CN109635807A - Information input method, device, equipment and computer readable storage medium - Google Patents

Information input method, device, equipment and computer readable storage medium Download PDF

Info

Publication number
CN109635807A
CN109635807A CN201811207882.3A CN201811207882A CN109635807A CN 109635807 A CN109635807 A CN 109635807A CN 201811207882 A CN201811207882 A CN 201811207882A CN 109635807 A CN109635807 A CN 109635807A
Authority
CN
China
Prior art keywords
address
word
information
preset
database
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
CN201811207882.3A
Other languages
Chinese (zh)
Inventor
吴静平
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.)
OneConnect Smart Technology Co Ltd
Original Assignee
OneConnect Smart 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 OneConnect Smart Technology Co Ltd filed Critical OneConnect Smart Technology Co Ltd
Priority to CN201811207882.3A priority Critical patent/CN109635807A/en
Publication of CN109635807A publication Critical patent/CN109635807A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/14Image acquisition
    • G06V30/148Segmentation of character regions
    • G06V30/153Segmentation of character regions using recognition of characters or words
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/26Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Machine Translation (AREA)

Abstract

The present invention provides a kind of information input method based on big data, comprising: based on OCR optical character recognition technology from the ID Card Image data that image capture device acquires extract identity card in address text information;Word cutting processing is carried out to the address text information, address word set is constructed based on the address word that word cutting is handled;The address word set of acquisition is matched with the pre-stored address information in preset address database, determine in the preset address database with the matched destination address subordinate relation branch of the address word set;The corresponding subaddressing item information of each default subaddressing item is extracted from the destination address subordinate relation branch, and the subaddressing item information of acquisition is respectively stored in the corresponding storage location of each default subaddressing item.The present invention also provides a kind of data input device, equipment and computer readable storage mediums.Data input efficiency can be improved in the present invention, reduces data input mistake.

Description

Information input method, device, equipment and computer readable storage medium
Technical field
The present invention relates to technical field of data processing more particularly to a kind of information input method, device, equipment and computers Readable storage medium storing program for executing.
Background technique
Identity card has applied to different social sectors as the effective management tool of population information, The acquisition of information of identity card has a very important role.During various businesses account number or business handling application, one As need to input ID card information, the especially address information on user identity card.Currently, the personal information typing in identity card Manual entry is mostly used greatly, manual entry mode is not only time-consuming, inefficiency, and is easy wrong because reason typing is manually entered Information accidentally, causes unnecessary loss.
Summary of the invention
The main purpose of the present invention is to provide a kind of information input method, device, equipment and computer-readable storage mediums Matter, it is intended to realize and improve data input efficiency, reduce data input mistake.
To achieve the above object, the present invention provides a kind of information input method, and the information input method includes following step It is rapid:
Identity card is extracted from the ID Card Image data that image capture device acquires based on OCR optical character recognition technology In address text information;
Word cutting processing is carried out to the address text information, address word is constructed based on the address word that word cutting is handled Collection;
The address word set of acquisition is matched with the pre-stored address information in preset address database, is determined described default In address database with the matched destination address subordinate relation branch of the address word set;
The corresponding subaddressing item information of each default subaddressing item is extracted from the destination address subordinate relation branch, it will The subaddressing item information of acquisition is respectively stored in the corresponding storage location of each default subaddressing item.
Optionally, the address word set by acquisition is matched with the pre-stored address information in preset address database, The step of determining destination address subordinate relation branch matched with the address word set in the preset address database include:
It is grabbed in the preset address database using web crawlers and the address word match in the address word set Target word;
Address word all with the address word set in the preset address database is determined according to the target word of crawl The matched address subordinate relation branch of language, and using determining address subordinate relation branch as destination address subordinate relation branch Road.
Optionally, the address word set by acquisition is matched with the pre-stored address information in preset address database, The step of determining destination address subordinate relation branch matched with the address word set in the preset address database include:
Based in the address text information character arranging sequence respectively to the address word in the address word set into Row arrangement, obtains the corresponding ordering address word set of the address word set;
It puts in order and puts in order and be associated with subordinate relation according to address word in the ordering address word set Relationship determines the subordinate relation of address word in the ordering address word set;
Using web crawlers putting in order by address word, based on address word from the preset address database Subordinate relation grabs the target word of address word one by one, until last in target word crawl failure or ordering address word set The target word of a address word, which grabs, to be completed;
When the target word of the last one address word in ordering address word set, which grabs, to be completed, then by the mesh of all crawls The address subordinate relation branch of word composition is marked as destination address subordinate relation branch.
Optionally, described that word cutting processing, the address word handled based on word cutting are carried out to the address text information Construct address word set the step of include:
Identify that the address rank in the address text information identifies based on preset address class letter library;
The address rank mark of identification divides the address text information as the decollator of address text information It cuts, extracts the address word that segmentation obtains;
Address word based on all extractions constructs address word set.
Optionally, described that word cutting processing, the address word handled based on word cutting are carried out to the address text information Construct address word set the step of include:
The address text information is matched with preset address namebase, is extracted in the address text information and pre- If the consistent character string of address name in address name library;
Character string based on extraction constructs address word set.
Optionally, the address word set by acquisition is matched with the pre-stored address information in preset address database, Before the step of determining destination address subordinate relation branch matched with the address word set in the preset address database also Include:
Grabbed in the preset address database using web crawlers with the target word of the address word match, and Extract the destination address coding of the target word;
Determine whether the destination address coding is deposited according to the address name more new data in the preset address database In corresponding address name more new record;
If it exists, then construct ground according to all address names in the address name more new record of destination address coding Location word set.
Optionally, described that the subaddressing item information of acquisition is respectively stored in the corresponding storage position of each default subaddressing item Include: after the step of setting
Each subaddressing item information is respectively displayed in data input interface in the edit box of corresponding informance item, for Confirmation is checked at family.
In addition, to achieve the above object, the present invention also provides a kind of data input device, the data input device packet It includes:
First extraction module, the identity card figure for being acquired based on OCR optical character recognition technology from image capture device As extracting the address text information in identity card in data;
Word cutting module, for carrying out word cutting processing, the address word handled based on word cutting to the address text information Language constructs address word set;
Matching module, the address word set for that will obtain and the pre-stored address information progress in preset address database Match, determine in the preset address database with the matched destination address subordinate relation branch of the address word set;
Second extraction module, it is corresponding for extracting each default subaddressing item from the destination address subordinate relation branch Subaddressing item information, the subaddressing item information of acquisition is respectively stored in the corresponding storage location of each default subaddressing item.
In addition, to achieve the above object, the present invention also provides a kind of Message Entry Device, the Message Entry Device includes Processor, memory and it is stored in the data input program that can be executed on the memory and by the processor, wherein institute When stating data input program and being executed by the processor, realize such as the step of above-mentioned information input method.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium Data input program is stored on storage medium, wherein realizing when the data input program is executed by processor as above-mentioned The step of information input method.
The present invention provides a kind of information input method, device, equipment and computer readable storage medium, the information record Entering method includes: to extract body from the ID Card Image data that image capture device acquires based on OCR optical character recognition technology Address text information in part card;Word cutting processing, the address word handled based on word cutting are carried out to the address text information Language constructs address word set;The address word set of acquisition is matched with the pre-stored address information in preset address database, is determined In the preset address database with the matched destination address subordinate relation branch of the address word set;From the destination address from The corresponding subaddressing item information of each default subaddressing item is extracted in category relationship branch, and the subaddressing item information of acquisition is deposited respectively Storage is in the corresponding storage location of each default subaddressing item.By the above-mentioned means, can be quasi- using OCR optical character recognition technology Address text information really is extracted, it will be to the address word set and preset address database obtained after the processing of address text information word cutting The targeted slave address relationship branch that matching obtains address word set is carried out, guarantees that the word that word cutting obtains has actual geographical position Meaning and word cutting are set, the destination address subordinate relation branch comprising user's actual address information is obtained, from destination address subordinate Relationship branch extracts the information of the default subaddressing item needed and is stored respectively to corresponding storage location, realizes address information Typing.In the process, user is not necessarily to every address information of identity card being manually entered into corresponding address entries editor respectively Frame simplifies user's operation, while user being avoided to judge incorrectly or be manually operated the content that demand subaddressing item needs to input It makes mistakes and the information of typing mistake, improves the efficiency of inputting of address information.
Detailed description of the invention
Fig. 1 is the hardware structural diagram of Message Entry Device involved in the embodiment of the present invention;
Fig. 2 is the flow diagram of information input method first embodiment of the present invention;
Fig. 3 is the flow diagram of information input method second embodiment of the present invention;
Fig. 4 is the flow diagram of information input method 3rd embodiment of the present invention;
Fig. 5 is the flow diagram of information input method fourth embodiment of the present invention;
Fig. 6 is the flow diagram of the 5th embodiment of information input method of the present invention;
Fig. 7 is the flow diagram of information input method sixth embodiment of the present invention;
Fig. 8 is the flow diagram of the 7th embodiment of information input method of the present invention;
Fig. 9 is the functional block diagram of data input device of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present embodiments relate to information input method be mainly used in Message Entry Device, which can To be that personal computer (personal computer, PC), portable computer, mobile terminal etc. are having data processing function Equipment.
Referring to Fig.1, Fig. 1 is the hardware structural diagram of Message Entry Device involved in the embodiment of the present invention.This In inventive embodiments, Message Entry Device may include (such as the central processing unit Central Processing of processor 1001 Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory 1005.Wherein, communication bus 1002 For realizing the connection communication between these components;User interface 1003 may include display screen (Display), input unit ratio Such as keyboard (Keyboard);Network interface 1004 optionally may include that standard wireline interface and wireless interface (is protected as wireless True WIreless-FIdelity, WI-FI interface);Memory 1005 can be high-speed random access memory (random Access memory, RAM), it is also possible to stable memory (non-volatile memory), such as magnetic disk storage, Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.Those skilled in the art can manage It solving, it may include components more more or fewer than diagram that hardware configuration shown in Fig. 1, which does not constitute a limitation of the invention simultaneously, Perhaps certain components or different component layouts are combined.
With continued reference to Fig. 1, the memory 1005 in Fig. 1 as a kind of computer readable storage medium may include operation system System, network communication module and data input program.In Fig. 1, network communication module can be used for linking parsing system, with analysis System carries out data communication;And processor 1001 can call the data input program stored in memory 1005, and execute sheet The information input method that inventive embodiments provide.
The embodiment of the invention provides a kind of information input methods.
It is the flow diagram of information input method first embodiment of the present invention referring to Fig. 2, Fig. 2.
In the present embodiment, the information input method the following steps are included:
Step S10 is mentioned from the ID Card Image data that image capture device acquires based on OCR optical character recognition technology Take the address text information in identity card;
The present embodiment can be applied to data entry techniques field.Identity card is as the effective management work of population information Tool, has applied to different social sectors, the acquisition of information of identity card has a very important role.In various industry During account number of being engaged in or business handling application, the ground on input ID card information, especially user identity card is generally required Location information.Currently, the personal information typing in identity card mostly uses greatly manual entry, manual entry mode is not only time-consuming, efficiency Lowly, it and is easy to cause unnecessary loss because the information of reason typing mistake is manually entered.The present embodiment provides one kind The address text on the identity card of user is identified based on OCR optical character recognition technology, the address text based on identification is come really Determine the address information of user and by the method for address information input system.In the present embodiment, OCR, that is, optical character identification skill Art, the image data extraction based on text go out the technology of the text in image.Image capture device may include optical instrument, shadow As scanner or facsimile machine etc..It can be in the default position near the identity card address information option in the input interface of user information The acquisition button of an address image data is installed, user can trigger starting camera by the button to shoot identity card Identity card can be put into suitable position, utilize the image capture device of terminal by the instruction of address information fields image, user The data for carrying out the identity card complete image of the address lteral data or carrying address text on captured identity card, then by address Lteral data is sent to the executing subject data entry system of the present embodiment, and data entry system is receiving image capture device When the ID Card Image data of acquisition, after pre-processing based on OCR technique by binaryzation and noise remove etc., pass through character features It extracts, compares identification and manual synchronizing with comparison data library, obtain the text information of address field, i.e. address text information.
Step S20 carries out word cutting processing to the address text information, the address word building handled based on word cutting Address word set;
After obtaining address text information, one or more kinds of word cutting modes is taken to carry out word cutting processing to text, obtained The address word of address text information, and the address word in such a way that the element that the address word of acquisition is set constructs corresponding word cutting Collection.The mode of word cutting may include: mode 1 in the present embodiment), the name of each address administrative hierarchy is referred to as address rank Mark constructs address rank home banking, wherein address home banking includes at least province, city, area, street, road, lane, lane or lanes and alleys Equal address ranks mark.After obtaining address text information, by address text information and the progress of preset address class letter library Match, identifies in the text information of address and identify consistent character string with the address rank in preset address class letter library, to know Address rank mark in the text information of other address, address rank mark is literary to address as the decollator of address text information Word information is split, and extracts the address word that segmentation obtains.Specifically, if address text information is that " Shenzhen City, Guangdong Province is precious Pacify the street ... Qu Xinan " when, the address rank mark that can be identified includes " province ", " city " and " street " etc., then after dividing Obtained address word includes " Guangdong ", " Shenzhen ", " Bao'an " and " new peace " etc..Mode 2), the acquisition whole nation is not gone together in advance All address names of political affairs grade, for example, provincial address name " Guangdong " and city-level title " Guangzhou " etc., building includes institute There is the address name library of the address name of different administrative hierarchies.When obtaining address text information, by address text information and in advance If address name library is matched, in the text information of address with the consistent character of address name in preset address namebase String, using the character string of extraction as address word, the character string based on extraction constructs address word set.Based on preset address namebase Word cutting method include Forward Maximum Method method and reverse maximum matching method etc..In the present embodiment, obtain ground in word cutting processing After the word of location, for all address words that every kind of word cutting mode is obtained as address element, building includes all address words Address word set.
Step S30 matches the address word set of acquisition with the pre-stored address information in preset address database, determines In the preset address database with the matched destination address subordinate relation branch of the address word set;
In the present embodiment, preset address database refer to include different administrative hierarchies in national or bigger region ground Subordinate relation information between location name information and each address name can also include the more new record letter of address name Breath, preset address database can be the National Geophysical Data library to public.Address subordinate relation branch refers to being based on The address path that the subordinate relation of address determines can correspond to multiple and different address paths with an address name, for example, Guangdong Province can correspond to the different paths such as " Baoan District, Shenzhen City, Guangdong Province ... " or " Guangzhou, Guangdong Yuexiu District ... ", Guangzhou The different path such as " Guangzhou, Guangdong Yuexiu District ... " or " Guangzhou, Guangdong Baiyun District ... " can be corresponded to.Target from Belong to path to refer to and the matched address subordinate relation branch of address word set.By the address word set of acquisition and preset address database In pre-stored address information matches during, can use web crawlers grabbed in preset address database with address word set in Each address word match target word, the address subordinate relation branch based on each target word fixed one comprising all The address subordinate relation branch of the target word of address word, using the address subordinate relation branch as destination address subordinate relation Branch.Certainly, in the present embodiment, when obtaining address word set, by the address word in the set of words of address according to address text Putting in order for text is ranked up in information, obtains ordering address word set, such as " Changning district, Shanghai Jiangsu This address text information of road ... ", the address word of acquisition may be Shanghai, Changning and Jiangsu etc., then ordering address word Collection is (Shanghai, Changning, Jiangsu ...), and the address word set in the present embodiment is arranged according to sequence from left to right, and definitely The subordinate relation of location word is that " Jiangsu " belongs to " Changning ", and " Changning " belongs in " Shanghai ", after obtaining ordering address word set, will sort Address word set extracts subordinate relation of the address word based on address word and default ground according to putting in order for address word one by one Address date in the database of location is matched, and determines whether each address word can find corresponding target word.Specifically, When sequence from left to right extracts first address word, grabbed from preset address database using web crawlers and first The target word of address word match, there may be multiple target words and first address word in preset address database Matching, and these are with the corresponding address subordinate relation branch of first aim word and non-intersecting, for example, if address Word is that " Jiangsu " web crawlers can grab target from the titles such as " Jiangsu Province " and " Jiangsu Road " in preset address database Word " Jiangsu ".In the present embodiment, the address name in preset address database can be associated according to subordinate relation deposits The associated junior that the title of junior's home address is stored in upper level address title is belonged to storage location by storage, such as by " Guangzhou The home address title such as city " and " Shenzhen " is stored in the associated junior's ownership storage location of upper level address title " Guangdong Province ". In the present embodiment, after the first object word for having grabbed first address word, first address word and second are based on The subordinate relation of a address word, which is searched in the preset database with first object word, has identical incidence relation and with the The two matched words of target word.Specifically, if address word in ordering address word set according to address information text from a left side to Right sequence arrangement, then address word is subordinated to previous word, i.e. the second ground according to sequence the latter word from left to right Location word is subordinated to the first address word, then after the first object word for having grabbed the first address word, is based on the second address Word is subordinated to the subordinate relation of the first address word in the storage position of junior's home address of each first object word association Set the second target word of the second address word of crawl.If the storage position of subordinate's home address in specific first object word There is no the second target words with the second address word match in setting, then give up corresponding first object word, retain and exist First object word corresponding with the second target word of the second address word match, if the junior of all first object words Home address storage location be all not present with the second target word, then stop grabbing to the target word to subsequent address word It takes, gives up current address word set, carry out word cutting again based on other preset word cutting methods, obtain new address word set, base Carry out the crawl of target word in preset address database again in new address word set.The mesh of the second address word is grabbed After marking word, the target word of crawl third address word and the address word after it is continued until ground based on the above method The crawl of the target word of all address words or one of address word are not present in the preset database in the word set of location Corresponding target word.When all address words complete the crawl of target word in ordering address word set, will own The address subordinate relation branch that the target word of reservation is constituted is as destination address subordinate relation branch.
Step S40 extracts the corresponding subaddressing of each default subaddressing item from the destination address subordinate relation branch Item information, is respectively stored in the corresponding storage location of each default subaddressing item for the subaddressing item information of acquisition.
The preset address item of the present embodiment refers to the data items for needing typing being arranged according to data inputting demand, number It can be arranged according to address administrative hierarchy according to project, specifically, preset address item may include provincial address entries, city-level address The subaddressings project such as item and area's grade address entries.It in the present embodiment, can be in preset address database to all addresses Title adds corresponding administrative hierarchy mark or address name is carried out classification storage according to administrative hierarchy, for example, by Guangdong Province is stored in corresponding provincial administrative hierarchy storage location.When obtaining targeted slave relationship branch, it is based on targeted slave relationship The subaddress information of each default subaddressing item of the administrative hierarchy information extraction of each address name in branch, such as provincial Location name information, city-level address name information or area's grade address name information, and corresponding subaddressing project information is stored in The corresponding storage location of each default subaddressing item.
In the present embodiment, the ID Card Image number acquired based on OCR optical character recognition technology from image capture device According to the address text information in middle extraction identity card;Word cutting processing is carried out to the address text information, is handled based on word cutting The address word building address word set arrived;Pre-stored address information in the address word set of acquisition and preset address database is carried out Matching, determine in the preset address database with the matched destination address subordinate relation branch of the address word set;From described The corresponding subaddressing item information of each default subaddressing item is extracted in destination address subordinate relation branch, by the subaddressing item of acquisition Information is respectively stored in the corresponding storage location of each default subaddressing item.By the above-mentioned means, utilizing OCR optical character identification Technology can accurately extract address text information, will be to obtained address word set after the processing of address text information word cutting and default Address database carries out the targeted slave address relationship branch that matching obtains address word set, guarantees that the word that word cutting obtains has in fact The geographical location meaning and word cutting on border obtain the destination address subordinate relation branch comprising user's actual address information, from mesh Mark address subordinate relation branch extracts the information of the default subaddressing item needed and is stored respectively to corresponding storage location, realizes The typing of address information.In the process, user is corresponding it is not necessary that every address information of identity card to be manually entered into respectively Address entries edit box, simplify user's operation, while avoid user to demand subaddressing item need input content misjudgment or Person, which is manually operated, to make mistakes and the information of typing mistake, improves the efficiency of inputting of address information.
It is the flow diagram of information input method second embodiment of the present invention referring to Fig. 3, Fig. 3.
Based on the above embodiment, in the present embodiment, step S30 includes:
Step S50 is grabbed in the preset address database and the address in the address word set using web crawlers The target word of word match;
Based on the above embodiment, in the present embodiment, web crawlers refers to webpage spider or network robot, is a kind of According to certain rules, the program or script of web message are automatically grabbed.Preset address database refers to including complete Subordinate relation information in state or bigger region between the address name information and each address name of different administrative hierarchies, It can also include the more new record information of address name, preset address database can be the National Geophysical Data to public Library.During the pre-stored address information matches in the address word set of acquisition and preset address database, it can use network and climb Worm grabs the target word with each address word match in the word set of address in preset address database,
Step S60 is determined all with the address word set in the preset address database according to the target word of crawl The matched address subordinate relation branch of address word, and using determining address subordinate relation branch as destination address subordinate Relationship branch.
Address subordinate relation branch refers to the address path that the subordinate relation based on address determines, can with an address name With the multiple and different address path of correspondence, for example, Guangdong Province can correspond to " Baoan District, Shenzhen City, Guangdong Province ... " or " Guangdong Province The difference path such as Guangzhou Yuexiu District ... ", Guangzhou can correspond to " Guangzhou, Guangdong Yuexiu District ... " or " Guangdong Province is wide The different paths such as state city Baiyun District ... ".Targeted slave path refers to and the matched address subordinate relation branch of address word set Road.In the present embodiment, after having grabbed corresponding target word to address word all in the word set of address, it is based on each target The address subordinate relation branch of the fixed target word comprising all address words of the address subordinate relation branch of word, by this Address subordinate relation branch is as destination address subordinate relation branch.If there are an address words on default ground in the word set of address The target word of Corresponding matching can not be grabbed in the database of location, or there is no the ground of the target word comprising all address words Location subordinate relation branch then gives up corresponding address word set, rebuilds new address word set, and based on new address word set into The crawl of row target word.In the present embodiment, after obtaining destination address subordinate relation branch, side based on the above embodiment Method extracts information and the storage of default subaddressing item from destination address subordinate relation branch, realizes the typing of address information.
In the present embodiment, grabbed in the preset address database using web crawlers with the address word set in The target word of address word match;According to the target word of crawl determine in the preset address database with the address word The matched address subordinate relation branch of the address word for collecting all, and as target using determining address subordinate relation branch Location subordinate relation branch.By the above-mentioned means, realizing the target word for grabbing address word by web crawlers, it is based on target Word determines targeted slave relationship branch.
Further, Fig. 4 is the flow diagram of information input method 3rd embodiment of the present invention.
Based on the above embodiment, in the present embodiment, step S30 includes:
Step S70, based on the character arranging sequence in the address text information respectively to the ground in the address word set Location word is arranged, and the corresponding ordering address word set of the address word set is obtained;
In the present embodiment, when obtaining address word set, the address word in the set of words of address is believed according to address text Putting in order for text is ranked up in breath, ordering address word set is obtained, for example, for " Changning district, Shanghai Jiangsu Road ... " This address text information, the address word of acquisition may be Shanghai, Changning and Jiangsu etc., then ordering address word set be (on Sea, Changning, Jiangsu ...), the address word set in the present embodiment is arranged according to sequence from left to right, and determines address word Subordinate relation is that " Jiangsu " belongs to " Changning ", and " Changning " belongs in " Shanghai ", obtains ordering address word set and determines in the word set of address Address word subordinate relation after, by ordering address word set according to address word put in order one by one extract address word base It is matched in the subordinate relation of address word with the address date in preset address database, whether determines each address word Corresponding target word can be found.Specifically, when sequence from left to right extracts first address word, using web crawlers from Grabbed in preset address database with the target word of first address word match, in preset address database there may be Multiple target words and first address word match, and these and the corresponding address subordinate of first aim word Relationship branch is simultaneously non-intersecting, for example, if address word is that " Jiangsu " web crawlers can be from " Jiangsu in preset address database Target word " Jiangsu " is grabbed in the titles such as province " and " Jiangsu Road ".In the present embodiment, the address name in preset address database Title can be associated storage according to subordinate relation, and the title of junior's home address is stored in the associated of upper level address title Junior belongs to storage location, such as the home address title such as " Guangzhou " and " Shenzhen " is stored in upper level address title " extensively The associated junior of Dong Sheng " belongs to storage location.In the present embodiment, in the first object word for having grabbed first address word Afterwards, the subordinate relation based on first address word and second address word is searched and first object word in the preset database Language have identical incidence relation and with the second matched word of target word.Specifically, if address in ordering address word set Word is arranged according to the sequence of address information text from left to right, then address word is according to sequence the latter word from left to right It is subordinated to previous word, i.e. the second address word is subordinated to the first address word, then is grabbing the of the first address word After one target word, the subordinate relation for being subordinated to the first address word based on the second address word is closed in each first object word The storage location of junior's home address of connection grabs the second target word of the second address word.If in specific first object word There is no the second target word with the second address word match in the storage location of subordinate's home address of language, then give up correspondence First object word, retain exist first object word corresponding with the second target word of the second address word match, if Junior's home address storage location of all first object words be all not present with the second target word, then stop to subsequent Current address word set is given up in the crawl of the target word of address word, is cut again based on other preset word cutting methods Word obtains new address word set, carries out the crawl of target word in preset address database again based on new address word set. After the target word for having grabbed the second address word, continue to grab third address word and the ground after it based on the above method The target word of location word is up to the crawl of the target word of all address words or one of address word in the word set of address Corresponding target word is not present in language in the preset database.All address words complete mesh in ordering address word set When marking the crawl of word, using the address subordinate relation branch of institute's target word with a grain of salt composition as destination address subordinate relation Branch.
Step S80, according in the ordering address word set address word put in order and put in order and subordinate close The incidence relation of system determines the subordinate relation of address word in the ordering address word set;
In the present embodiment, the arrangement mode of address word includes but is not limited to following two in ordering address word set: being pressed Corresponding address word is arranged according to the sequence after arriving first according to the sequence of address text information from left to right, sequence ground The subsequent address word that comes in the word set of location belongs to the address word for coming front;From right to left according to address text information Sequence corresponding address word is arranged according to the sequence after arriving first, the ground for coming front in ordering address word set Location word, which belongs to, comes subsequent address word.In the present embodiment, default position can be stored in based on incidence relation information It sets, sequence during data input based on above-mentioned incidence relation and address word determines in the ordering address word set of address The subordinate relation of address word.Specifically, for " Changning district, Shanghai Jiangsu Road ... " this address text information, acquisition Address word may be Shanghai, Changning and Jiangsu etc., then ordering address word set is (Shanghai, Changning, Jiangsu ...), this implementation Address word set in example is arranged according to sequence from left to right, and determines that the subordinate relation of address word is that " Jiangsu " belongs to " length Rather ", " Changning " belongs to " Shanghai ".
Step S90, using web crawlers putting in order by address word, based on ground from the preset address database The subordinate relation of location word grabs the target word of address word one by one, until target word crawl failure or ordering address word set In the last one address word target word grab complete;
After the subordinate relation for determining address word, according to the target word of sequencing crawl address word.Extract the When one address word, grabbed from preset address database using web crawlers and the target word of first address word match Language, there may be multiple target words and first address word match in preset address database, and these are with The corresponding address subordinate relation branch of one target word is simultaneously non-intersecting, for example, if address word is that " Jiangsu " network is climbed Worm can grab target word " Jiangsu " from the titles such as " Jiangsu Province " and " Jiangsu Road " in preset address database.In this implementation In example, the address name in preset address database can be associated storage according to subordinate relation, by junior's home address Title is stored in the associated junior ownership storage location of upper level address title, such as " Guangzhou " and " Shenzhen " etc. are belonged to Address name is stored in the associated junior's ownership storage location of upper level address title " Guangdong Province ".In the present embodiment, it is grabbing After the first object word of first address word, subordinate relation based on first address word and second address word In the preset database search with first object word with identical incidence relation and with the second matched word of target word. Specifically, if the address word in ordering address word set is arranged according to the sequence of address information text from left to right, address word Language is subordinated to previous word according to sequence the latter word from left to right, i.e. the second address word is subordinated to the first address word Language is subordinated to the first address word based on the second address word then after the first object word for having grabbed the first address word Subordinate relation grab the of the second address word in the storage location of junior's home address of each first object word association Two target words.If being not present and the second address word in the storage location of subordinate's home address of specific first object word The matched second target word of language, then give up corresponding first object word, retains the existed with the second address word match The corresponding first object word of two target words, if junior's home address storage location of all first object words is not deposited With the second target word, then stop crawl to the target word to subsequent address word, give up current address word set, base Word cutting again is carried out in other preset word cutting methods, obtains new address word set, based on new address word set again default The crawl of target word is carried out in address database.After the target word for having grabbed the second address word, based on the above method after The target word of continuous crawl third address word and the address word after it is up to all address words in the word set of address Corresponding target word is not present in the crawl of target word or one of address word in the preset database
Step S100, when the target word of the last one address word in ordering address word set, which grabs, to be completed, then by institute The address subordinate relation branch being made of the target word of crawl is as destination address subordinate relation branch;
When all address words complete the crawl of target word in ordering address word set, by institute's mesh with a grain of salt The address subordinate relation branch of word composition is marked as destination address subordinate relation branch.In the present embodiment, target is being obtained After the subordinate relation branch of address, method based on the above embodiment extracts default subaddressing item from destination address subordinate relation branch Information and storage, realize the typing of address information.
In the present embodiment, based on the character arranging sequence in the address text information respectively in the address word set Address word arranged, obtain the corresponding ordering address word set of the address word set;According to the ordering address word set Putting in order and putting in order for middle address word determines the ordering address word intensively with the incidence relation of subordinate relation The subordinate relation of location word;Using web crawlers putting in order by address word, it is based on from the preset address database The subordinate relation of address word grabs the target word of address word one by one, until target word crawl failure or ordering address word It concentrates the target word of the last one address word to grab to complete;When the target of the last one address word in ordering address word set When word crawl is completed, then the address subordinate relation branch formed the target word of all crawls is closed as destination address subordinate It is branch.By the above-mentioned means, being ranked up to address word set, to ordering address word set using web crawlers in preset address number According to target word is grabbed in library, obtain and word subordinate relation matched destination address subordinate relation branch in address in word set.
Further, Fig. 5 is the flow diagram of information input method fourth embodiment of the present invention.
Based on the above embodiment, in the present embodiment, step S20 includes:
Step S110 identifies that the address rank in the address text information identifies based on preset address class letter library;
Based on the above embodiment, in the present embodiment, the name of each address administrative hierarchy is referred to as address rank mark, Construct address rank home banking, wherein address home banking includes at least the ground such as province, city, area, street, road, lane, lane or lanes and alleys Location class letter.After obtaining address text information, address text information is matched with preset address class letter library, is known Consistent character string is identified with the address rank in preset address class letter library in the text information of other address, to identify address Address rank mark in text information.
Step S120 believes the address text address rank mark of identification as the decollator of address text information Breath is split, and extracts the address word that segmentation obtains;
Address rank mark is split address text information as the decollator of address text information, extracts segmentation Obtained address word.It specifically, can be with if address text information is " Xinan, Baoan District, Shenzhen City, Guangdong Province street ... " The address rank mark of identification includes " provinces ", " city " and " street " etc., then the address word obtained after dividing including " Guangdong ", " Shenzhen ", " Bao'an " and " new peace " etc..
Step S130, the address word based on all extractions construct address word set.
After extracting the address word in the text information of address, using the address word of extraction as the element of set, building packet Containing the address word set for identifying cutting address text information based on address rank.
In the present embodiment, the address rank mark in the address text information is identified based on preset address class letter library Know;The address rank mark of identification is split the address text information as the decollator of address text information, mentions The address word for taking segmentation to obtain;Address word based on all extractions constructs address word set.It is based on by the above-mentioned means, realizing Address rank mark cuts address text information, and the address word obtained based on cutting constructs address word set, and simplification is cut Word operand improves word cutting efficiency.
Further, Fig. 6 is the flow diagram of the 5th embodiment of information input method of the present invention.
Based on the above embodiment, in the present embodiment, step S20 includes:
The address text information is matched with preset address namebase, extracts the address text by step S140 In information with the consistent character string of address name in preset address namebase;
Based on the above embodiment, in the present embodiment, all addresses name of national different administrative hierarchies can be acquired in advance Claim, for example, provincial address name " Guangdong " and city-level title " Guangzhou " etc., building includes the ground of all different administrative hierarchies The address name library of location title.When obtaining address text information, by address text information and the progress of preset address namebase Match, with the consistent character string of address name in preset address namebase in the text information of address, the character string of extraction is made For address word, the character string based on extraction constructs address word set.Word cutting method based on preset address namebase includes forward direction Maximum matching method and reverse maximum matching method etc..
Step S150, the character string based on extraction construct address word set.
After word cutting processing obtains address word, all address words that every kind of word cutting mode is obtained are as address member Element, building include the address word set of all address words.
Further, Fig. 7 is the flow diagram of information input method sixth embodiment of the present invention.
Based on the above embodiment, in the present embodiment, before step S40 further include:
Step S160 is grabbed in the preset address database and the mesh of the address word match using web crawlers Word is marked, and extracts the destination address coding of the target word;
Based on the above embodiment, in the present embodiment, the update note of address name is also store in preset address database Information is recorded, the title of address more new packets include all former name information of address name and currently with name name information, ground All name informations of location are associated with a changeless address code.In the present embodiment, address word is obtained in word cutting Afterwards, the target word of the address word match obtained with word cutting first can be whether there is in preset address database lookup, if depositing The fixing address coding of the target word is then being extracted, i.e. destination address encodes.
Step S170 determines that the destination address is compiled according to the address name more new data in the preset address database Code whether there is corresponding address name more new record;
After obtaining destination address coding, searched whether in storing all address name more storage locations of new record information There are destination address codings to determine whether that there are the destination addresses to encode corresponding address name more new record.If address There are destination address codings in the storage location of title more new record, then the address name that there is destination address coding updates Record.If there is no the destination addresses to encode in the storage location of address name more new record, there is no the destination addresses to compile The address name more new record of code.
Step S180, and if it exists, then according to all addresses in the address name more new record of destination address coding Title constructs address word set.
When destination address encode there are when corresponding address name more new record information, the target is extracted from storage location The corresponding address name of address code, the various combination mode that can be based respectively on each address name construct address word.Specifically Ground, if obtaining (A, B, C, D) after word cutting in an address word set, if the address code of A corresponds to two address names of A and A1, B, C and D zero-address more new record can then construct (A, B, C, D) and (A1, B, C, D) two address word sets.It is constructing At, again respectively to each address word set respectively with preset address database matching, determining destination address subordinate relation after multiple word sets Branch, and then extract the address information of default subaddressing item.
In the present embodiment, it is grabbed in the preset address database using web crawlers and the address word match Target word, and extract the target word destination address coding;According to the address name in the preset address database More new data is claimed to determine the destination address coding with the presence or absence of corresponding address name more new record;If it exists, then according to institute State all address names building address word set in the address name more new record of destination address coding.By the above-mentioned means, base The corresponding address name of the address word more new record information after determining cutting is encoded in destination address, is updated based on address name The case where record constructs more comprehensive address word set, avoids the change history due to address name that from can not being effectively matched.
Further, Fig. 8 is the flow diagram of the 7th embodiment of information input method of the present invention.
Based on the above embodiment, in the present embodiment, include: after step S40
Each subaddressing item information is respectively displayed on the edit box of corresponding informance item in data input interface by step S190 In, so that user checks confirmation.
It based on the above embodiment, in the present embodiment, can be in advance by each default subaddressing item at data input interface Information be associated with corresponding storage location, store by the information of each subaddressing item in corresponding storage location, Information in storage location is shown in corresponding edit box, for user check confirmation address information it is whether correct, with Address information is deposited carries out manual amendment in error conditions.
In the present embodiment, each subaddressing item information is respectively displayed on to the volume of corresponding informance item in data input interface It collects in frame, so that user checks confirmation.By the above-mentioned means, address entries information is shown corresponding after extracting address entries information Edit box, so that user checks confirmation.
In addition, the embodiment of the present invention also provides a kind of data input device.
It is the functional block diagram of data input device first embodiment of the present invention referring to Fig. 9, Fig. 9.
In the present embodiment, the data input device includes:
First extraction module 10, the identity card for being acquired based on OCR optical character recognition technology from image capture device The address text information in identity card is extracted in image data;
Word cutting module 20, for carrying out word cutting processing, the address handled based on word cutting to the address text information Word constructs address word set;
Matching module 30, the address word set for that will obtain and the pre-stored address information progress in preset address database Match, determine in the preset address database with the matched destination address subordinate relation branch of the address word set;
Second extraction module 40, it is right for extracting each default subaddressing item from the destination address subordinate relation branch The subaddressing item information of acquisition is respectively stored in the corresponding storage position of each default subaddressing item by the subaddressing item information answered It sets.
Wherein, each virtual functions module of above- mentioned information input device is stored in the storage of Message Entry Device shown in Fig. 1 It is functional for realizing the institute of data input program in device 1005;When each module is executed by processor 1001, information can be improved Efficiency of inputting avoids typing error message.
Further, the matching module is also used to:
It is grabbed in the preset address database using web crawlers and the address word match in the address word set Target word;
Address word all with the address word set in the preset address database is determined according to the target word of crawl The matched address subordinate relation branch of language, and using determining address subordinate relation branch as destination address subordinate relation branch Road.
Further, the matching module is also used to:
Based in the address text information character arranging sequence respectively to the address word in the address word set into Row arrangement, obtains the corresponding ordering address word set of the address word set;
It puts in order and puts in order and be associated with subordinate relation according to address word in the ordering address word set Relationship determines the subordinate relation of address word in the ordering address word set;
Using web crawlers putting in order by address word, based on address word from the preset address database Subordinate relation grabs the target word of address word one by one, until last in target word crawl failure or ordering address word set The target word of a address word, which grabs, to be completed;
When the target word of the last one address word in ordering address word set, which grabs, to be completed, then by the mesh of all crawls The address subordinate relation branch of word composition is marked as destination address subordinate relation branch.
Further, the word cutting module is also used to:
Identify that the address rank in the address text information identifies based on preset address class letter library;
The address rank mark of identification divides the address text information as the decollator of address text information It cuts, extracts the address word that segmentation obtains;
Address word based on all extractions constructs address word set.
Further, the word cutting module is also used to:
The address text information is matched with preset address namebase, is extracted in the address text information and pre- If the consistent character string of address name in address name library;
Character string based on extraction constructs address word set.
Further, the data input device further includes the second building module, and the second building module is used for:
Grabbed in the preset address database using web crawlers with the target word of the address word match, and Extract the destination address coding of the target word;
Determine whether the destination address coding is deposited according to the address name more new data in the preset address database In corresponding address name more new record;
If it exists, then construct ground according to all address names in the address name more new record of destination address coding Location word set.
Further, the data input device further includes display module, and the display module is used for:
Each subaddressing item information is respectively displayed in data input interface in the edit box of corresponding informance item, for Confirmation is checked at family.
In addition, the embodiment of the present invention also provides a kind of computer readable storage medium.
Data input program is stored on computer readable storage medium of the present invention, wherein the data input program is located When managing device execution, realize such as the step of above-mentioned information input method.
Wherein, data input program, which is performed realized method, can refer to each reality of information input method of the present invention Example is applied, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art The part contributed out can be embodied in the form of software products, which is stored in one as described above In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone, Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills Art field, is included within the scope of the present invention.

Claims (10)

1. a kind of information input method, which is characterized in that the information input method includes:
It is extracted in identity card based on OCR optical character recognition technology from the ID Card Image data that image capture device acquires Address text information;
Word cutting processing is carried out to the address text information, address word set is constructed based on the address word that word cutting is handled;
The address word set of acquisition is matched with the pre-stored address information in preset address database, determines the preset address In database with the matched destination address subordinate relation branch of the address word set;
The corresponding subaddressing item information of each default subaddressing item is extracted from the destination address subordinate relation branch, will be obtained Subaddressing item information be respectively stored in the corresponding storage location of each default subaddressing item.
2. information input method as described in claim 1, which is characterized in that the address word set and preset address by acquisition Pre-stored address information in database is matched, determine in the preset address database with the matched mesh of address word set Mark address subordinate relation branch the step of include:
The mesh with the address word match in the address word set is grabbed in the preset address database using web crawlers Mark word;
Determine that address word all with the address word set in the preset address database is equal according to the target word of crawl Matched address subordinate relation branch, and using determining address subordinate relation branch as destination address subordinate relation branch.
3. information input method as described in claim 1, which is characterized in that the address word set and preset address by acquisition Pre-stored address information in database is matched, determine in the preset address database with the matched mesh of address word set Mark address subordinate relation branch the step of include:
The address word in the address word set is arranged respectively based on the character arranging sequence in the address text information Column, obtain the corresponding ordering address word set of the address word set;
According to the incidence relation for putting in order and putting in order with subordinate relation of address word in the ordering address word set Determine the subordinate relation of address word in the ordering address word set;
Using web crawlers putting in order by address word, the subordinate based on address word from the preset address database Relationship grabs the target word of address word one by one, until the last one ground in target word crawl failure or ordering address word set The target word of location word, which grabs, to be completed;
When the target word of the last one address word in ordering address word set, which grabs, to be completed, then by the target word of all crawls The address subordinate relation branch of language composition is as destination address subordinate relation branch.
4. information input method as described in claim 1, which is characterized in that described to carry out word cutting to the address text information The step of processing, the address word handled based on word cutting constructs address word set includes:
Identify that the address rank in the address text information identifies based on preset address class letter library;
The address rank mark of identification is split the address text information as the decollator of address text information, mentions The address word for taking segmentation to obtain;
Address word based on all extractions constructs address word set.
5. information input method as described in claim 1, which is characterized in that described to carry out word cutting to the address text information The step of processing, the address word handled based on word cutting constructs address word set includes:
The address text information is matched with preset address namebase, is extracted in the address text information with default The consistent character string of address name in the namebase of location;
Character string based on extraction constructs address word set.
6. information input method as described in claim 1, which is characterized in that the address word set and preset address by acquisition Pre-stored address information in database is matched, determine in the preset address database with the matched mesh of address word set Before the step of marking address subordinate relation branch further include:
Grabbed in the preset address database using web crawlers with the target word of the address word match, and extract The destination address of the target word encodes;
According to the address name more new data in the preset address database determine destination address coding with the presence or absence of pair The address name answered more new record;
If it exists, then address word is constructed according to all address names in the address name more new record of destination address coding Collection.
7. information input method as described in claim 1, which is characterized in that described to deposit the subaddressing item information of acquisition respectively Storage each default subaddressing item corresponding storage location the step of after include:
Each subaddressing item information is respectively displayed in data input interface in the edit box of corresponding informance item, so that user looks into See confirmation.
8. a kind of data input device, which is characterized in that the data input device includes:
First extraction module, the ID Card Image number for being acquired based on OCR optical character recognition technology from image capture device According to the address text information in middle extraction identity card;
Word cutting module, for carrying out word cutting processing, the address word structure handled based on word cutting to the address text information Build address word set;
Matching module, for matching the address word set of acquisition with the pre-stored address information in preset address database, really In the fixed preset address database with the matched destination address subordinate relation branch of the address word set;
Second extraction module, for extracting the corresponding son of each default subaddressing item from the destination address subordinate relation branch The subaddressing item information of acquisition is respectively stored in the corresponding storage location of each default subaddressing item by address entries information.
9. a kind of Message Entry Device, which is characterized in that the Message Entry Device includes processor, memory and storage On the memory and the data input program that can be executed by the processor, wherein the data input program is by the place When managing device and executing, the step of realizing information input method as described in any one of claims 1 to 7.
10. a kind of computer readable storage medium, which is characterized in that be stored with information record on the computer readable storage medium Enter program, wherein realizing the letter as described in any one of claims 1 to 7 when the data input program is executed by processor The step of ceasing input method.
CN201811207882.3A 2018-10-16 2018-10-16 Information input method, device, equipment and computer readable storage medium Pending CN109635807A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811207882.3A CN109635807A (en) 2018-10-16 2018-10-16 Information input method, device, equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811207882.3A CN109635807A (en) 2018-10-16 2018-10-16 Information input method, device, equipment and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN109635807A true CN109635807A (en) 2019-04-16

Family

ID=66066508

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811207882.3A Pending CN109635807A (en) 2018-10-16 2018-10-16 Information input method, device, equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN109635807A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111896016A (en) * 2020-07-28 2020-11-06 拉扎斯网络科技(上海)有限公司 Position information processing method and device, storage medium and terminal
CN113515548A (en) * 2021-07-29 2021-10-19 快宝(上海)网络技术有限公司 Address information processing method and device, electronic equipment and storage medium

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1877598A (en) * 2005-06-06 2006-12-13 英华达(上海)电子有限公司 Method for gathering and recording business card information in mobile phone by using image recognition
US20110087839A1 (en) * 2009-10-09 2011-04-14 Verizon Patent And Licensing Inc. Apparatuses, methods and systems for a smart address parser
CN102169498A (en) * 2011-04-14 2011-08-31 中国测绘科学研究院 Address model constructing method and address matching method and system
CN102317955A (en) * 2009-04-20 2012-01-11 万涛国际有限公司 Data managing method and system based on image
CN104462059A (en) * 2014-12-01 2015-03-25 银联智惠信息服务(上海)有限公司 Commercial tenant address information recognition method and device
CN105069056A (en) * 2015-07-24 2015-11-18 湖北文理学院 Character string matching based method and system for analyzing address information of identification card
CN105528606A (en) * 2015-10-30 2016-04-27 小米科技有限责任公司 Region identification method and device
WO2016127677A1 (en) * 2015-02-13 2016-08-18 深圳市华傲数据技术有限公司 Address structuring method and device
CN107133215A (en) * 2017-05-20 2017-09-05 复旦大学 A kind of Chinese canonical address recognition methods of offline handwriting
CN107239453A (en) * 2016-03-28 2017-10-10 平安科技(深圳)有限公司 Information write-in method and device
CN107292227A (en) * 2017-05-03 2017-10-24 浙江百世技术有限公司 Part information extracting method and system are received/posted to one kind
CN108038090A (en) * 2017-12-26 2018-05-15 北京明朝万达科技股份有限公司 A kind for the treatment of method and apparatus of Text Address
CN108428187A (en) * 2017-12-21 2018-08-21 中国平安人寿保险股份有限公司 Address matching method, apparatus and storage medium

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1877598A (en) * 2005-06-06 2006-12-13 英华达(上海)电子有限公司 Method for gathering and recording business card information in mobile phone by using image recognition
CN102317955A (en) * 2009-04-20 2012-01-11 万涛国际有限公司 Data managing method and system based on image
US20110087839A1 (en) * 2009-10-09 2011-04-14 Verizon Patent And Licensing Inc. Apparatuses, methods and systems for a smart address parser
CN102169498A (en) * 2011-04-14 2011-08-31 中国测绘科学研究院 Address model constructing method and address matching method and system
CN104462059A (en) * 2014-12-01 2015-03-25 银联智惠信息服务(上海)有限公司 Commercial tenant address information recognition method and device
WO2016127677A1 (en) * 2015-02-13 2016-08-18 深圳市华傲数据技术有限公司 Address structuring method and device
CN105069056A (en) * 2015-07-24 2015-11-18 湖北文理学院 Character string matching based method and system for analyzing address information of identification card
CN105528606A (en) * 2015-10-30 2016-04-27 小米科技有限责任公司 Region identification method and device
CN107239453A (en) * 2016-03-28 2017-10-10 平安科技(深圳)有限公司 Information write-in method and device
CN107292227A (en) * 2017-05-03 2017-10-24 浙江百世技术有限公司 Part information extracting method and system are received/posted to one kind
CN107133215A (en) * 2017-05-20 2017-09-05 复旦大学 A kind of Chinese canonical address recognition methods of offline handwriting
CN108428187A (en) * 2017-12-21 2018-08-21 中国平安人寿保险股份有限公司 Address matching method, apparatus and storage medium
CN108038090A (en) * 2017-12-26 2018-05-15 北京明朝万达科技股份有限公司 A kind for the treatment of method and apparatus of Text Address

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
JYH-WIN HUANG ET AL.: "State-oriented based smart card internet access framework", 《IEEE REGION 10 INTERNATIONAL CONFERENCE TENCON》, pages 134 - 137 *
林晓帆 等,: "名片自动录入系统的实现", 《数据采集与处理》, vol. 13, no. 2, pages 67 - 71 *
顾安朋 等,: "营销客户地址数据标准化应用分析与研究", 《科技与创新》, vol. 2018, no. 16, pages 142 - 144 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111896016A (en) * 2020-07-28 2020-11-06 拉扎斯网络科技(上海)有限公司 Position information processing method and device, storage medium and terminal
CN113515548A (en) * 2021-07-29 2021-10-19 快宝(上海)网络技术有限公司 Address information processing method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
JP6574904B2 (en) Method, server, and storage medium for mining a target object social account
CN108197311B (en) House source data aggregation display method, device and equipment and readable storage medium
US20100121880A1 (en) Identifying and/or extracting data in connection with creating or updating a record in a database
CN101986292A (en) Method and system for processing forms based on an image
CN108804516A (en) Similar users search device, method and computer readable storage medium
CN107633081A (en) A kind of querying method and system of user profile of breaking one's promise
CN105187632B (en) Method and device for determining mobile phone number
CN103076879A (en) Multimedia interaction method and device based on face information, and terminal
CN106095738A (en) Recommendation tables single slice
CN110399448B (en) Chinese place name address searching and matching method, terminal and computer readable storage medium
CN109635807A (en) Information input method, device, equipment and computer readable storage medium
CN109299235A (en) Knowledge base searching method, apparatus and computer readable storage medium
CN108777806A (en) A kind of method for identifying ID, device and storage medium
US9665574B1 (en) Automatically scraping and adding contact information
CN105930313A (en) Method and device for processing notification message
CN104008151B (en) Method, system and the terminal device of retrieving contacts
CN106156275A (en) A kind of method and apparatus of singulated inquiry
CN107437174B (en) Virtual card management method and device
CN108921193A (en) Picture input method, server and computer storage medium
CN107908525A (en) Alert processing method, equipment and readable storage medium storing program for executing
CN106446270A (en) Classifying method and device
CN110580299B (en) Method, system, equipment and storage medium for generating matching diagram of recommended language of object
CN106227661A (en) Data processing method and device
CN105872232A (en) Number on-line inquiry method and number on-line inquiry apparatus
Dejean Extracting structured data from unstructured document with incomplete resources

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