CN103176999A - Reading auxiliary system based on OCR - Google Patents

Reading auxiliary system based on OCR Download PDF

Info

Publication number
CN103176999A
CN103176999A CN 201110432827 CN201110432827A CN103176999A CN 103176999 A CN103176999 A CN 103176999A CN 201110432827 CN201110432827 CN 201110432827 CN 201110432827 A CN201110432827 A CN 201110432827A CN 103176999 A CN103176999 A CN 103176999A
Authority
CN
China
Prior art keywords
terminal
content
user
search
identification
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
CN 201110432827
Other languages
Chinese (zh)
Inventor
顾健
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.)
Shanghai Bolu Information Technology Co Ltd
Original Assignee
Shanghai Bolu Information Technology 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 Shanghai Bolu Information Technology Co Ltd filed Critical Shanghai Bolu Information Technology Co Ltd
Priority to CN 201110432827 priority Critical patent/CN103176999A/en
Publication of CN103176999A publication Critical patent/CN103176999A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a reading auxiliary system based on an OCR. The reading auxiliary system based on the OCR comprises a terminal scanning module, an identifying module, a searching and content processing module and the like. According to the reading auxiliary system based on the OCR, after contents are identified at a terminal or the system, searching and processing of the contents are performed. Sequencing is performed according to content correlation, and a searched and processed result is sent back to the terminal. The terminal analyses and processes data transmitted by the system and displays the data on a terminal display interface of the user in an overlapping mode. Content auxiliary information needed by the user is obtained by scanning the terminal and identifying user reading contents and searching and processing based on the contents of the scanned part of the user, and therefore business experience based on terminal reading auxiliary is provided.

Description

A kind of reading auxiliary system based on OCR
Technical field
The present invention relates to mobile terminal, the technical fields such as word identification refer to a kind of reading auxiliary system based on OCR especially.
Background technology
Along with the development of the development of terminal technology, software engineering, particularly intelligent terminal, OCR technology and software engineering, for a kind of reading auxiliary system based on OCR provides feasibility.
when the user reads under various environment, may need further to understand to the content in reading process, traditional approach is that word corresponding to manual input obtains Search Results on computers, produced interference to reading flow process, the user need leave current reading process and the operation such as search for, and obtain and identify content on user's reading object by the terminal real time scan, and carry out initiating search with recognition result after the identification of content, customized content in search system and the various contents on the internet, and process and sort with search result relevance, and the Overlapping display as a result that will obtain is on the user terminal interface, the user can view for information about various of content that the user is concerned about immediately, reached the effect that assisted user is read.
In view of this, the object of the invention is to propose a kind of simple, by a kind of reading auxiliary system based on OCR of terminal scanning and identification.
Summary of the invention
As can be seen from above, a kind of reading auxiliary system based on OCR provided by the invention, scan the interested content part of user and identify the word content that it comprises by pictograph, carry out the correlativity search and Search Results is provided on terminal interface based on these contents, having realized that a kind of use is simply based on the terminal reading backup system.
Further, a kind of reading auxiliary system based on OCR that passes through to provide is for the development that a kind of user reads indirect activities provides powerful guarantee, satisfies the requirement of user each side, promotes user friendly experience.
For achieving the above object, one aspect of the present invention provides a kind of reading auxiliary system based on OCR, and the method comprises:
Object by terminal scanning user reading, obtain the content that the user reads, carry out carrying out after the identification of content search and the processing of content in terminal or system, sort according to content relevance, and the result that will search for and process returns to terminal, terminal the data of system's transmission are resolved and are processed and Overlapping display at user's terminal display interface.
In an embodiment of a kind of reading auxiliary system based on OCR provided by the invention, the method also comprises:
Terminal is by the interested content of camera scanning user, comprise newspaper, the interested part of user on the media such as advertisement, original contents in crawl camera scanning scope is obtained its original image and the processing such as is compressed, and with the image that obtains as data source, carry out the word identification in image, obtain the text that it comprises.
After obtaining the image of the interested content part of user of scanning, carry out text identification by the interior OCR identification service that perhaps provides based on remote service method of calling Request System end that the local OCR mode of terminal recognition image is corresponding, and the recognition result that returns of acquisition system.
In an embodiment of a kind of reading auxiliary system based on OCR provided by the invention, the method also comprises:
System passes through the method for service development diagram as the text identification service interface, end side is by providing the local original image content that scans and initiating the request of far-end pictograph identification service with this, and system end can be carried out corresponding identification service after obtaining corresponding identification request and original image.
Terminal is obtained the text that image comprises, and initiates search to search engine with this text as keyword, obtains the Search Results of search engine and further obtains the content that it comprises, and is presented on the terminal applies interface.
In an embodiment of a kind of reading auxiliary system based on OCR provided by the invention, the method also comprises:
Terminal gets the Search Results that search engine returns, and is presented at the window stacked system on user's read interface, and the user can find for information about various of corresponding content immediately.
Search engine has comprised the search engine of system inside and outside, various data in the search engine search system of internal system, include file, database, the search engine of system outside is open various search engines on the internet, corresponding content is obtained in the search that terminal is initiated keyword according to the grammer of corresponding engine, and according to the matching degree processing of sorting, obtains the various Search Results of maximum exact matching.
In an embodiment of a kind of reading auxiliary system based on OCR provided by the invention, the method also comprises:
Identification and searching request that terminal is constantly updated along with the variation of user's sweep limit, and according to upgrade and identification parameter constantly identification and text corresponding to search and the search information of upgrading on user terminal show, realized the related content with the mobile continuous renewal sweep test of scanning input.
 
Have the following advantages specifically:
Easy to use:
The user comprises the object of website information by camera scanning newspaper etc., can complete the identification of corresponding content and about the relevant information of this part content, use simple and fast.
Read in real time supplementary:
Terminal is used the interested content of camera scanning user, the related content of corresponding content part can instant Overlapping display on the user terminal interface, and along with user terminal mobile constantly updated corresponding displaying contents, realize the display effect of namely clapping namely to go out.
    
Description of drawings
Accompanying drawing described herein is used to provide a further understanding of the present invention, consists of the application's a part, and illustrative examples of the present invention and explanation thereof are used for explaining the present invention, do not consist of improper restriction of the present invention.In the accompanying drawings:
Fig. 1 is the schematic diagram of system module structure of the present invention.
Fig. 2 is pictograph identification process schematic diagram of the present invention.
Fig. 3 is operation flow schematic diagram of the present invention.
 
Embodiment
With reference to the accompanying drawings the present invention is described more fully, exemplary embodiment of the present invention wherein is described.
For achieving the above object, a kind of reading auxiliary system based on OCR has been proposed.
Below in conjunction with the drawings, embodiments of the present invention are described.
 
The key point that realizes a kind of reading auxiliary system based on OCR is as follows:
Pictograph identification:
After the terminal scanning original image, the OCR recognition capability module by terminal self or system identify with the open OCR identification service of service form, obtain the word content that comprises in image.
Content search:
After the text that obtains the content that the scanning input image comprises, terminal is initiated the search to each search engine, comprise the search of system for content database and each internet open search engine, obtain the Search Results of each search engine, and carry out the processing of result according to correlativity, obtain the highest search result set of correlativity.
Stack is upgraded:
After terminal is obtained Search Results, with Search Results with the application interface of overlapped way Overlapping display the user, the user can check result set immediately, check a plurality of Search Results by rolling at window, and along with the movement of scanning input scope, constantly update the content of user's supplementary, realize namely clapping the display effect that namely gets.
 
Main functional modules
As shown in Figure 1, a kind of structure of the reading auxiliary system based on OCR mainly comprises:
End side and system side: but the whole function of end side complete independently, and according to the ability of terminal, optional background system provides service, serves for the terminal that does not possess the OCR ability, comprises the functions such as OCR identification service and contents processing.
 
Module forms:
Terminal camera 100:
End side camera hardware part provides the function of content scanning, obtains original view data.
Log pattern 101:
Recording user is at activity datas such as the business operations of end side and be kept at terminal in the daily record mode.
Logic module 102:
Control and the execution of the service logic flow process of end side are called other logic function modules and are completed alternately the miscellaneous service logic function with it.
Scan module 103:
Be responsible for calling terminal camera and scan, and the raw image data after scanning offers other function logic modules, as identification module.
Identification module 104:
The OCR identification module of end side, according to terminal software and the hardware capabilities recognition function module in the optional installation of terminal, the raw image data of being responsible for the scanning of identification scan module also provides recognition result to arrive other functional modules.
Services request module 105:
End side is not supported OCR identification as this locality in the situation that need systemic-function to support, by the service of open system, the services request module is initiated the request to system service, completes various functions.
Contents processing and display module 106:
Terminal is resolved and is processed the identification content of obtaining, comprise processing and demonstration to the content results of the content of scanning recognition and search, to the scanning recognition result, content processing module is completed the complete functions such as statement that comprise of selecting and intercepting in sweep limit, to Search Results, content processing module is completed the format analysis processing to the relevance ranking of Search Results and content demonstration, and after being disposed, Overlapping display is on user's application interface.
Management configuration module 107:
The terminal user carries out business configuration and data management, and the user arranges the data of business and the configuration of business by administration module.
Interface module 108:
End side and system carry out mutual module, carry out transmission and the reception of various mutual and message by interface and system, initiate to ask and the various message of receiving system according to interface parameters.
Transmission channel 109:
The physical channel of the reality of data transmission is provided, and can be wireless broadband network and mobile data network, comprises the data channel of each mobile communication, WIFI, fixed broadband etc.
System interface module 110:
System side and terminal are carried out mutual module, communicate with terminal, provide various interface to carry out the access of system for terminal, carry out data transmission according to the agreement of consulting, and send the data to the request msg of terminal and receiving terminal.
Log pattern 111:
The information recording/of the various operations of system to system journal, and is offered the user and inquires about.
Database 112:
System end provides the various functions of data storage and various based on databases, as the data system of the logic functions such as data trigger, function.
Business logic modules 113:
Be responsible for execution and the functions such as logic setting, preservation of each service logic of correspondence of system end, call each functional module finishing service flow process and process miscellaneous service request logic.
Message module 114:
System and terminal are carried out the mutual of message, the request message of processing terminal, and the various message of tectonic system end and terminal interaction are constructed various message datas and are offered the transmission that interface carries out message according to mutual agreement and interface protocol mode.
Security module 115:
Be responsible for subscriber authentication and safely relevant various functions be set, comprising verification terminal user identity and attribute, the functions such as the various message datas of encryption and decryption.
OCR service module 116:
The functional module of OCR word that system end provides identification service, for the terminal that does not possess the OCR recognition capability provides the OCR recognition function, by the interface service opening to terminal.
System literal processing module 117:
System end is resolved and is processed the identification content of obtaining, and selects the statement fragment of identification fully that wherein comprises, and removes the character of the decoded in error that may comprise in recognition result.
Administration module 118:
The management function part of system is carried out integrated management to system, comprises user management, logic flow management, service parameter, the various management functions such as systematic parameter configuration.
System's door 119:
System user is logined the door of the system of door, and interface that the user uses system and the carrying of miscellaneous service flow process are provided.
Search engine 120:
Various contents in the search engine search system and internet, and Search Results is provided,
Comprise search engine and the external the Internet search engine of internal system, and provide search to connect
Mouthful, use by the various functions of open search access interface calling search engine and obtain the search knot
Really.
 
Fig. 2 is shown pictograph identification process schematic diagram of the present invention.
As shown in the figure, this flow process has comprised following steps:
1) user uses the interested content part of terminal scanning user;
2) terminal judges recognition method comprises the local identification of terminal or system identification;
After the scan text of 3) identification correspondence, the word of scanning area is processed and resolved, obtain the keyword and the statement fragment that comprise in corresponding sweep limit;
The below gives one example to illustrate that user of the present invention uses the flow process of business by the terminal reading backup system, and as shown in Figure 3, in this embodiment, business comprises the following steps:
Step 1: the terminal user uses the interested content of terminal camera scanning user;
Step 2: terminal is obtained original image, identifies in terminal or Request System OCR service;
Step 3: the character information that terminal is obtained after identification is processed and is filtered, and obtains the complete statement fragment or the keyword that wherein comprise;
Step 5. is initiated the searching request of search engine take the recognition result that obtains as keyword;
Step 6. terminal is obtained Search Results, Search Results is processed obtained the highest result set of correlativity;
Step 7. terminal is the result set Overlapping display that the obtains application interface the user, user's corresponding content of can leafing through immediately.
 
Description of the invention is in order to provide for the purpose of example and explanation, and is not exhaustively or limit the invention to disclosed form.Many modifications and variations are obvious for the ordinary skill in the art.Selecting and describing embodiment is for better explanation principle of the present invention and practical application, thereby and makes those of ordinary skill in the art can understand the various embodiment with various modifications that the present invention's design is suitable for special-purpose.

Claims (8)

1. reading auxiliary system based on OCR, it is characterized in that, object by terminal scanning user reading, obtain the content that the user reads, identify in terminal or Request System search and the processing of carrying out content after the identification of content is carried out in service, sort according to content relevance, and the result that will search for and process returns to terminal, terminal the data of system's transmission are resolved and are processed and Overlapping display at user's terminal display interface.
2. as claimed in claim 1, the object that terminal is read by the terminal scanning user, obtain the content that the user reads, it is characterized in that, terminal is by the interested content of camera scanning user, comprise newspaper, the interested part of user on the media such as advertisement, the original contents in crawl camera scanning scope are obtained its original image and the processing such as are compressed, and with the image that obtains as data source, carry out the word identification in image, obtain the text that it comprises.
3. as claimed in claim 1, terminal is by the interested content of camera scanning user and initiate the identification of word, it is characterized in that, after obtaining the image of the interested content part of user of scanning, carry out text identification by the interior OCR identification service that perhaps provides based on online service method of calling Request System end that the local OCR mode of terminal recognition image is corresponding, and the recognition result that returns of acquisition system.
4. as claimed in claim 1, the identification of content is carried out in terminal or Request System identification service, it is characterized in that, system opens image text identification service interface by method of service, end side is by providing the local original image content that scans and initiating the request of far-end pictograph identification service with this, and system end can be carried out corresponding identification service after obtaining corresponding identification request and original image.
5. as claimed in claim 1, carry out carrying out after the identification of content search and the processing of content in terminal or system, it is characterized in that, terminal is obtained the text that image comprises, and initiate search to search engine with this text as keyword, obtain the Search Results of search engine and further obtain the content that it comprises, being presented on the terminal applies interface.
6. as claimed in claim 5, terminal is obtained the Search Results of search engine and is presented at terminal, it is characterized in that, terminal gets the Search Results that search engine returns, be presented at the window stacked system on user's read interface, the user can find for information about various of corresponding content immediately.
7. as claimed in claim 5, terminal is obtained the Search Results of corresponding content by search engine, it is characterized in that, search engine has comprised the search engine of system inside and outside, various data in the search engine search system of internal system, include file, database, the search engine of system outside is open various search engines on the internet, corresponding content is obtained in the search that terminal is initiated keyword according to the grammer of corresponding engine, and according to the matching degree processing of sorting, obtain the various Search Results of maximum exact matching.
8. as claimed in claim 6, terminal is obtained the Search Results of search engine and is presented at terminal, it is characterized in that, identification and searching request that terminal is constantly updated along with the variation of user's sweep limit, and according to upgrade and identification parameter constantly identification and text corresponding to search and the search information of upgrading on user terminal show, realized the related content with the mobile continuous renewal sweep test of scanning input.
CN 201110432827 2011-12-21 2011-12-21 Reading auxiliary system based on OCR Pending CN103176999A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201110432827 CN103176999A (en) 2011-12-21 2011-12-21 Reading auxiliary system based on OCR

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201110432827 CN103176999A (en) 2011-12-21 2011-12-21 Reading auxiliary system based on OCR

Publications (1)

Publication Number Publication Date
CN103176999A true CN103176999A (en) 2013-06-26

Family

ID=48636880

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201110432827 Pending CN103176999A (en) 2011-12-21 2011-12-21 Reading auxiliary system based on OCR

Country Status (1)

Country Link
CN (1) CN103176999A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105518712A (en) * 2015-05-28 2016-04-20 北京旷视科技有限公司 Keyword notification method, equipment and computer program product based on character recognition
CN107256242A (en) * 2017-05-27 2017-10-17 北京小米移动软件有限公司 Search result display methods and device, terminal, server and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105518712A (en) * 2015-05-28 2016-04-20 北京旷视科技有限公司 Keyword notification method, equipment and computer program product based on character recognition
CN105518712B (en) * 2015-05-28 2021-05-11 北京旷视科技有限公司 Keyword notification method and device based on character recognition
CN107256242A (en) * 2017-05-27 2017-10-17 北京小米移动软件有限公司 Search result display methods and device, terminal, server and storage medium

Similar Documents

Publication Publication Date Title
US20140298293A1 (en) System for generating application software
CN103428525B (en) Internet video and the online query of TV programme and control method for playing back and system
CN101334792B (en) Personalized service recommendation system and method
CN112106049B (en) System and method for generating privacy data quarantine and report
CN104125290A (en) System and method for realizing collection, management and authorization of personal big data
US20130144721A1 (en) Individualization service providing system, server, terminal using user's feed back and privacy based on user and method thereof
JP5404728B2 (en) System and method for providing advertisement information by sound recognition
CN103176965A (en) Translation auxiliary system based on voice recognition
CN106407361A (en) Method and device for pushing information based on artificial intelligence
KR101610883B1 (en) Apparatus and method for providing information
CN1167021C (en) Method and device for authenticating user
US11562586B2 (en) Systems and methods for generating search results based on optical character recognition techniques and machine-encoded text
KR20150026107A (en) Apparatus for providing legal service and method thereof
KR101307578B1 (en) System for supplying a representative phone number information with a search function
CN103176964A (en) Translation auxiliary system based on OCR
CN103176998A (en) Read auxiliary system based on voice recognition
CN103176999A (en) Reading auxiliary system based on OCR
US20180040006A1 (en) Method for generating webpage on basis of consumer behavior patterns and method for utilizing webpage
KR20210079001A (en) Devices and methods for solving corporate problems based on the database
CN104168362A (en) Terminal, two-dimensional management apparatus, and electronic card management method
CN105939222B (en) A method of based on open network and station acquisition App information
CN102982327A (en) Enhanced information system of terminal scanning
CN102982040A (en) Method of fast searching of terminal scanning
KR20230120709A (en) Method and system for recommending user customized policy
CN109660588B (en) Picture uploading method and device, storage medium and terminal

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C05 Deemed withdrawal (patent law before 1993)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20130626