CN105630765A - Place name address identifying method - Google Patents
Place name address identifying method Download PDFInfo
- Publication number
- CN105630765A CN105630765A CN201510971470.7A CN201510971470A CN105630765A CN 105630765 A CN105630765 A CN 105630765A CN 201510971470 A CN201510971470 A CN 201510971470A CN 105630765 A CN105630765 A CN 105630765A
- Authority
- CN
- China
- Prior art keywords
- address
- place name
- substring
- word
- factor
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Character Discrimination (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a place name address identifying method, which comprises the following steps of setting a place name dictionary base and an address element base, wherein a plurality of place names are stored in the place name dictionary base, and a plurality of address elements are stored in the address element base; segmenting a non-login address to be identified according to the preset segmentation length, and obtaining matching substrings; matching the matching substrings obtained through segmentation with the place names in the place name dictionary base; comparing the successfully matched matching substrings with the address elements in the address element base; and determining the matching substrings with the consistent address elements in the comparison result as identified place name addresses. The place name address identifying method has the advantages that the concept of place name address elements is introduced; a non-login address name identifying mechanism based on the address elements is built through the examination on the integrity of the place name address elements and the processing of the address names which cannot be identified; and a word segmentation algorithm is further improved, so that the goal of precisely segmenting place name address strings is achieved.
Description
Technical field
The present invention relates to computer realm, particularly to a kind of place name Address Recognition method.
Background technology
In Chinese, word be minimum can the significant linguistic unit of independent activities. Chinese word segmentation is to be the process of rational word sequence according to specific specification by continuous print word sequence cutting in Chinese, and it is the basis of Chinese information processing. Conventional segmentation methods has mechanical Chinese word segmentation method and statistical morphology. According to matching direction, the former is divided into again Forward Maximum Method method, reverse maximum matching method and two-way maximum matching method. Algorithm above never ipsilateral (solves unregistered word, ambiguity analysis and participle efficiency) and optimizes Chinese Word Automatic Segmentation.
Place name address participle is Chinese word segmentation application in place name address. It is the process that place name address string splits into some geographic elements. Place name address participle is widely used in information retrieval, the Chinese many-side such as geocoding and address information identification. One place name address segmentation methods OK, key sees this algorithm identification ability to dictionary unregistered word. Owing to China's address name is many, dictionary cannot cover whole nation address name, and therefore the identification ability being not logged in address name is become the bottleneck of segmentation methods by algorithm, and solve annual reporting law becomes the matter of utmost importance of participle to the identification problem being not logged in address name.
Summary of the invention
The purpose of the embodiment of the present invention is to provide a kind of place name Address Recognition method, the problem low to solve existing Address Recognition method identification ability.
The embodiment of the present invention proposes a kind of place name Address Recognition method, including:
One dictionary of place name storehouse and an Address factor storehouse are set, described dictionary of place name storehouse stores multiple place name, the described multiple Address factor of Address factor library storage;
According to default cutting length, the to be identified address that is not logged in is carried out cutting, obtain coupling substring;
The described coupling substring that cutting obtains is mated with the place name in described dictionary of place name storehouse;
The coupling substring that the match is successful is compared with the Address factor in described Address factor storehouse;
The coupling substring that there is consistent Address factor in comparison result is defined as the place name address identified.
According to the place name Address Recognition method described in present pre-ferred embodiments,
Described place name Address Recognition method also includes: arranges a special symbol dictionary, stores multiple special symbol in described special symbol dictionary;
The to be identified address that is not logged in is carried out cutting by the cutting length that described basis is preset, include before obtaining the step of coupling substring: the to be identified address that is not logged in is mated with described special symbol dictionary, removes the to be identified special symbol being not logged in address.
According to the place name Address Recognition method described in present pre-ferred embodiments, the to be identified address that is not logged in is carried out cutting by the cutting length that described basis is preset, obtain in the step of coupling substring, adopt Forward Maximum Method method that the to be identified address that is not logged in is carried out participle.
According to the place name Address Recognition method described in present pre-ferred embodiments, described dictionary of place name storehouse includes dictionary text, glossarial index table and lead-in hash table.
According to the place name Address Recognition method described in present pre-ferred embodiments, described dictionary text includes conventional Chinese entry, numeral entry and place name address entry.
According to the place name Address Recognition method described in present pre-ferred embodiments, described described coupling substring cutting obtained includes after carrying out, with the place name in described dictionary of place name storehouse, the step mated:
Judge that coupling substring length is whether more than the character length of two words, if it is not, then the stop bit of coupling substring to be deducted the character length of a word, and return previous step and mate with the place name in described dictionary of place name storehouse.
According to the place name Address Recognition method described in present pre-ferred embodiments, described judge whether coupling substring length includes more than after the step of the character length of two words: if coupling substring length is more than the character length of two words, then will the coupling single word of substring cutting.
According to the place name Address Recognition method described in present pre-ferred embodiments, described the step that the coupling substring that the match is successful and the Address factor in described Address factor storehouse are compared is included:
Judge whether coupling substring terminates word for ending with Address factor;
If judging, coupling substring is to terminate word for ending with Address factor, then judge whether coupling substring terminates word equal to Address factor;
If coupling substring is not equal to Address factor and terminates word, then will instantly mate substring and confirm as place name address.
According to the place name Address Recognition method described in present pre-ferred embodiments, described judge the step whether coupling substring terminates word equal to Address factor after include:
If coupling substring is not equal to Address factor and terminates word, then judge that whether coupling substring instantly is first word of place name address string, if so, then will instantly mate substring and confirm as place name address.
According to the place name Address Recognition method described in present pre-ferred embodiments, the step mating the place name address that substring is defined as identifying that there is consistent Address factor in comparison result is included: incomplete Address factor word in the coupling substring in comparison result is merged.
Relative to prior art, the invention has the beneficial effects as follows: present invention introduces the concept of place name Address factor, by checking the integrity of place name Address factor and processing the address name that not can recognise that, set up and be not logged in address name recognition mechanism based on Address factor, improve segmentation methods further, reach the purpose of Precise Segmentation place name address string.
Accompanying drawing explanation
Fig. 1 is the flow chart of a kind of place name Address Recognition method of the embodiment of the present invention;
Fig. 2 is the flow chart of the another kind of place name Address Recognition method of the embodiment of the present invention.
Detailed description of the invention
For the present invention aforementioned and other technology contents, feature and effect, can clearly present in following cooperation describes in detail with reference to graphic preferred embodiment. By the explanation of detailed description of the invention, when can be reach technological means that predetermined purpose takes and effect is able to more deeply and concrete understanding to the present invention, however institute's accompanying drawings be only to provide with reference to and purposes of discussion, be not used for the present invention is any limitation as.
Referring to Fig. 1, it is the flow chart of a kind of place name Address Recognition method of the embodiment of the present invention, and it comprises the following steps:
S11, arranges a dictionary of place name storehouse and an Address factor storehouse, stores multiple place name, the described multiple Address factor of Address factor library storage in described dictionary of place name storehouse.
S12, carries out cutting according to default cutting length to the to be identified address that is not logged in, obtains coupling substring.
S13, mates the described coupling substring that cutting obtains with the place name in described dictionary of place name storehouse.
S14, compares the coupling substring that the match is successful with the Address factor in described Address factor storehouse.
S15, is defined as the place name address identified by the coupling substring that there is consistent Address factor in comparison result.
Dictionary is the basis of mechanical Chinese word segmentation method, and the quality of dictionary mechanisms directly influences speed and the efficiency of Chinese word segmentation. The present invention can adopt the dictionary for word segmentation structure based on whole word two points. This dictionary configuration can be divided into dictionary text, glossarial index table and lead-in hash table three grades. Dictionary text is the ordered list in units of word, and glossarial index table is directed in dictionary text the pointer gauge of each word, and lead-in hash table is the ordered list of the lead-in composition of each word. Positioned by the Hash of lead-in hash table and appointment word position range in dictionary text determined by glossarial index table, and then positioned by whole word two points in dictionary text.
Dictionary text can include conventional Chinese entry, numeral entry and place name address entry. Chinese word included in conventional Chinese entry, for identifying the everyday expressions in address. Chinese character, Roman number, Arabic numerals etc. included in numeral entry. Place name address entry comprises province (municipality directly under the Central Government), provincial capital (prefecture-level city), district (county, city) and peculiar place name road name.
It is also possible to individually set up special symbol dictionary, for resolving the symbol in place name address. Because the difference of address usage custom, it is possible that replace Chinese character with symbol or divide the phenomenon of geographic element title with symbol in the process of registration place name address. " # " in " inside the city street 342# ", and for example " " in " community, natural home, Ha Shuan North Road, Harbin City the 7th building 812 floor ". The present invention can according to country code central tissue organization address data, summary and induction special symbol, first resolve and remove special symbol, to reach the purpose of further Precise Segmentation place name address string before participle.
Address factor of the present invention refers in a certain restriction region, it is possible to specify the address of a certain concrete scope. One address is made up of one or more Address factors, and each Address factor is a relatively independent part in the string of address. Address factor has certain regularity, generally with key word endings such as province, city, district, county, town, communities. According to this rule, it can be determined that just whether point result is full address key element, and full address key element is not processed, adjacent incomplete Address factor is merged, thus reaching to identify the purpose being not logged in address name. With reference to the Ministry of Construction " People's Republic of China's industry standard (the CJJ/T106-2010 number of putting on record J455-2010): Comprehensive management of civil engineering information systems technology specification ", Address factor can be divided into 11 ranks, rank from high to low, as shown in table 1. According to 11 grades of Address factor features, the Address factor summed up, it is used for judging Address factor integrity.
Table 1
General place name address character string comprises Chinese character, English alphabet, numeral and special symbol, therefore special symbol can first be removed before participle, adopt FMM algorithm (Forward Maximum Method method) participle again, mark word attribute at participle simultaneously, whether this word of attribute record is full address key element, processes incomplete Address factor finally according to attribute.
Referring to Fig. 2, it is the another kind of place name Address Recognition method of the embodiment of the present invention, and it comprises the following steps:
S201 removes special symbol, becomes to comprise the character string of Chinese character, letter and number by the string manipulation of place name address; S202 determines initial cutting length and coupling substring content; S203 mates substring and mates with dictionary; S204 judges whether successfully: success, divides out by result, and initial cut-off increases the length of coupling substring, performs step S207; Unsuccessful, perform step S205; S205 judges that whether coupling substring length will be more than 2 (mating substring length during equal to 2 will be 1, it is not necessary to coupling is directly syncopated as single word): not, coupling substring stop bit subtracts 1, performs step S203; Otherwise, step S206 is performed; The single word of S206 cutting, initial cut-off increases by 1; S207 judges whether coupling substring terminates word for ending with Address factor: if it is not, word attribute assignment false, perform step S210; If so, step S208 is performed; S208 judges whether coupling substring terminates word equal to Address factor: if so, perform step S209; If it is not, word attribute is true instantly, perform step S210; S209 judges that whether word instantly is the 1st word of place name address string: if so, word attribute is true instantly; Otherwise, front 1 word attribute changes false into, and word attribute is true instantly, performs step S210; S210 judges that whether dicing position is beyond address string length, or not does not perform step S202, is, performs step S211; S211 checks word segmentation result attribute, merges incomplete Address factor word, and participle terminates.
Wherein step S207, S208, S209, S211 identify and are not logged in address name. First according to " be not with Address factor terminate word be ending word be full address key element scarcely " proposition, primarily determine that incomplete Address factor attribute. Such as " Sanlihe ", when this word do not included by dictionary, word segmentation result is " in three/river ", and " in three " terminate word for ending with Address factor, and it is not sufficient address key element, and attribute is false; Secondly, according to " the previous word terminating word equal to Address factor is not full address key element word " proposition, incomplete Address factor attribute is determined completely. Such as " Min Yuan road ", word segmentation result is " people/institute/road ", and " institute " and " road " terminates word for ending with full address key element, and be equal to Address factor and terminate word, according to this rule, " institute " cannot function as full address key element and terminate word, and attribute is also false. But when this situation occurs in the string beginning of place name address, directly instantly true will be defined as by word attribute, it is not necessary to other process. Such as " West Street, square ", " square " terminates word equal to Address factor, but it occurs in the beginning of place name address string, and attribute is true. Through above step, namely can determine that the attribute of each participle. Finally from left to right merging incomplete Address factor word, participle terminates. Such as: " Sanlihe Road, Beiwanzhuang, Beijing nine ", it is " in Beijing/million/village/tri-/river/road/No. nine " by dictionary matching word segmentation result. Increasing after being not logged in the recognition mechanism of address name, word segmentation result is " Beijing/million village/Sanlihe Road/No. nine ". Participle content is as shown in table 2 with attribute labeling.
Table 2
For solving the identification problem being not logged in address name, present invention introduces the concept of place name Address factor. By checking the integrity of place name Address factor and processing the address name that not can recognise that, set up and be not logged in address name recognition mechanism based on Address factor, improve Chinese Word Automatic Segmentation further, reach the purpose of Precise Segmentation place name address string. Owing to place name address is made up of a string noun, being absent from the rearmounted problem of head, therefore inventive algorithm is based on two points of dictionaries for word segmentation of whole word, adopts the FMM algorithm easily realized, increase the recognition mechanism being not logged in address name on this basis, it is achieved the cutting to place name address string.
The present invention, with country code central tissue organization data for experimental data, chooses whole nation place name address date 1110, is divided into 10,100,1000 3 partial tests. Test environment is: IntelCore (TM) 2DuoCPU, 4GB internal memory PC, Windowserver2003 operating system, VisualStudio2005 and SQLServer2000 data base.
Experiment achieves FMM algorithm and new algorithm respectively. Part place name address string word segmentation result is as shown in table 3. From word segmentation result, new algorithm is significantly improved in the precision of word segmentation of place name address. Being limited by dictionary, FMM algorithm generally can only identify 2 grades to 3 grades Address factors, and new algorithm may identify which 10 grades even 11 grades. It addition, experiment is from the precision of word segmentation and 2 aspect statistical analysiss of the participle elapsed time performance of 2 kinds of segmentation methods. Result is as shown in table 4. From precision of word segmentation angle, new algorithm accuracy is more than 85%, hence it is evident that higher than FMM algorithm.
Table 3
Table 4
The present invention is directed to place name address, it is proposed to based on the segmentation methods of Address factor recognition mechanism. Algorithm, based on two points of dictionaries for word segmentation of whole word, adopts the maximum segmenting method of forward, increases the recognition mechanism being not logged in address name. The present invention tests with country code central tissue organization data for experimental data, contrasts new algorithms and FMM algorithm performance from the precision of word segmentation and 2 aspects of elapsed time. Result shows that the method precision of word segmentation of invention improves nearly one times than FMM algorithm, especially advantage in being not logged in noun identification is prominent.
Through the above description of the embodiments, those skilled in the art is it can be understood that can realize by hardware to the embodiment of the present invention, it is also possible to the mode adding necessary general hardware platform by software realizes. Based on such understanding, the technical scheme of the embodiment of the present invention can embody with the form of software product, it (can be CD-ROM that this software product can be stored in a non-volatile memory medium, USB flash disk, portable hard drive etc.) in, including some instructions with so that a computer equipment (can be personal computer, server, or the network equipment etc.) performs the embodiment of the present invention, each implements the method described in scene.
The above, it it is only presently preferred embodiments of the present invention, not the present invention is done any pro forma restriction, although the present invention is disclosed above with preferred embodiment, but it is not limited to the present invention, any those skilled in the art, without departing within the scope of technical scheme, when the technology contents of available the disclosure above makes a little change or is modified to the Equivalent embodiments of equivalent variations, in every case it is without departing from technical scheme content, according to any simple modification that above example is made by the technical spirit of the present invention, equivalent variations and modification, all still fall within the scope of technical solution of the present invention.
Claims (10)
1. a place name Address Recognition method, it is characterised in that including:
One dictionary of place name storehouse and an Address factor storehouse are set, described dictionary of place name storehouse stores multiple place name, the described multiple Address factor of Address factor library storage;
According to default cutting length, the to be identified address that is not logged in is carried out cutting, obtain coupling substring;
The described coupling substring that cutting obtains is mated with the place name in described dictionary of place name storehouse;
The coupling substring that the match is successful is compared with the Address factor in described Address factor storehouse;
The coupling substring that there is consistent Address factor in comparison result is defined as the place name address identified.
2. place name Address Recognition method as claimed in claim 1, it is characterised in that
Described place name Address Recognition method also includes: arranges a special symbol dictionary, stores multiple special symbol in described special symbol dictionary;
The to be identified address that is not logged in is carried out cutting by the cutting length that described basis is preset, include before obtaining the step of coupling substring: the to be identified address that is not logged in is mated with described special symbol dictionary, removes the to be identified special symbol being not logged in address.
3. place name Address Recognition method as claimed in claim 1, it is characterized in that, the to be identified address that is not logged in is carried out cutting by the cutting length that described basis is preset, and obtains in the step of coupling substring, adopts Forward Maximum Method method that the to be identified address that is not logged in is carried out participle.
4. place name Address Recognition method as claimed in claim 1, it is characterised in that described dictionary of place name storehouse includes dictionary text, glossarial index table and lead-in hash table.
5. place name Address Recognition method as claimed in claim 4, it is characterised in that described dictionary text includes conventional Chinese entry, numeral entry and place name address entry.
6. place name Address Recognition method as claimed in claim 1, it is characterised in that described described coupling substring cutting obtained includes after carrying out, with the place name in described dictionary of place name storehouse, the step mated:
Judge that coupling substring length is whether more than the character length of two words, if it is not, then the stop bit of coupling substring to be deducted the character length of a word, and return previous step and mate with the place name in described dictionary of place name storehouse.
7. place name Address Recognition method as claimed in claim 6, it is characterized in that, described judge whether coupling substring length includes more than after the step of the character length of two words: if coupling substring length is more than the character length of two words, then will the coupling single word of substring cutting.
8. place name Address Recognition method as claimed in claim 1, it is characterised in that described the step that the coupling substring that the match is successful and the Address factor in described Address factor storehouse are compared is included:
Judge whether coupling substring terminates word for ending with Address factor;
If judging, coupling substring is to terminate word for ending with Address factor, then judge whether coupling substring terminates word equal to Address factor;
If coupling substring is not equal to Address factor and terminates word, then will instantly mate substring and confirm as place name address.
9. place name Address Recognition method as claimed in claim 8, it is characterised in that described judge the step whether coupling substring terminates word equal to Address factor after include:
If coupling substring is not equal to Address factor and terminates word, then judge that whether coupling substring instantly is first word of place name address string, if so, then will instantly mate substring and confirm as place name address.
10. place name Address Recognition method as claimed in claim 1, it is characterized in that, the step mating the place name address that substring is defined as identifying that there is consistent Address factor in comparison result is included: incomplete Address factor word in the coupling substring in comparison result is merged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510971470.7A CN105630765A (en) | 2015-12-21 | 2015-12-21 | Place name address identifying method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510971470.7A CN105630765A (en) | 2015-12-21 | 2015-12-21 | Place name address identifying method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105630765A true CN105630765A (en) | 2016-06-01 |
Family
ID=56045722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510971470.7A Pending CN105630765A (en) | 2015-12-21 | 2015-12-21 | Place name address identifying method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105630765A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106445918A (en) * | 2016-09-26 | 2017-02-22 | 深圳市数字城市工程研究中心 | Chinese address processing method and system |
| CN107305540A (en) * | 2016-04-20 | 2017-10-31 | 顺丰科技有限公司 | Address cutting recognition methods |
| CN107527312A (en) * | 2016-06-22 | 2017-12-29 | 顺丰科技有限公司 | Express mail address process system and method |
| CN107562834A (en) * | 2017-08-23 | 2018-01-09 | 四川长虹电器股份有限公司 | The method of geographic location criteriaization extraction |
| CN108628811A (en) * | 2018-04-10 | 2018-10-09 | 北京京东尚科信息技术有限公司 | The matching process and device of address text |
| CN108920457A (en) * | 2018-06-15 | 2018-11-30 | 腾讯大地通途（北京）科技有限公司 | Address Recognition method and apparatus and storage medium |
| CN109359200A (en) * | 2018-10-11 | 2019-02-19 | 北京国信达数据技术有限公司 | Place name address date intelligently parsing system |
| CN109947893A (en) * | 2017-12-11 | 2019-06-28 | 航天信息股份有限公司 | Address Recognition method and device |
| CN110275940A (en) * | 2019-06-11 | 2019-09-24 | 北京贝壳时代网络科技有限公司 | A kind of Chinese address recognition methods and equipment |
| CN110852620A (en) * | 2019-11-12 | 2020-02-28 | 上海德启信息科技有限公司 | Logistics order processing method and device, electronic equipment and storage medium |
| CN110851696A (en) * | 2018-08-01 | 2020-02-28 | 北京京东尚科信息技术有限公司 | Interest point extraction method and device |
| CN111079386A (en) * | 2019-11-11 | 2020-04-28 | 浙江省北大信息技术高等研究院 | Address recognition method, device, equipment and storage medium |
| CN111324679A (en) * | 2018-12-14 | 2020-06-23 | 阿里巴巴集团控股有限公司 | Method, device and system for processing address information |
| CN111401083A (en) * | 2019-01-02 | 2020-07-10 | 阿里巴巴集团控股有限公司 | Name identification method and device, storage medium and processor |
| CN113190596A (en) * | 2021-04-22 | 2021-07-30 | 华中科技大学 | Method and device for mixing and matching place name and address |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101499058A (en) * | 2009-03-05 | 2009-08-05 | 北京理工大学 | Chinese word segmenting method based on type theory |
| JP2012113606A (en) * | 2010-11-26 | 2012-06-14 | Nippon Telegr & Teleph Corp <Ntt> | Protection object information masking device, protection object information masking method, and protection object information masking program |
-
2015
- 2015-12-21 CN CN201510971470.7A patent/CN105630765A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101499058A (en) * | 2009-03-05 | 2009-08-05 | 北京理工大学 | Chinese word segmenting method based on type theory |
| JP2012113606A (en) * | 2010-11-26 | 2012-06-14 | Nippon Telegr & Teleph Corp <Ntt> | Protection object information masking device, protection object information masking method, and protection object information masking program |
Non-Patent Citations (1)
| Title |
|---|
| 赵阳阳等: "地址要素识别机制的地名地址分词算法", 《测绘科学》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107305540A (en) * | 2016-04-20 | 2017-10-31 | 顺丰科技有限公司 | Address cutting recognition methods |
| CN107527312A (en) * | 2016-06-22 | 2017-12-29 | 顺丰科技有限公司 | Express mail address process system and method |
| CN106445918A (en) * | 2016-09-26 | 2017-02-22 | 深圳市数字城市工程研究中心 | Chinese address processing method and system |
| CN106445918B (en) * | 2016-09-26 | 2019-08-27 | 深圳市数字城市工程研究中心 | A kind of Chinese address processing method and system |
| CN107562834A (en) * | 2017-08-23 | 2018-01-09 | 四川长虹电器股份有限公司 | The method of geographic location criteriaization extraction |
| CN109947893A (en) * | 2017-12-11 | 2019-06-28 | 航天信息股份有限公司 | Address Recognition method and device |
| CN108628811A (en) * | 2018-04-10 | 2018-10-09 | 北京京东尚科信息技术有限公司 | The matching process and device of address text |
| CN108920457A (en) * | 2018-06-15 | 2018-11-30 | 腾讯大地通途（北京）科技有限公司 | Address Recognition method and apparatus and storage medium |
| CN110851696A (en) * | 2018-08-01 | 2020-02-28 | 北京京东尚科信息技术有限公司 | Interest point extraction method and device |
| CN109359200A (en) * | 2018-10-11 | 2019-02-19 | 北京国信达数据技术有限公司 | Place name address date intelligently parsing system |
| CN111324679A (en) * | 2018-12-14 | 2020-06-23 | 阿里巴巴集团控股有限公司 | Method, device and system for processing address information |
| CN111324679B (en) * | 2018-12-14 | 2023-04-11 | 阿里巴巴集团控股有限公司 | Method, device and system for processing address information |
| CN111401083B (en) * | 2019-01-02 | 2023-05-02 | 阿里巴巴集团控股有限公司 | Name identification method and device, storage medium and processor |
| CN111401083A (en) * | 2019-01-02 | 2020-07-10 | 阿里巴巴集团控股有限公司 | Name identification method and device, storage medium and processor |
| CN110275940A (en) * | 2019-06-11 | 2019-09-24 | 北京贝壳时代网络科技有限公司 | A kind of Chinese address recognition methods and equipment |
| CN111079386A (en) * | 2019-11-11 | 2020-04-28 | 浙江省北大信息技术高等研究院 | Address recognition method, device, equipment and storage medium |
| CN111079386B (en) * | 2019-11-11 | 2023-08-25 | 杭州未名信科科技有限公司 | Address recognition method, device, equipment and storage medium |
| CN110852620A (en) * | 2019-11-12 | 2020-02-28 | 上海德启信息科技有限公司 | Logistics order processing method and device, electronic equipment and storage medium |
| CN110852620B (en) * | 2019-11-12 | 2024-03-05 | 上海德启信息科技有限公司 | Logistics order processing method and device, electronic equipment and storage medium |
| CN113190596A (en) * | 2021-04-22 | 2021-07-30 | 华中科技大学 | Method and device for mixing and matching place name and address |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105630765A (en) | Place name address identifying method | |
| CN107463666B (en) | sensitive word filtering method based on text content | |
| US8055498B2 (en) | Systems and methods for building an electronic dictionary of multi-word names and for performing fuzzy searches in the dictionary | |
| WO2016165538A1 (en) | Address data management method and device | |
| CN107918604B (en) | Chinese word segmentation method and device | |
| CN107704501B (en) | Method and system for identifying homologous binary file | |
| Chen et al. | Template detection for large scale search engines | |
| CN107784110B (en) | Index establishing method and device | |
| WO2006010163A2 (en) | User interface and database structure for chinese phrasal stroke and phonetic text input | |
| TWI604318B (en) | Method of data sorting | |
| CN102750379B (en) | Fast character string matching method based on filtering type | |
| CN105069056A (en) | Character string matching based method and system for analyzing address information of identification card | |
| CN106909575B (en) | Text clustering method and device | |
| EP3091450A1 (en) | Method and system for performing binary searches | |
| CN107085568B (en) | Text similarity distinguishing method and device | |
| JP2019512127A (en) | String distance calculation method and apparatus | |
| CN104252542A (en) | Dynamic-planning Chinese words segmentation method based on lexicons | |
| CN102867049A (en) | Chinese PINYIN quick word segmentation method based on word search tree | |
| CN109670153B (en) | Method and device for determining similar posts, storage medium and terminal | |
| Soori et al. | Text similarity based on data compression in Arabic | |
| US10127219B2 (en) | System and method for organizing and processing feature based data structures | |
| Hakak et al. | An efficient text representation for searching and retrieving classical diacritical arabic text | |
| CN111190937A (en) | Native place information query method and device, electronic equipment and storage medium | |
| Matsuoka et al. | Examination of effective features for CRF-based bibliography extraction from reference strings | |
| CN103116607B (en) | A kind of text retrieval system based on the Chinese phonetic alphabet newly |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160601 |
|
| WD01 | Invention patent application deemed withdrawn after publication |