Royal Bank of Canada

The Bank of Nova Scotia

Ajinkya Kulkarni

Iman Rezaeian

Xiuzhan Guo

Brechann McGoey

Kostya Belezko

Guang Wang

Tanaby Zibamanzar Mofrad

Min Li

Patrick Allan Heiland

Andrew Peter Kujtan

Simrandeep Singh

Andrew Gordon Storey

Pragnya Addala

Barak Edelstein

Saif Charaniya

Yannick Lallement

Matthew Chang-kit

A system for generating a storage-efficient data structure representing a plurality of inter-related data tables and adapted for use in data processing. The system configured to receive input data and generate a graph database having edges and vertices. Each inter-related data table of a plurality of inter-related data tables is received as input data and defines a corresponding vertex of the vertices. The edges defining pairwise relationships between the vertices based on one or more common elements of a corresponding pair of data tables. A reduced graph database is generated, as well as its connected-components. A partition defined by an equivalence relation on the graph database is used to generate the reduced graph database. Each set of the plurality of sets of the partition is represented by a single vertex of the corresponding set. An output data structure indicative of the connected-components, or additionally or alternatively, the irreducible generators, is generated.

Systems and methods for generating graph data structure objects with homomorphism

The present disclosure pertains to a system and method for determining differences between at least two documents. A preferred embodiment disclosed herein pertains to a system and method for determining differences in the text or terms of legal documents, for example transactional legal agreements, such as but not limited to Trade Confirmations. The document review system can compare text documents to other text documents but is further capable of comparing text documents to structured spreadsheet data. The combination of static component verification in combination with dynamic component verification leads to a powerful tool which greatly reduces the time and efficient of document review while reducing the risk of human errors. Utilizing word embeddings in the static verification in combination with the use of named entity recognition, rule parsers in the dynamic verification, enables the system to produce concise and meaningful summaries of differences between multiple documents.

System and method for reviewing and evaluating discrepancies between two or more documents

Growing community of inventors

Toronto, Canada

Ajinkya Kulkarni