	US 11,755,978 B2
	System for providing dynamic recommendations based on interactions in retail stores
Eric Tamblyn, Murphy, TX (US); Simon Wright, Sheffield (GB); Yochai Konig, San Francisco, CA (US); Christopher Connolly, New York City, NY (US); Chad David Hendren, Elkhorn, NE (US); and Arnaud Lejeune, Chicago, IL (US)
Filed by Genesys Telecommunications Laboratories, Inc., Daly, CA (US)
Filed on Sep. 24, 2018, as Appl. No. 16/139,662.
Application 16/139,662 is a division of application No. 14/451,322, filed on Aug. 4, 2014, granted, now 10,121,116.
Claims priority of provisional application 62/003,508, filed on May 27, 2014.
Prior Publication US 2019/0026676 A1, Jan. 24, 2019
Int. Cl. G06Q 30/00 (2023.01); G06Q 10/0639 (2023.01); G06Q 30/0201 (2023.01); G06Q 30/0601 (2023.01); H04M 3/51 (2006.01)

CPC G06Q 10/06393 (2013.01) [G06Q 10/0639 (2013.01); G06Q 30/0201 (2013.01); G06Q 30/0631 (2013.01); H04M 3/5175 (2013.01); H04M 3/5191 (2013.01); G06Q 30/0601 (2013.01); G06Q 30/0613 (2013.01)]

5 Claims

1. A multi-tenant analytics system comprising:

a data store, for storing event data in correlation with customer experience data related to respective customers collected by one or more objects stored in the data store;

a scanner disposed at a plurality of physical retail stores configured to scan and transmit one or more identifiers for identifying the customers;

a processor coupled to the data store; and

a memory, wherein the memory stores therein instructions that, when executed by the processor, cause the processor to:

collect from the one or more objects over a data communication network, real-time metrics data for the plurality of physical retail stores associated with a plurality of respective contact centers, wherein the real-time metrics data includes:

interaction data collected from interactions between customers and respective websites associated with the plurality of physical retail stores; and

information on sales of products or services by the plurality of physical retail stores;

store the collected real-time metrics data in the data store;

dynamically generate, by an analytics module, benchmark data based on the collected real-time metrics data and determine a performance of a particular retail store of the plurality of physical retail stores in relation to the benchmark data;

perform, by the analytic module, real-time analytics using the collected metrics data to identify a product or service;

generating, by the analytics module, one or more prediction trees that correlate the collected metrics data and key performance indicators used to calculate the benchmark data;

modify, by the analytics module using the one or more prediction trees, a prior service or product to be offered by the particular retail store with the identified service or product, wherein the modifying is based on the one or more prediction trees optimizing one or more of the key performance indicators for the particular retail store; and

push the modified service or product via a display on an electronic device at the particular retail store;

wherein the display on the electronic device comprises a modified upsell script relating to the modified service or product;

wherein a particular customer of the customers is identified in response to the particular customer visiting the particular retail store by the scanner disposed at the particular retail store, wherein the instructions further cause the processor to:

receive the scanned one or more identifiers transmitted by the scanner;

associate the stored interaction data to the particular customer based on the one or more identifiers;

recommend offering the modified service or product to the particular customer instead of the identified service or product based on the associating of the stored interaction data of the particular customer with an interest in at least one of the modified service or product and the identified service or product;

capture current interaction data related to the particular customer's visit to the particular retail store and the recommended offering of the modified service or product to the particular customer;

update, by the analytics model, the one or more prediction trees based on the collected real-time metrics data, the captured current interaction data, and the recommended offering of the modified service or product to the particular customer; and

dynamically generate, by the analytics module, updated benchmark data based on the collected real-time metrics data, the captured current interaction data, and the one or more updated prediction trees, the updated benchmark data then being used to determine a performance of another retail store of the plurality of physical retail stores in relation to the updated benchmark data for identifying another product or service by which to modify a prior product or service associated thereto.