US 12,141,748 B2
Matching inventory characteristics and structure
Saman Baghestani, Plano, TX (US); Brandon Drumheller, Plano, TX (US); Walker Ramirez, Frisco, TX (US); and Veerendra Jote, Frisco, TX (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Sep. 2, 2022, as Appl. No. 17/901,976.
Application 17/901,976 is a continuation of application No. 17/104,684, filed on Nov. 25, 2020, granted, now 11,436,561.
Prior Publication US 2023/0108984 A1, Apr. 6, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/08 (2024.01); G06Q 10/087 (2023.01); G06Q 40/03 (2023.01)
CPC G06Q 10/087 (2013.01) [G06Q 40/03 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by one or more computing devices, from a client device, a query comprising configuration information describing an asked inventory item and information describing a preferred structure, wherein the configuration information comprises a plurality of facet values corresponding to respective facets of a plurality of facets of the asked inventory item;
retrieving, by the one or more computing devices, a plurality of inventory items based on the configuration information describing the asked inventory item from a plurality of records stored in a first database;
generating, by the one or more computing devices, score values of the plurality of inventory items based on the plurality of facet values of the configuration information;
defining, by the one or more computing devices, a plurality of data points each corresponding to the score values for a respective inventory item of the plurality of inventory items, wherein:
the plurality of data points are placed into a plurality of clusters within n-dimensional space by a clustering algorithm based on the score values;
each dimension of the n dimensions corresponds to a facet of the asked inventory item; and
a data point of the plurality of data points corresponding to the asked inventory item is a centroid of a cluster of the plurality of clusters;
determining, by the one or more computing devices, a subset of the plurality of inventory items that are most similar to the asked inventory item based on a plurality of data points within a preconfigured distance from the centroid of the cluster;
retrieving, by the one or more computing devices, from a second database, financial information for a buyer and underwriting policies for a lender from which the buyer has obtained prequalification;
generating, by the one or more computing devices, one or more structures corresponding to the subset of the plurality of inventory items, wherein the one or more structures are dynamically generated based on the underwriting policies for the lender, the financial information for the buyer, the preferred structure information and structure information associated with the asked inventory item;
scoring, by the one or more computing devices, a combination of the asked inventory item according to the configuration information and the preferred structure, and combinations of the subset of the plurality of inventory items and the corresponding one or more structures, for similarity to the configuration information and the preferred structure; and
based on the scoring, responding, by the one or more computing devices, to the query with one or more combinations of an alternative inventory item and corresponding structure from the subset of the plurality of inventory items and the one or more structures corresponding to the subset of the plurality of inventory items.