eBay Inc.
Smaller Proximate Search Index

Abstract:

A data management system accesses a set of vectors containing binary values and generates vector blocks comprising binary values from each vector. Each of at least a portion of the vector blocks for each vector contain a set of two or more binary values from the vector. The data management system generates a block index based on the vector blocks. The block index includes a set of vector block arrays, each vector block array corresponding to a position in the vectors and including the binary values of a vector block from each vector. The data management system can identify relevant vectors for a target vector by generating vector blocks from the target vector and querying the block index to identify candidate vectors.