| 主权项 |
1. A method performed with a distributed computing system for classifying one or more commodities, the method comprising:
matching one or more attributes of a commodity with one or more terms of a plurality of terms in a word matrix, the word matrix comprising a plurality of nodes and a plurality of links, each node including a term of the plurality of terms, and each link connecting two or more nodes and defining a similarity between the two or more nodes; generating, based on the matching, a particular vector for the commodity; identifying a vector space including two or more vectors, the one or more vectors including the particular vector; identifying, by a support vector machine, one or more decision surfaces that separate the vector space into one or more classification regions, wherein each classification region includes at least one of the two or more vectors and corresponds to a classification; identifying, based on the vector, a particular classification region of the one or more classification regions; receiving a query from an enterprise computing system, the query comprising data associated with the commodity; and preparing data associated with the particular classification for display at the enterprise computing system. |
