Extraction rule determination based on user-selected text

This invention describes a computer program that helps users extract specific information from raw data shown in a table. When a user clicks on a piece of text in a table cell, the program automatically figures out a rule to pull out similar information. It then offers this rule as an option, and if selected, uses it to extract all matching data from the rest of the table, specifically focusing on user selections made within the table's cells or columns.

Why it matters: Filed before the widespread availability and capability of large language models. These models can now more effectively infer complex data extraction rules from limited user examples, simplifying the core 'automatic determination' challenge.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedComplex software logic for rule inference

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10