公开(公告)号：US10044862B1

公开(公告)日：2018-08-07

申请号：US15581798

申请日：2017-04-28

Applicant: International Business Machines Corporation

Inventor： Keke Cai ,  Jing Ding ,  Li Zhang ,  Shiwan Zhao ,  Zhong Su

IPC: H04M3/00 ,  H04M5/00 ,  H04M3/51 ,  G06Q10/06 ,  G06N3/08 ,  G10L25/63 ,  G10L15/18 ,  G10L25/87

Abstract: A topic guidance method, system, and computer program product for creating a conversation model by learning a conversation pattern from a customer response to a conversation topic segment and suggesting a conversation topic for the agent to engage the customer in the conversation topic based on a customer response associated with the conversation model.

公开(公告)号：US20190205753A1

公开(公告)日：2019-07-04

申请号：US16286917

申请日：2019-02-27

Applicant: International Business Machines Corporation

Inventor： Keke Cai ,  Jing Ding ,  Li Zhang ,  Shiwan Zhao ,  Zhong Su

IPC: G06N3/08 ,  G06F17/27 ,  H04M3/51 ,  G06Q10/06

Abstract: A topic guidance method, system, and computer program product for suggesting, via a processor on a computer, a conversation topic for the agent to engage the customer based on a learned conversation topic model, the conversation model being a static model.

公开(公告)号：US10296830B2

公开(公告)日：2019-05-21

申请号：US15955882

申请日：2018-04-18

Applicant: International Business Machines Corporation

Inventor： Keke Cai ,  Jing Ding ,  Li Zhang ,  Shiwan Zhao ,  Zhong Su

IPC: H04M3/00 ,  H04M5/00 ,  G06N3/08 ,  G06Q10/06 ,  G06F17/27 ,  H04M3/51 ,  G10L25/63

Abstract: A topic guidance method, system, and computer program product for creating a conversation model by learning a conversation pattern from a customer response to a conversation topic segment and suggesting a conversation topic for the agent to engage the customer in the conversation topic based on a customer response associated with the conversation model.

公开(公告)号：US20190121853A1

公开(公告)日：2019-04-25

申请号：US15793227

申请日：2017-10-25

Applicant: International Business Machines Corporation

Inventor： Ke Ke Cai ,  Jing Ding ,  Zhong Su ,  Chang Hua Sun ,  Li Zhang ,  Shi Wan Zhao

IPC: G06F17/27 ,  G06N3/08 ,  G06N3/04

Abstract: Techniques are provided for training, by a system operatively coupled to a processor, an attention weighted recurrent neural network encoder-decoder (AWRNNED) using an iterative process based on one or more paragraphs of agent sentences from respective transcripts of one or more conversations between one or more agents and one or more customers, and based on one or more customer response sentences from the respective transcripts, and generating, by the system, one or more groups respectively comprising one or more agent sentences and one or more customer response sentences selected based on attention weights of the AWRNNED.