http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109447658-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_3bffc478d0bb2aacde9a141354d700b1 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06Q30-0185 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06Q40-08 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06Q30-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06Q40-08 |
filingDate | 2018-09-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_be87b8918553f9f227b3be74891fe12d |
publicationDate | 2019-03-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-109447658-A |
titleOfInvention | Anti-fraud model generation and application method, device, device and storage medium |
abstract | The invention discloses a method and a device, a device and a storage medium for generating and applying an anti-fraud model. The generating method comprises: obtaining a historical data set from the insurance claim database, the historical data set includes a training data set and a test data set; generating a training target social network map according to the training data set; and acquiring the SDEE algorithm according to the training target social network map An objective function, the objective function is used as a first objective function; constructing a second objective function according to the first objective function and a preset constraint; acquiring an optimal super parameter of the second objective function, and using the optimal super parameter as a known quantity Adding to the second objective function to generate an optimal objective function; and training the optimal objective function with the training target social network map to generate an anti-fraud model. By implementing the solution, the problem of identifying claim fraud in the prior art needs to rely on manually defining user behavior characteristics and not considering the local and global structure in the social network. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110490750-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110490750-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110147389-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110147389-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111143684-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111143684-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111447179-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110263106-A |
priorityDate | 2018-09-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 27.