U.S. Bancorp has been granted a patent for a classification code parser and method. The technology involves analyzing text to determine the strength of a match between a classification code and the content based on keyword matching and proximity factors. GlobalData’s report on U.S. Bancorp gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on U.S. Bancorp, Virtual banking assistant was a key innovation area identified from patents. U.S. Bancorp's grant share as of January 2024 was 94%. Grant share is based on the ratio of number of grants to total number of patents.

Classification code parser for matching text with keywords

Source: United States Patent and Trademark Office (USPTO). Credit: U.S. Bancorp

A recently granted patent (Publication Number: US11886819B2) outlines a method for classifying text based on a classification code and generating a note token stream. The method involves removing negative content from the text, creating a keyword map, determining a match ratio and proximity factor, and assessing the strength of the match between the classification code and the text. The classification code includes an ICD-O-3 code and a behavior code, with specific factors influencing the strength calculation, such as the behavior factor. The process also includes tokenizing the text to create the note token stream, utilizing equations to determine match ratio and proximity factor, and generating a keyword map to associate keywords with positions in the text.

Furthermore, the patent describes a non-transitory computer-readable medium storing instructions for executing the classification method. The medium includes steps for generating a note token stream from the text, determining match ratio and proximity factor, and assessing the strength of the match between the classification code and the text. Similar to the method, the computer-readable medium involves specific equations for calculating match ratio and proximity factor, as well as instructions for creating a keyword map and tokenizing the text. The medium provides a structured approach to text classification, particularly in the context of medical codes like ICD-O-3, by utilizing various factors and algorithms to determine the strength of the match between the classification code and the text.

To know more about GlobalData’s detailed insights on U.S. Bancorp, 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

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.