US 12,039,976 B2
Man- machine interaction system and multi-task processing method in the man-machine interaction system
Yingtao Li, Shenzhen (CN); Xin Jiang, Hong Kong (CN); Xiao Chen, Hong Kong (CN); Baofeng Zhang, Shenzhen (CN); and Li Qian, Shenzhen (CN)
Assigned to HUAWEI TECHNOLOGIES CO., LTD., Guangdong (CN)
Filed by HUAWEI TECHNOLOGIES CO., LTD., Guangdong (CN)
Filed on Feb. 9, 2021, as Appl. No. 17/171,166.
Application 17/171,166 is a continuation of application No. PCT/CN2019/122544, filed on Dec. 3, 2019.
Claims priority of application No. 201811489837.1 (CN), filed on Dec. 6, 2018.
Prior Publication US 2021/0166693 A1, Jun. 3, 2021
Int. Cl. G10L 15/22 (2006.01); G06F 40/35 (2020.01); G10L 15/16 (2006.01); G10L 15/18 (2013.01); G06F 40/30 (2020.01)
CPC G10L 15/22 (2013.01) [G06F 40/35 (2020.01); G10L 15/16 (2013.01); G10L 15/1815 (2013.01); G06F 40/30 (2020.01); G10L 2015/223 (2013.01); G10L 2015/227 (2013.01); G10L 2015/228 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A multi-task processing method in a man-machine interaction system, the method comprising:
determining a first task based on request information entered by a user;
obtaining key information corresponding to the first task, wherein the key information comprises one or more slots and values of the one or more slots;
executing the first task;
storing task status information of the first task comprising the key information; and
predicting and initiating a second task based on the task status information of the first task, wherein predicting the second task comprises:
predicting, based on an implicit status vector ht, the second task, wherein ht=f(Wxxt+Wzzt+Whht-1+b), f is a transformation function, xt is a task status information vector, zt is an environment information vector, ht-1 is a historical implicit status vector, Wx, Wz and Wh are parameter matrices, and b is a parameter vector.