17884986. DISCRIMINATIVE MODEL FOR IDENTIFYING AND DEMARCATING TEXTUAL FEATURES IN RISK CONTROL DOCUMENTS simplified abstract (Capital One Services, LLC)
Contents
DISCRIMINATIVE MODEL FOR IDENTIFYING AND DEMARCATING TEXTUAL FEATURES IN RISK CONTROL DOCUMENTS
Organization Name
Inventor(s)
Peter Tanski of Marlborough MA (US)
Matthew Peroni of Bedford MA (US)
Deny Daniel of Medford MA (US)
Ranjith Zachariah of Waltham MA (US)
Viji Soundar of Richmond VA (US)
Kevin Zhang of Braintree MA (US)
DISCRIMINATIVE MODEL FOR IDENTIFYING AND DEMARCATING TEXTUAL FEATURES IN RISK CONTROL DOCUMENTS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17884986 titled 'DISCRIMINATIVE MODEL FOR IDENTIFYING AND DEMARCATING TEXTUAL FEATURES IN RISK CONTROL DOCUMENTS
Simplified Explanation
- A computing system is described that automatically identifies risk control features and entities in a risk control document. - The system uses a generative machine learning model to transform the document into sequences of words, classify risk control features, and pair them with the sequences of words. - A natural language processing model is then used to identify syntactic characteristics of the word sequences. - A discriminative predictor system corrects the classified risk control features based on the identified syntactic characteristics, identifies boundaries of the corrected features, and pairs them with the corrected features.
Potential Applications
- Risk management in various industries such as finance, healthcare, and cybersecurity. - Compliance monitoring and auditing processes. - Enhancing document analysis and information extraction tasks.
Problems Solved
- Automating the identification of risk control features in documents. - Improving accuracy and efficiency in risk management processes. - Enhancing the understanding of complex documents with technical language.
Benefits
- Increased efficiency in identifying and managing risk control features. - Improved accuracy in classifying and analyzing risk-related information. - Enhanced compliance with regulations and standards in various industries.
Original Abstract Submitted
Embodiments disclosed are directed to a computing system that performs steps to automatically identify risk control features and entities in a risk control document. The computing system uses a generative machine learning (ML) model to transform a risk control document into sequences of words, classify risk control features associated with the sequences of words, and pair the sequences of words with the classified risk control features. The computing system then uses a natural language processing (NLP) model to identify syntactic characteristics of the sequences of words. Subsequently, the computing system uses a discriminative predictor system to correct the classified risk control features based on the identified syntactic characteristics, identify boundaries of the corrected classified risk control features, and pair the identified boundaries with the corrected classified risk control features.
