US 12,340,400 B2
Method and non-transitory computer readable medium for models based on data augmented with conceivable transitions
Choudur K. Lakshminarayan, Austin, TX (US); and Ram Kosuru, Austin, TX (US)
Assigned to Micro Focus LLC, Santa Clara, CA (US)
Filed by Micro Focus LLC, Santa Clara, CA (US)
Filed on Jun. 8, 2023, as Appl. No. 18/207,612.
Application 18/207,612 is a division of application No. 15/770,899, granted, now 11,720,940, previously published as PCT/US2015/058109, filed on Oct. 29, 2015.
Prior Publication US 2023/0316352 A1, Oct. 5, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/0601 (2023.01); G06N 20/00 (2019.01); G06Q 30/06 (2023.01)
CPC G06Q 30/0601 (2013.01) [G06N 20/00 (2019.01); G06Q 30/06 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method, comprising:
augmenting, by a processor, historical interaction data of prior buyers and non-buyers that browsed a website by imputing connections among links between universal resource locators (URLs) of the website and estimating an augmented set of transition probabilities based on conceivable transitions arising from the imputed connections, each of the conceivable transitions including a multi-step transition between a first URL and a second URL via at least one intermediate URL of the website;
training, by the processor, each of a plurality of different models using the historical interaction data and/or augmented historical interaction data;
receiving, by the processor from a client device, interaction data of a user browsing the website;
providing, by the processor, a plurality of different models for an intent of the user based on the interaction data, the plurality of different models comprising at least one augmented buyer model based on the augmented set of transition probabilities of the conceivable transitions and an alternate buyer model based on an actual transition between the first URL and the second URL;
comparing, by the processor, a transition probability of the augmented set of transition probabilities associated with the augmented buyer model based on a conceivable transition to a significance threshold measure;
applying, by the processor, the following rules:
when the transition probability of the augmented set of transition probabilities exceeds the significance threshold measure, selecting the augmented buyer model; and
when the transition probability of the augmented set of transition probabilities does not exceed the significance threshold measure, selecting the alternate buyer model;
determining, by the processor, when the user is likely to be a buyer, based on the interaction data and the selected one of the augmented buyer model and the alternate buyer model; and
presenting, by the processor, the user with an offer to buy from the website upon the determination that the user is likely to be the buyer.