Dialog management system for using multiple artificial intelligence service providers

Patent metadata

Field	Value
Publication number	US-10847157-B2
Application number	US-201916453428-A
Country	US
Kind code	B2
Filing date	Jun 26, 2019
Priority date	Nov 26, 2018
Publication date	Nov 24, 2020
Grant date	Nov 24, 2020

Abstract

Implementations of the present disclosure include methods, systems, and computer-readable storage mediums for utilizing multiple AI service providers by a dialog management system. The dialog management system can include a dispatcher bot, multiple worker bots, and multiple AI adapters that are each associated with a different cloud-based AI service provider. In response to receiving a query, the dispatcher bot selects a particular worker bot to handle the query. The particular worker bot is assigned to a particular AI service provider. An AI adapter associated with the particular AI service provider, generates a query message based on the query. The AI adapter sends the query message to the particular AI service provider and receives a response message. The dialog management system sends a representation of the response message to the particular worker bot, receives an answer for the query from the particular worker bot, and provides the answer for output.

First claim

What is claimed is:

1. A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations, the operations comprising:
receiving a query;
dynamically selecting a particular worker bot to handle the query based at least on (i) data that associates the particular worker bot with a subject matter of the query;
generating a query message based on the query;
sending the query message to a particular cloud-based, third party AI service provider;
receiving a response message from the particular cloud-based, third party AI service provider, the response message includes first data that indicates content of the query message;
generating a representation of the response message that is consumable by a knowledge retriever, comprising discarding, without outputting to a submitter of the query, one or more portions of the response message that were generated by the third party AI service provider as a substantive response to the query but that are not used by the knowledge retriever or the particular worker bot to generate an answer for the query; and
sending the representation of the response message to the particular worker bot, and in response:
receiving the answer for the query from the particular worker bot, and
forwarding the answer to the channel adapter; and

providing, by the channel adapter, the answer for output.

2. The non-transitory computer-readable storage medium of claim 1 , wherein generating the query message comprises adding context data that is derived from prior interactions with a user that submitted the query.

3. A system comprising:
a computing device; and
a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations, the operations comprising:
receiving a query;
dynamically selecting a particular worker bot to handle the query based at least on (i) data that associates a particular worker bot with a subject matter of the query, and (ii) historical latency data or cost data associated with a particular cloud-based, third party AI service provider that is configured to provide a natural language processing of the query and that is assigned to the particular worker bot;
generating a query message based on the query;
sending the query message to the particular cloud-based, third party AI service provider;
receiving a response message from the particular cloud-based, third party AI service provider, the response message includes first data that indicates content of the query message;
generating a representation of the response message that is consumable by a knowledge retriever, comprising discarding, without outputting to a submitter of the query, one or more portions of the response message that were generated by the third party AI service provider as a substantive response to the query but that are not used by the knowledge retriever or the particular worker bot to generate an answer for the query;
sending the representation of the response message to the particular worker bot, and in response:
receiving the answer for the query from the particular worker bot, and
forwarding the answer to the channel adapter; and

providing, by the channel adapter, the answer for output.

4. The system of claim 3 , wherein generating the query message comprises adding context data that is derived from prior interactions with a user that submitted the query.

5. The system of claim 3 , wherein the actions further comprise consulting a list of cloud-based AI service providers that are indicated as capable of determining content of the query.

6. The system of claim 3 , wherein the particular worker bot is dynamically selected based further on historical accuracy data associated with the particular cloud-based, third party AI service providers in answering other queries with the same subject matter by other users of the dialog management system.

7. The system of claim 3 , wherein generating query message comprises reformatting the query into a format that is capable of being consumed by the particular cloud-based AI service provider.

8. The system of claim 3 , wherein generating the query message comprises adding context data that is derived from prior interactions with a user that submitted the query.

9. The system of claim 3 , wherein generating the query message comprises adding user profile information.

10. A computer-implemented method comprising:
receiving a query;
dynamically selecting a particular worker bot to handle the query based at least on (i) data that associates the particular worker bot with a subject matter of the query;
generating a query message based on the query;
sending the query message to a particular cloud-based, third party AI service provider;
receiving a response message from the particular cloud-based, third party AI service provider, the response message includes first data that indicates content of the query message;
generating a representation of the response message that is consumable by a knowledge retriever, comprising discarding, without outputting to a submitter of the query, one or more portions of the response message that were generated by the third party AI service provider as a substantive response to the query but that are not used by the knowledge retriever or the particular worker bot to generate an answer for the query; and
sending the representation of the response message to the particular worker bot, and in response:
receiving the answer for the query from the particular worker bot, and
forwarding the answer to the channel adapter; and

providing, by the channel adapter, the answer for output.

11. The method of claim 10 , wherein generating the query message comprises adding context data that is derived from prior interactions with a user that submitted the query.

Assignees

• Accenture Global Solutions Ltd

Inventors

• Eriksson Laetitia Cailleteau
• Wickes Christopher
• Duncan Marion Danielle Claude Perichaud
• Gugliotta Augusto

Classifications

• G06N5/043

  Distributed expert systems; Blackboards · CPC title

• G06F16/3334

  Selection or weighting of terms from queries, including natural language queries · CPC title

• G10L15/22 Primary

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

• G10L2015/225

  Feedback of the input speech · CPC title

• G06F16/3329

  Natural language query formulation · CPC title