US 12,073,334 B2
Human-computer dialogue method and apparatus
Lifeng Shang, Hong Kong (CN); Zhengdong Lu, Shenzhen (CN); and Hang Li, Shenzhen (CN)
Assigned to HUAWEI TECHNOLOGIES CO., LTD., Shenzhen (CN)
Filed by Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed on Jan. 18, 2022, as Appl. No. 17/577,713.
Application 17/577,713 is a continuation of application No. 16/514,683, filed on Jul. 17, 2019, granted, now 11,308,405.
Application 16/514,683 is a continuation of application No. PCT/CN2018/072630, filed on Jan. 15, 2018.
Claims priority of application No. 201710030361.4 (CN), filed on Jan. 17, 2017.
Prior Publication US 2022/0147848 A1, May 12, 2022
Int. Cl. G06N 5/043 (2023.01); G06F 16/33 (2019.01); G06F 16/332 (2019.01); G06F 40/35 (2020.01); G10L 13/08 (2013.01); G10L 15/22 (2006.01); H04L 51/02 (2022.01)
CPC G06N 5/043 (2013.01) [G06F 16/3329 (2019.01); G06F 16/3344 (2019.01); G06F 40/35 (2020.01); G10L 13/08 (2013.01); G10L 15/22 (2013.01); H04L 51/02 (2013.01); G10L 2015/225 (2013.01); G10L 2015/228 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A human-computer dialogue method performed by a human-computer dialogue apparatus that is pre-equipped with a plurality of dialogue robots, wherein each dialogue robot is configured to conduct a human-computer dialogue based on at least one topic, and wherein the human-computer dialogue method comprises:
obtaining text entered by a user;
determining at least one first topic related to the text;
determining a target dialogue robot from the plurality of dialogue robots based on the at least one first topic and a predefined mapping relationship between a dialogue robot and a topic, wherein a target topic corresponding to the target dialogue robot is some or all of the at least one first topic;
allocating, based on determining the target dialogue robot, the text to the target dialogue robot; and
obtaining a reply for the text from the target dialogue robot, wherein the reply is generated by the target dialogue robot based on at least one semantic understanding of the text, and wherein the at least one semantic understanding has a one-to-one correspondence with the target topic.