Intuit has been granted a patent for a method that uses a statistical approach to correct errors in text fields of financial transactions. The method involves extracting transactions from financial institutions using web scraping and then applying a statistical analysis to determine the correct alternative when errors are detected. The incorrect alternative is replaced with the correct alternative in the text field. GlobalData’s report on Intuit gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Intuit, Dynamic premium pricing was a key innovation area identified from patents. Intuit's grant share as of September 2023 was 60%. Grant share is based on the ratio of number of grants to total number of patents.

Text field error correction in financial transaction extraction

Source: United States Patent and Trademark Office (USPTO). Credit: Intuit Inc

A recently granted patent (Publication Number: US11775737B2) describes a computing system implemented method for generating corrected text field data based on removing numeric characters and delimiter characters from the text field data. The method involves generating first stripped text field data by removing numeric characters, and then determining unigram count data and bigram count data for each unigram and bigram within the first stripped text field data. Additionally, second stripped text field data is generated by removing numeric characters and delimiter characters, such as tabs, commas, or semicolons. The method further involves detecting inconsistencies within the second stripped text field data and determining a pair ratio for equivalent unigrams and bigrams within the first stripped text field data based on the count data. In response to detecting an inconsistency, corrected text field data is generated based on the pair ratio.

The method also includes determining pairs of equivalent unigrams and bigrams from the first stripped text field data, where the pair ratio is based on these determined pairs. The pair ratio is compared with a threshold, and if it exceeds the threshold, the corrected text field data is generated. The corrected text field data is selected from the equivalent unigrams and bigrams.

The patent also describes a system comprising at least one processor and memory that stores instructions for executing the method. The system generates stripped text field data, determines count data, detects inconsistencies, and generates corrected text field data based on the pair ratio.

In another embodiment, the method involves determining unigrams and bigrams in the first stripped text field data, generating second stripped text field data by removing numeric characters and delimiter characters, detecting inconsistencies within the second stripped text field data, determining count data for each unigram and bigram in the first stripped text field data, determining a pair ratio for equivalent unigrams and bigrams, and generating corrected text field data based on the pair ratio. The corrected text field data can be generated by replacing equivalent unigrams with equivalent bigrams or vice versa, based on the number of equivalent unigrams or bigrams in the first stripped text field data.

Overall, this patent presents a method and system for generating corrected text field data by removing numeric characters and delimiter characters, detecting inconsistencies, and determining a pair ratio for equivalent unigrams and bigrams. The corrected text field data is generated based on this pair ratio, providing improved accuracy and consistency in text field data processing.

To know more about GlobalData’s detailed insights on Intuit, 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.