发明名称 |
Automatic task classification based upon machine learning |
摘要 |
A system and method is provided that processes a training database of human-generated requests in each of a plurality of task categories with a machine learning algorithm to develop a task classifier model that may be applied to subsequent user requests to determine the most likely one of the task categories for the subsequent user request. |
申请公布号 |
US9471887(B2) |
申请公布日期 |
2016.10.18 |
申请号 |
US201514871595 |
申请日期 |
2015.09.30 |
申请人 |
NTT DOCOMO Inc. |
发明人 |
Shin Hyung Sik;Sujithan Ronald;Mukherjee Sayandev;Yin Hongfeng;Sun Yang;Akinaga Yoshikazu;Subasic Pero |
分类号 |
G06N99/00;G06F15/18;G10L15/00;G10L15/18;G06F17/30;G06F9/48;G10L15/06 |
主分类号 |
G06N99/00 |
代理机构 |
Haynes and Boone, LLP |
代理人 |
Haynes and Boone, LLP |
主权项 |
1. A machine-implemented method, comprising:
requesting a plurality of users to generate human-generated user requests for each of a plurality of task categories to collect a plurality of the human-generated user requests to create a training database of user requests, each user request corresponding uniquely to one of the task categories; for each task category, extracting a training feature vector from each corresponding user request in the training database by assigning a numeric value to each different word in the corresponding user request to form a training data set having a plurality of training feature vectors for each task category; for each task category, processing the training feature vectors in the training data set corresponding to the task category to determine a task classifier model for the task category; receiving an additional request from a user, the additional request being classifiable into one of the task categories; and in the machine, comparing an extracted feature vector from the additional request to the task classifier model to identify which task category corresponds to the additional request. |
地址 |
Tokyo JP |