# US 2013/0156324 A1 · Geographical location rendering system and method and computer readable recording medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2013/0156324 A1 - Document ID: US20130156324A1 - Status: Published application - Kind: A1 - Application number: 13/604,278 - Filed: 2012-09-05 - Published: 2013-06-20 - Earliest claimed: 2011-12-15 - Assignees: Industrial Technology Research Institute - Inventors: Wen Tsui; Tai-Ting Wu; Shin-Yi Wu; Yu-Hsiang Hsiao - Web page: https://patentgrep.com/patent/US20130156324A1 ## CPC - G06F 16/9537: Spatial or temporal dependent retrieval, e.g. spatiotemporal queries - G06N 5/02: Knowledge representation; Symbolic representation - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A geographical location rendering method executed in a geographical location rendering system for identifying at least one semantic region is provided. A density clustering is performed on a plurality of user generated contents of respective geographical location name information to generate a plurality of region candidates. A name extraction is performed on the region candidates to extract and confirm a common region name of the region candidates as a name of the semantic region. A region scope of the region candidates is detected as a location scope of the semantic region according to a spatial density analysis. ## Claims ### Claim 1 A geographical location rendering method, executed in a geographical location rendering system for identifying a semantic region, the geographical location rendering method comprising: performing a density clustering on a plurality of user generated contents having respective information of geographical location name, to generate a plurality of region candidates; performing a name extraction on the region candidates respectively, to extract and confirm a common region name of the region candidates as a name of the semantic region; and detecting a region scope of the region candidates as a location scope of the semantic region according to a spatial density analysis. ### Claim 2 (depends on 1) The method according to claim 1, wherein the step of performing the name extraction on a region candidate comprises: attempting to obtain a possible name for the region candidate. ### Claim 3 (depends on 2) The method according to claim 2, wherein the step of performing the name extraction comprises: determining whether the possible name of the region candidate is obtained; when no possible name is obtained, adjusting an extraction criterion; and when the extraction criterion is non-adjustable, determining the name extraction as failed and discarding the region candidate. ### Claim 4 (depends on 3) The method according to claim 3, wherein the step of performing the name extraction comprises: confirming whether the possible name passes. ### Claim 5 (depends on 4) The method according to claim 4, wherein the step of performing the name extraction comprises: when the user generated contents in the region candidate are concentrated, determining that the possible name passes confirmation; when the user generated contents in the region candidate are dispersed, determining that the possible name fails confirmation; adjusting the extraction criterion when the possible name fails in confirmation; and determining the step of name extraction as failed and discarding the region candidate when the extraction criterion is non-adjustable. ### Claim 6 (depends on 3) The method according to claim 3, wherein the step of performing the name extraction comprises: when adjusting the extraction criterion, a strictness for the extraction criterion is gradually lowered till a reaching a lowest strictness for the extraction criterion. ### Claim 7 (depends on 6) The method according to claim 6, wherein the step of detecting the region scope comprises: for the region candidates passed the name extraction and having the same name, selecting one of the region candidates having a highest name density of the region candidates as a core region of the semantic region; wherein, a name density represents a percentage occupied by the user generated contents having the same name out of a total number of the user generated contents. ### Claim 8 (depends on 7) The method according to claim 7, wherein the step of detecting the region scope comprises: for the region candidates passed the name extraction and having the same name, determining an outermost periphery region jointly formed by the region candidates as a periphery region of the semantic region. ### Claim 9 (depends on 8) The method according to claim 8, wherein the step of detecting the region scope comprises: integrating the core region and the periphery region to a map information to determine the location scope of the semantic region. ### Claim 10 (depends on 1) The method according to claim 1, wherein the step of detecting the region scope comprises: determining a relation among the region candidates to collectively perform the name extraction on the region candidates having the relation. ### Claim 11 (depends on 10) The method according to claim 10, wherein when performing the name extraction on the region candidates having the relation, the step of the name extraction comprises: determining whether an individual name is extracted respectively for the region candidates; and determining whether the individual names of region candidates are the same. ### Claim 12 (depends on 11) The method according to claim 11, wherein a common name is obtained for the region candidates through the relation among the region candidates, and an outermost periphery region formed by the region candidates is the location scope of the semantic region. ### Claim 13 (depends on 1) The method according to claim 1, wherein when a new user generated content falls in the semantic region, the step of detecting the region scope is again performed on the semantic region. ### Claim 14 (depends on 1) The method according to claim 1, wherein when a new user generated content falls in unnamed region candidates of the region candidates, the step of performing the name extraction and the step of detecting the location scope are again performed on the unnamed region candidates. ### Claim 15 (depends on 1) The method according to claim 1, wherein when a new user generated content does not fall in any of the region candidates, the method further comprising: performing the density clustering on a region of the new user generated content to generate at least one new region candidate; performing the name extraction step on the at least one new region candidate; and performing the step of detecting the location scope on the region candidates having the same name as the at least one new region candidate. ### Claim 16 A geographical location rendering system, for identifying a semantic region, comprising: a density clustering module, for performing a density clustering on a plurality of user generated contents having respective information of geographical location name to generate a plurality of region candidates; a name extraction module, for performing a name extraction on the region candidates respectively, to extract and confirm a common region name of the region candidates as a name of the semantic region; and a region scope detecting module, for performing a region scope detection on the region candidates as a location scope of the semantic region according to a spatial density analysis. ### Claim 17 (depends on 16) The system according to claim 16, wherein: the name extraction module attempts to obtain a possible name for a region candidate of the region candidates; the name extraction module determines whether the possible name of the region candidate is obtained; when no possible name is obtained, the name extraction module adjusts an extraction criterion; when the extraction criterion is non-adjustable, the name extraction module determines the name extraction as failed and discards the region candidate; the name extraction module confirms whether the possible name passes; when the user generated contents in the region candidate are concentrated, the name extraction module determines the possible name passes confirmation; when the user generated contents in the region candidate are dispersed, the name extraction module determines the possible name fails confirmation; the name extraction module adjusts the extraction criterion when the possible name fails confirmation; and the name extraction module determines the name extraction as failed and discards the region candidate when the extraction criterion is non-adjustable; wherein, when adjusting the extraction criterion, a strictness for the extraction criterion is gradually lowered till a reaching a lowest strictness of the extraction criterion. ### Claim 18 (depends on 17) The system according to claim 17, wherein: for the region candidates having passed the name extraction and having the same name, the region scope detecting module selects one of the region candidates having a highest name density of the region candidates as a core region of the semantic region; a name density represents a percentage occupied by the user generated contents having the name out of a total number of the user generated contents; for the region candidates passed the name extraction and having the same name, the region scope detecting module determines an outermost periphery region jointly formed by the region candidates as a periphery region of the semantic region; and the region scope detecting module integrates the core region and the periphery region to a map information to determine the location scope of the semantic region. ### Claim 19 (depends on 18) The system according to claim 18, wherein: the region scope detecting module determines a relation among the region candidates to collectively perform the name extraction on the region candidates having the relation; and when the name extraction is collectively performed on the region candidates having the relation, the name extraction module determines whether an individual name is extracted respectively for the region candidates, and determines whether the individual names of region candidates are the same. ### Claim 20 (depends on 19) The system according to claim 19, wherein a common name is obtained for the region candidates through the relation among the region candidates, and the outermost periphery region formed by the region candidates is the location scope of the semantic region. ### Claim 21 (depends on 16) The system according to claim 16, wherein: when a new user generated content falls in the semantic region, the region scope detection is again performed on the semantic region; when the new user generated content falls in unnamed region candidates of the region candidates, the name extraction and the region scope detection are again performed on the unnamed region candidates; and when a new user generated content does not fall in any of the region candidates, the density clustering is performed on a region of the new user generated content to generate at least one new region candidate, the name extraction is performed on the at least one new region candidate, and the region scope detection is again performed on the region candidates having the same name as the at least one new region candidate. ### Claim 22 (depends on 1) A computer readable recording medium for storing a program, capable of implementing a method according to claim 1 after the program is loaded on a computer and is executed.