Adaptive knowledge base of complex information through interactive voice dialogue

• US 5,774,860 A
• Filed: 10/30/1996
• Issued: 06/30/1998
• Est. Priority Date: 06/27/1994
• Status: Expired due to Term

• Current Assignee: Qwest Communications International Incorporated (Lumen Technologies, Inc.)
• Original Assignee: US West Technologies, Inc.
• Inventors: Bayya, Aruna, Cox, Louis A. Jr.
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): SAX, ROBERT L
• Application Number:
  US08/741,298
• Time in Patent Office: 608 Days
• Field of Search: 395/2.84, 395/2.79, 364/444.1, 364/449.4, 364/443
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method and system for providing user access to complex information through interactive voice dialog. The computerized method includes the provision of a memory and storage in the memory of a plurality of selected words which may be recognized in predetermined phrases and dialogue contexts when spoken by users. A voice template is further stored in memory having selected information slots in corresponding frames. Each of the slots and frames is adapted to be continuously filled by recognized words. User speech utterances are initiated for receipt by the computer which requests complex information or responds to generated queries. By continuously receiving and comparing the user speech utterances to the stored plurality of selected words, slots and frames of the voice template are filled. Based on the context of the interactive dialogue and the extent of recognized vocabulary words, responsive speech segments are generated which provide the requested complex information or, alternatively, request additional information necessary to provide a full response to the user.

Claims

1. A computerized method for providing user access to an adaptive knowledge base of complex information through an interactive voice dialogue, comprising:

providing a memory;

storing in memory a plurality of selected words as recognized in predetermined phrases and contexts when spoken by a user;

storing in memory a voice template having selected information slots in corresponding frames, each of the slots and frames adapted to be continuously filled by recognized words, wherein the selected information slots comprise "current location", "destination" and "orientation", and wherein the frames corresponding to the "current location", "destination", and "orientation" slots each comprise "cross street" and "landmarks";

initiating user speech utterances for receipt by the computer, the speech utterances requesting complex information;

continuously receiving and comparing the user speech utterances to the stored plurality of selected words so as to fill the slots and frames of the voice template; and

adaptably generating, based on the context of the interactive dialogue and the extent of filled slots and frames of the voice template, responsive speech segments which provide the requested complex information or, alternatively, request additional information necessary to provide a full response to the user.

2. A system for providing user access to an adaptive knowledge base of complex information through an interactive voice dialogue, comprising:

a computer having a memory and adapted to store a plurality of selected words as recognized in predetermined phrases and contexts when spoken by a user;

a voice template having selected information slots and corresponding frames, each of the slots and frames adapted to be continuously filled by recognized words, the voice template also adapted to be stored in the computer memory, wherein the selected information slots comprise "current location", "destination" and "orientation", and wherein the frames corresponding to the "current location", "destination", and "orientation" slots each comprise "cross street" and "landmarks";

a processor in electrical communication with the computer memory, the processor adapted to continuously receive and compare user speech utterances requesting complex information to the stored plurality of selected words so as to fill the slots and frames of the voice template; and

means for adaptably generating, based on the context of the interactive dialogue and the extent of filled slots and frames of the voice template, responsive speech segments which provide the requested complex information or, alternatively, request additional information necessary to provide a full response to the user.