Blending content in an output

摘要

Techniques include obtaining ranges of content relevance scores for different collections of content; generating a normalized range based on the ranges of content relevance scores; and normalizing a particular range of a particular collection of content including: generating a distribution of content relevance scores for the collection of content; identifying portions in the distribution; and generating a mapping of portions from the distribution to portions in the normalized range.

主权项

1. A method comprising:
obtaining ranges of content relevance scores for different collections of content; generating a normalized range of normalized values based on the ranges of content relevance scores; normalizing a particular range of a particular collection of content by
generating a distribution of content relevance scores for the particular collection of content;dividing the distribution into first subsets, with a first subset including a portion of the content relevance scores in the distribution;dividing the normalized range into a plurality of second subsets, with a second subset including one or more of the normalized values;generating a mapping of the first subsets to the second subsets;selecting a content relevance score from the distribution;determining one of the first subsets that includes the content relevance score selected;determining one of the second subsets that is mapped to the one of the first subsets;identifying a normalized value included in the one of the second subsets; andupdating the content relevance score with the normalized value; performing searches of the different collections of content to identify content that is relevant to a search query; determining where, in the normalized range, content relevance scores corresponding to the identified content fall; ranking the identified content based, at least in part, on where the content relevance scores fall in the normalized range; and outputting at least part of the identified content based the ranking.