http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-106534976-B

Outgoing Links

Predicate Object
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H04N21-4667
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H04N21-466
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H04N21-4532
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H04N21-6125
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H04N21-44213
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H04N21-44204
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/H04N21-442
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/H04N21-45
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/H04N21-466
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/H04N21-61
filingDate 2016-10-12-04:00^^<http://www.w3.org/2001/XMLSchema#date>
grantDate 2019-11-08-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationDate 2019-11-08-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-106534976-B
titleOfInvention The intelligent Forecasting method of user satisfaction in IPTV video traffic
abstract The invention proposes the intelligent Forecasting methods of user satisfaction in IPTV video traffic, need to model the defects of not accurate enough reasonable by subjectivity marking come internal association between measure user satisfaction and user satisfaction and its influence factor in existing user satisfaction prediction technique for solving.Implementing procedure of the invention are as follows: determine the factor for influencing user satisfaction first, then with user using business duration come objective measure user satisfaction, then CART tree-model is established by training, and data to be predicted are divided into relevant range with it, it is searched in the area with KNN, and finally uses distance weighted average value as prediction result.Using method of the invention, the operand that can be effectively reduced during prediction, and precision of prediction is highly improved.
priorityDate 2016-10-12-04:00^^<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/CID25572
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID415713197

Total number of triples: 20.