http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111198950-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-288 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-367 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F40-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F40-284 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F16-28 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F16-36 |
| filingDate | 2019-12-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2021-10-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2021-10-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-111198950-B |
| titleOfInvention | A Knowledge Graph Representation Learning Method Based on Semantic Vectors |
| abstract | A method for learning knowledge graph representation based on semantic vector, comprising the following steps: 1) building a semantic vector by merging a text corpus; 2) building a semantic vector by merging a text corpus and a context of a knowledge graph; 3) building a semantic matrix, the process is as follows: Taking the semantic vector of triples and relations as input, the semantic matrix corresponding to each relation is obtained; 4) Modeling and training, the process is as follows: A new scoring function is designed to build the embedding representation of entities and relations in the knowledge graph. to obtain the embedded representation model of the knowledge graph; use the stochastic gradient descent method to train the embedded representation model to minimize the value of the loss function to obtain the semantic vectors of entities and relationships in the final knowledge graph. The representation learning cube proposed by the present invention can relatively model the complex relationship of the knowledge graph, and can improve the accuracy of vector representation. |
| priorityDate | 2019-12-24-04:00^^<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/SID419591226 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID3824 |
Total number of triples: 18.