Ranking Pattern Matches

[Mousheng Xu <xu@xxxxxxxxxx>]

Hi, Smarties,
	Suppose you have an empirical pattern database, each pattern has its
number of instances found in the collected real world. If two patterns have
been searched out that match against a board, suppose:
	1. The two patterns are of different lengths (e.g., 5 stones vs. 4 stones);
	2. The shorter pattern is not a subpattern of the longer one;
	3. The shorter pattern has a larger number of instances in the database
than the longer one.

	How do you rank the two patterns? Obviously, there are two factors
considered here: length & number of instances collected. How do you balance
these two factors? Given an arbituray example, one pattern has 5 stones,
and there are 2 instances of this same pattern in the database; the other
pattern has 4 stones, which is shorter than 5, but there are 36 instances
of it in the database. Which pattern would be a better match? If the 4
stone pattern is a subpattern of the 5 stone pattern, you most likely will
prefer the longer pattern. But if this is not the case, how do you weight
them?
	Thanks a lot.

-- Mousheng Xu