公开(公告)号：US11227342B2

公开(公告)日：2022-01-18

申请号：US16616842

申请日：2017-05-26

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Xianchao Wu ,  Katsuya Iida

IPC: G06Q50/00 ,  G06F16/9535 ,  G06F16/901 ,  H04L12/58 ,  H04L29/06

Abstract: The present disclosure provides method and apparatus for recommending friends in automated chatting. A message is received from a user in a chat flow. An intention of looking for friends is identified from the message. One or more recommended friends are identified based on a topic knowledge graph. The recommended friends are provided in the chat flow.

公开(公告)号：US11093711B2

公开(公告)日：2021-08-17

申请号：US15433162

申请日：2017-02-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Katsuya Iida ,  Momo Klyen ,  Keizo Fujiwara ,  Xianchao Wu ,  Zhan Chen

IPC: G06F40/253 ,  G06N5/02 ,  G06N20/00 ,  G06K9/62 ,  G06F16/9032 ,  G06F16/2457 ,  G06K9/00

Abstract: The present disclosure is directed to systems, methods and devices for providing artificial intelligence (AI) entity-specific feedback. Official content related to an entity or entity figure may be extracted and analyzed. The extracted content may be classified in an entity corpus based on a determined language style of the content. An input into a conversational AI system may be received. A plurality of potential responses related to the input may be determined from one or more entity corpus. Each of the plurality of potential responses may be ranked according to a rank match value calculated for each of the plurality of determined responses, and at least one of potential responses may be provided as feedback.

公开(公告)号：US20180089164A1

公开(公告)日：2018-03-29

申请号：US15433162

申请日：2017-02-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Katsuya Iida ,  Momo Klyen ,  Keizo Fujiwara ,  Xianchao Wu ,  Zhan Chen

IPC: G06F17/27 ,  G06N99/00 ,  G06N5/02

CPC classification number: G06F17/274 ,  G06F16/24578 ,  G06F16/90332 ,  G06N5/022 ,  G06N20/00

Abstract: The present disclosure is directed to systems, methods and devices for providing artificial intelligence (AI) entity-specific feedback. Official content related to an entity or entity figure may be extracted and analyzed. The extracted content may be classified in an entity corpus based on a determined language style of the content. An input into a conversational AI system may be received. A plurality of potential responses related to the input may be determined from one or more entity corpus. Each of the plurality of potential responses may be ranked according to a rank match value calculated for each of the plurality of determined responses, and at least one of potential responses may be provided as feedback.