http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114676353-B

Outgoing Links

Predicate Object
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-047
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-048
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-042
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-9537
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N5-041
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F16-9537
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N5-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
filingDate 2022-05-25-04:00^^<http://www.w3.org/2001/XMLSchema#date>
grantDate 2022-10-18-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationDate 2022-10-18-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-114676353-B
titleOfInvention An Address Matching Method Based on Segmentation Inference
abstract The invention is applicable to the technical field of urban governance systems, and provides an address matching method based on segmented inference. During implementation, three ESIM inference models and three pointer networks are first trained, and key addresses and standard addresses are divided into three sub-elements. Including regional elements, building elements and road code elements, and using the ESIM inference model to match the sub-elements, and finally according to the matching results of the three sub-elements, comprehensively judge whether the address matches. Compared with the existing address matching methods based on deep learning, the method of the invention reduces the sensitivity to the address length, increases the sensitivity to numbers, and improves the matching accuracy.
priorityDate 2022-05-25-04:00^^<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/compound/CID165166
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID452858641

Total number of triples: 21.