System and method for intelligent task management and routing

• US 10,162,685 B2
• Filed: 11/20/2017
• Issued: 12/25/2018
• Est. Priority Date: 06/29/2015
• Status: Active Grant

• Current Assignee: Genesys Cloud Services Incorporated
• Original Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Inventors: Ristock, Herbert Willi Artur, Placiakis, Vidas, Teryoshin, Vitaliy, Korolev, Nikolay I., Petrovykh, Yevgeniy, Nitin, Anand Pai Krishnanand
• Primary Examiner(s): Tang, Kenneth
• Application Number:
  US15/818,191
• Publication Number:
  US 20180074866A1
• Time in Patent Office: 400 Days
• Field of Search: None
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/06316 Sequencing of tasks or work
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2203/2038 Call context notifications
• CPC Class Codes: H04M 2203/556 Statistical analysis and interpretation
• CPC Class Codes: H04M 3/523 with call distribution or queueing

Abstract

Systems and methods are shown for routing task objects to multiple agents that involve analyzing content of each task object in an input buffer to determine a classification relevant to the content of the task object that is added to task object metadata, which is placed in a second buffer. Objects in the second buffer are analyzed and the classification in the object metadata used to search workforce management data representing agent characteristics to identify agents who match the classification. A routing strategy is applied to the object to select an agent and the object is routed to the agent'"'"'s workbin. Another aspect involves organizing workbin tasks objects by priority, according to recent system conditions excluding objects that cannot presently be processed based on a workflow strategy or status data, and presenting remaining objects based on order of priority, or re-arranging objects between workbins based on recent status info.

Claims

1. A system for routing tasks to multiple agents, the system comprising:

one or more servers, each server having at least one processor and a memory, wherein the memory has stored therein instructions that, when executed by the processor, cause the processor to;

receive one or more tasks and, for each task, create a task object representing the task and place the task in a first buffer;

execute a first routing strategy, wherein the instructions that cause the processor to execute the first routing strategy include instructions that cause the processor to analyze the content of each task object in the first buffer, determine at least one classification that is relevant to the content of the task object, and add the classification to metadata of the task object;

route each task object in the first buffer to a second buffer in response to executing the first routing strategy;

execute a second routing strategy different from the first routing strategy, wherein the instructions that cause the processor to execute the second routing strategy include instructions that cause the processor to analyze the metadata and the content of a particular task object of the task objects in the second buffer and identify one or more agents for assignment of the particular task object based on at least a partial match of the classification with one or more characteristics associated with the one or more agents; and

route the particular task object in the second buffer to a workbin corresponding to one of the one or more agents in response to executing the second routing strategy.

2. The system of claim 1, wherein the instructions further cause the processor to:

on at least one of a periodic, parametric or event basis, move unprocessed task objects from agent workbins to one of the first buffer and second buffer for re-assignment.

3. The system of claim 2, wherein the event basis further comprises a status change of at least one agent from unavailable to available, and the parametric basis further comprises analysis of workload levels in the workbins corresponding to the one or more agents.

4. The system of claim 2, wherein the periodic basis further comprises a pre-determined time interval.

5. The system of claim 1,

wherein the identified one or more agents are agents predicted to be capable to process the task corresponding to the task object, within a pre-defined performance criterion.

6. The system of claim 5,

wherein the defined performance criterion is an amount of time used to process tasks previously assigned to the one or more agents.

7. The system of claim 1, wherein the instructions that cause the processor to analyze the content of each task object in the second buffer further include instructions that cause the processor to:

evaluate workforce data to forecast at least one of availability and unavailability of the one or more agents to process the task corresponding to the task object within a defined performance criterion.

8. The system of claim 1, wherein the instructions further cause the processor to:

evaluate statistical data relating to agent performance to determine that the one or more agents are forecast to not be capable of processing the task corresponding to the task object within a defined performance criterion; and

move the task object corresponding to the task, from the workbin corresponding to the one or more agents, to one of first buffer and the second buffer for re-assignment.

9. The system of claim 1, wherein the instructions further cause the processor to:

analyze the task object in the workbin corresponding to the one or more agents to forecast that the one or more agents are predicted to not process the task corresponding to the task object within a defined performance criterion;

identify a second agent for reassignment of the task object; and

move the task object for the task from the workbin corresponding to the one or more agents, to a second workbin corresponding to the second agent.

10. The system of claim 1, wherein the instructions further cause the processor to:

analyze the task objects in the workbin to determine an order of priority of the task objects;

exclude a particular one of the task objects that cannot be presently be processed based on at least one of a predefined workflow strategy and status data; and

present a particular one of remaining ones of the task objects to an agent of the one or more agents based on the order of priority of the task objects.

11. The system of claim 10, wherein the instructions further cause the processor to:

further exclude the particular one of the task objects from presentation to the agent of the one or more agents that cannot be processed within a defined performance parameter based on a routing strategy and statistical data for the agent of the one or more agents.

12. The system of claim 10, wherein the instructions further cause the processor to:

move the excluded task object to one of the first buffer and the second buffer for reassignment.

13. The system of claim 10 wherein the instructions further cause the processor to:

order the remaining ones of the task objects for presentation based on a workflow strategy.

14. The system of claim 1, wherein the instructions that cause the processor to analyze the content of each task object in the first buffer further includes:

applying a predefined model to the task object and automatically adding an additional destination to the task object based on the content of the task object.

15. The system of claim 1, wherein the instructions that cause the processor to analyze the content of each task object in the first buffer further includes:

analyzing the content of the task object in the first buffer and adding a keyword to the metadata of the task object, wherein the keyword is relevant to the content of the task object.

16. The system of claim 1, wherein the tasks further comprise interactions.

17. The system of claim 1, wherein the instructions that cause the processor to analyze the content of each task object in the first buffer further includes:

determining whether an agent has previously interacted with a source of the task object and adding metadata identifying the agent.

18. The system of claim 1, wherein the instructions further cause the processor to:

execute a re-rerouting process in response to detecting a trigger condition; and

move a particular task object in the workbin back to at least one of the first buffer or second buffer in response to executing the re-routing process.

19. The system of claim 18, wherein the re-routing process analyzes the task objects in the workbin to determine that the one or more agents are forecast to not be capable of processing the task corresponding to the particular task object within a defined performance criterion.

20. A method for managing tasks for processing by agents, the tasks being represented by task objects, the method comprising:

executing a first routing strategy, wherein the executing includes analyzing each task object in a first buffer to identify at least one of a classification or keyword relevant to the task corresponding to the task object, and adding the identified relevant classification or keyword to the task object as metadata;

routing each task object in the first buffer to a second buffer in response to executing the first routing strategy;

executing a second routing strategy different from the first routing strategy, wherein the executing of the second routing strategy includes;

using the identified relevant classification or keyword from the metadata of the task object to request data representing characteristics of the agents,

receiving the data including the characteristics of the agents;

identifying one or more of the agents with the characteristics that at least partially match the relevant classification or keyword, and

routing a particular task object of the task objects in the second buffer to a workbin corresponding to one of the one or more agents, in response to executing the second routing strategy.