Sampling method for estimating co-occurrence counts

Details Sampling method for estimating co-occurrence counts Sampling method for estimating co-occurrence counts

2005-02-11

2008-09-30

Alam, Hosain T (Department: 2166)

Data processing: database and file management or data structures

Database design

Data structure types

C707S793000, C707S793000, C707S793000

Reexamination Certificate

active

07430550

ABSTRACT:
The subject invention leverages data sampling techniques to provide an efficient means to determine co-occurrence count estimations for objects and features from relational data, simplifying measure-of-association determinations. By providing an efficient mechanism to estimate co-occurrence counts, instances of the subject invention can be incorporated directly into a database, increasing its versatility and performance for such uses as collaborative filtering recommendations. Other instances of the subject invention can be utilized for enhancing database query selectivity, optimizing query performance through employment of á priori co-occurrence counts.

REFERENCES:
patent: 6487541 (2002-11-01), Aggarwal et al.
patent: 6498955 (2002-12-01), McCarthy et al.
patent: 2002/0156763 (2002-10-01), Marchisio
patent: 2002/0178057 (2002-11-01), Bertram et al.
patent: 2002/0199194 (2002-12-01), Ali
patent: 2005/0261987 (2005-11-01), Bezos et al.
D. Chickering, et al., Fast Learning from Sparse Data, In Proceedings of Fifteenth Conference on Uncertainty in Artificial Intelligence, Stockholm, Sweden, Morgan Kaufmann, Aug. 1999. Also appears as Technical Report MSR-TR-00-15, Microsoft Research, Feb. 1999 (Revised May 1999).
Moore, A.W., et al., Cached Sufficient Statistics for Efficient Machine Learning with Large Datasets, Journal of Artificial Intelligence Research, 1998, pp. 67-91, vol. 8.

Affiliated with

Also associated with

Rating

Sampling method for estimating co-occurrence counts does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Sampling method for estimating co-occurrence counts, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Sampling method for estimating co-occurrence counts will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3984037