CN115016710B - App Recommendation Method - Google Patents

Abstract

The application program recommending method is provided. The method comprises the following steps: the electronic equipment responds to a first operation of a user on a first picture in a first application, a first icon is displayed in a first area of the first application, and the first icon is an application icon of a second application; responding to a second operation of a user on a second picture in the first application, and displaying a second icon for character recognition in a second area of the first application; responding to a third operation of the user on the second icon, displaying a third icon in a third area of the first application, wherein the third icon is an application icon of the third application; and responding to a fourth operation of the user on the third picture in the second application, and displaying a fourth icon in a fourth area of the second application. According to the application program recommending method, the electronic equipment can conduct application recommending based on the text contained in the picture, the user does not need to exit from the current 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

App Recommendation Method

technical field

The present application relates to the field of terminal equipment, and in particular to a method for recommending application programs.

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 have the need to view pictures and even extract text from pictures. For example: when viewing a food picture shared by a friend in Moments of a social application, the food picture contains the address of the store, and the user wants to extract the address of the store and view the specific location of the store in a navigation application. At this time, the user needs to exit Moments, search for navigation applications from a large number of applications on the main interface, and then open a navigation application found and manually enter the store address. The operation process is cumbersome and time-consuming, and the user experience is poor.

Contents of the invention

The present application provides an application recommendation method, which can perform OCR recognition on pictures, and recommend applications to users based on the OCR recognition results, without requiring users to manually search for target applications from a large number of applications installed in electronic devices, which can improve user experience.

In some embodiments, the electronic device can determine based on the scene where the picture is located to recommend an application after active OCR of the picture, or whether the user triggers the application recommendation after OCR of the picture. It is only necessary to search for the target application in the application, and the user does not need to manually search for the target application from a large number of application programs installed in the electronic device, which can improve user experience. In the second aspect, after the user selects the target application, the text can be extracted from the OCR recognition result and pasted into the target application, without the user needing to manually enter the text. In the third aspect, the electronic device determines whether to actively perform OCR on the picture according to the scene where the picture is located, instead of blindly performing OCR on the picture for application recommendation, which can avoid the problem of disturbing users due to blind recommendation.

In a first aspect, the present application provides an application recommendation method applied to an electronic device, wherein the method includes: the electronic device responds to the user's first operation on the first picture in the first application, such as clicking, selecting, or copying, etc., The first icon is displayed in the first area of the first application, and the first icon is the application icon of the second application, wherein the first picture contains the first text; wherein, the first area can be displayed in the form of a sidebar or an application list Displaying the first icon; the electronic device displays the second icon in the second area of the first application in response to the user's second operation on the second picture in the first application, such as clicking, copying or selecting, and the second icon is text recognition icon, wherein the second picture contains the second text, the second icon is the OCR button hereinafter, and text recognition can also be referred to as performing OCR on the picture; the electronic device responds to the user's third operation on the second icon, such as clicking, Long press and other operations will display a third icon in the third area of the first application, the third icon is the application icon of the third application, and the second application is different from the third application; where in the third area, you can use the sidebar or The third icon is displayed in the form of an application list; the electronic device displays the fourth icon in the fourth area of the second application in response to the user's fourth operation on the third picture in the second application, such as clicking, selecting, or copying. The icon is the application icon of the fourth application, wherein the first picture contains the first text, and the fourth area can display the third icon in the form of a sidebar or an application list, the first application is different from the second application, and the fourth The application is different from the second application and the third application.

In this application recommendation method, the electronic device can determine the application recommendation after the active OCR of the image based on the scene where the image is located, or the application recommendation after the user triggers the OCR of the image. Find the target application in a large number of applications, the operation is convenient and can save the time spent on application search. And it will not blindly and actively perform OCR on pictures to recommend applications, which can avoid disturbing users.

According to the application program recommendation method of the first aspect, the electronic device displays the first icon in the first area of the first application in response to the user's first operation on the first picture in the first application, including: the electronic device responds to the user's first operation on the first application The first operation of the first picture in an application displays the first icon in the first area of the first application, and highlights the first text included in the first picture. This way of highlighting the first text can prompt the user that the OCR recognition has been completed, and the displayed first text can be selected, copied or selected.

According to the first aspect, or any implementation manner of the above first aspect, the displaying the first icon in the first area of the first application by the electronic device in response to the user's first operation on the first picture in the first application includes: In response to the user's click operation on the first picture in the chat interface of the communication application, the device displays the first picture in full screen, and displays a sidebar in the first picture, and the sidebar includes the first icon of the second application . The sidebar can be displayed at any appropriate position in the interface, for example: the left side of the interface, the right side of the interface, and so on. The pictures in the chat interface of communication applications are pictures posted by users actively. Such pictures have a high probability of containing useful information. Therefore, when users view pictures, they actively perform OCR on the pictures and recommend applications without the need for users to manually trigger OCR. The operation is convenient and can improve the user experience.

According to the first aspect, or any implementation manner of the above first aspect, when the first text contains an address, the electronic device displays a map application icon, a shopping application icon, and a taxi application icon in the sidebar. With this type of recommendation rule, the recommended application matches the user's expectations with a high degree of matching, which is convenient for the user to quickly find the target application.

According to the first aspect, or any implementation of the above first aspect, when the first text contains a phone number, the electronic device displays a service list in the sidebar, and the service list includes: call options, send messages option, Add to Contacts option, and Copy option. This way of recommending the service list in the sidebar provides multiple service options associated with the phone number for the user to choose, which is convenient for the user to quickly find the target application.

According to the first aspect, or any implementation manner of the above first aspect, the displaying the second icon in the second area of the first application by the electronic device in response to the user's second operation on the second picture in the first application includes: electronically In response to the user's click operation on the second picture in the subscription account of the communication application, the device displays the second picture in full screen; in response to the user's long press operation on the second picture, the device displays the second Two icon. The duration of the long press operation can be flexibly set by those skilled in the art, and there is no specific limitation here, for example, it is set to 2 seconds, 1.5 seconds or 1 second. The pictures in the subscription account of the communication application are not pictures posted by the user actively. The probability of such pictures containing useful information is low. OCR can avoid disturbing users by blindly performing OCR on pictures for application recommendation.

According to the first aspect, or any implementation of the above first aspect, the electronic device responds to the user's third operation on the second icon, and displaying the third icon in the third area of the first application includes: the electronic device responds to the user The click operation on the second icon displays the third icon in the third area of the second picture. By clicking the second icon, the user can trigger the electronic device to perform OCR on the picture, and recommend applications based on the OCR recognition result, which is convenient to operate.

According to the first aspect, or any implementation manner of the above first aspect, the electronic device responds to the user’s fifth operation on the fourth picture in the first application, such as clicking, long pressing, and two-finger clicking, etc., in the first application The second icon is displayed in the fifth area of , and the second icon is an icon for character recognition, wherein the fourth picture contains the third text; in response to the user's sixth operation on the second icon, the electronic device highlights the fourth picture containing of the third text. In this application recommendation method, after actively performing OCR on the picture, the application is recommended based on the OCR recognition result, that is, the third text, which is convenient for the user to find the target application to be switched, and the OCR recognition result is highlighted to remind the user of the picture. OCR has been completed, and operations such as copying, selecting, and clicking can be performed on the OCR recognition result.

In a second aspect, the present application further provides an application recommendation method applied to an electronic device, the method comprising: the electronic device receives a user's first operation on a picture in the first interface of the first application; in response to the first operation, parsing the second The location mark of the picture; determine the scene type corresponding to the picture according to the parsed position mark, wherein the scene type includes: a high probability scene and a low probability scene; when the scene type is a high probability scene, OCR is performed on the picture, and based on The OCR recognition result is used for application recommendation; in the case that the scene type is a low-probability scene, after receiving the second operation of triggering OCR by the user, OCR is performed on the picture.

In this application program recommendation method, on the one hand, since the application recommendation will be performed, the user only needs to find the target application from the recommended applications, and the user does not need to manually search for the target application from a large number of application programs installed in the electronic device, which can improve user experience. In the second aspect, the electronic device determines whether to actively perform OCR on the picture according to the scene where the picture is located, instead of blindly performing OCR on the picture for application recommendation, which can avoid the problem of disturbing users due to blind recommendation.

According to the application program recommendation method of the first aspect, the electronic device determines the probability type corresponding to the picture according to the position mark, including: the electronic device compares the position mark with the position mark of the high-probability scene pre-stored in the database; In the case of the target position mark, it is determined that the scene type corresponding to the picture is a high-probability scene. The location mark can include the application mark and the interface mark, and the method of determining the probability type corresponding to the picture through the position mark has a small amount of calculation and high accuracy.

According to the first aspect, or any implementation method of the above first aspect, performing OCR on the picture by the electronic device, and recommending an application program based on the OCR recognition result includes: performing OCR on the picture by the electronic device to obtain the OCR recognition result; determining the OCR recognition Whether the preset entity is included in the result; in the case that the preset entity is included in the OCR recognition result, determine the application recommendation information matched by the included preset entity, wherein the recommendation information includes: at least one application or service list, in the service list Include at least one service option; display recommended information on the enlarged image, and highlight OCR recognition results. The preset entities can be flexibly set and pre-stored in the system by those skilled in the art, and the preset entities at least include: phone numbers, addresses, and password-like texts. The application recommendation method recommends applications for users based on preset entities, and the recommended applications have a high degree of matching with the applications that users expect to find.

According to the first aspect, or any implementation manner of the above first aspect, after the electronic device determines whether the OCR recognition result contains the preset entity, the method further includes: the electronic device does not contain the preset entity in the OCR recognition result In this case, the electronic device highlights the OCR recognition result on the enlarged picture. This method of highlighting the OCR recognition result can, on the one hand, prompt the user that the OCR has been completed, and on the other hand, prompt the user to perform operations such as copying, selecting, and clicking on the OCR recognition result.

According to the first aspect, or any implementation of the above first aspect, when the scene type is a low-probability scene, after the electronic device receives the second operation of triggering OCR by the user, performing OCR on the picture includes: When the type is a low-probability scene, the electronic device enlarges and displays the picture, and does not actively perform OCR on the picture; when receiving the third operation of the user on the picture, such as a long press operation, a sliding operation, or a double-click operation, display the first button , wherein the first button is used to trigger the OCR of the picture; it is judged whether a fourth operation on the first button is received within the first preset duration, wherein the fourth operation at least includes: clicking; within the first preset duration When the fourth operation on the first button is received, OCR is performed on the picture; application program recommendation is performed based on the OCR recognition result. This method in which the user actively triggers the OCR of the image is easy to operate.

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

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

Description of drawings

FIG. 1 is a schematic diagram of a hardware structure of an exemplary electronic device;

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

FIG. 3 is a schematic diagram of an interface for recommending applications after active OCR of pictures in the chat interface;

FIG. 4 is a schematic diagram of an interface for recommending applications after actively OCRing pictures in Moments;

FIG. 5 is another schematic diagram of an interface for recommending applications after actively OCRing pictures in Moments;

FIG. 6 is a schematic diagram of another interface for recommending applications after active OCR of pictures in the chat interface;

Fig. 7 is an exemplary interface diagram showing a process of viewing pictures in a subscription account;

FIG. 8A is an exemplary interface diagram for recommending applications after passive OCR of pictures in a subscription account;

Fig. 8B is another schematic diagram of an interface for recommending applications after passive OCR of pictures in the subscription account;

FIG. 9 is an exemplary flow chart showing the interaction between the user and the device when recommending applications based on pictures;

FIG. 10 is a schematic flowchart of an exemplary application recommendation method;

FIG. 11 is a flow chart of an exemplary active OCR triggering process and a passive OCR triggering process.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.

The term "and/or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations.

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, the first target object, the second target object, etc. are used to distinguish different target objects, rather than describing a specific order of the target objects.

In the embodiments of the present application, words such as "exemplary" or "for example" are used as examples, illustrations or illustrations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application shall not be interpreted as being more preferred or more advantageous than other embodiments or design schemes. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete manner.

In the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more. 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 will distinguish the triggering mode of Optical Character Recognition (OCR) according to the different scenes of the picture being viewed. One way is that the electronic device actively performs OCR on the picture , another way is to passively perform OCR on the picture by the electronic device, and the OCR recognition result is displayed on the picture, and can be directly selected, clicked, copied, etc. Whether to actively perform OCR on the picture depends on the source of the picture. If the picture is a picture actively pushed by the user in a communication application (such as a picture in the chat interface, a picture dynamically shared in Moments, etc.), the picture will be judged when viewing the picture. Originated from high-probability scenes, it actively performs OCR recognition on pictures. Except for pictures in high-probability scenes, pictures in other scenes are passively recognized by OCR.

After OCR is performed on the picture, no matter it is active OCR or passive OCR, the system can analyze the OCR recognition result to determine whether the OCR recognition result contains preset entities, and if so, recommend applications based on the included preset entities.

The method for recommending an application program in the embodiment of the present application may be applied to a scenario where text contained in a picture in one application of the same electronic device is extracted into another application.

In an example, the scenario may be, for example, extracting text from an OCR recognition result of a picture into an application. Among them, the picture can come from a gallery, a real-time screenshot, a browser, an email, a communication application such as WeChat, QQ, and the like. The embodiment of this application does not limit the source of the picture. Operations on text extraction may include but not limited to: copy and paste, select and paste automatically, or select and paste manually.

For example, a photo of a courier is displayed on the chat interface of a social application, and the photo contains address information, 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 may be applied to extract the address information in the photo into the delivery address of the shopping application.

It should be noted that the above examples are only schematic descriptions of application scenarios of the embodiments of the present application. The embodiment of the present application does not limit the source application of the picture (that is, the application containing the picture) and the destination application (that is, the application that needs to paste the target text selected by the user).

Herein, an application program may be simply referred to as an application.

The application interaction method in the embodiments of the present application may be applied to electronic devices. The electronic device may be, for example, a mobile phone, a tablet, and the like. The following takes the electronic device 100 as an example to describe the hardware structure and software structure of the electronic device to which the application interaction method in the embodiment of the present application is applied.

FIG. 1 is a schematic structural diagram 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, and two or more components may be combined , or can 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 (universal serial bus, USB) interface 130, a charging management module 140, a power management module 141, and a battery 142 , antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, earphone jack 170D, sensor module 180, button 190, motor 191, indicator 192, camera 193 , a display screen 194, and a subscriber identification module (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, bone conduction sensor 180M, etc.

The software system of the electronic device 100 may adopt a layered architecture, an event-driven architecture, a micro-kernel architecture, a micro-service architecture, or a cloud architecture. In this embodiment of the present application, the software structure of the electronic device 100 is exemplarily described by taking an Android system with a layered architecture as an example.

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

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

The application layer can consist of a series of application packages.

As shown in Figure 2, the application package of the application layer may include applications such as sensors, cameras, image galleries, OCR engines, application recommendations, third-party applications, and screenshots.

Wherein, the OCR engine is used to perform OCR on the picture to obtain an OCR recognition result of the picture, and the OCR recognition result includes text information from the picture that can be selected and copied. The picture may be a screenshot 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 picture.

The application recommendation is used to predict an application related to the OCR recognition result according to the OCR recognition result, and recommend the predicted application to the user. Third-party applications are used to provide pictures or provide text information that can be selected and copied. In an optional embodiment, the application program layer may further include an application interaction module, configured to perform related operations of pasting text content into the target application.

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

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

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

The resource manager provides various resources for the application, such as localized text strings, icons, pictures, layout files, video files, and so on.

A window manager is used to manage window programs. The window manager can obtain the size of the display screen, 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 program and the navigation fallback function, and is responsible for creating the main thread of Android and maintaining the life cycle of each application program.

Android runtime includes core library and virtual machine. The Android runtime is responsible for the scheduling and management of the Android system.

The core library includes two parts: one part is the function function that the java language needs to call, and the other part is the core library of Android (Android).

The application layer and the application framework layer run in virtual machines. The virtual machine executes the java files of the application program layer and the application program 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 (surface manager) and the like.

The surface manager is used to manage the display subsystem and provides 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 drivers and sensor drivers.

It can be understood that the layers in the software structure shown in FIG. 2 and the components included 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, and each layer may include more or fewer components, which is not limited in the present application.

For the convenience of description, the electronic device will be referred to as a device for short in the following text. It should be understood that the electronic devices mentioned herein can all have the same hardware structure (such as the hardware structure shown in FIG. 1 ) and the same software structure (such as the software structure shown in FIG. structure).

In the application recommendation method provided by the embodiment of this application, no matter where the video is viewed by the user, such as a video in an album, a video in an application, or an advertisement video, etc., it is prohibited to trigger OCR for the video viewed by the user. Prohibiting triggering OCR includes prohibiting Actively perform ORC on it, and prohibit passive OCR on it, that is, the user triggers the device to perform OCR on it. For the picture viewed by the user, it is first necessary to determine whether the picture contains text. If the picture does not contain text, there will be no OCR result even after ORC, so OCR will not be triggered. For a picture containing text, it is determined whether the picture is in a low-probability scene or a high-probability scene based on the interface where the picture is located. The high-probability scene actively performs OCR on the picture, and the low-probability scene passively performs OCR on the picture. For the determination rules of high and low probability, please refer to the subsequent related instructions. For example, in communication applications, for pictures actively promoted by users, it can be judged as high probability scenes when viewing pictures. This is because the pictures posted by the user have a higher probability of containing useful information, and the user has a higher probability of extracting text from them. Therefore, OCR is actively performed on it without waiting for the user to trigger OCR, which can save time and reduce operation steps. Regardless of the system's active OCR or passive OCR, the text in the image will be analyzed during the OCR process of the image to find out whether the text contains preset entities such as addresses, phone numbers, or passwords, and apply them if they are included Recommendation, if not included, no application recommendation will be made. When recommending an application, an application icon or a service list may be recommended, and the service list includes multiple service options.

The application recommendation method in the embodiment of the present application will be described below in conjunction with the flowchart of interaction between the user and the device when the application recommendation based on pictures is exemplarily shown in FIG. 9 . As shown in FIG. 9 , the application recommendation method may include Follow the steps below:

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

The pictures can come from a gallery, real-time screenshots, browsers, emails, and communication applications such as WeChat, QQ, etc. In this embodiment of the application, there is no limitation on the source of the pictures, and the APP is an application program. After the device receives the user's operation of clicking the picture in the APP, it will display the clicked picture in full screen or enlarged.

The user's click on the picture may include: single click, double click, or two-finger click, etc., which is not specifically limited here. In addition, in addition to clicking on the picture, the device can also be triggered to execute S2 through operations such as long pressing and sliding.

S2: Analyze the position mark of the clicked picture, compare it with the position mark of the database, and distinguish high and low probability scenes.

The application recommendation method in the embodiment of this application is implemented by three parts: device-side input, application program framework, and device-side output. The device-side input and device-side output mainly perform interaction with users and interface display, and the application program framework performs application recommendation. For the convenience of subsequent reading, the three parts are collectively referred to as devices in this embodiment.

The location flag is used to indicate the xx interface in the xx application, and the location flag may include an application identifier and an interface identifier. After the device receives the picture of the APP clicked by the user, it determines the application opened in the foreground and the currently displayed interface, and can analyze the position mark of the picture based on the determined application and interface information.

The position mark corresponding to the pre-stored high-probability scene in the database, after parsing the position mark of the clicked picture, compare it with the pre-stored position mark in the database, if there is a position in the database that matches the parsed position mark flag, it is determined that the current scene of the picture is a high-probability scene; if there is no position mark matching the parsed position mark in the database, it is determined that the current scene of the picture is a low-probability scene.

The location markers corresponding to the high-probability scenes prestored in the database can be flexibly set by those skilled in the art, and this is not specifically limited in this embodiment of the present application. For example, it can be set as a high-probability scene for an interface where the user can actively push pictures under the communication application, such as a chat interface, a dynamic sharing interface, and the like. User active push does not only refer to users of this electronic device, but also includes users of other electronic devices. For example: friends in the user's communication software can be regarded as users.

S3: Generate a determination result.

Judgment results include: high-probability scenarios and low-probability scenarios. If the judgment result is a high-probability scene, perform active OCR on the picture and the application recommendation branch, and directly jump to S6 to execute S6 and subsequent steps; if the judgment result is a low-probability scene, perform passive OCR on the picture OCR and application recommendation branches are S4-S7.

S4: In a low-probability scenario, the user presses and holds the picture for 2 seconds, and the system pops up the OCR button.

It should be noted that the duration of the long press on the picture is not limited to 2s, and the specific value can be flexibly set by those skilled in the art, such as 3 seconds or 1.5 seconds. The OCR button can also be called the first button. After the OCR button is clicked by the user, the system can be triggered to perform OCR on the picture.

The operation that triggers the pop-up OCR button of the system is not limited to long press on the picture, but can also include but not limited to: press with two fingers; click on the picture N times in a row within the preset duration, where N is greater than or equal to 2 or slide the preset track in the picture, etc. .

If the device does not detect the operation of clicking the OCR button within the first preset period of time after the OCR button pops up on the screen, it can be confirmed that the user does not need to perform OCR on the picture to trigger the system to recommend an application. At this time, the device may actively stop displaying the OCR button on the device screen, that is, the OCR recognition button disappears from the image interface. The first preset duration can be flexibly set by those skilled in the art, for example, set to 2 seconds, 3 seconds, 5 seconds, etc., which is not specifically limited in this embodiment of the present application.

In an exemplary implementation process, if the user does not need to OCR trigger the system to recommend applications for pictures, the user can also click any place other than the OCR button in the current interface. At this time, the device detects that the user clicks any place other than the OCR button, and may stop displaying the OCR button on the device screen. In this way, the device passively stops displaying the OCR button based on user actions.

Of course, in another exemplary implementation process, if the user does not require the OCR triggering system to recommend applications for pictures, the device may also keep the OCR button in the off state.

The style of the OCR button can be flexibly set by those skilled in the art, and is not specifically limited in this embodiment of the present application. An exemplary display manner of the OCR button may be that the OCR button pops up and is grayed out, and the user clicks the OCR button and cancels the graying, so that the user can distinguish whether the OCR button is selected.

S5: the user clicks the OCR button.

The click operation for OCR may include but not limited to: single click, double click, etc. Clicking is merely an example of an operation for selecting the OCR button, and a long-press operation may also be performed in an actual implementation process.

S6: OCR is performed on the picture, and the text contained in the picture is recognized.

S5-S6 is the process that the system performs OCR recognition on the picture after the user clicks the OCR button. This process can avoid the problem of blindly OCRing pictures and occupying device processing resources. In the actual implementation process, it is also possible to perform OCR recognition on the picture in the background after receiving the user's click operation on the picture, and the OCR button will still pop up after the recognition. OCR can directly display the pre-recognized OCR results, and the response speed is fast.

S7: Generate and analyze the image OCR recognition result.

The recognition result of the OCR recognition of the picture is the text contained in the picture. After the recognition is completed, the text is highlighted on the picture displayed in full screen. Push application information in the sidebar when the highlighted text contains preset entities. In the case where the highlighted text does not contain preset entities, it is not recommended to apply the information. The pushed application can be displayed in the form of a floating ball, a floating window, a sidebar, or an application list, and the pushed application information can be an application icon or a service list, and the service list includes multiple service options.

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

The recommendation applications corresponding to different preset entities are different, and the recommendation rules can be flexibly set by those skilled in the art. An exemplary list of recommendation rules can include:

Addresses recommend map apps, shopping apps, and taxi apps; foreign languages recommend single translation apps, courier tracking numbers recommend shopping apps, Taobao passwords recommend Taobao apps, Douyin passwords recommend Douyin apps, etc.

The phone number corresponds to the recommended first service list, which may include but not limited to: "call phone", "send message", "add to address book" and "copy" service options. The ID card number corresponds to the recommended second service list, which may include but not limited to "add to address book", "copy", "share" and "previous switching application" service options.

Codes may include but not limited to payment codes, identification QR codes, etc. Codes correspond to the recommended third service list, which may include but not limited to: "open in xxx app", "open in browser", "copy link" , "Share" and "Add to Notes" and other service options. The URL corresponds to the recommended fourth service list, which may include but 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 not limited to: service options such as "create email", "copy" and "share".

In an exemplary display mode, an underline is added below the preset entity, and the user clicks on the underlined preset entity or the underline below it to select the preset entity, which is convenient to operate.

The highlighted text on the picture is selectable, clickable, and copyable, and users can extract all or part of the text content from it.

The branch of actively performing OCR on pictures and recommending applications will be described below with reference to FIGS. 3 to 6 .

FIG. 3 is a schematic diagram of an interface that exemplarily shows an interface for recommending applications after active OCR of pictures in a chat interface.

As shown in Figure 3(a), when user A, that is, "I", clicks picture a in the chat interface of a communication application, the device analyzes the location marker of picture a, and compares the location marker with the high-probability location markers managed in the database. Yes, it is determined that the position marker of the picture a is within the high-probability position markers managed by the database, and it is determined to perform active OCR on the picture a. After performing active OCR on picture a, the OCR recognition result is "XX Park, ×× Road, Haidian District, Beijing". As shown in Figure 3(b), after picture a is enlarged and displayed, the OCR recognition result "XX Park, ×× Road, Haidian District, Beijing" is highlighted.

It should be noted that FIG. 3( b ) is only an exemplary way of highlighting the OCR recognition result in a highlighted form. In the actual implementation process, those skilled in the art can flexibly set, and there is no specific limitation on the manner of highlighting the OCR recognition result.

For example, in one example, a border may be 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 frame may be added to the characters in the OCR recognition result and the frame may be filled with a background color different from that of the picture background.

The device actively performs OCR recognition on the picture a to get the text "×× Park, Haidian District ×× Road, Beijing". After analyzing the recognized text, it is determined that the text is an address belonging to a preset entity. From the list of recommended rules preset in the system The recommended applications corresponding to the search address are map applications, shopping applications, and taxi-hailing applications, and map applications, shopping applications, and taxi-hailing applications are recommended in the sidebar.

The system respectively determines the target applications "map application A", "shopping application B" and "taxi application C" from these three types of applications, and generates the target application including "map application A", "shopping application B" and "taxi application C". The taskbar 301 of the class application C" icon, and the schematic diagram of the interface displaying the taskbar is shown in FIG. 3( b ). In addition to including multiple recommended application icons, the task bar may also include an add button 302 . The user can click any application icon recommended in the taskbar to trigger the system to open the interface of the second application corresponding to the clicked application icon. After the interface of the second application is displayed, the user can manually drag the recognized address "Beijing Haidian District ×× Road ×× Park" to navigate in the interface of the second application. After displaying the interface of the second application, the system may automatically navigate the recognized address "XX Park, ×× Road, Haidian District, Beijing" to the interface of the second application. Wherein, the task bar may also be called a side bar or an application list.

Correspondingly, when wanting to display application icons of other applications (such as map application D) other than "map application A", "shopping application B" and "taxi application C" in the task bar, the user can click The button 302 is added. At this time, the task bar may display "shopping application B", "taxi-hailing application C" and "map application D" in sequence from top to bottom. The user can switch the recommended application icons in the taskbar by clicking the add button 302 . The task bar 301 can also be regarded as a floating window, and the floating window can be regarded as the first icon.

It should be noted that if only one map application, one shopping application, and one taxi application are installed on the device, the taskbar may only display one map application, one shopping application, and one taxi application when recommending applications. icon, since there is no other application to switch to the recommendation, the add button 302 may not be displayed.

In the embodiment of the present application, the control corresponding to the task bar is located at the top of the screen, so that the recommended application list can be prevented from being covered by other interfaces on the device screen, which will affect the subsequent operation of selecting an application icon from the recommended application list.

It should be understood that the above method of determining the recommended application list based on the address obtained after the active OCR of the picture is only a schematic example. The display position of is not specifically limited.

As shown in Figure 3, the method of actively recommending applications after OCR of images does not require users to manually trigger the OCR process to actively recommend applications for users. Since applications are recommended for users, users do not need to search for targets from a large number of applications on the desktop. The application is easy to operate and saves time spent on searching for applications.

Fig. 4 is an exemplary diagram showing an interface for recommending applications after actively OCRing pictures in the circle of friends, wherein the circle of friends in the communication application can be regarded as a dynamic sharing interface.

As shown in Figure 4(a), when the user "I" clicks on the picture b shared by myself in the circle of friends of the communication application, the device analyzes the location mark of the picture b, and compares the location mark with the high-probability position mark managed in the database. After comparison, it is determined that the location marker of picture b is within the high-probability location marker managed by the database, and it is determined to perform active OCR on picture b. After performing active OCR on picture b, the OCR recognition result is "Xixi:/ah FfthxKgYVSh Wei Shi Gaozhi's glory days full set...more information". As shown in Figure 4(b), after picture b is displayed in full screen, the OCR recognition result "Xixi:/ah FfthxKgYVSh Wei Shi Gaozhi's glory days full set... more information" is highlighted.

The device recognizes that the OCR recognition result is a Taobao password, finds the application corresponding to the Taobao password from the preset recommendation rules as the Taobao password, and generates a task bar 401 containing the icon of "Taobao application", and the schematic diagram of the interface showing the task bar is shown in Figure 4 ( c) as shown. In addition to the recommended "Taobao application" icon, the taskbar may also include an add button 402 . The user can click the "Taobao application" icon to trigger the system to open the Taobao application and enter the main interface of the Taobao application.

For the taskbar and the function of the add button 402 in the taskbar, please refer to the relevant description in FIG. 3 , which will not be repeated here.

It should be noted that adding the recommended application icon to the sidebar for recommendation in FIG. 4(c) is just an example. In actual implementation, the recommended application icon can also be in the form of a floating ball or a floating window. No matter the sidebar, floating ball or floating window can be regarded as a display area. In the embodiment of the present application, no specific limitation is imposed on the display position, size, and shape of the display area.

As shown in Figure 4, the method of actively recommending applications after OCR of images does not require users to manually trigger the OCR process to actively recommend applications for users. Since applications are recommended for users, users do not need to search for targets from a large number of applications on the desktop. The application is easy to operate and saves time spent on searching for applications.

FIG. 5 is an exemplary schematic diagram of another interface for recommending applications after active OCR of pictures in the circle of friends.

As shown in Figure 5(a), when the user clicks on the picture c shared by the friend "Contact B" in the circle of friends of the communication application, the device analyzes the position mark of the picture c, and compares the position mark with the high probability position managed in the database. The marks are compared to determine that the position mark of the picture c is within the high-probability position marks managed by the database, and it is determined to perform active OCR on the picture c. After performing active OCR on picture c, the OCR recognition result is "Xixi:/ah FfthxKgYVSh Wei Shi Gaozhi's glory days full set...more information". As shown in Figure 5(b), after picture b is displayed in full screen, the OCR recognition result "Xixi:/ah FfthxKgYVSh Wei Shi Gaozhi's glory days full set... more information" is highlighted, and the recommended one is displayed in the task bar 501 “Taobao application” icon and add button 502 . The user can click the "Taobao application" icon to trigger the system to open the Taobao application and enter the main interface of the Taobao application.

For the relevant description of how the device determines the recommended Taobao application, task bar and add button according to the OCR recognition result, please refer to the relevant description in FIG. 4 , and will not repeat them here.

As shown in Figure 5, after recognizing that the user is in the communication application, the user actively pushes the picture, and then actively recommends the application after OCR. The user does not need to manually trigger the OCR process to actively recommend applications for the user. The application is selected, so there is no need for the user to search for the target application from a large number of applications on the desktop, the operation is convenient and the time spent on application search can be saved.

Figures 3-5 are all schemes for recommending applications based on the preset entities contained in the OCR recognition results when the OCR recognition results of the pictures contain preset entities such as passwords and addresses after active OCR of the pictures. In the actual application process, after actively performing OCR recognition on the picture, the OCR recognition result may not contain the preset entity. In this case, no application recommendation will be performed. The situation will be described below with reference to FIG. 6 .

FIG. 6 is a schematic diagram of an interface for recommending applications after actively OCRing pictures in a chat interface.

As shown in Figure 6(a), when the user clicks on the picture d in the chat interface of the communication application, the device analyzes the position mark of the picture d, compares the position mark with the high-probability position mark managed in the database, and determines the position mark of the picture d The location markers of are within the high-probability location markers managed by the database, and it is determined to perform active OCR on the picture d. After active OCR of picture d, the OCR recognition result is "the main function of the mobile phone is communication, which is convenient for people to communicate. Today's smart phones also have entertainment, navigation, shopping and other functions." As shown in Figure 6(b), after picture b is displayed in full screen, the OCR recognition result "The main function of the mobile phone is communication, which is convenient for people to communicate. Today's smart phones also have entertainment, navigation, shopping and other functions" are highlighted, No app recommendations.

The full-screen display of picture d in Figure 6(b) is just an example of zooming in on picture d. In actual implementation, picture d can also be enlarged by a preset multiple, so that the enlarged picture d does not occupy the entire screen. It should be noted that, in FIG. 6 , it is only an example that when the picture in the chat interface does not contain a preset entity, although the OCR is actively performed, no application recommendation is performed. The rule of not recommending an application when it is determined that the OCR recognition result does not contain a preset entity is also applicable to the application recommendation of active OCR pictures in other scenarios and the application recommendation of passive OCR pictures.

As shown in Figure 6, after recognizing that the user is actively pushing the picture in the communication application, after actively performing OCR, since the OCR recognition result does not contain the preset entity, in order to avoid blindly recommending the application to interfere with the user, it is not performed. App recommendations. However, since the text in picture d has been OCRed, the OCR result shown in picture d can be copied and selected, and users can extract text from the displayed OCR recognition results according to their needs. The extracted text can be directly pasted into the target application opened by the user, without the need for the user to manually enter the text information, which is convenient and time-saving.

The branch of passively performing OCR on pictures and recommending applications will be described below with reference to FIG. 7 to FIG. 8 .

Fig. 7 is an exemplary interface diagram showing a process of viewing pictures in a subscription account. Fig. 8A is a schematic diagram of an interface for recommending applications after passive OCR of pictures in a subscription account; Fig. 8B is an example of another interface for recommending applications after passive OCR of pictures in a subscription account Interface diagram.

In this example, when viewing a picture in a subscription account, the passive OCR branch of the picture is triggered as an example. There are many scenarios corresponding to the passive OCR of the picture. For example, when the user clicks to view the picture in the browser, the passive OCR of the picture is triggered. The passive OCR of the image is triggered when the image in the file is triggered, and the passive OCR of the image is triggered when the user views the image in the file, etc., except for the high-probability scene pre-stored in the device database, other scenes are regarded as low-probability scenes. enumerate.

As shown in Figure 7(a), the main interface of the subscription number information contains multiple subscription numbers such as "Tiantongyuan Culture and Art Center", "Supermarket Fat Life", etc., and the user clicks the picture e under "Supermarket Fat Life" to enter the "Supermarket Fat Life" In the "Private Kitchen Express - High Soup Noodles" column in the subscription account, you have successfully entered the subscription account at this time.

After entering the subscription account, when the user clicks to view the picture e, the device receives the user's click operation on the picture e, and the device analyzes the position mark of the picture e, compares the position mark with the high-probability position mark managed in the database, and determines the position mark of the picture e. The position mark is not in the high-probability position marks managed by the database, and it is determined to perform passive OCR on the picture e. Therefore, when the user clicks on the picture e, the picture e is enlarged and displayed without OCR. At this time, the enlarged picture e The text "Noodle Soup" in is in a state that cannot be selected, copied, or clicked. As shown in Figure 7(f), when the user wants to perform OCR on the picture e, he can press and hold any area in the picture, the trigger system will display the OCR button 801 as shown in Figure 8A(a), and the user can click the OCR button Step 801 triggers the device to perform OCR on the picture e, and after performing OCR on the picture e, the device highlights the OCR result "Noodles in Broth", and a schematic diagram of the interface displaying the OCR result is shown in Figure 8A(b). The selection operation of the OCR button is not limited to the click shown in FIG. 8A(a), but may also include but not limited to: long press, two-finger click or slide operation, etc., which is not specifically limited in this embodiment of the present application.

The OCR button is used to trigger the device to perform OCR on the picture. It should be noted that the OCR button shown in the drawings of the embodiment of the present application is only an example, and the style, display position and size of the OCR button are not specifically limited in the embodiment of the present application. Since the OCR recognition result of picture e is "Noodles in Soup" which does not belong to preset entities such as passwords, addresses, or phone numbers, the device does not recommend applications for "Noodles in Soup" based on the OCR recognition result. Correspondingly, in 8A Application recommendation information is not displayed in the interface shown in (b).

FIG. 8B is a schematic diagram of another interface for recommending applications after passive OCR of pictures in the subscription account.

Take the picture e viewed by the user in the subscription account as the picture shown in Figure 8B(a) as an example, the user enters the subscription account to view the picture e according to the process shown in Figure 7, and presses and holds the enlarged picture e. , the device displays the OCR button floating on the picture e. After the user clicks the OCR button, the device is triggered to perform OCR on the picture e. After the device performs OCR on the picture e, the OCR result is highlighted, "noodle shop phone: 151xxxx", and the interface with the OCR result The schematic diagram is shown in Fig. 8B(b). The device conducts text analysis on the OCR result "noodle shop phone: 151xxxx", determines that the OCR result is a phone number, compares it with the preset entities stored in the system, determines that the phone number is a preset entity, and further determines the phone number according to the recommendation rules The recommended information corresponding to the number is the first service list 802, and the first service list 802 is displayed on the enlarged picture e, and the interface displaying the first service list is shown in FIG. 8B(b). Include in the first service list 802: Include in the first service list: " call phone 151xx ", " send message ", " add to address book " and " copy " service option, show that first service list 80 users can click any A service option triggers the system to jump to the target interface corresponding to the service option, and the user can manually or automatically add the phone number "151xxxx" to the target input box in the target interface. The recommended service list may be displayed in the form of a floating window, and each recommended service option is displayed in the floating window. The duration of the long press on the enlarged picture e can be flexibly set by those skilled in the art, and is not specifically limited in this embodiment of the present application. For example: set to 2s, 3s or 1.5s, etc.

It should be noted that the recommended applications, service lists and other recommended information displayed in the drawings of the embodiments of the present application are schematic examples, and specific rules for application recommendation based on OCR recognition results can be flexibly preset by those skilled in the art in in the device. As shown in Figure 7-8, when it is recognized that the user is viewing a picture that is not a communication application, when the user actively pushes the picture, the device passively performs OCR on the picture, and the user manually controls the device to perform OCR on the picture, which can prevent the device from blindly Actively performing OCR on pictures to recommend apps interferes with users. When the user subjectively wishes to perform OCR on the picture, the user performs operations such as long pressing the picture or clicking the OCR button to trigger the device to perform OCR on the picture and recommend applications based on the OCR recognition results. The user does not need to exit the current application from the main interface. Finding the target application among a large number of applications displayed in , the operation is convenient and can save the time spent in finding the target application, and can prompt the user experience.

The flow of the application program recommendation method according to the embodiment of the present application will be described below with reference to FIG. 10 and FIG. 11 . Wherein, FIG. 10 is a schematic flowchart of an exemplary application recommendation method; FIG. 11 is an exemplary flowchart of an active OCR triggering process and a passive OCR triggering process.

As shown in FIG. 10 , the process of the application recommendation method mainly includes: the device receives an operation triggered by the user to view pictures, wherein the operation triggered to view pictures may include but not limited to: single-click operation, double-click operation, etc. on the picture. The device analyzes the position mark of the viewed picture, and the device compares the parsed position mark with the position mark of the high-probability scene pre-stored in the database, and determines the probability category for the user to perform OCR on the picture. Among them, the probability category includes: high probability and low probability.

When it is determined that the probability category for the user to perform OCR on the picture is high probability, zoom in on the picture and actively perform OCR on the picture, and highlight the OCR recognition result in the enlarged picture. The device recommends applications based on the OCR recognition results, and the application recommendation process ends. For a specific manner of recommending an application based on the OCR recognition result, refer to the above-mentioned related content in the embodiment, and details will not be repeated here.

When it is determined that the probability category of the user performing OCR on the picture is low probability, it is determined to perform passive OCR on the picture. The passive OCR process is: zoom in on the picture, and display the OCR button when receiving the user's long press operation on the picture; determine whether the user triggers OCR button, if yes, in response to the operation of the user triggering the OCR button, OCR is performed on the picture, the OCR recognition result is highlighted, and the application recommendation is made according to the OCR recognition result; if the user does not receive the user triggering the OCR button within the first preset time period operation to end the application recommendation process.

The method of determining whether to perform active OCR or passive OCR on a picture according to the position mark of the picture provided by the embodiment of the present application can avoid blindly performing OCR on the picture and recommending an application program, causing interference to the user.

FIG. 11 exemplarily shows a flowchart of an active OCR triggering process and a passive OCR triggering process. The two triggering processes will be described below with reference to FIG. 11 .

As shown in Figure 11, the active OCR triggering process includes: the device responds to the operation of clicking the picture, displays the picture in full screen, and after performing OCR on the picture, highlights the text in the picture, which is the OCR recognition result. When the OCR recognition result contains address, phone number or password text, a side application bar will pop up to recommend related applications. When the OCR recognition result does not contain the preset entity, that is, when the OCR recognition result is ordinary text, no application recommendation is made.

The passive OCR triggering process includes: displaying the picture in full screen in response to the operation of clicking the picture. When the user clicks on the picture, the picture will be restored to its original size without triggering OCR. The user presses and holds the picture for 2 seconds to trigger OCR, and the OCR button pops up on the side of the screen. When the user clicks the OCR button, the device performs OCR recognition on the picture, and the highlighted text in the picture is the OCR recognition result. When the OCR recognition result contains address, phone number or password text, a side application bar will pop up to recommend related applications. When the OCR recognition result does not contain the preset entity, that is, when the OCR recognition result is ordinary text, no application recommendation is made.

It can be understood that, in order to realize the above functions, the electronic device includes hardware and/or software modules corresponding to each function. Combining 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 certain function is executed by hardware or computer software drives hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions in combination with the embodiments for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

Wherein, all relevant content of each step involved in the above-mentioned method embodiment can be referred to the function description of the corresponding function module, and will not be repeated here.

This embodiment also provides a computer storage medium, the computer storage medium stores computer instructions, and when the computer instructions are run on the electronic device, the electronic device executes the above-mentioned related method steps to implement the application program recommendation method in the above-mentioned embodiment .

This embodiment also provides a computer program product, which, when running on a computer, causes the computer to execute the above-mentioned related steps, so as to realize the screen recording method in the above-mentioned embodiment.

Wherein, the electronic device, computer storage medium, computer program product or chip provided in this embodiment is all used to execute the corresponding method provided above, therefore, the beneficial effects it can achieve can refer to the corresponding method provided above The beneficial effects in the method will not be repeated here.

Through the description of the above embodiments, those skilled in the art can understand that for the convenience and brevity of the description, only the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned functions can be assigned by different Completion of functional modules means that the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

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

A unit described as a separate component may or may not be physically separated, and a component shown as a unit may be one physical unit or multiple physical units, which may be located in one place or distributed to multiple different places. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this 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 contents is within the scope of the present application.

Those skilled in the art should be aware that, in the foregoing one or more examples, the functions described in the embodiments of the present application may be implemented by hardware, software, firmware or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

The embodiments of the present application have been described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementations. The above-mentioned specific implementations are only illustrative and not restrictive. Those of ordinary skill in the art will Under the inspiration of this application, without departing from the purpose of this application and the scope of protection of the claims, many forms can also be made, all of which belong to the protection of this application.

Claims (14)

1. A method for recommending an application program, applied to an electronic device, characterized in that it comprises: In response to the user's first operation on the first picture in the first application, determine the application opened in the foreground of the electronic device and the currently displayed interface; According to the interface information of the application opened in the current foreground and the currently displayed interface, analyze the position mark of the first picture, the position mark includes the application mark and the interface mark; Determine the scene type corresponding to the first picture according to the position mark of the first picture, wherein the scene type includes: a high probability scene and a low probability scene; When the scene type corresponding to the first picture is a high-probability scene, OCR is performed on the first picture, and a first icon is displayed in a first area of the first application based on an OCR recognition result, and the first icon is displayed in the first area of the first application. An icon is an application icon of the second application, wherein the first picture contains the first text; In response to the user's seventh operation on the second picture in the first application, determine the application opened in the foreground of the electronic device and the currently displayed interface; Analyzing the position mark of the second picture according to the interface information of the currently opened application in the foreground and the currently displayed interface; determining the scene type corresponding to the second picture according to the position mark of the second picture; In the case that the scene type corresponding to the second picture is a low-probability scene, in response to the user's second operation on the second picture in the first application, a second icon is displayed in the second area of the first application, so The second icon is an icon for text recognition, wherein the second picture contains a second text; In response to a third operation performed by the user on the second icon, a third icon is displayed in a third area of the first application, where the third icon is an application icon of a third application, where the second application is the same as the said third application is different; In response to the user's fourth operation on the third picture in the second application, a fourth icon is displayed in a fourth area of the second application, and the fourth icon is an application icon of the fourth application, wherein the third The picture includes third text, wherein the first application is different from the second application, and the fourth application is different from the second application and the third application. 2. The method according to claim 1, wherein the step of displaying the first icon in the first area of the first application in response to the user's first operation on the first picture in the first application, include: In response to the user's first operation on the first picture in the first application, the first icon is displayed in the first area of the first application, and the first text included in the first picture is highlighted. 3. The method according to claim 1, wherein the step of displaying the first icon in the first area of the first application in response to the user's first operation on the first picture in the first application, include: In response to the user's click operation on the first picture in the chat interface of the communication application, the first picture is displayed in full screen, and a sidebar is displayed in the first picture, and the sidebar includes the second picture. The first icon of the application. 4. The method according to claim 3, characterized in that: When the first text contains an address, the displayed sidebar includes a map application icon, a shopping application icon, and a taxi application icon. 5. The method according to claim 3, characterized in that: In the case that the first text contains a phone number, the displayed sidebar includes a service list, and the service list includes: an option to call a phone, an option to send a message, an option to add to an address book, and an option to copy. 6. The method according to claim 1, wherein the step of displaying a second icon in the second area of the first application in response to the user's second operation on the second picture in the first application, include: In response to the user's click operation on the second picture in the subscription account of the communication application, displaying the second picture in full screen; In response to the user's long press operation on the second picture, a second icon is displayed in a floating manner in the second area of the second picture. 7. The method according to claim 6, wherein the step of displaying the third icon in the third area of the first application in response to the third operation of the second icon by the user comprises: In response to a user's click operation on the second icon, a third icon is displayed in a third area of the second picture. 8. The method of claim 3, wherein, In response to the user's fifth operation on the fourth picture in the first application, a second icon is displayed in the fifth area of the first application, the second icon is an icon for character recognition, wherein the fourth picture contains third text; In response to a sixth user operation on the second icon, the third text contained in the fourth picture is highlighted. 9. A method for recommending an application, applied to an electronic device, comprising: receiving a user's first operation on the picture in the first interface of the first application; In response to the first operation, determine the application opened in the foreground of the electronic device and the currently displayed interface; According to the interface information of the application currently opened in the foreground and the currently displayed interface, analyze the position mark of the picture, the position mark includes the application mark and the interface mark; Determining the scene type corresponding to the picture according to the position mark, wherein the scene type includes: a high probability scene and a low probability scene; When the scene type is a high-probability scene, OCR is performed on the picture, and an application program recommendation is performed based on the OCR recognition result; In a case where the scene type is a low-probability scene, OCR is performed on the picture after receiving a second operation of triggering OCR by the user. 10. The method according to claim 9, wherein the step of determining the probability type corresponding to the picture according to the location marker comprises: Comparing the position mark with the position mark of the high probability scene pre-stored in the database; If there is a target position marker matching the position marker, it is determined that the scene type corresponding to the picture is a high-probability scene. 11. The method according to claim 9, wherein the step of performing OCR on the picture and recommending an application based on the OCR recognition result comprises: Performing OCR on the picture to obtain an OCR recognition result; Determine whether the OCR recognition result contains a preset entity; In the case that the OCR recognition result contains a preset entity, determine the application recommendation information matched by the preset entity, wherein the recommendation information includes: at least one application or service list, and the service list contains at least one service options; The recommendation information is displayed on the enlarged image, and the OCR recognition result is highlighted. 12. The method of claim 11, further comprising: If the OCR recognition result does not contain a preset entity, the OCR recognition result is highlighted on the enlarged image. 13. The method according to claim 9, wherein when the scene type is a low-probability scene, after receiving the second operation of triggering OCR by the user, the step of performing OCR on the picture comprises: In the case that the scene type is a low-probability scene, zoom in and display the picture; In the case of receiving a third user operation on the picture, displaying a first button, wherein the first button is used to trigger OCR on the picture, wherein the third operation includes at least: long press; judging whether a fourth operation on the first button is received within the first preset time period; In the case that a fourth operation on the first button is received within the first preset duration, OCR is performed on the picture; App recommendation based on OCR recognition results. 14. A computer-readable storage medium, comprising a computer program, characterized in that, when the computer program is run on an electronic device, the electronic device is made to execute the application according to any one of claims 1-13 Program recommended method.

Images