Document entity extraction using machine-learned models

WO2025042893A3 Publication Date: 2025-04-17GOOGLE LLC
4 Cites 0 Cited by

Patent Information

Application Number
PCT/US2024/043042
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-08-21
Filing Date
2024-08-20
Publication Date
2025-04-17

AI Technical Summary

Technical Problem

Existing document entity extraction techniques rely on hand-crafted parsers or specific machine-learned models, which are costly to instantiate and lack flexibility to parse new document types effectively.

Method used

A computer-implemented method and system for document entity extraction using a machine-learned model, where an inference document and a target schema are processed to generate document and schema inputs, which are then used to extract entity data with reference and inference location tags for validation.

Benefits of technology

The approach enables accurate and flexible document entity extraction by grounding model outputs in the document rendering, mitigating errors, and allowing for the processing of arbitrary documents and schemas, thereby improving reliability and reducing costs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Systems and methods for performing document entity extraction are described herein. The method can include receiving an inference document and a target schema. The method can also include generating one or more document inputs from the inference document and one or more schema inputs from the target schema. The method can further include, for each combination of the document input and schema input, obtaining one or more extraction inputs by generating a respective extraction input based on the combination, providing the respective extraction input to the machine-learned model, and receiving a respective output of the machine-learned model based on the respective extraction. The method can also include validating the extracted entity data based on reference spatial locations and inference spatial locations and outputting the validated extracted entity data.
Need to check novelty before this filing date? Find Prior Art