CN110147420A - A kind of place name address matching querying method and system based on spectrum model - Google Patents
A kind of place name address matching querying method and system based on spectrum model Download PDFInfo
- Publication number
- CN110147420A CN110147420A CN201910373652.2A CN201910373652A CN110147420A CN 110147420 A CN110147420 A CN 110147420A CN 201910373652 A CN201910373652 A CN 201910373652A CN 110147420 A CN110147420 A CN 110147420A
- Authority
- CN
- China
- Prior art keywords
- address
- section
- field
- place name
- data structure
- 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
- 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
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2246—Trees, e.g. B+trees
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of place name address matching method and system, belong to GIS-Geographic Information System field, are specifically related to a kind of place name address matching method and system based on spectrum model.The system and method quickly forms participle library by technological means in map establishment process, the context relation of address section is considered in address matching process, the deficiency that nature semantic constraint is made up by spatial position constraint, so that the accuracy of hit address is substantially improved.
Description
Technical field
The present invention relates to a kind of place name address matching querying method and systems, belong to GIS-Geographic Information System field, specifically
It is related to a kind of place name address matching querying method and system based on spectrum model.
Background technique
In recent years, to adapt to smart city development, it is city that address, which is the ways and means for enhancing people, real estate management's reason,
The important reference object of management puts forward new requirements place name address search technology.The total amount of city's domain addresses in one city with
Urban population quantity is substantially in 1:1 relationship, big city especially more in population, and address total amount is also larger.Because of these cities
The transition in city are very fast, in development process, various irregular active address occur, although irregularly, having become set
The fact, this precisely matches with address to address specificationization and brings difficulty.To promote the matching rate of address search and correct
Rate needs to administer from address date and start with, and huge data volume needs investment a large amount of artificial, and this is one and continues
Process because new building can generate new address, new address may also be lack of standardization.
In the prior art, address is gone to the way for realizing address search according to tree tissue, and there is also but matching
It cannot accomplish to level off to 100% in terms of correctness, to be difficult to correct address and problem address area by programming automation
It separates, so that subsequent address correction works, needs a large amount of artificial investigation workloads.In addition, yet there are no tree-shapedly
The way that the correcting of spatial position is considered in the organizational process of location, further to promote the accuracy rate of address matching.
During address lookup, address search in the prior art is had the following problems:
(1) traditional address search focuses on search without focusing on matching
Traditional address search often goes to realize that address search, this mode are needing man-machine interactively using search engine
Application scenarios under be feasible, but in the case where unattended, using search engine, default takes the ground of first hit
Location carries out under the scene of address matching, and accuracy can reduce.For example, " the Shenzhen City, Guangdong Province Futian District road Fu Yun Tianxiang mansion CD
702 ", when inputting this address, it is likely that first address that search engine returns is " Shenzhen City, Guangdong Province Futian District day
The mansion Xiang Lu Fuyun CD 702 ", but this is two different addresses.This is because the purpose of search engine is as far as possible
" more " find the address with associated description, without considering this kind of special natural languages in address on apparent
It hereafter constrains, that is to say, that the verification of search engine is not stringent enough.
(2) traditional address matching is unable to flexible setting matching constraint condition
Traditional search engine can strengthen matched constraint when promoting address hit accuracy by every means, and some
When address matching constraint condition it is stringenter, although matched accuracy can improve, the address that can be hit is got over
Few, the address for needing manually to check is more.
(3) traditional address matching model cannot safeguard the relationship between the multiple dimensions in address
What is considered in the application of traditional address search is status place name address, less pays close attention to the life cycle of address itself
Effectively whether () and its various dimensions information (former name, is commonly called as alias) can generate a large amount of because the cost of maintenance is too big
Redundancy (these former names, are commonly called as alias, often only a part in full address).But in novel smart city
In management application, need by those also in the former name of the address used, alias is commonly called as waiting to establish with status address being associated with
System, to understand the life cycle of these city management objects of reference in depth.
Therefore, place name address matching querying method in the prior art and system are improved, to meet different application
The demand of scene is current technical problem in the urgent need to address.
Summary of the invention
A brief summary of one or more aspects is given below to provide to the basic comprehension in terms of these.This is summarized not
It is the extensive overview of all aspects contemplated, and is both not intended to identify critical or decisive element in all aspects
Also the non-range attempted to define in terms of any or all.Its unique purpose is to provide one or more side in simplified form
Some concepts in face are with the sequence for more detailed description given later.
The main purpose of the present invention be in the presence of solving the prior art it is upper this technical issues of, provide a kind of base
In the place name address matching querying method and system of spectrum model.The system and method passes through technology in map establishment process
Means quickly form participle library, and the context relation of address section is considered in address matching process, more by spatial position constraint
The deficiency for mending nature semantic constraint, so that the accuracy of hit address is substantially improved.
To solve the above problems, the scheme of the invention is:
A kind of place name address storage method based on spectrum model, comprising:
Address merogenesis step, for address to be divided into several grades according to default rule；
Map constructions steps, the field of next stage address data structure is directed toward in building in the data structure of addresses at different levels；
Interface construction step, the package drawing model data query interface service on the basis of data structure of addresses at different levels are used
All data item in inquiry and access data structure.
Preferably, in the address merogenesis step, institute address section write-in participle library, and level is marked to number.
Preferably, the map constructions steps identify address dates at different levels by the numerical identity UID of 16 systems
Structure uses hash rope by UID, UID and the AddrLink field that another field addrLink identifies next stage address section
Draw and is stored in No. 1 node.
Preferably, the map constructions steps are established complete respectively using the Chinese of Name field recording address section
Text index is indexed with term, is stored in No. 2 nodes；Using Lev field record address level, using binary tree structure index number
Value Types are stored in No. 3 nodes；The central point of spatial position uses Loc field record where the section of address, establishes GeoHash rope
Draw, is stored in No. 4 nodes.These data are used for different nodes from index type distributed storage according to field, convenient for subsequent
Distributed computing.
A kind of place name address inquiring method based on spectrum model, comprising:
Address dividing step segments address to be matched according to address layer grade, forms the address of different address level
Section；
Query steps are classified, according to the spatial dimension where the level of address section and address to be matched, empty with address
Between information address section database in carry out address section matching；
Evaluation of result step arranges matching result to the address calculation similarity score being matched to, and according to scoring
Sequence；
Wherein, the address in the address section database is divided into several grades according to default rule, in addresses at different levels
The field for being directed toward next stage address data structure is built in data structure.
A kind of place name address storage system based on spectrum model, comprising:
Address merogenesis module, for address to be divided into several grades according to default rule；
Map construction module, the field of next stage address data structure is directed toward in building in the data structure of addresses at different levels；
Interface constructs module, and the package drawing model data query interface service on the basis of data structure of addresses at different levels is used
All data item in inquiry and access data structure.
Preferably, in the address merogenesis module, institute address section write-in participle library, and level is marked to number.
Preferably, the map construction module identifies address dates at different levels by the numerical identity UID of 16 systems
Structure uses hash rope by UID, UID and the AddrLink field that another field addrLink identifies next stage address section
Draw and is stored in No. 1 node.
Preferably, the map construction module is established complete respectively using the Chinese of Name field recording address section
Text index is indexed with term, is stored in No. 2 nodes；Using Lev field record address level, using binary tree structure index number
Value Types are stored in No. 3 nodes；The central point of spatial position uses Loc field record where the section of address, establishes GeoHash rope
Draw, is stored in No. 4 nodes.These data are used for different nodes from index type distributed storage according to field, convenient for subsequent
Distributed computing.
A kind of place name address lookup system based on spectrum model, comprising:
Address dividing module segments address to be matched according to address layer grade, forms the address of different address level
Section；
It is classified enquiry module, according to the spatial dimension where the level of address section and address to be matched, empty with address
Between information address section database in carry out address section matching；
Evaluation of result module arranges matching result to the address calculation similarity score being matched to, and according to scoring
Sequence；
Wherein, the address in the address section database is divided into several grades according to default rule, in addresses at different levels
The field for being directed toward next stage address data structure is built in data structure.
Therefore, the invention has the advantages that
(1) present invention mixes engine with matching using search, scans for, makes under the premise of considering context matches
The accuracy for obtaining hit address is substantially improved, can be under unattended mode, ideally by correct address and problem address area
It separates, and is capable of the address section of automatic polishing missing；
(2) the invention proposes the method for improving match hit rate, the description that can be saved to each address is established different
Index, the address section that certain levels can be dynamically set in matching use " equal ", " including entirely " or " partially including ", this
Matching constraint is actually relaxed, then reduces interference by introducing other constraint conditions, under the premise of guaranteeing accuracy,
Promote the hit rate of address matching.
(3) present invention uses search mixes engine with matching, the tissue by the way of map is saved in address, with building jointly
Found a thesaurus, it will be able to establish the relationship between multiple dimensions of address section well, realize between address indirectly
Various dimensions relationship, by any one dimension can retrieve other dimensions of address information (because by any one dimension
Degree can obtain normal address, and multiple dimensions of address section can be inquired by the address section in normal address), and
Almost without data redundancy, the maintenance workload of address various dimensions information is smaller.
Detailed description of the invention
It is incorporated herein and the attached drawing for forming part of specification instantiates the embodiment of the present invention, and attached drawing and say
Bright book is further used for explaining the principle of the present invention together and one of ordinary skill in the art is enabled to make and use this public affairs
It opens.
Fig. 1 instantiates the address merogenesis schematic diagram in the embodiment of the present invention；
Fig. 2 instantiates the address map construction schematic diagram in the embodiment of the present invention；
Fig. 3 instantiates the section checking process figure of the address in the embodiment of the present invention；
Fig. 4 is instantiated in the embodiment of the present invention and is exported former name address schematic diagram by normal address.
The embodiment of the present invention is described with reference to the accompanying drawings.
Specific embodiment
Embodiment
The present embodiment provides a kind of place name address matching querying method and system based on spectrum model.Below with reference to
Attached drawing is illustrated the present embodiment.
Fig. 1 instantiates the address merogenesis schematic diagram in the embodiment of the present invention；By full address " Shenzhen City, Guangdong Province South Mountain
Area, Tianxiang mansion, South Mountain street CD seat 702 " is split from left to right according to specification are as follows: [Guangdong Province] [Shenzhen] [Nanshan District] [south
Mountain street] [Tianxiang mansion] [CD] [702].
Participle library is written in address above mentioned section, and level is marked to number, when to areal subsequent address progress merogenesis
When, these sections divided by automatic word segmentation and are filled into corresponding address ganglionic layer grade.Address merogenesis formed two at
Fruit: the 1, address after merogenesis；2, library (merging address section of the same name) is segmented.
Fig. 2 instantiates the address map construction schematic diagram in the embodiment of the present invention；Neighbor address section passes through 16 systems
Numerical identity its uniqueness (UID), the next stage address section of its " association " is identified by another field addrLink
UID, UID and AddrLink field are stored in No. 1 node (NODE1) using hash index；Use Name field recording address section
Chinese, establish respectively full-text index and term index (individual character matching can be carried out), be stored in No. 2 nodes (NODE2)；
Using Lev field record address level, value type is indexed using binary tree structure, is stored in No. 3 nodes (NODE3)；Address
The central point of spatial position uses Loc field record where section, establishes GeoHash index, is stored in No. 4 nodes (NODE4).
These data are used for different nodes from index type distributed storage according to field, are convenient for subsequent distributed computing.
On the basis of this data model, " graph model " data-query interfaces service is encapsulated, for inquiring and accessing data knot
All data item in structure.
Fig. 3 instantiates the section checking process figure of the address in the embodiment of the present invention；Address to be matched is grading according to address layer
Row participle, the address for forming different address level are saved, the spatial dimension where the level saved according to address and address to be matched,
The matching that address section is carried out in the address section database with address space information, to the address calculation similarity being matched to
Scoring, and matching result is ranked up according to scoring.Address matching supports that (former name is commonly called as, referred to as address name synonym
Deng) inquiry.
The present embodiment mixes engine with matching using search, scans under the premise of considering context matches, so that
The accuracy of hit address is substantially improved, and ideally can distinguish correct address and problem address under unattended mode
It opens, and is capable of the address section of automatic polishing missing.Such as: " road Fu Yun Tianxiang mansion CD 702 ", after inputting this address, meeting
Hit " the Shenzhen City, Guangdong Province Futian District road Fu Yun Tianxiang mansion CD 702 ", automatic polishing is provincial, city-level and area's grade this three
A address section.Principle is that number of addresses is retrieved from leaf node to root node, and path is uniquely, so being capable of accurate polishing
The upper level address section of missing.
The present embodiment proposes the method for improving match hit rate, and the description that can be saved to each address is established different
Index, the address section that certain levels can be dynamically set in matching use " equal ", " including entirely " or " partially including ", this
Matching constraint is actually relaxed, then reduces interference by introducing other constraint conditions, under the premise of guaranteeing accuracy,
Promote the hit rate of address matching.As shown in Fig. 4, " [Fu Yunlu] [Tianxiang mansion] [C D] [702] " this address is when " building
The matching constraint of level " be it is complete comprising when, then will not hit [Fu Yunlu] [Tianxiang center] [C D] [702] this ground
Location, when the matching constraint of " building level " is that part includes, [Fu Yunlu] [Tianxiang center] [C D] [702] this address
It can be hit.But [Tianxiang mansion] and [Tianxiang center] on earth be the same position, can by other constraint means come
Determine, such as use space position.For example, the status address that express company provides does not meet code requirement very much (but with inadequate
Accurately location information), it is that it is corresponding to find address that this does not meet address standard requirements for which normal address, so that it may
To use the above method, the matching constraint in building and cell hierarchy is adjusted to " partially including ", and utilizes the position of input address
Confidence breath buffers, by the way of position+semanteme double constraints, can in the nonstandard situation of input address, acquisition compared with
High address matching accuracy and hit rate.
The present embodiment has used search to mix engine with matching, and by address section tissue by the way of map, cooperation is established
One thesaurus, it will be able to establish the relationship between multiple dimensions of address section well, realize between address indirectly
Various dimensions relationship can retrieve the information of other dimensions of address (because by any one dimension by any one dimension
Normal address can be obtained, and multiple dimensions of address section can be inquired by the address section in normal address), and it is several
There is no data redundancy, the maintenance workload of address various dimensions information is smaller.
In the present embodiment, although the above method to be illustrated to and is described as a series of actions to simplify to explain, answer
It is appreciated and understood that, the order that these methods are not acted is limited, because according to one or more embodiments, some movements can be pressed
Different order occur and/or with from depicted and described herein or not shown herein and describe but those skilled in the art
It is understood that other movements concomitantly occur.
It is noted that " one embodiment ", " embodiment ", " example embodiment ", " some embodiments " etc. in specification
Reference instruction described embodiment may include a particular feature, structure, or characteristic, but each embodiment may not necessarily include
The a particular feature, structure, or characteristic.Moreover, such phrase is not necessarily referring to the same embodiment.In addition, ought be in conjunction with the embodiments
When describing a particular feature, structure, or characteristic, regardless of whether being expressly recited, such feature, knot are realized in conjunction with other embodiments
Structure or characteristic will be in the knowledges of those skilled in the art.
Offer is to make any person skilled in the art all and can make or use this public affairs to the previous description of the disclosure
It opens.The various modifications of the disclosure all will be apparent for a person skilled in the art, and as defined herein general
Suitable principle can be applied to other variants without departing from the spirit or scope of the disclosure.The disclosure is not intended to be limited as a result,
Due to example described herein and design, but should be awarded and principle disclosed herein and novel features phase
Consistent widest scope.
Claims (10)
1. a kind of place name address storage method based on spectrum model characterized by comprising
Address merogenesis step, for address to be divided into several grades according to default rule；
Map constructions steps, the field of next stage address data structure is directed toward in building in the data structure of addresses at different levels；
Interface construction step, the package drawing model data query interface service on the basis of data structure of addresses at different levels, for looking into
Ask and access all data item in data structure.
2. a kind of place name address storage method based on spectrum model according to claim 1, which is characterized in that describedly
In the merogenesis step of location, institute address section write-in participle library, and level is marked to number.
3. a kind of place name address storage method based on spectrum model according to claim 1, which is characterized in that the figure
Construction step is composed, address data structures at different levels are identified by the numerical identity UID of 16 systems, pass through another field
UID, UID and the AddrLink field of addrLink mark next stage address section are stored in No. 1 node using hash index.
4. a kind of place name address storage method based on spectrum model according to claim 3, which is characterized in that the figure
Construction step is composed, using the Chinese of Name field recording address section, full-text index is established respectively and term indexes, be stored in
No. 2 nodes；Using Lev field record address level, value type is indexed using binary tree structure, is stored in No. 3 nodes；Address
The central point of spatial position uses Loc field record where section, establishes GeoHash index, is stored in No. 4 nodes.These are counted
Different nodes are used for from index type distributed storage according to according to field, are convenient for subsequent distributed computing.
5. a kind of place name address inquiring method based on spectrum model characterized by comprising
Address dividing step segments address to be matched according to address layer grade, forms the address section of different address level；
Query steps are classified, according to the spatial dimension where the level of address section and address to be matched, are believed with address space
The matching of address section is carried out in the address section database of breath；
Evaluation of result step is ranked up matching result to the address calculation similarity score being matched to, and according to scoring；
Wherein, the address in the address section database is divided into several grades according to default rule, the data in addresses at different levels
The field for being directed toward next stage address data structure is built in structure.
6. a kind of place name address storage system based on spectrum model characterized by comprising
Address merogenesis module, for address to be divided into several grades according to default rule；
Map construction module, the field of next stage address data structure is directed toward in building in the data structure of addresses at different levels；
Interface constructs module, the package drawing model data query interface service on the basis of data structure of addresses at different levels, for looking into
Ask and access all data item in data structure.
7. a kind of place name address storage system based on spectrum model according to claim 6, which is characterized in that describedly
In the merogenesis module of location, institute address section write-in participle library, and level is marked to number.
8. a kind of place name address storage system based on spectrum model according to claim 6, which is characterized in that the figure
Spectrum building module identifies address data structures at different levels by the numerical identity UID of 16 systems, passes through another field
UID, UID and the AddrLink field of addrLink mark next stage address section are stored in No. 1 node using hash index.
9. a kind of place name address storage system based on spectrum model according to claim 3, which is characterized in that the figure
Spectrum building module is established full-text index respectively and term indexes, be stored in using the Chinese of Name field recording address section
No. 2 nodes；Using Lev field record address level, value type is indexed using binary tree structure, is stored in No. 3 nodes；Address
The central point of spatial position uses Loc field record where section, establishes GeoHash index, is stored in No. 4 nodes.These are counted
Different nodes are used for from index type distributed storage according to according to field, are convenient for subsequent distributed computing.
10. a kind of place name address lookup system based on spectrum model characterized by comprising
Address dividing module segments address to be matched according to address layer grade, forms the address section of different address level；
It is classified enquiry module, according to the spatial dimension where the level of address section and address to be matched, is believed with address space
The matching of address section is carried out in the address section database of breath；
Evaluation of result module is ranked up matching result to the address calculation similarity score being matched to, and according to scoring；
Wherein, the address in the address section database is divided into several grades according to default rule, the data in addresses at different levels
The field for being directed toward next stage address data structure is built in structure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910373652.2A CN110147420A (en) | 2019-05-07 | 2019-05-07 | A kind of place name address matching querying method and system based on spectrum model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910373652.2A CN110147420A (en) | 2019-05-07 | 2019-05-07 | A kind of place name address matching querying method and system based on spectrum model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110147420A true CN110147420A (en) | 2019-08-20 |
Family
ID=67595038
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910373652.2A Pending CN110147420A (en) | 2019-05-07 | 2019-05-07 | A kind of place name address matching querying method and system based on spectrum model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110147420A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191084A (en) * | 2020-04-09 | 2020-05-22 | 速度时空信息科技股份有限公司 | Map structure-based place name address resolution method |
| CN112256821A (en) * | 2020-09-23 | 2021-01-22 | 北京捷通华声科技股份有限公司 | Method, device, equipment and storage medium for complementing Chinese address |
| CN114676353A (en) * | 2022-05-25 | 2022-06-28 | 武大吉奥信息技术有限公司 | Address matching method based on segmentation inference |
| CN112256821B (en) * | 2020-09-23 | 2024-05-17 | 北京捷通华声科技股份有限公司 | Chinese address completion method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104679867A (en) * | 2015-03-05 | 2015-06-03 | 深圳市华傲数据技术有限公司 | Address knowledge processing method and device based on graphs |
| CN106709065A (en) * | 2017-01-19 | 2017-05-24 | 国家电网公司 | Standardization processing method and standardized processing device for address information |
| US20170351733A1 (en) * | 2016-06-03 | 2017-12-07 | Facebook, Inc. | User address match based on match quality |
-
2019
- 2019-05-07 CN CN201910373652.2A patent/CN110147420A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104679867A (en) * | 2015-03-05 | 2015-06-03 | 深圳市华傲数据技术有限公司 | Address knowledge processing method and device based on graphs |
| US20170351733A1 (en) * | 2016-06-03 | 2017-12-07 | Facebook, Inc. | User address match based on match quality |
| CN106709065A (en) * | 2017-01-19 | 2017-05-24 | 国家电网公司 | Standardization processing method and standardized processing device for address information |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191084A (en) * | 2020-04-09 | 2020-05-22 | 速度时空信息科技股份有限公司 | Map structure-based place name address resolution method |
| CN112256821A (en) * | 2020-09-23 | 2021-01-22 | 北京捷通华声科技股份有限公司 | Method, device, equipment and storage medium for complementing Chinese address |
| CN112256821B (en) * | 2020-09-23 | 2024-05-17 | 北京捷通华声科技股份有限公司 | Chinese address completion method, device, equipment and storage medium |
| CN114676353A (en) * | 2022-05-25 | 2022-06-28 | 武大吉奥信息技术有限公司 | Address matching method based on segmentation inference |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019200752A1 (en) | Semantic understanding-based point of interest query method, device and computing apparatus | |
| CN104376053B (en) | A kind of storage and retrieval method based on magnanimity meteorological data | |
| CN109657074B (en) | News knowledge graph construction method based on address tree | |
| CN107145577A (en) | Address standardization method, device, storage medium and computer | |
| CN103853738B (en) | A kind of recognition methods of info web correlation region | |
| CN104375992A (en) | Address matching method and device | |
| CN104346438A (en) | Data management service system based on large data | |
| CN110472066A (en) | A kind of construction method of urban geography semantic knowledge map | |
| CN104252507B (en) | A kind of business data matching process and device | |
| CN103440311A (en) | Method and system for identifying geographical name entities | |
| CN106462624A (en) | Tile-based geocoder | |
| CN109446207A (en) | A kind of normal address database update method and address matching method | |
| CN109657063A (en) | A kind of processing method and storage medium of magnanimity environment-protection artificial reported event data | |
| CN103546326A (en) | Website traffic statistic method | |
| Tucci et al. | Using spatial analysis and geovisualization to reveal urban changes: Milan, Italy, 1737–2005 | |
| CN112528174A (en) | Address finishing and complementing method based on knowledge graph and multiple matching and application | |
| CN110147420A (en) | A kind of place name address matching querying method and system based on spectrum model | |
| CN114077674A (en) | Power grid dispatching knowledge graph data optimization method and system | |
| CN107463711A (en) | A kind of tag match method and device of data | |
| CN114417802A (en) | Intelligent report generation system | |
| CN106886517A (en) | Business site selecting method, device and system | |
| CN106682175A (en) | Method and system for matching address | |
| CN109522335B (en) | Information acquisition method and device and computer readable storage medium | |
| CN114201480A (en) | Multi-source POI fusion method and device based on NLP technology and readable storage medium | |
| CN107463559A (en) | A kind of business location information obtains analysis and storage system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190820 |