Systems and methods for machine learning-enhanced pairing of user search stimuli-to-online digital profile data
US11386162B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 4, 2022 |
| Grant date | Jul 12, 2022 |
| Priority date | — |
| Expiry date | Mar 4, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/20
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system and method for pairing user stimuli-to-online digital profile data includes receiving user stimulus data; computing a classification inference, by a machine learning-based model, based on features extracted from the user stimulus data, wherein the classification inference includes a machine learning-based classification label identified from a plurality of digital profile subdomain classification labels; constructing a digital profile search query, wherein constructing the digital profile search query includes: deriving a digital profile search parameter based on the machine learning-based classification label, and defining the digital profile search query using the digital profile search parameter; executing the digital profile search query, wherein executing the digital profile search query includes: searching a corpus of digital profile data based on the digital profile search parameter; and selectively pairing the digital profile search query to digital profiles of the corpus of digital profile data based on the search parameter; and displaying the digital profiles.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.