CN108734556A

CN108734556A - Recommend the method and device of application

Info

Publication number: CN108734556A
Application number: CN201810480566.7A
Authority: CN
Inventors: 潘岸腾
Original assignee: Guangzhou Youshi Network Technology Co Ltd
Current assignee: Alibaba China Co Ltd
Priority date: 2018-05-18
Filing date: 2018-05-18
Publication date: 2018-11-02

Abstract

The embodiment of the present application provides a kind of method and device for recommending application, wherein this method includes：Obtain the icon of intended application and the icon of multiple applications to be compared；Determine the similarity value between the icon of intended application and the icon of each application to be compared；The application that similarity value meets preset condition is chosen from multiple applications to be compared, as the corresponding recommendation application of intended application.The technical solution of the embodiment of the present application can also realize certain applications for lacking user behavior data by the method that the similarity for the icon applied compares the recommendation of application；In addition, for a series of application, since the similarity of icon is larger, the method in the present embodiment is directed to a series of application for lacking user behavior data, and recommendation effect can be fine.

Description

Recommend the method and device of application

Technical field

This application involves image processing field more particularly to a kind of method and devices for recommending application.

Background technology

Widely available with terminal device, the application for terminal device exploitation is also more and more, and user can be in terminal It is downloaded in equipment, arbitrary application is installed.Most of user is applied down by the application shop on terminal device It carries, installation, in general, when user checks some in application, can also show application shop on current page in application shop Recommend some other applications to user.

In the prior art, recommending to user in application, being usually according to the user behavior data recorded in each application Determine application recommended to the user.But some are lacked with the application of user behavior data, possibly can not recommend user or Person is based on the application and recommends other application to user.

Therefore, it is necessary to propose a kind of method for recommending application, the application that user behavior data is lacked for some also can Realize the recommendation of application.

Invention content

The purpose of the embodiment of the present application is to provide a kind of method and device for recommending application, to solve to be directed in the prior art The problem of some applications for lacking user behavior data cannot achieve the recommendation of application.

In order to solve the above technical problems, what the embodiment of the present application was realized in：

The embodiment of the present application provides a kind of method for recommending application, including：

Obtain the icon of intended application and the icon of multiple applications to be compared；

Determine the similarity value between the icon of the intended application and the icon of each application to be compared；

The application that the similarity value meets preset condition is chosen from the multiple application to be compared, as the target It is applied using corresponding recommendation.

The embodiment of the present application also provides a kind of devices for recommending application, including：

Acquisition module, the icon of icon and multiple applications to be compared for obtaining intended application；

Determining module, it is similar between the icon of the intended application and the icon of each application to be compared for determining Angle value；

Module is chosen, meets answering for preset condition for choosing the similarity value from the multiple application to be compared With as the corresponding recommendation application of the intended application.

The embodiment of the present application also provides a kind of equipment for recommending application, including：

Processor；And

It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed Manage device：

The embodiment of the present application also provides a kind of storage mediums, described executable for storing computer executable instructions Following below scheme is realized in instruction when executed：

Technical solution in the present embodiment, by obtaining the icon of intended application and the icon of multiple applications to be compared, really Set the goal the similarity value of the icon of application and the icon of application to be compared, and chooses similarity value from multiple applications to be compared The application for meeting preset condition, as the corresponding recommendation application of intended application；In this way, passing through the similarity for the icon applied The method of comparison can also realize certain applications for lacking user behavior data the recommendation of application；In addition, being directed to same system The application of row, since the similarity of icon is larger, the method in the present embodiment is directed to a series of shortage user behavior The application of data, recommendation effect can be fine.

Description of the drawings

In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this Some embodiments described in application, for those of ordinary skill in the art, in the premise of not making the creative labor property Under, other drawings may also be obtained based on these drawings.

Fig. 1 is the first method flow chart of the method provided by the embodiments of the present application for recommending application；

Fig. 2 is to divide a kind of schematic diagram of subregion in the method provided by the embodiments of the present application for recommending application；

Fig. 3 is the second method flow chart of the method provided by the embodiments of the present application for recommending application；

Fig. 4 is to show that the interface for recommending application is illustrated to user in the method provided by the embodiments of the present application for recommending application Figure；

Fig. 5 is the module composition schematic diagram of the device provided by the embodiments of the present application for recommending application；

Fig. 6 is the structural schematic diagram of the equipment provided by the embodiments of the present application for recommending application.

Specific implementation mode

In order to make those skilled in the art better understand the technical solutions in the application, below in conjunction with the application reality The attached drawing in example is applied, technical solutions in the embodiments of the present application is clearly and completely described, it is clear that described implementation Example is merely a part but not all of the embodiments of the present application.Based on the embodiment in the application, this field is common The every other embodiment that technical staff is obtained without creative efforts should all belong to the application protection Range.

The embodiment of the present application provides a kind of method for recommending application, using method provided by the embodiments of the present application, for Some lack the application of user behavior data, can also realize the recommendation of application.For example, when user checks some in application shop In application, for belonging to a series of application newly reached the standard grade, even if these are applied lacks use in application shop with the application Family behavioral data, but by method provided by the embodiments of the present application, can still determine it as related application and recommend user. Application in the embodiment of the present application refers to application program；Lack the application of user behavior data in above application shop, it can be with It is either field feedback or to lack answering for some functional descriptions without corresponding user's usage record in application shop With.Such as the application newly reached the standard grade in certain application shop, this kind of application due to not yet forming corresponding user group, application shop without Method obtains corresponding user behavior data.

Fig. 1 is the first method flow chart of the method provided by the embodiments of the present application for recommending application, side shown in FIG. 1 Method includes at least following steps：

Step S102 obtains the icon of intended application and the icon of multiple applications to be compared.

Intended application in the embodiment of the present application refers to carrying out the application using recommending, for example, it may be user Some application checked is opened in the application or user downloaded from application shop at application shop midpoint.

The executive agent of method provided by the embodiments of the present application is server, in general, being stored with application in the server The information of all applications in shop, the information include at least：The title of application, the icon of application, application related introduction letter Breath, user are to the installation procedure etc. of comment and the application of the film.

When user downloads by application shop or checks intended application, application shop client can be sent to server The information acquisition request of intended application, to obtain the relevant information of intended application；Wherein, it is carried in the information acquisition request The mark of intended application, the mark of intended application can be the title of intended application.

It, can also basis while handling the request after server receives the information acquisition request of client transmission The corresponding icon of identifier lookup intended application of the intended application carried in the request.

In addition, being answered due to choosing the corresponding recommendation of the intended application from the application in addition to intended application that it is stored With therefore, it is also desirable to obtain the icon of all other application in addition to intended application.In the embodiment of the present application, mesh will be removed All other application except mark application is known as application to be compared.

Step S104 determines the similarity value between the icon of above-mentioned intended application and the icon of each application to be compared.

Wherein, it in above-mentioned steps S104, determines similar between the icon of intended application and the icon of each application to be compared Degree, specifically comprises the following steps (1) and step (2)；

First fingerprint characteristic of the icon of step (1), acquisition intended application；And obtain the icon of each application to be compared The second fingerprint characteristic；

Step (2) is based on the first fingerprint characteristic and each second fingerprint characteristic, determine the icon of intended application with it is each to be compared Similarity value between the icon of application.

In the embodiment of the present application, the fingerprint characteristic of icon refers to the contour feature etc. of figure, word on icon etc..

Specifically, the acquisition methods of the first fingerprint characteristic and the second fingerprint characteristic are identical in above-mentioned steps (1), therefore herein The specific acquisition process of fingerprint characteristic is introduced by taking the first fingerprint characteristic as an example, the acquisition methods of the second fingerprint characteristic can refer to first Fingerprint characteristic, details are not described herein again.

In a specific embodiment, above-mentioned steps (1) can obtain the icon of intended application by following process First fingerprint characteristic：Determine the first eigenvector of the icon of intended application；According to first eigenvector, intended application is determined First fingerprint characteristic of icon.

Wherein, above-mentioned first eigenvector be by each pixel on icon eigenvalue cluster at.

In the embodiment of the present application, (A1), step (A2) and step (A3) intended application can be determined as follows Icon first eigenvector；

Step (A1) determines the corresponding gray matrix of the icon of intended application；Wherein, above-mentioned gray matrix is by each pixel The gray value composition of point.

Specifically, the icon of application is actually a picture, it is made of multiple pixels, for example, it may be M*N picture The picture that vegetarian refreshments is constituted, wherein M indicates that the line number of pixel, N indicate the columns of pixel.

In the embodiment of the present application, the line number phase of the icon of intended application and the pixel on the icon of each application to be compared Deng the icon of intended application is equal with the columns of pixel on the icon of each application to be compared.

In above-mentioned steps (A1), in the corresponding gray matrix of the icon that determines intended application, need to obtain each picture Then the color value of vegetarian refreshments calculates the gray value of the pixel according to the color value of each pixel.

Wherein, each pixel is made of three kinds of colors of RGB (RGB), therefore, the figure of above-mentioned acquisition intended application The color value for putting on each pixel, R color values, B color values and the G color values of each pixel actually obtained.

For example, for the pixel of the i-th row, jth row on the icon of intended application, the face of the pixel of acquisition Color value is R (i, j), B (i, j) and G (i, j).

Specifically, can intended application directly be determined according to the color value of each pixel on the icon of intended application First eigenvector.But since the color value of each pixel includes three values, if directly according to the color value of pixel Data volume is larger, causes follow-up calculation amount larger, to reduce the arithmetic speed of server.Therefore, in the embodiment of the present application In, in order to improve arithmetic speed, needs to execute above-mentioned steps (A1), that is, determine the gray matrix of intended application.

Wherein, according to the color value of each pixel, the method for determining the corresponding gray matrix of the icon of intended application has It is a variety of, it is following the determination process of gray matrix to be discussed in detail by taking one of which as an example.

In a specific embodiment, being averaged for the R color values of each pixel, B color values and G color values can be calculated Value, is determined as the corresponding gray value of the pixel by the average value of the RGB color value of each pixel；Then, by intended application Put in order composition Gray Moment of the gray value of each pixel according to each pixel in the icon of intended application on icon Battle array.

Specifically, calculating the corresponding gray value of each pixel on the icon of intended application by following formula：

Wherein, in above-mentioned formula, f (i, j) indicate be positioned at the i-th row, jth arrange pixel gray value, R (i, What j), G (i, j) and B (i, j) was indicated is the color value of the pixel arranged positioned at the i-th row, jth.

After calculating the corresponding gray value of each pixel by the above method, all gray values are formed into the icon Corresponding gray matrix, wherein a kind of possible concrete form of gray matrix is as follows：

Wherein, what M was indicated is the line number of pixel on the icon of intended application, and what N was indicated is on the icon of intended application The columns of pixel, in above-mentioned matrix, the row of each gray value to put in order with the pixel on the icon of intended application Row sequence consensus.For example, being the icon positioned at intended application positioned at the gray value f (i, j) that the i-th row, jth are listed in gray matrix On the i-th row, jth row the corresponding gray value of pixel.

The determination process of above-mentioned gray matrix for ease of understanding, following will be illustrated by concrete numerical value illustrate.

For example, in a specific embodiment, the pixel region of a 2*2 on the icon of intended application is chosen, the pixel Color value beWherein, the color value of each pixel puts in order and four pictures in the matrix Vegetarian refreshments putting in order on the icon of intended application is consistent, the color value of each pixel successively according to the sequence of red, green, blue into Row arrangement, calculates the corresponding gray value of each pixel, according to color value (1,2,3) calculated gray value by above-mentioned formula It is 2, is 4 according to color value (3,4,5) calculated gray value, is 1 according to color value (0,1,2) calculated gray value, root It is 8 according to color value (7,8,9) calculated gray value, according to put in order row of four pixels on the icon of intended application Above-mentioned gray value is arranged, obtained gray matrix is

Step (A2) converts above-mentioned gray matrix to specified vector according to setting rule；Wherein, above-mentioned specified vector is Row vector, above-mentioned setting rule include being arranged in order all gray values in a row according to putting in order for pixel column in icon； Or above-mentioned specified vector is column vector, above-mentioned setting rule includes that all gray values are suitable according to the arrangement of pixel column in icon Sequence is arranged in order into a row；The number of gray value in above-mentioned specified vector is equal with the number of the gray value in gray matrix.

Specifically, in the embodiment of the present application, follow-up phase can be carried out directly using gray matrix as first eigenvector Like the calculating of angle value, still, it is inconvenient to calculate in this way, for the ease of the calculating of follow-up similarity value, then converts gray matrix For row vector, or and drops gray matrix and be converted into column vector

If above-mentioned specified vector is row vector, then need the arrangement of each pixel column in the icon according to intended application suitable Sequence arranges the corresponding gray value of all pixels row in gray matrix in a row.It is specifically, by the second row in gray matrix Gray value is arranged in behind the first row gray value, and the third line gray value is arranged in behind the second row gray value, and so on, Obtain the corresponding row vector of gray matrix.For ease of understanding, following to illustrate citing.

For example, above-mentioned gray matrix isAccording to upper It states rule and the gray matrix is converted to row vector, then the row vector after converting is：[P₁ P₂ … P_M]；Wherein, P₁It indicates It is all gray values for the first row being located in above-mentioned gray matrix, and constant, the P that puts in order of all gray values₂It indicates It is all gray values for the second row being located in above-mentioned gray matrix, and constant, the P that puts in order of all gray values_MIt indicates Be be located at above-mentioned gray matrix in M rows all gray values, and all gray values put in order it is constant；For example, P₁In Including the gray value being known as it is as follows, P₁={ f (1,1) f (1,2) ... f (1, i) ... f (1, N) }.

If above-mentioned specified vector is column vector, then need the arrangement of each pixel column in the icon according to intended application suitable All pixels in gray matrix are arranged corresponding gray value and are arranged in a row by sequence.It is specifically, by the secondary series in gray matrix Gray value is arranged in first row gray value in the following, third row gray value is arranged in below secondary series gray value, and so on, Obtain the corresponding column vector of gray matrix.For ease of understanding, following to illustrate citing.

For example, above-mentioned gray matrix isAccording to upper It states rule and the gray matrix is converted to column vector, the column vector converted is：Wherein, S₁What is indicated is positioned at upper State all gray values of the first row in gray matrix, and constant, the S that puts in order of each gray value₂What is indicated is positioned at upper State all gray values of the secondary series in gray matrix, and constant, the S that puts in order of each gray value_NWhat is indicated is positioned at upper State all gray values of Nth column in gray matrix, and each gray value put in order it is constant.

In the embodiment of the present application, in the number and original gray matrix of the gray value in the specified vector after above-mentioned conversion Gray value number it is equal.I.e. in the embodiment of the present application, during converting above-mentioned gray matrix to specified vector, Only each gray value in above-mentioned gray matrix is rearranged, does not change gray value in original gray matrix Number, and each gray value occurrence.

Above-mentioned row vector or column vector are determined as first eigenvector by step (A3).

In the embodiment of the present application, in the first eigenvector for the icon for determining intended application, it is first determined target is answered The corresponding gray matrix of icon, using the gray value of each pixel on the icon of intended application determine fisrt feature to Amount, and the calculating of follow-up similarity value is carried out, carry out similarity with the color value of each pixel in intended application is directly used Calculating compare, calculate used in data volume it is less, it is possible to reduce the operand of server, to improve arithmetic speed； In addition, in the embodiment of the present application, the vector after converting gray matrix to row vector or column vector is as fisrt feature Vector can calculate simple in this way, first eigenvector only includes a line or a row in order to the calculating of follow-up similarity value It is convenient.

In addition, in the another embodiment of the application, it is contemplated that the number of lines of pixels on the icon of intended application and row Number may be relatively more, i.e., the number of element is more in above-mentioned gray matrix, if it is special directly to generate first according to the gray matrix Sign vector, when determining the first fingerprint characteristic according to the first eigenvector, and subsequently calculating similarity according to fingerprint characteristic, Calculation amount is larger, slower so as to cause calculating speed, influences user experience.Therefore, in order to reduce subsequent calculation amount, meter is improved Calculate speed, it is desirable to reduce the number of gray value in above-mentioned gray matrix can be answered in the embodiment of the present application by compression goal The mode of icon reduces the number of the pixel on the icon of intended application, to reduce the gray value in gray matrix Number.Therefore, in the embodiment of the present application, before executing above-mentioned steps (A2), it is also necessary to execute following steps：

According to each gray value pair in the row compression multiple of setting, the row compression multiple of setting and above-mentioned gray matrix The icon of intended application is compressed, and the gray matrix of compressed icon is obtained.

Wherein, above-mentioned row compression multiple and row compression multiple can be identical, can not also be identical.In the embodiment of the present application In, as long as long as above-mentioned row compression multiple can be divided exactly by the number of lines of pixels of the icon of intended application, row compression multiple can be by The pixel columns of the icon of intended application is divided exactly.For example, it is 128*128 that the icon of above-mentioned intended application, which is size, wherein 128 indicate be intended application icon number of lines of pixels or columns, then the row compression multiple of above-mentioned selection and row compression times Several are required to be divided exactly by 128, for example, can be 16.The embodiment of the present application to above-mentioned row compression multiple and is not set The concrete numerical value of fixed row compression multiple is defined, and user row compression multiple can be chosen according to practical application scene and row are pressed The specific value of demagnification number.

Specifically, in the embodiment of the present application, can compress, obtain to the icon of intended application as follows The gray matrix of compressed icon：According to the row compression multiple of above-mentioned setting and the row compression multiple of setting, by above-mentioned target The icon of application is divided into multiple subregions；By the row of the average value and setting of the gray value of all pixels point in every sub-regions The ratio of the product of compression multiple and the row compression multiple of setting is determined as corresponding gray value after subregion compression；To own Corresponding gray value forms the gray matrix of compressed icon after subregion compression.

In a specific embodiment, the row compression multiple of above-mentioned setting is denoted as C, above-mentioned row compression multiple is denoted as D, then by the icon of above-mentioned intended application since some angle, D*C pixel of interception is as a sub-regions.For example, Fig. 2 Show a kind of division schematic diagram of the icon of above-mentioned intended application, in icon shown in Fig. 2, including 8 row pixels, 16 row pictures Element, and the row compression multiple chosen is 2, row compression multiple is 4, then is suffered since some angle of icon according to the rule of 2*4 The division for carrying out subregion.

Certainly, the above-mentioned illustrative explanation of Fig. 2 instructions, number of lines of pixels, pixel columns and row compression multiple, the row of icon The concrete numerical value of compression multiple is not limited thereto.

Specifically, in the embodiment of the present application, corresponding gray value after being compressed per sub-regions is calculated by following formula；

Wherein, in above-mentioned formula, what h (e, f) was indicated is the corresponding ash after the subregion compression that e rows, f are arranged Angle value,What is indicated is the average value of the gray value of all pixels point in above-mentioned subregion.

For ease of understanding, following will be illustrated by concrete numerical value illustrates.

For example, continuing to use the example above, it is by gray matrixAs a sub-regions, it is corresponding to calculate the subregion Gray value, in the citing, row compression multiple and row compression multiple are 2, and therefore, calculation formula is：

Therefore, in the example above, the corresponding gray value of the subregion is

In the embodiment of the present application, the icon of intended application can be carried out by compression processing by the above method, obtained The number of gray value is less in the gray matrix of compressed image, and follow-up the is carried out using the gray matrix of compressed icon The determination of one feature vector and the calculating of the similarity value of icon etc., calculation amount is less, it is possible to reduce the operation of server Amount, to improve the arithmetic speed of server.

In the embodiment of the present application, when determining the corresponding first eigenvector of the icon of intended application by the above process Afterwards, then the first fingerprint characteristic of the icon of intended application is determined according to above-mentioned first eigenvector.In the embodiment of the present application, It is above-mentioned according to first eigenvector, determine the first fingerprint characteristic, specifically include：

Calculate the average value of all gray values in first eigenvector；For each gray scale in first eigenvector Value, which is compared with above-mentioned average value, the corresponding fingerprint characteristic value of the gray value is determined according to comparison result；It will The corresponding fingerprint characteristic value of all gray values in first eigenvector is determined as the first fingerprint characteristic.

Wherein, in the embodiment of the present application, all gray values in first eigenvector are calculated by following formula to be averaged Value：

Wherein, in above-mentioned formula,What is indicated is the average value of all gray values in first eigenvector, and what Q was indicated is The number of gray value in first eigenvector, x_iWhat is indicated is i-th of gray value in first eigenvector.

After the average value for determining all gray values in first eigenvector, by each gray scale in feature vector Value is compared with above-mentioned average value, if the gray value is more than or equal to the average value of all gray values, then by the gray scale It is worth corresponding fingerprint characteristic value and is denoted as 1, it is if the gray value is less than the average value of all gray values, then the gray value is corresponding Fingerprint characteristic value is denoted as 0, it is specific as follows shown in：

Wherein, in above-mentioned formula, y_iWhat is indicated is the corresponding fingerprint characteristic of i-th of gray value in first eigenvector Value.

The corresponding fingerprint characteristic value of each gray value in first eigenvector can be obtained by the above process, it will be all Fingerprint characteristic value is arranged according to the corresponding gray value of the fingerprint characteristic value putting in order in first eigenvector, composition First fingerprint characteristic.In fact, the first fingerprint characteristic is the vector for belonging to same type with first eigenvector, if fisrt feature Vector is row vector, then the first fingerprint characteristic is also row vector, if first eigenvector is column vector, the first fingerprint characteristic For column vector.

Certainly, it can determine that the corresponding fingerprint of the icon of each application to be compared is special using with above-mentioned same method Sign, in the embodiment of the present application, the second fingerprint characteristic is denoted as by the fingerprint characteristic of the icon of each application to be compared.

In the specific implementation mode of the application, it can determine that each of application shop is answered by the above method The corresponding fingerprint characteristic of icon, and the corresponding fingerprint characteristic of the icon of the application is stored correspondingly, In this way, in the recommendation applied using method provided in an embodiment of the present invention, it can also be directly from pre-stored fingerprint The corresponding fingerprint characteristic of each application is searched in feature.

After the first fingerprint characteristic and each second fingerprint characteristic is determined, then (2) determine that target is answered through the above steps Similarity value between icon and the icon of each application to be compared.

In the embodiment of the present application, it is then specifically special according to each fingerprint in the first fingerprint characteristic in above-mentioned steps (2) Each fingerprint characteristic value in value indicative and the second fingerprint characteristic calculates the figure of the icon and each application to be compared of intended application Similarity value between mark, specifically includes：

According to each fingerprint characteristic value in each fingerprint characteristic value and the second fingerprint characteristic in the first fingerprint characteristic, lead to Cross the similarity value between the icon and the icon of application to be compared of following formula calculating intended application；

Wherein, in above-mentioned formula, A indicates that intended application, B indicate application to be compared, S_A,BIndicate the figure of the icon and B of A Similarity value between mark, F indicate the number for the fingerprint characteristic value that the first fingerprint characteristic and the second fingerprint characteristic include, y_A,i Indicate i-th of fingerprint characteristic value in the first fingerprint characteristic；y_B,iIndicate i-th of fingerprint characteristic value in the second fingerprint characteristic.

Step S106 chooses the application that similarity value meets preset condition from multiple applications to be compared, is answered as target It is applied with corresponding recommendation.

In the embodiment of the present application, the application that similarity value meets preset condition is chosen from multiple applications to be compared, is made For the corresponding recommendation application of intended application, the following two kinds situation is included at least：

The first situation chooses setting quantity according to the sequence of similarity value from high to low from multiple applications to be compared A application is as the corresponding recommendation application of intended application.

In that case, all applications to be compared can be arranged according to the sequence of above-mentioned similarity value from high in the end Then sequence intercepts setting quantity application, by the setting number from the application to be compared after sequence according to vertical sequence Amount application is as the corresponding recommendation application of intended application.

Alternatively, in that case, can also by all applications to be compared according to similarity value sequence from low to high into Row sequence, then, according to sequence interception setting quantity application from back to front from the application to be compared after sequence, by interception Quantity is set to apply as the corresponding recommendation application of intended application.

The second situation is chosen the application that similarity value is greater than or equal to given threshold from multiple applications to be compared, is made For the corresponding recommendation application of intended application.

In that case, then it is to be compared above-mentioned each similarity value with given threshold, if the similarity value More than or equal to given threshold, then applied the corresponding application of the similarity value as the corresponding recommendation of intended application.

After determining the corresponding recommendation application of intended application by method provided by the embodiments of the present application, then by intended application Corresponding recommendation application is sent to client, so that client shows above-mentioned recommendation application.

Method provided by the embodiments of the present application for ease of understanding, it is following that itself will be discussed in detail in conjunction with concrete application scene in fact The method that the recommendation application of example offer is provided.Fig. 3 is the second method flow chart provided by the embodiments of the present application for recommending application, figure Jie of above-described embodiment can be referred in method shown in 3 with the something in common of the method for the recommendation application in above-described embodiment It continues, details are not described herein again.

In method shown in Fig. 3, when downloading " Taobao " by application shop with user, recommend to belong to Taobao to user For the concrete scene of the application of identical series, the method provided by the embodiments of the present application for recommending application is introduced.Side shown in Fig. 3 Method includes at least following steps：

Step S302 obtains the icon of " Taobao " after " Taobao " relevant information acquisition request for receiving user's transmission, and The icon of application to be compared.

Wherein, can be user when checking " Taobao " in above-mentioned steps, triggering user end to server, which is sent, " to be washed in a pan The relevant information of treasured " obtains request.In the request, the mark of Taobao is carried, server can be searched according to the mark and " be washed in a pan The icon of treasured ".

In addition, the application to be compared in step S302 refers to all applications in addition to " Taobao " in application shop.

Step S304 determines that the icon of the corresponding gray matrix of " Taobao " icon and above-mentioned application to be compared is corresponding Gray matrix.

Step S306 converts above-mentioned each gray matrix to row vector according to setting rule.

Wherein, above-mentioned setting rule includes being arranged in order into all gray values according to putting in order for pixel column in icon A line.

Step S308, the row vector after " Taobao " icon is converted are determined as first eigenvector, to be compared are answered each Row vector after icon conversion is determined as second feature vector.

Step S310 determines first fingerprint characteristic of " Taobao " icon according to first eigenvector, according to each second feature Vector determines the second fingerprint characteristic of the icon of each application to be compared.

Specifically, above-mentioned determine that the detailed process of fingerprint characteristic can refer to above-described embodiment according to feature vector, herein It repeats no more.

Step S312, according to each finger in each fingerprint characteristic and the second fingerprint characteristic in the first fingerprint characteristic Line feature calculates the similarity value of " Taobao " icon and the icon of application to be compared.

Specific calculating process, with reference to above-described embodiment, details are not described herein again.

Step S314 chooses setting quantity application, as intended application pair according to the sequence of similarity value from high in the end The recommendation application answered.

Determining recommendation application is sent to client by step S316, so that client shows above-mentioned recommendation application.

Wherein, above-mentioned " Taobao " corresponding recommendation application can be " one washes in a pan ", " rural area Taobao ", " Taobao's special price version " etc., Therefore, after user is in application shop opening " Taobao ", show a kind of specific interface schematic diagram of user as shown in Figure 4.

Certainly, for the relatively more similar application of some icons of homologous series, existed using method provided by the embodiments of the present application It, can also in the case of lacking user behavior data or user behavior data being not present or lacks being discussed in detail of application User is recommended into the application of homologous series, also, the possibility for leaking choosing is relatively low.

It is to be directed to a series of application above, since the similarity of icon is larger, the method needle in the present embodiment To with a series of application for lacking user behavior data, recommendation effect can be fine.

Other than the application has good recommendation effect in above-mentioned scene, skilled artisans appreciate that at it In his plurality of application scenes, the scheme of the application can also have good recommendation effect.For example, certain user compares love to automobile It is good, when it chooses some automobile application in application shop, using the application recommended to the user of the scheme of the application, it is likely that And class application, the application of service class or amusement class application etc. are introduced in terms of automobile, the application of above-mentioned recommendation can be very The expection that the user is also complied in big degree, improves using the effect recommended.

Method provided by the embodiments of the present application, by obtaining the icon of intended application and the icon of multiple applications to be compared, It determines the similarity value of the icon of intended application and the icon of application to be compared, and similarity is chosen from multiple applications to be compared Value meets the application of preset condition, as the corresponding recommendation application of intended application；Above by the similar of the icon applied The method that degree compares realizes the recommendation of application, can largely meet the expection of user, improves using the effect recommended.

Based on the identical thinking of the method applied with above-mentioned recommendation, recommending application the embodiment of the present application also provides a kind of Device, for executing the method provided by the embodiments of the present application for recommending application.Fig. 5 applies for recommendation provided by the embodiments of the present application Device structural schematic diagram, device shown in fig. 5 includes at least：

Acquisition module 51, the icon of icon and multiple applications to be compared for obtaining intended application；

Determining module 52, for determining the phase between the icon of the intended application and the icon of each application to be compared Like angle value；

Module 53 is chosen, the application for meeting preset condition for choosing similarity value from the multiple application to be compared, As the corresponding recommendation application of the intended application.

Optionally, above-mentioned determining module 52, including：

First acquisition unit, the first fingerprint characteristic of the icon for obtaining the intended application；And it obtains each described Second fingerprint characteristic of the icon of application to be compared；

First determination unit determines the mesh for being based on first fingerprint characteristic and each second fingerprint characteristic Mark the similarity value between the icon and the icon of each application to be compared of application.

Optionally, above-mentioned first determination unit, including：

Computation subunit, for according in first fingerprint characteristic each fingerprint characteristic value and second fingerprint it is special Each fingerprint characteristic value in sign calculates the icon of the icon and the application to be compared of the intended application by following formula Between similarity value；

Wherein, in above-mentioned formula, A indicates that intended application, B indicate application to be compared, S_A,BIndicate the figure of the icon and B of A Similarity value between mark, F indicate the fingerprint characteristic value that first fingerprint characteristic and second fingerprint characteristic include Number, y_A,iIndicate i-th of fingerprint characteristic value in first fingerprint characteristic；y_B,iIndicate in second fingerprint characteristic I fingerprint characteristic value.

Optionally, above-mentioned first acquisition unit, including：

First determination subelement, the first eigenvector of the icon for determining the intended application；

Second determination subelement, for according to the first eigenvector, determining the first of the icon of the intended application Fingerprint characteristic.

Optionally, above-mentioned second determination subelement, is specifically used for：

Calculate the average value of all gray values in the first eigenvector；For every in the first eigenvector The gray value is compared by a gray value with the average value, determines that the corresponding fingerprint of the gray value is special according to comparison result Value indicative；The corresponding fingerprint characteristic value of all gray values in the first eigenvector is determined as first fingerprint characteristic.

Optionally, above-mentioned selection module 53, including：

First selection unit is selected for the sequence according to the similarity value from high in the end from multiple applications to be compared Take the application of setting quantity as the corresponding recommendation application of the intended application；

Alternatively,

Second selection unit is greater than or equal to answering for given threshold for choosing similarity value from multiple applications to be compared With as the corresponding recommendation application of the intended application.

Optionally, above-mentioned first determination subelement, is specifically used for,

Determine the corresponding gray matrix of the icon of intended application；Wherein, above-mentioned gray matrix is by each pixel Gray value forms；Above-mentioned gray matrix conversion row is specified into vector according to setting rule；Wherein, it is above-mentioned it is specified vector for row to Amount, above-mentioned setting rule includes being arranged in order all gray values in a row according to putting in order for row pixel in above-mentioned icon； Alternatively, above-mentioned specified vector is column vector, above-mentioned setting rule includes by all gray values according to row pixel in above-mentioned icon It puts in order and is arranged in order into a row；The number of gray value in above-mentioned specified vector and the gray value in above-mentioned gray matrix Number is equal；Above-mentioned specified vector is determined as first eigenvector.

Optionally, above-mentioned first determination subelement, also particularly useful for：

According to each gray value pair in the row compression multiple of setting, the row compression multiple of setting and above-mentioned gray matrix The icon of the intended application is compressed, the gray matrix of icon after being compressed.

According to the row compression multiple of the setting and the row compression multiple of the setting, the icon of intended application is divided into Multiple subregions；

By the average value of the gray value of all pixels point in every sub-regions and the row compression multiple of setting and the row of setting The ratio of the product of compression multiple is determined as corresponding gray value after subregion compression；It is corresponding after all subregions are compressed Gray value forms the gray matrix of compressed icon.

The device provided by the embodiments of the present application for recommending application, by obtaining the icon of intended application and multiple to be compared answering Icon determines the similarity value of the icon of intended application and the icon of application to be compared, and from multiple applications to be compared The application that similarity value meets preset condition is chosen, as the corresponding recommendation application of intended application；In this way, by being applied The method that the similarity of icon compares can also realize certain applications for lacking user behavior data the recommendation of application；Separately Outside, for a series of application, since the similarity of icon is larger, the method in the present embodiment is directed to a series of Shortage user behavior data application, recommendation effect is more preferably.Also, it is compared above by the similarity for the icon applied Method realize application recommendation, can largely meet the expection of user, improve using recommend effect.

Further, it is based on method shown in above-mentioned Fig. 1 to Fig. 4, the embodiment of the present application also provides a kind of recommendation applications Equipment, as shown in Figure 6.

Recommend the equipment of application that can generate bigger difference because configuration or performance are different, may include one or one Above processor 601 and memory 602, can be stored in memory 602 one or more storage application programs or Data.Wherein, memory 602 can be of short duration storage or persistent storage.The application program for being stored in memory 602 may include One or more modules (diagram is not shown), each module may include to recommending the series of computation in the equipment of application Machine executable instruction.Further, processor 601 could be provided as communicating with memory 602, in the equipment for recommending application Execute the series of computation machine executable instruction in memory 602.Recommend application equipment can also include one or one with Upper power supply 603, one or more wired or wireless network interfaces 604, one or more input/output interfaces 605, One or more keyboards 606 etc..

In a specific embodiment, it includes memory and one or more to recommend the equipment of application Program, either more than one program is stored in memory and one or more than one program may include one for one of them A or more than one module, and each module may include to recommending the series of computation machine in the equipment of application is executable to refer to Enable, and be configured to by one either more than one processor execute this or more than one program include for carry out with Lower computer executable instructions：

The application that similarity value meets preset condition is chosen from the multiple application to be compared, as the intended application Corresponding recommendation application.

Optionally, computer executable instructions when executed, the icon of the determination intended application with it is each described Similarity value between the icon of application to be compared, including：

Obtain the first fingerprint characteristic of the icon of the intended application；And obtain the icon of each application to be compared The second fingerprint characteristic；

Based on first fingerprint characteristic and each second fingerprint characteristic, the icon of the intended application and each institute are determined State the similarity value between the icon of application to be compared.

Optionally, computer executable instructions are when executed, described based on first fingerprint characteristic and each described the Two fingerprint characteristics determine the similarity value between the icon of the intended application and the icon of each application to be compared, including：

According to each fingerprint in each fingerprint characteristic value and second fingerprint characteristic in first fingerprint characteristic Characteristic value calculates the similarity between the icon of the intended application and the icon of the application to be compared by following formula Value；

Optionally, when executed, the first of the icon for obtaining the intended application refers to computer executable instructions Line feature, including：

Determine the first eigenvector of the icon of the intended application；

According to the first eigenvector, the first fingerprint characteristic of the icon of the intended application is determined.

Optionally, computer executable instructions are when executed, described according to the first eigenvector, determine the mesh The first fingerprint characteristic of the icon of application is marked, including：

Calculate the average value of all gray values in the first eigenvector；

For each gray value in the first eigenvector, which is compared with the average value, root The corresponding fingerprint characteristic value of the gray value is determined according to comparison result；

It is special that the corresponding fingerprint characteristic value of all gray values in the first eigenvector is determined as first fingerprint Sign.

Optionally, when executed, the first of the icon of the determination intended application is special for computer executable instructions Sign vector, including：

Determine the corresponding gray matrix of the icon of the intended application；Wherein, the gray matrix is by each pixel The gray value composition of point；

It converts the gray matrix to specified vector according to setting rule；Wherein, the specified vector is row vector, institute It includes being arranged in order all gray values in a row according to putting in order for row pixel in the icon to state setting rule；Alternatively, The specified vector is column vector, and the setting rule includes that all gray values are suitable according to the arrangement of row pixel in the icon Sequence is arranged in order into a row；The number phase of the number and the gray value in the gray matrix of gray value in the specified vector Deng；

The specified vector is determined as the first eigenvector.

Optionally, computer executable instructions are when executed, described to convert the gray matrix according to setting rule Before specified vector, the method further includes：

According to each gray value pair in the row compression multiple of setting, the row compression multiple of setting and the gray matrix The icon of the intended application is compressed, and the gray matrix of compressed icon is obtained.

Optionally, computer executable instructions when executed, the row compression multiple according to setting, setting row pressure Each gray value in demagnification number and the gray matrix compresses the icon of the intended application, obtains compressed The gray matrix of icon, including：

According to the row compression multiple of the setting and the row compression multiple of the setting, the icon of the intended application is drawn It is divided into multiple subregions；

By the average value of the gray value of all pixels point in every sub-regions and the row compression multiple of the setting and described The ratio of the product of the row compression multiple of setting is determined as corresponding gray value after subregion compression；

Corresponding gray value forms the gray matrix of compressed icon after all subregions are compressed.

Optionally, computer executable instructions when executed, it is described from the multiple application to be compared choose described in Similarity value meets the application of preset condition, as the corresponding recommendation application of the intended application, including：

According to the sequence of the similarity value from high in the end, setting quantity is chosen from the multiple application to be compared and is answered It is used as the corresponding recommendation application of the intended application；

Alternatively,

The application that the similarity value is greater than or equal to given threshold is chosen from the multiple application to be compared, as institute State the corresponding recommendation application of intended application.

The equipment provided by the embodiments of the present application for recommending application, by obtaining the icon of intended application and multiple to be compared answering Icon determines the similarity value of the icon of intended application and the icon of application to be compared, and from multiple applications to be compared The application that similarity value meets preset condition is chosen, as the corresponding recommendation application of intended application；In this way, by being applied The method that the similarity of icon compares can also realize certain applications for lacking user behavior data the recommendation of application；Separately Outside, for a series of application, since the similarity of icon is larger, the method in the present embodiment is directed to a series of Shortage user behavior data application, recommendation effect is more preferably.Also, it is compared above by the similarity for the icon applied Method realize application recommendation, can largely meet the expection of user, improve using recommend effect.

Further, it is based on method shown in above-mentioned Fig. 1 to Fig. 4, the embodiment of the present application also provides a kind of storage medium, For storing computer executable instructions, in a kind of specific embodiment, which can be USB flash disk, CD, hard disk etc., The computer executable instructions of storage medium storage can realize following below scheme when being executed by processor：

Optionally, the computer executable instructions of storage medium storage are when being executed by processor, described in the determination Similarity value between the icon of intended application and the icon of each application to be compared, including：

Optionally, the computer executable instructions of storage medium storage are described based on described when being executed by processor First fingerprint characteristic and each second fingerprint characteristic determine the figure of the icon and each application to be compared of the intended application Similarity value between mark, including：

Optionally, the computer executable instructions of storage medium storage are when being executed by processor, described in the acquisition First fingerprint characteristic of the icon of intended application, including：

Determine the first eigenvector of the icon of the intended application；

Optionally, the computer executable instructions of storage medium storage are when being executed by processor, described in the basis First eigenvector determines the first fingerprint characteristic of the icon of the intended application, including：

Calculate the average value of all gray values in the first eigenvector；

Optionally, the computer executable instructions of storage medium storage are when being executed by processor, described in the determination The first eigenvector of the icon of intended application, including：

The specified vector is determined as the first eigenvector.

Optionally, the computer executable instructions of storage medium storage are described according to setting when being executed by processor Before rule converts the gray matrix to specified vector, the method further includes：

Optionally, the computer executable instructions of storage medium storage are described according to setting when being executed by processor Row compression multiple, setting row compression multiple and each gray value in the gray matrix to the figure of the intended application Mark is compressed, and the gray matrix of compressed icon is obtained, including：

Optionally, the computer executable instructions of storage medium storage are described from described more when being executed by processor The application that the similarity value meets preset condition is chosen in a application to be compared, is answered as the corresponding recommendation of the intended application With, including：

Alternatively,

The computer executable instructions stored in storage medium provided by the embodiments of the present application lead to when being executed by processor The icon for crossing the icon and multiple applications to be compared that obtain intended application, determines the figure of the icon and application to be compared of intended application Target similarity value, and selection similarity value meets the application of preset condition from multiple applications to be compared, as intended application Corresponding recommendation application；In this way, lacking user behavior for certain by the method that the similarity for the icon applied compares The application of data can also realize the recommendation of application；In addition, for a series of application, since the similarity of icon is larger, Therefore, the method in the present embodiment is directed to a series of application for lacking user behavior data, and recommendation effect is more preferably；Also, The recommendation that application is realized above by the method that the similarity for the icon applied compares, can largely meet user Expection, improve using recommend effect.

In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example, Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit. Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device (Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " patrols Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development, And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language (Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL (Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL (Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language) etc., VHDL (Very-High-Speed are most generally used at present Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages, The hardware circuit for realizing the logical method flow can be readily available.

Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can Read medium, logic gate, switch, application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), the form of programmable logic controller (PLC) and embedded microcontroller, the example of controller includes but not limited to following microcontroller Device：ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, are deposited Memory controller is also implemented as a part for the control logic of memory.It is also known in the art that in addition to Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic Controller is obtained in the form of logic gate, switch, application-specific integrated circuit, programmable logic controller (PLC) and embedded microcontroller etc. to come in fact Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions For either the software module of implementation method can be the structure in hardware component again.

System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity, Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment The combination of equipment.

For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this The function of each unit is realized can in the same or multiple software and or hardware when application.

It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application Apply the form of example.Moreover, the application can be used in one or more wherein include computer usable program code computer The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) The form of product.

The application is with reference to method, the flow of equipment (system) and computer program product according to the embodiment of the present application Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.

These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or The function of being specified in multiple boxes.

These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one The step of function of being specified in a box or multiple boxes.

In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net Network interface and memory.

Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/or The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium Example.

Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method Or technology realizes information storage.Information can be computer-readable instruction, data structure, the module of program or other data. The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, tape magnetic disk storage or other magnetic storage apparatus Or any other non-transmission medium, it can be used for storage and can be accessed by a computing device information.As defined in this article, it calculates Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.

It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability Including so that process, method, commodity or equipment including a series of elements include not only those elements, but also wrap Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wanted including described There is also other identical elements in the process of element, method, commodity or equipment.

It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program product. Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) Formula.

The application can describe in the general context of computer-executable instructions executed by a computer, such as program Module.Usually, program module includes routines performing specific tasks or implementing specific abstract data types, program, object, group Part, data structure etc..The application can also be put into practice in a distributed computing environment, in these distributed computing environments, by Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with In the local and remote computer storage media including storage device.

Each embodiment in this specification is described in a progressive manner, identical similar portion between each embodiment Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality For applying example, since it is substantially similar to the method embodiment, so description is fairly simple, related place is referring to embodiment of the method Part explanation.

Above is only an example of the present application, it is not intended to limit this application.For those skilled in the art For, the application can have various modifications and variations.It is all within spirit herein and principle made by any modification, equivalent Replace, improve etc., it should be included within the scope of claims hereof.

Claims

1. a kind of method for recommending application, which is characterized in that the method includes：

The application that the similarity value meets preset condition is chosen from the multiple application to be compared, as the intended application Corresponding recommendation application.

2. the method as described in claim 1, which is characterized in that the icon of the determination intended application described waits comparing with each To the similarity value between the icon of application, including：

Obtain the first fingerprint characteristic of the icon of the intended application；And obtain each application to be compared icon the Two fingerprint characteristics；

Based on first fingerprint characteristic and each second fingerprint characteristic, determine that the icon of the intended application described is waited for each Compare the similarity value between the icon of application.

3. method as claimed in claim 2, which is characterized in that described to be referred to each described second based on first fingerprint characteristic Line feature determines the similarity value between the icon of the intended application and the icon of each application to be compared, including：

According to each fingerprint characteristic in each fingerprint characteristic value and second fingerprint characteristic in first fingerprint characteristic Value, the similarity value between the icon of the intended application and the icon of the application to be compared is calculated by following formula；

Wherein, in above-mentioned formula, A indicates that intended application, B indicate application to be compared, S_A,BIndicate A icon and B icon it Between similarity value, F indicates the number for the fingerprint characteristic value that first fingerprint characteristic and second fingerprint characteristic include, y_A,iIndicate i-th of fingerprint characteristic value in first fingerprint characteristic；y_B,iIndicate i-th of finger in second fingerprint characteristic Line characteristic value.

4. method as claimed in claim 2, which is characterized in that the first fingerprint of the icon for obtaining the intended application is special Sign, including：

Determine the first eigenvector of the icon of the intended application；

5. method as claimed in claim 4, which is characterized in that it is described according to the first eigenvector, determine the target First fingerprint characteristic of the icon of application, including：

Calculate the average value of all gray values in the first eigenvector；

For each gray value in the first eigenvector, which is compared with the average value, according to than The corresponding fingerprint characteristic value of the gray value is determined compared with result；

The corresponding fingerprint characteristic value of all gray values in the first eigenvector is determined as first fingerprint characteristic.

6. method as claimed in claim 4, which is characterized in that the fisrt feature of the icon of the determination intended application to Amount, including：

Determine the corresponding gray matrix of the icon of the intended application；Wherein, the gray matrix by each pixel gray scale Value composition；

It converts the gray matrix to specified vector according to setting rule；Wherein, the specified vector is row vector, described to set Set pattern includes then being arranged in order all gray values in a row according to putting in order for row pixel in the icon；Alternatively, described Specified vector is column vector, the setting rule include by all gray values according in the icon row pixel put in order according to It is secondary to be arranged in a row；The number of gray value in the specified vector is equal with the number of the gray value in the gray matrix；

The specified vector is determined as the first eigenvector.

7. method as claimed in claim 6, which is characterized in that described to convert the gray matrix to finger according to setting rule Before orientation amount, the method further includes：

According to each gray value in the row compression multiple of setting, the row compression multiple of setting and the gray matrix to described The icon of intended application is compressed, and the gray matrix of compressed icon is obtained.

8. the method for claim 7, which is characterized in that described to be compressed according to the row compression multiple of setting, the row of setting Each gray value in multiple and the gray matrix compresses the icon of the intended application, obtains compressed figure Target gray matrix, including：

According to the row compression multiple of the setting and the row compression multiple of the setting, the icon of the intended application is divided into Multiple subregions；

By the average value of the gray value of all pixels point in every sub-regions and the row compression multiple of the setting and the setting Row compression multiple product ratio be determined as the subregion compression after corresponding gray value；

9. the method as described in claim 1, which is characterized in that it is described chosen from the multiple application to be compared it is described similar Angle value meets the application of preset condition, as the corresponding recommendation application of the intended application, including：

According to the sequence of the similarity value from high in the end, setting quantity application is chosen from the multiple application to be compared and is made For the corresponding recommendation application of the intended application；

Alternatively,

The application that the similarity value is greater than or equal to given threshold is chosen from the multiple application to be compared, as the mesh The corresponding recommendation of mark application is applied.

10. a kind of device for recommending application, which is characterized in that described device includes：

Determining module, the similarity between icon and the icon of each application to be compared for determining the intended application Value；

Module is chosen, the application for meeting preset condition for choosing the similarity value from the multiple application to be compared is made For the corresponding recommendation application of the intended application.

11. device as claimed in claim 10, which is characterized in that the determining module, including：

First acquisition unit, the first fingerprint characteristic of the icon for obtaining the intended application；And it obtains and each described waits comparing To the second fingerprint characteristic of the icon of application；

First determination unit determines that the target is answered for being based on first fingerprint characteristic and each second fingerprint characteristic Similarity value between icon and the icon of each application to be compared.

12. device as claimed in claim 11, which is characterized in that first determination unit includes：

Computation subunit, for according in each fingerprint characteristic value and second fingerprint characteristic in first fingerprint characteristic Each fingerprint characteristic value, calculated between the icon of the intended application and the icon of the application to be compared by following formula Similarity value；

13. device as claimed in claim 11, which is characterized in that the first acquisition unit, including：

Second determination subelement, for according to the first eigenvector, determining the first fingerprint of the icon of the intended application Feature.

14. device as claimed in claim 13, which is characterized in that second determination subelement is specifically used for：

Calculate the average value of all gray values in the first eigenvector；For each ash in the first eigenvector Angle value, which is compared with the average value, and the corresponding fingerprint characteristic value of the gray value is determined according to comparison result； The corresponding fingerprint characteristic value of all gray values in the first eigenvector is determined as first fingerprint characteristic.

15. device as claimed in claim 10, which is characterized in that the selection module, including：

First selection unit is selected for the sequence according to the similarity value from high in the end from the multiple application to be compared Take the application of setting quantity as the corresponding recommendation application of the intended application；

Alternatively,

Second selection unit is greater than or equal to given threshold for choosing the similarity value from the multiple application to be compared Application, as the intended application corresponding recommendation application.

16. a kind of equipment for recommending application, which is characterized in that including：

Processor；And

It is arranged to the memory of storage computer executable instructions, the executable instruction makes the processing when executed Device：

17. a kind of storage medium, for storing computer executable instructions, which is characterized in that the executable instruction is being held Following below scheme is realized when row：