公开(公告)号：US20250021602A1

公开(公告)日：2025-01-16

申请号：US18900105

申请日：2024-09-27

Applicant: Amazon Technologies, Inc.

Inventor： Shrikant G Nayak ,  Sathya Prakash Podila Venkata Subramanya ,  Divya Nalam ,  Vijay Daniel Manason ,  Valluri Subbanna Chowdary

IPC: G06F16/84 ,  G06F18/214 ,  G06F40/154 ,  G06F40/16 ,  G06N5/02 ,  G06N20/20

Abstract: Results of applying a set of voting rules to a target corpus of documents are used to obtain a set of derived probabilistic labels indicating the probabilities of the presence of a particular attribute within the documents' constituent objects. A machine learning model is trained to identify a candidate portion of a document from which a value of the attribute is to be extracted. The training data for the model includes learned representations obtained from paths of constituent objects, and the corresponding derived labels. A proposed value for the attribute, obtained based on an assigned attribute value presence probability score for an individual constituent object from a selected candidate portion of a document, is provided.

公开(公告)号：US12130863B1

公开(公告)日：2024-10-29

申请号：US17107633

申请日：2020-11-30

Applicant: Amazon Technologies, Inc.

Inventor： Shrikant G Nayak ,  Sathya Prakash Podila Venkata Subramanya ,  Divya Nalam ,  Vijay Daniel Manason ,  Valluri Subbanna Chowdary

IPC: G06F16/80 ,  G06F16/84 ,  G06F18/214 ,  G06F40/154 ,  G06F40/16 ,  G06N5/02 ,  G06N20/20

CPC classification number: G06F16/86 ,  G06F18/2148 ,  G06F40/154 ,  G06F40/16 ,  G06N5/02 ,  G06N20/20

Abstract: Results of applying a set of voting rules to a target corpus of documents are used to obtain a set of derived probabilistic labels indicating the probabilities of the presence of a particular attribute within the documents' constituent objects. A machine learning model is trained to identify a candidate portion of a document from which a value of the attribute is to be extracted. The training data for the model includes learned representations obtained from paths of constituent objects, and the corresponding derived labels. A proposed value for the attribute, obtained based on an assigned attribute value presence probability score for an individual constituent object from a selected candidate portion of a document, is provided.