US Patent 10235449 Extracting product facets from unstructured data

Disclosed is a platform for assessing queries related to a catalog entry. The platform is able to determine what attributes of the catalog entry the query is directed to using one or more language processing techniques. Once an attribute is identified, the platform may check for appropriate unit types and/or formats based on a category associated with the attribute. The platform then parses additional data associated with the catalog entry (or another catalog entry within the same browse node) to identify a set of potential values for the identified attribute. One or more rule sets may be used to filter the set of potential values to a single probable value, which may then be provided in a response to the query.