Genpact has been granted a patent for a method and system that utilizes machine learning to match records between dissimilar databases. The process involves selecting character sequences, identifying unique identifiers, and applying analytical models to enhance accuracy in record matching and retrieval. GlobalData’s report on Genpact gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Genpact, was a key innovation area identified from patents. Genpact's grant share as of July 2024 was 79%. Grant share is based on the ratio of number of grants to total number of patents.
Method for matching records between dissimilar databases using ml
The patent US12061605B2 outlines a method and system for matching records between two dissimilar databases using advanced machine learning techniques. The process begins with receiving a record from a first database, followed by selecting a sequence of characters within that record. The method employs multiple machine learning models, including an identity model utilizing regular expression matching, a named entity recognition model based on conditional random fields, and pattern similarity models that leverage term frequency-inverse document frequency (TF-IDF) and word embedding vectors. These models work together to identify and extract information predicted to serve as an identifier for the record in the first database, which is then prioritized and aggregated based on confidence scores. If the confidence score surpasses a predetermined threshold, the extracted information is used as a digital key to retrieve a corresponding record from a second, dissimilar database.
The claims further specify that the first database may be a bank database, with records such as bank statements, while the second database could be a customer invoice database. The digital key can be defined by various parameters, including customer account numbers or invoice numbers, and may involve regular expression-based extraction or entity name recognition processes. The system is designed to continuously improve its predictive capabilities by retraining the machine learning models in response to alerts associated with the extracted information. Additionally, post-prediction operations include identifying and processing open records linked to the user based on the digital key. Overall, the patent presents a comprehensive approach to enhancing database record matching through sophisticated analytical processes and machine learning methodologies.
To know more about GlobalData’s detailed insights on Genpact, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
