Ranking search results based on word weight

A method, comprising:

• retrieving a plurality of search results that includes a corresponding plurality of target strings that relate to a query string;
• segmenting, using one or more processors, the query string and a target string of the plurality of target strings;
• pairing 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 segmented query string and a segmented word from the target string;
• retrieving a plurality of weights that corresponds to the plurality of word pairs based on a mapping of word pairs and their respective weights;
• selecting 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;
• determining 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;
• and
• ranking 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.

A system for ranking search results, 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;
• determine, based on a mapping of word pairs and their respective weights, a selected weight of each inserted word associated with the target string with respect to segmented words in the query string, wherein to determine the selected weight of the inserted word comprises to select the selected weight of the inserted word from a plurality of weights that corresponds to respective ones of word pairs that commonly include the inserted word;
• determine, based on the mapping of word pairs and their respective weights, a selected weight of each deleted word associated with the query string with respect to segmented words in the target string;
• determine a total edit distance corresponding to the target string based at least in part on the selected weight of each inserted word and the selected weight of each deleted word;
• and
• rank the target string among at least a portion of the plurality of target strings based on the total edit distance 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.

A method for ranking search results, comprising:

• retrieving a plurality of search results that includes a corresponding plurality of target strings that relate to a query string;
• segmenting, using one or more processors, the query string and a target string of the plurality of target strings;
• determining, based on a mapping of word pairs and their respective weights, a selected weight of each inserted word associated with the target string with respect to segmented words in the query string, wherein determining the selected weight of the inserted word comprises selecting the selected weight of the inserted word from a plurality of weights that corresponds to respective ones of word pairs that commonly include the inserted word;
• determining, based on the mapping of word pairs and their respective weights, a selected weight of each deleted word associated with the query string with respect to segmented words in the target string;
• determining a total edit distance corresponding to the target string based at least in part on the selected weight of each inserted word and the selected weight of each deleted word;
• and
• ranking the target string among at least a portion of the plurality of target strings based on the total edit distance corresponding to the target string.