Methods and arrangements for employing descriptors for agent-customer interactions

• US 8,589,384 B2
• Filed: 08/25/2010
• Issued: 11/19/2013
• Est. Priority Date: 08/25/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation, ServiceNow Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Bhide, Manish Anand, Deshmukh, Om Dadaji, Verma, Ashish
• Primary Examiner(s): Jami, Hares
• Application Number:
  US12/868,282
• Publication Number:
  US 20120054186A1
• Time in Patent Office: 1,182 Days
• Field of Search: 707/705, 707/722, 707/736, 707/737, 707/754
• US Class Current: 707/722
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

Methods and arrangements for employing descriptors for agent-customer interactions are disclosed. Filtering the pooled records based on one or more predetermined criteria is done such that analyzing the filtered records and comparing one interaction between an agent and a customer with another interaction between an agent and a customer may occur.

Claims

1. A method comprising:

executing with one or more processors one or more modules of computer program code configured for obtaining a record of an agent-customer interaction;

categorizing the record with one or more characterizing descriptors, wherein the descriptors comprise at least one characterization of at least one member selected from the group consisting of an agent in the agent-customer interaction;

a customer in the agent-customer interaction;

a manner of interaction between the agent and customer in the agent-customer interaction; and

a detail of interaction between the agent and customer in the agent-customer interaction;

pooling the record with other records of agent-customer interaction;

filtering the pooled records via applying at least one filter related to one or more of the one or more characterizing descriptors, and thereby reducing the number of pooled records to a comparison pool having a smaller number of records; and

within the comparison pool of records, analyzing the records and comparing one agent-customer interaction with another agent-customer interaction.

2. The method according to claim 1, further comprising extracting a characterizing descriptor via analyzing an agent-customer interaction.

3. The method according to claim 1, further comprising extracting a characterizing descriptor via analyzing metadata associated with an agent-customer interaction.

4. The method according to claim 1, wherein said filtering comprises filtering the pooled records based on one or more characterizing descriptors which have similar values with respect to interactions being compared.

5. The method according to claim 1, wherein said obtaining comprises obtaining one taken from the group consisting of:

a record of telephonic interaction between an agent and a customer; and

a record of written electronic interaction between an agent and a customer.

6. The method according to claim 1, wherein said categorizing comprises categorizing the record with one or more domain-independent descriptors.

7. The method according to claim 6, wherein the one or more domain-independent descriptors are taken from the group consisting of:

number of parties in the interaction;

customer demographics;

a duration-based parameter;

type of conversation in the interaction;

customer familiarity with a product;

agent experience.

8. The method according to claim 1, wherein said categorizing comprises categorizing the record with one or more domain-dependent descriptors.

9. The method according to claim 8, wherein the one or more domain-dependent descriptors are taken from the group consisting of:

a type of phone call characterizing the interaction;

an indication of whether a sale was closed in the interaction;

customer-confidential information;

information on customer occupation or business.

10. The method according to claim 1, wherein said filtering comprises filtering the pooled records based on one or more predetermined criteria related to one or more of the characterizing descriptors.

11. An apparatus comprising:

one or more processors; and

a computer readable storage medium having computer readable program code embodied therewith and executable by the one or more processors, the computer readable program code comprising;

computer readable program code configured to obtain a record of an agent-customer interaction;

computer readable program code configured to categorize the record with one or more characterizing descriptors, wherein the descriptors comprise at least one characterization of at least one member selected from the group consisting of;

an agent in the agent-customer interaction;

a customer in the agent-customer interaction;

a manner of interaction between the agent and customer in the agent-customer interaction; and

a detail of interaction between the agent and customer in the agent-customer interaction;

computer readable program code configured to pool the record with other records of agent-customer interactions;

computer readable program code configured to filter the pooled records via applying at least one filter related to one or more of the one or more characterizing descriptors, and thereby reduce the number of pooled records to a comparison pool having a smaller number of records; and

computer readable program code configured to, within the comparison pool of records, analyze the records and compare one agent-customer interaction with another agent-customer interaction.

12. A computer program product comprising:

a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer readable program code configured to obtain a record of an agent-customer interaction;

computer readable program code configured to categorize the record with one or more characterizing descriptors, wherein the descriptors comprise at least one characterization of at least one member selected from the group consisting of;

an agent in the agent-customer interaction;

a customer in the agent-customer interaction;

a manner of interaction between the agent and customer in the agent-customer interaction; and

a detail of interaction between the agent and customer in the agent-customer interaction;

computer readable program code configured to pool the record with other records of agent-customer interactions;

computer readable program code configured to filter the pooled records via applying at least one filter related to one or more of the one or more characterizing descriptors, and thereby reduce the number of pooled records to a comparison pool having a smaller number of records; and

computer readable program code configured to, within the comparison pool of records, analyze the records and compare one agent-customer interaction with another agent-customer interaction.

13. The computer program product according to claim 12, further comprising computer readable program code configured to extract one taken from the group consisting of:

a characterizing descriptor via analyzing an agent-customer interaction; and

a characterizing descriptor via analyzing metadata associated with an agent-customer interaction.

14. The computer program product according to claim 12, wherein said computer readable program code is configured to filter the pooled records based on one or more characterizing descriptors which have similar values with respect to interactions being compared.

15. The computer program product according to claim 12, wherein said computer readable program code is configured to obtain one taken from the group consisting of:

a record of telephonic interaction between an agent and a customer; and

a record of written electronic interaction between an agent and a customer.

16. The computer program product according to claim 12, wherein said computer readable program code is configured to categorize the record with one or more domain-independent descriptors.

17. The computer program product according to claim 16, wherein the one or more domain-independent descriptors are taken from the group consisting of:

number of parties in the interaction;

customer demographics;

a duration-based parameter;

type of conversation in the interaction;

customer familiarity with a product;

agent experience.

18. The computer program product according to claim 12, wherein said computer readable program code is configured to categorize the record with one or more domain-dependent descriptors.

19. The computer program product according to claim 18, wherein the one or more domain-dependent descriptors are taken from the group consisting of:

a type of phone call characterizing the interaction;

an indication of whether a sale was closed in the interaction;

customer-confidential information;

information on customer occupation or business.

20. The computer program product according to claim 12, wherein said computer readable program code is configured to filter the pooled records based on one or more predetermined criteria related to one or more of the characterizing descriptors.