Classifying digital documents in multi-document transactions based on embedded dates
AssigneeInternational Business Machines Corporation
InventorsANDREW R. FREED, CORVILLE O. ALLEN
Life of this patent
Estimating the term…
Abstract
A generator categorizes documents in one or more transactions into buckets, each identified by a separate category for an expected time window based on a separate relative age of each of the documents evaluated from one or more dates identified in the documents. The generator trains a document classifier with a model of the separate relative age of each of the documents as a temporal characteristic correlated with the respective category of a respective bucket of the buckets. The document classifier executes on a input documents to classify each of the input documents as a particular logical type identified by a particular category from among multiple logical types.
Claims20
A method comprising:
- categorizing, by a computer system, a plurality of documents in one or more transactions into a plurality of buckets each identified by a separate category of a plurality of categories for an expected time window based on a separate relative age of each of the plurality of documents evaluated from one or more dates identified in the plurality of documents;
- training, by the computer system, a document classifier with a model of the separate relative age of each of the plurality of documents as a temporal characteristic correlated with the respective category of a respective bucket of the plurality of buckets;
- and
- executing, by the computer system, the document classifier on a plurality of input documents to classify each of the plurality of input documents as a particular logical type identified by a particular category from among a plurality of logical types.
A computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable storage devices, and program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
- program instructions to categorize a plurality of documents in one or more transactions into a plurality of buckets each identified by a separate category of a plurality of categories for an expected time window based on a separate relative age of each of the plurality of documents evaluated from one or more dates identified in the plurality of documents;
- program instructions to train a document classifier with a model of the separate relative age of each of the plurality of documents as a temporal characteristic correlated with the respective category of a respective bucket of the plurality of buckets;
- and
- program instructions to execute the document classifier on a plurality of input documents to classify each of the plurality of input documents as a particular logical type identified by a particular category from among a plurality of logical types.
A computer program product comprises a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a computer to cause the computer to:
- categorize, by the computer, a plurality of documents in one or more transactions into a plurality of buckets each identified by a separate category of a plurality of categories for an expected time window based on a separate relative age of each of the plurality of documents evaluated from one or more dates identified in the plurality of documents;
- train, by the computer, a document classifier with a model of the separate relative age of each of the plurality of documents as a temporal characteristic correlated with the respective category of a respective bucket of the plurality of buckets;
- and
- execute, by the computer, the document classifier on a plurality of input documents to classify each of the plurality of input documents as a particular logical type identified by a particular category from among a plurality of logical types.
Dependencies are inferred from the claim text.