CN116383513A

CN116383513A - Application recommending method, electronic equipment and storage medium

Info

Publication number: CN116383513A
Application number: CN202310636068.8A
Authority: CN
Inventors: 刘俊良; 黄龙; 李勇; 谢泽雄; 秦涛
Original assignee: Honor Device Co Ltd
Current assignee: Honor Device Co Ltd
Priority date: 2023-06-01
Filing date: 2023-06-01
Publication date: 2023-07-04

Abstract

The application discloses a method for recommending applications, electronic equipment and a storage medium, which are applied to the electronic equipment, wherein the electronic equipment supports login of different accounts. Acquiring an account of the current login electronic equipment when recommending the application; determining a first application set according to first data under the condition that the account currently logged in the electronic equipment is a first account; or, in the case that the account currently logged in the electronic device is the second account, determining the second application set according to the second data. The electronic device can predict the application of interest to the user and present the application of interest to the user on the designated area of the display interface of the electronic device, thereby reducing the time and difficulty for the user to find the required application. According to the method and the device, collected data are distinguished through different accounts, namely the first account corresponds to the first data, and the second account corresponds to the second data, so that personalized recommendation can be carried out for different users on the same equipment, and the method and the device have pertinence.

Description

Application recommending method, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of electronic technologies, and in particular, to a method for recommending applications, an electronic device, and a storage medium.

Background

At present, electronic devices such as notebook computers and tablet computers have become common tools in daily life, and when a user wants to open an application program in the electronic device, the user often searches for a shortcut of the application program on a desktop of the electronic device. Because the number of applications installed in the electronic device is often relatively large, and besides the shortcuts of the applications, various documents, pictures and the like may be displayed on the desktop, so that the user needs to search for the shortcuts of the applications from a plurality of files on the desktop, and experience is poor.

Disclosure of Invention

The application recommending method, the electronic device and the storage medium can recommend the application for different users on the same device. The technical scheme is as follows:

in a first aspect, an embodiment of the present application provides a method for recommending an application, where the method is applied to an electronic device, and the electronic device supports login of different accounts.

The method comprises the following steps: acquiring an account of the current login electronic equipment; determining a first application set according to first data under the condition that the account currently logged in the electronic equipment is a first account, and displaying the application in the first application set in a first area of a display interface of the electronic equipment, wherein the first data comprises data which is collected by the electronic equipment and related to user operation acting on at least one application during the process of logging in the electronic equipment by the first account, and the at least one application comprises the application in the first application set; or alternatively, the first and second heat exchangers may be,

And under the condition that the account currently logged in the electronic equipment is a second account, determining a second application set according to second data, and displaying the applications in the second application set in a second area of a display interface of the electronic equipment, wherein the second data comprises data which are collected by the electronic equipment and related to user operation acting on at least one application during the process of logging in the electronic equipment by the second account.

Based on the technical scheme, according to the collected data related to the user operation acting on the application, the electronic device can learn the habit of using the application by the user, forecast the application interested by the user and present the application interested by the user on the appointed area of the display interface of the electronic device, so that the user does not need to search the application which is wanted to be used from a plurality of files on the desktop, the time and difficulty for searching the application which are needed by the user are reduced, the efficiency of searching the application by the user can be improved, and the user experience is improved. In addition, in the embodiment of the application, the electronic device supports different account login, during the period that the user logs in the electronic device using a certain account, data are collected, and the collected data are distinguished through different accounts, namely, the first account corresponds to the first data, and the second account corresponds to the second data, so that during the period that the electronic device logs in the electronic device using a certain account, the habit of using the application by the user corresponding to the account can be analyzed based on the data corresponding to the logged-in account, and the application is recommended to the user. When the login account is changed, the application can be recommended for the user by using the data corresponding to the changed account, personalized recommendation can be performed for different users on the same equipment, and the method has pertinence.

With reference to the first aspect, in certain implementations of the first aspect, the user operation acting on the at least one application includes at least one of: an operation of starting an application, an operation of exiting the application, and an operation of switching between applications. Wherein the operation of switching between applications refers to switching from a display window of one application to a display window of another application.

With reference to the first aspect and the implementation manner of the first aspect, in certain implementation manners of the first aspect, the first data includes data related to user operations acting on a preset application collected by the electronic device during the logging of the first account into the electronic device, and at least one application includes a preset application, where the preset application includes an application in the first application set.

In some situations, although the electronic device collects data related to user operations acting on each application, a recommended application list and/or an un-recommended application list is preset in the electronic device, when an application is recommended, the data related to the user operations acting on the recommended application is obtained, and a first application set is determined according to the data, wherein the recommended application is a preset application, so that some applications installed in the electronic device cannot be recommended to the user, and applications affecting the safety and performance of the electronic device such as virus application pushing are avoided.

With reference to the first aspect and the implementation manner of the first aspect, in some implementation manners of the first aspect, before displaying the applications in the first application set in the first area of the display interface of the electronic device, the method further includes: determining applications in the first application set which are already installed in the electronic equipment;

displaying applications in the first application set in a first area of a display interface of the electronic device, including: and displaying the applications installed in the electronic device in the first application set in a first area of a display interface of the electronic device.

In some cases, the electronic device installs a certain application and collects data related to user operations acting on the application in a data collection phase, but the user may uninstall the application from the electronic device after collecting the data. When recommending the application, after determining the first application set, the electronic device judges whether each application in the first application set is currently installed in the electronic device, determines the application currently installed in the electronic device in the first application set, displays the application installed in the electronic device in the first application set in a first area, and displays the application not installed in the electronic device in the first application set in the first area, so that the recommendation of the uninstalled application is avoided, and the user experience is improved.

With reference to the first aspect and the implementation manner of the first aspect, in some implementation manners of the first aspect, the electronic device is a computer, and the first area includes a task bar in a display interface. The first area may be a task bar in the desktop or an area other than the task bar. The position of the first region may be fixed or may be displayed at a position not blocked by a window displayed in the desktop as the position of the window displayed on the desktop changes. The position of the first area can also be set by the user independently, so that user experience is improved.

With reference to the first aspect and the implementation manner of the first aspect, in some implementation manners of the first aspect, before displaying the applications in the first application set in the first area of the display interface of the electronic device, the method further includes: determining whether an application to be displayed in the task bar in the first application set is an application fixed in the task bar;

displaying applications in the first application set in a first area of a display interface of the electronic device, including: and displaying the application which is not fixed in the task bar under the condition that the application to be displayed in the task bar in the first application set is the application which is not fixed in the task bar.

Since some applications may be set to be pinned to the taskbar, icons of those pinned applications are always displayed on the taskbar. After the first application set is determined, determining whether an application to be displayed in the task bar in the first application set is an application fixed in the task bar, and if not, displaying the application in the task bar; if the application to be displayed in the task bar in the first application set has the application fixed in the task bar, the application fixed in the task bar is not required to be displayed any more, and therefore repeated display of icons of the same application in the task bar is avoided.

The applications to be displayed in the taskbar in the first application set are all applications in the first application set or are applications currently installed in the electronic device in the first application set.

In addition, during normal running of the application, if a display interface (window) of an application is displayed on the desktop, an icon of the application is also displayed on the taskbar. The electronic device may also determine whether an application in the first application set to be displayed in the taskbar is already in a running state and whether an icon thereof is displayed in the taskbar. If a certain application in the first application set is running and the icon is displayed in the task bar, the application is not required to be displayed any more, and other applications in the first application set are displayed in the task bar of the desktop; and if not, displaying the corresponding application in the first application set on a task bar of the desktop.

With reference to the first aspect and the implementation manner of the first aspect, in some implementation manners of the first aspect, before displaying the applications in the first application set in the first area of the display interface of the electronic device, the method further includes: determining whether an association relationship exists between the application in the first application set and other applications, wherein the other applications do not belong to the first application set;

displaying applications in the first application set in a first area of a display interface of the electronic device, including: in the case that an association relationship exists between the application in the first application set and other applications, the other applications are displayed in the first area, and the applications in the first application set are not displayed in the first area. Since the use of some applications may depend on other applications, i.e. there is an association, for example, when starting one application a, it is necessary to start another application B first, and start the application a in another application B. After the first application set is determined, if the association relationship exists between the application in the first application set and other applications, other applications are displayed in the first area without displaying the application in the first application set, so that the situation that a user needs to search the application associated with the application after displaying a certain application is avoided, and the user can use the application more conveniently.

With reference to the first aspect and the implementation manner of the first aspect, in certain implementation manners of the first aspect, at least two time periods correspond to each other during the login of the first account to the electronic device, where the at least two time periods include a first time period and a second time period, and determining the first application set according to the first data includes:

determining a first weight for each application used by the user during the first period of time based on data collected during the first period of time relating to user operation on the at least one application;

determining a second weight for each application used by the user during the second time period based on data collected during the second time period relating to user operation on the at least one application;

and determining a first application set from at least one application according to the first weight and the second weight.

With reference to the first aspect, in certain implementation manners of the first aspect, specific implementation manners of determining the second data and displaying the applications in the second application set may refer to the content in the foregoing method.

In a second aspect, an embodiment of the present application provides an electronic device, including: one or more processors; one or more memories; the memory stores one or more programs that, when executed by the processor, cause the electronic device to perform any of the possible methods of the first aspect described above.

In a third aspect, an embodiment of the present application provides an apparatus, where the apparatus is included in an electronic device, and the apparatus has a function of implementing the foregoing aspects and a possible implementation manner of the foregoing aspects of the electronic device. The functions may be realized by hardware, or may be realized by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the functions described above. Such as a display module or unit, a detection module or unit, a processing module or unit, etc.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the method of the first aspect described above.

In a fifth aspect, embodiments of the present application provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of the first aspect described above.

The technical effects obtained by the second, third, fourth and fifth aspects are similar to the technical effects obtained by the corresponding technical means in the first aspect, and are not described in detail herein.

Drawings

Fig. 1 is a schematic structural diagram of an electronic device 100 according to an embodiment of the present disclosure;

fig. 2 is a schematic software architecture diagram of an example electronic device 100 according to an embodiment of the present application;

FIG. 3 shows an exemplary interface diagram provided by an embodiment of the present application;

FIG. 4 is a flowchart illustrating an exemplary method for recommending an application according to an embodiment of the present application;

FIG. 5 shows an exemplary interface diagram provided by an embodiment of the present application;

FIG. 6 is a schematic diagram illustrating an exemplary decision tree structure according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of an example of decision tree cross-validation training provided by an embodiment of the present application;

FIG. 8 is a flowchart illustrating an exemplary multi-way recall method according to an embodiment of the present disclosure;

FIG. 9 is a schematic diagram illustrating an example of determining a recall weight for each path according to an embodiment of the present application;

fig. 10 is a flowchart of a method for recommending an application according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, embodiments of the present application will be described in further detail below with reference to the accompanying drawings. The terms "first" and "second" are used below for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

The embodiment of the application recommending method can provide personalized application recommendation for users aiming at different accounts of the same electronic equipment. The method provided by the embodiment of the application is applied to electronic equipment capable of installing applications, such as mobile phones (mobile phones), tablet computers, notebook computers, palm computers, mobile internet devices (mobile internet device, MID), wearable devices, virtual Reality (VR) devices, augmented reality (augmented reality, AR) devices, electronic equipment in smart home (smart home), and the like. The following describes embodiments of the present application in detail using a notebook computer as an example.

A schematic hardware architecture of the electronic device 100 in which the above method can be implemented is described below. Exemplary, fig. 1 shows a schematic hardware structure of an electronic device 100 according to an embodiment of the present application.

The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (universal serial bus, USB) interface 130, a charge management module 140, a power management module 141, a battery 142, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a camera 193, a display 194, and the like. Wherein the sensor module 180 may include a pressure sensor 180A.

It should be understood that the structure illustrated in the embodiments of the present invention is not limited to the specific embodiment of the mobile phone 100. In other embodiments of the present application, the handset 100 may include more or fewer components than shown, or certain components may be combined, or certain components may be split, or different arrangements of components may be provided. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

Fig. 2 is a schematic software structure of an electronic device 100 according to an embodiment of the present application.

The layered architecture divides the software into several layers, each with distinct roles and branches. The layers communicate with each other through a software interface. In some embodiments, the software systems of the electronic device 100 are respectively an application layer, an application framework layer, and a hardware abstraction layer from top to bottom.

The application layer may include a series of application packages.

As shown in FIG. 2, the application package may include applications such as recommendation manager, account, music, video, etc.

The application framework layer provides an application programming interface (application programming interface, API) and programming framework for application programs of the application layer. The application framework layer includes a number of predefined functions.

As shown in FIG. 2, the application framework layer may include a window manager, a content provider, a view system, a resource manager, a notification manager, and the like.

The window manager is used for managing window programs. The window manager may obtain the size of the display screen, determine whether there is a lock screen, intercept the screen, etc.

The content provider is used to store and retrieve data and make such data accessible to applications. The data may include video, images, audio, browsing history, bookmarks, and the like.

The view system includes visual controls, such as controls to display text, controls to display pictures, and the like. The view system may be used to build applications. The display interface may be composed of one or more views.

The resource manager provides various resources for the application program, such as localization strings, icons, pictures, layout files, video files, and the like.

The notification manager allows the application to display notification information in a status bar, can be used to communicate notification type messages, can automatically disappear after a short dwell, and does not require user interaction. Such as notification manager is used to inform that the download is complete, message alerts, etc.

The overall workflow of the electronic device 100 is illustrated below for ease of understanding.

The electronic device 100 is provided with a functional module for implementing the method for providing recommended applications according to the embodiment of the present application. In one embodiment, the functional module is installed in an electronic device in the form of an APP, having a display interface and icons that can interact with a user. When the function module is in the form of an APP, the APP corresponding to the function module may be referred to as a "recommendation manager". The recommendation manager may be automatically started and operated when the user is started, or the recommendation manager may not be automatically started when the user is started, and may be started when the user's start operation is detected. After the recommendation manager starts, an account for logging in the electronic device can be acquired, data related to user operation acting on at least one application is acquired, and the application is recommended for a user corresponding to the account according to the acquired data. The data related to the user operation acting on the at least one application may subsequently be referred to as simply data related to the user operation.

It should be noted that the above process is only exemplary, and not limiting.

The account for logging into the electronic device is described below.

When a user normally uses the electronic device, the user needs to log in the electronic device by using an account. After logging into the electronic device, the user may view information of the logged-in account, and illustratively, as shown in fig. 3, the user may click "start" to click on the avatar at the location shown by the dashed box to view information of the current account.

The electronic device supports login of different accounts, and after a user logs in the electronic device by using the first account, the logged-in account can be switched. Illustratively, the user may switch the first account to the second account by entering a "start-switch user" into the switch page as shown in FIG. 3. The user may also add new account information by starting-changing the account settings into the settings page. An account may also be referred to as an account number, a login account number, account information, and the like.

The account may be represented by an identity (Identity document, id), may be noted as sed, or userid, and the electronic device considers that different accounts correspond to different users. The behavior of different users using an application is differentiated by sil.

The method for recommending the application provided by the embodiment of the application is described in detail below. Fig. 4 is a schematic flow chart of a method for recommending applications according to an embodiment of the present application, where the method includes the following steps S401 to S403.

S401, acquiring an account of the current login electronic equipment.

When recommending an application, a recommendation manager may obtain an account of the current electronic device from the account through an interface provided by the system.

In one implementation, the recommendation manager may obtain the account of the current electronic device at preset time intervals, and illustratively, the recommendation manager may obtain the account information every 30 minutes. In another implementation, after the account information is acquired for the first time, the recommendation manager can monitor the account of the login electronic device, and when the account of the login electronic device is monitored to change, the account information after the change is acquired again.

S402, determining a first application set according to first data and displaying applications in the first application set in a first area of a display interface of the electronic device under the condition that an account currently logged in the electronic device is a first account, wherein the first data comprises data which is collected by the electronic device and related to user operation acting on at least one application during the process of logging in the electronic device by the first account, and the at least one application comprises the applications in the first application set; or alternatively, the first and second heat exchangers may be,

s403, determining a second application set according to second data when the account currently logged in the electronic device is a second account, and displaying the applications in the second application set in a second area of a display interface of the electronic device, wherein the second data comprises data, which are collected by the electronic device and are related to user operations acting on at least one application during the process of logging in the electronic device by the second account.

To be implemented as a user recommended application requires that the data generated when the user uses the application be collected first. Illustratively, the recommendation manager is able to perceive the operation of the user plane acting on the application. In the case where the user clicks on an application, the recommendation manager may perceive the click application event. The recommendation manager then collects the time of occurrence of the event clicking the application and the application clicked by the corresponding user, generates data related to the user operation, and associates the data related to the user operation with an account logged in the electronic device when the data was collected.

After obtaining the data related to the user operation, the recommendation manager may process the data related to the user operation associated with the account during a period when the account logs into the electronic device, to obtain a recommendation application list, which may also be referred to as a recommendation application set. After determining the final recommended application set, the recommendation manager may display the applications in the recommended application set at preset positions on the display interface of the electronic device. The specific process of data processing may refer to the following related description, which is not repeated.

The collection of data related to user operations is described below. When collecting data related to user operations, a recommendation manager can acquire the current account sild of the electronic equipment from the account through an interface provided by the system, and the collected data related to the user operations are related to the acquired sild. In one implementation, the recommendation manager may obtain an account sil for logging into the electronic device once after each acquisition of data related to the user operation. In another implementation, the recommendation manager may obtain an account sid logged in to the electronic device after the electronic device is started, associate the collected data related to the user operation with the sed, monitor whether the account is switched in real time, and associate the data related to the user operation after switching the account with the switched account sed if the account is switched. Illustratively, during the logging of the first account into the electronic device, the recommendation manager associates the collected data related to the user operation with the sed of the first account, representing the behavior of the user corresponding to the first account using the application. After the account of the login electronic device is switched from the first account to the second account, during the second account login electronic device, the recommendation manager associates the collected data related to the user operation with the sild of the second account, which indicates the behavior of the user corresponding to the second account to use the application. The data related to the user operation collected by the recommendation manager during the first account logging in the electronic device is referred to as first data, and the data related to the user operation collected by the recommendation manager during the second account logging in the electronic device is referred to as second data.

In this embodiment of the present application, the recommendation manager collects the date and time of each execution of the user operation and the application of the operation action, and stores these information in the database corresponding to the account sed to indicate which user uses what application at what time, where the application information may be represented by a process name (process name). For example, the information stored by the electronic device after the user clicks the application 1 includes: the process name, date (2023/5/11), time of day (13:00) of application 1.

Illustratively, the user operation may include at least one of: an operation of starting an application, an operation of exiting the application, and an operation of switching between applications. The operation designation for starting the application is an operation for starting the application to run, and may be, for example, an icon for double clicking the application, clicking the icon for the application with a right click of a mouse and opening the application in a pop-up window, clicking the icon for the application by starting a taskbar, or the like. The operation designation to exit the application is an operation to cause the application to exit the background run, and may be, for example, clicking on an exit control on a display interface of the application. The operation of switching between applications refers to an operation of switching a display interface from a display window of one application to a display window of another application, that is, switching a window process of a different application, for example, a window of the application 1 is currently displayed on a desktop, a user clicks the application 2 in a taskbar, and the window of the application 2 is displayed on the desktop, where the clicking operation is an operation of switching between applications. The user operation may also be an operation in the application, where the operation in the application refers to an operation performed when a function of the application is used after the application is started, for example, clicking to play a certain video after the video software is started, clicking a certain dialog after the chat software is started, and the clicking operation is an operation in the application.

Further, the electronic device may use the ChangeState field in the database to distinguish different user operations with different state values, for example, use state value "1" to indicate an operation of starting an application, use state value "2" to indicate an operation of exiting the application, use state value "3" to indicate an operation of switching between applications, and use state value "4" to indicate an operation within the application. For example, after the user switches the application used from application 1 to application 2, the information stored by the electronic device includes: application 2's process name, date (2023/5/11), time of day (13:00), status value (3). The application corresponding to the operation of the inter-application handover is the application after handover (application 2).

The user operation may be a click operation, a voice operation, or the like.

The data collection is a continuous process, and for the first account, the first data can be used for recommending the application for the user of the first account after the corresponding first data is collected, and the electronic equipment can still collect the first data while performing recommendation calculation, so that only the first data collected at the moment is used for the next recommendation. In one implementation, application recommendation may be performed using the first data whenever it is collected, e.g., the first day when the recommended application function begins to be used collects some first data, then the next day may use the first data to make application recommendation. In another implementation, the collected data needs to be accumulated up to a certain amount of data to be usable. For example, 31 natural days of data need to be acquired. For another example, it is necessary to acquire data of 31 active days, which means that there is a record of the use of applications by the user in the electronic device on the day, and for example, in one week, the Monday user uses the electronic device and uses some of the applications in the electronic device, the Tuesday user uses the electronic device but only turns on the electronic device and does not use the applications, and the Sunday to Sunday user does not turn on the electronic device, then Monday is active, tuesday to Sunday is not active, monday to Sunday is 7 natural days, and 1 day is active. The electronic equipment is not necessarily used every day, and application recommendation is performed by acquiring data according to the effective day, so that insufficient data can be avoided, and user habit can be effectively learned.

In view of the fact that the interest degree of the user in the application may change with time, the collected data related to the user operation has a storage period, and after the storage period is reached, the electronic device may delete the data, and illustratively, at most 31 valid days, or 90 natural days may be reserved.

When the acquired data related to the user operation is used for recommending the application, a recommendation manager can acquire an account sid of the current login electronic equipment, acquire data related to the user operation corresponding to the account sid according to the acquired account sid, and further process the data related to the user operation. The recommendation manager obtains the account currently logged in to the electronic device as a first account, obtains first data associated with the first account according to the first account, and determines a first application set according to the first data. The recommendation manager obtains the account currently logged in to the electronic device as a second account, obtains second data associated with the second account according to the second account, and determines a second application set according to the second data.

In the embodiment of the application, the first data and the second data are isolated. When the account currently logged in the electronic equipment is a first account, the data of a second account cannot be acquired; similarly, when the account currently logged into the electronic device is the second account, the data of the first account cannot be obtained. The applications in the first set of applications are applications that were used by the user during the first account logging into the electronic device. The applications in the second set of applications are applications that have been used by the user during the second account logging into the electronic device, thereby protecting the privacy of different users. It should be noted that the application used by the user during the second account logging in the electronic device (i.e. the at least one application that the user operates on) may be completely different from the application used by the user during the first account logging in the electronic device, or the same application may exist. Accordingly, the applications in the first application set and the applications in the second application set may be different, which means that the behavior habits of the user corresponding to the first account and the user corresponding to the second account using the applications are different. The applications in the first application set and the applications in the second application set may also have the same application, which means that the user corresponding to the first account and the user corresponding to the second account have the same behavior habit of using the application.

It should be noted that the data collection and application recommendation corresponding to a certain account may occur during a continuous period of time, for example, the account logged into the electronic device during one month is the first account. The data collection and application recommendation corresponding to a certain account can also occur in two time periods with intervals, for example, during a period from month 1 to month 10, the account logged in the electronic device is a first account, and the data collected during the period and related to the user operation are associated with the first account; during the period from No. 11 to No. 15, logging in the account of the electronic device to be a second account, wherein the data related to the user operation collected during the period are associated with the second account; the account logged in the electronic device at 16 is the first account, and the recommendation manager can recommend the interested application to the user of the first account by using the data related to the user operation collected from 1 to 10.

It should be noted that the foregoing description is only illustrative, and the electronic device may support more accounts with the first account and the second account, which is not limited thereto.

Based on the technical scheme, according to the collected data related to the user operation acting on the application, the electronic device can learn the habit of using the application by the user, forecast the application interested by the user and present the application interested by the user on the appointed area of the display interface of the electronic device, so that the user does not need to search the application which is wanted to be used from a plurality of files on the desktop, the time and difficulty for searching the application which are needed by the user are reduced, the efficiency of searching the application by the user can be improved, and the user experience is improved. In addition, in the embodiment of the application, the electronic device supports different account login, data are collected during the process that a user logs in the electronic device by using a certain account, and the collected data are distinguished through different accounts, namely, the first account corresponds to the first data, and the second account corresponds to the second data, so that the electronic device can analyze the habit of using the application by the user corresponding to the account based on the data corresponding to the logged-in account during the process that the electronic device logs in the electronic device by a certain account, and recommend the application to the user. When the login account is changed, the application can be recommended for the user by using the data corresponding to the changed account, personalized recommendation can be performed for different users on the same equipment, and the method has pertinence.

How to display the applications in the application set is described below using the first account as an example.

The electronic device can process the collected first data, learn the behavior habit of the user using the application, predict the application which the user probably wants to use, and accordingly determine a first application set, present the application in the first application set on a desktop and recommend the application to the user. The first application set may include one, two or more applications, the applications in the first application set are ranked according to the user interest level from high to low, and the electronic device may select one, two or more applications to display in the first area of the display interface.

Illustratively, fig. 5 shows a schematic diagram of a display interface provided in an embodiment of the present application. As shown in fig. 5, the display interface is a desktop of a computer, and shortcuts (icons) of a plurality of applications and a plurality of files are displayed in the desktop. The first area may include a task bar in the desktop, or the first area may be an area in which the task bar in the desktop is located, and applications in the first application set are to be displayed in the task bar, and illustratively, application 1, application 2, and application 3 in the first application set are displayed in the task bar. The first area may also be an area other than a taskbar, such as area 10, for example, application 1, application 2 in the first application set being displayed in area 10. The position of the area 10 can be fixed, can also be changed along with the position of the window displayed in the desktop, and can be displayed at the position which is not blocked by the window displayed on the desktop, and can also be set by a user independently, so that the user experience is improved.

It should be noted that, because the habits of the users corresponding to the first account and the second account using the applications may be different, the applications in the first application set may be different from the applications in the second application set, and the applications may also have the same application. The second area may be an area where the task bar in the desktop is located, or may be an area other than the task bar, for example, the area 20, where the area 10 and the area 20 may be located at the same location, or may be located at different locations, and illustratively, the

applications

3 and 4 in the second application set are displayed in the area 20.

In some implementations, after the first application set is obtained, some processing is performed on the applications in the first application set, and whether the applications in the first application set need to be displayed or not is judged and then displayed. The processing modes provided by the embodiment of the application comprise the following steps: application deduplication and application conversion. The following is a detailed description.

The application deduplication includes installed application filtering, taskbar opening application filtering, and taskbar fixed application filtering.

After determining the first application set, the electronic device determines applications in the first application set which are already installed in the electronic device before displaying the applications in the first application set in a first area of a display interface of the electronic device; and then displaying the applications installed in the electronic device in the first application set in a first area of a display interface of the electronic device.

In some cases, the electronic device installs a certain application and collects data related to user operations acting on the application in a data collection phase, but the user may uninstall the application from the electronic device after collecting the data. When recommending the application, after determining the first application set, the electronic device judges whether each application in the first application set is currently installed in the electronic device, determines the application currently installed in the electronic device in the first application set, displays the application installed in the electronic device in the first application set in a first area, and displays the application not installed in the electronic device in the first application set in the first area, so that the recommendation of the uninstalled application is avoided, and the user experience is improved. For example, the applications in the first application set are application 1, application 2, application 3, application 4, and application 5, respectively, where application 4 and application 5 have been uninstalled, then in the interface shown in fig. 5, only application 1, application 2, and application 3 are displayed in the taskbar.

Specifically, when the application is started, information of the application, such as a corresponding process name and a corresponding installation path of the application, is obtained, and the information of the application is stored in a database. After determining the first set of applications, the electronic device reads information of the installed applications from the database. And judging whether the installed application information comprises an installation path of the application in the first application set according to the application process name, and judging whether a starting file corresponding to the application in the first application set exists according to the installation path to judge whether the application is installed. If the electronic device reads the installation path of an application in the first application set from the database and the corresponding starting file exists, the application is an installed application.

After determining the first application set, the electronic device determines whether an application to be displayed in the taskbar in the first application set is an application fixed in the taskbar before displaying the application in the first application set in a first area of a display interface of the electronic device; and then displaying the application which is not fixed in the task bar under the condition that the application to be displayed in the task bar in the first application set is the application which is not fixed in the task bar.

Since some applications may be set to be pinned to the taskbar, icons of those pinned applications are always displayed on the taskbar. After determining the first application set, if the task bar is in an open state, the electronic device determines whether an application to be displayed in the task bar in the first application set is an application fixed in the task bar, and if not, displays the application in the task bar; if the application to be displayed in the task bar in the first application set has the application fixed in the task bar, the icon of the application fixed in the task bar is not required to be displayed in the task bar, so that repeated display of the icon of the same application in the task bar is avoided. For example, the applications in the first application set are application 1, application 2, application 3, and application 6, respectively, where application 6 is fixed to the taskbar, and then in the interface shown in fig. 5, only application 1, application 2, and application 3 are displayed in the taskbar.

Specifically, the application that is pinned to the taskbar corresponds to a startup process and the relevant configuration of the startup process is stored in a configuration file. The electronic equipment acquires the process name of the application fixed on the task bar from the configuration file, compares the process name with the process name corresponding to the application in the first application set, and judges whether the application in the first application set is the application fixed on the task bar. If the process name of an application in the first application set is the same as the process name of the application fixed on the task bar, the application is the application fixed on the task bar.

In addition, during normal running of the application, if a display interface (window) of an application is displayed on the desktop, an icon of the application is also displayed on the taskbar. The electronic device may also determine whether an application in the first set of applications to be displayed in the taskbar is already in a launch state and its icon is displayed in the taskbar. Specifically, the electronic device obtains all running processes through the system interface, and determines whether there are processes of the applications in the first application set. If the running process does not have the process of the application in the first application set, displaying the application in the first application set on a task bar of a desktop; if the running process has the process of the application in the first application set, namely, if some application in the first application set is running, judging whether the process of the application corresponds to a foreground window which can be seen by a user, if the running process has the foreground window which can be seen by the user, displaying the icon of the application on a task bar, and displaying other applications in the first application set on the task bar of a desktop without displaying any more; and if not, displaying the corresponding application in the first application set on a task bar of the desktop. For example, the applications in the first application set are application 1, application 2, application 3, and application 7, respectively, where application 7 is currently running in the foreground, and only application 1, application 2, and application 3 are displayed in the taskbar in the interface as shown in fig. 5.

Application conversion refers to converting an icon of a predicted application into an icon of another application. After determining the first application set, the electronic device determines whether an association relationship exists between the application in the first application set and other applications, which do not belong to the first application set, before displaying the application in the first application set in a first area of a display interface of the electronic device;

in the case that an association relationship exists between the application in the first application set and other applications, the other applications are displayed in the first area, and the applications in the first application set are not displayed in the first area.

Since the use of some applications may depend on other applications, i.e. there is an association (which may also be referred to as a mapping), for example, when starting one application a, it is necessary to start another application B first, and start the application a in another application B. After the first application set is determined, if the association relationship exists between the application in the first application set and other applications, other applications are displayed in the first area without displaying the application in the first application set, so that the situation that a user needs to search the application associated with the application after displaying a certain application is avoided, and the user can use the application more conveniently. For example, some game applications such as hero alliance and crossing fire wire are started through a WeGame cube platform, when the applications in the first application set include hero alliance and crossing fire wire applications, mapping relations of application configurations are obtained, and according to the mapping relations, the hero alliance and crossing fire wire applications are converted into WeGame applications for display. Similarly, the method is also suitable for applications depending on a foam platform and an Epic platform.

The following describes in detail how the first data is processed to obtain the first set of applications.

In one implementation, the first data acquired by the electronic device at the time of application recommendation is all data related to user operation collected during the first account login to the electronic device.

In another implementation, when recommending the application, the first data acquired by the electronic device is data corresponding to a preset application in all data related to user operations acquired during the logging of the first account into the electronic device.

In some scenarios, although the electronic device collects data related to user operations acting on each application, a list of recommended applications and/or a list of non-recommended applications is preset in the electronic device, when an application is recommended, the electronic device obtains data related to user operations acting on the recommended applications from the database, determines a first application set according to data corresponding to the recommended applications, and only applications in the recommended applications in the first application set are determined, wherein the recommended applications are preset, so that some applications installed in the electronic device are not recommended to the user, and applications affecting the safety and performance of the electronic device such as virus application pushing are avoided.

The list of recommended applications is not fixed. In one implementation, the electronic device may obtain a list of recommended applications each time an application is recommended, and thus obtain relevant data. In another implementation manner, the electronic device may cache the acquired data, and when recommending the application, the electronic device determines whether the application in the recommended application list changes, and if not, the electronic device only needs to acquire the data related to the user operation newly added between the previous application recommendation and the current application recommendation from the database. If the application in the recommended application list changes, the electronic device retrieves the data of the changed recommended application, which is related to the user operation, from the database.

Taking a user operation as an example of a clicking operation, according to first data, the electronic device can determine the characteristics of the number of times, the frequency, the use duration and the like of the application used by the user, and then predict according to the characteristics to obtain a first application set, and for a data processing method, three strategies are provided in the embodiment of the application, and are described in detail below.

First strategy: and sorting the applications based on the application clicking times and/or the application using time, and determining a first application set based on the sorting condition.

In a first implementation, the electronic device may determine the number of clicks of each application, then rank the applications appearing in the first data from high to low based on the number of clicks of the application, and determine the first few applications with higher number of clicks as applications in the first application set. The number of clicks is the number of times the user clicks on an application. For the acquired first data, the number of clicks may be the number of all clicking operations acting on one application, and one clicking operation is counted as 1. Alternatively, the number of clicks may be the number corresponding to all the start operations and the switch operations acting on one application. Alternatively, the number of clicks may be the number corresponding to all the launch operations acting on one application.

In a second implementation, the electronic device may determine a frequency of use of each application, then order applications that appear in the first data from high to low based on the frequency of use of the applications, and determine the first few applications that have higher frequencies of use as the first application set. For example, the frequency of use of the application may be determined according to the number of days of use, for example, the effective day corresponding to the first data is 30 days, wherein the number of days of use 1 is 5 days, and the frequency of use 1 is 5/30.

In a third implementation manner, the electronic device may determine a usage duration of each application, rank all applications in the first data from high to low according to the usage duration of each application, and determine the first few applications with longer usage duration as applications in the first application set. For example, the electronic device may determine the usage period of the application according to the adjacent operation of starting the application and the operation of exiting the application. For example, the electronic device may determine a duration of use of the application based on a time between a first time and a last time of operation within the application.

In a fourth implementation manner, the electronic device may determine application weights according to a plurality of application click times, use frequencies and use durations, sort the applications according to the application weights, and determine the first few applications with higher weights as applications in the first application set. For example, a weight 1, a weight 2, and a weight 3 are respectively assigned to the number of clicks, the frequency of use, and the time length of use, then the ratio of the number of clicks of each application to the total number of clicks of all applications is determined as a first ratio, the frequency of use is determined as a second ratio, the ratio of the time length of use of each application to the total time length of use of all applications is determined as a third ratio, and the weight of one application=the first ratio×the second ratio×the weight 1+the third ratio×the weight 3.

In a fifth implementation manner, the electronic device divides the first data into data of a plurality of time periods according to the time information, then determines the current time information when the application recommends, acquires the first data in the corresponding time, determines one or more of the number of clicks, the frequency of use and the duration of use of the application in the time, and then sorts the applications in the time based on one or more of the number of clicks, the frequency of use and the duration of use, and determines the first application set.

The time may be divided from the date or the time period of each day. The time information may include week information and/or date information (e.g., year, month, and day information); information about the time of day (e.g., information about hours and minutes) may also be included.

From the viewpoint of date division, there may be the following two division modes: the division is performed in units of one week, and the division is performed in units of weekdays and holidays.

Taking the number of clicks as an example, in one implementation, the electronic device may determine the number of clicks of the application per day in a week, and further may determine the average number of clicks of each application in the same number of days in different weeks, and determine the first application set based on the average number of clicks of the application. For example, the electronic device may determine the number of clicks for different applications used each day over 7 days monday through monday, e.g., 5 applications are used on monday, and the number of clicks for each application is determined. The average number of clicks per application for the same day for different weeks may then be determined. For example, the electronic device may determine a sum of the number of clicks for the same application used by each monday for 5 weeks, and then determine an average number of clicks for each application used by monday.

In another embodiment, the first data is in units of weekdays and holidays. I.e. the electronic device may be divided into two types, namely a workday and a holiday. Whether each day is a weekday or holiday may be determined by a calendar or a work schedule. The electronic device may then determine an average number of clicks for each application on all weekdays, and determine an average number of clicks for each application on all holidays, so that the first application set may be determined according to the average number of clicks for different applications on weekdays and the average number of clicks for different applications on holidays.

From the viewpoint of division of the time period per day, there may be the following two manners of division: the division is performed at time intervals and at time windows.

Taking the number of clicks as an example, in one embodiment, the electronic device may divide the time of day into a plurality of time intervals that do not overlap, and determine an average number of clicks for each application within each time interval.

Illustratively, the day is divided into 24 time intervals, each time interval being 1 hour, and the electronic device can determine the number of clicks per application per hour over 10 days. The average number of clicks per application at 00:00-01:00, average number of clicks per application at 01:00-02:00, average number of clicks per application per day over the 10 days, were then calculated average number of clicks per application at 02:00-03:00, … …, average number of clicks per application at 23:00-00:00. The above-mentioned 10 may be monday, weekdays, holidays, or the like, and is not limited thereto.

In another embodiment, the electronic device may slide a time window of a particular length at a particular window interval (length of time) to determine an average number of clicks per application within each time window.

Illustratively, determining the time window as 1 hour, the window interval as 30 minutes, the electronic device may determine the number of clicks per application within each time window over 30 days. The average number of clicks per application per day, 00:00-01:00, 00:30-01:30, 01:00-02:00, … …, 23:00-00:00, were then calculated over the 30 days. The time length of the time window is longer than the time length of the window interval.

The time division may be combined with the two angle division modes, and the total time division may include four division modes, and the following specific description will be given by taking the click times as an example:

mode 1: the electronic device may determine an average number of clicks per application per week for each time interval, divided in units of one week and at different time intervals.

Mode 2: the electronic device may determine the average number of clicks per application per week for each time window, divided in units of one week and in different time windows.

For example, the electronic device may determine the number of clicks for different applications within 30 minutes of each of monday through 7 days of the week of 5. The average number of clicks per application over the same period of time for different weeks may then be determined. For example, the electronic device may determine the average number of clicks for each application for each time period between 00:00-00:30, 00:30-01:00, and 01:00-01:30 … … for monday of 5 weeks, where the time interval may be 30 minutes, 1 hour, or 2 hours, and the length of the time interval is not limited. For another example, the electronic device may determine an average number of clicks for different applications for each time window between 00:00-00:30, 00:15-00:45, and 00:30-01:00: 00 … … for monday of 5 weeks. Wherein the time window (e.g., 00:00-00:30 is 30 minutes) is 30 minutes long and each time slides for 15 minutes (e.g., a sliding time interval of one time window from 00:00 to 00:15).

Mode 3: the electronic device may divide the date into two types, namely, a workday and a holiday, and into a plurality of time intervals that do not overlap, and the time of day is divided into a plurality of time intervals that do not overlap, and the average number of clicks of each application in each time interval is determined.

Mode 4: the electronic device may divide the date into two types, namely, the working day and the holiday, and slide a time window with a specific length according to a specific window interval to determine an average click frequency of each application in each time window.

For example, the electronic device may determine the number of clicks of each application for different time periods of the day for the first two months (60 days, with 44 days on weekdays, 16 days on holidays), and then may determine which days are weekdays, which days are holidays, and determine the average number of clicks of each application for the same time period in the weekdays of 44 days, and the average number of clicks of each application for the same time period in the 16 days holidays. For example, the electronic device may determine the number of clicks for different applications for each time period between 00:00-00:30, 00:30-01:00, and 01:00-01:30 … … each day of the 44 day workday, and the number of clicks for different applications for each time period between 00:00-00:30, 00:30-01:00, and 01:00-01:30 … … each day of the 16 day holiday, in turn determining the average number of clicks for each application for the same time period in the workday and holiday. The time interval for each determination may be 30 minutes, 1 hour, or 2 hours, and the length of the time interval is not limited. For another example, the electronic device may determine 00:00-00:30, 00 every day of the 44 day workday: the number of clicks for each application that is different for each time window between 15-00:45 and 00:30-01:00: 00 … …, and the number of clicks for each application that is different for each time window between 00:00-00:30, 00:15-00:45, and 00:30-01:00: 00 … … each day in a holiday for 16 days, are determined, thereby determining the average number of clicks for each application for the same time window in the weekday and holiday. The length of the time window and the time interval of each sliding are exemplary, and are not limited. The number of days (60 days) of the sample is not limited.

After the first data is obtained, the electronic device may determine information (year, month and day) of a current date, obtain data of a corresponding date from the first data, for example, monday, workday and holiday, then determine an average number of clicks of the applications in the corresponding date, and rank the average number of clicks from high to low, so as to obtain a first application set. Further, in addition to determining the current date information (e.g., 2023/5/22, monday), the electronic device may determine the current time (e.g., 11:09), obtain data of a time period or a time window where 11:09 is located in each monday from the first data, determine an average number of clicks of the application, and rank the average number of clicks from high to low, so as to obtain the first application set.

Second strategy: and inputting the first data into a first decision tree to obtain a first application set.

After the electronic device obtains the first data, the first data may be input into a first decision tree to obtain a first application set. The applications in the first application set are arranged in order of magnitude from big to small.

Fig. 6 is a schematic structural diagram of a decision tree according to an embodiment of the present application. As shown in fig. 6, the first decision tree is a first decision tree obtained by CART algorithm. The first decision tree comprises 12 nodes, of which node 7 is illustrated as an example. The keni coefficient Gini in the node 7 is 0.817, the ratio of the training instance to the total instance is 4.7%, the value (value) results are 0.0,0.0,0.009,0.0,0.0,0.0,0.017,0.0,0.252,0.0,0.022,0.0,0.23,0.026,0.0,0.03,0.117,0.0,0.222,0.017,0.0,0.004,0.0,0.026 in sequence according to the application order, the first application set can be obtained based on the high-to-low ranking of the value, and the mailbox (value=0.252) with the highest use frequency is obtained. The value in the first decision tree may be a probability value of clicking each application by the user, i.e. the first application set may be an application list ordered according to the probability values.

The first decision tree needs to be generated before the first data is entered into the first decision tree. The method of generating the first decision tree is described below:

in the application recommendation scenario, the electronic device may collect the first data in time sequence, and the user uses the result data of the application, and may use the first data and the result data as a data set. The electronic device may employ a cross-validated model training method to obtain a first decision tree.

In the K-fold cross validation method, the K-fold cross validation data sets divide the data sets into K parts in a random division mode, and K-1 parts are selected as training sets and 1 part is used as validation set each time. In the context of application recommendation, time series partitioning is employed to cross-verify the data sets. Firstly, sorting the data sets according to the ascending order of the clicking time, then equally dividing the data sets into K parts, and carrying out K-fold cross verification. In the first fold verification, the first n parts are selected as training sets, and the n+1th part is selected as verification set. In the second fold verification, the first n+1 parts are selected as training sets, the n+2 parts are selected as verification sets, and the like.

Illustratively, FIG. 7 is a schematic diagram of a decision tree cross-validation training as disclosed in an embodiment of the present application. As shown in fig. 7, the electronic device may divide the above-described data set into equal 10 copies based on the time sequence. In the first fold verification, the electronic device may use the first 6 shares as a training set and the 7 th as a verification set; in the second fold verification, the electronic device may use the first 7 parts as a training set and the 8 th part as a verification set; in the third-fold verification, the electronic device may use the first 8 parts as a training set and the 9 th part as a verification set; in the fourth-fold verification, the electronic device may use the first 9 copies as a training set and the 10 th copy as a verification set.

It should be noted that, in the above process of determining the first decision tree hyper-parameters, a grid search method may be adopted, or other methods may be used, which is not limited.

Third strategy: the electronic device may obtain the first application set through a multi-way recall ordering algorithm.

The core of the multi-way recall ordering algorithm is to select a proper result from a large number of existing selection results and finally display the result to a user. Generally comprising two phases: a recall phase and a sort phase. The recall stage is to obtain a small part of the results possibly interested by the user from all the alternative results to form a candidate set, and the sorting stage is to sort the obtained candidate set and recommend the sorted results to the user. The goal of recall is to quickly screen the recommended item candidate set to thousands or even hundreds of thousands of orders of magnitude from the tens of millions of candidates using a simple model. The sorting is to uniformly score and sort the results of a plurality of recall methods, and select the optimal ones.

The multiple recalls divide the data into at least two time periods according to the time period, for example, long-term data, recent data, and real-time data. Illustratively, the long-term data may be data related to user operations within 31 available days; the recent data may be data related to user operations over nearly 3 available days; real-time data is data of a few recent user clicks on an application, for example, 10 times, 5 times, and so on.

Fig. 8 is a flow chart of a method of a third strategy disclosed in an embodiment of the present application. As shown in fig. 8, the recall in the third strategy may be divided into three-way recalls. The three recall inputs may be long term data, near term data and real time data, respectively, as described above. Based on the three-way recall, the electronic device can acquire three weights of each application, and then can comprehensively process the three weights to acquire a first application set.

The three-way recall process is specifically described as follows:

the first path is recalled: the electronic device may input the long-term data into the second decision tree to obtain a first probability value of each application, and then obtain a first weight of each application based on the first probability value and the first recall weight of each application, and obtain a first recall result. Wherein the first probability values of all applications add to 1. The first way recall weight represents the weight of the first way recall in all way rankings. After the electronic device obtains the first probability value of each application, the first recall weight may be multiplied by the first probability value of each application to obtain the first weight of each application.

Alternatively, the electronic device may sort based on the first weight to obtain the first k thereof ₁ Application as first path recall result, k ₁ Is a positive integer. It should be noted that the second decision tree may be the same as the first decision tree or may be a different decision tree. The processing procedure of the second decision tree may refer to the processing procedure of the first decision tree, which is not described in detail. The training of the second decision tree may refer to the training of the first decision tree, and will not be described in detail.

Specifically, a first probability value p of an ith application of the X applications is obtained based on the second decision tree _i1 Wherein 1 represents the current 1 st recall policy, after which a first weight W of an ith application of the X applications may be determined _i1 ，W _i1 ＝p _i1 ·w ₁ Wherein w is ₁ And the first path recall weight. Illustratively, the first probabilities for obtaining 5 applications based on the second decision tree are respectively: application 1:0.30, application 2:0.08, application 3:0.14, application 4:0.16, application 5:0.32. under the condition that the first path recall weight is 0.2, the first weights of the applications are respectively as follows: application 1:0.06, application 2:0.016, application 3:0.028, application 4:0.032, application 5:0.064. the first recall result may be application 5:0.064, application 4:0.032,Application 3:0.028, application 2:0.016, application 1:0.06.

In the above embodiment, the history data of the user for a long period (for example, the last 3 months) is obtained, the decision tree model is trained, and the model can learn the habit of using the application stably for a long period. Inputting new characteristics to obtain probability values of each application, further determining a first weight, and taking out the front k after the arrangement from high to low according to the first weight ₁ And (5) obtaining a first-path recall result by application.

Second recall: the electronic device may input near-future data (e.g., near 3 days) into a most recent popular recall algorithm to obtain a second probability value for each application, and then based on the second probability value and the second recall weight for each application, obtain a second weight for each application, and obtain a second recall result. Recently popular recall algorithms are used to obtain applications that are frequently used by users in the near future. In one case, the most recent popular recall algorithm determines a first score as a proportion of the number of clicks of each application in the recent data to the total number of clicks, and the first score as a second probability value. For example, the total number of clicks for three days is 60, where application 4 occupies 6 times and application 5 occupies 6 times, so that it can be determined that the second probability value of application 4 is 0.1 and the second probability value of application 5 is 0.1. In another case, the recent data may include a usage time period of each application, and the recent recall algorithm may determine a specific gravity of the usage time period of each application in the recent data to a total usage time period of all applications as the second specific gravity, and use the second specific gravity as the second probability value. In yet another case, the recently trended recall algorithm may determine the second probability value in combination with the number of clicks and the length of use of each application described above. Optionally, after determining the second weights of the applications, the electronic device may sort based on the second weights to obtain the first k of the second weights ₂ The application acts as a second recall result. In addition, the second-way recall weight represents the specific gravity, k, of all the ways occupied in the second-way recall ₂ Is a positive integer.

Specifically, a second probability value p of an ith application in Y applications is obtained based on a recently popular recall algorithm _i2 . Wherein 2 represents the current path 2Recall the policy. A second weight W of an ith application of the Y applications may then be determined _i2 Is W _i2 ＝p _i2 ·w ₂ Wherein w is ₂ And the second recall weight.

Illustratively, the second probability values for 5 applications based on the most recently popular recall algorithm are application 1:0.28, application 2:0.10, application 3:0.15, application 4:0.15, application 5:0.32. in the case that the second recall weight is 0.3, the second weights of the respective applications are respectively: application 1:0.084, application 2:0.03, application 3:0.045, application 4:0.045, application 5:0.096. wherein, the second recall result may be application 5:0.096, application 1:0.084, application 4:0.045, application 3:0.045, application 2:0.03.

in the above embodiment, the recent data (e.g., the last 3 days) of the user is acquired, the recent use frequency of each application is calculated and the previous k is extracted according to the second weight from the top to the bottom ₂ And obtaining a second recall result reflecting the use habit of the recent application of the user.

And a third recall: the electronic device may input the real-time data into a time decay algorithm to obtain a third probability value of each application, and then obtain a third weight of each application based on the third probability value and the third recall weight of each application, and obtain a third recall result. The real-time data is the latest application names and the corresponding click times. The click time difference is the time difference of the click time and the current time, after which a third weight of the applications can be determined based on the click time differences of the applications. Optionally, the electronic device may sort based on the third weight to obtain the top k thereof ₃ The application acts as a third-way recall result. Wherein k is ₃ Is a positive integer.

Specifically, the electronic device may acquire Z applications clicked by the user in real time, and determine a time difference t between each application time clicked by the user and the current time. The third probability value of the ith application of the Z applications is N (t) _i = N ₀ e ^-α(ti+1) . Wherein N (t) _i For the ith application time interval t _i Attenuation values of (2); n (N) ₀ Is the initial attenuation value; alpha is an exponential decay constant; l is the translation to the left, let the value not necessarily go from N ₀ Beginning the decay while continuing the decay from any location; t is the time difference between the click time of the ith application and the current time. Wherein N is ₀ And alpha and l are all values obtained by training the electronic equipment in advance. For example, N ₀ Alpha and l are constant values determined based on data related to user operations on the previous day. The electronic device may determine that the third weight of the ith application is W based on the third probability value of the ith application and the third recall weight _i3 ＝N(t) _i ·w ₃ . Wherein 3 represents the current 3 rd way recall policy, w ₃ And a third recall weight.

For example, the electronic device may obtain a record of the applications clicked by the user in real time (e.g., the first 5 records clicked recently), calculate a time difference between the clicking time of each application and the current time, and calculate a third probability value for each application using a time decay algorithm: application 1:0.30, application 2:0.08, application 3:0.14, application 4:0.16, application 5:0.32. in the case that the third recall weight is 0.5, the second weights of the respective applications are respectively: application 1:0.15, application 2:0.04, application 3:0.07, application 4:0.08, application 5:0.16. arranging according to the weight values from large to small, wherein the third recall result is application 5:0.16, application 1:0.15, application 4:0.08, application 3:0.07, application 2:0.04.

In the above embodiment, the real-time click record of the user application is obtained, the time difference between the click time and the current time of each application is calculated, the third weight of each application is calculated by using the time decay algorithm, and the previous k is extracted from the arrangement of the third weight value from large to small ₃ And (5) obtaining a third-path recall result by application.

The electronic device may add the first weight, the second weight and the third weight of each application to obtain a fourth weight of each application, and then the electronic device may sort the applications according to the order of the fourth weight from the big to the small, to obtain the first application set. Specifically, the electronic device may apply the first weight W of the ith application _i1 Second weight W _i2 And a third weight W _i3 The sum is determined as the fourth weight W _i4 。

In the recall process of each path, the first path recall weight, the second path recall weight and the third path recall weight are weights of models trained in advance, and the weights are directly used in the recall process. The following specifically describes the determination process of each path of weight:

FIG. 9 is a schematic diagram of determining a recall weight for each path as disclosed in an embodiment of the present application. As shown in fig. 9, the electronic device may acquire data related to the user operation for 90 days. Wherein, 90 days corresponds to t-90 days, t-89 days, t-88 days, … … and t-1 days respectively. The electronic equipment can train the data of the t-90 th day, the t-89 th day, the t-88 th day, the … … th day and the t-2 th day into a third decision tree, the clicking behavior of the t-1 th day is predicted by using the third decision tree, the accuracy of the t-1 th day can be obtained, and the accuracy of the t-1 th day is used as the first recall weight. The electronic equipment can predict the clicking behavior of the t-1 day through a latest hot recall algorithm based on the data of the t-4 th day, the … … th day and the t-2 th day, the accuracy of the t-1 day can be obtained, and the accuracy of the t-1 day is used as the second recall weight. The electronic equipment can predict the clicking behavior of the t-1 day based on a time decay algorithm, the accuracy of the t-1 day can be obtained, and the accuracy of the t-1 day is used as a third recall weight.

It should be appreciated that the foregoing is merely illustrative of three-way recalls, and that in other implementations, two-way recalls may be used to determine the first set of applications, and that two-way recalls may be the first and second ways, or the first and third ways, or the second and third ways.

In the third strategy, the multi-way recall is used for respectively learning the long-term, recent and real-time use habits of the user. And dynamically calculating the recall weight of each recall by adopting the recall rate of each recall, and realizing multi-way recall fusion sorting. Thus, not only the habit of using the application for a long time by the user can be considered, but also the change of the application by the user in the near term and the habit of using the application by the user in real time can be considered. The data in long term, near term and real time are considered, so that the accuracy of recommended application can be ensured, and the user experience can be improved.

Fig. 10 illustrates a policy selection method for processing first data according to an embodiment of the present application.

As shown in fig. 10, the same policy may be used to determine the first set of applications for different accounts supported by the electronic device. Among the three policies described above, the electronic device may select one of the policies to determine the application set corresponding to each account. The electronic device may also select at least two of the policies as target policies, and determine an application set corresponding to each account through weighted calculation. For example, the target policy may include a first policy and a second policy; the first policy and the third policy may also be included; a second policy and a third policy may also be included; a first policy, a second policy, and a third policy may also be included. The specific target strategy is not limited.

For different accounts supported by the electronic device, different policies may also be used to determine the first application set, and, for example, when the first account logs in, the electronic device uses policy 1 to process the first data and recommend an application for user a. When the second account is logged in, the electronic device processes the second data by using the strategy 2, and recommends an application for the user B. When the third account is logged in, the electronic equipment processes corresponding third data by using the strategy 3, and recommends application for the user C.

In one implementation, for each account, the electronic device performs policy selection according to the number of applications used by the user, which may be an average number of applications started per unit time in a preset period of time. For example, for a first account, the electronic device may first determine that the number of applications used by the user per day (unit time) is the first number of applications on average over 31 active days (time periods). When the first application number falls into a first number range, the electronic device can process the first data through a first strategy; when the first application number falls into the second number range, the electronic device can process the first data through a second strategy; when the first number of applications falls within the third number range, the electronic device may process the first data through a third policy. In this way, the electronic device can select different recommendation strategies to recommend based on the first application number, so that the application recommendation efficiency can be improved while the accuracy of the recommended application is ensured.

The number of applications mentioned above is the number of application categories used by the user. The preset time period is greater than or equal to a unit time, and the preset time period can be 1 week, 1 month, two months, three months, 1 day and the like, and the unit time can be 1 day, 12 hours and the like, and the specific time length is not limited.

The first number range is a range in which the first number of applications is less than or equal to the first threshold, the second number range is a range in which the first number of applications is greater than the first threshold and less than or equal to the second threshold, and the third number range is a range in which the first number of applications is greater than the second threshold. The first threshold and the second threshold may be preset thresholds or trained thresholds, and the specific size is not limited.

It should be noted that, determining the second application set according to the second data may refer to determining the content of the first application set according to the first data. The policy selection method for processing the second data may refer to the policy selection method for processing the first data, which is not described in detail.

In summary, in the embodiment of the present application, according to collected data related to user operations acting on an application, an electronic device may learn a habit of using the application by a user, predict an application of interest to the user, and present the application of interest to the user on a designated area of a display interface of the electronic device, so that the user does not need to search for an application that is wanted to be used from a plurality of files on a desktop, thereby reducing time and difficulty for the user to search for the required application, improving efficiency of searching for the application by the user, and improving user experience. In addition, in the embodiment of the application, the electronic device supports different account login, during the period that the user logs in the electronic device using a certain account, data are collected, and the collected data are distinguished through different accounts, namely, the first account corresponds to the first data, and the second account corresponds to the second data, so that during the period that the electronic device logs in the electronic device using a certain account, the habit of using the application by the user corresponding to the account can be analyzed based on the data corresponding to the logged-in account, and the application is recommended to the user. When the login account is changed, the application can be recommended for the user by using the data corresponding to the changed account, personalized recommendation can be performed for different users on the same equipment, and the method has pertinence.

It should be understood that in one possible design, the steps in the method embodiments provided herein may be performed by integrated logic circuits in hardware in a processor or instructions in software. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method. To avoid repetition, a detailed description is not provided herein.

It should be noted that the processor in the embodiments of the present application may be an integrated circuit chip with signal processing capability. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or instructions in software form.

In the embodiments of the present application, the processor may be a CPU, and the processor may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

It should be appreciated that in embodiments of the present application, memory may include read only memory and random access memory, and provide instructions and data to the processor. The memory may also include non-volatile random access memory. The memory may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM).

Embodiments of the present application also provide a computer-readable storage medium storing a computer program (which may also be referred to as code, or instructions) that, when executed by a processor, implements steps that may be implemented in the various method embodiments described above.

Embodiments of the present application provide a computer program product comprising: a computer program (which may also be referred to as code, or instructions), which when executed, causes an electronic device to perform steps that may be implemented as described in the various method embodiments above.

In addition, embodiments of the present application also provide an apparatus, which may be specifically a chip, a component, or a module, and may include a processor and a memory connected to each other; the memory is configured to store computer-executable instructions, and when the device is operated, the processor may execute the computer-executable instructions stored in the memory, so that the chip performs the methods in the above method embodiments.

The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions in accordance with the embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus and the electronic device described above may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown 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 may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units 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 application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that reference to "a plurality" in this specification and the appended claims refers to two or more. In the description of the present application, "/" means or, unless otherwise indicated, for example, a/B may represent a or B; "and/or" herein is merely an association describing an associated object, and refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations, e.g., a and/or B, which may represent: a exists alone, A and B exist together, and B exists alone.

As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".

Reference in the 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 application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims

1. A method of recommending applications, characterized by being applied to an electronic device that supports login of different accounts, the method comprising:

acquiring an account currently logged in the electronic equipment;

determining a first application set according to first data under the condition that an account currently logged in the electronic equipment is a first account, and displaying applications in the first application set in a first area of a display interface of the electronic equipment, wherein the first data comprises data which are collected by the electronic equipment and related to user operation acting on at least one application during the process of logging in the electronic equipment by the first account, and the at least one application comprises the applications in the first application set; or alternatively, the first and second heat exchangers may be,

and under the condition that the account currently logged in the electronic equipment is a second account, determining a second application set according to second data, and displaying the applications in the second application set in a second area of a display interface of the electronic equipment, wherein the second data comprises data which are collected by the electronic equipment and related to user operations acting on at least one application during the process of logging in the electronic equipment by the second account.

2. The method of claim 1, wherein the user operation on at least one application comprises at least one of: an operation of starting an application, an operation of exiting the application, and an operation of switching between applications.

3. The method of claim 2, wherein the first data comprises data collected by the electronic device during a first account login to the electronic device relating to user operations acting on a preset application, the at least one application comprising the preset application, the preset application comprising an application in the first set of applications.

4. The method of any of claims 1-3, wherein prior to displaying the applications in the first set of applications in the first area of the display interface of the electronic device, the method further comprises:

determining applications in the first application set which are already installed in the electronic equipment;

the displaying the applications in the first application set in the first area of the display interface of the electronic device includes:

and displaying the applications installed in the electronic equipment in the first application set in a first area of a display interface of the electronic equipment.

5. A method according to any one of claims 1 to 3, wherein the electronic device is a computer and the first region includes a taskbar in the display interface.

6. The method of claim 5, wherein prior to displaying the applications in the first set of applications in the first area of the display interface of the electronic device, the method further comprises:

determining whether an application to be displayed in the task bar in the first application set is an application fixed in the task bar;

and displaying the application which is not fixed in the task bar under the condition that the application to be displayed in the task bar in the first application set is the application which is not fixed in the task bar.

7. The method of any of claims 1-3, wherein prior to displaying the applications in the first set of applications in the first area of the display interface of the electronic device, the method further comprises:

determining whether an association relationship exists between an application in the first application set and other applications, wherein the other applications do not belong to the first application set;

in the case that an association relationship exists between an application in the first application set and other applications, displaying the other applications in the first area, and not displaying the applications in the first application set in the first area.

8. A method according to any of claims 1 to 3, wherein at least two time periods are corresponding during the logging of the electronic device by the first account, the at least two time periods including a first time period and a second time period, the determining the first set of applications from the first data comprising:

determining a first weight for each application used by the user during the first time period based on data collected during the first time period relating to user operation on at least one application;

determining a second weight for each application used by the user during the second time period based on data collected during the second time period relating to user operation on at least one application;

and determining the first application set from the at least one application according to the first weight and the second weight.

9. An electronic device, comprising: one or more processors; one or more memories; the memory stores one or more programs that, when executed by the processor, cause the electronic device to perform the method of any of claims 1-8.

10. A computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the method of any of claims 1 to 8.