Patent · US Active

Machine learning systems for computer generation of automated recommendation outputs

US11538076B1 · kind B1 · utility

4Cited by
5References
15Claims
0Family size

Assignee

Inventor

Key dates

Filing dateNov 23, 2020
Grant dateDec 27, 2022
Priority date
Expiry dateApr 29, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06Q30/0205
  • WIPO fieldIT methods for management
  • WIPO sectorElectrical engineering

Abstract

A computerized method of automatically generating a recommendation output includes training a machine learning model with historical feature vector inputs to generate a recommendation output, generating a set of inputs specific to an entity, and transforming the set of inputs into a profile data structure. The profile data structure includes multiple attributes. The transforming includes, for each attribute, assigning a preference according to the set of inputs. The method includes obtaining structured supplemental data associated with the entity. The method includes obtaining a set of option identifiers by filtering the option identifiers according to option criteria specific to the entity. The method includes creating a feature vector input according to the set of option identifiers, the structured supplemental data, and the assigned preferences of the profile data structure. The method includes processing, by the machine learning model, the feature vector input to generate the recommendation output.

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