System and methods for delivering advanced natural language interaction applications

• US 8,346,563 B1
• Filed: 08/02/2012
• Issued: 01/01/2013
• Est. Priority Date: 04/10/2012
• Status: Active Grant

• Current Assignee: Artificial Solutions Iberia, S. L.
• Original Assignee: Artificial Solutions, Ltd.
• Inventors: Hjelm, David, Krüger, Robert, Gülsdorff, Björn, Gustavii, Ebba Birgitta, Cheadle, Maria
• Primary Examiner(s): Abebe, Daniel D
• Application Number:
  US13/565,790
• Time in Patent Office: 152 Days
• Field of Search: 704/251, 704/257, 704/275, 379/88.01
• US Class Current: 704/275
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A system for delivering advanced natural language interaction applications, comprising a dialog interface module, a natural language interaction engine, a solution data repository component operating comprising at least one domain model, at least one language model, and a plurality of flow elements and rules for managing interactions with users, and an interface software module. Upon receipt of a request from a user via a network, the dialog interface module preprocesses the request and transmits it to the natural language interaction engine. The natural language interaction engine interprets the request using a plurality of language recognition rules stored in the solution data repository, and based at least determined semantic meaning or user intent, the natural language interaction engine forms an appropriate response and delivers the response to the user via the dialog module, or takes an appropriate action based on the request.

Claims

1. A system for delivering advanced natural language applications, the system comprising:

a dialog interface module operating on a server computer and adapted for exchanging information with a user via a network;

a natural language interaction engine operating on a server computer and coupled to the dialog interface module, for interpreting a received user request;

a solution data repository component operating on a server computer and coupled to the natural language interaction engine, the solution data repository comprising a plurality of hierarchical ontological domain models, a plurality of hierarchical language models comprising a preconfigured, hierarchical arrangement of language objects, a plurality of language recognition rules expressed in terms of elements of the plurality of hierarchical language models, and a plurality of flow elements and rules for managing interactions with users; and

an interface software module coupled to the natural language interaction engine and adapted to exchange data or commands with a plurality of external software services over a network;

wherein upon receipt of a request from a user via a network, the dialog interface module preprocesses the request and transmits it to the natural language interaction engine; and

wherein the natural language interaction engine interprets the request to determine one or more semantic meanings or user intents associated with the request, using the plurality of language recognition rules, the plurality of hierarchical ontological domain models, and the plurality of flow elements stored in the solution data repository; and

further wherein, based at least on the one or more semantic meanings or user intents, the natural language interaction engine forms an appropriate response and delivers the response to the dialog module, which uses one or more output means of the computing device to provide a response to the user via a network, or takes an appropriate automated action in response to the request.

2. A method for delivering advanced natural language interaction applications, the method comprising the steps of:

(a) receiving a request from a user at a dialog interface module;

(b) pre-processing the request by the dialog interface module;

(c) transmitting the request in an appropriate form to a natural language interaction engine;

(d) evaluating the request using a plurality of hierarchical language models, a plurality of language recognition rules expressed in terms of elements of the plurality of hierarchical language models comprising a preconfigured, hierarchical arrangement of language objects, a plurality of hierarchical ontological domain models, and a plurality of flow elements stored in the solution data repository until either a determination is made that additional input is needed from the user or that no further conditions exist;

(e) sending an appropriate response to the user or taking an appropriate action based at least on the results of step (d); and

(f) awaiting a further user request or a session end event.

3. An automated assistant operating on a computing device, the assistant comprising:

a dialog interface module operating on the computing device and adapted for exchanging information with a user using one of a plurality of input and output means of the computing device;

a natural language interaction engine coupled to the dialog interface module, for interpreting a received user request;

a solution data repository component, comprising a plurality of hierarchical ontological domain models, a plurality of hierarchical language models comprising a preconfigured, hierarchical arrangement of language objects, a plurality of language recognition rules expressed in terms of elements of the plurality of hierarchical language models, and a plurality of flow elements and rules for managing interactions with users; and

an interface software module coupled to the natural language interaction engine and adapted to exchange data or commands with a plurality of external software services over a network;

wherein upon receipt of a request from a user via an input means of the computing device, the dialog interface module preprocesses the request and transmits it to the natural language interaction engine; and

wherein the natural language interaction engine interprets the request using a plurality of hierarchical language models comprising a preconfigured, hierarchical arrangement of language objects, a plurality of language recognition rules expressed in terms of elements of the plurality of hierarchical language models, a plurality of hierarchical ontological domain models, and a plurality of flow elements stored in the solution data repository until either a determination is made that additional input is needed from the user or that no further conditions exist; and

further wherein, based at least on the one or more semantic meanings or user intents, the natural language interaction engine forms an appropriate response and delivers the response to the dialog module, which uses one or more output means of the computing device to provide a response to the user, or takes an appropriate automated action based on the request.