http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109697630-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06Q30-0201 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-28 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06Q30-0202 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06Q30-02 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
filingDate | 2018-11-21-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2020-08-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2020-08-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-109697630-B |
titleOfInvention | A multi-factor analysis and prediction method of merchant traffic flow based on sparse regression |
abstract | The invention relates to a sparse regression multi-factor analysis and prediction method of merchant passenger flow, comprising the steps of: step 1, preprocessing historical passenger flow data; step 2, construction of a multi-factor dictionary of merchant passenger flow; step 3, solution and prediction of sparse coefficients . The beneficial effects of the invention are: the multi-factor sparse regression prediction method proposed by the invention is obviously better than other comparative prediction methods; compared with the sparse regression model without additional factors, the prediction effect of the multi-factor sparse regression prediction method is improved When the error is 0.2 and 0.3, the multi-factor sparse regression prediction method has a 10%-50% increase in the number of merchants compared with other methods; the training time and prediction of the sparse regression model and the multi-factor sparse regression model The time is far less than the other two models; the performance of the multi-factor sparse regression prediction model proposed by the present invention is more superior. |
priorityDate | 2018-11-21-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 25.