Human-machine interaction method and apparatus based on artificial intelligence

Patent metadata

Field	Value
Publication number	US-10923120-B2
Application number	US-201816054671-A
Country	US
Kind code	B2
Filing date	Aug 3, 2018
Priority date	Sep 19, 2017
Publication date	Feb 16, 2021
Grant date	Feb 16, 2021

Abstract

A human-machine interaction method and apparatus based on artificial intelligence. In the method, a user-entered interaction sentence is received, and whether to generate an interaction result corresponding to the interaction sentence is determined; and interaction information to be presented to the user is determined based on a determining result, the interaction information including at least one of following items: the generated interaction result corresponding to the interaction sentence, or a search result corresponding to the interaction sentence in a search engine.

First claim

What is claimed is:

1. A human-machine interaction method based on artificial intelligence, the method comprising:
setting a core-type database in a terminal, the core-type database including a navigation database or a control database, wherein the navigation database includes interaction information responsive to a sentence including a navigation instruction, and the control database includes interaction information responsive to a sentence including a control instruction;
receiving, by the terminal, a user-entered interaction sentence;
determining that the user-entered interaction sentence includes the navigation instruction or the control instruction;
searching locally in the terminal for interaction information responsive to the user-entered interaction sentence including the navigation instruction or the control instruction;
determining interaction information to be presented to a user based on a search result;
receiving by the terminal a second user-entered interaction sentence;
determining that the second user-entered interaction sentence does not include the navigation instruction and the control instruction;

sending the second user-entered interaction sentence that does not include the navigation instruction and the control instruction to a search engine remotely connected to the terminal arranged in a vehicle; and
obtaining by the search engine a second search result corresponding to the interaction sentence.

2. The method according to claim 1 , wherein the navigation instruction is an instruction for navigating the vehicle, and the control instruction is an instruction for controlling the vehicle.

3. The method according to claim 2 , wherein the user-entered interaction sentence includes the navigation instruction for navigating the vehicle,
wherein the searching locally in the terminal for interaction information responsive to the user-entered interaction sentence including the navigation instruction or the control instruction comprises: searching the navigation database arranged in the vehicle for the interaction information responsive to the user-entered interaction sentence including the navigation instruction.

4. The method according to claim 1 , wherein the determining that the second user-entered interaction sentence does not include the navigation instruction and the control instruction comprises: determining that the second user-entered interaction sentence is a weather query; and
sending the second user-entered interaction sentence that does not include the navigation instruction and the control instruction to a search engine remotely connected to the terminal comprises: sending the weather query from the vehicle to the search engine remotely connected to the terminal of the vehicle.

5. A human-machine interaction apparatus based on artificial intelligence, the apparatus comprising:
at least one processor; and
a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
setting a core-type database in a terminal, the core-type database including a navigation database or a control database, wherein the navigation database includes interaction information responsive to a sentence including a navigation instruction, and the control database includes interaction information responsive to a sentence including a control instruction;
receiving, by the terminal, a user-entered interaction sentence;
determining that the user-entered interaction sentence includes the navigation instruction or the control instruction;
searching locally in the terminal for interaction information responsive to the user-entered interaction sentence including the navigation instruction or the control instruction; and
determining interaction information to be presented to a user based on a search result;
receiving by the terminal a second user-entered interaction sentence;
determining that the second user-entered interaction sentence does not include the navigation instruction and the control instruction;

sending the second user-entered interaction sentence that does not include the navigation instruction and the control instruction to a search engine remotely connected to the terminal arranged in a vehicle; and
obtaining by the search engine a second search result corresponding to the interaction sentence.

6. The apparatus according to claim 5 , wherein the navigation instruction is an instruction for navigating the vehicle, and the control instruction is an instruction for controlling the vehicle.

7. The apparatus according to claim 6 , wherein the user-entered interaction sentence includes the navigation instruction for navigating the vehicle,
wherein the searching locally in the terminal for interaction information responsive to the user-entered interaction sentence including the navigation instruction or the control instruction comprises: searching the navigation database arranged in the vehicle for the interaction information responsive to the user-entered interaction sentence including the navigation instruction.

8. The apparatus according to claim 5 , wherein the determining that the second user-entered interaction sentence does not include the navigation instruction and the control instruction comprises: determining that the second user-entered interaction sentence is a weather query; and
sending the second user-entered interaction sentence that does not include the navigation instruction and the control instruction to a search engine remotely connected to the terminal comprises: sending the weather query from the vehicle to the search engine remotely connected to the terminal of the vehicle.

9. A non-transitory computer readable medium, storing a computer program, wherein the program, when executed by a processor, causes the processor to perform operations, the operations comprising:
setting a core-type database in a terminal, the core-type database including a navigation database or a control database, wherein the navigation database includes interaction information responsive to a sentence including a navigation instruction, and the control database includes interaction information responsive to a sentence including a control instruction;
receiving, by the terminal, a user-entered interaction sentence determining that the user-entered interaction sentence includes the navigation instruction or the control instruction;
searching locally in the terminal for interaction information responsive to the user-entered interaction sentence including the navigation instruction or the control instruction; and
determining interaction information to be presented to a user based on a search result;
receiving by the terminal a second user-entered interaction sentence;
determining that the second user-entered interaction sentence does not include the navigation instruction and the control instruction;

sending the second user-entered interaction sentence that does not include the navigation instruction and the control instruction to a search engine remotely connected to the terminal arranged in a vehicle; and
obtaining by the search engine a second search result corresponding to the interaction sentence.

Assignees

• Beijing Baidu Netcom Sci & Tec

Inventors

• Lin Yingzhan
• Xie Zeying
• Liang Yichuan
• Wang Wenmin
• Zhang Yin
• Ling Guang
• Zhou Chao

Classifications

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L2015/0631

  Creating reference templates; Clustering · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title