Fuzzy proximity boosting and influence kernels

摘要

A method and apparatus are provided for ranking documents according to relevancy scoring. In one implementation, a computer-implemented method is provided for receiving, from a database over a network, a document resulting from a search on a database, the document containing terms that match the search criteria. The method may calculate a standard deviation of a probability distribution function representing a distribution of the terms in the document that match the search criteria. The method may further determine relative distances between the terms in the document that match the search criteria according to the standard deviation. The method may further calculate a proximity boost value using the relative distances, and apply the proximity boost value to a base relevancy score of the document to determine a relevancy ranking. The document may then be ranked according to the relevancy ranking.

主权项

1. A computer-implemented ranking method comprising:
sending, to a remote computer system via a network, a search query containing query terms; obtaining, at the remote computer system, documents resulting from performing the search query on a document database, the documents containing terms that match the search query; determining base relevancy scores for the documents; adjusting the base relevancy scores by applying a lead boosting value calculated according to an influence function, the influence function promoting a particular word position in a document, the particular word position being a predetermined number of words from the beginning of the document; and ranking the documents according to the adjusted base relevancy scores.