US 11,775,989 B1
Systems and methods for omnichannel environment relevance analytics
Ping Hao, Palo Alto, CA (US); Burke Miller White, San Anselmo, CA (US); Daniel Quynh-Hung Nguyen, Palo Alto, CA (US); and Peter Andrew Zelasney, New York, NY (US)
Assigned to BRAND3P INCORPORATED, Palo Alto, CA (US)
Filed by Brand3P Incorporated, Palo Alto, CA (US)
Filed on Oct. 14, 2020, as Appl. No. 17/70,837.
Claims priority of provisional application 62/914,925, filed on Oct. 14, 2019.
Int. Cl. G06Q 30/0201 (2023.01); G06Q 30/0601 (2023.01); G06Q 30/0282 (2023.01); G06F 16/22 (2019.01); G06N 20/00 (2019.01); G06Q 10/0639 (2023.01)
CPC G06Q 30/0201 (2013.01) [G06F 16/22 (2019.01); G06N 20/00 (2019.01); G06Q 10/06393 (2013.01); G06Q 30/0627 (2013.01); G06Q 30/0629 (2013.01); G06Q 30/0282 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving a request to obtain an omnichannel relevance index for a product;
identifying a set of domain priorities, wherein the set of domain priorities correspond to one or more platforms through which the product is made available;
obtaining product data sets associated with the one or more platforms through which the product is made available, wherein the product data sets are obtained via navigation pathways across the set of domain priorities, wherein the product data sets include data corresponding to the product and a set of other products, and wherein the data is weighted based on listing positions of the product and the set of other products within the one or more platforms;
normalizing the product data sets to generate normalized product data sets;
generating one or more machine learning algorithms to provide a score based on the normalized product data sets, wherein the one or more machine learning algorithms are generated by iteratively varying a set of hyperparameters associated with the one or more machine learning algorithms according to a test data set and a predefined specification;
processing the normalized product data sets through the one or more machine learning algorithms to generate the score;
generating the omnichannel relevance index for the product and a set of recommendations for improving the omnichannel relevance index, wherein the omnichannel relevance index and the set of recommendations are generated based on the score, and wherein the omnichannel relevance index indicates a position of the product in relation to the set of other products;
receiving feedback resulting from implementation of the set of recommendations; and
updating the set of hyperparameters associated with the one or more machine learning algorithms based on the feedback.