US 2015/0317281 A1Published application

Generating correlation scores

AssigneeGoogle Inc.

InventorsMatthew Sharifi, Dominik Roblek

Life of this patent

Estimating the term…

Loading patent…

Abstract

A computer-implemented method includes obtaining first and second binary vectors. For each of a plurality of vector locations in a first of j words in the first binary vector, the method includes shifting the binary values for the second binary vector so that a particular one of the binary values in the second binary vector is located at a vector location in a first of the k words in the second binary vector that matches the vector location in the first of j words in the first binary vector. For each of the j words in the first binary vector, the method includes aligning the second binary vector with the word in the first binary vector and determining a binary correlation score. A similarity of the first binary vector and the second binary vector can be determined based at least on one or more of the determined binary correlation scores.

Claims20

Dependent claims

A computer-implemented method, comprising:

obtaining a first binary vector of length X and a second binary vector of length Y, the first and second binary vectors each being segmented into words of length n, the first binary vector of length X being longer than the second binary vector of length Y, the first binary vector comprising respective binary values for a plurality of vector locations 0 through X−1, the second binary vector comprising respective binary values for a plurality of vector locations 0 through Y−1;
aligning the second binary vector in a first position with respect to the first binary vector so that each of the binary values in the second binary vector aligns with a respective binary value in the first binary vector;
generating a binary correlation score for the first position of the second binary vector with respect to the first binary vector by performing respective binary operations between each binary value in the second binary vector in the first position and the aligned binary value in the first binary vector;
aligning the second binary vector in a second position with respect to the first binary vector, without shifting binary values of the second binary vector to different vector locations in the second binary vector, so that each of the binary values in the second binary vector aligns with a respective binary value in the first binary vector, the second position being offset by a multiple of n vector locations from the first position with respect to the first binary vector;
generating a binary correlation score for the second position of the second binary vector with respect to the first binary vector by performing respective binary operations between each binary value in the second binary vector in the second position and the aligned binary value in the first binary vector;
and
determining whether the first binary vector is similar to the second binary vector based at least on one or more of the binary correlation scores.

4 more elements

A computer-implemented method, comprising:

obtaining a first binary vector of length X and a second binary vector of length Y, the first binary vector of length X being longer than the second binary vector of length Y, the first binary vector being segmented into j words of length n, the second binary vector being segmented into k words of length n, the first binary vector comprising respective binary values for a plurality of vector locations 0 through X−1, the second binary vector comprising respective binary values for a plurality of vector locations 0 through Y−1;
for each of a plurality of vector locations in a first of the j words in the first binary vector:
shifting the binary values for the second binary vector so that a particular one of the binary values in the second binary vector is located at a vector location in a first of the k words in the second binary vector that matches the vector location in the first of the j words in the first binary vector, and
for each of the j words in the first binary vector, aligning the second binary vector with the word in the first binary vector and determining a binary correlation score;
and
determining a similarity of the first binary vector and the second binary vector based at least on one or more of the determined binary correlation scores.

3 more elements

One or more computer-readable storage devices including instructions that, when executed by one or more computer processors, cause the one or more computer processors to perform operations comprising:

obtaining a first binary vector of length X and a second binary vector of length Y, the first binary vector of length X being longer than the second binary vector of length Y, the first binary vector being segmented into j words of length n, the second binary vector being segmented into k words of length n, the first binary vector comprising respective binary values for a plurality of vector locations 0 through X−1, the second binary vector comprising respective binary values for a plurality of vector locations 0 through Y−1;
for each of a plurality of vector locations in a first of the j words in the first binary vector:
shifting the binary values for the second binary vector so that a particular one of the binary values in the second binary vector is located at a vector location in a first of the k words in the second binary vector that matches the vector location in the first of the j words in the first binary vector, and
for each of the j words in the first binary vector, aligning the second binary vector with the word in the first binary vector and determining a binary correlation score;
and
determining a similarity of the first binary vector and the second binary vector based at least on one or more of the determined binary correlation scores.

3 more elements

Dependencies are inferred from the claim text.