Smaller proximate search index

A data management system comprising:

• one or more computer processors;
• and
• one or more computer-readable mediums storing instructions that, when executed by the one or more computer processors, cause the data management system to perform operations comprising:
• accessing a set of vectors, each vector containing binary values and being assigned a numerical vector identifier;
• for each vector from the set of vectors, generating a corresponding set of sequentially ordered vector blocks, each vector block from the corresponding set of sequentially ordered vector blocks containing a set of two or more binary values ordered sequentially in the vector and the numerical vector identifier for the vector;
• generating a block index based on each corresponding set of sequentially ordered vector blocks, the block index including a set of vector block arrays, each vector block array corresponding to a respective sequential position and including one vector block from each of the corresponding sets of sequentially ordered vector blocks that are in the respective sequential position, the vector blocks in each vector block array being are ordered sequentially based on the two or more sequential binary values in each respective vector block;
• and
• for each vector block array, combining pairs of sequentially ordered vector blocks containing matching sets of two or more binary values into combined vector blocks, each combined vector block containing the respective matching set of two or more binary values and numerical vector identifiers assigned to the respective pair of sequentially ordered vector blocks that were combined to form the combined vector block.

A non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of a computing system, cause the computing system to perform operations comprising:

• accessing a set of vectors, each vector containing binary values and being assigned a numerical vector identifier;
• for each vector from the set of vectors, generating a corresponding set of sequentially ordered vector blocks, each vector block from the corresponding set of sequentially ordered vector blocks containing a set of two or more binary values ordered sequentially in the vector and the numerical vector identifier for the vector;
• generating a block index based on each corresponding set of sequentially ordered vector blocks, the block index including a set of vector block arrays, each vector block array corresponding to a respective sequential position and including one vector block from each of the corresponding sets of sequentially ordered vector blocks that are in the respective sequential position, the vector blocks in each vector block array being are ordered sequentially based on the two or more sequential binary values in each respective vector block;
• and
• for each vector block array, combining pairs of sequentially ordered vector blocks containing matching sets of two or more binary values into combined vector blocks, each combined vector block containing the respective matching set of two or more binary values and numerical vector identifiers assigned to the respective pair of sequentially ordered vector blocks that were combined to form the combined vector block.