Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
1998-05-14
2001-05-22
Dorvil, Richemond (Department: 2741)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
C704S270000
Reexamination Certificate
active
06236968
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention is directed in general to an automatic dialog car system. More particularly, the invention is directed to an automatic dialog car system designed to prevent a driver from falling asleep during long trips or trips that extend into the evening.
A leading cause of traffic accidents is by drivers who fall asleep at the wheel. There exist various devices designed to prevent drivers from falling asleep. For example, one conventional device includes a miniature system installed in a driver's hat, to measure the slope of the driver's head. If the slope of the driver's head exceeds a predetermined threshold, a loud audible signal is generated to awaken the driver. The problem with such a prevention system is that the driver can lose control of the car several moments before his head changes positions. That is, a driver may fall asleep before his head drops beyond the threshold that triggers the audible signal. Various other methods have been tried, for example, the use of stimulation drinks (e.g., coffee and tea) and tablets for preventing drivers from sleeping during such situations. However, all such methods have not been successful.
It is well known that to keep the driver awake while driving, he should talk with someone in the car (or over a car telephone). However, it is obvious that such options are not always available for those times when a driver is driving alone in the car or a car telephone is not accessible.
SUMMARY OF THE INVENTION
Accordingly, in view of the above and other problems with the conventional art, it is an object of the present invention to provide an automatic dialog system that is capable of keeping a driver awake during long or evening trips. The system can carry on a conversation with a driver on any one of various topics with the help of a natural dialog car system. In such a system, the driver is obliged to participate in the conversation with the dialog car system. The natural dialog car system often includes humorous content for combating fatigue in the driver.
It is a further object of the present invention to provide a natural dialog car system including a natural language processing module that can understand the content of answers or questions uttered by a driver, and produce meaningful responses.
It is a further object of the present invention to provide a natural dialog car system for interpreting a driver's answers and producing machine responses.
An even further object of the present invention is to provide a natural dialog car system that understands content of tapes, books and radio programs, and extracts and reproduces appropriate phrases from those materials while it is talking with a driver. For example, a system can find out if someone is singing on a channel of a radio station. The system will state “And now you will hear a wonderful song!” or detect that there is news and state “Do you know what happened now—hear the following—and play some news.” The system also includes a recognition system to detect who is speaking over the radio and alert the driver if the person speaking is one the driver wishes to hear.
According to yet a further object of the present invention, there is provided a natural dialog car system directed to human factor engineering, for example, people using different strategies to talk. For instance, short vs. elaborate responses. In this manner, the individual is guided to talk in a certain way so as to make the system work (e.g., “sorry I didn't get it, could you say it briefly”). Here, the system defines a narrow topic of the user reply (answer or question) via an association of classes of relevant words via decision trees. The system builds a reply sentence asking what are most probable word sequences that could follow the users' reply.
According to yet a further object of the present invention, there is provided a natural dialog car system including a conversation planner for keeping the driver alert. An analyzer of the driver's answers and content of the answers and his voice patterns are judged to determine the alertness of the driver while he is driving. This module contains a set of prototypes for different voice patterns corresponding to different levels of a driver's alertness. The system analyzes the quality of the driver's answers, and detects a time that is needed for the driver to answer. The system matches the output parameters (response time and quality of answers, etc.) with a table and determines whether the driver conditions from this and the other set of parameters. The system alerts a driver or changes a topic of conversation and/or sounds an alarm if it finds that he is tired or about to fall asleep. The system may detect whether a driver is effected by drug or alcohol in this manner as well.
REFERENCES:
patent: 3707710 (1972-12-01), Adler et al.
patent: 5101926 (1992-04-01), Berman et al.
patent: 5559927 (1996-09-01), Clynes
patent: 5577165 (1996-11-01), Takebayashi et al.
patent: 5649060 (1997-07-01), Ellozy et al.
patent: 5684455 (1997-11-01), Williams et al.
patent: 5694116 (1997-12-01), Kojima
patent: 5745031 (1998-04-01), Yamamoto
patent: 5774860 (1998-06-01), Bayya et al.
patent: 5786765 (1998-07-01), Kumakura et al.
patent: 5809269 (1998-09-01), Favot et al.
patent: 5915238 (1999-06-01), Tjaden
patent: 5952928 (1999-09-01), Washington et al.
patent: 5983189 (1999-11-01), Lee
patent: 5990795 (1999-11-01), Miller
patent: 6009355 (1999-12-01), Obradovich et al.
patent: 6048324 (2000-04-01), Socci et al.
patent: 1234345 (1999-11-01), None
patent: 2111134 (1998-05-01), None
“The Design and Implementation of the TRAINS-96 System: A Prototype Mixed-Initiative Planning Assistant”, G. Ferguson et al., The University of Rochester, Computer Science Department, TRAINS Technical Note 96-5, Oct. 1996.
C. Lee et al, Automatic Speech and Speaker Recognition, An Overview of Automatic Speech Recognition, pp. 1-5, 1996.
F. Jelinek et al, Decision Tree Parsing using a Hidden Derivation Model, IBM Research, T.J. Watson Research Center, Yorktown Heights, N.Y. 10598, 1994.
G. Gazdar, et al, Natural Language Processing in POP-11, An Introduction to Computational Linguistics, Addison-Wesley Publishing Co., pp 21-27, 244-249, 356-361, 1989.
L.R. Bahl et al, A Tree-Based Statistical Language Model for Natural Language Speech Recognition, IEEE Transaction on Acoustics, Speeck and Signal Processing, vol. 37, No. 7, Jul. 1989, pp 1001-1008.
W.G. Lehnert, BORIS—An Experiment in In-Depth Understanding of Narratives, Artificial Intelligence, pp 15-63, 1983.
Kanevsky Dimitri
Zadrozny Wlodek Wlodzimierz
Armstrong Angela
Dorvil Richemond
International Business Machines - Corporation
Sughrue Mion Zinn Macpeak & Seas, PLLC
LandOfFree
Sleep prevention dialog based car system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Sleep prevention dialog based car system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Sleep prevention dialog based car system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2543423