Phrase-based dialogue modeling with particular application to creating a recognition grammar

• US 9,342,504 B2
• Filed: 01/14/2014
• Issued: 05/17/2016
• Est. Priority Date: 05/28/1999
• Status: Expired due to Term

• Current Assignee: Nant Holdings IP, LLC (NantWorks, LLC), Sheda, Inc.
• Original Assignee: Nant Holdings IP, LLC (NantWorks, LLC)
• Inventors: Ehsani, Farzad, Knodt, Eva M., Master, Demitrios L.
• Primary Examiner(s): Neway, Samuel G
• Application Number:
  US14/155,235
• Publication Number:
  US 20140136189A1
• Time in Patent Office: 854 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

The invention enables creation of grammar networks that can regulate, control, and define the content and scope of human-machine interaction in natural language voice user interfaces (NLVUI). The invention enables phrase-based modeling of generic structures of verbal interaction to be used for the purpose of automating part of the design of such grammar networks. Most particularly, the invention enables such grammar networks to be used in providing a voice-controlled user interface to human readable text data that is also machine-readable (such as a Web page, a word processing document, a PDF document, or a spreadsheet).

Claims

1. A voice-interactive dialog system for facilitating conversational speech across different domains, comprising:

a phrase database storing (i) phrases grouped into equivalence classes and (ii) a probability of occurrence for each phrase within a corpus;

wherein each equivalence class is associated with one or more domains;

a user interface configured to allow interaction with an interactive part of the system;

a recognition server coupled with the phrase database and the user interface and configured to;

identify a user request upon receiving a user utterance via the user interface, wherein the user request is associated with a domain;

formulate a system prompt in response to the user utterance, the prompt comprising a combination of one or more phrases from the phrase database that are associated with the domain;

upon receiving a user response to the system prompt via the user interface, generate a recognition grammar from phrases in the phrase database that fall within an equivalent class associated with the user response; and

generate a recommendation to the user via the user interface, wherein the recommendation is associated with the domain.

2. The system of claim 1, wherein the domain is food.

3. The system of claim 2, wherein the recommendation is a specific restaurant.

4. The system of claim 1, wherein the domain is one of banking transactions, news, and weather.

5. The system of claim 1, wherein the recognition grammar is representative of anticipated user responses.

6. The system of claim 1, wherein the user interface comprises a phone.

7. The system of claim 1, wherein the recognition server comprises a web-based application.

8. The system of claim 1, wherein the user interface comprises a telephone interface.