CN108304104B

CN108304104B - Data acquisition method and equipment, storage medium and terminal thereof

Info

Publication number: CN108304104B
Application number: CN201711000155.5A
Authority: CN
Inventors: 龙振海; 张锦建; 邓衍; 罗俊; 谢建平
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2017-10-24
Filing date: 2017-10-24
Publication date: 2022-01-28
Anticipated expiration: 2037-10-24
Also published as: CN108304104A

Abstract

The embodiment of the invention discloses a data acquisition method and equipment, a storage medium and a terminal thereof, wherein the method comprises the following steps: acquiring an icon image carrying a target application icon in a current display page of a target terminal; identifying a target application identifier corresponding to a target application icon in the icon image based on a preset icon identification model; and searching and acquiring application data corresponding to the target application identifier, and installing the target terminal application indicated by the target application identifier based on the application data. By adopting the method and the device, the terminal application in the target terminal can be downloaded and installed in the data acquisition equipment by identifying and analyzing the application icon in the target terminal, and the recovery efficiency of the terminal application can be improved.

Description

Data acquisition method and equipment, storage medium and terminal thereof

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a data acquisition method, a device thereof, a storage medium, and a terminal.

Background

With the rapid development of internet technology, terminal devices such as smart phones and tablet computers are updated more and more quickly, and when a user starts to use a new terminal device, the user is usually accustomed to using a terminal application that is used in an old device all the time, so that the related application in the old device needs to be transmitted to the new device or downloaded again in the new device. In the prior art, data transmission between new and old devices can be realized through a near field communication technology, and related applications in the old devices are recovered in the new devices. However, when the device does not support near field communication, it takes a long time to download and install the relevant application in the old device in the new device by a conventional manner (for example, manually inputting an application name to download and install a terminal application), which affects the recovery efficiency of the application.

Disclosure of Invention

Embodiments of the present invention provide a data acquisition method and device, a storage medium, and a terminal, which can download and install a terminal application in a target terminal in a data acquisition device by identifying and analyzing an application icon in the target terminal, and can improve recovery efficiency of the terminal application.

A first aspect of an embodiment of the present invention provides a data acquisition method, which may include:

acquiring an icon image carrying a target application icon in a current display page of a target terminal;

identifying a target application identifier corresponding to a target application icon in the icon image based on a preset icon identification model;

and searching and acquiring application data corresponding to the target application identifier, and installing the target terminal application indicated by the target application identifier based on the application data.

In a possible design, before obtaining an icon image carrying a target application icon in a current display page of a target terminal, the method further includes:

carrying out icon recognition training on an initial recognition model by adopting training application icons corresponding to training application identifications in an application icon training set to obtain model parameters corresponding to the initial recognition model;

adding the model parameters to the initial recognition model to generate a trained preset icon recognition model;

and acquiring training pixel point parameters corresponding to the training application identifications based on the training application icons and the preset icon recognition model.

In a possible design, the obtaining an icon image carrying a target application icon in a current display page of a target terminal includes:

acquiring an effective page image carrying a target application icon in a current display page of a target terminal by using a camera;

performing icon area division processing on the effective page image according to the distribution mode of each application icon in the effective page image to obtain each icon area corresponding to each application icon after the icon area division processing;

and acquiring an icon image carrying the target application icon in the target icon area according to a preset icon acquisition rule.

In a possible design, the obtaining, by using a camera, an effective page image corresponding to a currently displayed page of a target terminal includes:

acquiring a current page image carrying a target application icon in a current display page of a target terminal by using a camera;

acquiring the total height of the page of the current page image and the first height of a page prompt bar in the current display page;

intercepting an effective page image indicated by a second page height in the current page image;

and the second page height is the page height left after the first height of the page prompt bar is removed from the total page height.

In one possible design, the truncating the effective page image indicated by the second page height in the current page image includes:

intercepting an effective page area indicated by a second page height in the current page image, and acquiring each application icon in the effective page area;

acquiring a first comparison application icon and a second comparison application icon from application icons in a history effective page image, wherein the first comparison application icon and the second comparison application icon are respectively any one of two corresponding boundaries in the history effective page image, and the corresponding relation of the two corresponding boundaries is associated with the page sliding direction;

identifying each application icon in the effective page area according to the preset icon identification model;

and when the first comparison application icon and the second comparison application icon do not appear in each application icon in the effective page area, determining the effective page area as an effective page image corresponding to the current display page.

In one possible design, the identifying, based on a preset icon recognition model, a target application identifier corresponding to a target application icon in the icon image includes:

and matching target application icons in the icon images by adopting various training application icons in a preset icon recognition model, and determining a training application identifier corresponding to the training application icon with the highest matching degree with the target application icon as a target application identifier corresponding to the target application icon.

In one possible design, the matching, by using each training application icon in a preset icon recognition model, a target application icon in the icon image, and determining a training application identifier corresponding to a training application icon with a highest matching degree with the target application icon as a target application identifier corresponding to the target application icon includes:

acquiring target pixel point parameters in the target application icon, and matching the target pixel point parameters with training pixel point parameters of training application icons corresponding to training application identifications in a preset icon recognition model;

acquiring a matching degree set of training pixel point parameters of training application icons corresponding to the training application identifications and the target pixel point set;

when a first matching degree which is greater than or equal to a preset matching degree threshold value exists in the matching degree set, acquiring a training application icon corresponding to a training pixel parameter indicated by the highest matching degree in the first matching degree, and determining a training application identifier corresponding to the training application icon as a target application identifier corresponding to the target application icon.

In one possible design, further comprising:

and when all the matching degrees in the matching degree set are smaller than the preset matching degree threshold value, adding the target application icon into the application icon training set.

A second aspect of an embodiment of the present invention provides a data acquisition device, which may include:

the image acquisition module is used for acquiring an icon image carrying a target application icon in a current display page of the target terminal;

the identification recognition module is used for recognizing a target application identification corresponding to a target application icon in the icon image based on a preset icon recognition model;

and the application installation module is used for searching and acquiring application data corresponding to the target application identifier and installing the target terminal application indicated by the target application identifier based on the application data.

In one possible design, further comprising:

the parameter acquisition module is used for carrying out icon recognition training on the initial recognition model by adopting the training application icons corresponding to the training application identifications in the application icon training set so as to acquire model parameters corresponding to the initial recognition model;

the model generation module is used for adding the model parameters into the initial recognition model so as to generate a trained preset icon recognition model;

and the pixel parameter acquisition module is used for acquiring training pixel point parameters corresponding to the training application identifications based on the training application icons and the preset icon recognition model.

In one possible design, the image acquisition module includes:

the effective image acquisition unit is used for acquiring an effective page image carrying a target application icon in a current display page of the target terminal by adopting a camera;

the area acquisition unit is used for dividing the effective page image into icon areas according to the distribution mode of each application icon in the effective page image and acquiring each icon area corresponding to each application icon after the icon area division processing;

and the image acquisition unit is used for acquiring the icon image carrying the target application icon in the target icon area according to a preset icon acquisition rule.

In one possible design, the effective image acquisition unit includes:

the current image acquisition subunit is used for acquiring a current page image carrying a target application icon in a current display page of the target terminal by adopting a camera;

the height obtaining subunit is used for obtaining the total page height of the current page image and the first height of a page prompt bar in the current display page;

the image intercepting subunit is used for intercepting an effective page image indicated by a second page height in the current page image;

In one possible design, the image capture subunit is specifically configured to: intercepting an effective page area indicated by a second page height in the current page image, and acquiring each application icon in the effective page area;

In one possible design, the identification module is specifically configured to:

In one possible design, the identification recognition module includes:

the pixel matching unit is used for acquiring target pixel point parameters in the target application icon and matching the target pixel point parameters with training pixel point parameters of training application icons corresponding to training application identifications in a preset icon recognition model;

a set obtaining unit, configured to obtain a matching degree set between a training pixel parameter of a training application icon corresponding to each training application identifier and the target pixel set;

and the identifier determining unit is used for acquiring a training application icon corresponding to a training pixel parameter indicated by the highest matching degree in the first matching degrees when the first matching degree which is greater than or equal to a preset matching degree threshold exists in the matching degree set, and determining a training application identifier corresponding to the training application icon as a target application identifier corresponding to the target application icon.

In one possible design, further comprising:

A third aspect of embodiments of the present invention provides a computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the following steps:

A fourth aspect of an embodiment of the present invention provides a terminal, which may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the steps of:

In the embodiment of the invention, the icon image carrying the target application icon in the current display page of the target terminal is obtained, the target application identifier corresponding to the target application icon in the icon image is identified based on the preset icon identification model, the application data corresponding to the target application identifier is searched and obtained, and then the target terminal application indicated by the target application identifier is installed based on the application data. By identifying the application icon in the target terminal and analyzing the application data corresponding to the application icon in the target terminal, the downloading and installation of the relevant terminal application in the target terminal are realized in the data acquisition equipment, and the recovery efficiency of the terminal application is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.

Fig. 1 is a schematic flow chart of a data acquisition method according to an embodiment of the present invention;

fig. 2a and fig. 2b are schematic structural diagrams of a page display effect according to an embodiment of the present invention;

FIG. 3 is a schematic flow chart of another data acquisition method provided by the embodiment of the invention;

FIG. 4 is a schematic flow chart diagram of another data acquisition method provided by the embodiment of the invention;

FIG. 5 is a schematic flow chart diagram of another data acquisition method provided by the embodiment of the invention;

6 a-6 c are schematic structural diagrams of another page display effect provided by the embodiment of the invention;

FIG. 7 is a schematic flow chart diagram of another data acquisition method provided by the embodiment of the invention;

fig. 8 is a schematic structural diagram of a data acquisition device according to an embodiment of the present invention;

FIG. 9 is a schematic structural diagram of another data acquisition device provided in an embodiment of the present invention;

FIG. 10 is a schematic structural diagram of an image acquisition module provided in an embodiment of the present invention;

FIG. 11 is a schematic structural diagram of an effective image acquisition unit provided by an embodiment of the present invention;

FIG. 12 is a schematic structural diagram of an identification module according to an embodiment of the present invention;

fig. 13 is a schematic structural diagram of a terminal according to an embodiment of the present invention.

Detailed Description

The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

The data acquisition method provided by the embodiment of the invention can be applied to a scene that new terminal equipment downloads terminal application in old equipment based on the application icon in the old terminal equipment, such as: the data acquisition equipment identifies a target application identifier corresponding to a target application icon in an icon image based on a preset icon identification model by acquiring the icon image carrying the target application icon in a current display page of a target terminal, then searches and acquires application data corresponding to the target application identifier, and then installs and processes the target terminal application indicated by the target application identifier based on the application data. By identifying the application icon in the target terminal and analyzing the application data corresponding to the application icon in the target terminal, the downloading and installation of the relevant terminal application in the target terminal are realized in the data acquisition equipment, and the recovery efficiency of the terminal application is improved.

The data acquisition device related to the embodiment of the invention can be a tablet computer, a smart phone, a palm computer, a Mobile Internet Device (MID) and other terminal devices with image acquisition functions (for example, with a camera shooting function).

The data acquisition method provided by the embodiment of the invention will be described in detail below with reference to fig. 1 to 7.

Referring to fig. 1, a flow chart of a data acquisition method according to an embodiment of the present invention is schematically shown. As shown in fig. 1, the method of the embodiment of the present invention may include the following steps S101 to S103.

S101, acquiring an icon image carrying a target application icon in a current display page of a target terminal;

specifically, the data obtaining device may obtain an icon image carrying a target application icon in a current display page of the target terminal, and it may be understood that the target terminal may be other terminal devices different from the data obtaining device, for example, a tablet computer, a smart phone, a palmtop computer, a Mobile Internet Device (MID), and the like. The current display page may be a current desktop displaying an application icon corresponding to a terminal application in the target terminal, for example, a mobile phone desktop shown in fig. 2 a. The icon image may be an area containing an application icon of a terminal application in the currently displayed page, for example, an area a shown by a dashed box in fig. 2 a. The target application icon may be an application icon of a terminal application in the icon image, such as application icon a1 in fig. 2 a.

S102, identifying a target application identifier corresponding to a target application icon in the icon image based on a preset icon identification model;

specifically, the data acquisition device may identify a target application identifier corresponding to a target application icon in the icon image based on a preset icon identification model, and it may be understood that the preset icon identification model may be an icon identification model obtained after an icon initial identification model, for example, a Back Propagation Neural Network (BP Neural Network) is trained to obtain model parameters by using icons in an icon training set (for example, 1000 application icon samples). The target application identifier corresponding to the target application icon may be an identifier capable of identifying the target terminal application indicated by the target application icon, may be an application name of the target terminal application, and may be, for example, an icon name (application 1, application 2 …) below each application icon in fig. 2 a.

S103, searching and acquiring application data corresponding to the target application identifier, and installing the target terminal application indicated by the target application identifier based on the application data;

specifically, the data obtaining device may search, in a data storage, whether application data corresponding to the target application identifier exists, and may also send a data download request carrying the target application identifier to a cloud server, so that the cloud server searches for the application data corresponding to the target application identifier, thereby obtaining the application data returned by the cloud server, where it may be understood that the application data may be a software installation package of a target terminal application corresponding to the target application identifier.

Further, the data obtaining device may install the target terminal application corresponding to the target application identifier through the application data.

Referring to fig. 3, a schematic flow chart of another data acquisition method according to an embodiment of the present invention is provided. As shown in fig. 3, the method of the embodiment of the present invention may include the following steps S201 to S208.

S201, performing icon recognition training on an initial recognition model by using training application icons corresponding to training application identifications in an application icon training set to obtain model parameters corresponding to the initial recognition model;

specifically, the data acquisition device may perform icon recognition training on the initial recognition model by using a training application icon corresponding to each training application icon in an application icon training set, where it is understood that the application icon training set may be a set of training application icons, for example, may include application icons of all currently existing terminal applications, and the training application identifier may be an identifier capable of identifying a terminal application corresponding to each training application icon in the training application icon set. The initial recognition model may be a model with an image recognition function, for example, a BP neural network, and the model parameter may be a weight parameter corresponding to training data in the initial recognition model.

S202, adding the model parameters into the initial recognition model to generate a trained preset icon recognition model;

specifically, the data obtaining device may add the model parameter to the initial recognition model to generate a trained preset icon recognition model. It can be understood that the preset icon recognition model generated after the model parameters obtained by training the training application icon are added can realize the recognition of the application icon.

S203, acquiring training pixel point parameters corresponding to the training application identifications based on the training application icons and the preset icon recognition model;

it can be understood that after the preset icon recognition model is trained by each training application icon in the training application icon set, the training application icons corresponding to each training application identifier have parameters required for matching with the target application icon, for example, the parameters may be pixel point parameters of each training application icon.

Specifically, the data obtaining device may obtain, based on the training application icon and the preset icon recognition model, a training pixel parameter corresponding to each training application identifier, where it may be understood that the training pixel parameter may be a parameter of a pixel constituting each training application icon in the preset icon recognition model (for example, a position, a color, a brightness, and the like of a pixel of the training application icon).

S204, acquiring an effective page image carrying a target application icon in a current display page of the target terminal by using a camera;

specifically, the data acquisition device may scan an effective page image carrying a target application icon in a current display page of a target terminal by using a camera, and it can be understood that the target terminal may be other terminal devices different from the data acquisition device, such as a tablet computer, a smart phone, a palm computer, a Mobile Internet Device (MID), and the like. The current display page may be a current desktop displaying an application icon corresponding to a terminal application in the target terminal, for example, a mobile phone desktop shown in fig. 2 a. The effective page image may be the effective page area shown in fig. 2b with the top status bar and the bottom navigation bar removed from the currently displayed page, and the target application icon may be an application icon of a terminal application in the effective page image, such as application icon a1 in fig. 2 b.

S205, performing icon area division processing on the effective page image according to the distribution mode of each application icon in the effective page image, and acquiring each icon area corresponding to each application icon after the icon area division processing;

specifically, the data acquisition device may perform icon area division processing on the effective page image according to a distribution manner of each application icon in the effective page image, and it may be understood that the distribution manner of each application icon may be a distribution manner in which application icons preset in the data acquisition device may be distributed in a terminal desktop, for example, 12 application icons a1-C4 shown in fig. 2a or fig. 2b may be distributed in a terminal desktop in 3 rows and 4 columns. The icon region dividing process may be a region dividing process of dividing each application icon in the effective page image according to a distribution manner thereof, for example, 12 dotted line grids in fig. 2b may represent 3 × 4 icon regions obtained by dividing each application icon in fig. 2b into icon regions.

Further, the data acquisition device may acquire each icon region corresponding to each application icon after the icon region division processing. It can be understood that each icon region may be an image region corresponding to each application icon in the effective page image after the icon region division processing.

S206, acquiring an icon image carrying a target application icon in the target icon area according to a preset icon acquisition rule;

it can be understood that the icon region corresponding to each application icon in the effective page image after the icon region division processing may be the icon image of each application icon, for example, 12 icon regions in fig. 2b may be 12 icon images corresponding to each application icon in fig. 2 b.

Specifically, the data obtaining device may obtain the icon image carrying the target application icon in the target icon area according to a preset icon obtaining rule, and it may be understood that the preset icon obtaining rule may be a preset sequential obtaining rule (for example, the preset obtaining order of the icon images in fig. 2B may be a1-a4, B1-B4, and C1-C4). The target icon area may be an icon area selected when the icon image is obtained according to a preset icon obtaining rule, for example, the icon area a corresponding to the application icon a1 in fig. 2b may be an icon image carrying the target application icon a1 in the target icon area.

In the embodiment of the invention, the application icons in the effective page image are analyzed, so that the processing of all the application icons in the current display page is avoided, the efficiency of analyzing and processing the application icons is improved, and the downloading efficiency of the terminal application is further improved; by dividing the icon area of the application icon in the effective page image, the distribution position of the application icon in the effective page image is determined, and the accuracy of analyzing and processing the target application icon is improved.

S207, matching target application icons in the icon images by adopting training application icons in a preset icon recognition model, and determining training application identifications corresponding to the training application icons with the highest matching degree with the target application icons as target application identifications corresponding to the target application icons;

it is understood that the preset icon recognition model can match the target application icon with the training application icon in the model to recognize the target application icon.

Specifically, the data acquisition device may match a target application icon in the icon image with each training application icon in a preset icon recognition model, and determine a training application identifier corresponding to a training application icon with a highest matching degree with the target application icon as a target application identifier corresponding to the target application icon. It can be understood that after the target application icon is matched with each training application icon, the preset icon recognition model can obtain corresponding matching degrees, and can obtain the highest matching degree from all the matching degrees. The data acquisition device may determine the training application icon indicated by the highest matching degree as the target application icon, and may determine the training application identifier corresponding to the training application icon with the highest matching degree as the target application identifier of the target application icon.

S208, searching and acquiring application data corresponding to the target application identifier, and installing the target terminal application indicated by the target application identifier based on the application data;

In a specific implementation manner of the embodiment of the present invention, the acquiring, by using a camera, an effective page image corresponding to a currently displayed page of a target terminal may include the following steps, as shown in fig. 4:

s301, acquiring a current page image carrying a target application icon in a current display page of a target terminal by using a camera;

specifically, the data obtaining device may scan a current page image carrying a target application icon in a current display page of a target terminal by using a camera, and it can be understood that page content included in the current page image may be identical to page content included in the current display page, that is, the current display page may be the current page image, for example, a desktop of a mobile phone shown in fig. 2a may be regarded as the current page image.

S302, acquiring the total height of the page of the current page image and the first height of a page prompt bar in the current displayed page;

it can be understood that the position of the page prompt bar is related to the page sliding direction of the data acquisition device, and when the page sliding direction of the data acquisition device is left-right sliding, the page prompt bar may be located at the bottom of the page in the current page image, may be located at the bottom of the page, or may be located at the bottom and the top of the page, for example, the status bar located at the top of the page and the navigation bar located at the bottom of the page in fig. 2a are collectively referred to as page prompt bars. It can be understood that, when the page sliding direction of the data acquisition device is up-down sliding, the page prompt bar may be located at the left end of the page in the current page image, at the right end of the page, or at the left end and the right end of the page.

Specifically, the data obtaining device may obtain a total page height of the current page image and a first height of a page hint bar in the current displayed page, where the total page height of the current page image may be a height h1 shown in fig. 2a, and the first height may be heights h2 and h3 in fig. 2 a.

S303, intercepting an effective page image indicated by a second page height from the current page image;

specifically, the data obtaining device may intercept an effective page image indicated by a second page height in the current page image, and it may be understood that the second page height may be a page height remaining after the first height of the page hint column is removed from the total page height, for example, a height h4 in fig. 2 a. The area indicated by the second page height may be the active page image, e.g. the page image containing application icons a1-C4 as in fig. 2a or fig. 2b is an active page image.

In the embodiment of the invention, the effective page image is determined by analyzing the page height, so that the accuracy of determining the effective page image is increased.

In a specific implementation manner of the embodiment of the present invention, the step of capturing the effective page image indicated by the second page height from the current page image may include the following steps, as shown in fig. 5:

s401, intercepting an effective page area indicated by a second page height in the current page image, and acquiring each application icon in the effective page area;

specifically, the data obtaining device may intercept an effective page area indicated by the second page height in the current page image, and obtain each application icon in the effective page area, where it is understood that the effective page area may be a page area corresponding to the height h4 shown in fig. 2a, and each application icon in the effective page area may be 12 application icons, in total, of the application icons a1-C4 shown in fig. 2 a.

S402, acquiring a first comparison application icon and a second comparison application icon from application icons in the history effective page image;

it is to be understood that the history effective page image may be an already confirmed effective page image, and the first and second comparison application icons are respectively any one of two corresponding boundaries in the history effective page image, and a correspondence relationship between the two corresponding boundaries is associated with a page sliding direction. For example, fig. 6a is a confirmed history valid page image, and when the page sliding direction is left-right sliding, the first comparison app icon may be any one of app icons a1, B1, and C1, and the second comparison app icon may be any one of app icons a4, B4, and C4; when the page sliding direction is up and down sliding, the first comparative application icon may be any one of application icons a1, a2, A3, and a4, and the second comparative application icon may be any one of application icons C1, C2, C3, and C4. In the embodiment of the present invention, the page sliding direction may be considered as left-right sliding and a1 and a4 may be selected as the first and second contrast application icons.

S403, identifying each application icon in the effective page area according to the preset icon identification model;

s404, when the first comparison application icon and the second comparison application icon do not appear in each application icon in the effective page area, determining the effective page area as an effective page image corresponding to the current display page;

it can be understood that, after the data acquisition device identifies each application icon in the effective page area, it may determine whether each application icon in the effective page area is consistent with each application icon in the history effective page image. It can be understood that, since the first and second comparison application icons are both application icons in a page boundary, when neither of the first and second comparison application icons appears in the application icons in the effective page area, it can be confirmed that the application icons in the effective page area are inconsistent with the application icons in the history effective page image.

In a specific implementation manner of the embodiment of the present invention, fig. 6a is a confirmed history valid page image, fig. 6b is a valid page area intercepted in a current page image, application icons a1 and a4 are the first comparative application icon and the second comparative application icon, and since neither application icon a1 nor a4 appears in fig. 6b, it can be determined that fig. 6b is a valid page image.

It is to be understood that if either or both of the first and second comparison app icons are present within an active page area, the active page area is a transition page image. For example, the area shown in fig. 6c is an effective page area, and the second comparison application identifier a2 exists in the effective page area, then the effective page area is a transition page image.

In the embodiment of the invention, the effective page images are further determined by comparing the effective page images with the application icons in the historical effective page images, so that the diversity of determining the effective page images is increased.

In a specific implementation manner of the embodiment of the present invention, the matching, by using each training application icon in the preset icon recognition model, a target application icon in the icon image, and determining a training application identifier corresponding to a training application icon with a highest matching degree with the target application icon as a target application identifier corresponding to the target application icon may include the following steps, as shown in fig. 7:

s501, acquiring target pixel point parameters in the target application icon, and matching the target pixel point parameters with training pixel point parameters of training application icons corresponding to training application identifications in a preset icon recognition model;

specifically, the data obtaining device may obtain a target pixel parameter in the target application icon, and it may be understood that the target pixel parameter may be a parameter corresponding to all pixels forming the target application identifier, for example, the target pixel parameter may be information of positions, colors, brightness, and the like of the pixels.

Further, the data acquisition device may match the target pixel point parameters with training pixel point parameters of training application icons corresponding to training application identifiers in a preset icon recognition model.

S502, acquiring a matching degree set of training pixel point parameters of training application icons corresponding to the training application identifications and the target pixel point set;

specifically, the data obtaining device may obtain a matching degree set of training pixel point parameters of training application icons corresponding to the training application identifiers and the target pixel point set, and it may be understood that the training pixel point parameters of the training application icons may be matched with the training pixel point parameters of the target application icons, and a matching degree set representing a pixel point matching degree may be obtained.

S503, when a first matching degree which is greater than or equal to a preset matching degree threshold value exists in the matching degree set, acquiring a training application icon corresponding to a training pixel parameter indicated by the highest matching degree in the first matching degree, and determining a training application identifier corresponding to the training application icon as a target application identifier corresponding to the target application icon;

specifically, when a first matching degree greater than or equal to a preset matching degree threshold exists in the matching degree set, the data acquisition device may acquire a training application icon corresponding to a training pixel parameter indicated by a highest matching degree among the first matching degrees. It can be understood that the preset matching degree threshold may be preset, and is used to determine a matching degree between the training pixel parameters of the training application icon and the training pixel parameters of the target application icon, so as to reach a value that may be considered as a possibility that the training application icon is the target application icon, for example, may be 60%. The first matching degree may be the matching degree greater than or equal to the preset matching degree threshold in the matching degree set, and may include one or more matching degrees, for example, the first matching degree may include matching degrees with values of 70%, 75%, 80%, and 90%, respectively, and then the matching degree with the highest value in the first matching degree is 90%, and the data obtaining device may obtain the training application icon (for example, may be the training application icon X1) corresponding to the training pixel parameter with the matching degree of 90%.

Further, the data obtaining device may determine the training application identifier corresponding to the training application icon as the target application identifier corresponding to the target application icon, for example, the data obtaining device may determine the training application identifier "app X" corresponding to the training application icon X1 as the target application identifier "app 1" of the target application icon a 1.

In the embodiment of the invention, the target application identifier of the target application icon is determined by analyzing the matching degree of the pixel point data in the application icon, so that the accuracy of determining the target application identifier is improved.

In a specific implementation manner of the embodiment of the present invention, after the step S503 is executed, the data obtaining apparatus may further execute the step of: when all the matching degrees in the matching degree set are smaller than the preset matching degree threshold value, adding the target application icon into the application icon training set;

specifically, when each matching degree in the matching degree set is smaller than the preset matching degree threshold, that is, the matching degree between the pixel point parameter of the training application icon and the target pixel point parameter of the target application image is low, and the possibility that the training application icon is the target application icon is not reached, the data acquisition device may add the target application icon to the application icon training set, so that the subsequent data acquisition device can meet the requirement that the target application icon is trained again, and the preset matching degree threshold can be reached.

In the embodiment of the invention, the target application icon which cannot be matched is retrained, so that the matching degree of the target application icon for re-matching is improved.

In the embodiment of the invention, the icon image carrying the target application icon in the current display page of the target terminal is obtained, the target application identifier corresponding to the target application icon in the icon image is identified based on the preset icon identification model, the application data corresponding to the target application identifier is searched and obtained, and then the target terminal application indicated by the target application identifier is installed based on the application data. By identifying the application icon in the target terminal and analyzing the application data corresponding to the application icon in the target terminal, the downloading and installation of the relevant terminal application in the target terminal are realized in the data acquisition equipment, and the recovery efficiency of the terminal application is improved; by analyzing the application icons in the effective page image, the processing of all the application icons in the current display page is avoided, and the efficiency of analyzing and processing the application icons is improved, so that the downloading efficiency of the terminal application is further improved; by dividing the icon area of the application icon in the effective page image, the distribution position of the application icon in the effective page image is determined, and the accuracy of analyzing and processing the target application icon is improved; the effective page image is determined by analyzing the page height, so that the accuracy of determining the effective page image is improved; effective page images are further determined through comparison with application icons in historical effective page images, and the diversity of the determined effective page images is increased; the target application identifier of the target application icon is determined through analysis of pixel point data in the application icon, so that the accuracy of determining the target application identifier is improved; by retraining the unmatched target application icons, the matching degree of the unmatched target application icons is improved.

The data acquisition device provided by the embodiment of the invention will be described in detail with reference to fig. 8 to 12. It should be noted that the apparatuses shown in fig. 8-12 are used for executing the method according to the embodiments of the present invention shown in fig. 1-7, and for convenience of description, only the parts related to the embodiments of the present invention are shown, and details of the technology are not disclosed, please refer to the embodiments of the present invention shown in fig. 1-7.

Referring to fig. 8, a schematic structural diagram of a data acquisition device is provided in an embodiment of the present invention. As shown in fig. 8, the data acquisition apparatus 1 according to an embodiment of the present invention may include: an image acquisition module 11, an identification recognition module 12 and an application installation module 13.

The image acquisition module 11 is configured to acquire an icon image carrying a target application icon in a current display page of the target terminal;

in a specific implementation, the image obtaining module 11 may obtain an icon image carrying a target application icon in a current display page of a target terminal, and it is understood that the target terminal may be other terminal devices different from the data obtaining device 1, for example, a tablet computer, a smart phone, a palmtop computer, a Mobile Internet Device (MID), and the like. The current display page may be a current desktop displaying an application icon corresponding to a terminal application in the target terminal, for example, a mobile phone desktop shown in fig. 2 a. The icon image may be an area containing an application icon of a terminal application in the currently displayed page, for example, an area a shown by a dashed box in fig. 2 a. The target application icon may be an application icon of a terminal application in the icon image, such as application icon a1 in fig. 2 a.

The identifier recognition module 12 is configured to recognize a target application identifier corresponding to a target application icon in the icon image based on a preset icon recognition model;

in a specific implementation, the identifier recognition module 12 may recognize the target application identifier corresponding to the target application icon in the icon image based on a preset icon recognition model, and it may be understood that the preset icon recognition model may be an icon recognition model obtained by training an initial icon recognition model (e.g., a BP neural network) by using icons in an icon training set (e.g., may include 1000 application icon samples) in advance. The target application identifier corresponding to the target application icon may be an identifier capable of identifying the target terminal application indicated by the target application icon, may be an application name of the target terminal application, and may be, for example, an icon name (application 1, application 2 …) below each application icon in fig. 2 a.

The application installation module 13 is configured to search and obtain application data corresponding to the target application identifier, and perform installation processing on the target terminal application indicated by the target application identifier based on the application data;

in specific implementation, the application installation module 13 may search whether there is application data corresponding to the target application identifier in the data storage, and may also send a data download request carrying the target application identifier to the cloud server, so that the cloud server searches for the application data corresponding to the target application identifier, thereby obtaining the application data returned by the cloud server, where it may be understood that the application data may be a software installation package of a target terminal application corresponding to the target application identifier.

Further, the application installation module 13 may install the target terminal application corresponding to the target application identifier through the application data.

Referring to fig. 9, a schematic structural diagram of another data acquisition device according to an embodiment of the present invention is provided. As shown in fig. 9, the data acquisition apparatus 1 according to an embodiment of the present invention may include: the system comprises an image acquisition module 11, an identification recognition module 12, an application installation module 13, a parameter acquisition module 14, a model generation module 15 and a pixel parameter acquisition module 16.

A parameter obtaining module 14, configured to perform icon recognition training on an initial recognition model by using a training application icon corresponding to each training application identifier in an application icon training set, so as to obtain a model parameter corresponding to the initial recognition model;

in a specific implementation, the parameter obtaining module 14 may perform icon recognition training on the initial recognition model by using a training application icon corresponding to each training application icon in an application icon training set, where it is understood that the application icon training set may be a set of training application icons, for example, may include application icons of all currently existing terminal applications, and the training application identifier may be an identifier capable of identifying a terminal application corresponding to each training application icon in the training application icon set. The initial recognition model may be a model with an image recognition function, for example, a BP neural network, and the model parameter may be a weight parameter corresponding to training data in the initial recognition model.

The model generation module 15 is configured to add the model parameters to the initial recognition model to generate a trained preset icon recognition model;

in a specific implementation, the model generating module 15 may add the model parameters to the initial recognition model to generate a trained preset icon recognition model. It can be understood that the preset icon recognition model generated after the model parameters obtained by training the training application icon are added can realize the recognition of the application icon.

A pixel parameter obtaining module 16, configured to obtain, based on the training application icon and the preset icon recognition model, a training pixel parameter corresponding to each training application identifier;

In a specific implementation, the pixel parameter obtaining module 16 may obtain, based on the training application icon and the preset icon recognition model, a training pixel parameter corresponding to each training application identifier, where it is understood that the training pixel parameter may be a parameter of a pixel point constituting each training application icon in the preset icon recognition model (for example, a position, a color, a brightness, and the like of the pixel point of the training application icon).

in a specific implementation, the image obtaining module 11 may obtain an icon image carrying a target application icon in a current display page of the target terminal.

Referring to fig. 10, a schematic structural diagram of an image capturing module according to an embodiment of the invention is provided. As shown in fig. 10, the image acquisition module 11 may include:

an effective image obtaining unit 111, configured to obtain, by using a camera, an effective page image carrying a target application icon in a current display page of a target terminal;

in a specific implementation, the effective image obtaining unit 111 may scan an effective page image carrying a target application icon in a currently displayed page of a target terminal by using a camera, and it can be understood that the target terminal may be other terminal devices different from the data obtaining device 1, for example, a tablet computer, a smart phone, a palm computer, a Mobile Internet Device (MID), and the like. The current display page may be a current desktop displaying an application icon corresponding to a terminal application in the target terminal, for example, a mobile phone desktop shown in fig. 2 a. The effective page image may be the effective page area shown in fig. 2b with the top status bar and the bottom navigation bar removed from the currently displayed page, and the target application icon may be an application icon of a terminal application in the effective page image, such as application icon a1 in fig. 2 b.

An area obtaining unit 112, configured to perform icon area division processing on the effective page image according to a distribution manner of each application icon in the effective page image, and obtain each application area corresponding to each application icon after the icon area division processing;

in a specific implementation, the area obtaining unit 112 may perform icon area division processing on the effective page image according to a distribution manner of each application icon in the effective page image, and it is understood that the distribution manner of each application icon may be a distribution manner in which application icons preset in the data obtaining device 1 may be distributed in a terminal desktop, for example, 12 application icons a1-C4 shown in fig. 2a or fig. 2b may be distributed in a terminal desktop in 3 rows and 4 columns. The icon region dividing process may be a region dividing process of dividing each application icon in the effective page image according to a distribution manner thereof, for example, 12 dotted line grids in fig. 2b may represent 3 × 4 icon regions obtained by dividing each application icon in fig. 2b into icon regions.

Further, the area obtaining unit 112 may obtain each icon area corresponding to each application icon after the icon area division processing. It can be understood that each icon region may be an image region corresponding to each application icon in the effective page image after the icon region division processing.

An image obtaining unit 113, configured to obtain an icon image carrying a target application icon in a target icon area according to a preset icon obtaining rule;

In a specific implementation, the image obtaining unit 113 may obtain the icon image carrying the target application icon in the target icon area according to a preset icon obtaining rule, and it is understood that the preset icon obtaining rule may be a preset sequential obtaining rule (for example, the preset obtaining order of the icon images in fig. 2B may be a1-a4, B1-B4, and C1-C4), may be other preset obtaining rules, and may also be a random obtaining rule. The target icon area may be an icon area selected when the icon image is obtained according to a preset icon obtaining rule, for example, the icon area a corresponding to the application icon a1 in fig. 2b may be an icon image carrying the target application icon a1 in the target icon area.

in a specific implementation, the identifier recognition module 12 may match a target application icon in the icon image with each training application icon in a preset icon recognition model, and determine a training application identifier corresponding to a training application icon with a highest matching degree with the target application icon as a target application identifier corresponding to the target application icon.

In a specific implementation, the identifier recognition module 12 may match a target application icon in the icon image with each training application icon in a preset icon recognition model, and determine a training application identifier corresponding to a training application icon with a highest matching degree with the target application icon as a target application identifier corresponding to the target application icon. It can be understood that after the target application icon is matched with each training application icon, the preset icon recognition model can obtain corresponding matching degrees, and can obtain the highest matching degree from all the matching degrees. The identifier recognition module 12 may determine the training application icon indicated by the highest matching degree as the target application icon, and may determine the training application identifier corresponding to the training application icon with the highest matching degree as the target application identifier of the target application icon.

In a specific implementation manner of the embodiment of the present invention, as shown in fig. 11, the effective image obtaining unit 111 may include:

a current image obtaining subunit 1111, configured to obtain, by using a camera, a current page image carrying a target application icon in a current display page of a target terminal;

in a specific implementation, the current image obtaining subunit 1111 may scan, by using a camera, a current page image carrying a target application icon in a current display page of a target terminal, and it can be understood that a page content included in the current page image may be identical to a page content included in the current display page, that is, the current display page may be the current page image, for example, a desktop of a mobile phone shown in fig. 2a may be regarded as the current page image.

A height obtaining subunit 1112, configured to obtain a total page height of the current page image and a first height of a page hint in the current displayed page;

it can be understood that the position of the page prompt bar is related to the page sliding direction of the data acquisition device 1, and when the page sliding direction of the data acquisition device 1 is left-right sliding, the page prompt bar may be located at the bottom of the page in the current page image, may be located at the bottom of the page, or may be located at the bottom and the top of the page, for example, the status bar located at the top of the page and the navigation bar located at the bottom of the page in fig. 2a are collectively referred to as page prompt bar. It can be understood that, when the page sliding direction of the data acquisition device 1 is up-down sliding, the page prompt bar may be located at the left end of the page in the current page image, may be located at the right end of the page, or may be located at the left end and the right end of the page.

In a specific implementation, the height obtaining sub-unit 1112 may obtain a total page height of the current page image and a first height of a page hint bar in the current displayed page, where the total page height of the current page image may be a height h1 shown in fig. 2a, and the first height may be heights h2 and h3 in fig. 2 a.

An image clipping sub-unit 1113, configured to clip the effective page image indicated by the second page height in the current page image;

in a specific implementation, the image intercepting subunit 1113 may intercept the effective page image indicated by the second page height in the current page image, and it is understood that the second page height may be a page height remaining after the first height of the page hint column is removed from the total page height, for example, a height h4 in fig. 2 a. The area indicated by the second page height may be the active page image, e.g. the page image containing application icons a1-C4 as in fig. 2a or fig. 2b is an active page image.

In a specific implementation manner of the embodiment of the present invention, the image capturing subunit 1113 is specifically configured to execute the following steps:

in a specific implementation, the image intercepting subunit 1113 may intercept an effective page area indicated by the second page height in the current page image, and obtain each application icon in the effective page area, where it is understood that the effective page area may be a page area corresponding to the height h4 shown in fig. 2a, and each application icon in the effective page area may be 12 application icons, in total, of the application icons a1-C4 shown in fig. 2 a.

Acquiring a first comparison application icon and a second comparison application icon from application icons in a history effective page image;

when the first comparison application icon and the second comparison application icon do not appear in each application icon in the effective page area, determining the effective page area as an effective page image corresponding to the current display page;

it is understood that, after the image capture subunit 1113 identifies the application icons in the effective page area, it may determine whether the application icons in the effective page area are consistent with the application icons in the history effective page image. It can be understood that, since the first and second comparison application icons are both application icons in a page boundary, when neither of the first and second comparison application icons appears in the application icons in the effective page area, it can be confirmed that the application icons in the effective page area are inconsistent with the application icons in the history effective page image.

In a specific implementation manner of the embodiment of the present invention, as shown in fig. 12, the identifier identifying module 12 may include:

the pixel matching unit 121 is configured to obtain a target pixel parameter in the target application icon, and match the target pixel parameter with a training pixel parameter of a training application icon corresponding to each training application identifier in a preset icon recognition model;

in a specific implementation, the pixel matching unit 121 may obtain a target pixel parameter in the target application icon, and it can be understood that the target pixel parameter may be a parameter corresponding to all pixels forming the target application identifier, for example, the target pixel parameter may be information such as a position, a color, and a brightness of a pixel.

Further, the pixel matching unit 121 may match the target pixel point parameter with a training pixel point parameter of a training application icon corresponding to each training application identifier in a preset icon recognition model.

A set obtaining unit 122, configured to obtain a matching degree set between the training pixel point parameters of the training application icon corresponding to each training application identifier and the target pixel point set;

in a specific implementation, the set obtaining unit 122 may obtain a matching degree set of training pixel parameters of training application icons corresponding to the training application identifiers and the target pixel set, and it may be understood that the training pixel parameters of the training application icons may be matched with the training pixel parameters of the target application icons, and a matching degree set representing a pixel matching degree may be obtained.

The identifier determining unit 123 is configured to, when a first matching degree greater than or equal to a preset matching degree threshold exists in the matching degree set, obtain a training application icon corresponding to a training pixel parameter indicated by a highest matching degree in the first matching degrees, and determine a training application identifier corresponding to the training application icon as a target application identifier corresponding to the target application icon;

in a specific implementation, when a first matching degree greater than or equal to a preset matching degree threshold exists in the matching degree set, the identifier determining unit 123 may obtain a training application icon corresponding to a training pixel parameter indicated by a highest matching degree in the first matching degrees. It can be understood that the preset matching degree threshold may be preset, and is used to determine a matching degree between the training pixel parameters of the training application icon and the training pixel parameters of the target application icon, so as to reach a value that may be considered as a possibility that the training application icon is the target application icon, for example, may be 60%. The first matching degree may be the matching degree greater than or equal to the preset matching degree threshold in the matching degree set, and may include one or more matching degrees, for example, the first matching degree may include matching degrees with values of 70%, 75%, 80%, and 90%, respectively, and then the matching degree with the highest value in the first matching degree is 90%, and the identifier determining unit 123 may obtain the training application icon (for example, may be the training application icon X1) corresponding to the training pixel parameter with the matching degree of 90%.

Further, the identifier determining unit 123 may determine the training application identifier corresponding to the training application icon as the target application identifier corresponding to the target application icon, for example, the identifier determining unit 123 may determine the training application identifier "app X" corresponding to the training application icon X1 as the target application identifier "app 1" of the target application icon a 1.

In a specific implementation manner of the embodiment of the present invention, the method further includes: when all the matching degrees in the matching degree set are smaller than the preset matching degree threshold value, adding the target application icon into the application icon training set;

in a specific implementation, when each matching degree in the matching degree set is smaller than the preset matching degree threshold, that is, the matching degree between the pixel point parameter of the training application icon and the target pixel point parameter of the target application image is low, and the possibility that the training application icon is the target application icon is not reached, the data acquisition device 1 may add the target application icon to the application icon training set, so that the subsequent data acquisition device can meet the requirement that the target application icon is again trained to reach the preset matching degree threshold through the training of the target application icon.

An embodiment of the present invention further provides a computer storage medium, where the computer storage medium may store a plurality of instructions, where the instructions are suitable for being loaded by a processor and executing the method steps in the embodiments shown in fig. 1 to 7, and a specific execution process may refer to specific descriptions of the embodiments shown in fig. 1 to 7, which are not described herein again.

Fig. 13 is a schematic structural diagram of a terminal according to an embodiment of the present invention. As shown in fig. 13, the server 1000 may include: at least one processor 1001, such as a CPU, at least one network interface 1004, a user interface 1003, memory 1005, at least one communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display (Display), a Keyboard (Keyboard), and an audio interface (Voice), and the selectable user interface 1003 may also include a standard wired interface and a standard wireless interface. The network interface 1004 may include a standard wired network interface, a wireless network interface (e.g., a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory). The memory 1005 may also be at least one storage device located remotely from the processor 1001. As shown in fig. 13, a memory 1005, which is one type of computer storage medium, may include an operating system, a network communication program module, a user interface program module, and a data acquisition application program therein.

In the terminal 1000 shown in fig. 13, the user interface 1003 is mainly used as an interface for providing input for a user, and acquiring data input by the user; the network interface 1004 is used for data communication with the user terminal; and the processor 1001 may be configured to invoke the data acquisition application stored in the memory 1005 and specifically perform the following operations:

In an embodiment, before the processor 1001 acquires the icon image carrying the target application icon in the current display page of the target terminal, the following operations are further performed:

In an embodiment, when executing acquiring an icon image carrying a target application icon in a current display page of a target terminal, the processor 1001 specifically executes the following operations:

In an embodiment, when the processor 1001 acquires an effective page image corresponding to a currently displayed page of the target terminal by using a camera, the following operations are specifically performed:

In one embodiment, when the processor 1001 intercepts the effective page image indicated by the second page height from the current page image, specifically performs the following operations:

In an embodiment, when the processor 1001 identifies, based on a preset icon identification model, a target application identifier corresponding to a target application icon in the icon image, specifically performs the following operations:

In an embodiment, when the processor 1001 performs matching on a target application icon in the icon image by using each training application icon in a preset icon recognition model, and determines a training application identifier corresponding to a training application icon with a highest matching degree with the target application icon as a target application identifier corresponding to the target application icon, the following operations are specifically performed:

In one embodiment, the processor 1001 is further configured to:

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.

Claims

1. A method of data acquisition, comprising:

the data acquisition equipment acquires a current page image carrying a target application icon in a current display page of a target terminal by adopting a camera;

intercepting an effective page area indicated by a second page height in the current page image, and acquiring each application icon in the effective page area; the second page height is the page height left after the first height of the page prompt bar is removed from the total page height;

when the first comparison application icon and the second comparison application icon do not appear in the effective page area, determining that the effective page area is an effective page image corresponding to the current display page;

performing icon area division processing on the effective page image according to the distribution mode of each application icon in the effective page image to obtain icon areas corresponding to the application icons after the icon area division processing; an icon area containing an application icon; the distribution mode of each application icon is the distribution mode of the preset application icon in the terminal desktop in the data acquisition equipment;

sequentially traversing each icon area, acquiring an icon image carrying a target application icon in the target icon area, matching the target application icon in the icon image by adopting each training application icon in a preset icon recognition model, and determining a training application identifier corresponding to the training application icon with the highest matching degree with the target application icon as a target application identifier corresponding to the target application icon; the target icon area belongs to the icon area after the icon area is divided; the target application identifier is an application name corresponding to the target application icon;

2. The method of claim 1, wherein before obtaining the icon image carrying the target application icon in the target icon area, further comprising:

3. The method of claim 1, wherein the matching of the target application icon in the icon image by using each training application icon in the preset icon recognition model and determining the training application identifier corresponding to the training application icon with the highest matching degree with the target application icon as the target application identifier corresponding to the target application icon comprises:

4. The method of claim 3, further comprising:

5. A data acquisition device, comprising:

the image acquisition module is used for acquiring an effective page image carrying a target application icon in a current display page of the target terminal;

the image acquisition module is further used for carrying out icon area division processing on the effective page image according to the distribution mode of each application icon in the effective page image, and acquiring each icon area corresponding to each application icon after the icon area division processing; an icon area containing an application icon; the distribution mode of each application icon is the distribution mode of the preset application icon in the terminal desktop in the data acquisition equipment;

the identification recognition module is used for sequentially traversing the icon areas, acquiring an icon image carrying a target application icon in the target icon area, matching the target application icon in the icon image by adopting each training application icon in a preset icon recognition model, and determining a training application identification corresponding to the training application icon with the highest matching degree with the target application icon as a target application identification corresponding to the target application icon; the target icon area belongs to the icon area after the icon area is divided; the target application identifier is an application name corresponding to the target application icon;

the application installation module is used for searching and acquiring application data corresponding to the target application identifier and installing the target terminal application indicated by the target application identifier based on the application data;

wherein the image acquisition module comprises:

the current image acquisition unit is used for acquiring a current page image carrying a target application icon in a current display page of the target terminal by adopting a camera;

the height obtaining unit is used for obtaining the total height of the page of the current page image and the first height of a page prompt bar in the current display page;

an image capturing unit, configured to capture an effective page area indicated by a second page height in the current page image, obtain each application icon in the effective page area, and obtain a first comparison application icon and a second comparison application icon in each application icon in a historical effective page image, where the first comparison application icon and the second comparison application icon are each any one of two corresponding boundaries in the historical effective page image, and a correspondence relationship between the two corresponding boundaries is associated with a page sliding direction; the second page height is the page height left after the first height of the page prompt bar is removed from the total page height;

the image capturing unit is further configured to determine that the effective page area is an effective page image corresponding to the currently displayed page when neither the first comparison application icon nor the second comparison application icon appears in the effective page area.

6. The apparatus of claim 5, further comprising:

7. A computer storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor and to perform the steps of:

performing icon area division processing on the effective page image according to the distribution mode of each application icon in the effective page image to obtain icon areas corresponding to the application icons after the icon area division processing; an icon area containing an application icon; the distribution mode of each application icon is a preset distribution mode of the application icons in the terminal desktop;

8. A terminal, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the steps of: