System and method for managing artificial conversational entities enhanced by social knowledge

• US 10,599,644 B2
• Filed: 09/14/2016
• Issued: 03/24/2020
• Est. Priority Date: 09/14/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Braz, Alan, Cavalin, Paulo Rodrigo, Diniz de Figueiredo, Flavio Vinicius, Gatti De Bayser, Maira, Santos Souza, Renan Francisco
• Primary Examiner(s): Hicks, Austin
• Application Number:
  US15/265,615
• Publication Number:
  US 20180075335A1
• Time in Patent Office: 1,287 Days
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems

Abstract

A method for answering a natural-language user query includes receiving a query from a user by a central agent, parsing the query, and determining if an answer is known to the central agent as being within a local database. If the answer is known, the query is answered with a known natural-language answer using the local database. If not, artificial conversational entity (ACE) invocation is performed. The ACE invocation includes determining a topical field for the query, determining an ACE, of a plurality of ACEs, to send the query to, based on the topical field, and sending the query to the ACE. If the ACE is capable of answering, a natural-language answer is received from the ACE and presented to the user. If not, a natural-language answer is created using social knowledge and presented to the user. Social knowledge includes data crawled from subscriber-provided content of social media services.

Claims

1. A method for answering a natural-language user query, comprising:

receiving a natural-language user query from a user by a central agent;

parsing the natural-language user query;

determining if an answer to the parsed natural-language user query is known to the central agent as being within a local database;

answering the parsed natural-language user query, in the form of a known natural-language answer, using the local database, when it is determined that the answer to the parsed natural-language user query is known to the central agent as being within the local database;

when it is determined that the answer to the parsed natural-language user query is not known to the central agent as being within the local database, artificial conversational entity (ACE) invocation is performed, the ACE invocation comprising;

determining a topical field for the parsed natural-language query;

determining an ACE, of a plurality of available ACEs, to send the parsed natural-language query to, based on the determined topical field;

sending the parsed natural-language query to the determined ACE; and

receiving a natural-language answer to the parsed natural-language query from the determined ACE, and presenting the received natural-language answer to the user when the determined ACE is capable of answering the parsed natural-language query; and

creating a natural-language answer to the parsed natural-language query using social knowledge, and presenting the created natural-language answer to the user when the determined ACE is not capable of answering the parsed natural-language query,

wherein social knowledge includes data that is crawled from social media services, and

wherein the data that is crawled from the social media services includes data provided by an influencer having followers exceeding a predetermined number or data having positive feedback exceeding a predetermined threshold.

2. The method of claim 1, wherein the natural-language query is sent from the user and transmitted to the central agent along a messaging service, application, or artificial intelligence user assistance platform and the known natural-language answer, the received natural-language answer, or the created natural-language answer is sent from the central agent to the user along the messaging service, application, or artificial intelligence user assistance platform.

3. The method of claim 2, wherein the messaging service, application, or artificial intelligence user assistance platform is a text, voice, or video messaging service.

4. The method of claim 2, wherein the messaging service, application, or artificial intelligence user assistance platform is a voice-based communication platform.

5. The method of claim 1, wherein each of the plurality of available ACEs is a stand-alone natural-language question answering application or service.

6. The method of claim 1, wherein the topical field for the parsed natural-language query is determined using a keyword comparison scan.

7. The method of claim 1, wherein the parsed natural-language query is sent to the determined ACE along a messaging service, application, or artificial intelligence user assistance platform.

8. The method of claim 1, wherein the social media services include a plurality of social media websites, applications, or services.

9. The method of claim 1, wherein the created natural-language answer is created by the central agent.

10. A system for answering a natural-language user query, comprising:

a central agent configured to receive a natural-language user query from a user and answer the received natural-language user query;

a local database, associated with the central agent, configured to provide the central agent with a limited set of natural-language answers;

a plurality of artificial conversational entities (ACE), each configured to answer natural-language user queries of a particular topical field; and

a messaging service, application, or artificial intelligence user assistance platform configured to provide communication between the user and the central agent and configured to provide communication between the central agent and the plurality of ACEs,

wherein the central agent is further configured to answer the received natural-language user query from the local database, from the plurality of ACEs, or from social knowledge including data that is crawled from social media services,

wherein the number of the plurality of ACEs is greater than one,

wherein the central agent is further configured to join the user and the plurality of ACEs in one chat instance, and

wherein the central agent, the local database, the plurality of ACEs, and the messaging service application, or artificial intelligence user assistance platform are embodied in one or more computer systems.

11. The system of claim 10, wherein the central agent and each of the plurality of ACEs access the messaging service, application, or artificial intelligence user assistance platform using various application program interfaces (APIs).

12. The system of claim 10, wherein the messaging service, application, or artificial intelligence user assistance platform is a text, voice, or video messaging service.

13. The system of claim 10, wherein the messaging service, application, or artificial intelligence user assistance platform is a voice-based communication platform.

14. The system of claim 10, wherein each of the plurality of ACEs is a stand-alone natural-language question answering application or service.

15. The system of claim 10, wherein the social media services include a plurality of social media websites, applications, or services.

16. The system of claim 10, wherein the central agent, each of the plurality of ACEs, and the messaging service, application, or artificial intelligence user assistance platform is hosted on at least one independent server and each of the independent servers is connected to the Internet.

17. A computer system comprising:

a processor; and

a non-transitory, tangible, program storage medium, readable by the computer system, embodying a program of instructions executable by the processor to perform method steps for answering a natural-language user query, the method comprising;

receiving a natural-language user query from a user by a central agent;

determining if an answer to the natural-language user query is known to the central agent as being within a local database;

answering the natural-language user query, in the form of a known natural-language answer, using the local database, when it is determined that the answer to the natural-language user query is known to the central agent as being within the local database;

when it is determined that the answer to the natural-language user query is not known to the central agent as being within the local database, artificial conversational entity (ACE) invocation is performed, the ACE invocation comprising;

determining a topical field for the natural-language query;

determining an ACE, of a plurality of available ACEs, to send the natural-language query to, based on the determined topical field;

sending the natural-language query to the determined ACE; and

receiving a natural-language answer to the natural-language query from the determined ACE, and presenting the received natural-language answer to the user when the determined ACE is capable of answering the natural-language query; and

creating a natural-language answer to the natural-language query using social knowledge, and presenting the created natural-language answer to the user when the determined ACE is not capable of answering the natural-language query,

wherein social knowledge includes data that is crawled from social media services, and

wherein the data that is crawled from the social media services includes data provided by an influence having followers exceeding a predetermined number or data having positive feedback exceeding a predetermined threshold.

18. The computer system of claim 17, wherein the natural-language query is sent from the user and transmitted to the central agent along a messaging service, application, or artificial intelligence user assistance platform and the known natural-language answer, the received natural-language answer, or the created natural-language answer is sent from the central agent to the user along the messaging service, application, or artificial intelligence user assistance platform.

19. The computer system of claim 17, wherein each of the plurality of available ACEs is a stand-alone natural-language question answering application or service.

20. The computer system of claim 17, wherein the created natural-language answer is created by the central agent.