US 11,854,051 B2
Systems and methods for generating efficient iterative recommendation structures
Taylor Griffin Smith, Addison, TX (US); Jason Matthew White, Dallas, TX (US); Joseph David Albright, Norcross, GA (US); and Tim G. Sanidas, Bloomington, IL (US)
Assigned to STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed by STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed on May 31, 2022, as Appl. No. 17/828,846.
Application 17/828,846 is a continuation of application No. 15/991,544, filed on May 29, 2018, granted, now 11,361,349.
Prior Publication US 2022/0292552 A1, Sep. 15, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/0282 (2023.01); G06Q 50/00 (2012.01); G06Q 30/0204 (2023.01); G06Q 30/0201 (2023.01)
CPC G06Q 30/0282 (2013.01) [G06Q 30/0201 (2013.01); G06Q 30/0205 (2013.01); G06Q 50/01 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A recommender system for generating efficient iterative reduced bi-directional data recommendation structures, the recommender system comprising:
a recommender server comprising one or more processors and one or more memories,
wherein the recommender server further comprises computing instructions that when executed by the one or more processors cause the one or more processors to:
aggregate a plurality of ratings vectors, each ratings vector associated with a vector type, and each ratings vector containing one or more content ranking metrics, the content ranking metrics associated with one or more users;
generate at least two similarity pairing values from the plurality of ratings vectors, each similarity pairing value generated by similarity mapping between a first ratings vector and a second ratings vector;
generate a reduced bi-directional data recommendation structure having a reduced data structure comprising a single similarity pairing value instead of the at least two similarity pairing values and based on the similarity pairing values, the reduced bi-directional data recommendation structure comprising one or more data objects accessible by a bi-directional look-up interface; and
return a bi-directional recommendation value determined from the generated reduced bi-directional data recommendation structure, after receiving a lookup request initiated by a client device via a computer network for either the vector type of the first ratings vector or the vector type of the second ratings vector.