Patent · US Active

System for handling workplace queries using online learning to rank

US11803556B1 · kind B1 · utility

8Cited by

11References

22Claims

0Family size

Inventors

Rajhans Samdani · Belmont, US
Ankit Goyal · Great Falls, US
Pierre Rappolt · San Francisco, US
Pratyus Patnaik · Los Altos, US

Key dates

Filing date	Jul 24, 2019
Grant date	Oct 31, 2023
Priority date	—
Expiry date	Feb 11, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/045
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A system creates and searches knowledge base (KB) articles inside an organization while supporting operation as a SaaS (Software as-a-Service) across a plurality of organizations. The system implements a real-time online learning-to-rank (L2R) algorithm for learning relevance scoring that is customized to each organization. This algorithm incorporates rich lexical features using a query similarity kernel. A scoring function includes a pairwise static module, which may be trained off-line using training data, and a lexical adaptive module, which is trained on-line based on user feedback. The scoring function makes the system easy to deploy, modify, and suitable for handling events that naturally happen over the lifecycle of any KB deployment, without manual training.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.