http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110162594-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_31565373c08678b1a7e68d5a1e4c5878 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F40-295 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F17-27 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F16-33 |
filingDate | 2019-01-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_40debd950aaf35cab3424d9beb6e1c1f |
publicationDate | 2019-08-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-110162594-A |
titleOfInvention | Method, device and electronic device for opinion generation of text data |
abstract | Embodiments of the present invention provide a text data opinion generation method, device and electronic equipment. The viewpoint generation method of the text data includes: obtaining target text data to be processed; extracting a first viewpoint of the target text data through a supervised machine learning model, and mining a second viewpoint of the target text data based on an unsupervised algorithm; According to the relationship between the characters contained in the first viewpoint and the characters contained in the second viewpoint, determine the candidate evaluation topics and candidate viewpoint contents of the target text data; according to the candidate evaluation topics and the candidate opinion content, generating an opinion of the target text data. The technical solution of the embodiment of the present invention can not only make full use of supervised methods to accurately identify the views of text data, but also effectively alleviate the problems of low recall rate and slow iterative processing of supervised methods through unsupervised algorithms, and improve the text data views. recognition accuracy and recognition efficiency. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111160035-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111160035-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115496039-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112434510-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111078875-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111428492-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111428492-B |
priorityDate | 2019-01-04-04:00^^<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/SID415789328 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID90787 |
Total number of triples: 22.