IP Library Granted Patent US 12,573,385
Granted Patent B2
US 12,573,385 · App. 17/442,024 · Granted Mar 10, 2026

Voice interaction method and electronic device

Inventors: Hongfeng Luo (Shenzhen, CN); Yuxi Zhao (Shenzhen, CN); Wen Zhang (Shenzhen, CN)
Assignee: HUAWEI TECHNOLOGIES CO., LTD.
G10L15/22G06F3/0482G06F3/167G06F9/453G06F16/3344G06F16/338G10L15/26G10L15/30G10L2015/223H04M1/725
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,573,385
App. No.
17/442,024
Granted
Mar 10, 2026
Kind
B2
Abstract

A voice interaction includes. displaying a first interface in response to an operation of waking up a voice assistant application; receiving first voice input of the user, where the first voice input includes first slot information; displaying a first card in the first interface, where the first card includes N candidate options of the first slot information, where the N candidate options are in a one-to-one correspondence with N query requests, and where each query request in the N query requests carries a corresponding candidate option of the first slot information; and in response to an operation of selecting a first candidate option from the N candidate options by the user, sending a first query request corresponding to the first candidate option to a first server.

Claims (62)

1 . A method comprising:

receiving a first operation of waking up a voice assistant application from a user;

displaying, in response to the first operation and in a foreground state, a first interface configured to display dialog content between the user and the voice assistant application;

receiving a first voice input from the user, wherein the first voice input comprises first slot information;

displaying, in response to the first voice input, a first card in the first interface, wherein the first card comprises N candidate options of the first slot information, wherein the N candidate options are in a first one-to-one correspondence with N query requests, wherein each query request in the N query requests carries a corresponding candidate option of the first slot information, and wherein N≥1;

receiving a second voice input from the user, wherein the second voice input comprises a screening condition for filtering the N candidate options;

displaying, in response to the second voice input, a second card in the first interface, wherein the second card comprises one or more candidate options that meet the screening condition, and wherein in response to detecting an interrupting event:

switching the voice assistant application from the foreground state to a background state;

continuing to run the voice assistant application in the background state;

automatically switching the voice assistant application from the background state back to the foreground state after the interrupting event ends; and

re-displaying the first interface including the second card;

receiving a second operation of selecting a first candidate option among the one or more candidate options in the second card from the user; and

sending, in response to the second operation, a first query request corresponding to the first candidate option to a first server to provide a service result corresponding to the first voice input.

2 . The method of claim 1 , further comprising receiving a third voice input that comprises the first candidate option.

3 . The method of claim 1 , wherein after receiving the first voice input from the user, the method further comprises:

sending the first voice input to the first server; and

receiving, in response to the first voice input, the first one-to-one correspondence from the first server.

4 . The method of claim 1 , further comprising receiving the first operation of waking up the voice assistant application when running the voice assistant application in foreground.

5 . The method of claim 1 , further comprising receiving a tapping operation on the first candidate option in the first card.

6 . The method of claim 1 , wherein the first voice input further comprises second slot information, and wherein the method further comprises displaying a third card in the first interface, wherein the third card comprises M candidate options of the second slot information, wherein the M candidate options are in a second one-to-one correspondence with M query requests, wherein the M query requests all carry the first candidate option from the user, wherein each query request in the M query requests carries a corresponding candidate option of the second slot information, and wherein M≥1.

7 . The method of claim 6 , further comprising receiving a third operation of selecting a second candidate option of the M candidate options from the user.

8 . The method of claim 7 , further comprising sending, in response to the third operation, a second query request corresponding to the second candidate option to the first server.

9 . The method of claim 7 , further comprising receiving a tapping operation on the second candidate option in the third card.

10 . The method of claim 7 , further comprising receiving a third voice input that comprises the second candidate option.

11 . An electronic device, comprising:

a memory configured to store instructions; and

a processor coupled to the memory and configured to execute the instructions to cause the electronic device to:

receive a first operation of waking up a voice assistant application from a user;

display, in response to the first operation and in a foreground state, a first interface configured to display dialog content between the user and the voice assistant application;

receive a first voice input from the user, wherein the first voice input comprises first slot information;

display, in response to the first voice input, a first card in the first interface, wherein the first card comprises N candidate options of the first slot information, wherein the N candidate options are in a first one-to-one correspondence with N query requests, wherein each query request in the N query requests carries a corresponding candidate option of the first slot information, and wherein N≥1;

receive a second voice input from the user, wherein the second voice input comprises a screening condition for filtering the N candidate options;

display, in response to the second voice input, a second card in the first interface, wherein the second card comprises one or more candidate options that meet the screening condition, and wherein in response to detecting an interrupting event:

switch the voice assistant application from the foreground state to a background state;

continue to run the voice assistant application in the background state;

automatically switch the voice assistant application from the background state back to the foreground state after the interrupting event ends; and

re-display the first interface including the second card;

receive a second operation of selecting a first candidate option among the one or more candidate options in the second card from the user; and

send, in response to the second operation, a first query request corresponding to the first candidate option to a first server to provide a service result corresponding to the first voice input.

12 . The electronic device of claim 11 , wherein the processor is further configured to execute the instructions to cause the electronic device to receive a third voice input that comprises the first candidate option.

13 . The electronic device of claim 11 , wherein the processor is further configured to execute the instructions to cause the electronic device to:

send the first voice input to the first server; and

receive, in response to the first voice input, the first one-to-one correspondence from the first server.

14 . The electronic device of claim 11 , wherein the processor is further configured to execute the instructions to cause the electronic device to receive a tapping operation on the first candidate option in the first card.

15 . A computer program product comprising computer-executable instructions stored on a non-transitory computer-readable storage medium that, when executed by one or more processors, cause an electronic device to:

receive a first operation of waking up a voice assistant application from a user;

display, in response to the first operation and in a foreground state, a first interface configured to display dialog content between the user and the voice assistant application;

receive a first voice input from the user, wherein the first voice input comprises first slot information;

display, in response to the first voice input, a first card in the first interface, wherein the first card comprises N candidate options of the first slot information, wherein the N candidate options are in a first one-to-one correspondence with N query requests, wherein each query request in the N query requests carries a corresponding candidate option of the first slot information, and wherein N≥1;

receive a second voice input from the user, wherein the second voice input comprises a screening condition for filtering the N candidate options;

display, in response to the second voice input, a second card in the first interface, wherein the second card comprises one or more candidate options that meet the screening condition, and wherein in response to detecting an interrupting event:

switch the voice assistant application from the foreground state to a background state;

continue to run the voice assistant application in the background state;

automatically switch the voice assistant application from the background state back to the foreground state after the interrupting event ends; and

re-display the first interface including the second card;

receive a second operation of selecting a first candidate option among the one or more candidate options in the second card from the user; and

send, in response to the second operation, a first query request corresponding to the first candidate option to a first server to provide a service result corresponding to the first voice input.

16 . The computer program product of claim 15 , wherein the computer-executable instructions that, when executed by the one or more processors, cause the electronic device to receive a third voice input that comprises the first candidate option.

17 . The computer program product of claim 15 , wherein the computer-executable instructions that, when executed by the one or more processors, cause the electronic device to receive a tapping operation on the first candidate option in the first card.

18 . The computer program product of claim 15 , wherein the interrupting event comprises receiving an incoming call.

19 . The computer program product of claim 15 , wherein the interrupting event comprises opening a notification message.

20 . The computer program product of claim 15 , wherein the interrupting event comprises tapping a back button or a home button.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 23, 2024
From: LUO, HONGFENG; ZHAO, YUXI; ZHANG, WEN
To: HUAWEI TECHNOLOGIES CO., LTD.
Reel/Frame 066544/0825 →
Priority Claims (1)
CN 201910224332.0 · Mar 22, 2019 · national
Continuity (1)
Related Publication 20220172717A1 · Jun 2, 2022
References Cited (27)
US 9558740B1 · Mairesse et al. · 2017 [cited by applicant]
US 10741185B2 · Gruber · 2020 [cited by examiner]
US 20040172258A1 · Dominach et al. · 2004 [cited by applicant]
US 20120265528A1 · Gruber · 2012 [cited by examiner]
US 20130073286A1 · Bastea-Forte et al. · 2013 [cited by applicant]
US 20140040748A1 · Lemay · 2014 [cited by examiner]
US 20150154953A1 · Bapat et al. · 2015 [cited by applicant]
US 20160150020A1 · Farmer et al. · 2016 [cited by applicant]
US 20160371800A1 · Kirshenboim · 2016 [cited by examiner]
US 20170068423A1 · Napolitano · 2017 [cited by examiner]
US 20180196683A1 · Radebaugh · 2018 [cited by examiner]
US 20180307761A1 · Felt · 2018 [cited by examiner]
US 20180308485A1 · Kudurshian et al. · 2018 [cited by applicant]
US 20180336894A1 · Graham · 2018 [cited by examiner]
US 20180336897A1 · Aggarwal · 2018 [cited by examiner]
US 20190304461A1 · Pan · 2019 [cited by examiner]
US 20200074993A1 · Lee · 2020 [cited by examiner]
US 20220172717A1 · Luo · 2022 [cited by examiner]
CN 103888600A · 2014 [cited by applicant]
CN 105448293A · 2016 [cited by applicant]
CN 106445940A · 2017 [cited by applicant]
CN 107193396A · 2017 [cited by applicant]
CN 107318036A · 2017 [cited by applicant]
CN 107680589A · 2018 [cited by applicant]
WO 2018213319A1 · 2018 [cited by applicant]
ITU-T H.264 “Series H: Audiovisual and Multimedia Systems, Infrastructure of audiovisual services—Coding of moving video, Advanced video coding for generic audiovisual services,” Apr. 2017, 812 pages. [cited by applicant]
Kwang B. Lee et al: “The Design and Development of User Interfaces for Voice Application in Mobile Devices”, International Professional Communication Conference, IEEE, PI, Oct. 1, 2006, 13 pages. [cited by applicant]