US 2022/0101065 A1 · AUTOMATIC DOCUMENT SEPARATION

Abstract

In an approach for an automatic document separation, a processor extracts one or more features from a document containing a plurality of pages. A processor generates a data frame based on the feature extraction. In response to analyzing a similarity between the plurality of pages, a processor determines whether the similarity exceeds a predetermined threshold. In response to determining that the similarity does not exceed the predetermined threshold, a processor transforms text into vectors forming float arrays. In response to benchmarking a set of predetermined clustering algorithms, a processor identifies a clustering algorithm using a predetermined criterion. A processor clusters the plurality of pages, using the clustering algorithm, to create a group of pages. A processor validates the clustered group of pages. In response to passing validation, a processor generates a set of final separated files based on the clustered group of pages.

Claims20

Dependent claims

A computer-implemented method comprising:

extracting, by one or more processors, one or more features from a document containing a plurality of pages;
generating, by one or more processors, a data frame based on the feature extraction;
in response to analyzing a similarity between the plurality of pages, determining, by one or more processors, whether the similarity exceeds a predetermined threshold;
in response to determining that the similarity does not exceed the predetermined threshold, transforming, by one or more processors, text into vectors forming float arrays;
in response to benchmarking a set of predetermined clustering algorithms, identifying, by one or more processors, a clustering algorithm using a predetermined criterion;
clustering, by one or more processors, the plurality of pages, using the clustering algorithm, to create a group of pages;
validating, by one or more processors, the clustered group of pages;
and
in response to passing validation, generating, by one or more processors, a set of final separated files based on the clustered group of pages.

6 more elements

A computer program product comprising:

one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to extract one or more features from a document containing a plurality of pages;
program instructions to generate a data frame based on the feature extraction;
program instructions to, in response to analyzing a similarity between the plurality of pages, determine whether the similarity exceeds a predetermined threshold;
program instructions to, in response to determine that the similarity does not exceed the predetermined threshold, transform text into vectors forming float arrays;
program instructions to, in response to benchmarking a set of predetermined clustering algorithms, identify a clustering algorithm using a predetermined criterion;
program instructions to cluster the plurality of pages, using the clustering algorithm, to create a group of pages;
program instructions to validate the clustered group of pages;
and
program instructions to, in response to passing validation, to generate a set of final separated files based on the clustered group of pages.

7 more elements

A computer system comprising:

one or more computer processors, one or more computer readable storage media, and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:
program instructions to extract one or more features from a document containing a plurality of pages;
program instructions to generate a data frame based on the feature extraction;
program instructions to, in response to analyzing a similarity between the plurality of pages, determine whether the similarity exceeds a predetermined threshold;
program instructions to, in response to determine that the similarity does not exceed the predetermined threshold, transform text into vectors forming float arrays;
program instructions to, in response to benchmarking a set of predetermined clustering algorithms, identify a clustering algorithm using a predetermined criterion;
program instructions to cluster the plurality of pages, using the clustering algorithm, to create a group of pages;
program instructions to validate the clustered group of pages;
and
program instructions to, in response to passing validation, to generate a set of final separated files based on the clustered group of pages.

7 more elements

Dependencies are inferred from the claim text.

Automatic document separation

Life of this patent

Automatic document separation

Life of this patent

Abstract

Claims20