发明名称 |
CROSS-DOMAIN ADAPTATION USING BLOOM FILTERS |
摘要 |
A system for cross-domain adaptation includes an analysis module, a set configuration module, a set multiplexer, a scalable bloom filter, a mapping module, and an aggregation module. The cross-domain adaptation system may allow for bloom filter adaptation across industries and domains with minimal increases in necessary hardware and consequentially minimal increases in power consumption and cost of area. A method for multi-domain adaptation in datasets includes performing multi-domain semantic analysis on a set of data, providing two complementary domain adaptive sets, processing the complementary domain adaptive sets to provide a multi-fractal representation of the dataset, processing the multi-fractal representation of the dataset with a scalable bloom filter to provide two filtered domain adaptive sets, providing a bijective holomorphic map of the filtered domain adaptive sets, and processing the bijective holomorphic map to provide multi-domain insight aggregator output. A computer program product corresponding to the method is also disclosed. |
申请公布号 |
US2016328382(A1) |
申请公布日期 |
2016.11.10 |
申请号 |
US201514704103 |
申请日期 |
2015.05.05 |
申请人 |
International Business Machines Corporation |
发明人 |
Alex Gokul B.;Ananthapur Bache Vijay Kumar;Joseph Joyil;Mantripragada Nagesh K.;Patil Madhusmita P.;Vasudevan Rengia R. |
分类号 |
G06F17/27 |
主分类号 |
G06F17/27 |
代理机构 |
|
代理人 |
|
主权项 |
1. A computer system, comprising:
one or more computer processors; one or more computer-readable storage media; program instructions stored on the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising instructions to: perform multi-domain semantic analysis on a dataset; process semantic information for the dataset to provide two complementary domain adaptive sets corresponding to the dataset; process the two complementary domain adaptive sets to provide a multi-fractal representation of the dataset; process the multi-fractal representation of the dataset to provide two filtered domain adaptive sets; process the filtered domain adaptive sets to provide a bijective holomorphic map of the two filtered domain adaptive sets; and process the bijective holomorphic map to provide a multi-domain insight aggregator corresponding to the dataset. |
地址 |
Armonk NY US |