CN102930263A - Information processing method and device - Google Patents

Information processing method and device Download PDF

Info

Publication number
CN102930263A
CN102930263A CN2012103648197A CN201210364819A CN102930263A CN 102930263 A CN102930263 A CN 102930263A CN 2012103648197 A CN2012103648197 A CN 2012103648197A CN 201210364819 A CN201210364819 A CN 201210364819A CN 102930263 A CN102930263 A CN 102930263A
Authority
CN
China
Prior art keywords
picture
image
literal
candidate
information
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.)
Pending
Application number
CN2012103648197A
Other languages
Chinese (zh)
Inventor
金远
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu International Technology Shenzhen Co Ltd
Original Assignee
Baidu International Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Baidu International Technology Shenzhen Co Ltd filed Critical Baidu International Technology Shenzhen Co Ltd
Priority to CN2012103648197A priority Critical patent/CN102930263A/en
Publication of CN102930263A publication Critical patent/CN102930263A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Processing Or Creating Images (AREA)

Abstract

The invention discloses an information processing method, a picture searching method, an information processing device and a server. The information processing method comprises the following steps of: acquiring an image containing contents of the current display interface by screenshot; identifying the contents in the image; and processing the identified contents. By the method, the contents of the current interface can be processed without exiting of the current interface or much operation on the current interface, so that operation paths of processing the contents of the current display interface by users are reduced greatly; and the method is convenient and quick.

Description

A kind of information processing method and device
Technical field
The present invention relates to a kind of information processing method and device.
Background technology
At present, no matter be on wireless terminal or desktop computer or other electronic equipment, when if the user need to the operation such as search for or preserve, share to the content at current operation interface, often courses of action are many, What is more need to jump out current display interface and just can carry out next step operation, and the content of a lot of current display interface is can not editing mode, can't choose, copy, and brings a lot of inconvenience to the user.
Will search for some contents of current display interface such as the user, at present general search class product mainly is divided into four kinds: place the inner search interface of the Google of homepage/Baidu's search box, application software (App), entity search button that the part mobile phone is supported and based on voice control function software (Siri) or the Siri similar products of speech recognition, natural language processing, semantic network technology.Wherein, for use placed the Google of homepage/Baidu's search box, often courses of action were many in use for the user, and such as wanting to search for when seeing a caricature, the user must jump out many times that the App of usefulness searches for.And the entity search button of the search interface of App inside, the support of part mobile phone, all be that search (for example in the microblogging App search others message sent out) take App inside is as main, although reduced the dependence of user to the simplex search series products, do not reduced the courses of action that the user will carry out routine search.The Siri of natural language processing and semantic network technology and similar search entrance thereof, the search entrance of intelligence although provide simple, the user can't use phonetic entry in many instances.
Summary of the invention
The technical matters that the present invention mainly solves provides a kind of information processing method, image searching method and device, server, can reduce the courses of action that the current display interface content is processed.By the search to picture, can return the information that the user is associated with picture, for the user provides more resource and service.
For solving the problems of the technologies described above, the technical scheme that the present invention adopts is: a kind of information processing method is provided, comprises: obtain the image that comprises the current display interface content by sectional drawing; Identify the content in the described image; The described content that identifies is processed.
Wherein, the described step that identifies the content in the image comprises: utilize mode identification method to demarcate picture in the described image and the literal of picture format; The literal of described picture format is identified and obtained editable literal, or the picture in the described image identified and obtain the candidate picture relevant with picture in the described image.
Wherein, described picture in the image is identified and the step that obtains the candidate picture relevant with picture in the described image comprises: size and color depth to the picture in the described image compress, and obtain the eigenwert of the picture in the described image; Described eigenwert is sent to server, and receives described server and adopt described eigenwert to compare and the relevant candidate's picture of the picture with in the described image that obtains.
Wherein, describedly the content that identifies exported to the step that the third party uses comprise: the editable literal that described identification is obtained and/or the candidate picture relevant with picture export to that search application, translation application, collection are used, the record application and share application in any one or two or more application.
Wherein, describedly identification is obtained the step that the candidate picture relevant with picture search for and comprise: obtain at least one information in the realm information of the eigenwert of described candidate's picture, the data message that described candidate's picture is relevant, described candidate's picture; Described at least one the information of obtaining is sent to server; Receive described server and mate at least one the related information corresponding with described candidate's picture that obtains.
The step of the data message that wherein, the described candidate's of obtaining picture is relevant comprises: the title, web page address, content, author, the news relevant with described candidate's picture, at least one information in the network service of obtaining described candidate's picture.
Wherein, after the described step of utilizing the literal that mode identification method demarcates picture in the image and picture format, before the step that literal or the picture in the image of described picture format are identified, comprise: picture frame on by the literal of the picture in described image or described picture format, smear, delineate, click and the self-defined at least a mode of choosing in the mode are chosen picture in the described image and the literal of picture format in order to identifying.
Wherein, described identification and obtaining after the step of editable literal also comprises before the step that the described content that identifies is processed: by phonetic entry, input method input, gesture identification input, handwriting input, picture frame, any one or the two or more mode smearing, delineate, click described editable literal is revised.
Wherein, before the described step of obtaining the image that comprises the current display interface content by sectional drawing, also comprise: start, call any one mode active information processing application of using small tool, clicking application icon, pressing the application start button, to comprise the operation of described sectional drawing by the induction of induced inside equipment.
For solving the problems of the technologies described above, another technical solution used in the present invention is: a kind of signal conditioning package is provided, comprise sectional drawing module, identification module and application module, wherein: described sectional drawing module is used for obtaining the image that comprises the current display interface content by sectional drawing, and the described image that will obtain sends to described identification module; Described identification module is used for receiving described image and identifies the content of image, and the content in the described image that identifies is sent to described application module; Described application module is used for receiving the content of the image after identification module identification.
Wherein, described identification module specifically is used for utilizing mode identification method to demarcate the picture of described image and the literal of picture format, the literal of described picture format is identified and obtained editable literal, or the picture in the described image identified and obtain the candidate picture relevant with picture in the described image, and the editable literal that described identification is obtained and/or the candidate picture relevant with picture in the described image send to described application module; Described application module specifically is used for receiving described identification and the editable literal that obtains and/or the candidate picture relevant with picture, the line search of going forward side by side, translation, collection, any one or the two or more operation of recording, sharing.
Wherein, described application module comprises information acquisition unit, transmitting element and the information receiving unit of searching for for to described candidate's picture relevant with picture, wherein: described information acquisition unit is used for obtaining at least one information of the realm information of the eigenwert of the described candidate's picture that needs search, the data message that described candidate's picture is relevant, described candidate's picture, and described at least one the information output that will obtain given described transmitting element; Described at least one the information that described transmitting element is used for described information acquisition unit is obtained sends to server; Described information receiving unit is used for receiving at least one the related information corresponding with described candidate's picture that obtains after described at least one the information of described server by utilizing is mated.
Wherein, described identification module specifically is used for utilizing mode identification method to demarcate the picture of image and the literal of picture format, and by picture frame on the literal of the picture in described image or described picture format, smear, delineate, click and the self-defined at least a mode of choosing in the mode is chosen picture in the described image and the literal of picture format, the literal of described picture format is identified and obtained editable literal, or the picture in the described image identified and obtain the candidate picture relevant with picture in the described image, and the editable literal that described identification is obtained and/or the candidate picture relevant with picture in the described image send to described application module.
Wherein, described device also comprises correcting module, be used for by phonetic entry, input method input, gesture identification input, handwriting input, picture frame, any one or the two or more mode smearing, delineate, click described identification module being identified the editable literal that obtains and revise, and revised described editable literal is sent to described application module.
Wherein, described device also comprises active module, for respond to the small tool that starts, calls application, the icon of click application, any one mode active information processing application of pressing the start button of application by induced inside equipment, to comprise the operation of described sectional drawing.
The invention has the beneficial effects as follows: the situation that is different from prior art, the invention provides a kind of information processing manner, directly obtain the image of current display interface content by the sectional drawing mode, and the image that comprises the current display interface content identified, the content that identification is obtained sends to third party's application, do not need to withdraw from current interface or current interface is done too much operation can realize the current interface content is processed, thereby reduce greatly the courses of action that the user processes the current display interface content, convenient and swift.
Description of drawings
Fig. 1 is the process flow diagram of information processing method one embodiment of the present invention;
Fig. 2 is the process flow diagram of the content in the recognition image in information processing method one embodiment of the present invention;
Fig. 3 is the process flow diagram of in information processing method one embodiment of the present invention picture in the image being identified;
Fig. 4 is the process flow diagram of in information processing method one embodiment of the present invention the relevant candidate's picture of the picture with in the image that obtains through identification being searched for;
Fig. 5 is the structural representation of signal conditioning package one embodiment of the present invention;
Fig. 6 is the structural representation of the application module of signal conditioning package one embodiment of the present invention.
Embodiment
Consult Fig. 1, information processing method one embodiment of the present invention comprises:
Step S101: obtain the image that comprises the current display interface content by sectional drawing;
When the user need to be further processed the current display interface content, by the sectional drawing function, the current display interface content is carried out sectional drawing.Certainly, at first to activate for information processing that the current display interface content is processed and use, can start, call by the induction of induced inside equipment applications (App) small tool (Widget), activate corresponding information by any one mode of clicking the icon used, pressing the start button of application and process application.Such as the camera that can block by object or hand equipment, respond to extraneous light and log-on message processing application by the light sensing equipment of device interior; Again such as if the words of mobile phone can be by rocking mobile phone or double-clicking to start corresponding Widget and process with active information and use; Perhaps process by the icon active information of the application in click tools hurdle or the message hurdle and use; Or the triggering entrance that passes through operational applications is processed application such as log-on messages such as started by press buttons.
Step S102: identify the content in the image;
The image that comprises the current display interface content that obtains by sectional drawing is identified, comprised the literal of picture format is wherein identified and the picture in the image is identified.Wherein, see also Fig. 2, the content in the recognition image comprises following substep:
Substep S201: utilize mode identification method to demarcate picture in the image and the literal of picture format;
Utilize pattern-recognition (literal, image etc.) method that the literal of the picture in the image of required identification and picture format is all marked respectively, carry out sectional drawing such as one piece of article to current display interface, a lot of literal are arranged in this article, attached several pictures, the every pictures in the writings and image of picture format can have been marked separately (as living with red circle).Certainly, also can choose a part according to user's needs indicates.Such as drawing a virtual box, only indicate the interior part picture of virtual box or literal etc.After sign was finished, at this moment the user can choose the literal and/or the picture that mark accordingly and identify.When the user chooses the literal that marks accordingly and/or picture and identifies, various ways can be arranged.Be such as but not limited to by picture frame on the literal of the picture in image and/or picture format, smear, delineate, click and the self-defined at least a mode of choosing in the mode choose.Such as passing through a picture frame, perhaps with a virtual circle on the content (such as a string literal and/or picture) of required identification, can accurately choose the content that needs identification by the size of adjusting frame; Such as if touch screen interface can be chosen the content that needs identification by the mode of delineating or smearing with finger, also can accurately obtain the content that needs identification by the scope that adjustment is delineated or smeared again.Can certainly be to utilize picture frame, delineate and smear the mode that combines to choose.Such as drawing a very large frame, choose the content that needs identification by the mode of smearing, delineating, can also find out content that needs identification etc. such as the mode of phonetic entry, handwriting input by the self-defined mode of choosing.
Substep S202: respectively the literal of picture format and the picture in the image are identified;
Here can identify the literal of all picture formats of marking and the picture in the image, also can only identify the literal of a part of picture format of choosing and/or the picture in the image according to user selection.Wherein, the literal of picture format identified can obtain editable literal, embodiment of the present invention adopts optical character recognition method that the literal of picture format is identified.Certainly, can also adopt method for distinguishing to come the literal of picture format identified in actual application and obtain editable literal, the present invention is not construed as limiting this.Picture in the image identified to obtain the candidate picture relevant with picture.Such as the picture that belongs to same field with the picture in the image, if the picture perhaps in the image can obtain picture concerned of same star or artist etc. about certain star or artist.
Wherein, see also Fig. 3, the picture in the image is identified and obtained the candidate picture relevant with picture comprise following substep:
Substep S301: size and color depth to the picture in the image compress, and obtain the eigenwert of the picture in the image;
Can but be not limited to by obtain the eigenwert of picture in the image based on the histogram feature extraction algorithm of gradient, based on any mode in metric space theory characteristic extraction algorithm and the filtering feature extraction algorithm.Such as, can extract the feature obtain figure itself by eigenwert, have at the bottom of the eyes figure such as the figure left side 1 centimeters above 2 centimeters face etc. is arranged.In actual application, owing to being carries out the image that sectional drawing obtains to the current display interface displaying contents, therefore in the image picture around may be relevant for some associated description of picture etc., if relevant description is arranged, in this process, also can extract relevant description and send in the lump server so that find with image in the correlation candidate picture that more mates of picture.
Substep S302: eigenwert is sent to server, and reception server adopts eigenwert to compare and the relevant candidate's picture of the picture with in the image that obtains;
After eigenwert sent to server, server can adopt the eigenwert comparison in the picture database within it, finds with the relevant candidate's picture of the picture in the image.If be a buildings such as the picture in the image, can find with the similar candidate's picture of this buildings and return to user etc.Because the server picture database has a large amount of pictures, what may return to the user also is a large amount of relevant candidate's pictures, the user at this time can come candidate's picture is sorted according to confidence level or user's clicking rate of pictorial information, so that can find the reliable candidate's picture that needs faster.
Step S103: the content that identifies is exported to the third party use;
The editable literal and/or the candidate picture relevant with picture in the image that obtain through identification can be exported to third party's application.In actual application, the editable literal that also might occur identifying is imperfect or inaccurate, at this moment can revise by phonetic entry, input method input, gesture identification input, handwriting input, picture frame, any one mode of smearing, delineate, clicking, export to the third party and use to obtain more accurate literal.Be " width of cloth landscape painting " such as the editable literal that obtains through identification, can and then export to the third party and use by above-mentioned any input mode input " landscape painting " or " scenery with hills and waters ", also can be directly on editable literal " width of cloth landscape painting " picture frame, smear, delineate or click to select " landscape painting " or " scenery with hills and waters " and then export to third party's application.
Third party of the present invention uses any one or the two or more application in can being that search application, translation application, collection are used, record is used and sharing application.Candidate's picture that can obtain to the editable literal that obtains through identification, through picture recognition by these application at least a searched for, translates, collects, records and share etc.But can also be that the editable literal that obtains through identification of other applications exploitings except above-mentioned application and/or the candidate's picture that obtains through picture recognition operate in the actual application.The editable literal that will obtain such as identifying and/or candidate's picture are used for the identification code of other some application.Again such as can be with candidate's picture of obtaining through picture recognition as desktop wallpaper or will can be used as document storing through the literal that literal identification obtains and get up etc.
Wherein, see also Fig. 4, the relevant candidate's picture of the picture with in the image that obtains through identification is searched for comprised following substep:
Substep S401: at least one information obtaining the realm information of the eigenwert of candidate's picture, relevant data message and candidate's picture;
Server is when setting up picture database, from network or a large amount of pictures of other source crawl, and obtain as much as possible the information such as the title, web page address, content, author of these pictures, news that realm information is relevant with picture, network service, and preserve and set up index etc. with corresponding picture according to these information.Therefore return in candidate's picture of user and also may comprise these information, when needs are searched for candidate's picture, obtain the eigenwert of candidate's picture, and obtain as much as possible candidate's picture related data information and realm information etc., so that server returns the higher relevant information of the degree of association and/or service.Such as, can extract the feature obtain figure itself by eigenwert, such as the figure left side 1 centimeters eyes are arranged, at the bottom of the figure above 2 centimeters a face is arranged, be van gogh " night of a star-studded sky " etc. such as obtain this width of cloth picture by acquisition of information again.
Substep S402: at least one information will obtaining is sent to server;
After user side obtains the eigenwert and candidate's picture related data information and realm information of candidate's picture, these information are sent to server, server mates according to these information picture database within it, returns to user side thereby obtain the related information relevant with candidate's picture.
Substep S403: reception server mates at least one the related information corresponding with candidate's picture that obtains;
The user side reception server carries out information matches according to the information from user side that receives in database, and related information corresponding to candidate's picture with the needs search that finds.Search for such as the famous painting " night of a star-studded sky " to the van gogh, can return this width of cloth and draw auction price, story behind, van gogh's information is drawn a picture the time etc.; Search for such as the head portrait to certain star, can return the information that this star of user is correlated with, such as he the native place, when engage in this profession and his relevant works etc.Even the star that can also obtain in conjunction with the realm information of picture in the picture is film ﹠ TV circles, can return news search that the user is correlated with this star or microblogging speech etc.In another kind of situation, can also utilize current positional information and the related information corresponding service prompts corresponding with picture of at least one information output in the temporal information of realm information, user of picture.If such as user search be near the picture in a dining room the user present position, at this moment can obtain the current positional information of user and current time information in conjunction with relevant application, return the service prompts of user's Reserved seating etc.; Or user search is the picture of the on-site cinema of user, can return the movie advance notice of current this cinema of user and corresponding denomination situation etc.At this moment can operate accordingly the selection of these service prompts according to the user.Can select the pre-ordered movie ticket such as the user, at this moment will enter corresponding ticket booking interface; If the user does not select corresponding service, then remain on not execution action of current interface.
In addition, in actual application, in order to make Search Results more accurate, the user can be to the picture in the current interface and literal together sectional drawing, the literal of the picture format that will obtain sectional drawing identification and candidate's picture send to together the search application and search for, thereby return information and the service prompts that is associated.If such as the interface that currently is " bird of indignation ", include the picture of bird on the interface, include literal " bird of indignation " below the bird picture.If at this moment the user obtains the image of the picture that comprises bird and following literal by sectional drawing, so the picture of bird is identified candidate's picture that may obtain various birds, if the picture of only searching for as needs with candidate's picture of bird, return results may have the picture of bird and the introduction of various birds etc.And if with candidate's picture of bird in conjunction with the literal " bird of indignation " of picture format together as the picture that needs to search for, at this moment server can extract Word message from the literal of picture format, candidate's picture in conjunction with Word message and bird mates in server database together, can return and comprise " bird of indignation " information that game is relevant, such as game download address, game on line address etc., this and user's demand is pressed close to more.
It is worth mentioning that, the editable literal that will obtain if only will identify sends to search the respective service prompting also can utilize relevant information to provide when searching for to be associated with the literal of searching for is provided.The editable literal that obtains such as identification is the title in a hotel, can return the service prompts in this hotel reservation room., the user enters the interface in hotel reservation room if selecting reservation, if do not select reservation then remain on not execution action of current interface.
Description by above-mentioned embodiment, be appreciated that, information processing method provided by the invention, directly obtain the image of current display interface content by the sectional drawing mode, and obtain editable literal and/or the candidate picture relevant with picture in the image to comprising the current display interface content to identify, be further processed with the content to current display interface, thereby reduce greatly the courses of action that the user processes the current display interface content, convenient and swift.
In addition, can search for the relevant candidate's picture of the picture with in the image that obtains through identification, information is compared in relevant information by obtaining the candidate's picture that needs search and the database set up in advance with server, thereby obtain with the relevant information of picture and return to the user, can also provide more service prompts for the user in conjunction with user's actual conditions, the saving user searches the time of resource, can obtain again simultaneously reliable comprehensively information, a kind of more powerful way of search is provided.
See also Fig. 5, signal conditioning package one embodiment of the present invention comprises sectional drawing module 11, identification module 12 and application module 13, wherein:
Sectional drawing module 11 is used for obtaining the image that comprises the current display interface content by sectional drawing, and the image that obtains is sent to identification module 12;
When the user need to be further processed the current display interface content, by sectional drawing module 11, the current display interface content is carried out sectional drawing, obtain the image that comprises the current display interface content and send to identification module 12 and identify.
The content that identification module 12 is used for receiving image and identifies image sends to application module 13 with the content in the image that identifies;
Picture in 12 pairs of images of identification module is identified and is obtained the candidate picture relevant with this picture, the literal of picture format in the image is identified and is obtained editable literal.Wherein, adopt optical character recognition method that the literal of picture format is identified in the embodiment of the present invention.The editable literal that identification is obtained and/or the candidate picture relevant with picture in the image send to application module 13 and are further processed.
Application module 13 is used for receiving the content of the image after identification module 12 identifications;
Application module 13 can be used for receive identification and literal and/or candidate's picture that obtain, the line search of going forward side by side, translation, record, collect with share in any one or two or more operations.Certainly, in the actual application can also be other operations the operation of enumerating except the present invention is above-mentioned.
Wherein, see also Fig. 6, present embodiment application module 13 also comprises information acquisition unit 21, transmitting element 22 and the information receiving unit 23 of searching for for candidate's picture that identification is obtained, wherein:
Information acquisition unit 21 is used for obtaining at least one information of the realm information of the eigenwert of the candidate's picture that needs search, data message that candidate's picture is relevant, candidate's picture, and with the information output that obtains to transmitting element 22;
Information acquisition unit 21 can be obtained the eigenwert of the candidate's picture that needs search, the information such as the title of candidate's picture, web page address, content, author, news that realm information is relevant with picture, network service.
The information that transmitting element 22 is used for information acquisition unit 21 is obtained sends to server;
At least one the related information corresponding with candidate's picture that obtains after at least one the information that information receiving unit 23 is used for the realm information of the eigenwert of candidate's picture that the reception server utilization need to search for, data message that candidate's picture is relevant, candidate's picture is mated;
Information receiving unit 23 reception servers carry out information matches according to the information from user side that receives in database, and related information corresponding to candidate's picture with the needs search that finds.
Preferably, signal conditioning package one embodiment of the present invention also comprises correcting module:
The editable literal that correcting module is used for identification module 12 identifications are obtained revises;
In actual application, the editable literal that might occur identifying is imperfect or inaccurate, at this moment any one mode of can adopt phonetic entry, input method input, gesture identification input, handwriting input, picture frame by correcting module, smearing, delineate, click is revised, and revised editable literal is sent to application module 13.
Preferably, signal conditioning package one embodiment of the present invention also comprises:
Active module is used for activating the information processing that the content of current display interface is processed and uses;
When needs are processed the current display interface content, need to process by the active module active information and use, can but be not limited to by calling application small tool, click the icon used, any one mode of pressing the start button of application activates corresponding information and processes and use.
Description by above-mentioned embodiment, be different from prior art, the invention has the advantages that: a kind of information processing manner is provided, directly obtain the image of current display interface content by the sectional drawing mode, and the image that comprises the current display interface content identified to process, thereby reduce greatly the courses of action that the user processes the current display interface content, make the current display interface content processed to become more simple and responsible, convenient and swift.
In addition, be different from the situation of prior art, another advantage of the present invention is: a kind of method that the candidate's picture that obtains through picture recognition is searched for also is provided, by obtaining the eigenwert of the candidate's picture that obtains through picture recognition, relevant data and realm information etc., and the data in the database of setting up in advance with server are compared, thereby can being returned, Search Results follows the relevant information of candidate's picture of obtaining through picture recognition, can only return the situation of the picture of being correlated with picture with respect to existing picture searching, the method that the candidate's picture that obtains through picture recognition is searched for of the present invention can provide more detailed information and Service Source for the user.
In several embodiments provided by the present invention, should be understood that disclosed apparatus and method can realize by another way.For example, device embodiments described above only is schematic, for example, the division of described module, only be that a kind of logic function is divided, during actual the realization other dividing mode can be arranged, for example a plurality of modules or assembly can in conjunction with or can be integrated into another system, or some features can ignore, or do not carry out.Another point, the shown or coupling each other discussed or direct-coupling or communication connection can be by some interfaces, indirect coupling or the communication connection of device or unit can be electrically, machinery or other form.
Described functional module as the separating component explanation can or can not be physically to separate also, the parts that show as the unit can be or can not be physical locations also, namely can be positioned at a place, perhaps also can be distributed on a plurality of network element.Can select according to the actual needs wherein some or all of unit to realize the present invention program's purpose.
In addition, each functional module in each embodiment of the present invention can be integrated in the processing unit, also can be that the independent physics of each functional module exists, and also can two or more functional modules be integrated in the unit.Above-mentioned integrated unit both can adopt the form of hardware to realize, also can adopt the form of SFU software functional unit to realize.
The above only is embodiments of the present invention; be not so limit claim of the present invention; every equivalent structure or equivalent flow process conversion that utilizes instructions of the present invention and accompanying drawing content to do; or directly or indirectly be used in other relevant technical fields, all in like manner be included in the scope of patent protection of the present invention.

Claims (15)

1. an information processing method is characterized in that, comprising:
Obtain the image that comprises the current display interface content by sectional drawing;
Identify the content in the described image;
The described content that identifies is exported to the third party to be used.
2. method according to claim 1, it is characterized in that, before the described step of obtaining the image that comprises the current display interface content by sectional drawing, also comprise: start, call any one mode active information processing application of using small tool, clicking application icon, pressing the application start button, to comprise the operation of described sectional drawing by the induction of induced inside equipment.
3. method according to claim 1 is characterized in that, the described step that identifies the content in the image comprises:
Utilize mode identification method to demarcate picture in the described image and the literal of picture format;
The literal of described picture format is identified and obtained editable literal, or the picture in the described image identified and obtain the candidate picture relevant with picture in the described image.
4. method according to claim 3 is characterized in that, described picture in the image is identified and the step that obtains the candidate picture relevant with picture in the described image comprises:
Size and color depth to the picture in the described image compress, and obtain the eigenwert of the picture in the described image;
Described eigenwert is sent to server, and receives described server and adopt described eigenwert to compare and the relevant candidate's picture of the picture with in the described image that obtains.
5. method according to claim 3, it is characterized in that, describedly the content that identifies is exported to the step that the third party uses comprise: the editable literal that described identification is obtained, the candidate picture relevant with picture at least a exported to search application, translation application, collection any one or the two or more application in using, record application and sharing application.
6. method according to claim 5 is characterized in that, described will identification and obtain the candidate picture relevant with picture and export to after the step that search uses also comprises:
Obtain at least one information in the realm information of the relevant data message of the eigenwert of described candidate's picture, described candidate's picture, described candidate's picture;
Described at least one the information of obtaining is sent to server;
Receive described server and mate at least one the related information corresponding with described candidate's picture that obtains.
7. method according to claim 6, it is characterized in that, the step of the data message that the described candidate's of obtaining picture is relevant comprises: the title, web page address, content, author, the news relevant with described candidate's picture, at least one information in the network service of obtaining described candidate's picture.
8. method according to claim 3 is characterized in that,
After the described step of utilizing the literal that mode identification method demarcates picture in the image and picture format, before the step that literal or the picture in the image of described picture format are identified, comprise:
By picture frame on the literal of the picture in described image or described picture format, smear, delineate, click and the self-defined at least a mode of choosing in the mode are chosen picture in the described image and the literal of picture format in order to identifying.
9. method according to claim 3, it is characterized in that, described identification and obtaining after the step of editable literal also comprises before the step that the described content that identifies is processed: by phonetic entry, input method input, handwriting input, gesture identification, picture frame, any one or the two or more mode smearing, delineate, click described editable literal is revised.
10. a signal conditioning package is characterized in that, comprises sectional drawing module, identification module and application module, wherein:
Described sectional drawing module is used for obtaining the image that comprises the current display interface content by sectional drawing, and the described image that will obtain sends to described identification module;
Described identification module is used for receiving described image and identifies the content of image, and the content in the described image that identifies is sent to described application module;
Described application module is used for receiving the content of the image after identification module identification.
11. device according to claim 10 is characterized in that,
Described device also comprises active module, for respond to the small tool that starts, calls application, the icon of click application, any one mode active information processing application of pressing the start button of application by induced inside equipment, to comprise the operation of described sectional drawing.
12. device according to claim 10 is characterized in that,
Described identification module specifically is used for utilizing mode identification method to demarcate the picture of described image and the literal of picture format, the literal of described picture format is identified and obtained editable literal, or the picture in the described image identified and obtain the candidate picture relevant with picture in the described image, and the editable literal that described identification is obtained and/or the candidate picture relevant with picture in the described image send to described application module;
Described application module specifically is used for receiving described identification and the editable literal that obtains and/or the candidate picture relevant with picture, the line search of going forward side by side, translation, collection, record with share in any one or two or more operations.
13. device according to claim 12 is characterized in that, described application module comprises information acquisition unit, transmitting element and the information receiving unit of searching for for to described candidate's picture relevant with picture, wherein:
Described information acquisition unit is used for obtaining at least one information of the realm information of the eigenwert of the described candidate's picture that needs search, the data message that described candidate's picture is relevant, described candidate's picture, and described at least one the information output that will obtain given described transmitting element;
Described at least one the information that described transmitting element is used for described information acquisition unit is obtained sends to server;
Described information receiving unit is used for receiving at least one the related information corresponding with described candidate's picture that obtains after described at least one the information of described server by utilizing is mated.
14. device according to claim 12, it is characterized in that, described identification module specifically is used for utilizing mode identification method to demarcate the picture of image and the literal of picture format, and by picture frame on the literal of the picture in described image or described picture format, smear, delineate, click and the self-defined at least a mode of choosing in the mode is chosen picture in the described image and the literal of picture format, the literal of described picture format is identified and obtained editable literal, or the picture in the described image identified and obtain the candidate picture relevant with picture in the described image, and the editable literal that described identification is obtained and/or the candidate picture relevant with picture in the described image send to described application module.
15. device according to claim 12 is characterized in that,
Described device also comprises correcting module, be used for by phonetic entry, input method input, handwriting input, gesture identification, picture frame, any one or the two or more mode smearing, delineate, click the editable literal that described identification module identification obtains being revised, and revised described editable literal is sent to described application module.
CN2012103648197A 2012-09-27 2012-09-27 Information processing method and device Pending CN102930263A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2012103648197A CN102930263A (en) 2012-09-27 2012-09-27 Information processing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2012103648197A CN102930263A (en) 2012-09-27 2012-09-27 Information processing method and device

Publications (1)

Publication Number Publication Date
CN102930263A true CN102930263A (en) 2013-02-13

Family

ID=47645060

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2012103648197A Pending CN102930263A (en) 2012-09-27 2012-09-27 Information processing method and device

Country Status (1)

Country Link
CN (1) CN102930263A (en)

Cited By (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103678290A (en) * 2013-12-12 2014-03-26 苏州市峰之火数码科技有限公司 Electronic foreign language reader
CN104022943A (en) * 2014-06-26 2014-09-03 北京奇虎科技有限公司 Method, device and system for processing interactive type massages
CN104077582A (en) * 2013-03-25 2014-10-01 腾讯科技(深圳)有限公司 Internet accessing method, Internet accessing device and mobile terminal
CN104239313A (en) * 2013-06-09 2014-12-24 百度在线网络技术(北京)有限公司 Method for searching for characters displayed in screen and based on mobile terminal and mobile terminal
CN104375815A (en) * 2013-08-15 2015-02-25 联想(北京)有限公司 Information processing method and electronic equipment
CN104427395A (en) * 2013-08-23 2015-03-18 三星电子株式会社 Electronic device and method for using captured image in electronic device
CN104461474A (en) * 2013-09-12 2015-03-25 北京三星通信技术研究有限公司 Mobile terminal and screen-shooting method and device therefor
CN104536729A (en) * 2014-11-28 2015-04-22 北京奇虎科技有限公司 Method and device for achieving image capture on browser page
CN104618991A (en) * 2014-12-31 2015-05-13 上海连尚网络科技有限公司 Wifi (wireless fidelity) connecting method and wifi connecting system for mobile terminal
CN104834855A (en) * 2015-04-20 2015-08-12 北京奇虎科技有限公司 System data acquiring method and apparatus, and mobile terminal
CN105242827A (en) * 2015-09-28 2016-01-13 小米科技有限责任公司 Screen capture method, apparatus and system
CN105288993A (en) * 2015-10-13 2016-02-03 苏州大学 Intelligent picture guessing system
CN105373552A (en) * 2014-08-25 2016-03-02 中兴通讯股份有限公司 Display terminal based data processing method
CN105760153A (en) * 2016-01-27 2016-07-13 努比亚技术有限公司 Text extracting device and method
CN105786163A (en) * 2014-12-19 2016-07-20 联想(北京)有限公司 Display processing method and display processing device
CN105812563A (en) * 2016-03-10 2016-07-27 上海银天下科技有限公司 Picture sending method and device
CN105988790A (en) * 2015-02-09 2016-10-05 腾讯科技(深圳)有限公司 Information processing method, transmitting terminal and receiving terminal
WO2017035985A1 (en) * 2015-08-31 2017-03-09 小米科技有限责任公司 String storing method and device
CN106547792A (en) * 2015-09-22 2017-03-29 阿里巴巴集团控股有限公司 A kind of picture sharing method and device
CN107004122A (en) * 2014-11-18 2017-08-01 索尼公司 The instruction based on screenshot capture of side information
CN107291352A (en) * 2017-06-20 2017-10-24 广州阿里巴巴文学信息技术有限公司 Application program is redirected in a kind of word read method and its device
CN107707458A (en) * 2017-10-01 2018-02-16 李子盈 A kind of communication means and system and equipment for transmitting picture format text information
CN108182183A (en) * 2017-12-27 2018-06-19 北京百度网讯科技有限公司 Picture character interpretation method, application and computer equipment
CN108351880A (en) * 2016-10-19 2018-07-31 华为技术有限公司 Image processing method, device, electronic equipment and graphic user interface
CN108475335A (en) * 2016-01-27 2018-08-31 霍尼韦尔国际公司 The Method and kit for of the postmortem analysis of tripping field device in process industrial for using optical character identification & intelligent character recognitions
CN108595152A (en) * 2017-03-14 2018-09-28 长沙博为软件技术股份有限公司 A kind of choice box recognition methods based on graphic correlation
CN110119461A (en) * 2018-01-25 2019-08-13 优酷网络技术(北京)有限公司 A kind of processing method and processing device of query information
CN110309517A (en) * 2019-07-02 2019-10-08 北京百度网讯科技有限公司 Expression official documents and correspondence processing method, device, system and storage medium
CN110413357A (en) * 2013-06-08 2019-11-05 苹果公司 For synchronizing the equipment, method and graphic user interface of two or more displays
CN110941736A (en) * 2015-03-27 2020-03-31 华为技术有限公司 Electronic photo display method and device and mobile equipment
CN111310482A (en) * 2020-01-20 2020-06-19 北京无限光场科技有限公司 Real-time translation method, device, terminal and storage medium
WO2021109960A1 (en) * 2019-12-05 2021-06-10 维沃移动通信有限公司 Image processing method, electronic device, and storage medium
CN115393198A (en) * 2022-10-27 2022-11-25 国泰新点软件股份有限公司 Method and device for processing pictures in file and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090249189A1 (en) * 2008-03-28 2009-10-01 International Business Machines Coporation Enhancing Data in a Screenshot
CN102523289A (en) * 2011-12-18 2012-06-27 上海量明科技发展有限公司 Method and system for storing screenshot in network
CN102547462A (en) * 2010-12-28 2012-07-04 联想(北京)有限公司 Information transmission device, method, system, retrieval server and video play device
CN102625937A (en) * 2009-08-07 2012-08-01 谷歌公司 Architecture for responding to a visual query
CN102681986A (en) * 2012-05-23 2012-09-19 董名垂 Webpage instant translation system and webpage instant translation method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090249189A1 (en) * 2008-03-28 2009-10-01 International Business Machines Coporation Enhancing Data in a Screenshot
CN102625937A (en) * 2009-08-07 2012-08-01 谷歌公司 Architecture for responding to a visual query
CN102547462A (en) * 2010-12-28 2012-07-04 联想(北京)有限公司 Information transmission device, method, system, retrieval server and video play device
CN102523289A (en) * 2011-12-18 2012-06-27 上海量明科技发展有限公司 Method and system for storing screenshot in network
CN102681986A (en) * 2012-05-23 2012-09-19 董名垂 Webpage instant translation system and webpage instant translation method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
YEH T 等: ""Sikuli: using GUI screenshots for search and automation"", 《UIST09 PROCEEDINGS OF THE 22ND ANNUAL ACM SYMPOSIUM ON USER INTERFACE SOFTWARE AND TECHNOLOGY》 *

Cited By (45)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104077582A (en) * 2013-03-25 2014-10-01 腾讯科技(深圳)有限公司 Internet accessing method, Internet accessing device and mobile terminal
CN110413357A (en) * 2013-06-08 2019-11-05 苹果公司 For synchronizing the equipment, method and graphic user interface of two or more displays
US11692840B2 (en) 2013-06-08 2023-07-04 Apple Inc. Device, method, and graphical user interface for synchronizing two or more displays
CN104239313B (en) * 2013-06-09 2019-07-30 百度在线网络技术(北京)有限公司 The searching method and mobile terminal of text are shown in screen based on mobile terminal
CN104239313A (en) * 2013-06-09 2014-12-24 百度在线网络技术(北京)有限公司 Method for searching for characters displayed in screen and based on mobile terminal and mobile terminal
CN104375815A (en) * 2013-08-15 2015-02-25 联想(北京)有限公司 Information processing method and electronic equipment
CN104375815B (en) * 2013-08-15 2021-12-24 联想(北京)有限公司 Information processing method and electronic equipment
CN104427395A (en) * 2013-08-23 2015-03-18 三星电子株式会社 Electronic device and method for using captured image in electronic device
US11238127B2 (en) 2013-08-23 2022-02-01 Samsung Electronics Co., Ltd. Electronic device and method for using captured image in electronic device
CN104461474A (en) * 2013-09-12 2015-03-25 北京三星通信技术研究有限公司 Mobile terminal and screen-shooting method and device therefor
US10402483B2 (en) 2013-09-12 2019-09-03 Samsung Electronics Co., Ltd. Screenshot processing device and method for same
CN103678290A (en) * 2013-12-12 2014-03-26 苏州市峰之火数码科技有限公司 Electronic foreign language reader
CN104022943A (en) * 2014-06-26 2014-09-03 北京奇虎科技有限公司 Method, device and system for processing interactive type massages
CN105373552A (en) * 2014-08-25 2016-03-02 中兴通讯股份有限公司 Display terminal based data processing method
CN107004122A (en) * 2014-11-18 2017-08-01 索尼公司 The instruction based on screenshot capture of side information
CN104536729B (en) * 2014-11-28 2019-02-22 北京奇虎科技有限公司 It is a kind of to realize the method and apparatus that screenshot is carried out in browser page
CN104536729A (en) * 2014-11-28 2015-04-22 北京奇虎科技有限公司 Method and device for achieving image capture on browser page
CN105786163A (en) * 2014-12-19 2016-07-20 联想(北京)有限公司 Display processing method and display processing device
CN105786163B (en) * 2014-12-19 2019-04-26 联想(北京)有限公司 Display processing method and display processing unit
CN104618991A (en) * 2014-12-31 2015-05-13 上海连尚网络科技有限公司 Wifi (wireless fidelity) connecting method and wifi connecting system for mobile terminal
CN105988790A (en) * 2015-02-09 2016-10-05 腾讯科技(深圳)有限公司 Information processing method, transmitting terminal and receiving terminal
CN105988790B (en) * 2015-02-09 2020-07-14 腾讯科技(深圳)有限公司 Information processing method, sending terminal and receiving terminal
CN110941736A (en) * 2015-03-27 2020-03-31 华为技术有限公司 Electronic photo display method and device and mobile equipment
CN104834855A (en) * 2015-04-20 2015-08-12 北京奇虎科技有限公司 System data acquiring method and apparatus, and mobile terminal
WO2017035985A1 (en) * 2015-08-31 2017-03-09 小米科技有限责任公司 String storing method and device
CN106547792A (en) * 2015-09-22 2017-03-29 阿里巴巴集团控股有限公司 A kind of picture sharing method and device
CN106547792B (en) * 2015-09-22 2020-08-25 阿里巴巴集团控股有限公司 Picture sharing method and device
CN105242827A (en) * 2015-09-28 2016-01-13 小米科技有限责任公司 Screen capture method, apparatus and system
CN105288993A (en) * 2015-10-13 2016-02-03 苏州大学 Intelligent picture guessing system
CN105760153A (en) * 2016-01-27 2016-07-13 努比亚技术有限公司 Text extracting device and method
CN108475335B (en) * 2016-01-27 2022-10-14 霍尼韦尔国际公司 Method for post-inspection analysis of tripped field devices in process industry using optical character recognition, smart character recognition
CN108475335A (en) * 2016-01-27 2018-08-31 霍尼韦尔国际公司 The Method and kit for of the postmortem analysis of tripping field device in process industrial for using optical character identification & intelligent character recognitions
CN105812563A (en) * 2016-03-10 2016-07-27 上海银天下科技有限公司 Picture sending method and device
CN108351880A (en) * 2016-10-19 2018-07-31 华为技术有限公司 Image processing method, device, electronic equipment and graphic user interface
CN108595152A (en) * 2017-03-14 2018-09-28 长沙博为软件技术股份有限公司 A kind of choice box recognition methods based on graphic correlation
CN107291352A (en) * 2017-06-20 2017-10-24 广州阿里巴巴文学信息技术有限公司 Application program is redirected in a kind of word read method and its device
CN107707458A (en) * 2017-10-01 2018-02-16 李子盈 A kind of communication means and system and equipment for transmitting picture format text information
CN108182183A (en) * 2017-12-27 2018-06-19 北京百度网讯科技有限公司 Picture character interpretation method, application and computer equipment
CN108182183B (en) * 2017-12-27 2021-09-17 北京百度网讯科技有限公司 Picture character translation method, application and computer equipment
CN110119461A (en) * 2018-01-25 2019-08-13 优酷网络技术(北京)有限公司 A kind of processing method and processing device of query information
CN110309517A (en) * 2019-07-02 2019-10-08 北京百度网讯科技有限公司 Expression official documents and correspondence processing method, device, system and storage medium
CN110309517B (en) * 2019-07-02 2023-10-17 北京百度网讯科技有限公司 Expression document processing method, device, system and storage medium
WO2021109960A1 (en) * 2019-12-05 2021-06-10 维沃移动通信有限公司 Image processing method, electronic device, and storage medium
CN111310482A (en) * 2020-01-20 2020-06-19 北京无限光场科技有限公司 Real-time translation method, device, terminal and storage medium
CN115393198A (en) * 2022-10-27 2022-11-25 国泰新点软件股份有限公司 Method and device for processing pictures in file and storage medium

Similar Documents

Publication Publication Date Title
CN102930263A (en) Information processing method and device
CN105975560B (en) Question searching method and device of intelligent equipment
CN106527892B (en) Screen capturing method and system of electronic equipment
CN102902771A (en) Method, device and server for searching pictures
CN102298533B (en) Method for activating application program and terminal equipment
CN103050025B (en) A kind of learning method of mobile terminal and learning system thereof
US8724963B2 (en) Method and system for gesture based searching
CN109189879B (en) Electronic book display method and device
CN105740402A (en) Method and device for acquiring semantic labels of digital images
CN106384108A (en) Text content retrieval method, word interpreting device and mobile terminal
US20080104020A1 (en) Handwritten Query Builder
CN104537339A (en) Information identification method and information identification system
CN105009113A (en) Queryless search based on context
CN107368550B (en) Information acquisition method, device, medium, electronic device, server and system
CN105631051A (en) Character recognition based mobile augmented reality reading method and reading system thereof
CN112698761A (en) Image display method and device and electronic equipment
CN109697242B (en) Photographing question searching method and device, storage medium and computing equipment
CN103812758A (en) System and method for distributing information via audio
EP3564833B1 (en) Method and device for identifying main picture in web page
CN112417095A (en) Voice message processing method and device
CN112183149B (en) Graphic code processing method and device
US11010978B2 (en) Method and system for generating augmented reality interactive content
CN114168775A (en) Characteristic information acquisition method and device, storage medium and electronic equipment
CN111198926B (en) Business handling management method and device, electronic equipment and storage medium
CN112287131A (en) Information interaction method and information interaction device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20130213

RJ01 Rejection of invention patent application after publication