| CPC G06Q 30/0281 (2013.01) [G06F 9/451 (2018.02); G06N 20/00 (2019.01); G06Q 10/06316 (2013.01); G06Q 10/06393 (2013.01); G06Q 10/06398 (2013.01); G06Q 20/40 (2013.01); G06Q 30/016 (2013.01); G10L 15/26 (2013.01); H04L 63/08 (2013.01); H04M 3/5166 (2013.01); H04M 3/5175 (2013.01)] | 17 Claims |
|
14. A non-transitory computer-readable storage medium including executable instructions that, when executed by a processor, cause the processor to:
identify a plurality of customer target contacts from a plurality of customers, each customer target contact being associated with an outstanding task item;
identify a first user as a customer-facing user of a customer relationship management (CRM) system based on an authentication of the first user to the CRM system;
select a subset of the plurality of customer target contacts for contact by the first user within a work period;
initiate a real-time interactive contact between the first user and a first customer target contact of the subset of customer target contacts;
monitor the real-time interactive contact to create monitored information associated with the first customer target;
execute a machine learning model in real-time as the real-time interactive contact is occurring to correlate the monitored information with historical information, wherein the historical information comprises at least one of previous interactive contact information associated with previous interactive contacts of the first customer target or the first user, historical debt collection information associated with the first customer target, or derived information generated from one or more machine learning algorithms analyzing the previous interactive contacts of the first customer target or the first user or the historical debt collection information associated with the first customer target;
based on the real-time correlation between the monitored information and the historical information, determine, generate, and display one or more real-time recommended actions to the first user with respect to the real-time interactive contact;
provide an indication of termination of the real-time interactive contact; and
responsive to the indication of termination:
collect the monitored information;
obtain results information associated with the real-time interactive contact;
store at least a portion of the monitored information and the results information in a data store; and
execute the one or more machine learning algorithms to update the machine learning model based on the monitored information and the results information, the updated machine learning model for use in future interactive contacts;
wherein the computing system is configured to provide one or more follow-up recommended actions for the first user with respect to the real-time interactive contact, the one or more follow-up recommended actions comprising scheduling a follow-up contact to the first customer target contact or recording a date and an amount of a promise to pay, the one or more follow-up recommended actions are configured to be executed in response to the first user's approval; and
wherein the one or more follow-up recommended actions are configured to be stored in the data storage and are used to update the machine learning model.
|