CN106980696B - Photo file classification method and device - Google Patents
Photo file classification method and device Download PDFInfo
- Publication number
- CN106980696B CN106980696B CN201710220250.XA CN201710220250A CN106980696B CN 106980696 B CN106980696 B CN 106980696B CN 201710220250 A CN201710220250 A CN 201710220250A CN 106980696 B CN106980696 B CN 106980696B
- Authority
- CN
- China
- Prior art keywords
- event
- photo
- description information
- type
- file
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Abstract
The invention discloses a classification method and device for photo files. Wherein the method comprises the following steps: obtaining event description information; analyzing the event description information to obtain a first type parameter, a second type parameter and corresponding parameter values, wherein the first type parameter is a file attribute parameter of a photo file, and the second type parameter is an image attribute parameter of the photo file; according to the first type parameters and the second type parameters, event photo files matched with the event description information are screened out from photo files to be classified; and aggregating the event photo files. The method and the device acquire a plurality of parameters in two types of parameters, namely the file attribute parameter and the image attribute parameter, based on the event description information, and aggregate and classify the photo files, so that the classified photo set comprises photos with higher event correlation, and the efficiency of searching and positioning the follow-up photos is improved.
Description
Technical Field
The invention relates to the technical field of file classification, in particular to a classification method and device for photo files.
Background
The prior art typically arranges the image files in a time sequence. When a user wishes to find a photo, it generally takes more time to browse through a large number of photos. It can be seen that the photo files are simply arranged according to the time sequence, so that the photo searching efficiency is low, and the use experience of a user is affected.
Disclosure of Invention
The embodiment of the invention provides a classification method and device for photo files, which are used for improving the searching efficiency of the photo files and improving the use experience of users.
In a first aspect, an embodiment of the present invention provides a method for classifying photo files, including:
obtaining event description information;
analyzing the event description information to obtain a first type parameter, a second type parameter and corresponding parameter values, wherein the first type parameter is a file attribute parameter of a photo file, and the second type parameter is an image attribute parameter of the photo file;
according to the first type parameters and the second type parameters, event photo files matched with the event description information are screened out from photo files to be classified;
and aggregating the event photo files.
In a second aspect, an embodiment of the present invention further provides a classification device for photo files, including:
The event acquisition module is used for acquiring event description information;
the event analysis module is used for analyzing the event description information to obtain first type parameters, second type parameters and corresponding parameter values, wherein the first type parameters are file attribute parameters of the photo file, and the second type parameters are image attribute parameters of the photo file;
the photo matching module is used for screening event photo files matched with the event description information from photo files to be classified according to the first type parameters and the second type parameters;
and the aggregation module is used for aggregating the event photo files.
The method and the device for classifying the photo files provided by the embodiment of the invention have at least the following beneficial effects:
in the embodiment of the invention, based on the event description information, the obtained file attribute parameters and the obtained multiple parameters in the two types of parameters are aggregated and classified on the photo files, so that the photo set obtained after classification comprises photos with higher correlation, and the efficiency of searching and positioning subsequent photos is improved. In addition, the embodiment of the invention gathers together the photos with higher event correlation, thereby facilitating the browsing and searching of the photo files by the user and improving the use experience of the user.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a photograph file provided in an embodiment of the present invention an application scene schematic diagram of the classification method of (a);
fig. 2 is a flow chart of a classification method of photo files according to an embodiment of the present invention;
fig. 3 is an exemplary diagram illustrating photo album in a terminal APP according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating an example of implementing photo collection sharing in an APP of a terminal according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating another method for classifying photo files according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a sorting device for photo files according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a sorting device for still another photo file according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a sorting device for still another photo file according to an embodiment of the present invention;
Fig. 9 is a schematic structural diagram of a sorting device for still another photo file according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of a sorting device for still another photo file according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
As described above, the processing manner of arranging the photo files in time sequence, when the user needs to find a certain photo, the user is usually required to browse and search one by one in a large number of photo files, so that the positioning and searching of the photo files are not facilitated, and the use experience of the user is affected.
The embodiment of the invention provides a classification method of photo files, which can improve the positioning accuracy and the searching efficiency of the photo files and improve the use experience of users. The classification method of the embodiment of the invention can be applied to terminal equipment to classify photos locally at the terminal equipment, for example, classifying photo files shot by a digital camera or a smart phone. The classifying method according to the embodiment of the present invention may also be applied to a server on a network side, for example, to classify photos uploaded to an album space by a user, where an application scenario of the embodiment of the present invention is shown in fig. 1, and a personal terminal of the user, such as a smart phone 11 and/or a personal computer 12, is connected to a remote server 15 through a network 14, and specifically, the smart phone 11 may be accessed to the network 14 through a base station 13 of a mobile communication network. The user can upload the photo files shot by the user to a remote server 15 through the personal terminal, and the server 15 sorts and aggregates the photo files and displays the photo files to the user in a webpage form or an Application (APP) form.
In order to help understand the technical scheme of the embodiment of the present invention, first, two types of parameters of the photo file related in the embodiment of the present invention are described.
In the embodiment of the invention, two types of parameters of a photo file need to be acquired:
the first type of parameters are file attribute parameters, which are parameters obtained based on file attributes of the photo file. For example, for a certain photo file, the file attribute thereof may specifically include a file format, a file size, a shooting time, a shooting location, a shooting device, and the like of the photo file, and thus the first type of parameter may include one or more of parameters of the file format, the file size, the shooting time, the shooting location, the shooting device, and the like. Specifically, parameters such as file format and file size can be obtained by reading file attribute information, and parameters such as shooting time, shooting location, shooting device and the like can be obtained by parsing exchangeable image file (ExIF, exchangeable Image File) information of a photo file.
The second type of parameter is an image attribute parameter, which is a parameter obtained based on the image attribute of the photo file. For example, for a certain photo file, the image attribute may specifically include content of the image, hue of the image, contrast of the image, brightness of the image, and so on, and thus the second type of parameter may include one or more of parameters of image content, hue of the image, contrast of the image, brightness of the image, and so on. Specifically, the image attribute parameters can be obtained by performing content recognition or feature extraction on the image through an image recognition algorithm. For example, features in the image are extracted through a convolutional neural network model, and relevant image content is obtained.
Of course, the image attribute parameter may be further subdivision parameters for the foregoing image content, image tone, image contrast, image brightness, and the like, for example, for image content including a face image, an animal image, and the like, specifically, for a parameter value of the face image, further subdivision may be performed according to person identities corresponding to different faces, for example, person identities may be persons in a plurality of age intervals divided by ages, such as old people, children, young people, and the like, persons divided by gender, such as men, women, and the like, or more specific users, such as user a, user B, user C, and the like.
In the embodiment of the present invention, the parameter values of the first type parameter and the second type parameter may be set according to specific parameters. For example, for a file format in the first type of parameters, the parameter values may be JPG format, BMP format, etc.; for the file size, because the values cannot be exhausted, for comparison, the values can be divided into a plurality of continuous and non-repeated value intervals, and the value interval corresponding to the file size is taken as the parameter value. Similarly, for parameters whose values cannot be exhausted, a manner of predefining a plurality of intervals/periods may be adopted to divide the parameter values into corresponding intervals/periods. For another example, for the photographing time, a specific photographing time corresponding to the photographing time may be divided into a certain natural day. For another example, for a shooting location, specific longitude and latitude coordinates may be divided into a predefined administrative area range, and of course, the sizes of administrative areas of different levels may be different, and different accuracies may be set as required.
For example, for the image content in the second type of parameter, parameter values of a plurality of image contents, such as "child", "sunrise", "desert", "delicacy", "running", etc., may be predefined, for example, if the image content is mainly about child, the image content may be categorized into "child" in the image content, where "child" is the parameter value of the image content. For another example, for the hue of an image in the second type of parameters, parameter values of a plurality of hues, such as "cold hue" and "warm hue", may be predefined, and further the parameter values of its hue parameters may be determined from the main hue of the image, and so on.
It should be noted that, since the first type of parameter and the second type of parameter may each include one or more parameters, in order to reduce the computation load of the classification process, in the embodiment of the present invention, the value ranges of one or more parameters and parameter values thereof included in each of the first type of parameter and the second type of parameter may be predetermined, for example, the first type of parameter may include only a photographing time and a photographing place, the parameter value of the photographing time is a date defined by natural month & natural day, and the parameter value of the photographing place may be a region range divided based on a predetermined administrative region; the second type of parameters may include only image content, and the parameter values of the image content may be food, people, sports, etc.
Referring to fig. 2, the method for classifying photo files according to the embodiment of the present invention may be applied to classifying photos in a local album or a web album of a terminal. As shown in fig. 2, the classification method includes:
Here, the event description information is related information describing a certain event, and a specific description manner may be in a form of voice, text, and the like. Events typically represent what happens at a particular time, location, and event description information may typically include information such as time, location, and event content. Of course, the event description information may also include more or less information. For example, "10 months 1 day holds the color run activity in Shenzhen bay", "1 month 1 day holds the annual fireworks show in Victoria harbor" are all possible event descriptors.
Specifically, the event description information may be input by a user, and at this time, the relevant event description information may be obtained by receiving input text or voice of the user. For example, when a user takes a picture using a digital camera, high-definition pictures have been taken for some flowers of interest, the file size of these picture files is large, and if the user wants to aggregate these pictures, event description information similar to "high-definition pictures of flowers of 10 months 3 days" can be input.
Considering photos taken by users, they are often indistinguishable from the daily activities of users, and in the internet age, users often post their daily activities on a network, for example, in personal websites, personal logs, microblogs or WeChat circles. In order to improve the intelligent and automatic degree of photo file classification, the embodiment of the invention can also search the content issued by the user on the network to obtain the event description information.
For example, the user has issued a friend circle message on a day: today's mood is very warm … …, an event description message may be generated by analyzing the content of the friend circle message, for example, converting "today" into an actual date, and assuming "10 months 5 days", an event description message such as "10 months 5 days mood is very warm" may be obtained.
For another example, the user has sent a log on the personal log: the "black night" can obtain the release time of the log by analyzing the content of the message, and obtain a time parameter, such as "10 months and 6 days", so as to obtain an event description message "black night of 10 months and 6 days".
For another example, assume that the user has issued a personal dynamic: "today I participated in The Color Run activity of Shenzhen Bay", an event description information can be generated by analyzing The dynamic content of The person, for example, the event description information of "The Color Run activity of Shenzhen Bay of 10 months 1 day" can be obtained by converting "today" into an actual date, which is assumed to be "10 months 1 day".
According to the embodiment of the invention, the event description information can be analyzed through voice recognition and/or semantic recognition and other technologies, related parameters and parameter values related to the event description information are obtained, and the event description information corresponds to the first type of parameters and the second type of parameters.
Continuing with the above example, for the event description information of the "high definition photo of flowers on day 10 months and 3" illustrated above, the information including "day 10 months and 3", "high definition photo" and "flowers" can be resolved. Wherein, "10 months 1 day" is a time parameter, which may correspond to a photographing time in the first type of parameters; the 'high-definition photo' can be resolved into a file size, and the file size, such as more than 8 Mbytes, is determined according to a file size interval of the predefined high-definition photo; "flowers" are event content, which may correspond to image content in a second class of parameters, and thus obtain: shooting time in the first type of parameters, wherein the parameter value is 10 months and 3 days; file size in the first class of parameters, the parameter value of which is "greater than 8 mbytes"; the image content in the second type of parameters has a parameter value of "flowers".
For another example, for an event description message such as "10 month 5 day mood is very warm", the message including "10 month 5 day", "mood is warm" etc. can be resolved. Wherein "10 month 5 day" is a time parameter, which may correspond to the shooting time in the first type of parameter, and the parameter value thereof is "10 month 5 day"; "mood warmth" can be resolved into image hues, with the specific parameter value being "warmth".
For another example, for an event description message such as "black night for 10 months and 6 days", the message including "black night for 10 months and 6 days" may be parsed. Wherein "10 month 6 day" is a time parameter, which may correspond to the shooting time in the first type of parameter, and the parameter value thereof is "10 month 6 day"; the "black-of-paint" may be resolved into image brightness, and the specific parameter value may be a predefined darker brightness interval.
For another example, for the event description information of "the color run activity is held in the Shenzhen bay on day 10 and day 1", information including "day 10 and day 1", "Shenzhen bay" and "run" can be resolved. Wherein, "10 months 1 day" is a time parameter, which may correspond to a photographing time in the first type of parameters; "Shenzhen bay" is a location parameter, which may correspond to a shooting location in the first type of parameters; "run" is event content, which may correspond to image content in the second type of parameter, and thus obtains: shooting time in the first type of parameters, wherein the parameter value is 10 months and 1 day; shooting places in the first type of parameters, wherein the parameter value of the shooting places is Shenzhen bay; the image content in the second type of parameters has a parameter value of "running".
And step 23, screening event photo files matched with the event description information from photo files to be classified according to the first type parameters and the second type parameters.
Here, the photo file to be classified may be a photo stored locally in the personal terminal or may be a photo file in a network album on the server side. After obtaining the first type parameter, the second type parameter and the parameter value corresponding to the event description information, the embodiment can perform targeted search in the photo files to be classified, and screen the photo files with parameter values matched with the parameter values of the parameters corresponding to the event description information, so as to obtain the event photo files.
Continuing with the above example, if the shooting time of a certain photo file is "10 months 3 days", the file size is 8 mbytes or more, and the image content is "flowers", the parameter values of the corresponding parameters are the same as those of the high-definition photo of flowers "of" 10 months 3 days ", and at this time, the photo file can be screened out as an event photo file.
For example, if the shooting time of a certain photo file is "10 months 5 days", and the image tone is "warm tone", the parameter values of the corresponding parameters are the same as those of "10 months 5 days with very warm mood", and at this time, the photo file may be selected as an event photo file.
For example, if the shooting time of a certain photo file is "10 months 6 days", and the brightness of the image is in a predefined darker brightness interval, the parameter values of the corresponding parameters are the same as those of "10 months 6 days black night", and at this time, the photo file may be screened out as an event photo file.
For example, if The shooting time of a certain photo file is "10 months 1 day", the shooting place is "Shenzhen bay", and The image content is "running", the photo file is selected as an event photo file at The same time as The parameter value of The corresponding parameter of "The Color Run activity held in Shenzhen bay on 10 months 1 day".
In order to reduce the screening workload, the embodiment of the invention can screen one parameter by one parameter, and screen the photo file screened based on a certain parameter based on the next parameter to finally obtain the event photo file. Therefore, the embodiment of the invention can acquire the specific parameter value of the photo file about the parameter when matching a certain parameter, and if the photo file is selected in the previous screening process, the photo file is not in a consideration range, and any parameter value of the photo file is not acquired, so that the screening workload can be reduced.
Specifically, in the step 23, the first type parameters and parameter values of the photo files to be classified may be obtained, and then the first type parameters of the photo files to be classified and the first type parameters of the event description information are correspondingly matched, so as to screen out the first photo files with the matched first type parameters; and then, obtaining second type parameters and parameter values of the first photo files, correspondingly matching the second type parameters of the first photo files with the second type parameters of the event description information, screening out first photo files matched with the second type parameters, and obtaining photo files matched with the event description information. Here, if the first type parameter or the second type parameter includes a plurality of parameters, in the above-described screening process, the screening process is also performed one by one for each parameter thereof.
And step 24, aggregating the event photo file.
Here, in step 24, an event photo set corresponding to the event description information may be generated, and the event photo files screened in step 23 are aggregated in the event photo set, so as to be convenient for presentation. Of course, in order to save storage space, the embodiment of the present invention may not copy and store the event photo file in the storage space corresponding to the event photo set, but construct an index table corresponding to the event photo set, where the index table includes a set name of the event photo set and pointing information of the photo file included in the event photo set. When a user browses the event photo set, the index table is analyzed, a structure of the corresponding event photo set is generated and displayed at the terminal, and when the user browses the photo files in the event photo set, the corresponding photo files can be loaded according to the pointing information of the photo files.
Fig. 3 shows an example of photo collection presentation in a certain Application (APP) of a terminal device. Specifically, a top page of each event photo set (for example, top pages 31 to 34 in which The left half of fig. 3 is displayed in a card form and representative photos in The corresponding photo sets can be displayed on The top page) can be generated, and a set name corresponding to each event photo set is displayed on The top page of The photo set, for example, "10 month 3 day banf national park", "10 month 3 day food", "10 month 3 day sky", "10 month 1 day Shenzhen Color Run" in fig. 3; and generating a detail page of each photo set, such as a detail page 310 of a 10 month 3 day banv national park in fig. 3, establishing a correspondence between a first page of the photo set and the detail page, and displaying each photo file (such as photos 1 to 9 shown in photos 312 in fig. 3) or pointing information of each photo file in the photo set in the detail page. Some features of the photo collection may also be presented in the detail page, such as displaying information of location 313 within the detail page.
Furthermore, the embodiment of the invention can also receive the sharing request of the user for the event photo set, and generate and release the sharing space of the event photo set according to the sharing request. For example, a user can share a certain photo set to friends in a sharing space mode, so that a sharing function is realized, and information exchange among users can be realized conveniently. Fig. 4 shows an example diagram of implementing photo collection sharing in a terminal-installed APP, where a photo collection may be shared to friends by triggering a "share" key in a detail page to initiate a sharing process.
Through the steps, the method can aggregate and classify the photo files based on the file attribute parameters and the image attribute parameters obtained by the event description information. In the classifying process, the parameters of the file attribute and the parameters of the image attribute are considered to comprise a plurality of dimensions and are associated with specific event description information, so that the photo set obtained after classification comprises photos which have higher correlation and are related to a certain event, and when a user needs to search a certain photo, the user can search in the corresponding photo set according to the event description information and the parameters, thereby improving the searching and positioning efficiency and improving the use experience of the user on the photo album.
The photo file classification method according to the embodiment of the invention is described above by taking photo album as an example. The method for classifying photo files according to the embodiment of the invention is not limited to classifying photo files in photo albums, and the embodiment of the invention can be applied to classifying any photo to be classified, for example, a photo/photo publishing system applied to a portal website for classifying and publishing photos, and at this time, the application scenario of the embodiment of the invention is similar to that of fig. 1, and the server 15 classifies the photo files acquired by the photo files and then displays the photo files to terminal devices such as the smart phone 11 and/or the personal computer 12. A specific implementation in this scenario will be described below.
Referring to fig. 5, another classification method for photo files provided by the embodiment of the present invention may be applied to classification processing of photo files to be classified, as shown in fig. 5, and the classification method includes:
Here, the event description information may be input by a user, for example, the user inputs description information of a currently occurring hot event, and may specifically include time, place, event content, and the like of occurrence of the hot event.
The event description information may also be content that the device actively crawls from the network, and one implementation manner may be that a photo publishing system of the website crawls news or hot events published on the network, for example, the currently occurring hot event on the network is "2018 world cup preselect asian twelve strong match-chinese VS korea", and then the date (such as 3 months and 23 days), place (long sand stadium) and event description information of the event content (football match) of the hot event may be obtained through extracting the related web content.
For example, by the semantic recognition technology, a time of 3 months 23 days, a place of a stadium, and event content of a football match are recognized from "2018 world cup pre-select asian twelve-strong match-chinese VS korea", which correspond to shooting time, shooting place, and image content in the first type of parameters of the photo file.
And step 53, screening event photo files matched with the event description information from photo files to be classified according to the first type parameters and the second type parameters.
Here, the photo files to be classified may be obtained by the server from news websites, social media, and the like, and in this step, the photo files to be classified are classified based on the first type parameter and the second type parameter, and event photo files matched with the event description information are screened out.
And step 54, generating a webpage corresponding to the event description information, and adding text description of the event description information and the pointing information of the event photo file into the webpage.
In this step, the server may generate a web page, embed text description of the event description information on the web page, attach a preview of the event photo file, and display the event photo file in a text-to-text combination manner. When the user clicks the preview of one of the event photo files, the original photo of the event photo file can be loaded according to the pointing information so as to be provided for the user.
Through the steps, the embodiment of the invention can actively acquire the related event description information, automatically aggregate the photos corresponding to the same event on the webpage for display, improve the intelligent and automatic degree of photo file classification, improve the information release efficiency of the hot event and improve the user experience.
Referring to fig. 6, the embodiment of the present invention further provides a classification device for photo files, where the classification device may be disposed at a personal terminal device (such as a digital camera, a smart phone, a personal computer, a PAD, etc.) or a server, and as shown in fig. 6, the classification device includes:
an event obtaining module 61, configured to obtain an event description information;
the event parsing module 62 is configured to parse the event description information to obtain a first type parameter, a second type parameter, and a corresponding parameter value, where the first type parameter is a file attribute parameter of a photo file, and the second type parameter is an image attribute parameter of the photo file;
the photo matching module 63 is configured to screen out event photo files matched with the event description information from photo files to be classified according to the first type parameter and the second type parameter;
And an aggregation module 64, configured to aggregate the event photo files.
Through the modules, the embodiment of the invention carries out aggregation classification based on multiple dimensions on the photo files based on the event description information, so that the photo set obtained after classification comprises photos with higher correlation, and the efficiency of searching and positioning subsequent photos is improved.
As shown in fig. 7, in some embodiments, the event obtaining module 61 includes:
a receiving module 611, configured to receive event description information input by a user; and/or
And the retrieving module 612 is configured to retrieve content published on the network to obtain the event description information.
As shown in fig. 8, in some embodiments, the photo matching module 63 includes:
a first obtaining module 631, configured to obtain a first type of parameter and a parameter value of a photo file to be classified;
a first matching module 632, configured to correspondingly match a first type parameter of a photo file to be classified with a first type parameter of the event description information, and filter out photo files with the first type parameter matched to obtain an intermediate photo file;
a second obtaining module 633, configured to obtain a second type parameter of the intermediate photo file and a parameter value thereof;
The second matching module 634 is configured to correspondingly match the second type parameter of the intermediate photo file with the second type parameter of the event description information, and screen out the intermediate photo file matched with the second type parameter to obtain the event photo file matched with the event description information.
As shown in fig. 9, in some embodiments, the aggregation module 64 includes:
the photo set aggregation module 641 is configured to generate an event photo set corresponding to the event description information, and aggregate the event photo file in the event photo set.
Through the modules, the embodiment of the invention aggregates the photos related to the event into the same photo collection, thereby facilitating the positioning and searching of the subsequent photo files and improving the user experience.
As shown in fig. 9, in some embodiments, the sorting apparatus further includes:
the sharing module 65 is configured to receive a sharing request for the event photo set, generate a sharing space of the event photo set according to the sharing request, and issue the sharing space.
Through the modules, the embodiment of the invention realizes the analysis function of the photo file and can improve the use experience of the photo album.
As shown in fig. 10, in some embodiments, the aggregation module 64 includes:
The web page aggregation module 642 is configured to generate a web page corresponding to the event description information, and add text description of the event description information and pointing information of the event photo file to the web page.
Through the modules, the embodiment of the invention realizes the display of the event photo file in the webpage form, and can improve the information release efficiency of the hot event information.
Referring to fig. 11, fig. 11 is a block diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 11, the electronic device includes: at least one processor 1101, memory 1102, at least one network interface 1104, and a user interface 1103. The various components in the electronic device are coupled together by a bus system 1105. It is appreciated that bus system 1105 is used to implement the connected communications between these components. The bus system 1105 includes a power bus, a control bus, and a status signal bus in addition to a data bus. But for clarity of illustration, the various buses are labeled as bus system 1105 in fig. 11.
The user interface 1103 may include, among other things, a display, keyboard, or pointing device (e.g., mouse, track ball, touch pad, or touch screen, etc.).
It will be appreciated that memory 1102 in embodiments of the invention can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate Synchronous DRAM (Double Data Rate SD RAM, ddr SDRAM), enhanced SD RAM (ESDRAM), synchronous link RAM (SLDRAM), and Direct RAM (DRRAM). The memory 1102 of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some implementations, the memory 1102 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof: an operating system 11021 and application programs 11022.
The operating system 11021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application programs 11022 include various application programs such as a Media Player (Media Player), a Browser (Browser), and the like for realizing various application services. A program for implementing the method of the embodiment of the present invention may be included in the application program 11022.
In the embodiment of the present invention, by calling a program or an instruction stored in the memory 1102, specifically, a program or an instruction stored in the application program 11022, the processor 1101 is configured to: obtaining event description information; analyzing the event description information to obtain a first type parameter, a second type parameter and corresponding parameter values, wherein the first type parameter is a file attribute parameter of a photo file, and the second type parameter is an image attribute parameter of the photo file; according to the first type parameters and the second type parameters, event photo files matched with the event description information are screened out from photo files to be classified; and aggregating the event photo files.
Optionally, the processor 1101 is further configured to: and receiving event description information input by a user and/or retrieving content published on a network to obtain the event description information.
Optionally, the processor 1101 is further configured to obtain a first type of parameter and a parameter value thereof of the photo file to be classified; correspondingly matching the first type parameters of the photo files to be classified with the first type parameters of the event description information, screening photo files with the matched first type parameters, and obtaining intermediate photo files; acquiring a second type parameter and a parameter value of the intermediate photo file; and correspondingly matching the second type parameters of the intermediate photo files with the second type parameters of the event description information, screening intermediate photo files matched with the second type parameters, and obtaining event photo files matched with the event description information.
Optionally, the processor 1101 is further configured to generate an event photo set corresponding to the event description information, and aggregate the event photo file in the event photo set.
Optionally, the processor 1101 is further configured to receive a sharing request for the event photo set, generate a shared space of the event photo set according to the sharing request, and issue the shared space.
Optionally, the processor 1101 is further configured to generate a web page corresponding to the event description information, and add a text description of the event description information and the pointing information of the event photo file to the web page.
In the embodiment of the invention, based on the event description information, the acquired file attribute parameters and the acquired multiple parameters in the two types of parameters of the image attribute parameters are subjected to aggregation classification based on multiple dimensions on the photo file, so that the photo set obtained after classification comprises photos with higher correlation, and the efficiency of searching and positioning subsequent photos is improved. In addition, the embodiment of the invention gathers together the photos with higher event correlation, thereby facilitating the browsing and searching of the photo files by the user and improving the use experience of the user.
The embodiment of the present invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps in the method for classifying photo files in any one of the method embodiments described above.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present invention.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (14)
1. A method for classifying photo files, comprising:
before searching for a photo, acquiring event description information, wherein the event description information at least comprises one of the following: information describing the time at which the event occurs, describing the place at which the event occurs, and the content of the event;
analyzing the event description information to obtain a first type parameter, a second type parameter and corresponding parameter values, wherein the first type parameter is a file attribute parameter of a photo file, and the second type parameter is an image attribute parameter of the photo file;
according to the first type parameters and the second type parameters, event photo files matched with the event description information are screened out from photo files to be classified;
aggregating the event photo files to generate and display an event photo set corresponding to the event description information;
generating a first page of the event photo collection, and displaying representative photos and collection names of the event photo collection on the first page of the event photo collection;
generating a detail page of the event photo set, and displaying each photo file in the event photo set and characteristic information of the event photo set on the detail page of the event photo set, wherein the displaying the characteristic information of the event photo set in the event photo set on the detail page of the event photo set comprises: the location information is displayed in the detail page in the form of a map.
2. The method of classifying as set forth in claim 1, wherein said step of obtaining an event description information includes:
receiving event description information input by a user, and/or,
and retrieving the content published on the network to obtain the event description information.
3. The method according to claim 1, wherein the step of screening event photo files matching the event description information from photo files to be classified according to the first type parameter and the second type parameter comprises:
acquiring first type parameters and parameter values of photo files to be classified;
correspondingly matching the first type parameters of the photo files to be classified with the first type parameters of the event description information, screening photo files with the matched first type parameters, and obtaining intermediate photo files;
acquiring a second type parameter and a parameter value of the intermediate photo file;
and correspondingly matching the second type parameters of the intermediate photo files with the second type parameters of the event description information, screening intermediate photo files matched with the second type parameters, and obtaining event photo files matched with the event description information.
4. The method of classifying as set forth in claim 1, wherein said step of aggregating said event photo files further comprises:
And aggregating the event photo files in the event photo collection.
5. The classification method of claim 4, wherein after the step of aggregating the event photo files in the event photo collection, the method further comprises:
and receiving a sharing request for the event photo set, generating a sharing space of the event photo set according to the sharing request, and publishing the sharing space.
6. The method of classifying as set forth in claim 1, wherein said step of aggregating said event photo files includes:
and generating a webpage corresponding to the event description information, and adding text description of the event description information and pointing information of the event photo file into the webpage.
7. The method of classification according to any of claims 1 to 6, characterized in that,
the first type of parameters includes at least one of the following: file format, file size, shooting time, shooting place, and shooting device;
the second type of parameters includes at least one of the following: image content, image hue, image contrast, and image brightness.
8. A photograph file sorting apparatus, comprising:
The event obtaining module is used for obtaining event description information before searching the photo, wherein the event description information at least comprises one of the following steps: information describing the time at which the event occurs, describing the place at which the event occurs, and the content of the event;
the event analysis module is used for analyzing the event description information to obtain first type parameters, second type parameters and corresponding parameter values, wherein the first type parameters are file attribute parameters of the photo file, and the second type parameters are image attribute parameters of the photo file;
the photo matching module is used for screening event photo files matched with the event description information from photo files to be classified according to the first type parameters and the second type parameters;
the aggregation module is used for aggregating the event photo files and generating a first page of an event photo set, and displaying representative photos and collection names of the event photo set on the first page of the event photo set; generating a detail page of the event photo set, and displaying each photo file in the event photo set and characteristic information of the event photo set on the detail page of the event photo set, wherein the displaying the characteristic information of the event photo set in the event photo set on the detail page of the event photo set comprises: the location information is displayed in the detail page in the form of a map.
9. The classification device of claim 8, wherein the event acquisition module comprises:
the receiving module is used for receiving event description information input by a user; and/or
And the retrieval module is used for retrieving the content published on the network to obtain the event description information.
10. The classification device of claim 8, wherein the photograph matching module comprises:
the first acquisition module is used for acquiring first type parameters and parameter values of photo files to be classified;
the first matching module is used for correspondingly matching the first type parameters of the photo files to be classified with the first type parameters of the event description information, screening the photo files with the matched first type parameters, and obtaining intermediate photo files;
the second acquisition module is used for acquiring second type parameters and parameter values of the intermediate photo file;
and the second matching module is used for correspondingly matching the second type parameters of the intermediate photo files with the second type parameters of the event description information, screening intermediate photo files matched with the second type parameters, and obtaining event photo files matched with the event description information.
11. The classification device of claim 8, wherein the aggregation module comprises:
And the photo set aggregation module is used for aggregating the event photo files in the event photo set.
12. The classification apparatus of claim 11, further comprising:
and the sharing module is used for receiving a sharing request aiming at the event photo set, generating a sharing space of the event photo set according to the sharing request and publishing the sharing space.
13. The classification device of claim 8, wherein the aggregation module comprises:
and the webpage aggregation module is used for generating a webpage corresponding to the event description information, and adding text description of the event description information and the pointing information of the event photo file into the webpage.
14. The classifying device according to any one of claims 8 to 13, wherein,
the first type of parameters includes at least one of the following: file format, file size, shooting time, shooting place, and shooting device;
the second type of parameters includes at least one of the following: image content, image hue, image contrast, and image brightness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710220250.XA CN106980696B (en) | 2017-04-06 | 2017-04-06 | Photo file classification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710220250.XA CN106980696B (en) | 2017-04-06 | 2017-04-06 | Photo file classification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106980696A CN106980696A (en) | 2017-07-25 |
| CN106980696B true CN106980696B (en) | 2023-06-20 |
Family
ID=59345775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710220250.XA Active CN106980696B (en) | 2017-04-06 | 2017-04-06 | Photo file classification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106980696B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679109A (en) * | 2017-09-14 | 2018-02-09 | 维沃移动通信有限公司 | A kind of picture sharing method and mobile terminal |
| CN107679559B (en) * | 2017-09-15 | 2020-01-10 | Oppo广东移动通信有限公司 | Image processing method, image processing device, computer-readable storage medium and mobile terminal |
| CN107943939A (en) * | 2017-11-23 | 2018-04-20 | 北京三快在线科技有限公司 | View data recommends method, apparatus and electronic equipment |
| CN108573070A (en) * | 2018-05-08 | 2018-09-25 | 深圳市万普拉斯科技有限公司 | Picture recognition method for sorting, device and Photo folder method for building up |
| CN110889002A (en) * | 2019-11-26 | 2020-03-17 | 维沃移动通信有限公司 | Image display method and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005108192A (en) * | 2004-08-17 | 2005-04-21 | Kingo Togashi | Easy association electronic album creation support system |
| CN101004754A (en) * | 2006-01-19 | 2007-07-25 | 富士胶片株式会社 | Image editing system and image editing program |
| WO2009113770A2 (en) * | 2008-03-14 | 2009-09-17 | Hong Soon-Bum | Method for producing photo album for showing the life of a person, system thereof, and photo album produced by same |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8732161B2 (en) * | 2007-04-27 | 2014-05-20 | The Regents Of The University Of California | Event based organization and access of digital photos |
| CN101692706B (en) * | 2009-07-30 | 2011-08-17 | 杭州联图科技有限公司 | Intelligent storage equipment for security monitoring |
| US9280545B2 (en) * | 2011-11-09 | 2016-03-08 | Microsoft Technology Licensing, Llc | Generating and updating event-based playback experiences |
| CN104239336B (en) * | 2013-06-19 | 2018-03-16 | 华为技术有限公司 | A kind of method for screening images, device and terminal |
| CN104767782A (en) * | 2014-01-08 | 2015-07-08 | 腾讯科技（深圳）有限公司 | Method and device for correlating photograph event |
| IL239237B (en) * | 2014-06-05 | 2018-12-31 | Rotem Efrat | Web document enhancement |
| EP3198471A4 (en) * | 2014-09-24 | 2018-02-21 | Hewlett-Packard Development Company, L.P. | Media organization |
| KR20170011177A (en) * | 2015-07-21 | 2017-02-02 | 삼성전자주식회사 | Display apparatus and control method thereof |
| CN105718555A (en) * | 2016-01-19 | 2016-06-29 | 中国人民解放军国防科学技术大学 | Hierarchical semantic description based image retrieving method |
| CN105760461A (en) * | 2016-02-04 | 2016-07-13 | 上海卓易科技股份有限公司 | Automatic album establishing method and device |
-
2017
- 2017-04-06 CN CN201710220250.XA patent/CN106980696B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005108192A (en) * | 2004-08-17 | 2005-04-21 | Kingo Togashi | Easy association electronic album creation support system |
| CN101004754A (en) * | 2006-01-19 | 2007-07-25 | 富士胶片株式会社 | Image editing system and image editing program |
| WO2009113770A2 (en) * | 2008-03-14 | 2009-09-17 | Hong Soon-Bum | Method for producing photo album for showing the life of a person, system thereof, and photo album produced by same |
Non-Patent Citations (2)
| Title |
|---|
| Social album: Linking and merging online albums based on social relationship;Kai-Yin Cheng等;2012 Asia-Pacific Signal and Information Processing Association 2012 Annual Summit and Conference;1-8 * |
| 浅析图像类互联网应用产品的信息设计模式;许正兵;通讯世界;第19卷;264-265 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106980696A (en) | 2017-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106980696B (en) | Photo file classification method and device | |
| US20230370673A1 (en) | Providing visual content editing functions | |
| US9972113B2 (en) | Computer-readable recording medium having stored therein album producing program, album producing method, and album producing device for generating an album using captured images | |
| JP6196316B2 (en) | Adjusting content distribution based on user posts | |
| US8190639B2 (en) | Ordering content in social networking applications | |
| CN103412951A (en) | Individual-photo-based human network correlation analysis and management system and method | |
| CN111125528B (en) | Information recommendation method and device | |
| US9081801B2 (en) | Metadata supersets for matching images | |
| US10885619B2 (en) | Context-based imagery selection | |
| Yanai | World seer: a realtime geo-tweet photo mapping system | |
| KR20080040063A (en) | Classificating and searching system of map structed video contents and method thereof | |
| KR101680701B1 (en) | System and method for providing contents curation service based on context | |
| CN103425685A (en) | Method and device for having access to paper media | |
| KR101445691B1 (en) | System and method for providing contents curation service based on context | |
| CN111813746A (en) | Data sharing method and device and computer readable storage medium | |
| EP3948659B1 (en) | Automatic generation of people groups and image-based creations | |
| CN115062594A (en) | Method, device, equipment and medium for generating work log based on artificial intelligence | |
| KR20210131770A (en) | System for dual-searching image using region of interest set | |
| CN115713539A (en) | Image processing method, device, equipment and computer readable storage medium | |
| CN115706836A (en) | Recommendation method, device and equipment for video cover and computer readable storage medium | |
| Stein | Carrying Off the Palaces: John Ruskin's Lost Daguerreotypes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |