CN118051287A

CN118051287A - Application program recommendation method and electronic equipment

Info

Publication number: CN118051287A
Application number: CN202211436782.4A
Authority: CN
Inventors: 熊健; 黄桂武; 谢泽雄
Original assignee: Honor Device Co Ltd
Current assignee: Honor Device Co Ltd
Priority date: 2022-11-16
Filing date: 2022-11-16
Publication date: 2024-05-17

Abstract

The application provides an application program recommending method and electronic equipment, and relates to the technical field of computers. The scheme improves the application recommendation hit rate of the electronic equipment. The specific scheme is as follows: the electronic equipment displays a first interface, wherein the first interface comprises a first control, and the first control is used for displaying application icons of application programs to be recommended to a user; when the electronic equipment is located in a first position area and the system time belongs to a first period, the electronic equipment displays an application icon of a first application in the first control; the first weight of the first application is higher than the first weight of the second application, the application icon of the second application is not displayed on the first control, the first weight is used for indicating the enabling probability of the application program in the scene which is located in the first position area, and the system time belongs to the first period.

Description

Application program recommendation method and electronic equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to an application program recommendation method and an electronic device.

Background

Currently, the number of applications installed in electronic devices is increasing. To facilitate a user to quickly launch a target application from a large number of applications, the electronic device may assist the user in selecting some applications, such as recommended applications, and centrally displaying application icons of the recommended applications, thereby facilitating the user to find and launch the target application.

Currently, electronic devices have higher recommendation accuracy for high frequency applications, but lower recommendation accuracy for long tail applications. Among these, long-tail applications are applications that use a lower heat. While long-tailed applications are generally less hot to use, long-tailed applications are applications that users have a high probability of using in certain scenarios.

Disclosure of Invention

The embodiment of the application provides an application program recommending method and electronic equipment, which are used for improving the hit rate of application recommendation.

In order to achieve the above purpose, the embodiment of the present application adopts the following technical scheme:

In a first aspect, an application recommendation method provided by an embodiment of the present application is applied to an electronic device, where the method includes: the electronic equipment displays a first interface, wherein the first interface comprises a first control, and the first control is used for displaying application icons of application programs to be recommended to a user. When the electronic equipment is located in a first position area and the system time belongs to a first period, the electronic equipment displays an application icon of a first application in a first control; the first weight of the first application is higher than the first weight of the second application, an application icon of the second application is not displayed on the first control, the first weight is used for indicating the enabling probability of the application program in the scene of being located in the first position area, and the system time belongs to the first period.

In the above embodiment, the electronic device may determine the first application with the usage rule in the space-time scene by using the temporal scene feature and the spatial scene feature, where the first application may include an application program with a low usage heat, so after the electronic device displays the application icon of the first application in the first control, the electronic device may increase the exposure of the application program with the low usage heat, but with the usage rule, thereby effectively providing the hit rate of the application recommendation.

In some embodiments, the method further comprises: when the electronic equipment is located in a first position area and the system time belongs to a first period, the electronic equipment displays an application icon of a third application in the first control; the second weight of the third application is higher than the second weight of the fourth application, and an application icon of the fourth application is not displayed on the first control, wherein the second weight is used for indicating the probability that the application program is used by a user in the current scene, and the second weight can be determined by the interaction frequency of the user and the application program in various scenes (scenes indicated by various scene characteristics) in historical data.

In the embodiment, the electronic device can recommend the first application determined by combining the space-time characteristics to the user, and can recommend the third application determined by combining the multiple scene characteristics capable of representing the current scene to the user, so that the long-tail application of the usage rule under some space-time fixed scenes is prevented from being missed and recommended, and the recommendation accuracy is improved.

In some embodiments, the electronic device includes a first recommendation model and a second recommendation model, the first recommendation model is used for determining a second weight corresponding to each application program in different scenes, the second recommendation model is used for determining the first weight corresponding to each application program in different scenes, and before the electronic device displays the first application and the third application in the first control, the method further includes: the electronic equipment acquires first time and first position information; and under the condition that the first time belongs to the first period and the first position information indicates the first position area, the electronic equipment determines the first application by utilizing a second recommendation model, and when the first weights of the application programs are arranged in the order from the large to the small, the first application is an application program with the first weights rearranged before the first ranking. In addition, the electronic device may further determine a third application by using the first recommendation model, where the third application is an application in which the second weights are rearranged before the second ranking when the second weights of the applications are arranged in order from the top to the bottom.

In some embodiments, the first location information includes one or a combination of a service set identifier provided by a first network, a cell identifier provided by a first base station, and first latitude and longitude information, where signal coverage areas of the first network and the first base station belong to the first location area.

In some embodiments, before the electronic device displays the first application in the first control, the method further comprises: the electronic equipment acquires a first number of days and a second number of days, wherein the first number of days is the number of days when the first application is started under the scene that the electronic equipment is positioned in the first position area and the system time belongs to the first period, and the second number of days is the number of days when the electronic equipment detects that the electronic equipment is positioned in the first position area and the system time belongs to the first period; the electronic equipment determines a first weight corresponding to a first application under the condition that the electronic equipment is positioned in a first position area and the system time belongs to a first period according to a first number of days and a second number of days; and the electronic equipment updates the first recommendation model according to the first application and the corresponding first weight.

In the above embodiment, the electronic device may update the first weight corresponding to the first application in each type of spatio-temporal scene in the first recommendation model according to a change of a number of days of use of the first application by the user in each type of spatio-temporal scene. Of course, the electronic device may update the first weights of other applications in different space-time scenarios in the same manner, so that the recommended application determined by the electronic device in various space-time scenarios may change along with the habit of the user.

In some embodiments, the method further comprises: the electronic equipment acquires interaction data, wherein the interaction data comprises the interaction times of users and various application programs under the condition that different position information, different time information, different user state information and different equipment state information are detected; and the electronic equipment clusters according to the position information, the time information, the user state information and the equipment state information in the interaction data to obtain the second recommendation model.

In the above embodiment, the second recommendation model may enhance the recognition of the real-time scene indicated by the multiple scene features by learning the interaction data having the multiple scene features, thereby enhancing the application recommendation matching degree for various real-time scenes.

In some embodiments, the electronic device obtains interaction data, including: when the electronic equipment detects a first operation aiming at any application program, acquiring the position information, the time information, the user state information and the equipment state information; under the condition that a first service set identifier and a first cell identifier are acquired, determining the first service set identifier as the detected position information, and associating the first cell identifier with the first service set identifier; and under the condition that the first cell identity is acquired and the first cell identity is already associated with the first service set identity, determining the first service set identity as the detected position information.

In some embodiments, in the event that the service set identity and the cell identity are not collected upon detection of the first operation, the electronic device determines the location information as a first identity, the first identity indicating an unidentified geospatial space.

In some embodiments, the first application includes a fifth application and a sixth application, and in the case that the third application includes the sixth application and the seventh application, the method further includes: the electronic equipment determines the recommendation weight of the sixth application according to the first weight, the second weight, the first recommendation factor and the second recommendation factor corresponding to the sixth application, wherein the first recommendation factor is used for indicating the recommendation hit rate of the first recommendation model, and the second recommendation factor is used for indicating the recommendation hit rate of the second recommendation model; the electronic equipment determines the recommendation weight of the sixth application according to the first weight and the first recommendation factor corresponding to the fifth application; and the electronic equipment determines the recommendation weight of the seventh application according to the second weight and the second recommendation factor corresponding to the seventh application.

In some embodiments, the application icons of the fifth application, the sixth application and the seventh application are arranged on the first control in the order of the corresponding recommendation weights from the top to the bottom. In addition, as the scene where the electronic device is located changes, the recommended application determined by the electronic device also changes, and thus, the application icon in the first control also changes. After the application icons in the first control change, the application icons in the first control may be randomly arranged.

In a second aspect, an electronic device provided by an embodiment of the present application includes one or more processors and a memory; the memory is coupled to the processor, the memory for storing computer program code comprising computer instructions that, when executed by the one or more processors, operate to: displaying a first interface, wherein the first interface comprises a first control, and the first control is used for displaying application icons of application programs to be recommended to a user; displaying an application icon of a first application in the first control under the condition that the electronic equipment is located in a first position area and the system time belongs to a first period; the first weight of the first application is higher than the first weight of the second application, an application icon of the second application is not displayed on the first control, the first weight is used for indicating the enabling probability of the application program in the scene of being located in the first position area, and the system time belongs to the first period.

In some embodiments, the one or more processors are configured to: displaying an application icon of a third application in the first control under the condition that the electronic equipment is located in the first position area and the system time belongs to a first period; the second weight of the third application is higher than the second weight of the fourth application, the application icon of the fourth application is not displayed on the first control, and the second weight is used for indicating the interaction frequency between the user and the application program in the current scene.

In some embodiments, the electronic device includes a first recommendation model for determining the second weight corresponding to each of the applications in different scenes and a second recommendation model for determining the first weight corresponding to each of the applications in different scenes, and the one or more processors are configured to, before displaying a first application and a third application in the first control: acquiring first time and first position information; determining the first application by using the second recommendation model when the first time belongs to the first period and the first location information indicates the first location area, wherein the first application is an application of which the first weight is rearranged before a first ranking when the first weights of the application are arranged in order from big to small; and determining the third application by using the first recommendation model, wherein the third application is an application program of which the second weight is rearranged before the second ranking when the second weights of the application programs are arranged in the order from big to small.

In some embodiments, the one or more processors are configured to, prior to displaying the first application in the first control: acquiring a first number of days and a second number of days, wherein the first number of days is the number of days when the first application is started in a scene that the electronic equipment is located in the first position area and the system time belongs to a first period, and the second number of days is the number of days when the electronic equipment detects that the electronic equipment is located in the first position area and the system time belongs to the first period; determining a first weight corresponding to the first application under the condition that the first position area is located and the system time belongs to the first period according to the first days and the second days; and updating the first recommendation model according to the first application and the corresponding first weight.

In some embodiments, the one or more processors are configured to: acquiring interaction data, wherein the interaction data comprises the interaction times of a user and various application programs under the condition that different position information, different time information, different user state information and different equipment state information are detected; and clustering according to the position information, the time information, the user state information and the equipment state information in the interaction data to obtain the second recommendation model.

In some embodiments, the one or more processors are configured to: when a first operation aiming at any application program is detected, collecting the position information, the time information, the user state information and the equipment state information; under the condition that a first service set identifier and a first cell identifier are acquired, determining the first service set identifier as the detected position information, and associating the first cell identifier with the first service set identifier; and under the condition that the first cell identity is acquired and the first cell identity is already associated with the first service set identity, determining the first service set identity as the detected position information.

In some embodiments, the one or more processors are configured to: and under the condition that the service set identification and the cell identification are not acquired when the first operation is detected, determining the position information as a first identification, wherein the first identification indicates unidentified geographic space.

In some embodiments, the one or more processors are configured to: the first application includes a fifth application and a sixth application, and the one or more processors are configured to: determining a recommendation weight of the sixth application according to the first weight, the second weight, the first recommendation factor and the second recommendation factor corresponding to the sixth application, wherein the first recommendation factor is used for indicating the recommendation hit rate of the first recommendation model, and the second recommendation factor is used for indicating the recommendation hit rate of the second recommendation model; determining a recommendation weight of the sixth application according to the first weight and the first recommendation factor corresponding to the fifth application; and determining the recommendation weight of the seventh application according to the second weight and the second recommendation factor corresponding to the seventh application.

In a third aspect, embodiments of the present application provide a computer storage medium comprising computer instructions which, when run on an electronic device, cause the electronic device to perform the method of the first aspect and possible embodiments thereof.

In a fourth aspect, the application provides a computer program product for causing an electronic device to carry out the method of the first aspect and possible embodiments thereof, when the computer program product is run on the electronic device.

It will be appreciated that the electronic device, the computer storage medium and the computer program product provided in the above aspects are all applicable to the corresponding methods provided above, and therefore, the advantages achieved by the electronic device, the computer storage medium and the computer program product may refer to the advantages in the corresponding methods provided above, and are not repeated herein.

Drawings

FIG. 1 is a diagram illustrating an example display interface of an electronic device provided in the related art;

Fig. 2 is one example diagram of a display interface of an electronic device according to an embodiment of the present application;

Fig. 3 is a diagram illustrating a hardware structure of an electronic device according to an embodiment of the present application;

FIG. 4 is a second exemplary diagram of a display interface of an electronic device according to an embodiment of the present application;

FIG. 5 is an exemplary diagram of determining a location tag in an embodiment of the present application;

FIG. 6 is an exemplary diagram of a geofence provided by an embodiment of the present application;

FIG. 7 is a third exemplary diagram of a display interface of an electronic device according to an embodiment of the present application;

FIG. 8 is a fourth exemplary diagram of a display interface of an electronic device according to an embodiment of the present application;

FIG. 9 is a flowchart of an application recommendation method according to an embodiment of the present application;

FIG. 10 is an exemplary diagram of a decision tree model provided by an embodiment of the present application;

FIG. 11 is an exemplary diagram of determining recommendation factors for model 1 according to an embodiment of the present application;

fig. 12 is an exemplary diagram of a chip system according to an embodiment of the present application.

Detailed Description

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 implementation of the present embodiment will be described in detail below with reference to the accompanying drawings.

The embodiment of the application provides an application program recommending method which is applied to electronic equipment. The electronic device is internally provided with a plurality of application programs (including a system application and a third party application), and different application programs can provide different application services for users.

In order to facilitate the use of application services provided by application programs, application icons of the respective application programs are displayed on a desktop of the electronic device. The application icon may be used as a launch portal for the application program to launch (or say open) the corresponding application program by the user. That is, after the electronic device receives the operation of the user on the application icon, a corresponding application program, for example, an application interface for displaying the application program, can be run.

As more applications are installed in electronic devices, more application icons need to be displayed, and in this scenario, the application icons of the application programs may be displayed on multiple sub-screens of the desktop. Of course, the application icons displayed by different sub-screens may be different. In the related art, when a user wants to use an application service provided by a specific application, the user needs to browse a plurality of sub-screens to find an application icon corresponding to the specific application.

For example, as shown in fig. 1, the unlocked electronic device displays a first sub-screen (such as an interface 101) of the desktop, and the main interface displays application icons corresponding to a plurality of application programs. During the display of the interface 101 by the electronic device, the user wants to use the WeChat ^TM, if the application icon of the WeChat ^TM is not displayed in the interface 101, the user needs to operate the electronic device to trigger the electronic device to switch to display other sub-screens, so that the user can search for the application icon of the WeChat ^TM on the other sub-screens. That is, the user may perform a sliding operation on the display screen of the electronic device, so as to trigger the electronic device to switch and display different sub-screens until the user finds the application icon of the WeChat ^TM.

For example, during display of interface 101, the electronic device may display interface 102 in response to a user sliding operation on the display screen. In the case of an application icon 103 including a WeChat ^TM in the interface 102, the user may trigger the electronic device to initiate the WeChat ^TM by clicking on the application icon 103. If the application icon 103 is not on the interface 102, the user also needs to continue to slide on the display screen to trigger the electronic device to switch the display interface to other sub-screens. Obviously, the human-computer interaction efficiency of the whole process is lower.

In order to improve the above problems, the embodiment of the application provides an application program recommending method. In this scheme, the electronic device may display the recommendation control during the bright screen. The recommendation control may be displayed on any display interface of the electronic device, for example, a lock screen interface, a sub-screen, a negative one-screen and an application interface, which is not limited in this embodiment of the present application, and the display interface for displaying the recommendation control may also be referred to as a first interface, and the recommendation control may also be referred to as a first control.

Included in the recommendation control are one or more application icons, which may be referred to as recommendation icons. The recommended icon is an application icon of the recommended application determined by the electronic equipment. The recommended application may include an application program that the electronic device evaluates from the installed application programs that the user wishes to use in the current scenario.

For example, the electronic device may identify a scene in which the electronic device is currently located from one or more dimensions of time, space, status (e.g., may include a user status or a device status), etc., and then determine an application that the user may use in the current scene based on the application that the user uses to top in various scenes, where the user uses the heat to indicate how frequently the user interacts with the application.

Also for example, the electronic device may identify a scene in which the electronic device is currently located from one or more dimensions such as time and space, and then determine an application that the user may use in the current scene according to an application that the user uses in various scenes (e.g., an application that enables a time period rule and a location rule in which the device is located when the application is used). For example, the electronic device is 9 in the morning each day: 00 will start an attendance application once, then it can be determined that 9 in the morning: in this scenario, 00, the attendance application is a regular-use application. For another example, the electronic device may enable the public transportation application at the bus stop, and then it may be determined that the public transportation application is a regular application in the context of the bus stop.

In this way, under different scenes, the electronic device can recommend the recommendation icon meeting the current requirement of the user to the user through the recommendation control.

For example, as shown in fig. 2, taking the electronic device as a mobile phone, a main interface (e.g., interface 201) may be displayed after the mobile phone is unlocked. Recommendation controls, such as recommendation cards 202, are included in the interface 201. The recommendation card 202 includes application icons of recommendation applications such as WeChat ^TM, public transportation, gallery, video, etc. The WeChat ^TM, public transportation, gallery, video and other applications are all applications that the electronic device evaluates the possible use of the user in the current scene. If the user wants to use the WeChat ^TM at this time, an application icon of WeChat ^TM may be clicked on the recommendation card 202 to trigger the electronic device to enable WeChat ^TM. Therefore, the user omits the operation of triggering the electronic equipment to switch and display different sub-screens, the man-machine interaction efficiency is improved, and the intelligent degree of the electronic equipment is also improved.

The electronic device may be a mobile phone, a television, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, a personal computer (personal computer, PC), a netbook, a Personal Digital Assistant (PDA), or the like, which has a display screen. The embodiment of the application does not limit the specific form of the electronic equipment.

As shown in fig. 3, in the embodiment of the present application, a mobile phone is taken as an example, and the structure of the electronic device provided in the embodiment of the present application is illustrated. An electronic device (such as a cell phone) may include: processor 310, external memory interface 320, internal memory 321, universal serial bus (universal serial bus, USB) interface 330, charge management module 340, power management module 341, battery 342, antenna 1, antenna 2, mobile communication module 350, wireless communication module 360, audio module 370, speaker 370A, receiver 370B, microphone 370C, headset interface 370D, sensor module 380, keys 390, motor 391, indicator 392, camera 393, display 394, and subscriber identity module (subscriber identification module, SIM) card interface 395, among others.

The sensor module 380 may include pressure sensors, gyroscope sensors, barometric pressure sensors, magnetic sensors, acceleration sensors, distance sensors, proximity sensors, fingerprint sensors, temperature sensors, touch sensors, ambient light sensors, bone conduction sensors, and the like.

It is to be understood that the configuration illustrated in this embodiment does not constitute a specific limitation on the electronic apparatus. In other embodiments, the electronic device 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. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

The processor 310 may include one or more processing units, such as: the processor 310 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (IMAGE SIGNAL processor, ISP), a controller, a memory, a video codec, a digital signal processor (DIGITAL SIGNAL processor, DSP), a baseband processor, and/or a neural Network Processor (NPU), etc. Wherein the different processing units may be separate devices or may be integrated in one or more processors.

The controller may be a neural hub and command center of the electronic device. The controller can generate operation control signals according to the instruction operation codes and the time sequence signals to finish the control of instruction fetching and instruction execution.

A memory may also be provided in the processor 310 for storing instructions and data. In some embodiments, the memory in the processor 310 is a cache memory. The memory may hold instructions or data that the processor 310 has just used or recycled. If the processor 310 needs to reuse the instruction or data, it may be called directly from the memory. Repeated accesses are avoided and the latency of the processor 310 is reduced, thereby improving the efficiency of the system.

In some embodiments, processor 310 may include one or more interfaces. The interfaces may include an integrated circuit (inter-INTEGRATED CIRCUIT, I2C) interface, an integrated circuit built-in audio (inter-INTEGRATED CIRCUIT SOUND, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver transmitter (universal asynchronous receiver/transmitter, UART) interface, a mobile industry processor interface (mobile industry processor interface, MIPI), a general-purpose input/output (GPIO) interface, a subscriber identity module (subscriber identity module, SIM) interface, and/or a universal serial bus (universal serial bus, USB) interface, among others.

It should be understood that the connection relationship between the modules illustrated in this embodiment is only illustrative, and does not limit the structure of the electronic device. In other embodiments, the electronic device may also use different interfacing manners in the foregoing embodiments, or a combination of multiple interfacing manners.

The charge management module 340 is configured to receive a charge input from a charger. The charger can be a wireless charger or a wired charger. The battery 342 is charged by the charge management module 340, and the electronic device may be powered by the power management module 341.

The power management module 341 is configured to connect the battery 342, the charge management module 340 and the processor 310. The power management module 341 receives input from the battery 342 and/or the charge management module 340 to power the processor 310, the internal memory 321, the external memory, the display screen 394, the camera 393, the wireless communication module 360, and the like. In some embodiments, the power management module 341 and the charge management module 340 may also be provided in the same device.

The wireless communication function of the electronic device may be implemented by the antenna 1, the antenna 2, the mobile communication module 350, the wireless communication module 360, a modem processor, a baseband processor, and the like. In some embodiments, the antenna 1 and the mobile communication module 350 of the electronic device are coupled, and the antenna 2 and the wireless communication module 360 are coupled, so that the electronic device can communicate with a network and other devices, such as with a wearable device, through wireless communication technology.

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

The mobile communication module 350 may provide a solution for wireless communication including 2G/3G/4G/5G, etc. applied on an electronic device. The mobile communication module 350 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA), or the like. The mobile communication module 350 may receive electromagnetic waves from the antenna 1, perform processes such as filtering, amplifying, and the like on the received electromagnetic waves, and transmit the processed electromagnetic waves to the modem processor for demodulation.

The mobile communication module 350 may amplify the signal modulated by the modem processor, and convert the signal into electromagnetic waves through the antenna 1 to radiate the electromagnetic waves. In some embodiments, at least some of the functional modules of the mobile communication module 350 may be disposed in the processor 310. In some embodiments, at least some of the functional modules of the mobile communication module 350 may be provided in the same device as at least some of the modules of the processor 310.

The wireless communication module 360 may provide solutions for wireless communication including WLAN (e.g., (WIRELESS FIDELITY, wi-Fi) network), bluetooth (BT), global navigation satellite system (global navigation SATELLITE SYSTEM, GNSS), frequency modulation (frequency modulation, FM), near Field Communication (NFC), infrared (IR), etc. applied on an electronic device.

The GNSS may include, among other things, a Beidou satellite navigation system (beidou navigation SATELLITE SYSTEM, BDS), a global positioning system (global positioning system, GPS), a global navigation satellite system (global navigation SATELLITE SYSTEM, GLONASS), a quasi zenith satellite system (quasi-zenith SATELLITE SYSTEM, QZSS) and/or a satellite based augmentation system (SATELLITE BASED AUGMENTATION SYSTEMS, SBAS).

The wireless communication module 360 may be one or more devices that integrate at least one communication processing module. The wireless communication module 360 receives electromagnetic waves via the antenna 2, modulates the electromagnetic wave signals, filters the electromagnetic wave signals, and transmits the processed signals to the processor 310. The wireless communication module 360 may also receive a signal to be transmitted from the processor 310, frequency modulate it, amplify it, and convert it to electromagnetic waves for radiation via the antenna 2.

The electronic device implements display functions through the GPU, display screen 394, and application processor, etc. The GPU is a microprocessor for image processing, connected to the display screen 394 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 310 may include one or more GPUs that execute program instructions to generate or change display information.

The display screen 394 is used for displaying images, videos, and the like. The display 394 includes a display panel.

The electronic device may implement shooting functions through the ISP, the camera 393, the video codec, the GPU, the display screen 394, the application processor, and the like. The ISP is used to process the data fed back by camera 393. Camera 393 is used to capture still images or video. In some embodiments, the electronic device may include 1 or N cameras 393, N being a positive integer greater than 1.

The external memory interface 320 may be used to connect an external memory card, such as a Micro SD card, to enable expansion of the memory capabilities of the electronic device. The external memory card communicates with the processor 310 through an external memory interface 320 to implement data storage functions. For example, files such as music, video, etc. are stored in an external memory card.

The internal memory 321 may be used to store computer executable program code comprising instructions. The processor 310 executes various functional applications of the electronic device and data processing by executing instructions stored in the internal memory 321. For example, in an embodiment of the present application, the processor 310 may be configured to execute instructions stored in the internal memory 321, and the internal memory 321 may include a storage program area and a storage data area.

The storage program area may store an application program (such as a sound playing function, an image playing function, etc.) required for at least one function of the operating system, etc. The storage data area may store data created during use of the electronic device (e.g., audio data, phonebook, etc.), and so forth. In addition, the internal memory 321 may include a high-speed random access memory, and may also include a nonvolatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (universal flash storage, UFS), and the like.

It should be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the application, the electronic device may include more or less components than illustrated, or certain components may be combined, or certain components may be split, or different arrangements of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

The methods in the following embodiments may be implemented in a device having the above-described hardware structure.

In some embodiments, interactions between a user and various applications may be detected in real-time during operation of the electronic device. For example, during display of the desktop, the user clicks an application icon corresponding to the application program. For another example, during display of an application interface provided by an application program, a user operates any of the functionality controls in the application interface. For another example, during display of the multi-tasking interface, a user may operate a thumbnail window corresponding to the application. For another example, the user triggers an operation to send a control command for the application, and so on.

In some embodiments, the electronic device may assign each detected interaction with a corresponding scene feature and application identification, i.e., associate the interaction with the corresponding scene feature and application identification. The scene feature may be a feature in at least one dimension such as time, space, device status, user status, and the like.

As one example, after the electronic device detects an interaction, the electronic device determines an application corresponding to the interaction. The interaction is then associated with an application identification of the application, which may be, for example, a package name of the application. Thereafter, the electronic device may obtain time information, such as time information a, for detecting the interaction, and take the time information a as a feature of the interaction in a time dimension.

The above-described time information a may include time information, for example. For example, at 9 a.m., when a user trigger to start a bus application is detected, the electronic device may associate the interactive operation with a bus application identifier, and may also associate the interactive operation with the system time information of 09:00:00.

Also illustratively, the above-described time information a may also include date information. For another example, at 9 a morning at 10.11 of 2022, the electronic device may associate an interaction with the bus application identification by detecting that the user is instructed to do so, and may also associate the interaction with system time information such as 10.11 of 2022, tuesday, 09:00:00, etc.

In this way, the electronic device can determine, in the time dimension, an application program with a front use heat corresponding to different time periods (for example, the use heat is arranged in the front k bits, and k is a positive integer) according to the time characteristics and the application identifier corresponding to the interactive operation, and the application program is used as a recommended application corresponding to the time period. For example, the electronic device counts the number of interactions having the same application identifier and time information belonging to the same period according to the interactions detected in T (positive integer greater than 1, where the value of T may be preset) days. It will be appreciated that having the same application label indicates that the same application program is corresponded. In this way, through the statistics, the electronic device may determine the number of interactions corresponding to each application program in each number of segments, that is, the electronic device may determine, according to the number of interactions corresponding to each application program in each time period, an application program with a front heat of use corresponding to each time period, that is, an application with a relatively high number of interactions.

In addition, the electronic device can determine the use condition corresponding to each application program according to the interactive operation corresponding to each application program, and then evaluate the application program with the use rule in the time dimension. It is appreciated that, at any time period (e.g., time period a), if the electronic device detects at least one interaction for any application (e.g., application b), the electronic device may determine that the user used application b at time period a. As an example, the electronic device obtains the number of days of use that the user used the application b under the period a within T days. If the corresponding number of days of use is greater than m days, it may be determined that application b is a regular-use application under period a. The value of m is a positive integer greater than 0 and not greater than T, and the value of m can be related to the value of T. If application b is a regular application used in period a, even if application b does not belong to an application program whose use heat is forward in period a, it can be determined as a recommended application in this period a.

That is, the electronic device may determine the recommended application corresponding to each time feature according to the interaction operation corresponding to each time feature. In this way, in the actual running process of the electronic device, the electronic device can identify the time feature corresponding to the current scene according to the system time, and if the time feature of the current scene corresponds to the recommended application, the electronic device can display the application icon of the recommended application corresponding to the current scene through the recommended control. That is, the electronic device detects that the system time reaches different periods, different recommended applications may be displayed on the recommended card. As shown in fig. 4, the electronic device determines that the recommended applications corresponding to the period to which the time 8:00 belongs include applications such as WeChat ^TM, public transportation, gallery, video, and the like, and when the detected system time reaches 8:00, the electronic device may display application icons of the applications such as WeChat ^TM, public transportation, gallery, video, and the like on a recommendation control (e.g., recommendation card 401). The electronic device determines time 10: the recommended applications corresponding to the period of 00 include applications such as take-out, memo, email and meeting, and when the detected system time reaches 10:00, the electronic device can display application icons of the applications such as take-out, memo, email and meeting on the recommendation control (such as the recommendation card 402).

In other embodiments, after the electronic device detects an interaction, the electronic device determines an application corresponding to the interaction. Then, the interactive operation is associated with the application identifier of the application program, and then the electronic device can acquire the position label corresponding to the current geographic space, and take the position label as the feature of the interactive operation in the space dimension.

The location tag may be, for example, a base station identifier carried in a base station signal collected by the electronic device, such as a cell identity (cellID). It will be appreciated that after entering the signal coverage area of the base station, the electronic device may access the base station and receive cellID sent by the base station. Because the location of the base station is fixed, the spatial location (i.e., the signal coverage) of the base station signal that can be received is also fixed, so that the electronic device can indicate the current geographic location of the electronic device according to cellID in the base station signal that is received in real time, that is, the obtained cellID is used as the location tag. That is, in the case where the electronic devices access the same base station, the detected interaction operation corresponds to the same location tag.

Also illustratively, the location tag may also be a service set identifier (SERVICE SET IDENTIFIER, SSID) of a wireless-fidelity (Wi-Fi) network to which the electronic device accesses. It can be appreciated that the coverage area of the Wi-Fi network is fixed, and the electronic device also needs to enter the coverage area of the Wi-Fi network to receive corresponding Wi-Fi information, where the Wi-Fi information may carry an SSID, and different SSIDs may indicate different Wi-Fi networks. In this way, the electronic device can indicate the current geographical location of the electronic device according to the SSID obtained in real time, that is, the obtained SSID is used as a location tag. That is, in the case where the electronic device accesses the same WiFi network, the detected interaction operation corresponds to the same location tag.

Also, for example, the location tag may also be latitude and longitude information collected by a positioning system in the electronic device.

In some possible examples, the location tag may also be one of or a combination of cellID, SSID, and latitude and longitude information. For example, a combination of latitude and longitude information and cellID is used as a location tag. For another example, cellID and SSID are combined to be used as a location tag, and the location tag in the present application only needs to be identified by an electronic device, and the content of the location tag is not specifically limited.

Taking the example that the position tag is a combination of longitude and latitude information and cellID, each time the electronic device detects an interactive operation, a positioning system (such as a GPS positioning technology) can be used to collect corresponding longitude and latitude information and obtain cellID corresponding to the currently accessed base station. Thus, each interaction corresponds to a latitude and longitude information sum cellID. And then clustering the interactive operation by using longitude and latitude information to obtain a plurality of clustering clusters. Each cluster comprises a plurality of interactive operations, and the longitude and latitude information corresponding to each interactive operation is relatively close to the position indicated in the geographic space. Then, cellID corresponding to an interaction in the same cluster is used as a geofence of the spatial position indicated by the cluster, and if cellID corresponding to different interactions belong to the same geofence, the interactions have the same position label. If the cellID corresponding to different interactions belong to different geofences, then the interactions have different location tags.

Taking the combination of longitude and latitude information and SSID as an example, when the electronic device detects one interaction operation, a positioning system (such as a GPS positioning technology) can be used to collect corresponding longitude and latitude information and obtain the SSID corresponding to the Wi-Fi network that is currently accessed. Thus, each interaction corresponds to one longitude and latitude information and SSID. And then clustering the interactive operation by using longitude and latitude information to obtain a plurality of clustering clusters. Each cluster comprises a plurality of interactive operations, and the longitude and latitude information corresponding to each interactive operation is relatively close to the position indicated in the geographic space. Then, taking the SSID corresponding to the interaction operation in the same cluster as the geofence of the spatial position indicated by the cluster, and if the SSIDs corresponding to different interaction operations belong to the same geofence, then the interaction operations have the same position label. If the SSID corresponding to a different interoperation belongs to a different geofence, the interoperation has a different location tag.

Taking the combination of cellID and SSID as an example, each time the electronic device detects an interaction, cellID corresponding to the base station accessed by the current electronic device and/or SSID corresponding to the Wi-Fi network accessed by the current electronic device can be obtained.

For example, if the electronic device accesses the base station but does not access any Wi-Fi network, then only the corresponding cellID may be acquired. If the electronic device accesses the Wi-Fi network but does not access any base station, only the corresponding SSID may be acquired. If the electronic device accesses the base station and also accesses the Wi-Fi network, the corresponding cellID and SSID may be obtained simultaneously. If the electronic device does not access the base station nor the Wi-Fi network, then no information may be available.

In some embodiments, the electronic device may determine the location tag of the detected interaction according to the SSID and/or cellID acquisition.

As one implementation, as shown in fig. 5, the electronic device determines whether cellID is acquired. In case the electronic device does not acquire cellID, i.e. the electronic device does not access any base station, the identification "-1" is taken as the location tag for this interaction.

In case the electronic device acquires cellID, i.e. the electronic device has access to any base station, the SSID matching cellID is looked up. Illustratively, the electronic device queries for interactions collected over T days that correspond to the same cellID, such as referred to as interaction a. And acquiring the SSID corresponding to each interaction operation a as a matched SSID. If none of the inter-operations a corresponds to an SSID (i.e., no matching SSID), and the number of inter-operations a is greater than or equal to a specified value (e.g., 20), the obtained cellID is determined as the location tag of the currently detected inter-operation. If none of the interactions a corresponds to an SSID and the number of interactions a is less than a specified value (e.g., 20), the identification "other" is determined as the location tag of the detected interaction.

In addition, in the case where at least one of the interoperations b is included in the interoperation a, the interoperation b is an operation in the interoperation a corresponding to cellID and SSID at the same time. If the SSID corresponding to the interaction b is the same (i.e. there is only one matching SSID), the SSID corresponding to the interaction b is used as the location tag of the detected interaction.

For example, when the electronic device detects a first operation (i.e., an interaction) for any application, if a first service set identifier (e.g., SSID provided by a WiFi network) and a first cell identifier (cellID provided by a base station) are collected, it may determine that the first service set identifier is location information (or referred to as a location tag) corresponding to the current detection, and associate the first cell identifier with the first service set identifier. And under the condition that the first cell identity is acquired and the first cell identity is already associated with the first service set identity, determining the first service set identity as the detected position information.

In the case that the interaction operation a includes at least one interaction operation b, if the SSIDs corresponding to the interaction operations b are not all the same, counting the number b of the interaction operations b corresponding to different SSIDs. Thus, the electronic device can use the SSID with the largest corresponding number b as the position label of the detected interaction operation.

For example, as shown in table 1:

TABLE 1

As shown in Table 1, interaction a is the interaction corresponding to cellID being 1234. The above-mentioned interaction operation a includes 430 interactions operation b. The number of the interactions corresponding to SSID "223" in the interactions b is 60, the number of the interactions corresponding to SSID "224" in the interactions b is 200, the number of the interactions corresponding to SSID "225" in the interactions b is 70, and the number of the interactions corresponding to SSID "226" in the interactions b is 100. Thus, SSID "224" may be used as a location tag for the currently detected interoperation.

In addition, typically the coverage of the same Wi-Fi network may overlap with the coverage of multiple base stations, i.e. in case the electronic device accesses the same Wi-Fi network, different time periods may access different base stations, i.e. in case the detected interoperable SSIDs are the same, the corresponding cellID may be different.

For example, as shown in fig. 6, in a home scenario, the electronic device may access the base station 1 in case the electronic device accesses a home WiFi access node. Of course, it is also possible for the electronic device to access base station 2, base station 3 or base station 4. When the electronic device detects the interaction operation, the SSID corresponding to the home WiFi access node can be used as a position label no matter the access base station 1, the base station 2, the base station 3 or the base station 4. That is, whether accessing base station 1, base station 2, base station 3, or base station 4, it may be determined that the electronic device enters the same piece of geographic space (i.e., enters a home scene) as long as it accesses a home WiFi access node. The cellID corresponding to the above base station 1, base station 2, base station 3, and base station 4 can be used as a geofence of the home scene.

After the electronic device determines the position label corresponding to each interactive operation, the electronic device can cluster the interactive operations detected in the T days according to the position labels to obtain the number of interactive operations corresponding to various cellID under different position labels. For example, the results obtained after clustering are shown in table 2 below:

TABLE 2

Wherein 123123, 147147, 159159, 126126, 101010 and 148148 are cellID corresponding to different base stations, and-1 represents no cellID, as shown in table 2, the number of interactions with position tag 1 and corresponding to cellID "126126" is 116, the number of interactions with position tag 1 and corresponding to cellID "101010" is 112, the number of interactions with position tag 2 and corresponding to cellID "123123" is 390, the number of interactions with position tag 2 and no cellID is 23, the number of interactions with position tag 2 and corresponding to cellID "147147" is 1, the number of interactions with position tag 2 and corresponding to cellID "159159" is 1, the number of interactions with the identifier "-1" is 190, and the number of interactions with the identifier "other" and corresponding to cellID "148148" is 77. The identifier "-1" may be referred to as determining that the first service set identifier is detected when the first service set identifier and the first cell identifier are collected.

From the above clustering, it can be determined that the geofences corresponding to position tag 1 include cellID "126126" and cellID "101010", the geofences corresponding to position tag 2 include cellID "123123", cellID "147147" and cellID "159159", and the identification "other" corresponding geofences include cellID "148148". The identifier "-1" indicates that the electronic device cannot collect the scene cellID, for example, the scene is located in a place where the base station is not covered, for example, further, the electronic device is not provided with the SIM card.

In some embodiments, in the case that the interaction operation corresponds to a position tag, the electronic device may further determine, in a spatial dimension, an application program with a front using heat of different position tags according to the position tag and the application identifier corresponding to the interaction operation, and use the application program with a front k-bit using frequency as a recommended application of the position tag, for example, under the different position tags, where k is a positive integer.

For example, the electronic device counts the number of interactions with the same application identifier and the same location tag according to the detected interactions within T (positive integer greater than 1) days. It will be appreciated that the same application label indicates the same application program, and the same location label indicates the same geographic space, i.e., the number of interactions described above may indicate the number of interactions with the same application program by the user in the same geographic space. In this way, through the statistics, the electronic device may determine the number of interactions between the user and each application program in different geographic spaces (which may be referred to by the location tag), and may further determine that the user uses the application program with the highest popularity ranking (the application with the higher interaction number) in each geographic space, and may also be referred to as the recommended application corresponding to the location tag as the recommended application corresponding to the geographic space.

In addition, the electronic device can determine the use condition of each application program according to the corresponding interaction operation of each application program, namely, the use condition of each application program is aimed at in each geographic space (indicated by a position label) by a user. Then, according to the space dimension, the application program of the usage rule in each geographic space is evaluated and used as the recommended application of the geographic space, which can be also called as the recommended application corresponding to the position label.

For example, according to the detected interaction operation within T days, the electronic device determines that the electronic device appears in the geographic space a and uses the application b for a number of days, if the number of days is greater than m, it is determined that the application b belongs to an application program with a regular usage, and if the geographic space a is indicated by the location tag a, the application b can be used as a recommended application corresponding to the location tag a.

After determining the recommended application corresponding to the different position tag, when the electronic device detects that the current scene is matched with the geofence corresponding to the position tag, the recommended application corresponding to the position tag can be displayed on the recommended card.

For example, after clustering for the interaction with the location tag, it is determined that the geofence corresponding to the location tag 2 indicating the home scene includes cellID "123123", cellID "147147" and cellID "159159", and at the same time, it is also determined that the recommended application corresponding to the location tag 2 includes WeChat ^TM, news, gallery, video, and other applications. Determining that the geofence corresponding to location tag 1 indicating the corporate scene includes cellID "126126" and cellID "101010", while also determining that the recommended applications corresponding to location tag 1 include document editing, office, email, meeting, etc. applications.

Thus, as shown in fig. 7, when the electronic device detects that the current scene matches the geofence corresponding to the position tag 2, for example, cellID "123123", cellID "147147" or cellID "159159" are parsed from the received base station signal, it may be determined that the electronic device is located in the home scene, and at this time, the electronic device may display application icons of applications such as WeChat ^TM, news, gallery, video, and the like on a recommendation control (such as recommendation card 701).

As shown in fig. 7, the electronic device detects that the current scene matches the geofence corresponding to the position tag 1, for example, it may determine that the electronic device is located in a company scene by parsing cellID "126126" or cellID "101010" from the received base station signal, and at this time, the electronic device may display application icons of applications such as document editing, office, email, conference, etc. on a recommendation control (e.g., recommendation card 702).

In other possible embodiments, after the electronic device detects an interaction, device state information (e.g., power information) when the interaction is detected may also be obtained and characterized as a device state dimension. And then, determining application programs with the top using heat ranks under different equipment states and application programs with regular use according to equipment state information corresponding to each interactive operation as corresponding recommended application under the equipment state, so that the application programs which are matched with the recommended application programs can be recommended to a user according to the real-time equipment state of the electronic equipment. For example, when the electric quantity is too low, pushing the charger rental application.

In other possible embodiments, after an electronic device detects an interaction, user state information (e.g., the user is in motion) at the time the interaction was detected may be obtained and characterized as a user state dimension. And then, determining application programs with top use heat ranks under different user states and application programs with regular use as corresponding recommendation applications under the user states according to user state information corresponding to each interactive operation, thereby realizing recommendation of the required application programs to the user according to the real-time states of the user. For example, as shown in fig. 8, when the user is in a motion state, the electronic device may display application icons of applications such as sports health, step count, camera, video, etc. on the recommendation control (i.e., recommendation card 801).

Of course, during the actual operation of the electronic device, the electronic device may assign multiple types of scene features to the detected interaction. For example, it has both time information and a location tag, etc. In this way, the electronic device can determine the corresponding recommended application under the scene indicated by the multi-class scene feature.

That is, in some embodiments, as shown in FIG. 9, the electronic device detects an interaction (e.g., a user clicking on an application icon), determines a scene feature corresponding to the interaction, such as one or more of time information, location tags, device state information, user state information, and the like. Based on the detected interaction operation in the T days and the corresponding various scene characteristic data, a preset algorithm is adopted, so that a model 1 (a first recommended model) and a model 2 (a second recommended model) can be respectively trained. The interaction operation and the corresponding various scene feature data can be collectively called as interaction data.

The model 1 is a model obtained by training a machine learning algorithm, and a large number of scene features are fully considered in the training and predicting process of the model 1. That is, model 1 may be trained based on the detected interaction and corresponding multiple scene features over T days in combination with a machine learning algorithm. In this way, model 1 may enable identification and application recommendation for complex scenarios.

Model 2 employs a simple statistical algorithm to learn and predict applications that need to be recommended in a particular spatio-temporal scene based on simple scene features (e.g., temporal features and spatial features). That is, model 2 may be trained based on detected interactions and corresponding specific scene features over T days.

In this way, the electronic device may determine the recommended application 1 and the corresponding usage frequency weight (second weight) according to the scene features and the model 1 detected in real time. The electronic device may determine the recommended application 2 and the corresponding rule weight (first weight) based on the scene features detected in real-time and the model 2. Then, fusing the weights corresponding to the recommended application 1 and the recommended application 2, and outputting an application list which is actually recommended and contains the recommended application 1, the recommended application 2 and the fused weight value. In a word, after the model 2 is configured in the electronic device as a supplement to the model 1, the exposure degree of the long-tail application on the recommendation control can be improved, and the accuracy of long-tail application recommendation can be improved.

For example, in a case where the electronic device is located in the first location area (spatial feature) and the system time belongs to the first period (temporal feature), that is, in a case where the electronic device detects the first location information, it may be determined that the electronic device is located in the first location area, and it may be understood that the first location information includes one or a combination of a Service Set Identifier (SSID) provided by the first network (WiFi network to which the electronic device is currently connected), a cell identity identifier (cellID) provided by the first base station (base station to which the electronic device is currently connected), and first longitude and latitude information (longitude and latitude information detected by the current location), where a signal coverage area of the first network and the first base station belongs to the first location area.

In the case where the electronic device detects that the system time point is the first time (time point within the first period), it may be determined that the system time of the electronic device belongs to the first period. At this time, using the model 2, the determined recommended application 2 includes a first application, which may be an application that may be displayed on a recommendation control in the recommended application 2. In the space-time scene indicated by the first location area and the first period, if the first weights of the installed application programs are arranged in order from large to small, the first weights of the first application are arranged before the first ranking (the first k names), the first weights of the second application are arranged after the first ranking, that is, the first weights of the first application are higher than the first weights of the second application, and in the current space-time scene, the application icon of the second application is not displayed on the recommendation control.

In the case that the electronic device is located in the first location area and the system time belongs to the first period, the electronic device may also determine a recommendation application 1 including the third application according to the detectable multi-type scene feature in the current scene, and it may be understood that the scene feature considered in determining the recommendation application 1 is not limited to the first location area (spatial feature) and the first period (temporal feature), and may include more or fewer types of scene features. In addition, if the second weights of the installed applications are arranged in order from large to small, the second weights of the third applications are arranged before the second ranking (the first k-th), the second weights of the fourth applications are arranged after the second ranking, that is, the first weights of the third applications are higher than the second weights of the fourth applications, and in addition, in the current scene, the application icon of the fourth application is not displayed on the recommendation control.

Of course, the same application may exist between the first application and the third application, or different applications may exist, for example, the first application may include a fifth application and a sixth application, and the third application may include a sixth application and a seventh application.

As in the previous embodiments, the machine learning algorithm employed to train model 1 may be: decision trees, lightGBM, logistic regression models, XGBoost, etc.

Taking the model 1 as an example, the model is obtained by training a decision tree algorithm, the model 1 may be a decision tree model created according to the interaction operation collected in the T days and the corresponding scene characteristics, and the principle of creating the decision tree model may refer to the related technology and will not be described herein.

For example, the resulting decision tree model may be as shown in fig. 10, where the first node corresponds to the number of interactions corresponding to all applications. In fig. 10, the number of interactions of each application program is shown in the form of a digital sequence, each node in fig. 10 corresponds to a digital sequence, each sequence bit in the digital sequence corresponds to an application program, and the value of each sequence bit is the number of interactions of the corresponding application program. For example, the first sequence bit refers to a calendar application, and as shown in fig. 10, the value of the first sequence bit of the first node is 1, which indicates that the number of interactions of the calendar application is 1.

In addition, the first node can split a plurality of child nodes according to a certain scene characteristic. For example, as shown in fig. 10, the second node and the third node are split according to whether there is a position tag indicating a home scene. The second node corresponds to the interaction times corresponding to each application program in the home scene. And the third node corresponds to the interaction times corresponding to each application program in the home scene.

Likewise, the second node and the third node may split according to other scene characteristics. For example, as shown in fig. 10, the second node is split to obtain a plurality of child nodes, that is, a fourth node and a fifth node, by using whether the time information is monday to thursday. The fourth node corresponds to the interaction times corresponding to each application program in the scene of home from monday to thursday. The fifth node corresponds to the interaction times corresponding to each application program in the scene of home from friday to sunday.

In addition, the fourth node may be split into a sixth node and a seventh node, where the sixth node corresponds to the number of interactions corresponding to each application program in the family scene from monday to wednesday. The seventh node corresponds to the interaction times corresponding to each application program in the family scene, and the time information is tuesday.

The fifth node may be split into an eighth node and a ninth node, where the eighth node corresponds to the number of interactions corresponding to each application program in the home scene, and the time information is from 0 point to 11 points from friday to sunday. The ninth node corresponds to the time information of 12 points to 23 points from friday to sunday in the home scene, and the interaction times of each application program correspond to each other.

In addition, the third node may split the tenth node and the eleventh node. The tenth node corresponds to the interaction times corresponding to each application program in the corporate scene. The eleventh node corresponds to the number of interactions corresponding to each application program in the scenes that are not at home and not at the company.

The tenth node may be split into a twelfth node and a thirteenth node. The twelfth node is in a company scene, the time information is the interaction times corresponding to the application programs from monday to friday. And the thirteenth node is in a company scene, the time information is the interaction times corresponding to each application program from Saturday to sunday.

The eleventh node may be split into a fourteenth node and a fifteenth node. The fourteenth node corresponds to the interaction times corresponding to each application program in the canteen scene. The fifteenth node corresponds to the number of interactions corresponding to each application program in the scenes of being out of home, out of company, and out of canteen.

In this way, the electronic device can detect the scene characteristics corresponding to the current scene in real time, and find the matched nodes from the model 1 according to the detected scene characteristics. Then, according to the interaction times of the respective application programs corresponding to the matched nodes, the application program with the top ranking of the using heat is evaluated as the application program adapted to the current scene, that is, the recommended application 1.

For example, when the electronic device detects that the scene feature corresponding to the current scene includes the position tag of the home scene and the time information is tuesday, according to the decision tree model shown in fig. 10, it can be determined that the current scene matches with the seventh node, and then according to the interaction times of each application program in the seventh node, the application program with the top ranking of using heat is evaluated.

In some examples, the process of evaluating applications using the top-ranked hotness may be: and carrying out normalization processing on the interaction times of each application program in the matching node to obtain the frequency of use weight of each application program, wherein the frequency of use weight can indicate the interaction frequency between a user and the application program under the scene pointed by the multiple scene characteristics. Wherein, the higher the frequency of use weight, the higher the usage heat of the corresponding application program is indicated. In this case, the electronic device may determine an application whose usage frequency weight is greater than the preset weight threshold 1 as an application whose usage heat is forward in the current scene. Or in this case, the electronic device may sort the applications by the usage frequency weight and determine the application that is arranged in the first k bits as the application whose usage heat is the first. Wherein k is a positive integer.

Taking model 1 as an example, the model is obtained by training by adopting LightGBM, logistic regression or XGBoost algorithm, and the model 1 can be obtained by training according to interaction operation acquired in T days and corresponding scene characteristics and other data. In this way, the model 1 can output a plurality of application programs and the use probability according to the scene characteristics acquired by the electronic device in real time, wherein the use probability is the probability that the model 1 predicts that the application programs adapt to the current scene. Then, the application whose use probability is ranked before the top k can be regarded as the application whose use heat is the top.

In some embodiments, the model 2 may be a rule weight indicating each application program in each type of scene. For example, as shown in table 3 below:

TABLE 3 Table 3

Wherein the scene may be characterized by a combination of spatial and temporal features, such as in table 3, a combination of position tag 1 and time period 9 indicates scene 1, and a combination of position tag 2 and time period 10 indicates scene 2.

In addition, one day may be quantized into a plurality of periods in advance, for example, into 24 periods, for example, period 0, period 1 … period 24. Wherein, period 0 indicates 0 point to 1 point, period 1 indicates 1 point to 2 points, and so on, period 9 indicates 9 points to 10 points, period 10 indicates 10 points to 11 points, and so on, and period 23 indicates 23 points to 0 point. It will be appreciated that if the electronic device is present in the geographic space indicated by location tag 1 within period 9 (i.e., 9 points to 10 points), then the electronic device may detect scene 1. If the electronic device is present in the geographic space indicated by the location tag 1 within the time period 10 (i.e., 10 points to 11 points), the electronic device may detect the scene 2.

As in table 3, the electronic device detects scene 1 in 22 days, and then scene 1 appears for 22 days. In the 22 days, the electronic device detects that the number of days that the user uses the application a in the scene 1 is 17 days, and the rule weight corresponding to the application a is 0.77. The rule weight may be a ratio between the number of days of use of the application a and the number of days of appearance of the scene 1, and may indicate an enabling probability for the application program in the specific spatio-temporal scene referred to by the spatio-temporal feature. In addition, in the 22 days, the electronic device detects that the number of days that the user uses the application b in the scene 1 is 11 days, the rule weight corresponding to the application b is 0.5, and the other similar matters are not repeated.

In some embodiments, the days of use in the different scenarios in table 3 are counted for interactions detected over T days.

Take the example of determining the number of days of use of application a in scenario 1 (location tag 1 and time period 9) and scenario 2 (location tag 1 and time period 10).

The first way is: first, training data 1 and training data 2 are acquired. The training data 1 and the training data 2 are interactive operations for the application a, and the difference is that the space-time scenes of the acquired training data 1 and the acquired training data 2 are different. The training data 1 comprises an interaction c with a position tag 1 and time information 1. The training data 2 comprises an interaction e with a position tag 1 and time information 2. The time information 1 refers to an arbitrary time point belonging to the period 9, and the time information 2 refers to an arbitrary time point belonging to the period 10. As shown in the foregoing embodiment, one day may be quantized into 24 periods in advance, the period 9 being a period indicating 9 to 10 points, and the period 10 being a period indicating 10 to 11 points. Thus, there is no overlapping portion between training data 1 and training data 2. Then, according to the detection date of the interaction operation c in the training data 1, the number of different dates corresponding to the interaction operation c is counted as the number of days of use of the application a in the scene 1 (the position tag 1 and the period 9). According to the detection date of the interaction operation e in the training data 2, the number of different dates corresponding to the interaction operation e is counted to be used as the using days of the application a in the scene 2 (the position label 1 and the period 10).

The second way is: training data 3 and training data 4 are first acquired. Wherein, the training data 3 and the training data 4 are both interactive operations for the application a, except that the space-time scenes of the acquired training data 3 and the acquired training data 4 are different. The training data 3 comprises an interaction w with a position tag 1 and time information 3. The training data 4 comprises an interaction q with a position tag 1 and time information 4. The time information 3 is an arbitrary time point belonging to the sliding window corresponding to the period 9, and the time information 4 is an arbitrary time point belonging to the sliding window corresponding to the period 10. As shown in the foregoing embodiment, one day may be quantized into 24 periods in advance, where the period 9 is a period indicating 9 to 10 points, and in the case where the sliding window duration is 15 minutes, the sliding window corresponding to the period 9 is 8:45 to 10:15. the period 10 is a period indicating 10 to 11 points, and in the case that the sliding window duration is 15 minutes, the sliding window corresponding to the period 10 is 9:45 to 11:15. i.e. there is a part of overlap between training data 3 and training data 4. It will be appreciated that the above-mentioned duration of the sliding window of 15 minutes is merely an example, and the embodiment of the present application is not particularly limited to the duration of the sliding window.

Then, according to the detection date of the interactive operation w in the training data 3, the number of different dates corresponding to the interactive operation w is counted as the number of days of use of the application a in the scene 1 (the position tag 1 and the period 9). According to the detection date of the interaction operation q in the training data 4, the number of different dates corresponding to the interaction operation q is counted to be used as the using days of the application a in the scene 2 (the position label 1 and the period 10).

In summary, the first manner and the second manner may both obtain the number of days of use of the application a in the scene 1 (the scene indicated by the position tag 1 and the period 9), and the number of days of use of the application a in the scene 2 (the scene indicated by the position tag 1 and the period 10), and other manners may be adopted in the embodiment of the present application to determine the number of days of use of the application a in different scenes, which is not limited specifically.

It can be understood that the number of days of use of other applications in each scenario may also be obtained in the above manner, which is not described herein. For example, a first number of days (application usage days) and a second number of days (scene appearance days) corresponding to the first application.

In summary, after creating model 2, the electronic device may detect the spatial and temporal features corresponding to the current scene in real-time. Based on the detected spatial features (e.g., location tags) and temporal features (e.g., time of day information), a matching scene is queried in model 2. And under the condition that the matched scene is inquired, acquiring the application program used in the scene and the corresponding rule weight. Then, an application whose regular weight is greater than the preset weight threshold 2 may be regarded as an application using the rule in the current scene, that is, recommended application 2.

It can be understood that, whether the model 1 is used to obtain the recommended application 1 with the front using heat, or the model 2 is used to obtain the recommended application 2 with the rule of use, the electronic device essentially adopts different recommendation algorithms (model 1 and model 2), and the application program to be recommended to the user is evaluated from different angles. In the embodiment of the application, other recommendation algorithms can be adopted, and application programs which need to be recommended to the user are evaluated from other angles, such as recommendation application 3.

For example, other recommendation algorithms may be an application jump prediction model that predicts applications that have jump relationships with foreground applications and act as corresponding recommended applications. When an application program is generally running in the foreground of the electronic device, the application jump prediction model can be started to predict the corresponding recommended application and display the recommended application on an application interface of the foreground application, and the specific implementation process can refer to the related technology and is not repeated here.

It will be appreciated that the same application may exist in recommended applications determined using different recommendation algorithms. In addition, in the process of screening the recommended application, various recommendation algorithms can give the recommended application corresponding weight, and the weight can represent the recommendation degree of the electronic equipment on the application program. Of course, the types of weights given by different recommendation algorithms are different, for example, recommendation application 1 corresponds to the frequency of use weight, recommendation application 2 corresponds to the regular weight, and recommendation application 3 corresponds to the other weight. If the same application program has multiple classes of weight values, that is, if the multiple analogies determine that the application is a recommended application, the multiple classes of weight values of the recommended application may be fused, and this process may also be referred to as fusing the multiple analogies.

As an implementation manner, the manner of fusing the multiple classes of weight values is as follows: and acquiring recommendation factors of each type of recommendation algorithm, wherein the first recommendation model corresponds to a first recommendation factor, and the second recommendation model corresponds to a second recommendation factor. Wherein the recommendation factor may indicate a recommendation accuracy of the corresponding recommendation algorithm for the application. For example, the higher the duty ratio predicted by the recommendation algorithm is selected by the user, the larger the recommendation factor corresponding to the recommendation algorithm is, the lower the duty ratio predicted by the recommendation algorithm is selected by the user, and the smaller the recommendation factor corresponding to the recommendation algorithm is. In some embodiments, the historical detection data may be used to evaluate recommendation factors corresponding to various recommendation algorithms, and the specific process may refer to related technology, which is not described herein. The history detection data may include interaction data detected by the electronic device within a specified number of days, where the interaction data includes detected interaction operations and corresponding scene tags.

Taking the example of determining the recommendation factor for model 1. For convenience of description, let T denote the day, T-1 denote the day before T, T-2 denote the day before T-1, and so on, T-T denotes the day before T-T+1. As shown in FIG. 11, the electronic device obtains interaction data detected within T-1 days prior to T-1, i.e., interaction data detected by the electronic device within T-2, T-3, … T-T. Then, using the interaction data detected within the above-described T-1 day, a model 1 is created in accordance with the method provided in the foregoing embodiment. And then, the electronic equipment predicts the recommended application to the user according to various scenes detected by the electronic equipment in t-1 by using the model 1. Then, the electronic application program which is actually started by the user and is detected in various scenes of t-1 is obtained. Then, based on the predicted recommended application and the actually enabled application in each scene, the recommendation accuracy of the model 1 is calculated as a recommendation factor of the model 1. The recommendation factor calculation method of other recommendation algorithms is the same and is not described in detail herein. Of course, based on the interaction data detected within T-1 days, model 1 is created only for testing the recommendation factor corresponding to model 1. The model 1 actually used in the electronic device may be a model trained based on interaction data detected within T days (i.e., within T-1, T-2, …, T-T).

After determining the recommendation factors for each type of recommendation algorithm, the electronic device may calculate a product of the weight given by each type of recommendation algorithm to each recommendation application and the recommendation factors as a recommendation weight for that recommendation application. When a recommendation application is recommended by a multi-analogy algorithm, the recommendation application corresponds to a plurality of recommendation weights, and under the scene, the plurality of recommendation weights are overlapped to be used as final recommendation weights of the recommendation application.

For example, the recommended applications predicted by the electronic device using model 1 and model 2 include WeChat ^TM、WeLink^TM and WeChat ^TM, wherein model 1 gives WeChat ^TM a frequency of use of 0.2, weLink ^TM a frequency of use of 0.3, and WeChat ^TM a frequency of use of 0.1. Model 2 gave WeChat ^TM a rule weight of 0.6, weLink ^TM a rule weight of 0.2, and ^TM a rule weight of 0.3. In addition, the electronic device determines that the recommendation factor corresponding to the model 1 is 0.98, and the recommendation factor corresponding to the model 2 is 0.95, and then the recommendation weight corresponding to the WeChat ^TM is finally: 0.2 x 0.98+0.6 x 0.95=0.76, and the final corresponding recommended weight of the wellink ^TM is: 0.3×0.98+0.2×0.95=0.48, knowing ^TM that the final corresponding recommended weights are: 0.1 x 0.98+0.3 x 0.95=0.38. Thus, after the weighting is fused, the electronic device determines that the recommendation level for WeChat ^TM is greater than the recommendation level for WeLink ^TM, and the recommendation level for WeLink ^TM is greater than the recommendation level for ^TM.

For another example, the recommended application determined by the model 1 further includes an office application, and if the frequency of use of the office application is given by the model 1 as a weight of 0.3 in a scenario that the recommended application determined by other recommendation algorithms does not include the office application, the final recommendation weight of the office application is: 0.3 x 0.98=0.29. In this way, when evaluating the recommendation degree for the application program according to the recommendation weight, it can be determined that the recommendation degree for the WeChat ^TM is greater than the recommendation degree for WeLink ^TM, the recommendation degree for WeLink ^TM is greater than the recommendation degree for the office application, and the recommendation degree for the office application is greater than the recommendation degree for the knowledge ^TM.

In some embodiments, the electronic device may arrange application icons of the recommended applications on the recommendation control from left to right in order of final recommendation weight from high to low. That is, the recommended application with the larger final recommendation weight is arranged on the left side, and the recommended application with the smaller final recommendation weight is arranged on the right side.

In other embodiments, the application icons on the recommendation control may also be arranged out of order. For example, it is determined for the first time that the recommended application includes WeChat ^TM and WeChat ^TM, and the electronic device arranges WeChat ^TM and WeChat ^TM application icons on the recommended control according to the recommendation weight. With the scene in which the electronic device is located, the second determined recommended applications include WeChat ^TM and WeLink ^TM, that is, the same applications exist and different applications exist compared to the recommended application determined last (first time), for example, less known about ^TM, but additionally WeLink ^TM, which of course, all contain WeChat ^TM. In this scenario, the application icon known as ^TM may be canceled from being displayed on the recommendation control, and then the application icon WeLink ^TM may be displayed at the display position of the application icon known as ^TM. Then, along with the scene change of the electronic device, the recommended application determined for the third time includes a note ^TM and an office application, that is, the recommended application determined for the last time (the second time) is completely different from the recommended application determined for the last time, in this scene, the electronic device may cancel the application icons of the WeChat ^TM and WeLink ^TM displayed on the recommended control, and meanwhile, the application icons of the note ^TM and the office application are arranged on the recommended control according to the recommended weight.

In a word, by adopting the method provided by the embodiment of the application, the recommended hit rate of long-tail application can be effectively improved. The long-tail application may include an application program with low use heat, but regular use conditions, that is, an application program with low use heat, such as an attendance application, an access control application, an intelligent home application, a public transportation application, and the like, which is usually started in a specific space-time scene.

In other possible embodiments, the electronic device may also recommend the function shortcut entry of the application program to the user through the recommendation control, and the process of determining the function shortcut entry to be recommended is similar to the process of determining the recommended application in the foregoing embodiment, which is not described herein.

The embodiment of the application also provides electronic equipment, which can comprise: a memory and one or more processors. The memory is coupled to the processor. The memory is for storing computer program code, the computer program code comprising computer instructions. The computer instructions, when executed by the processor, cause the electronic device to perform the steps performed by the handset in the embodiments described above. Of course, the electronic device includes, but is not limited to, the memory and the one or more processors described above.

The embodiment of the application also provides a chip system which can be applied to the terminal equipment in the embodiment. As shown in fig. 12, the system-on-chip includes at least one processor 2201 and at least one interface circuit 2202. The processor 2201 may be a processor in an electronic device as described above. The processor 2201 and the interface circuit 2202 may be interconnected by wires. The processor 2201 may receive and execute computer instructions from the memory of the electronic device described above through the interface circuit 2202. The computer instructions, when executed by the processor 2201, cause the electronic device to perform the steps performed by the handset in the embodiments described above. Of course, the system-on-chip may also include other discrete devices, which are not particularly limited in accordance with embodiments of the present application.

In some embodiments, it will be clearly understood by those skilled in the art from the foregoing description of the embodiments, for convenience and brevity of description, only the division of the above functional modules is illustrated, and in practical application, the above functional allocation may be implemented by different functional modules, that is, the internal structure of the apparatus is divided into different functional modules to implement all or part of the functions described above. The specific working processes of the above-described systems, devices and units may refer to the corresponding processes in the foregoing method embodiments, which are not described herein.

The functional units in the embodiments 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 integrated units may be implemented in hardware or in software functional units.

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

The foregoing is merely a specific implementation of the embodiment of the present application, but the protection scope of the embodiment of the present application is not limited to this, and any changes or substitutions within the technical scope disclosed in the embodiment of the present application should be covered in the protection scope of the embodiment of the present application. Therefore, the protection scope of the embodiments of the present application shall be subject to the protection scope of the claims.

Claims

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

The electronic equipment displays a first interface, wherein the first interface comprises a first control, and the first control is used for displaying application icons of application programs to be recommended to a user;

When the electronic equipment is located in a first position area and the system time belongs to a first period, the electronic equipment displays an application icon of a first application in the first control;

The first weight of the first application is higher than the first weight of the second application, an application icon of the second application is not displayed on the first control, the first weight is used for indicating the enabling probability of the application program in the scene of being located in the first position area, and the system time belongs to the first period.

2. The method according to claim 1, wherein the method further comprises:

When the electronic equipment is located in the first position area and the system time belongs to a first period, the electronic equipment displays an application icon of a third application in the first control; the second weight of the third application is higher than the second weight of the fourth application, the application icon of the fourth application is not displayed on the first control, and the second weight is used for indicating interaction frequency between the user and the application program in the current scene.

3. The method of claim 2, wherein the electronic device includes a first recommendation model and a second recommendation model, the first recommendation model is used to determine the second weights corresponding to the applications in different scenarios, the second recommendation model is used to determine the first weights corresponding to the applications in different scenarios, and the electronic device is further configured to, before displaying the first application and the third application in the first control:

The electronic equipment acquires first time and first position information;

Determining, by the electronic device, the first application using the second recommendation model, in a case where the first time belongs to the first period and the first location information indicates the first location area, the first application being an application in which the first weights are rearranged before a first ranking when the first weights of the applications are arranged in order from large to small;

The electronic device determines the third application by using the first recommendation model, wherein the third application is an application program with the second weights rearranged before the second ranking when the second weights of the application programs are arranged in the order from the big to the small.

4. A method according to claim 3, wherein the first location information comprises one or a combination of a service set identity provided by a first network, a cell identity provided by a first base station and first latitude and longitude information, wherein the signal coverage areas of the first network and the first base station belong to the first location area.

5. The method of claim 3, wherein prior to the electronic device displaying a first application in the first control, the method further comprises:

The electronic equipment acquires a first number of days and a second number of days, wherein the first number of days is the number of days when the first application is started in a scene that the electronic equipment is located in the first position area and the system time belongs to a first period, and the second number of days is the number of days when the electronic equipment detects that the electronic equipment is located in the first position area and the system time belongs to the first period;

the electronic device determines a first weight corresponding to the first application when the electronic device is located in the first location area and the system time belongs to the first period according to the first number of days and the second number of days;

and the electronic equipment updates the first recommendation model according to the first application and the corresponding first weight.

6. A method according to claim 3, characterized in that the method further comprises:

The electronic equipment acquires interaction data, wherein the interaction data comprises the interaction times of users and various application programs under the condition that different position information, different time information, different user state information and different equipment state information are detected;

And the electronic equipment clusters according to the position information, the time information, the user state information and the equipment state information in the interaction data to obtain the second recommendation model.

7. The method of claim 6, wherein the electronic device obtaining interaction data comprises:

The electronic equipment collects the position information, the time information, the user state information and the equipment state information when detecting a first operation aiming at any application program;

Under the condition that a first service set identifier and a first cell identifier are acquired, determining the first service set identifier as the detected position information, and associating the first cell identifier with the first service set identifier;

And under the condition that the first cell identity is acquired and the first cell identity is already associated with the first service set identity, determining the first service set identity as the detected position information.

8. The method of claim 7, wherein the electronic device determines the location information as a first identification indicating unidentified geospatial if a service set identification and a cell identity are not acquired upon detection of the first operation.

9. A method according to claim 3, wherein the first application comprises a fifth application and a sixth application, and wherein in the case where the third application comprises a sixth application and a seventh application, the method further comprises:

The electronic equipment determines the recommendation weight of the sixth application according to the first weight, the second weight, the first recommendation factor and the second recommendation factor corresponding to the sixth application, wherein the first recommendation factor is used for indicating the recommendation hit rate of the first recommendation model, and the second recommendation factor is used for indicating the recommendation hit rate of the second recommendation model;

The electronic equipment determines the recommendation weight of the sixth application according to the first weight and the first recommendation factor corresponding to the fifth application;

and the electronic equipment determines the recommendation weight of the seventh application according to the second weight and the second recommendation factor corresponding to the seventh application.

10. The method of claim 9, wherein application icons of the fifth application, the sixth application, and the seventh application are arranged on the first control in an order of the corresponding recommendation weights from high to low.

11. An electronic device comprising one or more processors and memory; the memory being coupled to a processor, the memory being for storing computer program code comprising computer instructions which, when executed by one or more processors, are for performing the method of any of claims 1-10.

12. A computer storage medium comprising computer instructions which, when run on an electronic device, cause the electronic device to perform the method of any of claims 1-10.