公开(公告)号：US20120076283A1

公开(公告)日：2012-03-29

申请号：US13239195

申请日：2011-09-21

Applicant: Dinesh AJMERA ,  Debashish Panda ,  Pankai Ghanshani ,  Sumit Kumar ,  Ravi Vijayaraghavan ,  Mathangi Sri Ramachandran

Inventor： Dinesh AJMERA ,  Debashish Panda ,  Pankai Ghanshani ,  Sumit Kumar ,  Ravi Vijayaraghavan ,  Mathangi Sri Ramachandran

IPC: H04M11/00

CPC classification number: G06N5/04 ,  G06N3/006 ,  G06N20/00 ,  G06Q10/10 ,  G06Q30/016 ,  G06Q30/0202 ,  H04L12/1827 ,  H04L51/02 ,  H04L51/04 ,  H04M3/5183

Abstract: A mechanism for facilitating customer interactions within a customer service environment provides prompt and accurate answers to customer questions. A smart chat facility for use in a customer service environment to predict a customer problem examines a customer chat transcript to identify customer statements that set forth a customer issue and, responsive to this, can route the customer to an agent, an appropriate FAQ, or can implement a problem specific widget in the customer UI. Customer queries are matched with most correct responses and accumulated knowledge is used to predict a best response to future customer queries. The iterative system thus learns from each customer interaction and can adapt to customer responses over time to improve the accuracy of problem prediction.

Abstract translation: 促进客户服务环境中的客户交互的机制可以提供客户问题的即时和准确的答案。 在客户服务环境中用于预测客户问题的智能聊天设施检查客户聊天记录，以识别出客户问题的客户声明，并且响应于此可将客户路由到代理，适当的常见问题解答或 可以在客户界面中实现特定于问题的小部件。 客户查询与最正确的答案匹配，积累的知识用于预测未来客户查询的最佳响应。 因此，迭代系统从每个客户交互中学习，并可随时间适应客户响应，以提高问题预测的准确性。