US 12,266,004 B2
Systems and methods for providing customer-behavior-based dynamic enhanced order conversion
Prakash Ranganathan, Villupuram (IN); and Miruna Jayakrishnasamy, Vellore (IN)
Assigned to Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed by Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed on Sep. 15, 2022, as Appl. No. 17/932,463.
Prior Publication US 2024/0095802 A1, Mar. 21, 2024
Int. Cl. G06Q 30/00 (2023.01); G06Q 30/0202 (2023.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0631 (2013.01) [G06Q 30/0202 (2013.01); G06Q 30/0633 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a device, dynamic customer data identifying current clickstream data, a time difference between clicks, a review page sentiment, and a chat session sentiment associated with a customer,
wherein the dynamic customer data is received, directly or indirectly, from a user device associated with the customer during a time period in which the customer is interacting with a web page,
wherein the time difference between clicks corresponds to a time period between when the customer selects an item displayed via the web page and when the customer selects another item on the web page, and
wherein the chat session sentiment indicates a sentiment associated with an interaction between the customer and an agent via the web page;
receiving, by the device, static customer data identifying a previous purchased product cost;
calculating, by the device, additional customer data identifying a buyer interest rate, a purchase cost bucket score, and a quantity of clicks based on the dynamic customer data and the static customer data;
processing, by the device, the static customer data, the dynamic customer data, and the additional customer data, with a first machine learning model, to determine a next action prediction;
processing, by the device, the static customer data, the dynamic customer data, and the additional customer data, with a second machine learning model, to determine a next sequence prediction;
concatenating, by the device, the static customer data, the dynamic customer data, the additional customer data, the next action prediction, and the next sequence prediction to generate concatenated data;
processing, by the device, the concatenated data, with a plurality of machine learning models, to calculate a fallout prediction, an add-cart-and-exit prediction, a stagewise score prediction, a chat assistance flag setting, and a purchase order probability;
displaying, by the device and when the purchase order probability satisfies a threshold and the chat assistance flag setting is one, a place order menu with a live chat agent to the customer;
processing, by the device and when the purchase order probability fails to satisfy the threshold, the fallout prediction, the add-cart-and-exit prediction, the stagewise score prediction, the chat assistance flag setting, and the purchase order probability, with a recommendation model, to generate a recommendation for the customer; and
implementing, by the device and during the time period in which the customer is interacting with the web page, the recommendation for the customer.