发明名称 |
PERSONALIZED RECOMMENDATION METHOD AND SYSTEM, AND COMPUTER-READABLE RECORD MEDIUM |
摘要 |
Provided is a method, system, and a computer-readable record medium for providing a personalized recommendation of products. The method of providing a personalized recommendation of products may include obtaining a first recommendation result using each of two or more single recommendation algorithms, performing a first performance evaluation, using a processor, with respect to the first recommendation result from each of the single recommendation algorithms, obtaining a second recommendation result based on the first recommendation result from each of the two or more single recommendation algorithms using a hybrid recommendation algorithm, the hybrid recommendation algorithms being different than each of the two or more single recommendation algorithms, performing a second performance evaluation, using the processor, with respect to the second recommendation result from the hybrid recommendation algorithm, and listing product recommendations after selecting a recommendation algorithm having a priority using the first performance evaluation and the second performance evaluation. |
申请公布号 |
US2016162974(A1) |
申请公布日期 |
2016.06.09 |
申请号 |
US201414563676 |
申请日期 |
2014.12.08 |
申请人 |
LG CNS CO., LTD. |
发明人 |
Lee Hwan Muk;Lee Dae Sik;Kim Byung Keug;Kim Soo Min;Park Min Yong;Song Han Yi;Lee Dong Yoon;Lee Yoon Jae |
分类号 |
G06Q30/06 |
主分类号 |
G06Q30/06 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method of providing a personalized recommendation of products, comprising:
obtaining a first recommendation result using each of two or more single recommendation algorithms; performing a first performance evaluation, using a processor, with respect to the first recommendation result from each of the single recommendation algorithms; obtaining a second recommendation result based on the first recommendation result from each of the two or more single recommendation algorithms using a hybrid recommendation algorithm, the hybrid recommendation algorithms being different than each of the two or more single recommendation algorithms; performing a second performance evaluation, using the processor, with respect to the second recommendation result from the hybrid recommendation algorithm; and listing product recommendations after selecting a recommendation algorithm having a priority using the first performance evaluation and the second performance evaluation. |
地址 |
Seoul KR |