CN110008364A

CN110008364A - Image processing method, device and system

Info

Publication number: CN110008364A
Application number: CN201910231390.6A
Authority: CN
Inventors: 柯海滨; 靳玉茹; 胡娜; 李杨
Original assignee: Lenovo Beijing Ltd
Current assignee: Lenovo Beijing Ltd
Priority date: 2019-03-25
Filing date: 2019-03-25
Publication date: 2019-07-12
Anticipated expiration: 2039-03-25
Also published as: CN110008364B

Abstract

Present disclose provides a kind of image processing methods, this method comprises: obtaining multiple images；According to pre-defined rule, multiple images are divided into one or more first image groups；Determine that one or more images in each first image group are the first typical image, for characterizing each first image group；And in response to the first acquisition request, show at least one first typical image of at least one the first image group in one or more first image groups.The disclosure additionally provides a kind of image processing apparatus and a kind of image processing system.

Description

Image processing method, device and system

Technical field

This disclosure relates to a kind of image processing method, device and system.

Background technique

With the improvement of living standards, people more gladly record life with photo or video, therefore people are often A large amount of photo or video are stored in terminal device.And with the development of electronic technology, it shoots photo or the camera shooting of video is set Standby pixel also quickly improves, and therefore, the data volume of each photo or video is also gradually increased.

During realizing disclosure design, at least there are the following problems in the prior art for inventor's discovery: existing Terminal device is often arranged successively storage according only to time sequencing when storing photos and videos.Storage is being shown to user When photos and videos, also tend to be with temporally tabular form or breviary diagram form to user show.But when user is searching When oneself wanting the photo seen or video, then need to browse to position to obtain photos and videos one by one, this can undoubtedly reduce use The efficiency of photo or video is searched at family, and very poor experience sense is brought to user.

Summary of the invention

An aspect of this disclosure provides a kind of for improving the image processing method of response efficiency.This method comprises: Obtain multiple images；According to pre-defined rule, multiple images are divided into one or more first image groups；Determine each first figure As one or more images in group be the first typical image, for characterizing each first image group；And it is obtained in response to first Request is taken, shows at least one first typical image of at least one the first image group in one or more first image groups.

Optionally, above-mentioned image processing method further include: in response to first acquisition request, show at least one the At least one one-to-one operational controls of one image group；And in response to the first operational controls quilt at least one operational controls The operation of selection shows the parts of images or all images of the first image group corresponding with the first operational controls, wherein part figure As including other images in addition to the first typical image.

Optionally, above-mentioned image processing method further include: in response to selecting at least one first typical figure in the first way The operation of the first image as in, shows at least one other figure in the first image group of the first characterization image in addition to the first image Picture, wherein at least one other image includes the first typical image and/or the image in addition to the first typical image；And/or Person shows the second characterization image in response to selecting the operation of the second image at least one first typical image in a second manner The first image group in the first typical image in addition to the second image, wherein the first image group of the second characterization image includes more A first typical image, and in response to the first acquisition request, only show each first image group at least one first image group First typical image.

Optionally, above-mentioned image processing method further include: the first typical image of each first image group is handled, Obtain the label of each first image group；And it in response to the second acquisition request, shows and the second acquisition request matched first The first typical image that image group includes.

Optionally, above-mentioned in response to the second acquisition request, displaying includes with the matched first image group of the second acquisition request The first typical image include: that the request feature of the second acquisition request is extracted using first nerves network model；Determine one or Image group to be presented in multiple first image groups, the image group to be presented have the label with request characteristic matching；And exhibition Show the first typical image that image group to be presented includes, wherein the second acquisition request include voice messaging, image information and/or Text information.

Optionally, above-mentioned image processing method further include: in response to rearrangement request, multiple images are divided into one or more A second image group；Determine that one or more images in each second image group are the second typical image, it is each for characterizing Second image group；And at least one first typical image of at least one the first image group of displaying is updated at least one At least one second typical image of second image group.

Optionally, above-mentioned according to pre-defined rule, multiple images, which are divided into one or more first image groups, includes；It will be more The image that shooting time belongs to same time period in a image is divided to same image group, obtains one or more first images Group；Alternatively, will include that the image of similar/same object is divided to same image group in multiple images, one or more be obtained First image group；Alternatively, being obtained same image group is divided to by the image that identical screening-mode is shot in multiple images One or more first image groups；Alternatively, by same image is divided in the image that same area is shot in multiple images Group obtains one or more first image groups.

Optionally, above-mentioned according to pre-defined rule, it includes: use that multiple images, which are divided into one or more first image groups, Multiple images are divided into one or more first image groups by nervus opticus network model；And/or above-mentioned determination is each It includes: using third nerve network model by the first image that one or more images in first image group, which are the first typical image, One or more images of each first image group of determination of group are the first typical image.

Another aspect of the disclosure provides a kind of image processing apparatus, the device include obtain module, grouping module, Typical image determining module and display module.Wherein, module is obtained for obtaining multiple images；Grouping module is used for according to predetermined Multiple images are divided into one or more first image groups by rule；Typical image determining module is for determining each first figure As one or more images in group be the first typical image, for characterizing each first image group；Display module is for responding In the first acquisition request, at least one first typical case of at least one the first image group in one or more first image groups is shown Image.

Optionally, above-mentioned display module is also used to: in response to the first acquisition request, being shown and at least one first image group At least one one-to-one operational controls；And in response to behaviour that the first operational controls at least one operational controls are selected Make, show the parts of images or all images of the first image group corresponding with the first operational controls, wherein parts of images includes removing Other images outside first typical image.

Optionally, above-mentioned display module is also used to: in response to being selected at least one first typical image in the first way The operation of first image shows at least one other image in the first image group of the first characterization image in addition to the first image. Wherein, at least one other image includes the first typical image and/or the image in addition to the first typical image.On and/or It states display module and is also used to operation in response to selecting the second image at least one first typical image in a second manner, show The first typical image in first image group of the second characterization image in addition to the second image.Wherein, the first of the second characterization image Image group includes multiple first typical images, and in response to the first acquisition request, is only shown every at least one first image group One the first typical image of a first image group.

Optionally, above-mentioned image processing apparatus further includes processing module, and the processing module is used for each first image First typical image of group is handled, and the label of each first image group is obtained.Above-mentioned display module is also used in response to Two acquisition requests show the first typical image for including with the matched first image group of the second acquisition request.

Optionally, above-mentioned display module includes extraction unit, determination unit and display unit.Wherein, the extraction unit For using first nerves network model, the request feature of second acquisition request is extracted；The determination unit is for determining Image group to be presented in one or more of first image groups, the image group to be presented have the mark with request characteristic matching Label；The display unit is for showing the first typical image that image group to be presented includes.Wherein, the second acquisition request includes language Message breath, image information and/or text information.

Optionally, above-mentioned grouping module is also used in response to rearrangement request, and multiple images are divided into one or more the Two image groups；Above-mentioned typical image determining module is also used to determine that one or more images in each second image group are second Typical image, for characterizing each second image group；At least one first image group that above-mentioned display module is also used to show At least one first typical image be updated at least one second typical image of at least one the second image group.

Optionally, above-mentioned grouping module is specifically used for: shooting time in multiple images is belonged to the image of same time period It is divided to same image group, obtains one or more first image groups；Alternatively, will include similar/phase jljl in multiple images The image of body is divided to same image group, obtains one or more first image groups；Alternatively, by multiple images by identical shooting The image that mode is shot is divided to same image group, obtains one or more first image groups；Alternatively, by multiple images It is divided to same image group in the image that same area is shot, obtains one or more first image groups.

Optionally, above-mentioned grouping module is specifically used for using nervus opticus network model, and multiple images are divided into one Or multiple first image groups.And/or above-mentioned typical image determining module be specifically used for using third nerve network model by One or more images of each first image group of the determination of first image group are the first typical image.

Another aspect of the present disclosure provides a kind of image processing system, including one or more processors；And storage Device, for storing one or more programs, wherein when one or more of programs are held by one or more of processors When row, so that one or more of processors execute above-mentioned image processing method.

Another aspect of the disclosure provides a kind of computer readable storage medium, is stored with the executable finger of computer It enables, which makes processor execute above-mentioned image processing method when being executed by processor.

Another aspect of the disclosure provides a kind of computer program, which, which includes that computer is executable, refers to It enables, described instruction is when executed for realizing image processing method as described above.

Detailed description of the invention

In order to which the disclosure and its advantage is more fully understood, referring now to being described below in conjunction with attached drawing, in which:

Fig. 1 diagrammatically illustrates the application scenario diagram of image processing method according to the embodiment of the present disclosure, device and system；

Fig. 2 diagrammatically illustrates the flow chart of the image processing method according to the first embodiment of the present disclosure；

Fig. 3 A diagrammatically illustrates the flow chart of the image processing method according to the second embodiment of the present disclosure；

Fig. 3 B is diagrammatically illustrated according to the bandwagon effect figure in the second embodiment of the present disclosure in response to user's operation；

Fig. 4 A diagrammatically illustrates the flow chart of the image processing method according to the third embodiment of the present disclosure；

Fig. 4 B is diagrammatically illustrated according to the bandwagon effect figure in the third embodiment of the present disclosure in response to user's operation；

Fig. 5 A diagrammatically illustrates the flow chart of the image processing method according to the fourth embodiment of the present disclosure；

Fig. 5 B is diagrammatically illustrated according to the bandwagon effect figure in the fourth embodiment of the present disclosure in response to user's operation；

Fig. 6 A diagrammatically illustrates the flow chart of the image processing method according to the fifth embodiment of the present disclosure；

Fig. 6 B diagrammatically illustrates the flow chart for showing image in response to the second acquisition request according to the embodiment of the present disclosure；

Fig. 7 A diagrammatically illustrates the flow chart of the image processing method according to the sixth embodiment of the present disclosure；

Fig. 7 B is diagrammatically illustrated according to the bandwagon effect figure in the sixth embodiment of the present disclosure in response to reordering operations；

Fig. 8 diagrammatically illustrates the structural block diagram of the image processing apparatus according to the embodiment of the present disclosure；And

Fig. 9 is diagrammatically illustrated according to the image processing system for being adapted for carrying out image processing method of the embodiment of the present disclosure Structural block diagram.

Specific embodiment

Hereinafter, will be described with reference to the accompanying drawings embodiment of the disclosure.However, it should be understood that these descriptions are only exemplary , and it is not intended to limit the scope of the present disclosure.In the following detailed description, to elaborate many specific thin convenient for explaining Section is to provide the comprehensive understanding to the embodiment of the present disclosure.It may be evident, however, that one or more embodiments are not having these specific thin It can also be carried out in the case where section.In addition, in the following description, descriptions of well-known structures and technologies are omitted, to avoid Unnecessarily obscure the concept of the disclosure.

Term as used herein is not intended to limit the disclosure just for the sake of description specific embodiment.It uses herein The terms "include", "comprise" etc. show the presence of the feature, step, operation and/or component, but it is not excluded that in the presence of Or add other one or more features, step, operation or component.

There are all terms (including technical and scientific term) as used herein those skilled in the art to be generally understood Meaning, unless otherwise defined.It should be noted that term used herein should be interpreted that with consistent with the context of this specification Meaning, without that should be explained with idealization or excessively mechanical mode.

It, in general should be according to this using statement as " at least one in A, B and C etc. " is similar to Field technical staff is generally understood the meaning of the statement to make an explanation (for example, " system at least one in A, B and C " Should include but is not limited to individually with A, individually with B, individually with C, with A and B, with A and C, have B and C, and/or System etc. with A, B, C).Using statement as " at least one in A, B or C etc. " is similar to, generally come Saying be generally understood the meaning of the statement according to those skilled in the art to make an explanation (for example, " having in A, B or C at least One system " should include but is not limited to individually with A, individually with B, individually with C, with A and B, have A and C, have B and C, and/or the system with A, B, C etc.).

Shown in the drawings of some block diagrams and/or flow chart.It should be understood that some sides in block diagram and/or flow chart Frame or combinations thereof can be realized by computer program instructions.These computer program instructions can be supplied to general purpose computer, The processor of special purpose computer or other programmable data processing units, so that these instructions are when executed by this processor can be with Creation is for realizing function/operation device illustrated in these block diagrams and/or flow chart.The technology of the disclosure can be hard The form of part and/or software (including firmware, microcode etc.) is realized.In addition, the technology of the disclosure, which can be taken, is stored with finger The form of computer program product on the computer readable storage medium of order, the computer program product is for instruction execution system System uses or instruction execution system is combined to use.

Embodiment of the disclosure provide it is a kind of for improving the image processing method of response efficiency, this method comprises: obtaining Take multiple images；According to pre-defined rule, multiple images are divided into one or more first image groups；Determine each first image One or more images in group are the first typical image, for characterizing each first image group；And it is obtained in response to first Request shows at least one first typical image of at least one the first image group in one or more first image groups.

The image processing method of the disclosure only shows the part or complete of each image group when user browses and searches image The typical image in portion, and and non-display all images, therefore response efficiency can be improved to a certain extent.Furthermore due to Image group is divided according to pre-defined rule, then user can quickly determine its institute searched according to the typical image of displaying The image group where image is needed, and the location efficiency of required image therefore can be improved, improves user experience.

Fig. 1 diagrammatically illustrates the application scenario diagram of image processing method according to the embodiment of the present disclosure, device and system. It should be noted that being only the example that can apply the scene of the embodiment of the present disclosure shown in Fig. 1, to help those skilled in the art Understand the technology contents of the disclosure, but is not meant to that the embodiment of the present disclosure may not be usable for other equipment, system, environment or field Scape.

As shown in Figure 1, including terminal device 111,112,113 according to the application scenarios 100 of the embodiment of the present disclosure.

Wherein, which for example can have store function, and the operation being able to respond in user is deposited Store up image.In accordance with an embodiment of the present disclosure, which can also have display function, in response to The displaying request at family shows the image of some or all of storage.Specifically, which can be and have Display screen and the various electronic equipments for being provided with storage unit, including but not limited to smart phone, tablet computer, it is on knee just Take computer and desktop computer etc..

In accordance with an embodiment of the present disclosure, the image of the above-mentioned operation storage in response to user for example can be terminal device 111,112,113 shootings obtain, and correspondingly, which should also have shooting function.Alternatively, ringing It should can also be in the image of the operation storage of user and get from external picture pick-up device, or from other external storages What equipment was got.

In accordance with an embodiment of the present disclosure, which can also for example have processing function, for pair The image of storage is handled, specifically such as the image of storage can be identified, classified and be shown.And/or it should Each image group that terminal device 111,112,113 can also obtain classification is handled, and is determined to each for characterizing The typical image of image group, in order to only show image page 140 when showing image.I.e. when showing image, only show every One or more typical images of a image group.For example, personage, movement and food and drink three can be divided the image into according to picture material A image group, and when showing the image of three image groups, only show personage's typical image 141 of representative figure's image group The image of both legs (people open one's arms), movement typical image 142 (basketball penalty area image) and the 143 (food and drink of food and drink typical image Sign image).

In accordance with an embodiment of the present disclosure, as shown in Figure 1, the application scenarios 100 for example can also include 120 kimonos of network Business device 130.Network 120 between terminal device 111,112,113 and server 130 to provide the medium of communication link.Net Network 120 may include various connection types, such as wired, wireless communication link or fiber optic cables etc..

Server 130 can be to provide the server of various services, such as can store to terminal device 111,112,113 Image identified, classified.Correspondingly, terminal device 111,112,113 can send out the image of shooting, acquisition or storage Server 130 is given, image is handled for server 130.Furthermore the server 130 may also respond to terminal device 111,112,113 request instruction sent pushes user to terminal device 111,112,113 and requests the image shown.

It should be noted that image processing method provided by the embodiment of the present disclosure generally can by terminal device 111, 112, it 113 executes, or part is executed by terminal device 111,112,113, is partially executed by server 130.Correspondingly, the disclosure Image processing apparatus provided by embodiment generally can be set in terminal device 111,112,113, alternatively, can be partly It is set in server 130, is partially provided in terminal device 111,112,113.

It should be understood that in the number of terminal device, network and server and the image page of displaying in Fig. 1 image it is interior Hold and number is only schematical.According to needs are realized, any number of terminal device, network and server can have, And image page can show any type sum number purpose image.

Fig. 2 diagrammatically illustrates the flow chart of the image processing method according to the first embodiment of the present disclosure.

As shown in Fig. 2, the image processing method of the embodiment of the present disclosure includes operation S201~operation S204.

In operation S201, multiple images are obtained.

Wherein, multiple image for example can be what captured in real-time obtained, or can be from external picture pick-up device or It is got in storage equipment.Multiple image can be the image in each shooting time, shooting location shooting, can be The image shot under various screening-modes can also be that shooting has the image of various scenery, be also possible to picture or video clip First frame image etc..The disclosure is not construed as limiting the acquisition modes of multiple image and concrete type of multiple image etc..

In operation S202, according to pre-defined rule, multiple images are divided into one or more first image groups.

Wherein, it is same for example to may is that the image that shooting time is belonged to same time period is divided to for above-mentioned pre-defined rule Image group, so that multiple images are divided at least one first image group.For example, when in the shooting time of multiple images, most Early shooting time is on January 1st, 2018, and shooting time the latest is on January 31st, 2019, then can belong to shooting time The image of the same moon is divided into same image group.In multiple shooting times of multiple images, including it is belonging respectively to from 2018 In January to 1 month 2019 in year when the shooting time of every month, then multiple image can be divided into 13 image groups.

Wherein, above-mentioned pre-defined rule, which for example may is that, is divided to same image for the image with similar/same object Group, so that multiple images are divided at least one image group.For example, when including personage in two images, it can should Two images point extremely same image group.In accordance with an embodiment of the present disclosure, operation S202 specifically can also include to multiple figures As the operation identified, the object for including with each image of determination.Furthermore operation S202 specifically for example can also be by adopting Multiple images are grouped with nervus opticus network model.It is specific to be, using multiple images as nervus opticus network mould The input of type, i.e., the exportable type for obtaining the object that multiple image includes, the then object for including according to multiple image The classification of multiple images can be realized in type.

Wherein, above-mentioned pre-defined rule for example may is that the image shot by identical screening-mode is divided to it is same Image group obtains at least one first image group.In accordance with an embodiment of the present disclosure, it is contemplated that store different screening-modes (such as Panning mode and preposition screening-mode) shooting obtain image when, obtain image data volume be it is different, therefore, this is pre- Set pattern, which then specifically can be, is grouped multiple images according to the data volume of image.Alternatively, this is according to screening-mode to image The operation classified can also realize that the disclosure is not construed as limiting this by above-mentioned nervus opticus network model.

Wherein, above-mentioned pre-defined rule for example may is that the image that will be shot in described multiple images in same area It is divided to same image group, obtains at least one first image group.In accordance with an embodiment of the present disclosure, which specifically can be with It is to be classified according to the shooting location of multiple images to multiple images.In view of existing picture pick-up device usually all has positioning Function, therefore the shooting location of image can be obtained while shooting obtains image, consequently facilitating aforesaid operations S202's holds Row.In accordance with an embodiment of the present disclosure, in the case where picture pick-up device does not have positioning function or do not open positioning function, operation S202 specifically can also be through the object in identification image the shooting location for determining image, for example, building when having in image When building object " the Forbidden City ", then it can determine that shooting location is " Beijing " etc..This is by identifying that image determines that the operation of shooting location has Body can also realize that this will not be detailed here by above-mentioned nervus opticus network model.

In accordance with an embodiment of the present disclosure, above-mentioned nervus opticus network model can for example be based on backpropagation neural network Network, radial base (Radial Basis Function, RBF) neural network or perceptron neural network etc. building, second mind It is trained to through network model for classifying to multiple images.Wherein, it will be understood by those skilled in the art that according to predetermined The difference of rule, the nervus opticus network model can have different structures and different parameters, and above-mentioned nervus opticus net The building of network model is used as example only in favor of understanding that the disclosure, the disclosure are not construed as limiting this.

In operation S203, determines that one or more images in each first image group are the first typical image, be used for table Levy each first image group；

Wherein, clarity, the pixel for the multiple images that operation S203 for example can include according to each first image group Size, shooting object account for the ratio of image and the frequency of occurrences of objects in images etc. to determine the first typical image.Specifically, Such as the object shot in multiple images can be accounted for image ratio be greater than preset ratio (50%) image be determined as first Typical image；Such as it can be and the maximum image of pixel size in multiple images is determined as first typical image etc..

In accordance with an embodiment of the present disclosure, in order to improve treatment effeciency, operation S203 specifically be can also be using third mind The first typical image is determined through network model.During processing, made with all images that each first image group includes For the input of third nerve network model, output obtain can as the image of the first typical image or number of the image etc., With one or more images of each first image group of determination by the first image group for the first typical image.It specifically for example may be used To be that screening obtains having the image of more common feature as the first typical image.Wherein, above-mentioned third nerve network model Such as can be with the same type of model of nervus opticus network model, be also possible to different types of model.The nervus opticus Network model is trained to determine most representational image in multiple images, such as can be based on reverse transmittance nerve network Or convolutional neural networks building.

In accordance with an embodiment of the present disclosure, the number of the first typical image of each first image group specifically can be according to first All images that image group includes determine, for example, when the first image group is character image group, and include in the image group children, When the image of young people and the elderly, so that it may determine first typical image of three images as the image group.It is understood that , the determination method of the typical image number of above-mentioned image group is only used as example in favor of understanding the disclosure, and the disclosure is to this It is not construed as limiting.

In operation S204, in response to the first acquisition request, show in one or more first image groups at least one first At least one first typical image of image group.

In accordance with an embodiment of the present disclosure, above-mentioned first acquisition request, which specifically can be, opens storage multiple images in user It is triggered when memory space, or triggered when user opens picture browsing program.Then in order to improve response efficiency, in user When opening the memory space of storage multiple images or opening picture browsing program, each first image group only can be shown to user The first typical image.

According to disclosed embodiment, all first typical images of each first image group can be specifically shown.In order into One step improves response efficiency, can also only show first typical image of each first image group, this one first typical Image can specifically be determined according to the historical viewings of user record etc..For example, when the first typical image include child image, It, can if record the frequency highest for determining user's browsing child image according to historical viewings when young people's image and old man's image To determine first typical image as child image.

In embodiment of the disclosure, in order to further improve response efficiency, operation S203 can be according only to image The attribute (such as shooting time, shooting location etc.) itself having is grouped multiple images, without to each image Carry out identifying processing.Specifically, above-mentioned image processing method specifically may is that first by image to be treated according to shooting date It is ranked up；Then the image that shooting date belongs to the same period is divided to an image group, obtains one or more figures As group；Then several (such as 3) images are randomly choosed from each image group as typical image；Then preferentially to selection Typical image carry out image recognition processing, determine the label of each image group；Consequently facilitating in response to the acquisition request of user, Timely show image.Wherein, it for non-selected atypia image, then can slowly be handled on the backstage of terminal device, In order to be shown when user requests more images.

In summary, the image processing method of the embodiment of the present disclosure, multiple images are grouped according to pre-defined rule, and Each image group determination has typical image.Then when user requests image browsing, each image group only can be shown to user Typical image to improve response efficiency, and quickly positions image group belonging to the image that its needs browses convenient for user, improves User positions the efficiency of image and improves user experience.

Fig. 3 A diagrammatically illustrates the flow chart of the image processing method according to the second embodiment of the present disclosure；Fig. 3 B is schematic It shows according to the bandwagon effect figure in the second embodiment of the present disclosure in response to user's operation.

As shown in Figure 3A, the image processing method of the embodiment of the present disclosure is other than operating S201~operation S203, can be with Including operation S304 and operation S305.

In operation S304, in response to the first acquisition request, show in one or more first image groups at least one first At least one first typical image of image group, and show at least one described first image it is one-to-one at least one Operational controls.In operation S305, in response to the operation that the first operational controls at least one operational controls are selected, show and the The parts of images or all images of the corresponding first image group of one operational controls.

In operation S304 and Fig. 2 operate S204 difference be only that, in response to the first acquisition request, also show that at least At least one one-to-one operational controls of one the first image group.The operational controls specifically for example can be push button.Its In, above-mentioned parts of images specifically for example may include other images in addition to the first typical image.By operation S304~ S305, the first image group belonging to image needed for navigating to it in user are operated, and the first typical image shown is not institute In the case where the image for stating needs, more figures can be obtained by clicking the corresponding operational controls of the first image group of positioning Picture, to further be positioned to required image.

It in accordance with an embodiment of the present disclosure, as shown in Figure 3B, include character image group, moving image in multiple first image groups In the case where group and food and drink image group, as shown in left hand view in Fig. 3 B, by aforesaid operations S304, displayed page displaying has difference And corresponding first operational controls 301 of character image group, the second operational controls 302 corresponding with moving image group and and food and drink The corresponding third operational controls 303 of image group.When the user clicks in the case where the first operational controls 301, such as right part of flg in Fig. 3 B It is shown, by aforesaid operations S305, then the operation that can be selected and (be clicked) in response to first operational controls 301, Personage's typical image 141 and 311~image of image 315 that character image group includes are shown in displayed page.

Wherein, it is contemplated that it is due to personage in the displayed page of left hand view in Fig. 3 B that user, which clicks the first operational controls 301, Typical image 141 and non-required image, and its required image belongs to character image group.Therefore, in order to enable right part of flg in Fig. 3 B Displayed page show that more images, the displayed page in the right part of flg can not also show personage's typical image 141.

In accordance with an embodiment of the present disclosure, first typical figure of each first image group is only shown in operation S304 As and in the case that character image group includes at least two first typical images, in Fig. 3 B for being obtained by aforesaid operations S305 Right side displayed page can not only show other first typical images in character image group in addition to personage's typical image 141, also It can show other images (i.e. atypia image) in character image group in addition to the first typical image.And it is opened up in operation S304 In the case where all first typical images for having shown each first image group, right side in Fig. 3 B for being obtained by aforesaid operations S305 Displayed page then can all show the atypia image of character image group.The disclosure is to via the displaying obtained after operation S305 Number and type of image etc. are not construed as limiting.

In summary, setting of the embodiment of the present disclosure by above-mentioned operational controls corresponding with the first image group, Ke Yifang Just other images of the first image group of its positioning of user's quick obtaining, and therefore can be further improved and scheme needed for user's positioning The efficiency of picture improves user experience.

Fig. 4 A diagrammatically illustrates the flow chart of the image processing method according to the third embodiment of the present disclosure；Fig. 4 B is schematic It shows according to the bandwagon effect figure in the third embodiment of the present disclosure in response to user's operation.

As shown in Figure 4 A, the image processing method of the embodiment of the present disclosure further includes other than operating S201~operation S204 Operate S406.

In operation S406, in response to selecting the operation of the first image at least one first typical image in the first way, Show at least one other image in the first image group of the first characterization image in addition to the first image.

It in accordance with an embodiment of the present disclosure, can be fast after for the ease of image group belonging to user's image needed for positioning it Speed gets more images of affiliated image group, can be by least one first typical image of each of displaying the first image group In hyperlink of first image as other images can get the image institute when selecting the image in the first way Belong at least one other image of image group.Wherein, first method specifically for example can be the mode that user clicks the first image, At least one other image includes the first typical image and/or the image in addition to the first typical image.Specifically, as operation S204 In do not show all in the case where the first typical images of the first image group, at least one of operation S406 other images can be with The first typical image including not showing and the image in addition to the first typical image.The first image group is illustrated when operating in S204 All in the case where the first typical images, other images of at least one of operation S406 then can only include except first is typical Other images outside image.

In embodiment of the disclosure, the first image group that multiple images divide is including character image group, movement In the case where image group and food and drink image group, as shown in left hand view in Fig. 4 B, the movement of moving image group is typical when the user clicks When image 142, the displayed page as shown in right part of flg in Fig. 4 B can be shown to user.It shows and movement typical image 142 Belong to tennis field picture 421, basketball field picture 422, Rugby field image 423 and the court image of moving image group 424.It is understood that above-mentioned 421~image of image 424 is only as example in favor of understanding the disclosure, the disclosure to this not It limits.

Fig. 5 A diagrammatically illustrates the flow chart of the image processing method according to the fourth embodiment of the present disclosure；Fig. 5 B is schematic It shows according to the bandwagon effect figure in the fourth embodiment of the present disclosure in response to user's operation.

In accordance with an embodiment of the present disclosure, first typical figure of each first image group is only shown in operation S204 In the case that picture and at least one first image group therein include at least two first typical images, looked into for the ease of user See other typical images of at least one the first image group, as shown in Figure 5A, the image processing method of the embodiment of the present disclosure in addition to It operates outside S201~operation S204, further includes operation S507.

In operation S507, in response to selecting the operation of the second image at least one first typical image in a second manner, Show the first typical image in the first image group of the second characterization image in addition to the second image.

Wherein, second method specifically for example can be the mode of sliding, aforesaid operations S507 be specifically in response to The operation of the second image of the first image group is slided at family, successively shows other first typical images.As shown in Figure 5 B, work as user Finger click personage's typical image 141 while, the second position of right part of flg is slid into from the first position of left hand view 501 In the case where 502, can show the typical image 311 for belonging to character image group in right part of flg with personage's typical image 141 and Typical image 312.

It is similar, when the character image group is other than typical image 141, typical image 311 and typical image 312, also wrap In the case where including other typical images, the image processing method of the embodiment of the present disclosure be can also continue in response to user from displaying The slide of the right side of the page to the left shows other typical images.

Similar, in the case where the current presentation page is the image right in Fig. 5 B, at the image of the embodiment of the present disclosure Reason method may also respond to user from the second position 502 to the slide of first position 501, will show image typical image 311 and typical image 312 gradually move right, and simultaneously gradually show personage's typical image 141.

In summary, the image processing method of the embodiment of the present disclosure, by the setting of aforesaid operations S507, can in order to Family is checked in addition to other typical images in the first image group other than the second image, consequently facilitating user determines that required image is It is no to belong to the first image group, and therefore can be further improved location efficiency, improve user experience.

Fig. 6 A diagrammatically illustrates the flow chart of the image processing method according to the fifth embodiment of the present disclosure.

As shown in Figure 6A, operation S201~operation S204 that the image processing method of the embodiment of the present disclosure is described in addition to Fig. 2 It outside, further include operation S608~operation S609.

In operation S608, the first typical image of each first image group is handled, each first image group is obtained Label.

Wherein, operation S608 can be executed between operation S203 and operation S204.Alternatively, passing through in operation S202 needs In the case where just can be carried out the division of image group to multiple images progress identifying processing, operation S608 for example can also be with operation S202 is synchronous to be executed, and after operation S203 has determined the first typical image, determines the label of each first image group.

In accordance with an embodiment of the present disclosure, operation S608, which specifically can be, carries out image recognition to the first typical image, mentions Characteristics of image is obtained, determines that multiple first typical image is total according to the characteristics of image of multiple first typical images extracted Some features, and determine according to the shared feature label of each first image group.In accordance with an embodiment of the present disclosure, the operation S608 can also specifically be executed by the good machine learning model of pre-training, then specifically with the typical case of determining each image group Input of the image as machine learning model, output obtains the common feature of each image group, to obtain each image group Label.

In operation S609, in response to the second acquisition request, displaying includes with the matched first image group of the second acquisition request The first typical image.

In accordance with an embodiment of the present disclosure, it is contemplated that the diversity of image may divide to obtain more according to pre-defined rule Image group may can not show institute in a page when operation S204 is shown the typical image of multiple image group There is the typical image of image group.Image group belonging to image needed for then quickly positioning for the ease of user, can also set for user Function of search is set, so that user is passed through input voice information, image or search statement etc. to scan for multiple images group.

Correspondingly, above-mentioned second acquisition request may include having voice messaging, image information and/or text information.It is above-mentioned When second acquisition request can be in the voice messaging for collecting user or get the image and search statement of user's input It generates, and second acquisition request includes the voice messaging of acquisition, the image of input and search statement etc..For example, working as user When inputting phonetic order " me please be help to look for lower cuisines picture ", by aforesaid operations S609, cuisines image group can be shown to user Typical image, for user browse select.

In accordance with an embodiment of the present disclosure, aforesaid operations S609 specifically for example also needs to identify second acquisition request Processing, to obtain the matched typical image shown to user.In such cases, for details, reference can be made to figures for the execution of operation S609 The description of 6B, details are not described herein.

Fig. 6 B diagrammatically illustrates the flow chart for showing image in response to the second acquisition request according to the embodiment of the present disclosure.

In accordance with an embodiment of the present disclosure, as shown in Figure 6B, aforesaid operations S609 can specifically include operation S6091~operation S6093。

The request feature of the second acquisition request is extracted using first nerves network model in operation S6091.It is operating S6092 determines that the image group to be presented in the first image group of one or more, the image group to be presented have and request feature The label matched.In operation S6093, the first typical image that image group to be presented includes is shown.

In accordance with an embodiment of the present disclosure, should in response to the second acquisition request show image process specifically may is that first with Second acquisition request (specifically can be the voice messaging of acquisition or the image of acquisition and search statement etc.) is used as first nerves net The input of network model, input obtain the request feature of second acquisition request, such as when user's input " please help me to look for lower cuisines figure When the voice messaging of piece ", it can extract to obtain request feature " cuisines ".Then by the request feature extracted with each first figure The label of picture group is compared, and using the first image group of label and the request characteristic matching as image group to be presented.Finally Directly show the typical image of the image group to be presented.

In accordance with an embodiment of the present disclosure, above-mentioned first nerves network model specifically for example can be convolutional neural networks mould Type, with the feature for extracting the second acquisition request (specifically extraction voice messaging, image or text).It is understood that The first nerves network model can have different structure and parameter according to the different type of the second acquisition request.And this first Neural network model can be the mould of same type with above-mentioned nervus opticus network model and/or third nerve network model Type or different types of structure, the disclosure are not construed as limiting this.

Fig. 7 A diagrammatically illustrates the flow chart of the image processing method according to the sixth embodiment of the present disclosure；Fig. 7 B is schematic It shows according to the bandwagon effect figure in the sixth embodiment of the present disclosure in response to reordering operations.

A variety of demands when in view of user's image needed for searching, can be by multiple images according to different pre-defined rules It is grouped, obtains a variety of different types of image groups.For example, multiple images can be divided into according to the picture material for including it is more A first image group；And multiple image can also be divided into multiple second image groups according to shooting time, thus for user's It searches and various modes is provided.For example, image needed for user just knows that it include content when, it can by checking multiple The typical image of one image group quickly navigates to image group belonging to required image；And when user just knows that its required image When shooting time, it can quickly position image belonging to required image by checking the typical image of multiple second image groups Group.

Therefore, the image processing method of the embodiment of the present disclosure should provide the choosing of the division mode of image group also for user It selects, and also should respond to the different demarcation mode selected in user, the content of current presentation page presentation is updated.Then such as Shown in Fig. 7 A, the image processing method of the embodiment of the present disclosure should also include operation S710~operation S712.

In operation S710, in response to rearrangement request, multiple images are divided into one or more second image groups.It is operating S711 determines that one or more images in each second image group are the second typical image, for characterizing each second image Group.In operation S712, at least one first typical image of at least one the first image group of displaying is updated at least one At least one second typical image of second image group.Wherein, image group is divided into multiple images in aforesaid operations S710 Operation, and operation S711 in determine the second image group the second typical image operation respectively with operation S202 and operate S203 class Seemingly, details are not described herein.

Specifically, as shown in Figure 7 B, the image processing method of the embodiment of the present disclosure can for example provide four kinds of different modes Image partition method, according to picture material divide, according to screening-mode divide, according to shooting time divide and according to shooting Place divides.Image group can be rung in the case where division according to picture material in the current presentation page shown in left hand view Rearrangement request should be generated in the operation of user's selection shooting time.And according to the rearrangement request, image group is carried out to multiple images Repartition, obtain at least one second image group.Then it determines the second typical image of each second image group, finally will The displayed page of left hand view is changed to the displayed page of right part of flg in Fig. 7 B.For example, can be obtained when being grouped according to shooting time Second image group of the second image group and the second time period shooting shot to first time period, then in the displayed page of right part of flg The middle typical image 701 (bed) and typical image 702 (dining table) for showing this two the second image groups respectively.It is understood that The generation of the displayed page with reference to described in Fig. 7 B and above-mentioned rearrangement request is used as example only in favor of understanding the disclosure, the disclosure This is not construed as limiting.

In summary, the embodiment of the present disclosure can be provided by aforesaid operations S710~operation S712 setting for user More selections, and the image needed for it therefore can be quickly navigated in order to user, further increase response efficiency and user Experience.

Fig. 8 diagrammatically illustrates the structural block diagram of the image processing apparatus according to the embodiment of the present disclosure.

As shown in figure 8, the image processing apparatus 800 of the embodiment of the present disclosure includes obtaining module 810, grouping module 820, allusion quotation Type image determining module 830 and display module 840.

Wherein, module 810 is obtained for obtaining multiple images.Grouping module 820 is used for according to pre-defined rule, by multiple figures As being divided into one or more first image groups.Typical image determining module 830 is used to determine one in each first image group A or multiple images are the first typical image, and the first typical image of each first image group is for characterizing each first figure As group.Display module 840 is used in response to the first acquisition request, show in one or more first image groups at least one first At least one first typical image of image group.In accordance with an embodiment of the present disclosure, above-mentioned acquisition module 810, grouping module 820, Typical image determining module 830 and display module 840 for example may be respectively used for executing operation S201~operation of Fig. 2 description S204, details are not described herein.

In accordance with an embodiment of the present disclosure, above-mentioned display module 840 for example can be also used for: in response to the first acquisition request, It shows and at least one one-to-one operational controls of at least one first image group；And in response at least one operational controls In the operation that is selected of the first operational controls, show the parts of images or whole of the first image group corresponding with the first operational controls Image, wherein parts of images includes other images in addition to the first typical image.In accordance with an embodiment of the present disclosure, the displaying mould Block 840 for example can be also used for executing operation S304~operation S305 of Fig. 3 A description, and details are not described herein.

In accordance with an embodiment of the present disclosure, above-mentioned display module 840 for example can be also used for: in response to selecting in the first way The operation of first image at least one first typical image shows and removes the first image in the first image group of the first characterization image Outer at least one other image.Wherein, at least one other image including the first typical image and/or removes the first typical image Outer image.In accordance with an embodiment of the present disclosure, which for example can be also used for executing the operation of Fig. 4 A description S406, details are not described herein.

In accordance with an embodiment of the present disclosure, above-mentioned display module 840 can also be for example also used to: in response to selecting in a second manner The operation of the second image at least one first typical image is selected, shows and removes the second figure in the first image group of the second characterization image The first typical image as outside.Wherein, the first image group of the second characterization image includes multiple first typical images, and shows mould Block 840 only shows first allusion quotation of each first image group at least one first image group in response to the first acquisition request Type image.In accordance with an embodiment of the present disclosure, which for example can be also used for executing the operation S507 of Fig. 5 A description, Details are not described herein.

In accordance with an embodiment of the present disclosure, as shown in figure 8, above-mentioned image processing apparatus 800 can also include processing module 850.The processing module 850 obtains each first image for handling the first typical image of each first image group The label of group.Correspondingly, above-mentioned display module 840 can be also used for showing to obtain with second and asking in response to the second acquisition request The first typical image for asking matched first image group to include.In accordance with an embodiment of the present disclosure, above-mentioned processing module 850 and displaying Module 840 can also for example be respectively used to execute the operation S608 of Fig. 6 A description and operation S609, and details are not described herein.

In accordance with an embodiment of the present disclosure, as shown in figure 8, display module 840 can specifically include extraction unit 841, determine Unit 842 and display unit 843.Wherein, extraction unit 841 is used to use first nerves network model, extracts the second acquisition and asks The request feature asked.For determination unit 842 for determining the image group to be presented in one or more first image groups, this is to be presented Image group has the label with request characteristic matching.Display unit 843 is used to show that image group to be presented includes first is typical Image.Wherein, the second acquisition request includes voice messaging, image information and/or text information.In accordance with an embodiment of the present disclosure, Said extracted unit 841, determination unit 842 and display unit 843 for example may be respectively used for executing the operation of Fig. 6 B description S6091, operation S6092 and operation S6093, details are not described herein.

In accordance with an embodiment of the present disclosure, above-mentioned grouping module 820 can also be for example also used in response to rearrangement request, will be more A image is divided into one or more second image groups.Above-mentioned typical image determining module 830 for example can be also used for determining every One or more images in a second image group are the second typical image, wherein the second typical figure of each second image group As for characterizing each second image group.Above-mentioned display module 840 for example can be also used at least one first figure that will be shown As at least one first typical image of group is updated at least one second typical image of at least one the second image group.According to Embodiment of the disclosure, above-mentioned grouping module 820, typical image determining module 830 and display module 840 can also for example be distinguished For executing the operation S710~operation S712 for referring to Fig. 7 A description, no longer trace herein.

In accordance with an embodiment of the present disclosure, above-mentioned grouping module 820 at least can be by following four mode to multiple images It is divided.Wherein, first way are as follows: shooting time in multiple images is belonged to the image point extremely same figure of same time period As group, one or more first image groups are obtained.The second way are as follows: will include similar/same object in multiple images Image point obtains one or more first image groups to same image group.The third mode are as follows: by multiple images by identical bat The image that the mode of taking the photograph is shot point obtains one or more first image groups to same image group.4th kind of mode are as follows: will be more The image point extremely same image group shot in a image in same area, obtains one or more first image groups.

In accordance with an embodiment of the present disclosure, above-mentioned grouping module 820 specifically can be used for using nervus opticus network model, will Multiple images are divided into one or more first image groups.Above-mentioned typical image determining module 830 specifically can be used for using third Neural network model is the first typical image by one or more images of each first image group of determination of the first image group.

It is module according to an embodiment of the present disclosure, submodule, unit, any number of or in which any more in subelement A at least partly function can be realized in a module.It is single according to the module of the embodiment of the present disclosure, submodule, unit, son Any one or more in member can be split into multiple modules to realize.According to the module of the embodiment of the present disclosure, submodule, Any one or more in unit, subelement can at least be implemented partly as hardware circuit, such as field programmable gate Array (FPGA), programmable logic array (PLA), system on chip, the system on substrate, the system in encapsulation, dedicated integrated electricity Road (ASIC), or can be by the hardware or firmware for any other rational method for integrate or encapsulate to circuit come real Show, or with any one in three kinds of software, hardware and firmware implementations or with wherein any several appropriately combined next reality It is existing.Alternatively, can be at least by part according to one or more of the module of the embodiment of the present disclosure, submodule, unit, subelement Ground is embodied as computer program module, when the computer program module is run, can execute corresponding function.

For example, obtaining module 810, grouping module 820, typical image determining module 830, display module 840, processing module 850, any number of in extraction unit 841, determination unit 842 and display unit 843 may be incorporated in real in a module Any one module existing or therein can be split into multiple modules.Alternatively, one or more modules in these modules At least partly function can be combined at least partly function of other modules, and realized in a module.According to this public affairs The embodiment opened obtains module 810, grouping module 820, typical image determining module 830, display module 840, processing module 850, at least one of extraction unit 841, determination unit 842 and display unit 843 can be at least implemented partly as On hardware circuit, such as field programmable gate array (FPGA), programmable logic array (PLA), system on chip, substrate is System, the system in encapsulation, specific integrated circuit (ASIC), or can be by carrying out integrated to circuit or encapsulating any other The hardware such as rational method or firmware realize, or with any one in three kinds of software, hardware and firmware implementations or with it In any several appropriately combined realize.Alternatively, obtain module 810, grouping module 820, typical image determining module 830, At least one of display module 840, processing module 850, extraction unit 841, determination unit 842 and display unit 843 can To be at least implemented partly as computer program module, when the computer program module is run, can execute corresponding Function.

Fig. 9 is diagrammatically illustrated according to the image processing system for being adapted for carrying out image processing method of the embodiment of the present disclosure Structural block diagram.It is understood that the image processing system shown in Fig. 9 is only an example, it should not be to the embodiment of the present disclosure Function and use scope bring any restrictions.

As shown in figure 9, image processing system 900 includes processor 910 and computer readable storage medium 920.The figure As processing system 900 can execute the image processing method according to the embodiment of the present disclosure.

Specifically, processor 910 for example may include general purpose microprocessor, instruction set processor and/or related chip group And/or special microprocessor (for example, specific integrated circuit (ASIC)), etc..Processor 910 can also include using for caching The onboard storage device on way.Processor 910 can be the different movements for executing the method flow according to the embodiment of the present disclosure Single treatment unit either multiple processing units.

Computer readable storage medium 920, such as can be non-volatile computer readable storage medium, specific example Including but not limited to: magnetic memory apparatus, such as tape or hard disk (HDD)；Light storage device, such as CD (CD-ROM)；Memory, such as Random access memory (RAM) or flash memory；Etc..

Computer readable storage medium 920 may include computer program 921, which may include generation Code/computer executable instructions execute processor 910 according to the embodiment of the present disclosure Method or its any deformation.

Computer program 921 can be configured to have the computer program code for example including computer program module.Example Such as, in the exemplary embodiment, the code in computer program 921 may include one or more program modules, for example including 921A, module 921B ....It should be noted that the division mode and number of module are not fixation, those skilled in the art can To be combined according to the actual situation using suitable program module or program module, when these program modules are combined by processor 910 When execution, processor 910 is executed according to the method for the embodiment of the present disclosure or its any deformation.

According to an embodiment of the invention, obtaining module 810, grouping module 820, typical image determining module 830, showing mould At least one of block 840, processing module 850, extraction unit 841, determination unit 842 and display unit 843 may be implemented Corresponding behaviour described above may be implemented when being executed by processor 910 for the computer program module with reference to Fig. 9 description Make.

The disclosure additionally provides a kind of computer readable storage medium, which can be above-mentioned reality It applies included in equipment/device/system described in example；Be also possible to individualism, and without be incorporated the equipment/device/ In system.Above-mentioned computer readable storage medium carries one or more program, when said one or multiple program quilts When execution, the method according to the embodiment of the present disclosure is realized.

In accordance with an embodiment of the present disclosure, computer readable storage medium can be non-volatile computer-readable storage medium Matter, such as can include but is not limited to: portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), portable compact disc read-only memory (CD-ROM), light Memory device, magnetic memory device or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or Person is in connection.

Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction It closes to realize.

It will be understood by those skilled in the art that the feature recorded in each embodiment and/or claim of the disclosure can To carry out multiple combinations and/or combination, even if such combination or combination are not expressly recited in the disclosure.Particularly, exist In the case where not departing from disclosure spirit or teaching, the feature recorded in each embodiment and/or claim of the disclosure can To carry out multiple combinations and/or combination.All these combinations and/or combination each fall within the scope of the present disclosure.

Although the disclosure, art technology has shown and described referring to the certain exemplary embodiments of the disclosure Personnel it should be understood that in the case where the spirit and scope of the present disclosure limited without departing from the following claims and their equivalents, A variety of changes in form and details can be carried out to the disclosure.Therefore, the scope of the present disclosure should not necessarily be limited by above-described embodiment, But should be not only determined by appended claims, also it is defined by the equivalent of appended claims.

Claims

1. a kind of image processing method, comprising:

Obtain multiple images；

According to pre-defined rule, described multiple images are divided into one or more first image groups；

Determine that one or more images in each first image group are the first typical image, for characterizing each first figure As group；And

In response to the first acquisition request, show that at least one first image group is at least in one or more of first image groups One the first typical image.

2. according to the method described in claim 1, further include:

In response to first acquisition request, show and at least one the one-to-one operation of at least one described first image group Control；And

In response to the operation that the first operational controls at least one described operational controls are selected, shows and controlled with first operation The parts of images or all images of the corresponding first image group of part, wherein the parts of images includes in addition to the first typical image Other images.

3. according to the method described in claim 1, further include:

In response to selecting the operation of the first image at least one described first typical image in the first way, described first is shown At least one other image in first image group of characterization image in addition to the first image, wherein it is described at least one its His image includes the first typical image and/or the image in addition to the first typical image；And/or

In response to selecting the operation of the second image at least one described first typical image in a second manner, described second is shown The first typical image in first image group of characterization image in addition to second image, wherein second characterization image First image group includes multiple first typical images, and in response to first acquisition request, only show it is described at least one the First typical image of each first image group in one image group.

4. according to the method described in claim 1, further include:

First typical image of each first image group is handled, the label of each first image group is obtained； And

In response to the second acquisition request, the first typical figure for including with the matched first image group of second acquisition request is shown Picture.

5. according to the method described in claim 4, wherein, in response to the second acquisition request, showing and second acquisition request The first typical image that matched first image group includes includes:

Using first nerves network model, the request feature of second acquisition request is extracted；

Determine the image group to be presented in one or more of first image groups, the image group to be presented has asks with described Seek the label of characteristic matching；And

Show the first typical image that the image group to be presented includes,

Wherein, second acquisition request includes voice messaging, image information and/or text information.

6. according to the method described in claim 1, further include:

In response to rearrangement request, described multiple images are divided into one or more second image groups；

Determine that one or more images in each second image group are the second typical image, for characterizing each second figure As group；And

At least one first typical image of at least one the first image group described in displaying is updated at least one second figure As at least one second typical image of group.

7. it is described according to pre-defined rule according to the method described in claim 1, wherein, described multiple images are divided into one Or multiple first image groups include:

The image that shooting time in described multiple images belongs to same time period is divided to same image group, is obtained one Or multiple first image groups；Or

To include that the image of similar/same object is divided to same image group in described multiple images, obtain it is one or Multiple first image groups；Or

Same image group will be divided to by the image that identical screening-mode is shot in described multiple images, obtained one Or multiple first image groups；Or

It will be divided to same image group in the image that same area is shot in described multiple images, obtained one or more A first image group.

8. according to the method described in claim 1, wherein:

According to pre-defined rule, it includes: using nervus opticus net that described multiple images, which are divided into one or more first image groups, Described multiple images are divided into one or more first image groups by network model；And/or

Determine that one or more images in each first image group be the first typical image include: using third nerve network mould Type is the first typical image by one or more images of each first image group of determination of the first image group.

9. a kind of image processing apparatus, comprising:

Module is obtained, for obtaining multiple images；

Grouping module, for according to pre-defined rule, described multiple images to be divided into one or more first image groups；

Typical image determining module, for determining that one or more images in each first image group are the first typical image, For characterizing each first image group；And

Display module, in response to the first acquisition request, showing at least one in one or more of first image groups the At least one first typical image of one image group.

10. a kind of image processing system, comprising:

One or more processors；

Storage device, for storing one or more programs,

Wherein, when one or more of programs are executed by one or more of processors, so that one or more of Method described in processor execution according to claim 1~any one of 8.