Performing tasks and returning audio and visual answers based on voice command

Patent metadata

Field	Value
Publication number	US-10311877-B2
Application number	US-201715641843-A
Country	US
Kind code	B2
Filing date	Jul 5, 2017
Priority date	Jul 4, 2016
Publication date	Jun 4, 2019
Grant date	Jun 4, 2019

Abstract

An artificial intelligence voice interactive system may provide various services to a user in response to a voice command by providing an interface between the system and a legacy system to enable providing various types of existing services in response to user speech without modifying systems for the existing services. Such system includes a central server, and the central server may perform operations of registering a plurality of service servers at the central server and storing registration information of each service server, analyzing voice command data from the user device and determining at least one task and corresponding service servers based on the analysis results, generating an instruction message based on the voice command data, the determined at least one task, and the registration information of the selected service servers, and transmitting the generated instruction message to the selected service servers, and receiving task results including audio and video data from the selected service servers and outputting the task results through at least one device associated with the user device.

First claim

What is claimed is:

1. A method for providing voice interactive services to a user through an artificial intelligence voice interactive system including a central server and a plurality of service servers each associated with a legacy system, the method comprising:
performing a registration operation in response to a predetermined event to register the plurality of service servers and store the registered information of each of the plurality of service servers;
receiving command data, determining a task to perform based on the command data, and selecting at least one of the plurality of service servers based on the determined task;
generating an instruction message based on the command data, the determined task, and the registered information of the selected at least one of the plurality of service servers, and transmitting the generated instruction message to the selected at least one of the plurality of service servers; and
receiving a response message from the selected at least one of the plurality of service servers and outputting at least one of audio and video data based on the response message.

2. The method of claim 1 , wherein:
the registering comprises: storing task essential information for performing a task for each of the plurality of service servers; and
the method further comprises: requesting additional information to a user device when the command data does not include task essential information for performing the determined task associated with the command data.

3. The method of claim 1 , wherein the predetermined event includes i) receiving a request message from at least one of the plurality of service servers, ii) receiving a request message from a user device, iii) requesting the at least one of the plurality of service servers to transmit registration information, and iv) regularly collecting the registration information from the at least one of the plurality of service servers.

4. The method of claim 1 , wherein the registration information of each one of the plurality of service servers include at least one of information on tasks to perform, service identification words, a communication address, and message formats.

5. The method of claim 1 , wherein the instruction message is generated based on a message format based on the registration information of the selected at least one of the plurality of service severs in order to cooperate with a non-voice interactive system to perform the determined task.

6. The method of claim 1 , wherein determining whether the received command data is related to an internal task or an external task based on service identification words included in the received command data.

7. The method of claim 6 , when the received command data includes at least one of service identification words, the received command data is a request for the external task that requires one of the service servers.

8. The method of claim 1 , wherein the selecting the at least one of the plurality of service servers comprises:
determining whether the command data includes one of service initiation words, service initiation sentences, sentence patterns, and keywords of the service servers based on the stored registration information of the service servers; and
selecting the at least one of the plurality of service servers mapped to the one included in the voice command data.

9. The method of claim 8 , wherein the selecting the at least one of the plurality of service servers further comprises:
applying a predetermined selection order to select the at least one of the plurality of service servers; and
the predetermined selection order is to firstly select one associated with the service initiation word, secondly select one associated with the service initiation sentence, thirdly select one associated with the sentence pattern, and lastly select one associated with the keyword.

10. The method of claim 1 , wherein the selecting the at least one of the plurality of service servers comprises:
determining whether the command data includes one of a service initiation word and a service initiation sentence of the service servers; and
when the command data include at least one of the service initiation word and the service initiation sentence, selecting a service server mapped to at least one of the service initiation word and the service initiation sentence.

11. The method of claim 1 , wherein the selecting the at least one of the plurality of service server comprises:
when more than two service servers are capable of performing the determined task associated with the command data, selecting at least one of the two service servers based on a predetermined selection condition.

12. The method of claim 11 , wherein the selecting the at least one of the plurality of service server further comprises:
when one of a keyword and a sentence pattern included in the voice command data is mapped to more than two service servers, determining that more than two service servers are capable of performing the determined task associated with the voice command.

13. The method of claim 11 , wherein the predetermined selection conditions is one of i) selecting one assigned with a higher priority than the others among the plurality of service servers, ii) selecting one previously selected more times than the others among the plurality of service servers, and iii) selecting one set as a default service server.

14. A method for providing, by a user device, various non-voice interactive services in response to a voice command from a user, the method comprising:
receiving a voice command from the user;
transmitting command data to a central server;
receiving a result message from at least one of the central server and service servers, wherein each of the service servers is associated with a legacy system; and
outputting at least one of audio and video data based on the result message through the user device,
wherein:
the result message is generated by one of the service servers, as a result of performing at least one task included in the command data through the selected service server, and

the selected service server and the central server are communicated through an instruction message which has information necessary for the selected service server to perform the task included in the command data.

15. The method of claim 14 , wherein the instruction message is generated based on a format enabling communication between the service servers and the central server.

Assignees

• Kt Corp

Inventors

• Lee Sang-Wook
• Chang Du-Seong

Classifications

• G10L15/22

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

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G06Q50/10 Primary

  Services · CPC title

• G06Q30/0633

  Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087) · CPC title