CN116126197B - Application Recommendation Method - Google Patents

Abstract

The application provides an application program recommending method. The method comprises the following steps: the electronic equipment displays a first text and a second text on a display interface of a first application; responding to a first operation of a user on a first text, and displaying a first icon corresponding to a second application on a display interface; the electronic equipment responds to a second operation of the user on the first icon, and displays an interface of a second application corresponding to the first icon; the user can also adjust the selected file, and the electronic equipment responds to a third operation of the user on the first text and the second text and displays a second icon corresponding to a third application on the display interface; and the electronic equipment responds to the fourth operation of the user on the second icon, and displays an interface of a third application corresponding to the second icon. According to the application program recommending method, the electronic equipment directly carries out application recommending according to the text selected by the user, the user does not need to exit the first application, the target application is searched from a large number of applications in the desktop, the operation is convenient, and the time for searching the application by the user can be saved.

Description

Application Recommendation Method

Technical Field

The present application relates to the field of terminal devices, and in particular to an application recommendation method.

Background technique

Currently, a large number of applications are usually installed in smart terminal electronic devices such as mobile phones and tablets. When using such electronic devices, users often encounter the need to find applications for content in text or pictures. For example, if the text contains an address, the user wants to find a map application to navigate to it. At this time, the user needs to exit the current text and search for a navigation application from a large number of applications contained in the main interface. The operation process is cumbersome and time-consuming, resulting in a poor user experience.

Summary of the invention

The present application provides an application recommendation method, through which application recommendation can be performed based on text selected by a user, without the need for the user to manually search for the target application from a large number of applications installed in the electronic device, thereby improving the user experience.

In some embodiments, the electronic device can respond to the user's first operation on the first text displayed on the display interface of the first application, such as copying, selecting, clicking or long pressing, and display the first icon corresponding to the second application on the display interface of the first application, recommend application information to the user in the form of the first icon, and the user performs a second operation on the first icon, triggering the electronic device to display the interface of the second application, without the user exiting the first application, and searching for the second application from a large number of applications on the desktop, which is convenient and can save the user time spent searching for applications. Not only that, the user can also adjust the selected text, and the electronic device responds to the user's third operation on the first text and the second text, and displays the second icon corresponding to the third application obtained by text analysis of the first text and the second text on the display interface; the electronic device responds to the user's fourth operation on the second icon, and displays the interface of the third application corresponding to the second icon. The user can flexibly adjust the selected text to trigger the system to recommend different applications, which is convenient and can enhance the fun of application recommendation.

In a first aspect, the present application provides an application recommendation method, which is applied to an electronic device, wherein the method includes: the electronic device displays a first text and a second text on a display interface of a first application; the electronic device displays a first icon corresponding to the second application on the display interface of the first application in response to a first operation of the user on the first text, so as to recommend the second application to the user; when the user wants to open the second application, the second operation, such as a single-click operation, can be performed on the first icon, and the electronic device displays the interface of the second application corresponding to the first icon in response to the second operation of the user on the first icon. Wherein, the first operation and the third operation can include but are not limited to: click, copy, select or long press operation, and the first application can include but are not limited to: gallery, real-time screenshot, browser, memo and short message, etc. When the user wants to adjust the selected text to trigger the electronic device to re-recommend the application, the third operation can be performed on the text displayed on the display interface of the first application again, and the electronic device displays the second icon corresponding to the third application on the display interface in response to the third operation of the user on the first text and the second text, wherein the second icon is obtained based on the text analysis of the first text and the second text; when the user wants to switch to the third application, the fourth operation can be performed on the second icon, and the electronic device displays the interface of the third application corresponding to the second icon in response to the fourth operation of the user on the second icon. The fourth operation and the second operation may include but are not limited to: single click, double click or long press, etc.

With this method of application recommendation, the electronic device can recommend applications to the user based on the text selected by the user. The user can trigger the electronic device to open the corresponding application by performing a second operation on the recommended application icon. The user does not need to exit the first application and then search for the target application from a large number of applications installed on the electronic device. The operation is convenient and can save time spent on application search.

According to the application recommendation method of the first aspect, the first text includes: plain text or text obtained by OCR recognition of a picture. The source of the plain text may include but is not limited to: a browser, a memo, and a short message. The source of the picture may include but is not limited to: a gallery, a real-time screenshot, a browser, or a social software. This application recommendation method can not only recommend applications for plain text but also for text in a picture, and has strong universality.

According to the first aspect, or any implementation of the first aspect above, before the electronic device displays the first text and the second text on the display interface of the first application, the method further includes: the electronic device displays the picture in the display interface of the first application in response to the user's fifth operation on the picture in the first application; when the picture includes text, the first button is displayed, wherein the first button is used to trigger the display of the first text and the second text obtained by OCR recognition of the picture; when the user wants to obtain the text obtained by OCR recognition, the first button can be operated. The electronic device responds to the user's sixth operation on the first button, and highlights the first text and the second text obtained by OCR recognition in the display interface. The fifth operation may include but is not limited to: single-click, double-click, long press, two-finger click and other operations, and the sixth operation may include but is not limited to: single-click, double-click or long press and other operations. This method of performing OCR recognition on pictures is simple and convenient to operate.

According to the first aspect, or any implementation of the first aspect above, when the electronic device highlights the first text and the second text in the display interface, the electronic device highlights the first text and the second text obtained by OCR recognition of the image in the display interface, and displays an underline under the first text and the second text, wherein the first text and the second text are preset entities, and the preset entity may include but is not limited to: address, code, ID number, telephone number, express number, website, email address, foreign language, Taobao password or Douyin password. This method of adding an underline under the preset entity for display, on the one hand, is convenient for users to intuitively know which are the preset entities, and on the other hand, the user can click on some preset entities or underlines to select the preset entity, without moving the cursor in the text to select multi-text text, which is convenient for user operation. It should be noted that for non-preset entities in the OCR recognition results, they can be highlighted but not underlined below them.

According to the first aspect, or any implementation of the first aspect above, the method further includes: when the electronic device detects that the user performs a third operation on the second text, canceling the display of the first icon in the display interface. In this manner of canceling the display of the icon of the last recommended application during the process of adjusting the selected text, since the icon is canceled from display, the text that the user wants to select will not be obscured, which facilitates the user's operation.

According to the first aspect, or any implementation of the first aspect above, the method also includes: the electronic device displays a first icon corresponding to the second application and a third icon corresponding to the fourth application on the display interface in response to the user's seventh operation on the third text and the second text; wherein the first text includes the third text, and the first icon and the third icon are obtained based on text analysis of the first text and the third text; in response to the user's eighth operation on the third icon, the interface of the fourth application corresponding to the third icon is displayed; the electronic device displays a second icon corresponding to the third application on the display interface in response to the user's third operation on the first text and the second text, wherein the second icon is obtained based on text analysis of the first text and the second text; in response to the user's fourth operation on the second icon, the interface of the second application corresponding to the first icon is displayed.

The seventh operation may be the same as the first operation in the above method, and the eighth operation may be the same as the second operation in the above method, which will not be repeated here. In this application recommendation method, when the third text selected by the user is not related to the first text, the electronic device performs text analysis on the third text to determine the fourth application, and performs text analysis on the first text to determine the second application, and then recommends the third icon of the fourth application and the first icon of the second application, without the user having to manually search for icons. When the first text selected by the user is related to the second text, the electronic device performs text analysis on the first text and the second text to determine the third application, and recommends the second icon corresponding to the third application. The application recommendation method is flexible and diverse.

According to the first aspect, or any implementation of the first aspect above, when the electronic device displays the first icon corresponding to the second application on the display interface of the first application in response to the user's first operation on the first text, it includes: the electronic device displays a floating ball on the display interface of the first application in response to the user's click operation on the first text, wherein the floating ball includes the first icon of the second application obtained by performing text analysis on the first text. Displaying the first icon of the second application in the form of a floating ball, on the one hand, can always remain at the top of the screen to avoid being covered by other content due to the floating display of the floating ball; on the other hand, the floating ball covers a smaller screen area to avoid excessive coverage of image content; third, directly displaying the first icon of the second application is more eye-catching, which is convenient for users to determine whether the second application is the application to be switched.

According to the first aspect, or any implementation of the first aspect above, the electronic device displays a first icon corresponding to a second application on a display interface of the first application in response to a first operation of a user on a first text, including: the electronic device displays a floating window on the display interface of the first application in response to a click operation of the user on the first text, the floating window includes service options obtained by text analysis of the first text, and the service options at least include service options corresponding to the second application. This method of recommending a matching service option list based on the first text selected by the user recommends multiple service options at the same time, making it easier for the user to find the target option from the recommended service options.

According to the first aspect, or any implementation of the first aspect above, the first operation includes: click, copy, select, and long press. Clicking may include but is not limited to: single-finger single click, single-finger double click, double-finger click, etc. Copying may include the cursor moving in the text to select the first text and then displaying a menu bar containing a copy option, and the user clicks the copy option to complete the copying of the first text. There is no specific restriction on the specific duration of the long press, for example: long press for 1 second, 2 seconds or 3 seconds, etc. This method of setting the first operation in a diversified manner makes the setting of the first operation more flexible.

According to the first aspect, or any implementation of the first aspect above, the electronic device displays a first icon corresponding to the second application on the display interface of the first application in response to the user's first operation on the first text, including: the electronic device displays a floating ball corresponding to the second application on the display interface of the first application in response to the user's selection operation on the first text, wherein the first text includes multiple combinable preset entities, and the floating ball includes the first icon corresponding to the second application. This application recommendation method, when recognizing that the first text contains multiple combinable preset entities, only recommends one application, namely the first icon corresponding to the second application, and the recommendation result is more accurate and convenient for users to choose.

According to the first aspect, or any implementation of the first aspect above, the electronic device displays a first icon corresponding to a second application on the display interface of the first application in response to a first operation of a user on a first text, including: the electronic device displays a floating window on the display interface of the first application in response to a selection operation of the user on the first text, wherein the first text includes a plurality of non-combinable preset entities, the floating window includes a plurality of application icons, and the plurality of application icons include at least the first icon of the second application. This application recommendation method, when recognizing that the first text contains a plurality of non-combinable preset entities, recommends a plurality of application recommendations for the user to select because the user's true intention is uncertain, so as to facilitate the user to select the second application to which he or she wishes to switch.

According to the first aspect, or any implementation of the first aspect above, the electronic device displays a first icon corresponding to a second application on a display interface of a first application in response to a first operation of a user on a first text, including: the electronic device displays a floating window on a display interface of the first application in response to a copy operation of the user on the first text, the floating window includes multiple application icons, and the multiple application icons include the first icon corresponding to the second application. In this application recommendation method, when the copied first text does not contain a preset entity, since the user's true intention is uncertain, multiple application recommendations are recommended for the user to choose, so that the user can select the second application to which he or she wishes to switch.

According to the first aspect, or any implementation of the first aspect above, the second operation includes: single click, double click, and long press. Single click may include but is not limited to: single finger single click, double finger single click, double click may also include but is not limited to: single finger double click, double finger double click, and there is no specific restriction on the specific duration of long press, for example: long press for 1 second, 2 seconds or 3 seconds, etc. This method of setting the second operation in a diversified manner makes the setting of the second operation more flexible.

In a second aspect, the present application further provides an application recommendation method, which is applied to an electronic device, and the method includes: the electronic device identifies a preset entity contained in a first text in response to a user's first operation on a first text in a first application, such as click, long press, or copy; when the first text contains the preset entity, determining the information to be recommended based on the preset entity contained in the first text; when the first text does not contain the preset entity, determining the information to be recommended based on the content of the first text, wherein the information to be recommended includes: an application icon or a service list; displaying a first icon in the display interface of the first application, the first icon corresponding to the information to be recommended.

This application recommendation method recommends an application or service list based on the first text selected by the user. The user can trigger the electronic device to open the second application by clicking on the second application from the recommendation. The user does not need to exit the first application and then search for the second application from a large number of applications installed on the electronic device. The operation is convenient and can save time spent on application search.

According to the application recommendation method of the second aspect, before the electronic device responds to the user's first operation on the first text in the first application, the method further includes: the electronic device responds to the user's second operation on the picture in the first application, such as: click, long press, etc., and displays the picture in the display interface of the first application; identifies whether the picture contains text; if the picture includes text, performs OCR recognition on the picture to obtain the second text; displays the first button, wherein the first button is used to trigger the display of the second text; when the user previews the OCR recognition result, the third operation can be performed on the first button, and the electronic device responds to the user's third operation on the first button, and highlights the second text in the display interface, wherein the second text includes the first text. This method of performing OCR recognition on pictures is simple and convenient to operate.

According to the first aspect, or any implementation of the first aspect above, in the case where a preset entity is included in the first text, the electronic device determines the information to be recommended based on the preset entity included in the first text, including: in the case of a single preset entity included in the first text, the electronic device determines a second application or service list that matches the preset entity contained in the first text. In this method of recommending a single application or service list based on a single preset entity, the recommended content is more in line with user expectations. For example: the preset entity is a Taobao password, and the user is very likely to want to open the Taobao application when viewing the Taobao password, so the Taobao application is recommended to the user. The user no longer needs to manually search for the Taobao application from the desktop.

According to the first aspect, or any implementation of the first aspect above, when the first text contains a preset entity, the electronic device determines the information to be recommended based on the preset entity contained in the first text, including: when the first text contains multiple preset entities, the electronic device determines whether the multiple preset entities are combinable; when the multiple preset entities are combinable, a third application is determined based on the multiple preset entities. This application recommendation method, when it is recognized that the first text contains multiple combinable preset entities, only one application, namely the second application, is recommended, and the recommendation result is more accurate and convenient for users to choose. For example: when it is recognized that the first text includes a name, a phone number, and an address, it is determined that the user is very likely to want to switch to a shopping application, so a shopping application is recommended.

According to the first aspect, or any implementation of the first aspect above, when the electronic device determines that multiple preset entities cannot be combined, it separately determines the fourth applications that match each preset entity contained therein, and determines the determined multiple fourth applications as recommendation information. This application recommendation method, when it is recognized that the first text contains multiple preset entities that cannot be combined, because the user's true intention is uncertain, multiple application recommendations are recommended for the user to choose, so that the user can choose the application to which he or she wishes to switch. For example: when the first text includes foreign language, Taobao password and address, since these three preset entities cannot be combined, the application translation application, map application and shopping application corresponding to each preset entity are recommended respectively.

According to the second aspect, or any implementation of the second aspect above, when the first text does not contain a preset entity, determining the information to be recommended based on the content of the first text includes: when the electronic device does not contain the preset entity in the first text, extracting features from the first text; determining the first application category and the second application category that match the first text based on the extracted features; screening out a first preset number of fifth applications from the first application category; screening out a second preset number of sixth applications from the second application category; the fifth application and the sixth application are determined as the information to be recommended. Among them, the first preset number is greater than the second preset number, and the specific values of the first preset number and the second preset number can be flexibly set by those skilled in the art, and no specific restrictions are made in this solution. In this application recommendation method, when the first text does not contain a preset entity, since the user's true intention is uncertain, multiple application recommendations are recommended for the user to choose, so that the user can choose the second application to which he or she wishes to switch.

According to the second aspect, or any implementation of the second aspect above, the first icon includes: a floating ball or a floating window. The floating ball covers a small screen area, and the floating window can display more content. The electronic device can adaptively select the first icon style according to the amount of content of the information to be recommended.

According to the second aspect, or any implementation of the second aspect above, the preset entity may include but is not limited to: address, code, ID number, telephone number, express number, website, email address, foreign language, Taobao password or Douyin password. The preset entity can be flexibly adjusted by those skilled in the art. Set up multiple preset entities, and pre-set corresponding application recommendation information for each preset entity, so as to facilitate reliable application recommendations for users during user use.

In a third aspect, the present application provides a computer-readable medium for storing a computer program, the computer program comprising instructions for executing a method in any possible implementation of the first aspect or the second aspect, or comprising instructions for executing a method in any possible implementation of the first aspect or the second aspect.

In a fourth aspect, the present application provides a computer program comprising instructions for executing a method in any possible implementation of the first aspect or the second aspect, or comprising instructions for executing a method in any possible implementation of the first aspect or the second aspect.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram showing a hardware structure of an electronic device;

FIG. 2 is a schematic diagram showing an exemplary software structure of an electronic device;

FIG3 is a schematic diagram of an interface for performing OCR recognition on pictures in a gallery;

FIG4A is a schematic diagram of an interface for exemplarily showing application recommendation based on a single preset entity;

FIG4B is a schematic diagram of an interface for recommending a service list based on a single preset entity;

FIG5 is a schematic diagram of an interface for recommending applications based on a Taobao password;

FIG6 is a timing flow chart showing an example of the interaction between a user and a device when making an application recommendation based on a single preset entity in a picture;

FIG. 7 is a schematic diagram showing an exemplary interface change when application recommendation is performed based on multiple associated preset entities selected twice by a user;

FIG8 is a schematic diagram showing another exemplary interface change when application recommendations are made based on multiple preset entities selected twice by a user;

FIG9 is a schematic diagram showing an exemplary interface change when an application list is recommended based on multiple non-associated preset entities selected twice by a user;

FIG10 is a timing flow chart showing an example of interaction between a user and a device when making application recommendations based on multiple preset entities in a picture;

FIG11 is a schematic diagram of an interface for recommending applications based on pictures that do not contain preset entities;

FIG. 12 is a timing flow chart showing an example of the interaction between a user and a device when making application recommendations based on image content.

Detailed ways

The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

The term "and/or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and/or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

The terms "first" and "second" in the description and claims of the embodiments of the present application are used to distinguish different objects rather than to describe a specific order of objects. For example, a first target object and a second target object are used to distinguish different target objects rather than to describe a specific order of target objects.

In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

In the description of the embodiments of the present application, unless otherwise specified, the meaning of "multiple" refers to two or more than two. For example, multiple processing units refer to two or more processing units; multiple systems refer to two or more systems.

The application recommendation method in the embodiment of the present application can be applied to a scenario where text in a first application of the same electronic device is copied to a second application.

In one example, the scenario may be: copying and pasting text in an application such as a browser, a memo, an email, or WeChat into another application different from the source application of the text. In this example, the text in the application can be directly selected, copied, or clicked.

In another example, the scenario may be, for example, copying and pasting the target text in the optical character recognition (OCR) result of the image into an application. The image may come from a gallery, real-time screenshot, browser, WeChat, QQ, and other applications. The embodiment of the present application does not limit the source of the image. In this example, the text in the application comes from the OCR recognition result of the image, and the text in the image cannot be directly selected before OCR recognition.

For example, a photo of a courier contains address information, phone number, recipient information, etc., and the user wants to add the address information to the delivery address of a shopping application. At this time, the application recommendation method in the embodiment of the present application can be applied to paste the address information in the photo into the delivery address of the shopping application.

By applying optical character recognition technology, the character strings in the image can be identified. These identified character strings, i.e., the OCR recognition results of the image, are texts. The target text selected by the user in the OCR recognition results can be referred to as the first text, the second text, etc. In the OCR recognition results of the image, the character string can be further determined whether it is a preset entity, such as: address, code, ID number, telephone number, express number, website, email address, foreign language, Taobao password or Douyin password, etc. The user can select a single or multiple preset entities in the OCR recognition results. The user can select, copy, and other operations on the non-preset entities of the OCR recognition results to select the target text. After selecting the target text, the user usually wants to paste the target text into the text input box of an application or a service. The system will recommend an application or service list based on the target text so that the user can select the target application or target service and paste the target text into the target application or target service. Among them, the application can also be referred to as an application program, and the application corresponding to the target application and the target service can also be referred to as the application that the system starts after the user clicks on the recommended icon. The application currently displaying the image can also be referred to as the first application.

The target text selected by the user may be in the following situations: first, it contains a single preset entity; second, it contains multiple preset entities with an associated relationship; third, it contains multiple preset entities that are not associated; fourth, it does not contain a preset entity. Depending on the preset entities contained in the target text, the system will use different recommendation methods to recommend application or service lists. When the target text contains a single preset entity, the system recommends a single application or service list; when the target text contains multiple preset entities with an associated relationship, the system recommends a single application or service list; when the target text contains multiple preset entities that are not associated, the system recommends a taskbar, which can also be called a recommended application list. When the target text does not contain a preset entity, the system recommends a taskbar. Among them, the taskbar contains multiple recommended applications. For the recommendation process and specific recommendation content of the application or service list in various situations, please see the relevant description below.

The application interaction method in the embodiment of the present application can be applied to an electronic device. The electronic device can be, for example, a mobile phone, a tablet, etc. FIG. 1 is a schematic diagram of the structure of an electronic device 100 exemplarily shown. It should be understood that the electronic device 100 shown in FIG. 1 is only an example of an electronic device, and the electronic device 100 may have more or fewer components than those shown in the figure, may combine two or more components, or may have different component configurations. The various components shown in FIG. 1 may be implemented in hardware, software, or a combination of hardware and software including one or more signal processing and/or application-specific integrated circuits.

1 , the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

The software system of the electronic device 100 may adopt a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. The embodiment of the present application takes the Android system of the layered architecture as an example to exemplify the software structure of the electronic device 100.

FIG. 2 is a block diagram showing a software structure of the electronic device 100 according to an embodiment of the present application.

The layered architecture of the electronic device 100 divides the software into several layers, each with clear roles and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom, namely, the application layer, the application framework layer, the Android runtime (Android runtime) and the system library, and the kernel layer.

The application layer can include a series of application packages.

As shown in FIG. 2 , the application package may include applications such as sensors, cameras, gallery, OCR engine, application recommendation module, third-party applications, and screenshots.

Among them, the OCR engine can be used to perform OCR recognition on images and identify preset entities in the OCR recognition results; the image can be a screenshot image obtained by a screenshot application, a photo taken by a camera application, or a picture stored in a gallery, etc. The embodiment of the present application does not limit the source of the image.

Application recommendation is used to predict the application or service list related to the target text content based on the target text content, and recommend the predicted application to the user. Third-party applications are used to provide pictures or selectable and copyable text information.

The application framework layer provides an application programming interface (API) and a programming framework for the applications in the application layer. The application framework layer includes some predefined functions.

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

The view system includes visual controls, such as controls for displaying text, controls for displaying pictures, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying pictures.

The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

The activity manager is used to manage the life cycle of each application and the navigation fallback function. It is responsible for creating the Android main thread and maintaining the life cycle of each application.

Android runtime includes core libraries and virtual machines. Android runtime is responsible for scheduling and management of the Android system.

The core library consists of two parts: one is the function that needs to be called by the Java language, and the other is the core library of Android.

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

The system library may include multiple functional modules, such as a surface manager, etc.

The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.

The kernel layer is the layer between hardware and software. The kernel layer can contain modules such as display driver and sensor driver.

It is understandable that the layers in the software structure shown in FIG2 and the components contained in each layer do not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer layers than shown in the figure, and each layer may include more or fewer components, which is not limited in the present application.

For ease of description, the electronic device is referred to as a device in the following text. It should be understood that the devices mentioned in this text can have the same hardware structure (such as the hardware structure shown in Figure 1) and the same software structure (such as the software structure shown in Figure 2) as the electronic device 100 in the above embodiment.

In the embodiments of the present application, the specific process of the application recommendation method of the present application is explained by taking three scenarios as examples, namely, the target text selected by the user contains a single entity, multiple entities, and does not contain an entity.

The following is a description of the process of recommending applications when the target text selected by the user contains a single entity, in conjunction with Figures 3 to 6. Figure 6 is an exemplary sequential flow chart of the interaction between the user and the device when recommending applications based on a single entity in a picture. The application recommendation process includes the following steps:

S1: The user clicks on picture a in the gallery.

S2: In response to clicking on picture a, the device displays picture a on the device screen.

The user can perform the operation of clicking on the picture in various situations, so that the picture is displayed on the device screen. The device here can be, for example, a mobile phone, a tablet, etc. This article takes the mobile phone as an example for description. It should be understood that the description of the mobile phone as an example in this article is also applicable to other non-mobile devices, such as a tablet, etc.

S3: The device detects whether there is text in image a. If there is text, the OCR recognition result of image a is obtained.

For example, FIG3 is a schematic diagram of an interface for performing OCR recognition on images in a gallery. Referring to FIG3, in an exemplary implementation, a user can click on the "Gallery" icon in the main interface of a mobile phone (see FIG3 (a)). After clicking on the "Gallery" icon, the user enters the internal interface of the "Gallery" application, and the interface display at this time is shown in FIG3 (b). Referring to FIG3 (b), the "Gallery" includes pictures such as picture a, picture 1, picture 2, picture 3, and picture n. The user can continue to click on pictures on the interface shown in FIG3 (b). For example, assuming that the user clicks on picture a.

At this time, the mobile phone responds to clicking on picture a and displays picture a on the mobile phone screen, as shown in Figure 3(c). Figures (a) to (c) in Figure 3 are explained by taking the example of entering the picture display interface from the gallery. It should be noted that the present application does not limit the method of entering the picture display interface. For example, in other embodiments of the present application, you can also enter the picture display interface by clicking on the screenshot image after taking a screenshot, you can also enter the picture display interface by clicking on the picture in the web page while browsing the web page, you can also enter the picture display interface by clicking on the picture in the chat interface during the chat of the social communication software, you can also enter the picture display interface by clicking on the picture in the circle of friends or the public account post, etc., which will not be listed one by one here.

Please continue to refer to FIG. 3. After displaying picture a, the application recommendation method of the embodiment of the present application further detects whether there is text in picture a. If there is text in picture a, the OCR recognition result of picture a is obtained. If there is no text in picture a, the application recommendation method process of the embodiment of the present application ends.

In the embodiment of the present application, the device can obtain the OCR recognition result of image a in a variety of ways.

In an exemplary implementation process, if the storage data of picture a includes the OCR recognition result of picture a, the device can directly read the OCR recognition result of picture a from the storage data of picture a.

In another exemplary implementation process, if the storage data of picture a does not include the OCR recognition result of picture a, the device can call the OCR engine of the application layer shown in Figure 2 to perform real-time OCR recognition on picture a, and obtain the OCR recognition result of picture a from the output data of the OCR engine.

Among them, the OCR engine is used to perform OCR recognition on the image and output the OCR recognition result of the image.

S4: If the OCR recognition result of image a is obtained, an OCR button pops up on the device screen.

In this step, the OCR recognition button popped up on the device screen is in an unactivated state. Please refer to FIG3 (d) for the device interface at this time. If the user does not click the OCR recognition button in FIG3 (d), the text and other characters in the image a cannot be selected or copied.

At this time, the user can click the OCR button to trigger the subsequent operation of highlighting the OCR recognition result and underlining the preset entity included in the OCR recognition result.

If the device does not detect the operation of clicking the OCR button within the preset time after the OCR button pops up on the screen, it can be confirmed that the user has not selected the target text from the OCR recognition results and triggered the system to recommend applications. At this time, the device can actively stop displaying the OCR button on the device screen, that is, the OCR recognition button disappears from the interface of picture a. The preset time can be flexibly set by those skilled in the art, for example: set to 2 seconds, 3 seconds, 5 seconds, etc., and there is no specific limitation on this in the embodiments of the present application.

In an exemplary implementation process, if the user does not select the target text from the OCR recognition results and trigger the system to recommend an application, the user can also click anywhere outside the OCR button. At this time, the device detects the user's click operation on any place outside the OCR button and can stop displaying the OCR button on the device screen. In this way, the device passively stops displaying the OCR button based on the user's operation.

Of course, in another exemplary implementation process, if the user has no need to select target text from the OCR recognition results and trigger the system to make application recommendations, the device can also keep the OCR button in an unactivated state.

S5: The user clicks the OCR button.

The device detects the user's click operation on the OCR button, and can confirm that the user has a need to select target text from the OCR recognition results to trigger the system to make application recommendations.

The click operation on the OCR button is not limited to the single click operation shown in FIG. 3 d , and may also be a double click or a long press operation.

S6: In response to the click operation on the OCR button, the device highlights the OCR recognition result of the image a on the device screen and adds a downward line to the recognized preset entity.

The system manages preset entity information, which can be stored in the form of a list. The preset entity may include but is not limited to: name, address, code, ID number, phone number, express number, website, email address, foreign language, Taobao password or Douyin password, etc. The preset entity can be flexibly added, deleted or modified by those skilled in the art.

Please refer to Figure 3 (e) for the interface after the user clicks the OCR button. At this time, the OCR recognition result is highlighted and an underline is added under the preset entity. The characters in the OCR recognition result shown in Figure 3 (e) are selectable, clickable, and copyable.

It should be noted that FIG. 3(e) is only an exemplary method of displaying the OCR recognition result and highlighting the preset entity in the OCR recognition result. In the actual implementation process, those skilled in the art can flexibly set it, and this application does not limit the display method of the OCR recognition result.

For example, in one example, a border is added to the characters in the OCR recognition result to indicate that the OCR recognition result is selectable, clickable, or copyable. In another example, a border can be added to the characters in the OCR recognition result and filled with a background color different from the image background.

The OCR recognition results in Figure 3(e) include three preset entities: "Recipient: xxx", "Tel: 151xxxxxx", and "xx Building, xx Road, Haidian District, Beijing". These three preset entities are underlined to prompt the user which of the preset entities in the OCR recognition results are recognized. It should be noted that Figure 3(e) only uses the example of underlining the preset entities to emphasize the preset entities. In the actual implementation process, the device can display in other preset emphasized display methods. For example, the device can highlight the entity with a color that is different from non-preset entities, or set a background color for the entity that is different from other non-preset entity texts in the OCR recognition results, etc. The present application does not limit the emphasized display method of preset entities in the OCR recognition results.

The entity recognition method can be implemented based on NLU (Natural Language Understanding) technology. The NLU system can be set in the OCR engine or separately in other functional modules. In the embodiment of the present application, the NLU system is set in the OCR engine as an example for explanation.

The NLU system imitates the basic way humans understand language, i.e., sentence segmentation and word segmentation, to divide text into a series of units with semantics and grammar. Of course, some segmentation methods do not conform to human intuition, such as the N-gram algorithm, byte pair encoding and other segmentation methods, and the string units obtained by segmentation are not words. For this reason, the word "token" is usually used to represent the string units obtained by text segmentation.

Based on the token sequence, the NLU system uses a text representation model such as a word vector space model and a distributed representation model to obtain a numerical vector or matrix. This matrix is the numerical representation of the text. Many algorithms in the field of artificial intelligence can only process numerical data. Some algorithms, such as the text similarity calculation method based on the bag-of-words model, can directly process string sequences, and can also deal with text representations in the form of numerical vectors. Therefore, people often use exponential vectors or matrices as a unified text representation form in a system. The NLU system will use classification algorithms, sequence labeling methods, etc. based on the text representation data to calculate the "key information" in the text, such as entities, triples, intentions, events, etc. In the embodiment of the present application, the OCR recognition result can be used as the text to be segmented, and the NLU system can be used to identify the file to be segmented to identify the preset entities contained in the OCR recognition result.

S7: The user clicks to select a single preset entity in the OCR recognition result.

After the OCR recognition result of image a is displayed in the interface, the user can select a preset entity by clicking any position of the preset entity or the corresponding underline of the preset entity.

S8: In response to the selection operation of the preset entity, the device recommends a single application or a service list according to the selected preset entity.

The preset entity selected by the user is the target text selected by the user. When the user selects a single preset entity, the system recommends a single application or service list based on the single preset entity. If the preset entity selected by the user is different, the single application or service list recommended based on the preset entity is different.

The system can pre-set the correspondence between the preset entity and the application, the preset entity and the service list, and the correspondence can be stored in the storage area in the form of a list or other forms. For the convenience of subsequent description, the list can be named as a recommendation rule list. It should be noted that the specific name of the list containing the correspondence between the preset entity and the application, the preset entity and the service list is not limited in the embodiment of the present application. When the system determines the single preset entity selected by the user, it can query the application or service list corresponding to the preset entity selected by the user from the recommendation list for recommendation display.

Please refer to FIG. 4A , which is a schematic diagram of an interface for recommending applications based on a single preset entity. As shown in FIG. 4A (a), the user clicks on the entity “×× Road, ×× Building, Haidian District, Beijing”, and the system determines that the preset entity selected by the user is an address, and searches for the recommended application corresponding to the address from the recommendation rule list. The recommended application is found to be a map application, and the system can select one or more map applications from the map applications installed on the device for recommendation. An exemplary schematic diagram of an interface for displaying a single map application is shown in FIG. 4A (b), where the icon “Map Application A” 401 of a recommended single application is displayed in a floating manner on the right side of the interface. The user can click on “Map Application A” to trigger the system to open Map Application A, and then add “×× Road, ×× Building, Haidian District, Beijing” to Map Application A to view the navigation route. The icon of a single application can be displayed in the form of a floating ball, and the floating ball contains the icon of the recommended application.

When the system determines that a map application needs to be recommended and searches for a map application from the map applications installed in the device for final recommendation, it may randomly select a map application from the map applications installed in the device for final recommendation; it may also select a map application with the highest frequency of use for final recommendation based on the frequency of use of each map application by the user. There is no specific limitation on this in the embodiments of the present application.

It should be noted that FIG. 4A(b) is only an exemplary interface diagram for recommending a single application. The icons of multiple recommended single applications are not limited to being displayed on the right side of the interface, but can also be displayed on the left side, in the middle, or in any other appropriate location. The icons of single applications can also be displayed in the taskbar. For the relevant description of the taskbar, please refer to the relevant introduction to the taskbar when recommending multiple applications below.

Please refer to FIG. 4B, which is another exemplary interface diagram for recommending applications based on a single preset entity. As shown in FIG. 4B (a), the user clicks on the preset entity "Phone: 151xxxxxxx", and the system determines that the preset entity selected by the user is a phone number, and searches for the recommended application corresponding to the phone number from the recommendation rule list, and finds the recommended first service list corresponding to the phone number. The first service list includes: call phone service options, send message service options, add to address book service options, and copy service options. After finding the first service list, the system recommends the first service list in the interface. An exemplary interface diagram for displaying the first service list is shown in FIG. 4B (b). The recommended first service list 402 is displayed in a floating manner on the right side of the interface. The first service list includes: "Call Phone", "Send Message", "Add to Address Book" and "Copy" service options. The user can click on any service option to trigger the system to jump to the target interface corresponding to the service option. The user can manually or the system can automatically add "Phone: 151xxxxxxx" to the target input box in the target interface. The recommended service list can be displayed in the form of a floating window, and the recommended service options are displayed in the floating window.

Figure 4A uses an address in the OCR recognition result of a picture selected by a user to recommend a single map application, and Figure 4B uses a phone number in the OCR recognition result of a picture selected by a user to recommend a first service list as an example. The following is a schematic diagram of an interface for recommending applications based on a Taobao password, with reference to Figure 5, to illustrate the process of the system recommending Taobao applications when a Taobao password in the OCR recognition result of a picture selected by a user.

Please refer to the process of performing OCR recognition on the image in FIG3 . After the OCR engine performs OCR recognition on the image containing the Taobao password “Xixi:/啊FfthxKgYVSh微史高治的光辉岁月全套…更多更多”, as shown in FIG5(a), the OCR recognition result is highlighted in the interface and an underline is added under the preset entity “Xixi:/啊FfthxKgYVSh微史高治的光辉岁月全套…更多更多”. As shown in FIG5(b), the user clicks “Xixi:/啊FfthxKgYVSh微史高治光辉岁月全套…更多更多”, and the terminal receives the instruction that the user has selected “Xixi:/啊FfthxKgYVSh微史高治光辉岁月全套…更多更多”, determines that the target text selected by the user is a Taobao password, searches the list of applications or services corresponding to the Taobao password from the list of recommended rules, and determines that the Taobao password corresponds to the Taobao application through the search. Therefore, the system recommends the Taobao application in the interface. An exemplary interface diagram for displaying the recommended Taobao application is shown in FIG5(c). A “Taobao application” icon is displayed in suspension on the right side of the interface. The user can click the “Taobao application” icon to trigger the system to jump to the Taobao application. The user can manually or the system can automatically add the Taobao password selected by the user to the corresponding interface in the Taobao application.

FIG. 4A, FIG. 4B and FIG. 5 are only exemplary illustrations of the correspondence between three entities and the application or service list. The specific correspondence included in the recommendation rule list can be flexibly set by those skilled in the art. An exemplary correspondence included in the recommendation rule list may include:

The address recommends a single map application, the foreign language recommends a single translation application, the express delivery number recommends shopping applications, the Taobao password recommends Taobao applications, the Douyin password recommends Douyin applications, etc.

The first service list recommended for the phone number may include but is not limited to the service options of "Call Phone", "Send Message", "Add to Contacts" and "Copy". The second service list recommended for the ID card number may include but is not limited to the service options of "Add to Contacts", "Copy", "Share" and "Previous Switch App".

The code may include but is not limited to payment code, identity recognition QR code, etc. The code corresponds to the recommended third service list, which may include but is not limited to: "Open in xxx application", "Open in browser", "Copy link", "Share" and "Add to memo" and other service options. The URL corresponds to the recommended fourth service list, which may include but is not limited to: "Open link", "Add to link list", "Copy link" and "Share" and other service options. The email address corresponds to the recommended fifth service list, which may include but is not limited to: "Create a new email", "Copy" and "Share" and other service options.

The embodiment of the present application provides a method for recommending a list of applications or services based on a single preset entity selected by the user. On the one hand, after the system automatically performs OCR recognition on the text in the image, the OCR recognition result is displayed to the user in a selectable and copyable state. The user can directly select the target text so that the target text can be subsequently added to the corresponding input box in the target application or target service. The user does not need to manually enter the target text, which is convenient to operate and can avoid the problem of user editing errors. On the other hand, after the user selects a single preset entity, the system makes a single application or service list based on the single preset entity selected by the user. The user can jump to the target interface by clicking on the service option in the recommended application or service list. The user does not need to copy the target text and leave the gallery to manually perform tedious operations to enter the target interface.

The following is a description of the process of recommending applications when the target text selected by the user contains multiple preset entities, in conjunction with Figures 7 to 10. Figure 10 is a time sequence flow chart of the interaction between the user and the device when recommending applications based on multiple preset entities in a picture, and the application recommendation process includes the following steps:

S1: The user clicks on image b in the gallery.

S2: In response to clicking on picture b, the device displays picture b on the device screen.

S3: The device detects whether there is text in image b. If there is text, the OCR recognition result of image b is obtained.

S4: If the OCR recognition result of image b is obtained, an OCR button pops up on the device screen.

S5: The user clicks the OCR button.

S6: In response to the click operation on the OCR button, the device highlights the OCR recognition result of the image b on the device screen and adds a downward line to the recognized preset entity.

S1 to S6 shown in Figure 10 are the process of performing OCR recognition on the image b in the gallery, recognizing the preset entity in the OCR recognition result, and displaying the OCR recognition result. For this process, refer to the specific description of S1 to S6 in Figure 6, which will not be repeated here.

S7: Click to select multiple preset entities in the OCR recognition results.

Please refer to FIG. 7 , which is a schematic diagram showing an exemplary interface change when an application is recommended based on multiple associated preset entities selected twice by the user. The schematic diagram of the interface showing picture b is shown in FIG. 7(a). In the interface, the OCR recognition result of picture b is highlighted and underlined under the preset entities "Recipient: xxx", "Tel: 151xxxxxx", and "xx Building, xx Road, Haidian District, Beijing". The user can use his finger to control the cursor on the screen to select multiple preset entities. As shown in FIG. 7(b), there are cursors at the starting position and the ending position of the preset entity selected by the user's finger, and the background fill color of the selected preset entity changes to indicate that the preset entity circled by the cursor has been selected. After the user completes the preset entity selection action, as shown in FIG. 7(b), the system displays a function menu bar, which includes function options such as "Select All", "Cut" and "Copy". The selected target text in FIG. 7(b) can be regarded as the first text.

It should be noted that FIG. 7( b) is only an exemplary method of selecting multiple preset entities. In actual implementation, the user can also select multiple preset entities by clicking on each preset entity in turn within the second preset time. The second preset time is a shorter time, such as 1 second or 1.5 seconds.

S8: In response to the selection operation on the multiple preset entities, the device determines whether the multiple preset entities are combinable.

The system identifies the number of preset entities contained in the target text. When it identifies that the target text contains multiple preset entities, such as two preset entities as shown in FIG7(b), it determines whether the multiple preset entities contained in the target text have an associated relationship. If the determination result is that the target text has an associated relationship, a recommended single application is determined based on each preset entity with an associated relationship. Determining whether the preset entities are combinable is to determine whether the preset entities have an associated relationship. If the multiple preset entities have an associated relationship, it is determined that the preset entities are combinable; otherwise, it is determined that the preset entities are not combinable.

The system stores associations between preset entities, which can be stored in an association list. Each association includes multiple preset entities and the application type recommended by the association. After the system performs preset entity recognition on the target text selected by the user, it determines the N preset entities contained in the target text, searches for associations matching the N preset entities from the association list, and if they exist, determines that the N preset entities are associable preset entities; otherwise, if they do not exist, determines that the N preset entities are non-associable preset entities. Wherein, N is an integer greater than or equal to 2.

The association list can be combined with the recommendation rule list or exist separately. The specific content included in the association list can be flexibly set and modified by those skilled in the art, and there is no specific limitation on this in the embodiments of the present application. For example, the association list may include: the first association: name-phone number-address-shopping application, the second association: name-ID number-ticket swiping applet, etc.

S9: If the multiple entities can be combined, the device recommends a single application based on the combined entity; if the multiple entities cannot be combined, the device recommends a task bar containing multiple applications based on the multiple entities.

When it is determined that the N preset entities included in the target text selected by the user are associable preset entities, the recommended application type corresponding to the association relationship between the N preset entities is searched from the association relationship list. After the application type is determined, a target application can be selected from the applications of the application type installed in the device for recommendation.

The screening rules can be set by those skilled in the art according to actual needs, for example, they can be set to random screening, screening based on application usage frequency, etc.

Continuing to refer to FIG7(c), since the two preset entities "Recipient: xxx" and "Phone: 151xxxxxx" are determined by the system to be preset entities with an associated relationship, it can be determined that these two preset entities correspond to the phone application by searching the associated relationship list, so the system only displays the phone application icon 701 when recommending. The user can click the phone application icon 701 to enter the interface of the phone application and make a call. As shown in FIG7(c), after completing the recommendation of a single application, the target text selected by the user is still highlighted and underlined under the preset entity, so that the user can reselect the preset entity later to trigger the system to make the next round of application recommendations.

After the user selects the two preset entities "Recipient: xxx" and "Tel: 151xxxxxx" to trigger the system to recommend applications, if the user wants to adjust the selected target text to trigger the system to recommend applications again, the user can manually adjust the cursor to adjust the selected target text as shown in FIG7(d), and adjust the selected target text to "Recipient: xxx", "Tel: 151xxxxxx", "xx Building, xx Road, Haidian District, Beijing". During the process of adjusting the selected target text, the last recommended phone application icon 701 disappears. In this specific example, "xx Building, xx Road, Haidian District, Beijing" is the newly added text selected by the user and can be regarded as the second text.

Continuing with reference to FIG7(e), since the three preset entities “Recipient: xxx”, “Tel: 151xxxxxx”, and “xx Building, xx Road, Haidian District, Beijing” are determined by the system to be preset entities with associated relationships, it can be determined that the three preset entities correspond to shopping applications by searching the associated relationship list. Therefore, the system only recommends a single shopping application, such as “Shopping Application B” 701.

As shown in FIG. 7 , the present application provides a method for recommending applications based on multiple associable preset entities. Regardless of whether the user selects 2, 3 or even more preset entities, if the selected preset entities are associable, the system recommends a single application.

The method shown in Figure 7 recommends a single application when it is determined that the target text selected by the user contains multiple associable preset entities. The recommended application has a high degree of match with the user's expectations. The user can directly click the recommended application icon to enter the target application. The user does not need to exit the current interface and then manually search for the target application from the desktop to enter the target application. The operation is convenient.

Please refer to FIG. 8 , which is a schematic diagram showing another exemplary interface change when application recommendations are made based on multiple preset entities selected twice by the user.

The schematic diagram of the interface showing the image b is shown in FIG8(a). In the interface, the OCR recognition result of the image b is highlighted and underlined under the preset entities "Recipient: xxx", "Telephone: 151xxxxxx", and "xx Building, xx Road, Haidian District, Beijing". As shown in FIG8(b), the user selects "Telephone: 151xxxxxx", and "xx Building, xx Road, Haidian District, Beijing" as the target text. After the user completes the action of selecting the preset entity, as shown in FIG8(b), the system displays a function menu bar, which includes function options such as "Select All", "Cut", and "Copy". The selected target text in FIG8 can be regarded as the first text. The device determines that the two preset entities "Telephone: 151xxxxxx" and "xx Building, xx Road, Haidian District, Beijing" are a telephone number and an address, which cannot be associated. The device determines that the telephone number corresponds to a recommended telephone application and the address corresponds to a recommended navigation application. As shown in FIG8(c), the telephone application icon and the navigation application A icon are recommended in the task bar 801. In addition, an add button 802 may be displayed in the task bar 801 . For the description of the add button 802 , please refer to the aforementioned related description, which will not be repeated here.

After the application is recommended, the two preset entities selected by the user, "Telephone: 151xxxxxx" and "XX Building, XX Road, Haidian District, Beijing", remain selected. The user can click the recommended application icon in the taskbar to trigger the system to enter the application corresponding to the selected application icon.

Moreover, after the user selects the two unassociated preset entities "Tel: 151xxxxxx" and "xx Building, xx Road, Haidian District, Beijing" to trigger the system to recommend applications, if the user wants to adjust the selected target text to trigger the system to recommend applications again, the user can manually adjust the cursor to adjust the selected target text as shown in FIG8(d), and adjust the selected target text to "Recipient: xxx", "Tel: 151xxxxxx", "xx Building, xx Road, Haidian District, Beijing". During the process of adjusting the selected target text, the last recommended task bar 801 disappears. In this specific example, "Recipient xxx" is the newly added text selected by the user and can be regarded as the second text.

Continuing with reference to FIG8(e), since the three preset entities "Recipient: xxx", "Telephone: 151xxxxxx", and "xx Building, xx Road, Haidian District, Beijing" are determined by the system to be preset entities with associated relationships, it can be determined that these three preset entities correspond to shopping applications by searching the associated relationship list. Therefore, the system only recommends a single shopping application, such as "Shopping Application B", when recommending.

As shown in FIG8 , the present application provides a method for recommending applications based on multiple associable preset entities. When the multiple preset entities selected by the user are non-associable entities, application recommendations are made based on each selected preset entity. After completing a recommendation, the user can adjust the selected target text. When the adjusted target text contains multiple associable preset entities, the system recommends a single application. It can be seen that when the system recommends applications, it does not only recommend based on the number of preset entities selected by the user, but also considers the associability of the selected preset entities.

Please refer to Figure 9, which is a schematic diagram of the interface changes when an application is recommended based on multiple non-associated preset entities selected twice by the user. Figure 9 takes the picture containing English, Taobao password and address as picture b as an example for explanation. Figures 9(a) to 9(b) show the process of the user selecting multiple preset entities in the displayed OCR recognition results. This process can be referred to the relevant description of Figures 7(a) to (b), and will not be repeated here. In the displayed OCR results, only the preset entities are underlined, and non-preset entities are not underlined. For example, if the "delivery address" in Figure 9(a) is not a preset entity, then these four words will not be underlined.

The user selects three preset entities, "Name: TOM", "Xixi:/啊FfthxKgYVSh微史高治光辉岁月全套…更多更多" and "××路××楼", Haidian District, Beijing". The system determines that these three preset entities are foreign languages, Taobao passwords and addresses. The system matches these three preset entities with the associations stored in the association list. No associations can be matched, so the three preset entities are determined to be non-association preset entities. The system searches the recommendation rule list for the recommended applications corresponding to the foreign languages, which are translation applications, the recommended applications corresponding to the Taobao passwords, which are shopping applications such as Taobao applications, and the recommended applications corresponding to the addresses, which are map applications. The system determines the target applications "translation application A", "map application B" and "shopping application C" from these three types of applications, and generates a task bar 901 containing "translation application A", "map application B" and "shopping application C". The interface diagram showing the task bar is shown in FIG9(c). The order of the application icons recommended in the task bar is consistent with the order of the selected preset entities in the picture. In addition to the recommended multiple applications, the task bar can also include an add button 902.

Accordingly, when the user wants to display application icons of other applications (e.g., translation application B) other than "translation application A", "map application B", and "shopping application C" in the taskbar, the user can click the add button 902. At this time, the taskbar can display "shopping application C", "map application B", and "translation application D" from top to bottom. The user can switch the recommended application icons in the taskbar by clicking the add button 902. The taskbar 901 can also be regarded as a floating window.

It should be noted that, continuing to refer to Figure 9, if only one translation application, one map application and one shopping application are installed in the device, the taskbar may only display icons of one translation application, one map application and one shopping application when recommending applications. Since there are no other applications to switch for recommendation, the add button 902 may not be displayed.

Continuing with reference to FIG9(d), after the user selects the three unrelated preset entities shown in FIG9(c) to trigger the system for application recommendation, if the user wants to adjust the selected target text to trigger the system to re-recommend application, the user can manually adjust the cursor to adjust the selected target text as shown in FIG9(d). The selected target text is adjusted to "Delivery address: xx Building, xx Road, Haidian District, Beijing". During the process of adjusting the selected target text, the last recommended task bar 901 disappears. The system recommends map application B based on the target text "Delivery address: xx Building, xx Road, Haidian District, Beijing" adjusted by the user.

In the application recommendation method shown in FIG9 , after the user selects the target text from the image OCR recognition result to trigger the system to recommend an application once, the user can also adjust the selected target text to trigger the system to recommend an application again. During the adjustment of the selected target text, the previous application recommendation information disappears. It should be noted that the above is only explained by adjusting the target text once. In the actual implementation process, the user can adjust the target text twice or even more times, and each adjustment of the target text can trigger the system to recommend applications again.

In the embodiment of the present application, the control corresponding to the taskbar is located at the top layer of the screen, so that the recommended application list can be prevented from being covered by other interfaces on the device screen, affecting the subsequent operation of selecting an application from the recommended application list.

It should be understood that the above method of determining the recommended application list according to the target text content is only an illustrative example, and the embodiment of the present application does not limit the specific method of determining the recommended application list according to the target text content.

The method shown in Figure 9 recommends multiple applications when it is determined that the target text selected by the user contains multiple non-related preset entities. The recommended applications are strongly associated with the preset entities selected by the user, and a task bar containing multiple applications is provided for the user to choose. After the user determines the target application from the multiple recommended applications, he or she can directly click on the corresponding application icon to enter the target application. The user does not need to exit from the current interface and then manually search for the target application from the desktop to enter the target application. The operation is convenient.

The following is a description of the process of recommending applications when the target text selected by the user does not contain a preset entity, in conjunction with Figures 11 and 12. Figure 12 is a time sequence flow chart showing the interaction between the user and the device when recommending applications based on image content. The application recommendation process includes the following steps:

S1: The user clicks on image c in the gallery.

S2: In response to clicking on picture c, the device displays picture c on the device screen.

S3: The device detects whether there is text in the image c. If there is text, the OCR recognition result of the image c is obtained.

S4: If the OCR recognition result of the image c is obtained, an OCR button pops up on the device screen.

S5: The user clicks the OCR button.

S6: In response to the click operation on the OCR button, the device highlights the OCR recognition result of the image c on the device screen.

S1 to S6 shown in Fig. 12 are the process of performing OCR recognition on the picture c in the gallery and displaying the OCR recognition result. For this process, please refer to the specific description of S1 to S6 in Fig. 6, which will not be repeated here.

S7: The user selects and copies target text in the OCR recognition result.

Please refer to Figure 11, which is an exemplary diagram of an interface for recommending applications based on a picture that does not contain a preset entity. The interface diagram showing picture c is shown in Figure 11(a), in which the OCR recognition result of picture c "The main function of a mobile phone is communication, which facilitates communication between people. Today's smart phones also have entertainment, navigation, shopping and other functions" is highlighted. Since the OCR recognition result does not contain a preset entity, no characters are underlined.

FIG11(b) shows the process of the user selecting the target text from the displayed OCR recognition results. The relevant description of the process can be referred to the relevant description in FIG11(b), which will not be repeated here. As shown in FIG11(c), the user clicks the "Copy" option in the function menu bar to select the target text circled by the cursor. The system receives the user's click operation on the "Copy" option and copies the target text selected by the user.

S8: In response to the operation of copying the target text, the device recognizes that the target text does not contain a preset entity.

The method of identifying whether the target text contains the preset entity can be referred to the relevant description under S6 in Figure 6, which will not be repeated here.

S9: The device extracts features of the target text, matches multiple applications based on the extracted features, and displays a task bar including the multiple applications.

An exemplary method of matching multiple applications based on extracted features is: predicting the extracted text features based on the application classification model, and the prediction result is the score corresponding to each application classification. The higher the score, the higher the matching degree between the extracted text features and the application classification. According to the predicted scores corresponding to each application classification, the first application classification with the highest score and the second application classification with the second highest score are selected. It is judged whether the number of applications under the first application classification installed in the device is greater than the first preset number, such as 3. If so, the first preset number of applications are screened out from the first application classification as the applications to be recommended. If not, all the applications contained in the first application classification are used as the applications to be recommended under the first application classification. It is judged whether the number of applications under the second application classification installed in the device is greater than the second preset number, such as 2. If so, the second preset number of applications are screened out from the second application classification as the applications to be recommended under the second application classification. If not, all the applications contained in the second application classification are used as the applications to be recommended under the second application classification. Finally, the applications to be recommended under the first application classification and the applications to be recommended under the second application classification are used as recommended applications, and a task bar containing recommended application icons is displayed. The application classification can be flexibly set by those skilled in the art, and no specific restrictions are made in the embodiments of the present application. For example, application categories may include: video applications, social applications, map applications, and shopping applications, etc.

Wherein, the first preset number is greater than the second preset number. When filtering the applications to be recommended from the first application category, the applications under the first application category can be sorted according to conditions such as the frequency of application use by the user within a preset time period, currently activated applications, etc., and the first preset number of applications ranked first are selected as the applications to be recommended. Similarly, the applications to be recommended can be filtered from the second application category.

Continuing to refer to FIG. 11 , the system determines to recommend shopping applications and social applications based on the target text selected by the user, "The main function of a mobile phone is communication, which facilitates people's communication. Today's smart phones also have entertainment, navigation, shopping and other functions." Since the shopping applications installed in the device only include shopping application B, and the social applications installed in the device only include social applications A and C, when recommending applications, as shown in FIG. 11 (d), icons of shopping application B, social application A and social application C are displayed in the task bar 1101. In addition to the icons of multiple recommended applications, the task bar 1101 also includes an add button 1102. For the introduction of the task bar 1101 and the add button 1102, please refer to the above-mentioned related descriptions, which will not be repeated here.

It should be noted that, if it is determined that the first preset number of social applications as the first application category is 3, and the second preset number of shopping applications as the second application category is 2, there are 3 social applications A, C and D installed in the device, and shopping applications B and E are installed in the device, then when recommending applications, the social applications A, C and D and shopping applications B and E are recommended applications. Since the number of application icons displayed in the taskbar is limited, only some of the icons of the recommended applications may be displayed, and the rest are hidden. After the user clicks on the add button 1102, they are displayed one by one.

It should be noted that the above embodiment is only described by taking the example that the user selects the target text in the image OCR recognition result, and the system recommends applications based on the target text selected by the user. In the actual implementation process, the user can also select, copy and click on the text content in the memo, short message and other interfaces to trigger the system to recommend applications based on the target text selected by the user.

It is understandable that, in order to realize the above functions, the electronic device includes hardware and/or software modules corresponding to the execution of each function. In combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application in combination with the embodiments, but such implementation should not be considered to be beyond the scope of the present application.

Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here.

This embodiment also provides a computer storage medium, in which computer instructions are stored. When the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned related method steps to implement the application recommendation method in the above-mentioned embodiment.

This embodiment also provides a computer program product. When the computer program product runs on a computer, it enables the computer to execute the above-mentioned related steps to implement the application recommendation method in the above-mentioned embodiment.

Among them, the electronic device, computer storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above and will not be repeated here.

Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

Any content of each embodiment of the present application, as well as any content of the same embodiment, can be freely combined. Any combination of the above content is within the scope of the present application.

Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented with hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein the communication media include any media that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that a general or special-purpose computer can access.

The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims (15)

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

Responding to a first operation of a user on a first text in a first application, and identifying a preset entity contained in the first text;

under the condition that a preset entity is contained in the first text, determining information to be recommended based on the preset entity contained in the first text;

under the condition that the first text does not contain a preset entity, determining information to be recommended based on the content of the first text, wherein the information to be recommended comprises: an application icon or a list of services;

Displaying a first icon in a display interface of the first application, wherein the first icon corresponds to the information to be recommended;

Under the condition that the first text contains a preset entity, determining the information to be recommended based on the preset entity contained in the first text comprises the following steps:

determining a second application or service list matched with a preset entity under the condition of a single preset entity contained in the first text;

determining whether the plurality of preset entities can be combined or not based on an association relationship list under the condition that the first text contains the plurality of preset entities; the association list comprises association relations among preset entities;

Determining a third application based on the preset entities under the condition that the preset entities can be combined;

And respectively determining fourth applications matched with the included preset entities under the condition that the preset entities cannot be combined.

2. The method of claim 1, wherein prior to the responding to the first user operation on the first text at the first application, the method further comprises:

responding to a second operation of a user on the picture in the first application, and displaying the picture in a display interface of the first application;

identifying whether the picture contains text;

Performing OCR (optical character recognition) on the picture to obtain a second text under the condition that the picture comprises the text;

displaying a first button, wherein the first button is used for triggering the display of the second text;

And responding to a third operation of the first button by a user, and highlighting the second text in the display interface, wherein the second text comprises the first text.

3. The method of claim 1, wherein determining information to be recommended based on the content of the first text without including a preset entity in the first text comprises:

extracting features of the first text under the condition that a preset entity is not included in the first text;

Determining a first application classification and a second application classification for the first text match based on the extracted features;

screening a first preset number of fifth applications from the first application classification;

screening a second preset number of sixth applications from the second application classification;

and the fifth application and the sixth application are determined to be information to be recommended.

4. The method of claim 1, wherein the first icon comprises: a floating ball or a floating window.

5. The method of claim 1, wherein the preset entity comprises: address, code, identification number, telephone number, courier number, web address, mailbox address, foreign language, panning password, or shaking password.

6. An application program recommending method applied to an electronic device is characterized by comprising the following steps:

displaying the first text and the second text on a display interface of the first application;

Responding to a first operation of a user on the first text, and displaying a first icon corresponding to a second application on the display interface, wherein the first icon is obtained according to text analysis of the first text;

responding to a second operation of the user on the first icon, and displaying an interface of the second application corresponding to the first icon;

when detecting that a user executes a third operation on the second text, canceling displaying the first icon in the display interface;

Responding to a third operation of the user on the first text and the second text, and displaying a second icon corresponding to a third application on the display interface, wherein the second icon is obtained according to text analysis of the first text and the second text;

Responding to a fourth operation of the user on the second icon, and displaying an interface of the third application corresponding to the second icon;

The method for displaying the first icon corresponding to the second application on the display interface in response to the first operation of the user on the first text comprises the following steps:

Responding to the selection operation of a user on the first text, and displaying a suspension ball corresponding to a second application on a display interface of the first application, wherein the first text comprises a plurality of combinable preset entities, and the suspension ball comprises a first icon corresponding to the second application;

Or responding to the selection operation of the user on the first text, displaying a floating window on a display interface of the first application, wherein the first text comprises a plurality of uncombinable preset entities, the floating window comprises a plurality of application icons, and the plurality of application icons at least comprise first icons corresponding to the second application.

7. The method according to claim 6, wherein:

The first text includes: plain text or picture OCR recognizes the resulting text.

8. The method of claim 7, wherein prior to displaying the first text and the second text on the display interface of the first application, the method further comprises:

Responding to a fifth operation of a user on a picture in a first application, and displaying the picture in a display interface of the first application;

displaying a first button under the condition that the picture comprises texts, wherein the first button is used for triggering and displaying a first text and a second text obtained by OCR recognition of the picture;

The displaying the first text and the second text on the display interface of the first application includes:

In response to a sixth operation of the first button by the user, highlighting the first text and the second text in the display interface, wherein the sixth operation includes at least: clicking.

9. The method of claim 8, wherein highlighting the first text and the second text in the display interface comprises:

Highlighting the first text and the second text in the display interface, and displaying an underline under the first text and the second text, wherein the first text and the second text are preset entities, and the preset entities comprise: address, code, identification number, telephone number, courier number, web address, mailbox address, foreign language, panning password, or shaking password.

10. The method of claim 6, wherein the method further comprises:

Responding to seventh operations of the user on the third text and the second text, and displaying a first icon corresponding to the second application and a third icon corresponding to the fourth application on the display interface; the first text comprises the third text, and the first icon and the third icon are obtained according to text analysis of the first text and the third text;

responding to eighth operation of the user on the third icon, and displaying an interface of the fourth application corresponding to the third icon;

Responding to a third operation of the user on the first text and the second text, and displaying a second icon corresponding to a third application on the display interface, wherein the second icon is obtained according to text analysis of the first text and the second text;

And responding to a fourth operation of the user on the second icon, and displaying an interface of the second application corresponding to the first icon.

11. The method of claim 9, wherein displaying a first icon corresponding to a second application on the display interface in response to a first operation of the first text by a user comprises:

And responding to clicking operation of the user on the first text, and displaying a suspension ball on the display interface, wherein the suspension ball comprises a first icon of a second application obtained by text analysis of the first text.

12. The method of claim 9, wherein displaying a first icon corresponding to a second application on the display interface in response to a first operation of the first text by a user comprises:

and responding to clicking operation of the user on the first text, displaying a floating window on the display interface, wherein the floating window comprises service options obtained by text analysis of the first text, and the service options at least comprise service options corresponding to the second application.

13. The method of claim 6, wherein displaying a first icon corresponding to a second application on the display interface in response to a first operation of the first text by a user comprises:

And responding to the copying operation of the user on the first text, displaying a floating window on a display interface of the first application, wherein the floating window comprises a plurality of application icons, and the plurality of application icons comprise first icons corresponding to the second application.

14. The method of claim 6, wherein the second operation comprises: single click, double click, long press.

15. A computer readable storage medium comprising a computer program, characterized in that the computer program, when run on an electronic device, causes the electronic device to perform the application recommendation method according to any one of claims 1-14.