CN106709027A

CN106709027A - Picture recommending method and device

Info

Publication number: CN106709027A
Application number: CN201611235929.8A
Authority: CN
Inventors: 沈显超
Original assignee: Beijing Xiaomi Mobile Software Co Ltd
Current assignee: Beijing Xiaomi Mobile Software Co Ltd
Priority date: 2016-12-28
Filing date: 2016-12-28
Publication date: 2017-05-24
Anticipated expiration: 2036-12-28
Also published as: CN106709027B

Abstract

The invention relates to a picture recommending method and device. The method comprises the following steps: analyzing features of a targeted picture to obtain feature information of the targeted picture; transmitting the feature information of the targeted picture to a server; and when similar matching is carried out by the server according to the feature information of the targeted picture to obtain a matched picture, receiving the matched picture or a thumbnail of the matched picture from the server. Therefore, when a user checks pictures, picture recommending to the pictures can be obtained, the recommended pictures can be stored, the time on searching of the pictures is saved, and the efficiency is improved for the user.

Description

Picture recommendation method and device

Technical field

This disclosure relates to moving communicating field, more particularly to a kind of picture recommendation method and device.

Background technology

At present, the picture in terminal is more and more, and has many pictures for repeating, and user is difficult among these pictures Pick out best one；In addition, may there are many similar pictures to be clapped better than user in the photo of terminal taking for user The picture taken the photograph, user cannot easily obtain the similar pictures better than original picture.

The content of the invention

To overcome problem present in correlation technique, the disclosure to provide a kind of picture recommendation method and device.

According to the first aspect of the embodiment of the present disclosure, there is provided a kind of picture recommendation method, for terminal, including：To target Picture carries out signature analysis, obtains the characteristic information of the Target Photo；The feature for sending the Target Photo to server is believed Breath；When server carries out Similarity matching according to the characteristic information of the Target Photo obtains matching picture, receive from service The matching picture of device or the thumbnail of the matching picture.

Alternatively, it is described that signature analysis is carried out to Target Photo, can include：The Target Photo is shown in the terminal When reaching Preset Time or receiving request recommendation instruction, signature analysis is carried out to the Target Photo, obtain the target The characteristic information of picture.

Alternatively, in the case where the thumbnail of the matching picture from server is received, methods described can be with Including：Generate about whether the prompting message for agreeing to the selection matching picture；When agreement instruction is received, sent out to server Send matching picture download request；Receive the matching picture sent in response to the server of the matching picture download request.

Alternatively, in the case where the matching picture from server is received, methods described can also include：Generation About whether the prompting message for agreeing to the selection matching picture；When receiving the first agreement and instructing, described in terminal storage With picture.

Alternatively, methods described can also include：When receive to it is described matching picture or the matching picture breviary During the refusal selection instruction of figure, the matching picture or the thumbnail of the matching picture that deletion is received.

Alternatively, methods described can also include：When server carried out according to the characteristic information of the Target Photo it is similar When matching cannot obtain matching picture, the Target Photo upload request that the reception server sends；Generation is uploaded about whether agreement Prompting message；When the second agreement instruction is received, the Target Photo is sent to server.

Alternatively, methods described can also include：The optimization picture of the Target Photo that the reception server sends, its In, the optimization picture is obtained after the Target Photo of the server to receiving optimizes treatment.

According to the second aspect of the embodiment of the present disclosure, there is provided a kind of picture recommendation method, for server, including：Receive The characteristic information of Target Photo；Characteristic information according to the Target Photo carries out similar to the picture stored in database Match somebody with somebody, to determine to match picture with the presence or absence of with the characteristic information of the Target Photo matches in database；Matched when existing During picture, the thumbnail of the matching picture or the matching picture is sent.

Alternatively, methods described can also include：Receive matching picture download request；Send the matching picture.

Alternatively, methods described can also include：When server carried out according to the characteristic information of the Target Photo it is similar When matching cannot obtain matching picture, Target Photo upload request is sent.

Alternatively, after the step of the transmission Target Photo upload request, methods described can also include：Receive described Target Photo；By Target Photo storage in database.

Alternatively, methods described can also include：The characteristic information of the Target Photo is stored in database.

Alternatively, methods described can also include：The Target Photo is optimized；By the optimization of the Target Photo Picture is sent to terminal.

Alternatively, the characteristic information of the Target Photo includes the classification and picture feature value of Target Photo, also, described Characteristic information according to the Target Photo carries out Similarity matching to the picture stored in database, can include：To data The picture stored in storehouse carries out signature analysis, the classification and picture feature value of the picture for having been stored；In classification and target In the picture that the classification identical of picture has been stored, it is determined whether there is the corresponding picture feature value of one or more picture in institute State in the approximate extents of Target Photo characteristic value；Described there is the corresponding picture feature value of one or more picture in institute when existing State in the approximate extents of Target Photo characteristic value, then select a pictures as matching figure from one or more picture Piece.

Alternatively, the characteristic information according to the Target Photo carries out similar to the picture stored in database Match somebody with somebody, can also include：When in the absence of described special in the Target Photo in the presence of the corresponding picture feature value of one or more picture In the approximate extents of value indicative, then confirm to obtain matching picture.

According to the third aspect of the embodiment of the present disclosure, there is provided a kind of picture recommendation apparatus, for terminal, including：Feature point Analysis module, is configured as carrying out signature analysis to Target Photo, obtains the characteristic information of the Target Photo；Characteristic information sends Module, is configured as being sent to server the characteristic information of the Target Photo；First receiver module, is configured as server Characteristic information according to the Target Photo carry out Similarity matching obtain matching picture when, receive the matching from server The thumbnail of picture or the matching picture.

Alternatively, the characteristics analysis module can be additionally configured to show that the Target Photo reaches in the terminal pre- If the time or receive request recommend instruction when, signature analysis is carried out to the Target Photo, obtain the Target Photo Characteristic information.

Alternatively, it is configured as receiving the thumbnail of the matching picture from server in first receiver module In the case of, described device can also include：Prompting generation module, is configurable to generate about whether the agreement selection matching The prompting message of picture；Download request sending module, when being configured as receiving agreement instruction, matching figure is sent to server Piece download request；Second receiver module, is configured as receiving what is sent in response to the server of the matching picture download request Matching picture.

Alternatively, it is configured as receiving the situation of the matching picture from server in first receiver module Under, described device can also include：Prompting generation module, is configurable to generate about whether the agreement selection matching picture Prompting message；Memory module, when being configured as receiving the first agreement instruction, picture is matched described in terminal storage.

Alternatively, described device can also include：Removing module, is configured as receiving to matching picture or the institute During the refusal selection instruction of the thumbnail for stating matching picture, the contracting of the matching picture or the matching picture that deletion is received Sketch map.

Alternatively, described device can also include：Upload request receiver module, is configured as server according to the mesh Mark on a map piece characteristic information carry out Similarity matching cannot obtain matching picture when, the reception server send Target Photo upload please Ask；Prompting generation module is uploaded, is configurable to generate about whether the prompting message for agreeing to upload；Uploading pictures sending module, When being configured as receiving the second agreement instruction, the Target Photo is sent to server.

Alternatively, described device can also include：Optimization picture receiver module, is configured as the institute of the reception server transmission The optimization picture of Target Photo is stated, wherein, the optimization picture is that the Target Photo of the server to receiving is optimized Obtained after treatment.

According to the fourth aspect of the embodiment of the present disclosure, there is provided a kind of picture recommendation apparatus, for server, including：Feature Information receiving module, is configured as receiving the characteristic information of Target Photo；Similarity matching module, is configured as according to the target The characteristic information of picture carries out Similarity matching to the picture stored in database, with determine to whether there is in database with it is described The matching picture that the characteristic information of Target Photo matches；First sending module, when being configured as existing matching picture, sends The thumbnail of the matching picture or the matching picture.

Alternatively, described device can also include：Download request receiver module, being configured as reception matching picture download please Ask；Second sending module, is configured as sending the matching picture.

Alternatively, described device can also include：Upload request sending module, is configured as server according to the mesh Mark on a map piece characteristic information carry out Similarity matching cannot obtain matching picture when, send Target Photo upload request.

Alternatively, described device can also include：Uploading pictures receiver module, is configured as receiving the Target Photo； Uploading pictures memory module, is configured as Target Photo storage in database.

Alternatively, described device can also include：Uploading pictures characteristic storage module, is configured as the Target Photo Characteristic information store in database.

Alternatively, described device can also include：Uploading pictures optimization module, is configured as carrying out the Target Photo Optimization；Optimization picture sending module, is configured as sending the optimization picture of the Target Photo to terminal.

Alternatively, the characteristic information of the Target Photo includes the classification and picture feature value of Target Photo, also, described Similarity matching module, including：Signature analysis submodule, is configured as carrying out signature analysis to the picture stored in database, The classification and picture feature value of the picture for having been stored；Approximate picture determination sub-module, is configured as in classification and target figure In the picture that the classification identical of piece has been stored, it is determined whether there is the corresponding picture feature value of one or more picture described In the approximate extents of Target Photo characteristic value；Picture selects submodule, is configured as the presence of one or more figure of the presence The corresponding picture feature value of piece is then selected in the approximate extents of the Target Photo characteristic value from one or more picture A pictures are selected as matching picture.

Alternatively, the Similarity matching module can also include：It fails to match confirms submodule, is configured as not existing It is described to there is the corresponding picture feature value of one or more picture in the approximate extents of the Target Photo characteristic value, then confirm Cannot obtain matching picture.

A kind of the 5th aspect according to the embodiment of the present disclosure, there is provided picture recommendation apparatus, including：Processor；For storing The memory of processor-executable instruction；Wherein, the processor is configured as：Signature analysis is carried out to Target Photo, is obtained The characteristic information of the Target Photo；The characteristic information of the Target Photo is sent to server；When server is according to the mesh Mark on a map piece characteristic information carry out Similarity matching obtain matching picture when, receive the matching picture or described from server Match the thumbnail of picture.

A kind of the 6th aspect according to the embodiment of the present disclosure, there is provided picture recommendation apparatus, including：Processor；For storing The memory of processor-executable instruction；Wherein, the processor is configured as：Receive the characteristic information of Target Photo；According to Whether the characteristic information of the Target Photo carries out Similarity matching to the picture stored in database, to determine deposited in database Picture is matched what the characteristic information with the Target Photo matched；When there is matching picture, the matching picture is sent Or the thumbnail of the matching picture.

The 7th aspect according to the embodiment of the present disclosure, there is provided a kind of non-transitorycomputer readable storage medium, when described Instruction in storage medium by terminal computing device when so that terminal is able to carry out a kind of picture recommendation method, the side Method includes：Signature analysis is carried out to Target Photo, the characteristic information of the Target Photo is obtained；The target is sent to server The characteristic information of picture；When server carries out Similarity matching according to the characteristic information of the Target Photo obtains matching picture, Receive the thumbnail of the matching picture or the matching picture from server.

According to the eighth aspect of the embodiment of the present disclosure, there is provided a kind of non-transitorycomputer readable storage medium, when described Instruction in storage medium by server computing device when so that server is able to carry out a kind of picture recommendation method, institute The method of stating includes：Receive the characteristic information of Target Photo；Characteristic information according to the Target Photo in database to having stored Picture carry out Similarity matching, to determine to whether there is and matching that the characteristic information of the Target Photo matches in database Picture；When there is matching picture, the thumbnail of the matching picture or the matching picture is sent.

The technical scheme provided by this disclosed embodiment can include the following benefits：By in terminal-pair Target Photo Signature analysis, the characteristic information that will be obtained sends the picture stored into server and server and carries out Similarity matching, obtain To the picture similar to Target Photo and the picture is sent back into terminal recommend user, allow users to easily obtain and mesh Other similar pictures of piece of marking on a map, are the step of user saves deliberately search pictures, improve efficiency.

It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not The disclosure can be limited.

Brief description of the drawings

Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows the implementation for meeting the disclosure Example, and it is used to explain the principle of the disclosure together with specification.

Fig. 1 is a kind of schematic diagram of the implementation environment according to an exemplary embodiment.

Fig. 2 is a kind of flow chart of the picture recommendation method according to an exemplary embodiment.

Fig. 3 A are a kind of flow charts of the picture recommendation method according to another exemplary embodiment.

Fig. 3 B are a kind of flow charts of the picture recommendation method according to another exemplary embodiment.

Fig. 4 A are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.

Fig. 4 B are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.

Fig. 5 A are a kind of flow charts of the picture recommendation method according to another exemplary embodiment.

Fig. 5 B are a kind of flow charts of the picture recommendation method according to another exemplary embodiment.

Fig. 6 A are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.

Fig. 6 B are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.

Fig. 7 A are a kind of flow charts of the picture recommendation method according to another exemplary embodiment.

Fig. 7 B are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.

Fig. 8 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment.

Fig. 9 is a kind of flow chart of the picture recommendation method according to an exemplary embodiment.

Figure 10 is a kind of flow chart of the picture recommendation method according to an exemplary embodiment.

Figure 11 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment.

Figure 12 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment.

Figure 13 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment.

Figure 14 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment.

Figure 15 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment.

Figure 16 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment.

Figure 17 is a kind of block diagram of the picture recommendation apparatus according to an exemplary embodiment.

Figure 18 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 19 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 20 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 21 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 22 is a kind of block diagram of the picture recommendation apparatus according to an exemplary embodiment.

Figure 23 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 24 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 25 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 26 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 27 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 28 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 29 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.

Figure 30 is a kind of block diagram of the picture recommendation apparatus according to an exemplary embodiment.

Figure 31 is a kind of block diagram of the picture recommendation apparatus according to an exemplary embodiment.

Specific embodiment

Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment Described in implementation method do not represent all implementation methods consistent with the disclosure.Conversely, they be only with it is such as appended The example of the consistent apparatus and method of some aspects described in detail in claims, the disclosure.

Fig. 1 is a kind of schematic diagram of the implementation environment according to an exemplary embodiment.As shown in figure 1, the implementation ring Border can include：Terminal 110 and server 120.Wherein, be configured with communication module in terminal 110, for server 120 Communicated.Illustratively, terminal 110 and server 120 can via such as bluetooth, ZigBee-network, WiFi network, 2G networks, 3G network, 4G networks etc. are communicated.Terminal 110 can be such as smart mobile phone, panel computer, personal digital assistant (PDA), PC Machine, notebook computer etc..With terminal 110 it is smart mobile phone in Fig. 1 to illustrate.

Fig. 2 is a kind of flow chart of the picture recommendation method according to an exemplary embodiment.As shown in Fig. 2 the party Method is applied in terminal, is comprised the following steps.

In step 201, signature analysis is carried out to Target Photo, obtains the characteristic information of the Target Photo.

Terminal can carry out signature analysis to Target Photo and obtain corresponding characteristic information.Wherein, the signature analysis Can include to the category analysis and Eigenvalues analysis of Target Photo, the characteristic information can include the classification of Target Photo and Characteristic value, the classification of the Target Photo can be such as landscape, personage, animal classification, and the characteristic value is the target figure The characteristic value of the vector matrix of piece, is corresponding with the Target Photo.

Alternatively, the signature analysis is to show that the Target Photo reaches Preset Time or receives in the terminal Request recommends what is started during instruction.Wherein, the Preset Time can be a time period, i.e. when terminal shows the target When the time of picture is more than or equal to the Preset Time, the condition that user triggers picture recommendation, Ke Yikai can be considered as Beginning carries out the first step of picture recommendation, i.e., carry out signature analysis to Target Photo；In addition, user can also check picture in terminal When actively send request recommend instruction, when terminal receives the instruction, can be considered as user trigger picture recommendation condition, The first step of picture recommendation can be proceeded by, i.e., signature analysis is carried out to Target Photo.

In step 202., the characteristic information of the Target Photo is sent to server.

Terminal will be sent to server to the characteristic information that Target Photo obtained after signature analysis, for server In the characteristic information of picture that has stored carry out Similarity matching.

In step 203, matching figure is obtained when server carries out Similarity matching according to the characteristic information of the Target Photo During piece, the thumbnail of the matching picture or the matching picture from server is received.

Similarity matching is main to be completed in server end, and the characteristic information of the Target Photo sent according to terminal when server is looked for To similar with the Target Photo when matching picture, server will send the matching picture or the matching picture to terminal Thumbnail, thumbnail of the terminal then to the matching picture or matching picture is received.Wherein, the breviary of the matching picture Figure is the compressed version of the matching picture, on the premise of it can roughly show the matching picture, relative to the matching The memory headroom that picture takes is smaller, therefore has efficiency of transmission benefit high in transmission.

Fig. 3 A are a kind of flow charts of the picture recommendation method according to another exemplary embodiment.As shown in Figure 3A, In this embodiment, after server carries out Similarity matching, what terminal was received is the breviary of the matching picture that server sends Figure, specifically：

In step 201, signature analysis is carried out to Target Photo, obtains the characteristic information of the Target Photo；

In step 202., the characteristic information of the Target Photo is sent to server；

In step 203-1, matched when server carries out Similarity matching according to the characteristic information of the Target Photo During picture, the thumbnail of the matching picture from server is received；

In step 204, generation is about whether the prompting message for agreeing to the selection matching picture；

In step 205, when agreement instruction is received, matching picture download request is sent to server；

In step 206, terminal receives the matching picture sent in response to the server of the matching picture download request.

In this embodiment, it is necessary to by user after the thumbnail of the matching picture of the terminal reception from server Determine whether the corresponding matching picture of thumbnail of the download matching picture, therefore terminal needs generation to be selected about whether agreement The prompting message of the matching picture, is displayed on the interface of terminal, when user's selection is agreed to download, that is to say, that terminal connects When receiving agreement instruction, the download request to matching picture, and following the reception server are sent according to the download request The matching picture for sending.So, user can be by checking that the thumbnail of the matching picture determines whether to agree to download to be somebody's turn to do Matching picture, it is directly perceived succinct.

Certainly, user can also select refusal to download the matching picture.Fig. 3 B are shown according to another exemplary embodiment A kind of flow chart of the picture recommendation method for going out.In the embodiment of Fig. 3 B, step 201, step 202, step 203-1, step 204 is identical with the embodiment of Fig. 3 A, unlike, in addition to being likely to be received and agreeing to instruction, terminal can be can receive Refusal instruction, i.e. also include：

In step 207, when the refusal selection instruction to the thumbnail of the matching picture is received, deletion is received The matching picture thumbnail.

Herein, user have selected refusal download after seeing prompting message, and terminal receives meeting after refusal selection instruction The thumbnail of the matching picture is deleted, the photo current to the Target Photo recommends scene to terminate.So, user is by looking into The thumbnail of the matching picture is seen, can be directly selected when user is unsatisfied with the matching picture and be refused the picture, and Thumbnail is deleted, the data space that picture thumbnail takes is small and transmission speed is fast, can so be saved under mistake for user Carry the time of picture.

Fig. 4 A are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.Corresponding to Fig. 3 A Embodiment, Fig. 4 A illustrate server to terminal send Target Photo matching picture thumbnail in the case of, Yong Hutong Signalling exchange during the meaning selection matching picture.It is related to user, terminal and server three in the interaction Individual object, in the case where picture recommendation condition is triggered：Terminal-pair Target Photo carries out signature analysis, obtains the Target Photo Characteristic information；The characteristic information of the Target Photo to server is sent to server；When server is according to the target figure The characteristic information of piece carry out Similarity matching obtain matching picture when, to terminal send it is described matching picture thumbnail；Terminal connects After receiving the thumbnail of the Target Photo, generation is about whether the prompting message for agreeing to the selection matching picture；User passes through Terminal checks the thumbnail of the matching picture, in the case where the thumbnail of the matching picture is pleased with, can select same Meaning, i.e., send to terminal and agree to instruction；After terminal receives the agreement instruction, matching picture can be sent to server and downloaded Request；Server sends the matching picture in response to the request to terminal.

Fig. 4 B are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.Corresponding to Fig. 3 B Embodiment, Fig. 4 B illustrate server to terminal send Target Photo matching picture thumbnail in the case of, user refuses The Signalling exchange during the matching picture is downloaded absolutely.It is related to user, terminal and server three in the interaction Individual object, in the example of Fig. 4 B, terminal-pair Target Photo carries out signature analysis, terminal to server and sends characteristic information, clothes The signaling that business device carries out thumbnail from matching picture to terminal and terminal generation prompting message that Similarity matching, server send is handed over Example mutually with Fig. 4 A is identical, unlike, user can also send refusal selection instruction to terminal, and terminal refers to receiving this After order, the thumbnail of matching picture can be deleted.

Fig. 5 A are a kind of flow charts of the picture recommendation method according to another exemplary embodiment.As shown in Figure 5A, After server carries out Similarity matching in this embodiment, what terminal was received is the matching picture that server sends, it is specific and Speech：

In step 203-2, matched when server carries out Similarity matching according to the characteristic information of the Target Photo During picture, the matching picture from server is received；

In a step 208, when the first agreement instruction is received, picture is matched described in terminal storage.

In this embodiment, it is necessary to be determined whether by user after the matching picture of the terminal reception from server The matching picture is stored, therefore terminal needs generation about whether the prompting message for agreeing to the selection matching picture, is displayed in On the interface of terminal, when storage is agreed in user's selection, that is to say, that when terminal receives agreement instruction, the matching figure is stored Piece.So, user can be quickly obtained matching picture, be easy to user to be stored.

Certainly, user can also select the refusal storage matching picture.Fig. 5 B are shown according to another exemplary embodiment A kind of flow chart of the picture recommendation method for going out.In the embodiment of Fig. 5 B, step 201, step 202, step 203-2, step 204th, step 208 is identical with the embodiment of Fig. 5 A, unlike, in addition to being likely to be received and agreeing to instruction, terminal can also connect Receive refusal instruction, i.e. also include：

In step 209, when the refusal selection instruction to the matching picture is received, described for receiving is deleted With picture.

Herein, user have selected refusal storage after seeing prompting message, and terminal receives meeting after refusal selection instruction The matching picture that deletion is received, the photo current to the Target Photo recommends scene to terminate.So, user can be The matching picture is directly deleted in the case of unsatisfied to the matching picture.

Fig. 6 A are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.Corresponding to Fig. 5 A Embodiment, Fig. 6 A illustrate server to terminal send Target Photo matching picture in the case of, user agree to selection institute State the Signalling exchange during matching picture.It is related to user, three objects of terminal and server in the interaction, In the case of triggering picture recommendation condition：Terminal-pair Target Photo carries out signature analysis, obtains the feature letter of the Target Photo Breath；The characteristic information of the Target Photo to server is sent to server；When server is according to the feature of the Target Photo When information carries out Similarity matching and obtains matching picture, the matching picture is sent to terminal；After terminal receives the matching picture, Generate about whether the prompting message for agreeing to the selection matching picture；User checks the matching picture by terminal, satisfied In the case of the matching picture, can select to agree to, i.e., be sent to terminal and agree to instruction；Terminal receives described with meaning After order, the matching picture to terminal can be stored.

Fig. 6 B are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.Corresponding to Fig. 5 B Embodiment, Fig. 6 B illustrate server to terminal send Target Photo matching picture in the case of, user refusal download institute State the Signalling exchange during matching picture.It is related to user, three objects of terminal and server in the interaction, In the example of Fig. 6 B, terminal-pair picture carries out signature analysis, terminal to server transmission characteristic information, server and carries out similar It is identical with the example of Fig. 6 A to the Signalling exchange that terminal sends matching picture and terminal generation prompting message with, server, no With user can also send refusal selection instruction to terminal, and terminal can be deleted after the refusal selection instruction is received The matching picture.

So, using the characteristic information of Target Photo, i.e. picture classification and picture feature value, to the spy of the Target Photo Reference breath carries out Similarity matching and obtains matching picture, and receives the thumbnail of the matching picture or the matching picture, can be with Efficiently complete the recommendation of the similar pictures to the Target Photo.

Fig. 7 A are a kind of flow charts of the picture recommendation method according to another exemplary embodiment, and the method is applied to In terminal, as shown in Figure 7 A, on the basis of the method shown in Fig. 2, the method is further comprising the steps of.

In step 210, cannot be obtained when server carries out Similarity matching according to the characteristic information of the Target Photo During with picture, the Target Photo upload request that the reception server sends；

In step 211, generation is about whether the prompting message for agreeing to upload；

In the step 212, when the second agreement instruction is received, the Target Photo is sent to server.

After server receives the characteristic information of the Target Photo, it is possible to use the picture classification of the Target Photo and The picture feature information stored in picture feature value and server carries out Similarity matching, if schemed without matching in database Piece, then the result of the Similarity matching can confirm that as it fails to match at this moment server can upload the mesh with requesting terminal Mark on a map piece, be available for other users to select so that server is indexed in database.Therefore, terminal can be with the reception server end The upload request to Target Photo for sending, when terminal receives the upload request to the Target Photo from server When, can generate about whether the prompting message for agreeing to upload and be displayed in terminal, user can check the prompting message, when When user agrees to the upload request, i.e., user is sent and agrees to instruction, and terminal can be received to the agreement instruction, in response to The agreement uploading instructions, terminal will send the Target Photo to server, so as to server to the picture that has stored and Picture feature information be updated it is perfect, to obtain more preferable result in Similarity matching afterwards.

Fig. 7 B are a kind of signaling interaction diagrams of the picture recommendation method according to an exemplary embodiment.Corresponding to Fig. 7 A Embodiment, Fig. 7 B illustrate server carries out Similarity matching according to the characteristic information of the Target Photo cannot obtain matching figure In the case of piece, the Signalling exchange during Target Photo is uploaded described in terminal-pair.It is related to use in the interaction Family, three objects of terminal and server, in the case where picture recommendation condition is triggered：Terminal-pair Target Photo carries out feature point Analysis, obtains the characteristic information of the Target Photo；Send the characteristic information of the Target Photo to server；When server according to The characteristic information of the Target Photo carry out Similarity matching cannot obtain matching picture when, server can to terminal send target Picture upload request；Terminal generation is about whether the prompting message for agreeing to upload；When the agreement for receiving user's transmission is instructed, Terminal sends to server Target Photo.

Fig. 8 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment, and the method is applied to In terminal, as shown in figure 8, on the basis of the method shown in Fig. 7 A, the method is further comprising the steps of.

In step 213, the optimization picture of the Target Photo that the reception server sends, wherein, the optimization picture It is to be obtained after the Target Photo of the server to receiving optimizes treatment.

In this embodiment, after terminal to server sends the Target Photo, server can be to the target figure Piece be analyzed optimization obtain optimization picture send to terminal, the optimization picture of Target Photo described in terminal-pair is received, institute Stating analysis optimization can complete in server end.So, user can receive the optimization picture of Target Photo, and province looks for excellent Change the trouble of picture.

Fig. 9 is a kind of flow chart of the picture recommendation method according to an exemplary embodiment, as shown in figure 9, the party Method is applied in server, is comprised the following steps.

In step 901, the characteristic information of Target Photo is received.

Terminal-pair Target Photo carries out the characteristic information that signature analysis obtains the Target Photo, and server is to the target The characteristic information of picture is received, and the characteristic information is used for the Similarity matching to the Target Photo.

In step 902, the characteristic information according to the Target Photo carries out similar to the picture stored in database Matching, to determine to match picture with the presence or absence of with the characteristic information of the Target Photo matches in database.

Can store a large amount of pictures in the database of server end and obtain after the picture to having stored carries out signature analysis Characteristic information.Then server is compared according to the characteristic information of Target Photo with the characteristic information of stored picture, really It is fixed whether to have matching picture.Determine whether that the mode for matching picture can use the scheme of various picture Similarity matchings, for example, According to a kind of embodiment, as shown in Figure 10, the characteristic information can include the classification and picture feature of the stored picture Value；Characteristic information according to the Target Photo can carry out Similarity matching to the picture stored in database, to determine number Picture is matched with the presence or absence of with the characteristic information of the Target Photo matches according in storehouse, can be included：

In step 9021, the picture to having been stored in database carries out signature analysis, the class of the picture for having been stored Other and picture feature value；

In step 9022, in the picture that classification has been stored with the classification identical of Target Photo, it is determined whether exist The corresponding picture feature value of one or more picture is in the approximate extents of the Target Photo characteristic value；

In step 9023, described there is the corresponding picture feature value of one or more picture in the target figure when existing In the approximate extents of piece characteristic value, then a pictures are selected from one or more picture as matching picture.

In this embodiment, after server receives the characteristic information of the Target Photo for carrying out self terminal, can be according to described The characteristic information of Target Photo carries out Similarity matching to the picture stored in database, and the Similarity matching can be to database In the picture that has stored carry out the classification and picture feature value of the picture that signature analysis has been stored, in classification and Target Photo The picture that has stored of classification identical in, it is determined whether there is one or more picture and meet matching condition, the matching bar Part can be the characteristic value of the picture for having stored in the approximate extents of the Target Photo characteristic value, when having described one Or multiple when meeting the picture of the matching condition, server can therefrom select a pictures as matching picture.This Sample, can obtain similar with the Target Photo matching picture by picture classification and picture feature value.

Furthermore it is also possible to there is the situation that cannot obtain matching picture.Figure 11 shows according to another exemplary embodiment A kind of flow chart of picture recommendation method.In the implementation environment of Figure 11, step 9021, step 9022, step 9023 and Figure 10 Embodiment it is identical, unlike, in addition to the matching picture that can obtain the Target Photo, it is also possible to cannot be matched Picture, i.e. also include：

In step 9024, when there is the corresponding picture feature value of one or more picture in the target in the absence of described In the approximate extents of picture feature value, then confirm to obtain matching picture.

Herein, in the picture for having been stored in database, if matching condition can be met without any pictures, So can confirm that cannot obtain the matching picture of the Target Photo.So, can to cannot obtain match picture situation Confirmed, be easy to server to take other measures.

In step 903, when there is matching picture, the thumbnail of the matching picture or the matching picture is sent.

When the result of Similarity matching is the matching picture that there is the Target Photo, can be by matching picture or the institute The thumbnail for stating matching picture is sent to terminal.Wherein, in the case where the matching picture is sent, user can intuitively look into See the matching picture and determine whether the matching picture is selected and stored.In addition, sending the matching figure In the case of the thumbnail of piece, matching result quickly can be sent to terminal, be easy to user to be selected, and can be use Reduce unnecessary down operation in family.

Figure 12 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment, and the method is applied to In server, as shown in figure 12, the method is comprised the following steps：

In step 901, the characteristic information of Target Photo is received；

In step 902, the characteristic information according to the Target Photo carries out similar to the picture stored in database Matching, to determine to match picture with the presence or absence of with the characteristic information of the Target Photo matches in database；

In step 9031, when there is matching picture, the thumbnail of the matching picture or the matching picture is sent；

In step 904, the download request of matching picture is received；

In step 905, the matching picture is sent.

As it was noted above, in the case where server sends to terminal the thumbnail of the matching picture, user can be with Checked and may determine whether to select the matching picture to be used as most by the thumbnail for matching picture described in terminal-pair Whole picture recommendation results, when user agrees to select in terminal, terminal can be sent to the matching picture to server Download request, server can receive the download request to the matching picture.When receive to it is described matching picture download After request, server can send the matching picture to terminal.

Figure 13 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment, and the method is applied to In server, as shown in figure 13, on the basis of the method shown in Fig. 9, the method is further comprising the steps of.

In step 906, cannot be obtained when server carries out Similarity matching according to the characteristic information of the Target Photo During with picture, Target Photo upload request is sent.

When during Similarity matching is carried out to the Target Photo, if there is no any picture for having stored Meet the matching condition, can confirm that cannot obtain matching picture, at this moment, can be sent to the Target Photo to terminal Upload request, to obtain the Target Photo.

Figure 14 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment, and the method is applied to In server, as shown in figure 14, on the basis of the method shown in Figure 13, the method is further comprising the steps of.

In step 907, the Target Photo is received；

In step 908, by Target Photo storage in database.

The upload request to the Target Photo that terminal can send in response to server, generates about whether in agreement The prompting message of biography, user can check the prompting message by terminal, and user can be selected to agree to upload, and terminal can be responded In agreement instruction, the Target Photo is sent to server, server can be received to the Target Photo, and The Target Photo is stored in database after receiving the Target Photo.

Figure 15 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment, and the method is applied to In server, as shown in figure 15, on the basis of the method shown in Figure 14, the method is further comprising the steps of.

In step 909, the characteristic information of the Target Photo is stored in database.

When server is in the Target Photo storage for sending terminal to database, can also be by the Target Photo Characteristic information store in database.Wherein, the characteristic information of the Target Photo is obtained by signature analysis in terminal 's.So, the picture and picture feature information that have stored can be carried out with convenient service device it is perfect, in Similarity matching after being easy to It is middle to obtain more preferable result.

Figure 16 is a kind of flow chart of the picture recommendation method according to another exemplary embodiment, and the method is applied to In server, as shown in figure 16, on the basis of the method shown in Figure 14, the method is further comprising the steps of.

In step 910, the Target Photo is optimized；

In step 911, the optimization picture of the Target Photo is sent to terminal.

After the Target Photo that server receiving terminal sends, the Target Photo can be optimized, obtained The optimization picture of the Target Photo can be sent to terminal after optimization picture.Wherein, it is described that the Target Photo is carried out Optimization can be optimized from various aspects to picture, the optimization such as to picture correlation, the compression to picture, to picture size Optimization, to optimization of picture clarity etc..Terminal can be received to the optimization picture of the Target Photo.So, use Family can check the optimization picture from terminal, be easy to user more preferably to be selected.

Figure 17 is a kind of block diagram of the picture recommendation apparatus according to an exemplary embodiment.Wherein, the device 1700 Can apply to terminal.As shown in figure 17.The device 1700 can include：Characteristics analysis module 1701, is configured as to target Picture carries out signature analysis, obtains the characteristic information of the Target Photo；Characteristic information sending module 1702, is configured as to clothes Business device sends the characteristic information of the Target Photo；First receiver module 1703, is configured as server according to the target When the characteristic information of picture carries out Similarity matching and obtains matching picture, the matching picture from server or described are received Thumbnail with picture.

Figure 18 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 18, exist On the basis of device shown in Figure 17, first receiver module 1703 is configured as receiving the matching figure from server In the case of the thumbnail of piece, described device 1700 can also include：Prompting generation module 1704, is configurable to generate on being The no prompting message for agreeing to the selection matching picture；Download request sending module 1705, is configured as receiving same meaning When making, matching picture download request is sent to server；Second receiver module 1706, is configured as terminal and receives in response to described Match the matching picture that the server of picture download request sends.

Figure 19 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 19, exist On the basis of device shown in Figure 17, first receiver module 1703 is configured as receiving the matching figure from server In the case of piece, described device 1700 can also include：Prompting generation module 1704, is configurable to generate and is selected about whether agreement Select the prompting message of the matching picture；Memory module 1707, when being configured as receiving the first agreement instruction, terminal storage The matching picture.

According to a kind of implementation method, described device 1700 can also include：Removing module, is configured as receiving to institute During the refusal selection instruction of the thumbnail for stating matching picture or the matching picture, the matching picture or institute that deletion is received State the thumbnail of matching picture.

Figure 20 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 20, exist On the basis of device shown in Figure 17, described device 1700 can also include：Upload request receiver module 1709, is configured as Server according to the characteristic information of the Target Photo carry out Similarity matching cannot obtain matching picture when, the reception server send Target Photo upload request；Prompting generation module 1710 is uploaded, is configurable to generate and is disappeared about whether the prompting for agreeing to upload Breath；Uploading pictures sending module 1711, when being configured as receiving the second agreement instruction, the target figure is sent to server Piece.

Figure 21 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 21, exist On the basis of device shown in Figure 20, described device 1700 can also include：Optimization picture receiver module 1712, is configured as connecing The optimization picture of the Target Photo that server sends is received, wherein, the optimization picture server is to described in receiving Target Photo optimizes what is obtained after processing..

Figure 22 is a kind of block diagram of the picture recommendation apparatus according to an exemplary embodiment.Wherein, the device 2200 Can apply to server.As shown in figure 22.The device 2200 can include：Characteristic information receiver module 2201, is configured as Receive the characteristic information of Target Photo；Similarity matching module 2202, is configured as the characteristic information pair according to the Target Photo The picture stored in database carries out Similarity matching, to determine to believe with the presence or absence of the feature with the Target Photo in database The matching picture of manner of breathing matching；First sending module 2203, when being configured as existing matching picture, sends the matching picture Or the thumbnail of the matching picture.

Figure 23 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 23, exist On the basis of device shown in Figure 22, described device 2200 can also include：Download request receiver module 2204, is configured as connecing Receive matching picture download request；Second sending module 2205, is configured as sending the matching picture.

Figure 24 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 24, exist On the basis of device shown in Figure 22, described device 2200 can also include：Upload request sending module 2206, is configured as Server according to the characteristic information of the Target Photo carry out Similarity matching cannot obtain matching picture when, send Target Photo on Pass request.

Figure 25 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 25, exist On the basis of device shown in Figure 24, described device 2200 can also include：Uploading pictures receiver module 2207, is configured as The upload request sending module be configured as server according to the characteristic information of the Target Photo carry out Similarity matching without When method obtains matching picture, after sending Target Photo upload request, the Target Photo is received；Uploading pictures memory module 2208, it is configured as Target Photo storage in database.

Figure 26 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 26, exist On the basis of device shown in Figure 25, described device 2200 can also include：Uploading pictures characteristic storage module 2209, is configured It is to store in database the characteristic information of the Target Photo.

Figure 27 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 27, exist On the basis of device shown in Figure 25, described device 2200 can also include：Uploading pictures optimization module 2210, it is right to be configured as The Target Photo is optimized；Optimization picture sending module 2211, is configured as sending out in the optimization picture of the Target Photo Deliver to terminal.

Figure 28 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 28, exist On the basis of device shown in Figure 22, described device 2200 can also include：Signature analysis submodule 2202-1, it is right to be configured as The picture stored in database carries out signature analysis, the classification and picture feature value of the picture for having been stored；Approximate picture Determination sub-module 2202-2, in the picture that the classification identical being configured as in classification and Target Photo has been stored, it is determined whether In the presence of the corresponding picture feature value of one or more picture in the approximate extents of the Target Photo characteristic value；Picture selection Module 2202-3, is configured as having the corresponding picture feature value of one or more picture of the presence in the Target Photo In the approximate extents of characteristic value, then a pictures are selected from one or more picture as matching picture.

Figure 29 is a kind of block diagram of the picture recommendation apparatus according to another exemplary embodiment.As shown in figure 29, exist On the basis of device shown in Figure 28, described device 2200 can also include：It fails to match confirms submodule 2202-4, is configured It is when in the absence of the approximate model that there is the corresponding picture feature value of one or more picture in the Target Photo characteristic value In enclosing, then confirm to obtain matching picture.

On the device in above-described embodiment, wherein modules perform the concrete mode of operation in relevant the method Embodiment in be described in detail, explanation will be not set forth in detail herein.

Figure 30 is a kind of block diagram of the picture recommendation apparatus 3000 according to an exemplary embodiment.For example, device 3000 can be mobile phone, computer, digital broadcast terminal, messaging devices, game console, tablet device, medical treatment Equipment, body-building equipment, personal digital assistant etc..

Reference picture 30, device 3000 can include following one or more assemblies：Processing assembly 3002, memory 3004, Electric power assembly 3006, multimedia groupware 3008, audio-frequency assembly 3010, the interface 3012 of input/output (I/O), sensor cluster 3014, and communication component 3016.

The integrated operation of the usual control device 3000 of processing assembly 3002, such as with display, call, data communication, Camera operation and the associated operation of record operation.Processing assembly 3002 can include one or more processors 3020 to perform Instruction, to complete all or part of step of picture recommendation method.Additionally, processing assembly 3002 can include one or more moulds Block, is easy to the interaction between processing assembly 3002 and other assemblies.For example, processing assembly 3002 can include multi-media module, To facilitate the interaction between multimedia groupware 3008 and processing assembly 3002.

Memory 3004 is configured as storing various types of data supporting the operation in device 3000.These data Instruction of the example including any application program or method for being operated on device 3000, contact data, telephone book data, Message, picture, video etc..Memory 3004 can by any kind of volatibility or non-volatile memory device or they Combination realizes, such as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), it is erasable can Program read-only memory (EPROM), programmable read only memory (PROM), read-only storage (ROM), magnetic memory, flash memory Reservoir, disk or CD.

Electric power assembly 3006 provides electric power for the various assemblies of device 3000.Electric power assembly 3006 can include power management System, one or more power supplys, and other generate, manage and distribute the component that electric power is associated with for device 3000.

Multimedia groupware 3008 is included in one screen of output interface of offer between described device 3000 and user. In some embodiments, screen can include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, Screen may be implemented as touch-screen, to receive the input signal from user.Touch panel includes that one or more touches are passed Sensor is with the gesture on sensing touch, slip and touch panel.The touch sensor can not only sensing touch or slip be dynamic The border of work, but also the detection duration related to the touch or slide and pressure.In certain embodiments, it is many Media component 3008 includes a front camera and/or rear camera.When device 3000 is in operator scheme, mould is such as shot When formula or video mode, front camera and/or rear camera can receive outside multi-medium data.Each preposition shooting Head and rear camera can be a fixed optical lens systems or with focusing and optical zoom capabilities.

Audio-frequency assembly 3010 is configured as output and/or input audio signal.For example, audio-frequency assembly 3010 includes a wheat Gram wind (MIC), when device 3000 is in operator scheme, such as call model, logging mode and speech recognition mode, microphone quilt It is configured to receive external audio signal.The audio signal for being received can be further stored in memory 3004 or via communication Component 3016 sends.In certain embodiments, audio-frequency assembly 3010 also includes a loudspeaker, for exports audio signal.

I/O interfaces 3012 are that interface, above-mentioned peripheral interface module are provided between processing assembly 3002 and peripheral interface module Can be keyboard, click wheel, button etc..These buttons may include but be not limited to：Home button, volume button, start button and Locking press button.

Sensor cluster 3014 includes one or more sensors, and the state for providing various aspects for device 3000 is commented Estimate.For example, sensor cluster 3014 can detect the opening/closed mode of device 3000, the relative positioning of component, such as institute Display and keypad that component is device 3000 are stated, sensor cluster 3014 can be with detection means 3000 or device 3,000 1 The position of individual component changes, and user is presence or absence of with what device 3000 was contacted, the orientation of device 3000 or acceleration/deceleration and dress Put 3000 temperature change.Sensor cluster 3014 can include proximity transducer, be configured to without any physics The presence of object nearby is detected during contact.Sensor cluster 3014 can also include optical sensor, and such as CMOS or ccd image are sensed Device, for being used in imaging applications.In certain embodiments, the sensor cluster 3014 can also include acceleration sensing Device, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.

Communication component 3016 is configured to facilitate the communication of wired or wireless way between device 3000 and other equipment.Dress Putting 3000 can access the wireless network based on communication standard, such as WiFi, 2G or 3G, or combinations thereof.It is exemplary at one In embodiment, communication component 3016 receives broadcast singal or broadcast correlation from external broadcasting management system via broadcast channel Information.In one exemplary embodiment, the communication component 3016 also includes near-field communication (NFC) module, to promote short distance Communication.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band can be based in NFC module (UWB) technology, bluetooth (BT) technology and other technologies are realized.

In the exemplary embodiment, device 3000 can be by one or more application specific integrated circuits (ASIC), numeral Signal processor (DSP), digital signal processing appts (DSPD), PLD (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components realization, for performing the above method.

In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instructing, example are additionally provided Such as include the memory 3004 of instruction, above-mentioned instruction can be performed to complete picture recommendation side by the processor 3020 of device 3000 Method.For example, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, magnetic Band, floppy disk and optical data storage devices etc..

Figure 31 is a kind of block diagram of the picture recommendation apparatus 3100 according to an exemplary embodiment.For example, device 3100 may be provided in a server.Reference picture 31, device 3100 include processing assembly 3122, its further include one or Multiple processors, and the memory resource as representated by memory 3132, can be by the execution of processing assembly 3122 for storing Instruction, such as application program.In memory 3132 store application program can include it is one or more each Corresponding to one group of module of instruction.Additionally, processing assembly 3122 is configured as execute instruction, to perform picture recommendation method.

Device 3100 can also include that a power supply module 3126 is configured as the power management of performs device 3100, one Wired or wireless network interface 3150 is configured as device 3100 being connected to network, and input and output (I/O) interface 3158.Device 3100 can operate the operating system in memory 3132, such as Windows ServerTM, Mac based on storage OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.

Those skilled in the art will readily occur to other embodiment party of the disclosure after considering specification and putting into practice the disclosure Case.The application is intended to any modification, purposes or the adaptations of the disclosure, these modifications, purposes or adaptability Change follows the general principle of the disclosure and including the undocumented common knowledge or usual skill in the art of the disclosure Art means.Description and embodiments are considered only as exemplary, and the true scope of the disclosure and spirit are by following claim Point out.

It should be appreciated that the disclosure is not limited to the precision architecture for being described above and being shown in the drawings, and And can without departing from the scope carry out various modifications and changes.The scope of the present disclosure is only limited by appended claim.

Claims

1. a kind of picture recommendation method, it is characterised in that for terminal, including：

Signature analysis is carried out to Target Photo, the characteristic information of the Target Photo is obtained；

The characteristic information of the Target Photo is sent to server；

When server carries out Similarity matching according to the characteristic information of the Target Photo obtains matching picture, receive from service The matching picture of device or the thumbnail of the matching picture.

2. method according to claim 1, it is characterised in that described to carry out signature analysis to Target Photo, including：

When the terminal shows that the Target Photo reaches Preset Time or receives request recommendation instruction, to the target Picture carries out signature analysis, obtains the characteristic information of the Target Photo.

3. method according to claim 1, it is characterised in that receiving the breviary of the matching picture from server In the case of figure, methods described also includes：

Generate about whether the prompting message for agreeing to the selection matching picture；

When agreement instruction is received, matching picture download request is sent to server；

Receive the matching picture sent in response to the server of the matching picture download request.

4. method according to claim 1, it is characterised in that receiving the situation of the matching picture from server Under, methods described also includes：

When the first agreement instruction is received, the matching picture is stored.

5. the method according to claim 3 or 4, it is characterised in that methods described also includes：

When the refusal selection instruction for receiving the thumbnail to the matching picture or the matching picture, what deletion was received The thumbnail of the matching picture or the matching picture.

6. method according to claim 1, it is characterised in that methods described also includes：

When server carries out Similarity matching according to the characteristic information of the Target Photo cannot obtain matching picture, service is received The Target Photo upload request that device sends；

Generate about whether the prompting message for agreeing to upload；

When the second agreement instruction is received, the Target Photo is sent to server.

7. method according to claim 6, it is characterised in that methods described also includes：

The optimization picture of the Target Photo that the reception server sends, wherein, the optimization picture is server to receiving The Target Photo optimize treatment after obtain.

8. a kind of picture recommendation apparatus, it is characterised in that for terminal, including：

Characteristics analysis module, is configured as carrying out signature analysis to Target Photo, obtains the characteristic information of the Target Photo；

Characteristic information sending module, is configured as being sent to server the characteristic information of the Target Photo；

First receiver module, is configured as server and carries out Similarity matching according to the characteristic information of the Target Photo obtaining During with picture, the thumbnail of the matching picture or the matching picture from server is received.

9. device according to claim 8, it is characterised in that the characteristics analysis module, is configured as in the terminal When showing that the Target Photo reaches Preset Time or receives request recommendation instruction, feature point is carried out to the Target Photo Analysis, obtains the characteristic information of the Target Photo.

10. a kind of picture recommendation apparatus, it is characterised in that including：

Processor；

Memory for storing processor-executable instruction；

Wherein, the processor is configured as：

The characteristic information of the Target Photo is sent to server；