US 12,243,021 B1
Machine learning based email time recommendation engine
Dibya Prakash Sahoo, Hyderabad (IN); Manish Kumar Choudhary, Hyderabad (IN); Liza Mohanty, Hyderabad (IN); Abhishek Sahu, Hyderabad (IN); and Upamanyu Sarangi, Hyderabad (IN)
Assigned to HIGHRADIUS CORPORATION, Houston, TX (US)
Filed by HIGHRADIUS CORPORATION, Houston, TX (US)
Filed on Nov. 22, 2023, as Appl. No. 18/516,973.
Int. Cl. G06Q 10/107 (2023.01); G06Q 10/04 (2023.01); G06Q 40/03 (2023.01); H04L 51/226 (2022.01)
CPC G06Q 10/107 (2013.01) [G06Q 10/04 (2013.01); G06Q 40/03 (2023.01); H04L 51/226 (2022.05)] 18 Claims
OG exemplary drawing
 
1. A machine-learning based (ML-based) computing method for computing one or more optimal times to transmit one or more electronic mails to a first one or more users, the ML-based computing method comprising:
receiving, by one or more hardware processors, one or more inputs from a second one or more users, wherein the one or more inputs comprises information related to at least one of: one or more entities associated with the first one or more users, and a contact prediction window associated with a predefined time duration during which the second one or more users requires an optimal instance for a communication with the first one or more users;
extracting, by the one or more hardware processors, one or more data associated with the first one or more users and the second one or more users from one or more databases, based on the one or more inputs received from the second one or more users;
computing, by the one or more hardware processors, one or more electronic mail feature scores based on the extracted one or more data associated with the first one or more users and the second one or more users, for each specified interval of the contact prediction window, wherein the one or more electronic mail feature scores comprises at least one of: incoming electronic mail score, outgoing electronic mail score, first user activity score, electronic mail productivity rate score, quarterly electronic mail productivity score, and incoming electronic mail ratio score;
computing, by the one or more hardware processors, one or more first user electronic mail scores for each specified interval of the contact prediction window based on the one or more electronic mail feature scores for each specified interval of the contact prediction window, using a machine learning model;
validating, by the one or more hardware processors, the machine learning model based on one or more validation datasets, wherein in validating the machine learning model comprises determining, by the one or more hardware processors, whether the machine learning model is trained until one or more losses reaches a stable state indicating a state of convergence is achieved;
computing, by the one or more hardware processors, at least one of: the one or more optimal times and a prioritized list of the one or more optimal times by ranking each specified interval of the contact prediction window associated with the one or more first user electronic mail scores;
providing, by the one or more hardware processors, an output of at least one of: the one or more optimal times and the prioritized list of the one or more optimal times to the second one or more users on a user interface associated with one or more electronic devices; and
transmitting, by the one or more hardware processors, one or more electronic mails to the first one or more users by scheduling the one or more electronic mails during the one or more optimal times.