First American Financial‘s patent involves multimodal techniques to classify start pages and document types in unstructured document image packages. The method includes using multiple trained models and a neural network to generate predictions for each page. The patent aims to streamline document processing and organization. GlobalData’s report on First American Financial gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on First American Financial, Virtual banking assistant was a key innovation area identified from patents. First American Financial's grant share as of April 2024 was 84%. Grant share is based on the ratio of number of grants to total number of patents.
Classification of document types using multimodal techniques
A recently granted patent (Publication Number: US11935316B1) discloses a computer-readable medium with executable instructions that, when processed by a computer, perform operations involving the analysis of document image files. The method includes generating predictions for each page of the document image file using multiple trained models, combining these predictions into a final output, and utilizing a neural network to determine if the page is the first page of a document or corresponds to a specific document type. The trained models encompass various features such as font changes, margin changes, image features, and textual features to make accurate predictions.
Furthermore, the patent details a method for obtaining feature embeddings for each page of a document image file using dependent models of a neural network. These feature embeddings, including image features, textual features, font features, and margin features, are combined and input into a neural network to predict whether the page is the first page of a document or corresponds to a particular document type. The patent also outlines the use of tensors to represent these features and the generation of likelihood outputs for each page, indicating the probability of being the first page of a document or associated with a specific document type. The method aims to enhance document analysis and classification processes by leveraging advanced machine learning techniques.
To know more about GlobalData’s detailed insights on First American Financial, 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.
