Data processing: artificial intelligence – Fuzzy logic hardware
Reexamination Certificate
2000-04-04
2003-04-22
Follansbee, John A. (Department: 2121)
Data processing: artificial intelligence
Fuzzy logic hardware
C706S052000
Reexamination Certificate
active
06553354
ABSTRACT:
FIELD OF THE INVENTION
This invention generally relates to a method for probabilistically modeling variables and more particularly, to a method for analyzing and selectively displaying the probabilistic relationship between the various permissible values of at least two variables.
BACKGROUND OF THE INVENTION
A process, condition, attribute, or phenomena, or an occurrence of such a condition, process, or phenomena is typically dependent upon the occurrence of and/or type of and/or value of other various events or conditions (“the underlying variables”). For example and without limitation, the length of an individual's life may be related to such variables as the age of the individual as well as to certain habits of the individual (e.g. smoking). Further by way of example and without limitation, the overall reliability attribute or characteristic of a particular vehicle may be related to the age or the time in service of the vehicle. Warranty events and, more particularly, the occurrence of such warranty events may also be related to the age of the vehicle.
In order to understand or analyze the occurrence of an event or the event itself and/or in order to analyze the various attributes of an item, it is desirable to understand or analyze the interrelationship between at least some of these various underlying variables (i.e., the manner in which certain combinations of different types or values of these underlying variables influence or effect the event or the occurrence of the event and/or the manner in which these combinations evidence the existence, non-existence, or characteristics of these attributes).
While many techniques exist to generally analyze or investigate the relationship of some of these variables to the condition/event or attribute of interest, none of the current techniques provide a substantial and accurate analysis of the overall reliability of a manufactured good, such as a vehicle, and the number of warranty claims associated with or predicted to be associated with a particular vehicle. Further, none of these techniques accurately allows or provides for an analysis of the potential occurrence of certain underlying variable combinations, effective to allow one to accurately make certain predictions or analyses of an event or phenomena and to allow one to create or devise certain programs or procedures related to a manufactured item or good (i.e., warranty protection programs, insurance programs, and service programs).
There is therefore a need for a new and improved method for ascertaining the nature of an attribute or characteristic of a good, such as a vehicle, and for analyzing events and/or occurrences of events related to the good (e.g. warranty claims).
SUMMARY OF THE INVENTION
It is a first object of the present invention to provide a method for analyzing events or occurrences of such events which overcomes the various and previously delineated drawbacks of prior methods.
It is a second object of the present invention to provide a method for analyzing various variables and/or conditions of a vehicle which overcomes the various and previously delineated drawbacks of prior methodologies and which allows for a relatively accurate indication and/or assessment to be made of the overall reliability of the vehicle.
It is a third object of the present invention to provide a method for analyzing the interrelationship between various underlying variables, effective to provide an indication of the liklihood of the occurrence of these variables and further effective to allow for the overall reliability of a vehicle to be measured.
According to a first aspect of the present invention, a method is provided for analyzing an attribute of a product. The method includes the steps of creating a first variable; creating a second variable; providing a first value for the first variable; providing a second value for the second variable; computing the likelihood that the first variable will have the first value when the second variable has the second value; and analyzing said attribute by use of said computed likelihood.
According to second aspect of the present invention, another method is provided. The method includes the steps of identifying a first vehicle having a first time in service when the first vehicle was driven a certain first distance; identifying a second vehicle having a second time in service when the second vehicle was driven a second distance; creating a first data point by use of the first time in service and the first distance; creating a second data point by use of the second time in service and said second distance; and assigning a certain respective probability to the first and to the second data points.
These and other features, advantages, and aspects of the present invention will become apparent by reading the following detailed description of the preferred embodiment of the invention and by reference to the following drawings.
REFERENCES:
patent: 6061610 (2000-05-01), Boer
Modeling and measuring the effects of vagueness in decision models, Chavez, T.; Systems, Man and Cybernetics, Part A, IEEE Transactions on , vol.: 26 Issue: 3, May 1996, pp. 311-323.*
Tradeoffs in knowledge-based construction of probabilistic models, Provan, G.M.; Systems, Man and Cybernetics, IEEE Transactions on , vol.: 24 Issue: 11, Nov. 1994, pp. 1580-1592.*
Multitarget tracking in clutter: fast algorithms for data association, Zhou, B.; Bose, N.K. Aerospace and Electronic Systems, IEEE Transactions on, vol.: 29 Issue: 2, Apr. 1993, pp. 352-363.*
PSACOIN level 0 intercomparison-an international verification exercise on a hypothetical safety assessment case study, Saltelli, A.; Andres, T.H.; Goodwin, B.W.; Sartori, E.; Carlyle, S.G.; System Sciences, 1989. vol. II: Software Track, 1989 pps. 267-274.
Bruce Stephen Frederick
Golec Daniel Peter
Hausner Christopher Karl
Follansbee John A.
Ford Motor Company
Holmes Michael B.
McKenzie F. G.
LandOfFree
Method of probabilistically modeling variables does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method of probabilistically modeling variables, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of probabilistically modeling variables will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3066120