Abstract: A system and method for natural language processing for document sequences comprises a computing device configured to train a neural network as a function of a corpus of documents, wherein training comprises receiving the corpus of documents, identifying significant terms, and tuning, as a function of the corpus of documents, the neural network to generate a plurality of vectors for each significant term of the plurality of significant terms, a vector in a vector space representing semantic relationships between the significant terms and semantic units in the corpus of documents, receive a current document sequence including a plurality of documents in a sequential order, map a plurality of mapped terms of the plurality of significant terms to the plurality of documents as a function of the neural network and the plurality of vectors, and generate a plurality of timelines as a function of the sequential order and the mapped terms.
Type:
Grant
Filed:
March 18, 2021
Date of Patent:
May 14, 2024
Assignee:
Augmented intelligence Technologies, Inc.
Inventors:
Martin Elisco, Jim Lindstrom, Logan Courtney
Abstract: A system and method for natural language processing for document sequences comprises a computing device configured to train a neural network as a function of a corpus of documents, wherein training comprises receiving the corpus of documents, identifying significant terms, and tuning, as a function of the corpus of documents, the neural network to generate a plurality of vectors for each significant term of the plurality of significant terms, a vector in a vector space representing semantic relationships between the significant terms and semantic units in the corpus of documents, receive a current document sequence including a plurality of documents in a sequential order, map a plurality of mapped terms of the plurality of significant terms to the plurality of documents as a function of the neural network and the plurality of vectors, and generate a plurality of timelines as a function of the sequential order and the mapped terms.
Type:
Application
Filed:
March 18, 2021
Publication date:
September 22, 2022
Applicant:
Augmented Intelligence Technologies, Inc.
Inventors:
Martin Elisco, Jim Lindstrom, Logan Courtney