US 12,223,522 B2
Probabilistic search biasing and recommendations
Byong Mok Oh, Los Altos, CA (US); Dhruv Mehrotra, Mountain View, CA (US); Chiaki Osaka, South San Francisco, CA (US); Naoya Makino, San Francisco, CA (US); Patrick Michael Wiseman, South San Francisco, CA (US); and Minami Sueyasu, San Francisco, CA (US)
Assigned to MERCARI, INC., Palo Alto, CA (US)
Filed by Mercari Inc., Palo Alto, CA (US)
Filed on Mar. 11, 2022, as Appl. No. 17/654,484.
Application 17/654,484 is a continuation of application No. 16/288,373, filed on Feb. 28, 2019, granted, now 11,282,100.
Claims priority of provisional application 62/740,165, filed on Oct. 2, 2018.
Prior Publication US 2022/0270121 A1, Aug. 25, 2022
Int. Cl. G06Q 30/00 (2023.01); G06F 16/903 (2019.01); G06F 16/9032 (2019.01); G06F 16/908 (2019.01); G06F 16/951 (2019.01); G06N 3/08 (2023.01); G06Q 30/0201 (2023.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0206 (2013.01) [G06F 16/90324 (2019.01); G06F 16/90335 (2019.01); G06F 16/908 (2019.01); G06F 16/951 (2019.01); G06N 3/08 (2013.01); G06Q 30/0629 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
generating, by at least one computer processor, a database query based on an input relating to an identified item;
receiving, by the at least one computer processor, a response to the database query, wherein the response comprises a plurality of comparable items, wherein the plurality of comparable items have been determined to be similar to the identified item based on at least one element of textual or non-textual descriptive data corresponding both to the identified item and to the plurality of comparable items, wherein the response further comprises corresponding metadata for the plurality of comparable items, including a plurality of values corresponding to the plurality of comparable items and a type of market platform corresponding to each of the plurality of comparable items, and wherein the plurality of values are normalized for differences in the corresponding metadata due to differences in the type of market platform corresponding to each of the plurality of comparable items;
generating, by the at least one computer processor, a probability score for at least two values of a range of values of the normalized plurality of values, based at least on a statistical analysis of the corresponding metadata for the plurality of comparable items;
modifying, by the at least one computer processor, a search ranking of the identified item, based on availability of application program interfaces (APIs) by which the identified item can be searched; and
outputting, by the at least one computer processor, at least a suggested value based on at least the generating the probability score for the at least two values of the range of values, together with a prompt for further input.