CN112732779B - Method for analyzing address text by big data based on site POI - Google Patents
Method for analyzing address text by big data based on site POI Download PDFInfo
- Publication number
- CN112732779B CN112732779B CN202011589770.6A CN202011589770A CN112732779B CN 112732779 B CN112732779 B CN 112732779B CN 202011589770 A CN202011589770 A CN 202011589770A CN 112732779 B CN112732779 B CN 112732779B
- Authority
- CN
- China
- Prior art keywords
- poi
- matching
- address
- road
- name
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2468—Fuzzy queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
-
- 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
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Automation & Control Theory (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to the technical field of address text analysis, in particular to a method for analyzing an address text by using big data based on a place POI (Point of interest), which comprises the following steps: s1, processing urban POI basic data; s2, analyzing the matched address text; and S3, analyzing data and visually displaying. According to the method, the statistics and analysis of the user package address can be realized through the urban POI basic data processing and the matching address text analysis, the address text can be accurately positioned, the accurate analysis and statistics of the user package address can be realized, effective user distribution data and images are provided for postal companies, logistics companies or e-commerce enterprises, and further a decision basis can be provided for the express package address selection and the personnel allocation.
Description
Technical Field
The invention relates to the technical field of address text analysis, in particular to a method for analyzing address texts based on big data of a place POI.
Background
For postal companies, logistics companies, e-commerce enterprises and the like with huge user volumes, a large number of user package addresses exist, and the distribution conditions of users are usually counted and analyzed according to the address texts. The difficulty is how to precisely locate these address texts. Since these addresses may come from a third party e-commerce platform or due to user input errors, the text data is difficult to be resolved, and the characteristics of these address texts are as follows: there is no fixed format, and random miswords, alias of location, or even non-existent location are included. The addresses are directly analyzed and positioned by using a third-party map company interface, so that a large amount of deviation is caused, the purpose of statistical analysis cannot be achieved, and accurate analysis and processing are difficult by using other conventional methods. In view of this, we propose a method for parsing address text based on big data of a place POI.
Disclosure of Invention
The present invention is directed to provide a method for parsing an address text based on big data of a location POI, so as to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for analyzing address text based on big data of a place POI comprises the following steps:
s1, processing urban POI basic data;
s2, analyzing the matched address text;
and S3, analyzing data and visually displaying.
As a preferred technical scheme of the invention, the city POI basic data processing in the S1 specifically comprises the following steps:
s11: POI data crawling;
s12: optimizing the POI name;
s13: automatically processing the alias of the POI;
s14: and (5) manually adjusting and optimizing the POI.
As a preferred technical scheme of the present invention, the concrete operation of the POI data crawling in S11 is:
a. for a Baidu and Gaode map, a place POI is crawled in a rectangular scanning mode of multiple times and different ranges, and other data acquisition modes including other websites and government statistical data can be continuously explored;
b. and storing the crawled POI data into a database in a classified mode.
As a preferred technical solution of the present invention, the specific operation of optimizing the POI name in S12 is:
a. removing obviously invalid and repeated data;
b, the POI names have inclusion relation, the distances are judged, and if the distances are smaller than 200 meters, the POI names are merged and processed;
c. the name includes Anhui province and fertilizer city, and is optimized as province and city; for property classes: if the electric bicycle only contains 'first stage', 'first seat' and 'A seat', the 'first stage', 'first seat' and 'A seat' are removed;
d. aiming at a property office building: the seat A and the seat A are automatically combined and renamed, and the seat B and the seat C are removed.
As a preferred technical solution of the present invention, the specific operation of the automatic processing of the POI alias in S13 is:
1) For property classes:
a. intelligently extracting prefixes in "-" and "-, such as" Wanke-gold name county ", extracting" Wanke "and storing the" Wanke "to tag _ poi;
b. encounter the resemblance "Wanke-gold MingJejun", "Wanke Jin Seming county", smart Add remark "Jin Seming county";
2) For government entity classes:
XX village membership, which may be abbreviated as XX village commission;
XX town Committee, which may be abbreviated as XX Zhen Commission, XX City Commission;
the XX Toolk Law examination committee can be abbreviated as XX Toolk and XX City Toolk;
and d, XX town people government, which can be abbreviated as XX town government and XX city government.
As a preferred technical solution of the present invention, the specific operations of the POI management interface in S14 are: and the WEB terminal is used for an administrator for manually supplementing the POI, and amending the alias and the remark of the POI.
As a preferred technical solution of the present invention, the parsing of the matching address text in S2 specifically includes the following steps:
s21: a treatment process;
s22: and (5) address final positioning processing.
As a preferred technical solution of the present invention, the specific operations of the processing flow in S21 are:
1) Data preprocessing, discarding obviously wrong addresses, such as blank addresses and addresses only with provincial and urban road names, and the like, and separately storing the addresses in a classified manner;
2) Fully matching intersections, intersections and road numbers, uniformly formatting the actual intersections, road names and road number basic data, and matching the road information corresponding to the addresses;
3) Completing the road tail road number, processing the address containing the 'Changjiang Xilu' and completing the address to be 'Changjiang Xilu' 339;
4) Road pinyin matching, wherein address Chinese pinyin matches road name + road number;
5) Intelligent road matching, fuzzy address matching of road name + road number or intersection, AI text similarity matching, processing fuzzy matching of wrong characters, multiple characters and few characters;
6) POI full-name alias matching, wherein the type of a house is matched preferentially, the length of a POI name is matched preferentially, and the alias of a special symbol is automatically processed to obtain the POI corresponding to the address;
7) POI full name, alias pinyin matching, residential area and school type POI, participating in pinyin matching;
8) POI intelligent matching, AI text similarity matching and fuzzy matching, wherein the types of the POI participating in the intelligent matching are residential areas, colleges and universities and comprehensive hospitals.
As a preferred technical solution of the present invention, the specific operations of the address final location processing in S22 are:
1) POI full name matching address processing:
whether the POI currently matched with the address corresponds to the matched road information or not is judged, if the POI is correctly corresponding to the matched road information, the POI is used for positioning, if the POI does not correspond to the matched road information, the full name/complete matching of the street information is taken as the standard, wherein the residential area type is positioned by the name of the POI, no road information is contained, and the POI is used for positioning;
2) And (3) POI alias matching address processing:
the method comprises the steps that full-name matching road information exists, positioning is carried out according to the road information, otherwise, when a plurality of aliases match the POI, positioning is carried out according to the maximum length, no road information exists, and positioning is carried out according to the POI;
3) And (3) POI fuzzy matching address processing:
the method comprises the steps that road full-name matching is carried out, road information positioning is carried out, road information does not exist, a plurality of POI names are positioned in the longest mode, and road fuzzy matching and POI fuzzy matching names are positioned in the longest mode;
4) And (3) processing the unmatched POI address:
fully matching and positioning the road, carrying out fuzzy matching and positioning on the road, and finally leaving unprocessed;
5) POI renaming processing:
when multiple duplicate names exist in the POI matched with the address, the POI needs to be determined according to the road information of the area, if the POI cannot be distinguished, the POI is discarded, and the POI is discarded when the address is different from the area to which the POI belongs.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, the statistics and analysis of the user package address can be realized through the urban POI basic data processing and the matching address text analysis, the address text can be accurately positioned, the accurate analysis and statistics of the user package address can be realized, effective user distribution data and images are provided for postal companies, logistics companies or e-commerce enterprises, and further a decision basis can be provided for the express package address selection and the personnel allocation.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the following embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment provides the following technical scheme:
a method for analyzing address text based on big data of a place POI comprises the following steps:
s1, processing urban POI basic data;
s2, analyzing the matched address text;
and S3, analyzing data and visually displaying.
As a preferred technical solution of this embodiment, the processing of the city POI base data in S1 specifically includes the following steps:
s11: POI data crawling;
s12: optimizing the POI name;
s13: automatically processing the alias of the POI;
s14: and (5) manually adjusting and optimizing the POI.
As a preferred technical solution of this embodiment, the specific operation of crawling POI data in S11 is:
a. for a Baidu and Gaode map, a place POI is crawled in a rectangular scanning mode of multiple times and different ranges, and other data acquisition modes including other websites and government statistical data can be continuously explored;
b. and storing the crawled POI data into a database in a classified manner.
As a preferred technical solution of this embodiment, the specific operation of optimizing the POI name in S12 is:
a. removing obviously invalid and repeated data;
b, the POI names have inclusion relation, the distances are judged, and if the distances are smaller than 200 meters, the POI names are merged and processed;
c. the name includes Anhui province and fertilizer city, and is optimized as province and city; for the property classes: if the user only has 'first stage', 'first seat' and 'A seat', the user removes 'first stage', 'first seat' and 'A seat';
d. aiming at a property office building: the seat A and the seat A are automatically combined and renamed, and the seat B and the seat C are removed.
As a preferred technical solution of this embodiment, the specific operation of the POI alias automatic processing in S13 is:
1) For property classes:
a. intelligently extracting prefixes in "-" and "-, such as" Wanke-gold name county ", extracting" Wanke "and storing the" Wanke "to tag _ poi;
b. similar to "Wanke-gold Minjishire", "Wanke Jin Seming county", smart Add remark "Jin Seming county";
2) For government entity classes:
XX village members, which may be abbreviated as XX village committee;
XX town Committee, which may be abbreviated as XX Zhen Wei, XX City Wei;
the XX Toolk Law examination committee can be abbreviated as XX Toolk and XX City Toolk;
and d, XX town people government, which can be abbreviated as XX town government and XX city government.
As a preferred technical solution of this embodiment, the specific operations of the POI management interface in S14 are: and the WEB terminal is used for providing the administrator for manually supplementing the POI and amending the alias and the remark of the POI.
As a preferred technical solution of this embodiment, the parsing of the matching address text in S2 specifically includes the following steps:
s21: a treatment process;
s22: and (5) address final positioning processing.
As a preferred technical solution of this embodiment, the specific operations of the processing flow in S21 are:
1) Data preprocessing, discarding obviously wrong addresses, such as blank addresses and addresses only with provincial and urban road names, and the like, and separately storing the addresses in a classified manner;
2) Fully matching intersections, intersections and road numbers, uniformly formatting the actual intersections, road names and road number basic data, and matching the road information corresponding to the addresses;
3) Completing the road tail road number, processing the address containing the 'Changjiang Xilu' and completing the address to be 'Changjiang Xilu' 339;
4) Road pinyin matching, wherein address Chinese pinyin matches road name + road number;
5) Intelligent road matching, fuzzy address matching of road name + road number or intersection, AI text similarity matching, processing fuzzy matching of wrong characters, multiple characters and few characters;
6) POI full-name alias matching, wherein the type of a house is matched preferentially, the length of a POI name is matched preferentially, and the alias of a special symbol is automatically processed to obtain the POI corresponding to the address;
7) POI full name, alias pinyin matching, residential area and school type POI, participating in pinyin matching;
8) POI intelligent matching, AI text similarity matching and fuzzy matching, wherein the types of the POI participating in the intelligent matching are residential areas, colleges and universities and comprehensive hospitals.
As a preferred technical solution of this embodiment, the specific operations of the address final positioning processing in S22 are:
1) POI full name matching address processing:
whether the POI matched with the address at present corresponds to the matched road information or not, if the POI is correctly corresponding to the road information, the POI is positioned, if the POI does not correspond to the road information, the matched street information is fully called/supplemented, wherein the residential area type is positioned by the name of the POI, no road information exists, and the POI is positioned;
2) And (3) POI alias matching address processing:
the method comprises the steps that full-name matching road information exists, positioning is carried out according to the road information, otherwise, when a plurality of aliases match the POI, positioning is carried out according to the maximum length, no road information exists, and positioning is carried out according to the POI;
3) And (3) POI fuzzy matching address processing:
the method comprises the following steps that full-name matching of roads is carried out, road information is located, the names of a plurality of POIs are located in the longest mode, and names of fuzzy roads and fuzzy POIs are located in the longest mode;
4) And (3) processing the unmatched POI address:
fully matching and positioning the road, carrying out fuzzy matching and positioning on the road, and finally leaving unprocessed;
5) POI renaming processing:
when multiple duplicate names exist in the POI matched with the address, the POI needs to be determined according to the road information of the area, if the POI cannot be distinguished, the POI is discarded, and the POI is discarded when the address is different from the area to which the POI belongs.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (1)
1. A method for analyzing address text based on big data of a place POI is characterized by comprising the following steps: the method comprises the following steps: s1, processing city POI basic data; s2, analyzing the matched address text;
s3, analyzing data and visually displaying;
the city POI basic data processing in S1 specifically comprises the following steps:
s11: POI data crawling;
s12: optimizing the POI name;
s13: automatically processing the alias of the POI;
s14: POI manual tuning;
the specific operation of POI data crawling in S11 is as follows:
a. on-line maps are crawled to obtain POI (point of interest) in a rectangular scanning mode of multiple times and different ranges, and meanwhile, other data obtaining modes including other websites and government statistical data can be continuously explored;
b. storing the crawled POI data into a database in a classified manner;
the specific operation of POI name optimization in S12 is:
a. removing obviously invalid and repeated data;
b, judging whether the POI names have inclusion relations, and if the POI names are less than 200 meters, merging and processing;
c. the names of the provinces comprise 'XX province' and 'XX city', and are optimized as 'province' and 'city'; for property classes: if the user only has 'first stage', 'first seat' and 'A seat', the user removes 'first stage', 'first seat' and 'A seat';
d. aiming at a property office building: automatically combining the seat A and the seat A, renaming, and removing the seat B, the seat C and the like;
the specific operation of the automatic processing of the POI alias in S13 is:
1) For property classes:
a. intelligently extracting prefixes in "-" and "-" such as "XX- # name county", extracting "XX" and saving to tag _ poi;
b. encountering the similarities "XX- # name county", "XX # name county", and the intelligent addition remark "# name county";
2) For government unit classes:
XX village members, which may be abbreviated as XX village committee;
XX town Committee, which may be abbreviated as XX Zhen Wei, XX City Wei;
the XX Toolk Law examination committee can be abbreviated as XX Toolk and XX City Toolk;
XX town people's government, may be abbreviated as XX town government, XX city government;
the specific operation of the POI management interface in S14 is: the WEB side gives the administrator for manually supplementing the POI, and amending the alias and the remark of the POI;
the step of analyzing the matched address text in the step S2 specifically comprises the following steps:
s21: a treatment process;
s22: final address positioning processing;
the specific operation of the processing flow in S21 is:
1) Data preprocessing, discarding obviously wrong addresses, such as blank addresses and addresses only with provincial and urban road names, and the like, and separately storing the addresses in a classified manner;
2) Fully matching intersections, intersections and road numbers, uniformly formatting the actual intersections, road names and road number basic data, and matching the road information corresponding to the addresses;
3) Completing the road tail road number, processing the address containing the 'Changjiang Xilu' and completing the address to be 'Changjiang Xilu' 339;
4) Road pinyin matching, wherein address Chinese pinyin matches road name + road number;
5) Intelligent road matching, fuzzy address matching of road name + road number or intersection, AI text similarity matching, processing fuzzy matching of wrong characters, multiple characters and few characters;
6) POI full-name alias matching, wherein the type of a house is matched preferentially, the length of a POI name is matched preferentially, and the alias of a special symbol is automatically processed to obtain the POI corresponding to the address;
7) POI full name, alias pinyin matching, residential area and school type POI, participating in pinyin matching;
8) POI intelligent matching, AI text similarity matching and fuzzy matching, wherein the types of the POI participating in the intelligent matching are residential areas, colleges and universities and comprehensive hospitals;
the specific operation of the address final location processing in S22 is:
1) POI full name matching address processing:
whether the POI currently matched with the address corresponds to the matched road information or not is judged, if the POI is correctly corresponding to the matched road information, the POI is used for positioning, if the POI does not correspond to the matched road information, the full name/complete matching of the street information is taken as the standard, wherein the residential area type is positioned by the name of the POI, no road information is contained, and the POI is used for positioning;
2) And (3) POI alias matching address processing:
if the POI exists, the POI with the maximum length is positioned without the road information, and the POI is positioned;
3) And (3) POI fuzzy matching address processing:
the method comprises the following steps that full-name matching of roads is carried out, road information is located, the names of a plurality of POIs are located in the longest mode, and names of fuzzy roads and fuzzy POIs are located in the longest mode;
4) And (3) processing the unmatched POI address:
road full-name matching positioning, road fuzzy matching positioning and final left unprocessed;
5) POI renaming processing:
when multiple duplicate names exist in the POI matched with the address, the POI needs to be determined according to the road information of the area, if the POI cannot be distinguished, the POI is discarded, and the POI is discarded when the address is different from the area to which the POI belongs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011589770.6A CN112732779B (en) | 2020-12-29 | 2020-12-29 | Method for analyzing address text by big data based on site POI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011589770.6A CN112732779B (en) | 2020-12-29 | 2020-12-29 | Method for analyzing address text by big data based on site POI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112732779A CN112732779A (en) | 2021-04-30 |
| CN112732779B true CN112732779B (en) | 2022-12-30 |
Family
ID=75607472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011589770.6A Active CN112732779B (en) | 2020-12-29 | 2020-12-29 | Method for analyzing address text by big data based on site POI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732779B (en) |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201306942D0 (en) * | 2013-04-17 | 2013-05-29 | Tomtom Int Bv | Methods, devices and computer software for facilitating searching and display of locations relevant to a digital map |
| CN104484790A (en) * | 2014-12-26 | 2015-04-01 | 清华大学深圳研究生院 | Address match method and device of logistics business |
| CN108021638B (en) * | 2017-11-28 | 2022-01-14 | 上海电科智能系统股份有限公司 | Offline geocoding unstructured address resolution system |
| CN109978430A (en) * | 2017-12-28 | 2019-07-05 | 青岛日日顺电器服务有限公司 | A kind of method, apparatus, server and storage medium parsing station address |
| CN109165273B (en) * | 2018-08-24 | 2021-10-26 | 安徽讯飞智能科技有限公司 | General Chinese address matching method facing big data environment |
| 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 |
| KR102119759B1 (en) * | 2018-12-13 | 2020-06-08 | 네이버 주식회사 | Apparatus for detecting error point of map data and method for the same |
| CN111723165B (en) * | 2019-03-18 | 2024-06-11 | 阿里巴巴集团控股有限公司 | Address interest point determination method, device and system |
| CN110795472A (en) * | 2019-11-11 | 2020-02-14 | 集奥聚合(北京)人工智能科技有限公司 | Address standardization method, system, equipment and medium based on fuzzy matching |
| CN111813819B (en) * | 2020-07-13 | 2022-07-22 | 南通市测绘院有限公司 | Space-time big data-based place name and address online matching method |
-
2020
- 2020-12-29 CN CN202011589770.6A patent/CN112732779B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112732779A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145169B (en) | Address matching method based on statistical word segmentation | |
| CN108628811B (en) | Address text matching method and device | |
| CN109933797A (en) | Geocoding and system based on Jieba participle and address dictionary | |
| JP5856618B2 (en) | Geospatial database integration method and device | |
| CN111324679B (en) | Method, device and system for processing address information | |
| CN106909611B (en) | Hotel automatic matching method based on text information extraction | |
| CN110472066A (en) | A kind of construction method of urban geography semantic knowledge map | |
| CN109344213B (en) | Chinese geocoding method based on dictionary tree | |
| CN106874287B (en) | Method and device for processing POI address codes | |
| WO2015027836A1 (en) | Method and system for place name entity recognition | |
| CN102289467A (en) | Method and device for determining target site | |
| CN103514234A (en) | Method and device for extracting page information | |
| CN112528174A (en) | Address finishing and complementing method based on knowledge graph and multiple matching and application | |
| CN106844527B (en) | Road surface disease identification and management decision-making method and system based on internet big data | |
| CN103473289A (en) | Device and method for completing communication addresses | |
| CN108536657A (en) | The address text similarity processing method and system artificially filled in | |
| CN116414823A (en) | Address positioning method and device based on word segmentation model | |
| CN114241501B (en) | Image document processing method and device and electronic equipment | |
| CN112069824B (en) | Region identification method, device and medium based on context probability and citation | |
| CN111896016A (en) | Position information processing method and device, storage medium and terminal | |
| CN117633137B (en) | Map data analysis and extraction method and system based on deep learning | |
| CN1367446A (en) | Chinese personal biographical notes information treatment system and method | |
| CN112732779B (en) | Method for analyzing address text by big data based on site POI | |
| CN111325235A (en) | Multilingual-oriented universal place name semantic similarity calculation method and application thereof | |
| CN116431625A (en) | Positioning analysis method and device for geographic entity and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |