Ranking search results based on word weight

摘要

Ranking search results, comprises retrieving search results that include target strings that relate to a query string; segmenting the query string and each of the target strings; pairing segments in the query string with respective segments in the target strings to form combinations; retrieving weights that correspond to the combinations; and determining a weighted word length based on the weights corresponding to each of the target strings; and ranking the target strings based on their respective weighted word lengths. Alternatively, ranking search results includes determining a minimum weight of each inserted word with respect to segments in the query string; determining a minimum weight of each deleted word with respect to segments in the target strings; determining a total edit distance for each target string; and ranking the target strings based on the total edit distances.

主权项

1. A system, comprising:
one or more processors configured to: retrieve a plurality of search results that includes a corresponding plurality of target strings that relate to a query string; segment the query string and a target string of the plurality of target strings; pair segmented words in the query string with respective segmented words in the target string to form a plurality of word pairs, wherein one word pair of the plurality of the word pairs comprises a segmented word from the query string and a segmented word from the target string; retrieve a plurality of weights that corresponds to the plurality of word pairs based on a mapping of word pairs and their respective weights; select a selected weight corresponding to a word pair including the segmented word from the target string from a subset of the plurality of weights that corresponds to respective ones of word pairs that commonly include the segmented word from the target string;
determine a weighted word length corresponding to the target string based at least in part on selected weights that correspond to word pairs of the plurality of word pairs that comprise segmented words from the target string; andrank the target string among at least a portion of the plurality of target strings based on the weighted word length corresponding to the target string; and one or more memories coupled to the one or more processors and configured to provide the one or more processors with instructions.