historical causal association path is determined to occur at intervals based on the starting time and the closing time of the APP in the historical causal association path, and the occurrence time of each historical causal association path is the same or similar, determining that the historical causal association path is a historical causal association path with a periodic use rule.

For example, if the determination occurs every other month and every time occurs at number 15 of each month based on the start time and the close time of the APP, the historical causal association path is determined to be a historical causal association path with a periodic usage rule. The algorithm module in this embodiment may also count the occurrence number of each historical causal association path.

S307, when the data acquisition module monitors that the APP operates, the data acquisition module sends the currently-operating APP identification and the APP starting time to the algorithm module through the data storage module. The transmission here may be synchronized in real time.

S308, the algorithm module determines a source APP of the alternative APP by taking the APP pointed by the APP identification as the alternative APP based on the APP identification and the start time of the APP, and obtains a causal association path where the currently running APP is located based on the alternative APP and the source APP.

The data acquisition module may trigger APP prediction when APP runtime is monitored. Before the APP prediction is carried out, the algorithm module positions the causal association path where the current operation APP is located to obtain the causal association path to which the algorithm module belongs, and thus the algorithm module can obtain a historical sub-path similar to the causal association path where the current operation APP is located based on the causal association path where the current operation APP is located and the historical causal association path.

In this embodiment, the algorithm module uses the APP to which the APP identifier points as a candidate APP, finds a source APP of the candidate APP, uses the source APP of the candidate APP as another candidate APP, searches for another source APP forward, and so on until the source APP cannot be found. And the algorithm module establishes a causal association path with the APP pointed by the APP identification as the last APP based on the relationship between the source APP and the alternative APP, wherein the causal association path is the causal association path where the currently running APP is located.

For example, the algorithm module uses the APP pointed by the APP identifier as a candidate APP, and finds APP1, APP2, and APP3 forward in sequence, then the causal association path where the currently running APP is located is: APP1 → APP2 → APP3 → currently running APP.

S309, the algorithm module obtains a sub-path similar to the causal association path where the currently running APP is located from the historical causal association path.

In this embodiment, the similar sub-paths are matched to the causal association path where the currently running APP is located because: the causal association path where the currently running APP is located may be a segment of a historical causal association path, and the similarity may be affected by the rest of the historical causal association path when the similarity of the two paths is calculated, so that the accuracy of the similarity is reduced when the historical causal association path is directly used for matching, and the accuracy of prediction is affected. Therefore, in this embodiment, the historical causal association path is split to obtain a plurality of sub-paths, and then a sub-path similar to the causal association path where the currently running APP is located in the sub-paths is searched.

The historical causal association path is split in order to improve the calculation speed, the current path is taken as a short name of the causal association path where the currently running APP is located, and one splitting mode is as follows:

(1) selecting historical causal associated paths containing APP with preset number of current paths, if the historical causal associated paths are not selected to finish the process, and if the historical causal associated paths are selected to execute (2); the preset number may be 85% of the total number, or may be other values, which are not described herein again; when (1) a historical causal association path is selected, the number of the included APPs is used as the standard, and the association relationship between the APPs is not considered (namely whether the relationship between the source APP and the alternative APP is correct or not); of course, to further ensure accuracy and reduce the amount of data calculated, the association between APPs may be referred to;

(2) performing secondary selection on the historical causal association path selected in the step (1), selecting the historical causal association path with the occurrence frequency smaller than a preset frequency threshold, and if the process is not finished; if the execution (3) is selected; the preset time threshold is used for determining that the historical causal association path is a path with a periodic use rule and a small occurrence number, the algorithm module can judge whether the historical causal association path has the use rule and the occurrence number when obtaining the historical causal association path, and if so, (2) the algorithm module is used as an optional step;

(3) for each selected historical causal association path, traversing each sub-path with the same length (namely the same number of APPs) as the current path in the selected historical causal association path;

(4) obtaining a feature vector of each sub-path and a feature vector of the current path, and obtaining the similarity between each sub-path and the current path based on the feature vector of each sub-path and the feature vector of the current path;

(5) taking the sub-path with the similarity larger than the similarity threshold as a sub-path similar to the current path; and if the sub-path similar to the current path is not obtained, ending the flow.

In this embodiment, the preset number threshold, and the similarity threshold may be set to values according to actual requirements, and this embodiment is not described in detail.

S310, the algorithm module sends a sub-path similar to the causal association path where the current operation APP is located and a historical causal association path where the similar sub-path is located to the prediction module.

S311, the prediction module predicts the target APP based on the similar sub-paths and the historical causal association paths where the similar sub-paths are located. The prediction module may use, as the target APP, an APP occurring after the similar sub-path in the historical causal association path, and further use, as the target APP, an APP occurring later with a usage number greater than a usage number threshold. Where the APP that appears later may be an APP that appears after a period of time, such as all APPs that appear after an hour, or the next APP that appears later, etc.

If the prediction module does not predict the target APP based on the later-occurring APPs, the last APP in the historical causal association path may be taken as the target APP. Of course, other methods may be used for prediction, and this embodiment is not described one by one.

Besides performing APP prediction by using historical causal association paths where similar sub-paths are located, the algorithm module may also directly calculate the similarity between the historical causal association paths and the current path, for example, obtain the feature vector of each APP in the path, calculate the similarity between the two paths based on the feature vectors of all APPs in the historical causal association paths and the feature vectors of all APPs in the current path, and obtain the historical causal association paths similar to the current path based on the similarity between the two paths; the prediction module then predicts a target APP based on a historical causal association path similar to the current path. The method can be used for determining APPs which appear after the current path from similar historical causal association paths, and predicting the target APP from the APPs which appear later.

S312, the prediction module sends the target APP with the first N bits to the system process manager.

S313, the system process manager preloads the target APP of the first N bits.

To illustrate with reference to the example, if the current path is: the line-calling APP → the middle line APP → the Gongji APP → the Jingdong APP; the algorithm module finds a historical causal association path based on the principle of 'selecting the historical causal association paths including the APP with the preset number of the current paths': the historical causal association path is a path with a periodic use rule and the occurrence frequency of the path is smaller than a preset frequency threshold value. The algorithm module can perform traversal splitting on the historical causal association path to obtain the following sub-paths:

move APP → middle move APP → accumulation fund APP → Taobao APP;

zhongxing APP → Gongji APP → Taobao APP → popular comment APP.

The algorithm module respectively calculates the similarity between the two sub-paths and the current path, and determines that the 'move line APP → middle line APP → accumulated fund APP → Taobao APP' is the sub-path similar to the current path.

The algorithm module can send the 'line calling APP → middle line APP → accumulation fund APP → panning APP' and the 'line calling APP → middle line APP → accumulation fund APP → panning APP → popular comment APP' to the prediction module, and then the prediction module determines the popular comment APP as the target APP and carries out preloading through the system process manager.

If other APPs are operated after the current operation APP, the current path can be continuously updated along with the operation of other APPs, and the algorithm module can continue to execute the steps (1) to (5) so as to update the similar sub-paths along with the update of the current path and remove the dissimilar sub-paths.

According to the application program processing method, the target APP of the current path is predicted based on the historical causal association path with the periodic use rule, and the target APP can be rapidly and effectively predicted for the APP use habit with the periodic use rule and few user use times.

Example four

The electronic device may combine the second embodiment with the third embodiment, as shown in fig. 14, at the electronic device end, the electronic device may monitor the running of the APP, for example, obtain the currently used APP, and further obtain the causal association path where the current APP is located; and then the electronic equipment respectively obtains respective alternative APPs on the basis of the currently used APP and the causal association path where the current APP is located. In some embodiments, the electronic device may obtain a gain score and a geographic position gain score of an alternative APP of a currently used APP (the two gain scores are calculated in advance), obtain a comprehensive gain score based on the gain score and the geographic position gain score of the alternative APP, and predict a second alternative APP based on the comprehensive gain score; the electronic device finds historical causal association paths based on the causal association path where the current APP is located, and obtains a plurality of sub paths from the historical causal association paths (for example, splitting the historical causal association paths to obtain sub paths). The electronic equipment sends the sub-path and the causal association path where the current APP is located to the cloud end, and obtains a feature vector from the cloud end side; and then the electronic equipment obtains similar sub-paths based on the feature vectors, and obtains a first alternative APP based on the similar sub-paths.

The electronic equipment determines that the causal association path where the current APP is located is a path with a time rule (such as a path with a periodic use and a small occurrence number), determines a target from the first alternative APP, determines a target APP from the second alternative APP if the causal association path is not the path with the time rule, and loads the target APP at a loading opportunity.

Calculation of the gain score of the alternative APP in fig. 14 is shown in fig. 15, and the electronic device may obtain the base times and the transition times based on the historical usage records (such as historical usage data) of the APP, and obtain the base probability and the transition probability based on the base times and the transition times; then, subtracting the basic probability from the transition probability to obtain a gain value of the alternative APP; when the gain score branch is taken, whether the duration of the geographic position is larger than a threshold value or not can be further judged, if the duration of the geographic position is larger than the threshold value, prediction is carried out by using the gain score of the alternative APP, if the duration of the geographic position is smaller than or equal to the threshold value, a comprehensive gain score is obtained based on the gain score of the alternative APP and the gain score of the geographic position, and prediction is carried out based on the comprehensive gain score.

The loading time of the target APP can be at least one of the time when the APP is opened, the time when the APP is closed and the APP running process. However, if the APP is started, the resource and the power consumption may be wasted, and if the APP is stopped, the resource and the power consumption may be wasted, and the problem of untimely preloading exists; the pre-loading can be carried out when the APP is closed in the APP operation process, the target APP is loaded, and the probability that the target APP is opened is large, so that the waste of resources and power consumption is solved, the problem that the pre-loading is not timely is solved, and the pre-loading time in the APP operation process can be as follows:

when prediction is performed based on a historical causal association path, the algorithm module/prediction module may obtain the use duration of the last APP in the similar sub-path, and obtain the minimum use duration Δ t from all the use durations ₁ The use duration can be obtained by subtracting the starting time of the APP from the closing time of the same APP; the algorithm module/prediction module obtains the interval time from the last APP to the next APP in the similar sub-path, and obtains the minimum interval value delta t from all the interval times ₂ The interval time may be the starting time of the next APP minus the starting time of the last APP; (Δ t) elapsed from the start time of the current APP ₁ +Δt ₂ ) Indicating the preload target APP.

When prediction is performed based on the gain score, the algorithm module/prediction module can obtain the use duration of each use of the current running APP in the historical time period, obtain the historical average use duration based on all the use durations, and take the preset quantile of the historical average use duration, for example, take the delta t of the 10 quantile of the historical average use duration ₃ (ii) a The algorithm module/prediction module takes a current running APP as a source APP and a predicted target APP as a standby APP to obtain a minimum value delta t of interval time between the two APPs in a historical time period ₄ (ii) a (Δ t) elapsed from the start time of the current APP ₃ +Δt ₄ ) Indicating the preload target APP.

Therefore, no matter based on historical causal associated path prediction or gain score prediction, the target APP can be preloaded after the currently running APP is opened and before the currently running APP is closed, and the timeliness of target APP loading is improved; and no matter based on historical causal associated path prediction or gain score prediction, prediction can be carried out based on the associated relation between the APPs, the associated relation between the APPs indicates another APP which is likely to be opened after the user opens one APP, and the APP is more in line with the use habit of the user, so that the predicted probability that the target APP is opened by the user is higher, the accuracy of the preloaded target APPs is improved, and the waste of resources and power consumption is reduced.

In addition, the application processing method provided by the embodiment has the following advantages:

1. the electronic equipment side carries out APP prediction in a simple calculation mode, and a model training process is omitted, so that the electronic equipment side can omit calculation of a large amount of complex model training data;

2. the electronic equipment side omits the calculation of a large amount of complex model training data, reduces the data volume used by the electronic equipment side, and saves the memory and the power consumption; some data used by the electronic equipment side can be provided by the cloud, and for example, the feature vectors used for calculating the similarity can be provided by the cloud, so that the power consumption is further saved;

3. geographic location and APP use data (such as opening time and closing time) can not be provided to the cloud, so that user privacy is protected;

4. the features used when the electronic device side performs APP prediction are few, for example, gain scores and the like can be used, so that the dependence on the performance of the electronic device is reduced, and the electronic device with low performance can also use the application processing method provided by the embodiment;

5. the incidence relation among the APPs and the incidence relation between the geographic position and the APPs are identified, and the APP can be predicted based on the incidence relations so as to improve the accuracy of prediction;

6. identifying the similarity between the causal association path where the current APP is located and the sub-path in the historical causal association path, and predicting the APP based on the sub-path of the similarity, wherein for the APPs which occur less times and have periodic use rules, the APP can be predicted in such a way, so that the application program processing method provided by the embodiment is perfected;

7. and a proper preloading opportunity is provided, the APP preloading starting time can be delayed, and the memory power consumption is further saved.

For the above embodiment, the gain score and the geographic position gain score of the alternative APP may be calculated in advance, or may be calculated in real time, and the gain score and the geographic position gain score of the alternative APP may be calculated by the electronic device or may be calculated by the cloud; the feature vectors of the same path can be calculated in advance, can be calculated in real time, and can be calculated by electronic equipment or cloud computing.

EXAMPLE five

In this embodiment, the UI change process of the electronic device displaying the preloaded application program through the hover ball at different trigger times will be described, where the prediction and preloading processes of the application program are the same as those in the first embodiment, and are not described herein again.

The electronic device has a floating ball function, and as shown in fig. 16, after the user sets the floating ball to the open mode on the setting page, the floating ball program will reside in the memory, that is, the floating ball program is always kept in the memory. In this scenario, icons of applications that may be opened next and have completed preloading may be displayed within the hover ball.

FIG. 17 is a schematic diagram of a UI interface for triggering APP prediction when an APP is opened for a user. After the hover ball is turned on, the hover ball always hovers over the currently displayed interface, as shown in (1) in fig. 17, and the hover ball is displayed over the desktop. When the user clicks an icon of an application program (e.g., an icon of a WeChat), the UI plane may jump to the main interface of the WeChat, as shown in (2) of FIG. 13.

Meanwhile, the user's operation of opening the WeChat triggers APP prediction, predicts that the user is most likely to open the video APP next, and preloads the starting resource of the video APP in the background, as shown in (2) in FIG. 13, the icon of the video APP is displayed in the hover ball, and after the user clicks the icon of the video APP in the hover ball, as shown in (3) in FIG. 13, the UI interface jumps from the WeChat interface to the preloaded page of the video APP. Meanwhile, the user's operation of opening the video APP can also trigger the APP prediction, and display the predicted and preloaded icons of the APP, such as music APPs, in the floating ball.

As shown in fig. 18, a UI diagram of the electronic device at the trigger timing of triggering APP prediction when returning to the desktop is shown, and as shown in (1) in fig. 18, when returning from an application to the desktop, APP prediction is triggered, the hover ball is displayed above the desktop, and since the next APP is not predicted at this time or the preloading process is not completed, no icon of any application is displayed in the hover ball. As shown in (2) in fig. 18, after the video APP is predicted and the preloading process is completed, an icon of the video APP is displayed within the floating ball. After the user clicks the icon of the video APP in the hover ball, as shown in (3) in fig. 18, the UI interface jumps to the interface of the video APP.

In addition, in a scenario where APP prediction is triggered when the user unlocks, the display of the hover ball is similar to the scenarios shown in fig. 17 and 18, and is not described here again.

In another scenario, the predicted and preloaded object may also be some service in APP. For example, as shown in fig. 19, after the user uses a certain APP and returns to the desktop, the APP prediction is triggered, it is predicted that the "ride code" service in the passing APP is the service to be opened next, as shown in (2) in fig. 19, the "ride code" service is displayed in the floating ball, at this time, if the user clicks the "ride code" service in the floating ball, the UI interface jumps from the system interface to the page of the "ride code" service, as shown in (3) in fig. 19. Besides the transition from APP to service, the electronic device may also predict a transition from service to service, a transition from geographic location to service, etc., and this embodiment is not described one by one.

If the APP prediction is triggered under the desktop, when the electronic equipment returns to the desktop, the APP prediction is started to be carried out by the electronic equipment, and after the target APP is predicted, the predicted target APP can be displayed in a floating ball of the desktop.

Some embodiments of the present application also provide an electronic device, which may include: one or more processors, memory, such as one or more processors including a CPU, GPU, and NPU; wherein the memory is configured to store one or more computer program codes comprising computer instructions that, when executed by the one or more processors, cause the electronic device to perform the above-described method.

The present embodiments also provide a computer-readable storage medium including instructions that, when executed on an electronic device, cause the electronic device to perform the above-mentioned method.

The present embodiment also provides a computer program product comprising instructions which, when run on an electronic device, cause the electronic device to perform the above-mentioned method.

The present embodiments also provide a control apparatus comprising one or more processors, a memory for storing one or more computer program codes comprising computer instructions, which when executed by the one or more processors, perform the above method. The control device may be an integrated circuit IC or may be a system on chip SOC. The integrated circuit can be a general integrated circuit, a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC).

Through the above description of the embodiments, it is clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.

In the several embodiments provided in this embodiment, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in the embodiments of the present embodiment may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present embodiment essentially or partially contributes to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a processor to execute all or part of the steps of the method described in the embodiments. And the aforementioned storage medium includes: flash memory, removable hard drive, read only memory, random access memory, magnetic or optical disk, and the like.

The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An application processing method applied to an electronic device, the method comprising:

the electronic equipment displays a recent task list, wherein the recent task list displays first content, and the first content comprises tasks which are started by a user in the electronic equipment;

after the memory clearing operation of the user is acquired, the latest task list is switched from displaying the first content to second content, and the second content is used for indicating that the electronic equipment does not start a task;

after a first starting operation of a user is acquired, displaying a first task;

switching from displaying the first task to displaying a desktop;

and after a second starting operation of the user is acquired, displaying a second task, wherein the second task is different from the first task, and the loading time length of the second task is different from the loading time length of the first task.

2. An application processing method applied to an electronic device, the method comprising:

the electronic equipment displays a floating mark, the floating mark displays third content, and the third content is at least one task which is started by a user in the electronic equipment;

after the memory clearing operation of the user is acquired, the display content of the suspension mark is empty;

after a first starting operation of a user is acquired, displaying a first task, wherein the related content of the first task can be displayed in the suspension mark;

switching from displaying the first task to displaying a desktop;

3. The method of claim 2, applied to an electronic device, further comprising:

acquiring the starting operation of the user on the suspension mark;

and responding to the starting operation, and controlling the suspension mark to be continuously displayed on the interface of the electronic equipment.

4. The method according to claim 1 or 2, characterized in that the method further comprises: when responding to the memory clearing operation of the user, storing the picture of the task started by the user;

after the first starting operation of the user is acquired, displaying the first task comprises: and after the first starting operation of the user is acquired, displaying the picture of the first task, wherein the picture of the first task is acquired when the memory clearing operation is responded in the historical use process of the first task.

5. The method according to claim 4, wherein the picture of the first task is an interface thumbnail of the first task, and the interface thumbnail is a thumbnail of an interface displayed when the first task responds to the memory clearing operation.

6. The method of claim 5, further comprising:

acquiring starting operation of a user on the first task;

and responding to the starting operation, and displaying the interface thumbnail of the first task on the electronic equipment.

7. The method according to claim 1 or 2, characterized in that the method further comprises: displaying the first task and the second task in the recent task list, wherein a display position of the first task displays a starting mark, and the starting mark is used for indicating that the first task is preloaded to a background when the user does not perform a starting operation on the first task.

8. The method according to claim 1 or 2, wherein the displaying the first task after acquiring the first opening operation of the user comprises:

after the first starting operation is acquired in a first scene, displaying a first task matched with the first scene;

and after the first starting operation is acquired in a second scene, displaying a first task matched with the second scene, wherein the first task matched with the second scene is different from the first task matched with the first scene.

9. The method of claim 8, wherein the first scene is a first time of a current date, the second scene is a second time of the current date, the first time and the second time;

and/or

The first scene is a first geographic position, the second scene is a second geographic position, and the first geographic position and the second geographic position are different.

10. The method according to claim 1 or 2, wherein the first task is a predicted task obtained in response to a predicted trigger operation by the user, the predicted task being obtained from historical usage of a plurality of tasks related to the predicted trigger operation.

11. The method of claim 10, wherein the predictive trigger operation comprises at least one of opening an application, opening a service, and bright screen unlocking; the predicted task includes at least one of a predicted application and a service.

12. The method of claim 10, further comprising:

determining a plurality of fourth tasks related to the predicted trigger operation from all the third tasks in the historical time period based on the start time of each third task in the historical time period and the stop time of the predicted trigger operation;

the predicted task is obtained according to the historical use conditions of a plurality of tasks related to the prediction trigger operation, and the predicted task comprises the following steps:

obtaining a gain score for each fourth task, the gain score being indicative of a transition from the predictive trigger operation to the fourth task over the historical period of time, and the gain score removing an effect of a usage status of the fourth task among the plurality of fourth tasks over the historical period of time;

deriving the predicted task from the plurality of fourth tasks based on the gain score of each of the fourth tasks.

13. The method of claim 12, wherein obtaining a gain score for each fourth task comprises:

obtaining a first basic probability of each fourth task based on the number of usage times of each fourth task in the historical time period and the total number of usage times of the plurality of fourth tasks, wherein the first basic probability of the fourth task is used for indicating the usage condition of the fourth task in the plurality of fourth tasks in the historical time period;

obtaining a first transition probability of each fourth task based on the number of transitions from the predictive trigger operation to the fourth task and the total number of transitions of the plurality of fourth tasks within the historical time period;

and subtracting the first basic probability of the fourth task from the first transfer probability of the fourth task to obtain a gain score of the fourth task.

14. The method of claim 12, further comprising: obtaining geographic location gain scores for a plurality of fifth tasks used at the current geographic location;

the step of obtaining the predicted task according to the historical use condition of a plurality of tasks related to the prediction trigger operation further comprises the following steps:

if the duration of the electronic equipment at the current geographic position is less than or equal to a threshold value, obtaining a comprehensive gain score of each task in the fourth task and the fifth task based on the geographic position gain score of the fifth task and the gain score of the fourth task;

obtaining the predicted task from the fourth and fifth tasks based on the combined gain scores of the tasks;

and if the duration of the current geographic position of the electronic equipment is greater than the threshold value, obtaining the predicted task from the plurality of fourth tasks based on the gain value of each fourth task.

15. The method of claim 14, wherein obtaining geographic location gain scores for a plurality of fifth tasks used in a current geographic location comprises:

obtaining a second base probability of using each of the fifth tasks at the current geographic location based on the number of uses of each of the fifth tasks at the current geographic location within the historical period of time and the total number of uses of the fifth tasks, wherein the second base probability of each of the fifth tasks is used for indicating the use condition of the fifth task in the fifth tasks at the current geographic location within the historical period of time;

obtaining a second transition probability of using each fifth task at the current geographic location based on the number of transitions from the current geographic location to the fifth task and the total number of transitions of the plurality of fifth tasks within the historical time period;

and subtracting the second basic probability of the fifth task from the second transition probability of the fifth task to obtain the geographic position gain score of the fifth task.

16. The method of claim 12, further comprising: loading the predicted task at a first preset loading opportunity;

the first preset loading opportunity is a first preset time after the start time of the task pointed by the prediction trigger operation passes, the first preset time is the sum of a third time and a fourth time, the third time is obtained based on the use time of the task pointed by the prediction trigger operation in each use in the historical time period, and the fourth time is obtained based on the interval time between the task pointed by the prediction trigger operation in the historical time period and the predicted task.

17. The method of claim 10, wherein the predicted task being derived from historical usage of a plurality of tasks associated with the predicted trigger operation comprises:

obtaining a related task path corresponding to the prediction trigger operation, wherein the related task path takes a task pointed by the prediction trigger operation as a last task and is obtained based on a task executed before the prediction trigger operation;

obtaining a historical associated task path in a historical time period;

obtaining a historical associated task path matched with the associated task path based on the feature vector of the associated task path and the feature vector of the historical associated task path;

and obtaining the predicted task based on the matched historical associated task path.

18. The method of claim 17, wherein obtaining a historical associated task path matching the associated task path based on the feature vector of the associated task path and the feature vector of the historical associated task path comprises:

selecting a first historical associated task path from all historical associated task paths in the historical time period, wherein the first historical associated task path is a historical associated task path containing a preset number of tasks in the associated task path;

selecting a second history associated task path from all the first history associated task paths, wherein the second history associated task path is the first history associated task path with the occurrence frequency smaller than a preset frequency threshold;

selecting a sub-path from the second historical associated task path, wherein the sub-path is the same as the number of tasks in the associated task path in the second historical associated task path;

obtaining sub-paths matched with the associated task paths based on the feature vectors of each sub-path and the feature vectors of the associated task paths;

the obtaining the predicted task based on the matched historical associated task path comprises: and obtaining the predicted task based on the tasks appearing after the matched sub-path.

19. The method of claim 18, further comprising: loading the predicted task at a second preset loading opportunity;

the second preset loading opportunity is a second preset time after the start time of the task pointed by the predicted trigger operation passes, the second preset time is the sum of a fourth time and a fifth time, the fourth time is obtained based on the use time of the last task in the matched sub-paths in the historical time period, and the fifth time is obtained based on the interval time from the last task to the next task in the matched sub-paths in the historical time period.

20. An application processing apparatus, applied to an electronic device, the apparatus comprising:

a display unit, configured to display a recent task list, where the recent task list displays first content, and the first content includes a task that has been started by a user in the electronic device;

the control unit is used for controlling the latest task list to be switched from displaying the first content to second content after the memory clearing operation of the user is acquired, wherein the second content is used for indicating that the electronic equipment does not start a task; after a first starting operation of a user is acquired, displaying a first task; and after a second starting operation of the user is acquired, displaying a second task, wherein the second task is different from the first task, and the loading time of the second task is equal to the loading time of the first task.

21. An application processing apparatus, applied to an electronic device, the apparatus comprising:

the display unit is used for displaying a floating mark, the floating mark displays third content, and the third content is at least one task started by a user in the electronic equipment;

the control unit is used for controlling the display content of the suspension mark to be empty after the memory clearing operation of the user is acquired; after a first starting operation of a user is acquired, displaying a first task, wherein the related content of the first task can be displayed in the suspension mark; and after a second starting operation of the user is acquired, displaying a second task, wherein the second task is different from the first task, and the loading time of the second task is equal to the loading time of the first task.

22. An electronic device comprising a memory and a processor, the memory storing instructions executable by the processor, the execution of the instructions by the processor causing the electronic device to perform the application processing method of any of claims 1 to 19.

23. A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor of an electronic device, causes the electronic device to perform an application processing method according to any one of claims 1 to 19.