Techniques for estimating expected performance in a task assignment system

Patent metadata

Field	Value
Publication number	US-2020351402-A1
Application number	US-202016931101-A
Country	US
Kind code	A1
Filing date	Jul 16, 2020
Priority date	Jul 10, 2017
Publication date	Nov 5, 2020
Grant date	—

Abstract

Techniques for estimating expected performance of a task assignment strategy in a task assignment system are disclosed. In one particular embodiment, the techniques may be realized as a method comprising receiving, by at least one computer processor communicatively coupled to a task assignment system, a plurality of historical agent task assignments; determining, by the at least one computer processor, a sample of the plurality based on a strategy for pairing agents with tasks; determining, by the at least one computer processor, an expected performance of the strategy based on the sample; outputting, by the at least one computer processor, the expected performance; and optimizing, by the at least one computer processor, the performance of the task assignment system based on the expected performance.

First claim

1 . A method comprising:
receiving, by at least one computer processor communicatively coupled to and configured to operate in a contact center system, a plurality of contact-agent interactions, wherein each of the plurality of contact-agent interactions is associated with a contact type of a plurality of contact types, an agent set of a plurality of agent sets, and an outcome; assigning, by the at least one computer processor, each of the contact-agent interactions to a plurality of interaction sets, wherein each interaction set is associated with one of the contact types and one of the agent sets; calculating, by the at least one computer processor, for the plurality of interaction sets, a plurality of aggregated outcomes; determining, by the at least one computer processor, a pairing strategy based on the plurality of aggregated outcomes; determining, by the at least one computer processor, an expected utilization of an agent set from the plurality of agent sets based on the pairing strategy; determining, by the at least one computer processor, an allocation of a contact type from the plurality of contact types based on the pairing strategy; and outputting, by the at least one computer processor, an estimated performance of the pairing strategy based on the expected utilization and the allocation, wherein a size of the plurality of interaction sets is greater than a sum of a size of the plurality of agent sets and a size of the plurality of contact types.

2 . The method of claim 1 , wherein the pairing strategy is configured so that each of the agent sets continues to receive a similar number of interactions as under the plurality of contact-agent interactions.

3 . The method of claim 1 , wherein the pairing strategy is configured so that each of the contact types continues to receive a similar number of connections to agents as under the plurality of contact-agent interactions.

4 . The method of claim 3 , wherein the pairing strategy is further configured so that each of the agent sets continues to receive a similar number of interactions as under the plurality of contact-agent interactions.

5 . The method of claim 1 , wherein at least one interaction set of the plurality of interaction sets is an empty set.

6 . The method of claim 1 , wherein the plurality of contact-agent interactions comprises historical contact-agent interactions.

7 . The method of claim 1 , wherein an agent set of the plurality of agents sets consists of exactly one agent.

8 . A system comprising:
at least one computer processor communicatively coupled to and configured to operate in a contact center system, wherein the at least one computer processor is further configured to:
receive a plurality of contact-agent interactions, wherein each of the plurality of contact-agent interactions is associated with a contact type of a plurality of contact types, an agent set of a plurality of agent sets, and an outcome;
assign each of the contact-agent interactions to a plurality of interaction sets, wherein each interaction set is associated with one of the contact types and one of the agent sets;
calculate, for the plurality of interaction sets, a plurality of aggregated outcomes;
determine a pairing strategy based on the plurality of aggregated outcomes;
determine an expected utilization of an agent set from the plurality of agent sets based on the pairing strategy;
determine an allocation of a contact type from the plurality of contact types based on the pairing strategy; and
output an estimated performance of the pairing strategy based on the expected utilization and the allocation,
wherein a size of the plurality of interaction sets is greater than a sum of a size of the plurality of agent sets and a size of the plurality of contact types.

9 . The system of claim 8 , wherein the pairing strategy is configured so that each of the agent sets continues to receive a similar number of interactions as under the plurality of contact-agent interactions.

10 . The system of claim 8 , wherein the pairing strategy is configured so that each of the contact types continues to receive a similar number of connections to agents as under the plurality of contact-agent interactions.

11 . The system of claim 10 , wherein the pairing strategy is further configured so that each of the agent sets continues to receive a similar number of interactions as under the plurality of contact-agent interactions.

12 . The system of claim 8 , wherein at least one interaction set of the plurality of interaction sets is an empty set.

13 . The system of claim 8 , wherein the plurality of contact-agent interactions comprises historical contact-agent interactions.

14 . The system of claim 8 , wherein an agent set of the plurality of agents sets consists of exactly one agent.

15 . An article of manufacture comprising:
a non-transitory computer processor readable medium; and instructions stored on the medium; wherein the instructions are configured to be readable from the medium by at least one computer processor communicatively coupled to and configured to operate in a contact center system and thereby cause the at least one computer processor to operate so as to:
receive a plurality of contact-agent interactions, wherein each of the plurality of contact-agent interactions is associated with a contact type of a plurality of contact types, an agent set of a plurality of agent sets, and an outcome;
assign each of the contact-agent interactions to a plurality of interaction sets, wherein each interaction set is associated with one of the contact types and one of the agent sets;
calculate, for the plurality of interaction sets, a plurality of aggregated outcomes;
determine a pairing strategy based on the plurality of aggregated outcomes;
determine an expected utilization of an agent set from the plurality of agent sets based on the pairing strategy;
determine an allocation of a contact type from the plurality of contact types based on the pairing strategy; and
output an estimated performance of the pairing strategy based on the expected utilization and the allocation,
wherein a size of the plurality of interaction sets is greater than a sum of a size of the plurality of agent sets and a size of the plurality of contact types.

16 . The article of manufacture of claim 15 , wherein the pairing strategy is configured so that each of the agent sets continues to receive a similar number of interactions as under the plurality of contact-agent interactions.

17 . The article of manufacture of claim 15 , wherein the pairing strategy is configured so that each of the contact types continues to receive a similar number of connections to agents as under the plurality of contact-agent interactions.

18 . The article of manufacture of claim 17 , wherein the pairing strategy is further configured so that each of the agent sets continues to receive a similar number of interactions as under the plurality of contact-agent interactions.

19 . The article of manufacture of claim 15 , wherein at least one interaction set of the plurality of interaction sets is an empty set.

20 . The article of manufacture of claim 15 , wherein the plurality of contact-agent interactions comprises historical contact-agent interactions.

21 . The article of manufacture of claim 15 , wherein an agent set of the plurality of agents sets consists of exactly one agent.

Assignees

• Afiniti Europe Tech Ltd

Inventors

• Chishti Zia
• Kan Ittai
• Khatri Vikash

Classifications

• H04M2203/402

  Agent or workforce management · CPC title

• H04M2203/401

  Performance feedback · CPC title

• H04M3/5232 Primary

  Call distribution algorithms · CPC title

• H04M3/5175

  Call or contact centers supervision arrangements · CPC title

• G06Q10/06311 Primary

  Scheduling, planning or task assignment for a person or group · CPC title