Intelligent scheduling tool

Patent metadata

Field	Value
Publication number	US-11068304-B2
Application number	US-201916285170-A
Country	US
Kind code	B2
Filing date	Feb 25, 2019
Priority date	Feb 25, 2019
Publication date	Jul 20, 2021
Grant date	Jul 20, 2021

Abstract

Systems and methods are disclosed for intelligent scheduling of calls to sales leads, leveraging machine learning (ML) to optimize expected results. One exemplary method includes determining, using a connectivity prediction model, call connectivity rate predictions; determining timeslot resources; allocating, based at least on the call connectivity rate predictions and timeslot resources, leads to timeslots in a first time period; determining, within a timeslot and using a lead scoring model, lead prioritization among leads within the timeslot; configuring, based at least on the lead prioritization, the telephone unit with lead information for placing a phone call; and applying a contextual bandit (ML) process to update the connectivity prediction model, the lead scoring model, or both. During subsequent time periods, the updated connectivity prediction and lead scoring models are used, thereby improving expected results over time.

First claim

What is claimed is:

1. A system for intelligent scheduling, the system comprising:
a telephone unit;
a processor coupled to the telephone unit; and
a computer-readable medium storing instructions that are operative when executed by the processor to:
determine, using a connectivity prediction model, first call connectivity rate predictions;
determine timeslot resources for a first time period;
allocate, based at least on the first call connectivity rate predictions and timeslot resources for the first time period, leads to timeslots in the first time period using contextual bandit learning, the contextual bandit learning providing an option to exploit a current solution or to explore a new solution in order to identify a global optimal solution, wherein the contextual bandit learning analyzes context vectors to identify the global optimal solution;
determine, within a timeslot in the first time period and using a lead scoring model, a first lead prioritization among leads within the timeslot in the first time period;
configure, based at least on the first lead prioritization, the telephone unit with lead information for placing a phone call to a selected lead; and
update the connectivity prediction model using the contextual bandit learning.

2. The system of claim 1 wherein the instructions are further operative to:
control the telephone unit, based at least on the configuration, to place the phone call.

3. The system of claim 1 wherein the time period comprises a day.

4. The system of claim 1 wherein the time period comprises a plurality of days.

5. The system of claim 1 wherein the instructions are further operative to:
apply the contextual bandit learning to update the lead scoring model.

6. The system of claim 1 wherein the timeslot resources comprise a plurality of available telephone units and a set of available time slots.

7. The system of claim 1 wherein the instructions are further operative to:
determine, using the updated connectivity prediction model, second call connectivity rate predictions; determine timeslot resources for a second time period;
allocate, based at least on the second call connectivity rate predictions and timeslot resources for the second time period, leads to timeslots in the second time period;
determine, within a timeslot in the second time period and using a lead scoring model, a second lead prioritization among leads within the timeslot in the second time period; and
configure, based at least on the second lead prioritization, the telephone unit with lead information for placing a phone call to a selected lead.

8. A method of intelligent scheduling, the method comprising:
determining, using a connectivity prediction model, first call connectivity rate predictions;
determining timeslot resources for a first time period;
allocating, based at least on the first call connectivity rate predictions and timeslot resources for the first time period, leads to timeslots in the first time period using contextual bandit learning, the contextual bandit learning providing an option to exploit a current solution or to explore a new solution in order to identify a global optimal solution, wherein the contextual bandit learning analyzes context vectors to identify the global optimal solution;
determining, within a timeslot in the first time period and using a lead scoring model, a first lead prioritization among leads within the timeslot in the first time period; configuring, based at least on the first lead prioritization, a telephone unit with lead information for placing a phone call to a selected lead; and
updating the connectivity prediction model using the context bandit learning.

9. The method of claim 8 further comprising:
controlling the telephone unit, based at least on the configuration, to place the phone call.

10. The method of claim 8 wherein the time period comprises a day.

11. The method of claim 8 wherein the time period comprises a plurality of days.

12. The method of claim 8 further comprising:
applying the contextual bandit learning to update the lead scoring model.

13. The method of claim 8 wherein the timeslot resources comprise a plurality of available telephone units and a set of available time slots.

14. The method of claim 8 further comprising:
determining, using the updated connectivity prediction model, second call connectivity rate predictions;
determining timeslot resources for a second time period;
allocating, based at least on the second call connectivity rate predictions and timeslot resources for the second time period, leads to timeslots in the second time period; determining, within a timeslot in the second time period and using a lead scoring model, a second lead prioritization among leads within the timeslot in the second time period; and
configuring, based at least on the second lead prioritization, the telephone unit with lead information for placing a phone call to a selected lead.

15. One or more computer storage devices having computer-executable instructions stored thereon for intelligent scheduling, which, on execution by a computer, cause the computer to perform operations comprising:
determining, using a connectivity prediction model, first call connectivity rate predictions;
determining timeslot resources for a first time period;
allocating, based at least on the first call connectivity rate predictions and timeslot resources for the first time period, leads to timeslots in the first time period using contextual bandit learning, the contextual bandit learning providing an option to exploit a current solution or to explore a new solution in order to identify a global optimal solution, wherein the contextual bandit learning analyzes context vectors to identify the global optimal solution;
determining, within a timeslot in the first time period and using a lead scoring model, a first lead prioritization among leads within the timeslot in the first time period;
configuring, based at least on the first lead prioritization, a telephone unit with lead information for placing a phone call to a selected lead; and
updating the connectivity prediction model using the context bandit learning.

16. The one or more computer storage devices of claim 15 wherein the operations further comprise:
controlling the telephone unit, based at least on the configuration, to place the phone call.

17. The one or more computer storage devices of claim 15 wherein the time period comprises at least one selected from the list consisting of:
a day and a work shift of less than a day.

18. The one or more computer storage devices of claim 15 wherein the operations further comprise:
applying the contextual bandit learning to update the lead scoring model.

19. The one or more computer storage devices of claim 15 wherein the timeslot resources comprise a plurality of available telephone units and a set of available time slots.

20. The one or more computer storage devices of claim 15 wherein the operations further comprise:
determining, using the updated connectivity prediction model, second call connectivity rate predictions;
determining timeslot resources for a second time period;
allocating, based at least on the second call connectivity rate predictions and timeslot resources for the second time period, leads to timeslots in the second time period;
determining, within a timeslot in the second time period and using a lead scoring model, a second lead prioritization among leads within the timeslot in the second t

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Li Jinchao
• Song Xinying
• Kim Ah Young
• Cao haiyuan
• Wang Yu
• Su Hui
• Ferdous Shahina
• Gao Jianfeng
• Srivastava Karan
• Sarkar Jaideep

Classifications

• G06F9/4881 Primary

  Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues · CPC title

• G06Q10/0631 Primary

  Resource planning, allocation, distributing or scheduling for enterprises or organisations · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F18/21

  Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation · CPC title

• G06N3/09

  Supervised learning · CPC title