http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20200083159-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_8d0fc2b70675ee19bd5fc464f5ae9061 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-587 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-532 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-36 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F16-36 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F16-587 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F16-532 |
filingDate | 2019-08-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_584fe5f76d7af1513a353dd9fce81c9d http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2d2aa3ce77e44c2bed28fec510124d4c http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5bdd48bc3a5d42d17e44c8b7aa9c6c2a http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5c9dc0145e8f3d7b8068642fbf30c779 |
publicationDate | 2020-07-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | KR-20200083159-A |
titleOfInvention | Method and system for searching picture on user terminal |
abstract | The present invention relates to a photo search method and system in a user terminal, in a photo search method in a user terminal performed by a photo search system for providing a photo search result according to a user's intention, a) a user query is input Converting the corresponding user query into a query word vector, and extracting the query semantic topic by applying the query word vector to a predefined topic classification tree based on an Open Directory Project (ODP); b) Analyzing object information and location information for each photo in the photo storage where one or more pictures are stored, extracting word vectors from the analyzed object information and location information, and combining the extracted word vectors to integrate word vectors Calculating, and extracting a photo semantic topic by applying the integrated word vector to the topic classification tree; And c) subject similarity is calculated through subject analysis between the query semantic topic and the photo semantic topic, and pictures having the highest subject similarity among the calculated subject similarities are extracted as a photo search result for the user query. And providing steps. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2023018150-A1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112328819-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112328819-A |
priorityDate | 2018-12-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419559532 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID24404 |
Total number of triples: 23.