US 12,443,608 B1
Personalized smart provider search
Lakshmi Manohar Akella, Naperville, IL (US); Adarsh Ramesh, Schaumburg, CT (US); Gregory Andrew Allard, East Lyme, CT (US); Shawn Wang, Kildeer, IL (US); and Ariel Bayewitz, Teaneck, NJ (US)
Assigned to Elevance Health, Inc., Indianapolis, IN (US)
Filed by Elevance Health, Inc., Indianapolis, IN (US)
Filed on Dec. 6, 2021, as Appl. No. 17/543,565.
Application 17/543,565 is a continuation of application No. 16/511,539, filed on Jul. 15, 2019, granted, now 11,194,820.
Application 16/511,539 is a continuation of application No. 16/234,918, filed on Dec. 28, 2018, granted, now 10,353,908.
Claims priority of provisional application 62/759,919, filed on Nov. 12, 2018.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/20 (2019.01); G06F 16/2457 (2019.01); G06F 16/90 (2019.01); G06F 16/9535 (2019.01)
CPC G06F 16/24578 (2019.01) [G06F 16/9535 (2019.01)] 29 Claims
OG exemplary drawing
 
1. A method for recommending one or more providers to a member, the method comprising:
at a server:
computing a member vector representative of one or more member characteristics representative of the member, wherein computing the member vector includes:
arranging the member characteristics into a member characteristics vector;
multiplying the member characteristics vector by a member feature matrix of learnt latent weights for each of the member characteristics to generate a member-characteristic-feature vector;
summing the member-characteristic-feature vector and a learnt member parameters vector to generate a member vector; and
storing the member vector;
after computing the member vector, receiving, from a computing device, a provider request including a member identifier and member specified criteria, wherein the member specified criteria include member preference fora provider treating a condition of the member, and wherein the one or more member characteristics are separate and distinct from the member specified criteria;
after receiving the provider request:
retrieving the member vector;
retrieving one or more provider identifiers for association with the member specified criteria;
for each provider identifier, retrieving one or more provider characteristics for association with the provider identifier, represented as a respective pre-computed provider vector;
analyzing the member characteristics and the provider characteristics to generate an ordered list of the providers, wherein the ordered list of the providers is based upon a relevancy rank of each provider that is specific to the member, wherein the relevancy rank is based on a plurality of provider-specific member-provider scores, wherein for each provider in a set of providers, a respective provider-specific member-provider score is generated as a function of the member vector and the respective provider vector;
transmitting the ordered list of the providers to the computing device.