IP Library Granted Patent US 11,922,935
Granted Patent B2
US 11,922,935 · App. 17/179,764 · Granted Mar 5, 2024

Voice interaction method and apparatus, terminal, and storage medium

Inventors: Zijuan Shi (Shanghai, CN); Weiran Nie (Shanghai, CN)
Assignee: HUAWEI TECHNOLOGIES CO., LTD.
G10L15/22G10L15/1815
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 11,922,935
App. No.
17/179,764
Granted
Mar 5, 2024
Kind
B2
Abstract

A voice interaction method, where a service type set on which a user has a voice interaction intention is predicted based on a target event that can trigger voice interaction, and when a service type of a first service expressed by a voice instruction is a target service type in the service type set, the first service is executed.

Claims (120)

1. A voice interaction method, comprising:

detecting a target event that can trigger a voice interaction;

querying, based on the target event, a mapping relationship to obtain a service type set and a first probability corresponding to a first target service type, wherein the first probability indicates a possibility of executing a first service corresponding to the first target service type;

collecting a voice instruction comprising semantic information;

obtaining, based on the semantic information, a second service corresponding to the semantic information;

executing the second service according to the voice instruction when a first service type of the second service is the first target service type;

filtering out, from the service type set, a second target service type comprising a second probability that does not meet a probability threshold before executing the second service and when the first service type is the first target service type;

updating, based on the semantic information, a third probability in the mapping relationship;

increasing a fourth probability corresponding to the first service type in the mapping relationship when the first service type is the first target service type;

decreasing the first probability when the first service type is different from the first target service type; and

increasing the fourth probability when the semantic information comprises a wakeup word.

2. The voice interaction method of claim 1 , further comprising:

detecting a first operation of a user; and

querying, based on the first operation, the mapping relationship to obtain the service type set, wherein the first target service type corresponds to a plurality of target operations associated with the first operation, and wherein the target operations are consecutive operations.

3. The voice interaction method of claim 1 , further comprising:

receiving a notification message from an operating system or an application; and

querying, based on the notification message, the mapping relationship to obtain the service type set, wherein the first target service type comprises a message viewing or a message processing corresponding to the notification message.

4. The voice interaction method of claim 3 , wherein the notification message comprises at least one of a call notification, a short message service message, an instant messaging message, or an alarm message, and wherein the voice interaction method further comprises at least one of:

querying, based on the call notification, the mapping relationship to obtain the service type set, wherein the first target service type comprises a call answering;

querying, based on the short message service message or the instant messaging message, the mapping relationship to obtain the service type set, wherein the first target service type comprises the message viewing or a message replying; or

querying, based on the alarm message, the mapping relationship to obtain the service type set, wherein the first target service type comprises a troubleshooting or an information query.

5. The voice interaction method of claim 1 , further comprising:

determining that a current environment parameter meets a first condition; and

querying, based on the current environment parameter, the mapping relationship to obtain the service type set, wherein the first target service type comprises an environment parameter adjustment.

6. The voice interaction method of claim 1 , further comprising:

determining that a progress of a current service meets a second condition; and

querying, based on the current service, the mapping relationship to obtain the service type set, wherein the first target service type comprises a second service type of the current service.

7. The voice interaction method of claim 1 , further comprising:

obtaining, based on a historical record, a historical service associated with a historical target event;

writing a third service type of the historical service and the historical target event into the mapping relationship;

invoking a machine learning model by inputting a sample target event into the machine learning model to predict an output service type; and

writing the output service type and the sample target event into the mapping relationship.

8. The voice interaction method of claim 1 , wherein after obtaining the second service, the voice interaction method further comprises:

identifying that the first service type is different from the first target service type; and

writing, in response to the identifying, the first service type into the mapping relationship.

9. The voice interaction method of claim 1 , wherein after obtaining the second service, the voice interaction method further comprises:

identifying that the first service type is different from the first target service type; and

discarding, in response to the identifying, the voice instruction.

10. A voice interaction apparatus comprising:

a memory configured to store instructions; and

a processor coupled to the memory, wherein the instructions cause the processor to be configured to:

detect a target event that can trigger a voice interaction;

query, based on the target event, a mapping relationship to obtain a service type set and a first probability corresponding to a first target service type, wherein the first probability indicates a possibility of executing a first service corresponding to the first target service type;

collect a voice instruction comprising semantic information;

obtain, based on the semantic information, a second service corresponding to the semantic information;

execute the second service according to the voice instruction when a first service type of the second service is the first target service type;

filter out, from the service type set, a second target service type comprising a second probability that does not meet a probability threshold before executing the second service and when the first service type is the first target service type;

update, based on the semantic information, a third probability in the mapping relationship;

increase a fourth probability corresponding to the first service type in the mapping relationship when the first service type is the first target service type;

decrease the first probability when the first service type is different from the first target service type; and

increase the fourth probability when the semantic information comprises a wakeup word.

11. The voice interaction apparatus of claim 10 , wherein the instructions further cause the processor to be configured to:

detect a first operation of a user; and

query, based on the first operation, the mapping relationship to obtain the service type set, wherein the first target service type corresponds to a plurality of target operations associated with the first operation, and wherein the target operations are consecutive operations.

12. The voice interaction apparatus of claim 10 , wherein the instructions further cause the processor to be configured to:

receive a notification message from an operating system or an application; and

query, based on the notification message, the mapping relationship to obtain the service type set, wherein the first target service type comprises a message viewing or a message processing corresponding to the notification message.

13. The voice interaction apparatus of claim 12 , wherein the notification message comprises at least one of a call notification, a short message service message, an instant messaging message, or an alarm message, and wherein the instructions further cause the processor to be configured to at least one of:

query, based on the call notification, the mapping relationship to obtain the service type set, wherein the first target service type comprises a call answering;

query, based on the short message service message or the instant messaging message, the mapping relationship to obtain the service type set, wherein the first target service type comprises the message viewing or a message replying; or

query, based on the alarm message, the mapping relationship to obtain the service type set, wherein the first target service type comprises a troubleshooting or an information query.

14. The voice interaction apparatus of claim 10 , wherein the instructions further cause the processor to be configured to:

determine that a current environment parameter meets a first condition; and

query, based on the current environment parameter, the mapping relationship to obtain the service type set, wherein the first target service type comprises an environment parameter adjustment.

15. The voice interaction apparatus of claim 10 , wherein the instructions further cause the processor to be configured to:

determine that a progress of a current service meets a second condition; and

query, based on the current service, the mapping relationship to obtain the service type set, wherein the first target service type comprises a second service type of the current service.

16. The voice interaction apparatus of claim 10 , wherein the instructions further cause the processor to be configured to:

obtain, based on a historical record, a historical service associated with a historical target event;

write a third service type of the historical service and the historical target event into the mapping relationship;

invoke a machine learning model by inputting a sample target event into the machine learning model to predict an output service type; and

write the output service type and the sample target event into the mapping relationship.

17. The voice interaction apparatus of claim 10 , wherein the instructions further cause the processor to be configured to:

identify that the first service type is different from the first target service type; and

write, in response to the identifying, the first service type into the mapping relationship.

18. The voice interaction apparatus of claim 10 , wherein the instructions further cause the processor to be configured to:

identify that the first service type is different from the first target service type; and

discard, in response to the identifying, the voice instruction.

19. A terminal comprising:

a memory configured to store instructions; and

a processor coupled to the memory, wherein the instructions cause the processor to be configured to:

detect an operation of a user that can trigger a voice interaction;

query, based on the operation, a mapping relationship to obtain a service type set and a first probability corresponding to a first target service type, wherein the first probability indicates a possibility of executing a first service corresponding to the first target service type;

collect a voice instruction comprising semantic information;

obtain, based on the semantic information, a second service corresponding to the semantic information;

execute the second service according to the voice instruction when a first service type of the second service is the first target service type;

filter out, from the service type set, a second target service type comprising a second probability that does not meet a probability threshold before executing the second service and when the first service type is the first target service type;

update, based on the semantic information, a third probability in the mapping relationship;

increase a fourth probability corresponding to the first service type in the mapping relationship when the first service type is the first target service type;

decrease the first probability when the first service type is different from the first target service type; and

increase the fourth probability when the semantic information comprises a wakeup word.

20. The terminal of claim 19 , wherein the instructions cause the processor to be configured to:

receive a notification message from an operating system or an application, wherein the notification message comprises a call notification; and

query, based on the call notification, the mapping relationship to obtain the service type set, and wherein the first target service type comprises a call answering.

21. The terminal of claim 19 , wherein the instructions cause the processor to be configured to:

receive a notification message from an operating system or an application, wherein the notification message comprises a short message service message or an instant messaging message; and

query, based on the short message service message or the instant messaging message, the mapping relationship to obtain the service type set, and wherein the first target service type comprises the message viewing or a message replying.

22. The terminal of claim 19 , wherein the instructions cause the processor to be configured to:

receive a notification message from an operating system or an application, wherein the notification message comprises an alarm message; and

query, based on the alarm message, the mapping relationship to obtain the service type set, and wherein the first target service type comprises a troubleshooting or an information query.

23. A computer program product comprising computer-executable instructions stored on a non-transitory computer-readable storage medium that, when executed by a processor cause an apparatus to:

detect a target event that can trigger a voice interaction;

query, based on the target event, a mapping relationship to obtain a service type set and a first probability corresponding to a first target service type, wherein the first probability indicates a possibility of executing a first service corresponding to the first target service type;

collect a voice instruction comprising semantic information;

obtain, based on the semantic information, a second service corresponding to the semantic information;

execute the second service according to the voice instruction when a first service type of the second service is the first target service type;

filter out, from the service type set, a second target service type comprising a second probability that does not meet a probability threshold before executing the second service and when the first service type is the first target service type;

update, based on the semantic information, a third probability in the mapping relationship;

increase a fourth probability corresponding to the first service type in the mapping relationship when the first service type is the first target service type;

decrease the first probability when the first service type is different from the first target service type; and

increase the fourth probability when the semantic information comprises a wakeup word.

24. The computer program product of claim 23 , wherein the computer-executable instructions that, when executed by the processor cause the apparatus to:

receive a notification message from an operating system or an application, wherein the notification message comprises a call notification; and

query, based on the call notification, the mapping relationship to obtain the service type set, and wherein the first target service type comprises a call answering.

25. The computer program product of claim 23 , wherein the computer-executable instructions that, when executed by the processor cause the apparatus to:

receive a notification message from an operating system or an application, wherein the notification message comprises a short message service message or an instant messaging message; and

query, based on the short message service message or the instant messaging message, the mapping relationship to obtain the service type set, and wherein the first target service type comprises the message viewing or a message replying.

26. The computer program product of claim 23 , wherein the computer-executable instructions that, when executed by the processor cause the apparatus to:

receive a notification message from an operating system or an application, wherein the notification message comprises an alarm message; and

query, based on the alarm message, the mapping relationship to obtain the service type set, and wherein the first target service type comprises a troubleshooting or an information query.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 12, 2024
From: HUAWEI TECHNOLOGIES CO., LTD.
To: SHENZHEN YINWANG INTELLIGENT TECHNOLOGIES CO., LTD.
Reel/Frame 069335/0897 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 27, 2021
From: SHI, ZIJUAN; NIE, WEIRAN
To: HUAWEI TECHNOLOGIES CO., LTD.
Reel/Frame 056054/0446 →
Priority Claims (1)
CN 201910755150.6 · Aug 15, 2019 · national
Continuity (2)
Continuation PCTCN2020074988 · Feb 13, 2020
Related Publication 20210183386A1 · Jun 17, 2021