Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
5469769 | Procedia CIRP | 2016 | 5 Pages |
Abstract
This paper presents a Chinese topic crawler focused on customer development, in order to meet the needs of users for more accurate and particular Internet information. The concept of meta-search engine is introduced, and the keywords are expanded by the ontology of HowNet. Through the web crawler, preprocessing and classification, the information on customer relations can be divided into three categories: company, platform and meaningless. Numerical experiments show that satisfactory results can be obtained in some particular information-seeking areas. The average accuracy for classification is more than 80%, which can meet customer needs in most cases.
Related Topics
Physical Sciences and Engineering
Engineering
Industrial and Manufacturing Engineering
Authors
Tong Wu, Yanchun Liang, Chunguo Wu, Shifeng Piao, Deyin Ma, Guozhong Zhao, Xiaosong Han,