Matching using agent/caller sensitivity to performance

• US 9,462,127 B2
• Filed: 09/24/2013
• Issued: 10/04/2016
• Est. Priority Date: 09/24/2012
• Status: Active Grant

• Current Assignee: Afiniti Ltd
• Original Assignee: Afiniti International Holdings, Ltd.
• Inventors: Kan, Ittai, Chishti, Zia, Merchant, Akbar A.
• Primary Examiner(s): AL AUBAIDI, RASHA S
• Application Number:
  US14/035,522
• Publication Number:
  US 20140086402A1
• Time in Patent Office: 1,106 Days
• Field of Search: 37926511-26512, 37926501-26503, 37926505-26506
• US Class Current: 1/1
• CPC Class Codes: H04M 2203/402 Agent or workforce management
• CPC Class Codes: H04M 3/00 Automatic or semi-automatic exchanges
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5191 interacting with the Internet
• CPC Class Codes: H04M 3/523 with call distribution or queueing
• CPC Class Codes: H04M 3/5232 Call distribution algorithms
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution
• CPC Class Codes: H04M 5/00 Manual exchanges substation equipment in general H04M1/00

Abstract

A method, system and program product, the method comprising: obtaining for each call in one set of calls a respective pattern representing multiple different respective data fields; obtaining performance data for the respective patterns of the calls; obtaining performance data for the respective agents; determining agent performance sensitivity to call pattern performance for agents in a set of agents comprising the agent performance data correlated to call performance data for the calls the agent handles; and matching a respective one of the agents from the set of agents to one of the calls based at least in part on the performance data for the respective pattern of the one call and on the agent sensitivity to call performance for the respective one agent of the set of agents.

Claims

1. A method of operating a call center system, comprising:

obtaining for a call, by one or more computers, a call pattern representing at least one data field;

obtaining, by the one or more computers, call pattern performance data for the call pattern;

obtaining, by the one or more computers, agent performance data for respective agents in a set of agents;

determining, by the one or more computers, call pattern sensitivity to agent performance for each agent in the set of agents, wherein the agent performance data is correlated to the call pattern performance data; and

matching, by the one or more computers, a respective one of the agents from the set of agents to the call based at least in part on the call pattern performance data and on the call pattern sensitivity to agent performance.

2. The method as defined in claim 1, wherein determining call pattern sensitivity to agent performance for each agent in the set of agents comprises correlating the agent performance data to the call pattern performance data for calls the agent has handled in a data set.

3. The method as defined in claim 1, further comprising:

percentiling or ranking, by the one or more computers, the call pattern based at least in part on the call pattern performance data;

percentiling or ranking, by the one or more computers, each agent in the set of agents based at least in part on the call pattern sensitivity to agent performance,

wherein the matching is based at least in part on the percentiling or ranking of the call pattern and the percentiling or ranking of each agent in the set of agents.

4. The method as defined in claim 1, wherein the call pattern is abstracted in whole or in part, so that a meaning for field data represented in the call pattern is not known by the system.

5. The method as defined in claim 1, wherein the agent performance data is based on at least one selected from the group of sales, retention of the caller in a program, call handle time, customer satisfaction, revenue, first call resolution, units sold, and transaction points.

6. The method as defined in claim 1, further comprising:

matching, by the one or more computers, a different set of calls to agents using a different matching algorithm;

comparing, by the one or more computers, performance data from call-agent matches of the different set of calls using the different matching algorithm with the call pattern performance data based at least in part on the call pattern sensitivity to agent performance; and

generating, by the one or more computers, a report or display data for the performance comparing results from using the matching algorithm based at least in part on call pattern sensitivity to agent performance against performance using the different matching algorithm.

7. A method of operating a call center system, comprising:

obtaining for each call in one set of calls, by one or more computers, a respective call pattern representing multiple different respective data fields;

obtaining, by the one or more computers, call pattern performance data for the respective patterns of the calls;

obtaining, by the one or more computers, agent performance data for respective agents in a set of agents;

determining, by the one or more computers, call pattern sensitivity to agent performance, wherein the agent performance data is correlated to the call pattern performance data for the calls the agent has handled;

grouping, by the one or more computers, the set of agents into at least two groups comprising one group and a different group based at least in part on the agent performance data;

matching for the one group of the agents, by the one or more computers, a respective one of the agents from the one group to one of the calls based at least in part on the call pattern performance data for the pattern of the one call and the agent performance data of the respective one agent in the one group; and

matching for the different group of the agents, by the one or more computers, a respective one of the agents from the different group of agents to a different one of the calls based at least in part on the call pattern performance data for the pattern of the one call and the call pattern sensitivity to agent performance for the one agent in the different group.

8. The method as defined in claim 7, wherein determining call pattern sensitivity to agent performance for agents in the set of agents comprises correlating agent performance to call performance data for the calls the agent has handled in a data set.

9. The method as defined in claim 7, further comprising:

percentiling or ranking, by the one or more computers, the respective patterns in the set of calls based at least in part on their respective call pattern performance data; and

percentiling or ranking, by the one or more computers, the agents in the set of agents based at least in part on the agent performance data;

percentiling or ranking, by the one or more computers, the agents in the set of agents based at least in part on the call pattern sensitivity to agent performance;

wherein the matching for the one group is based at least in part on the percentiling or ranking of the respective pattern of the one call and the percentiling or ranking of the one agent in the one group, and

wherein the matching for the different group is based at least in part on the percentiling or ranking of the respective pattern of the one call and the percentiling or ranking by the call pattern sensitivity to agent performance of the one agent in the different group.

10. The method as defined in claim 7, further comprising:

percentiling or ranking, by the one or more computers, the agents based at least in part on the agent performance data;

wherein the grouping is based at least in part on the performance percentiling or ranking of the agents, with the agents in one of the groups having lower percentilings or rankings than agents in the different group.

11. The method as defined in claim 10, further comprising:

wherein a percentiling or ranking break point between the one group and the different group is determined based on one or more criteria.

12. The method as defined in claim 7, wherein the matching steps are performed concurrently.

13. The method as defined in claim 7, wherein the matching steps are performed consecutively or with partial overlap in time.

14. The method as defined in claim 7, further comprising:

matching, by the one or more computers, a different set of calls to agents using a different matching algorithm;

comparing, by the one or more computers, performance from call-agent matches of the different set of calls using the different matching algorithm with performance for the one set of calls using a combination of the matching of the one group of agents to calls and the matching of the different group of agents to calls; and

generating, by the one or more computers, a report or display data for the performance comparing results from using the combination of matching algorithms against performance using the different matching algorithm.

15. A system of operating a call center system, comprising:

one or more computers configured with the following components;

a call data extractor component for obtaining for a call a call pattern representing at least one data field;

a call pattern performance extractor for obtaining call pattern performance data for the call pattern;

an agent performance extractor component for obtaining agent performance data for respective agents in a set of agents;

an agent performance sensitivity to call pattern performance correlation engine for determining call pattern sensitivity to agent performance for each agent in the set of agents, wherein the agent performance data is correlated to the call pattern performance data; and

a matching engine for matching a respective one of the agents from the set of agents to the call based at least in part on the call pattern performance data and on the call pattern sensitivity to agent performance.

16. The system as defined in claim 15, further comprising:

a first percentiling or ranking engine configured for percentiling or ranking the call pattern based at least in part on the call pattern performance data; and

a second percentiling or ranking engine configured for percentiling or ranking each agent in the set of agents based at least in part on the call pattern sensitivity to agent performance;

wherein the matching engine is configured to perform matching based at least in part on the percentiling or ranking of the call pattern and the percentiling or ranking of each agent in the set of agents.

17. A system of operating a call center system, comprising:

one or more computers configured with the following components;

a call data extractor component for obtaining for each call in one set of calls a respective call pattern representing multiple different respective data fields;

a call pattern performance extractor for obtaining call pattern performance data for the respective patterns of the calls;

an agent performance extractor for obtaining agent performance data for respective agents of a set of agents;

an agent performance sensitivity to call pattern performance correlation engine for determining call pattern sensitivity to agent performance, wherein the agent performance data is correlated to call pattern performance data for the calls the agent has handled;

a grouping engine configured for grouping the set of agents into at least two groups comprising one group and a different group based at least in part on the agent performance data;

a first matching engine configured for matching a respective one of the agents from the one group to one of the calls based at least in part on the call pattern performance data for the pattern of the one call and the agent performance data of the respective one agent in the one group; and

a second matching engine configured for matching for the different group of the agents a respective one of the agents from the different group of agents to a different one of the calls based at least in part on the call pattern performance data for the pattern of the one call and the call pattern sensitivity to agent performance for the one agent in the different group.

18. The system as defined in claim 17, further comprising:

a first percentiling or ranking engine for percentiling or ranking the respective patterns in the set of calls based at least in part on their respective call pattern performance data; and

a second percentiling or ranking engine for percentiling or ranking the agents in the set of agents based at least in part on the agent performance data;

a third percentiling or ranking engine for percentiling or ranking the agents in the set of agents based at least in part on the call pattern sensitivity to agent performance;

wherein the first matching engine is configured for matching the one group based at least in part on the percentiling or ranking of the respective pattern of the one call and the percentiling or ranking of the one agent in the one group, and

wherein the second matching engine is configured for matching the different group based at least in part on the percentiling or ranking of the respective pattern of the one call and the percentiling or ranking by the call pattern sensitivity to agent performance of the one agent in the different group.

19. The system as defined in claim 17, further comprising:

a percentiling or ranking engine for percentiling or ranking the agents based at least in part on the agent performance data;

wherein the grouping is based at least in part on the performance percentiling or ranking of the agents, with the agents in one of the groups having lower percentilings or rankings than agents in the different group.

20. The system as defined in claim 19, wherein the grouping engine is configured for setting a percentiling or ranking break point between the one group and the different group based on one or more criteria.

21. A method of operating a call center system, comprising:

obtaining for a call, by one or more computers, a call pattern representing at least one data field;

obtaining, by the one or more computers, call pattern performance data for the call pattern;

obtaining, by the one or more computers, agent performance data for respective agents in a set of agents;

determining, by the one or more computers, agent performance sensitivity to call pattern performance for agents in the set of agents, wherein the agent performance data is correlated to call performance data;

determining, by the one or more computers, call pattern performance sensitivity to agent performance, wherein the call pattern performance data is correlated to the agent performance data; and

matching, by the one or more computers, a respective one of the agents from the set of agents to the call based at least in part on the call pattern performance sensitivity to agent performance and on the agent performance sensitivity to call pattern performance.