Customer service management system

• US 9,224,147 B2
• Filed: 05/02/2015
• Issued: 12/29/2015
• Est. Priority Date: 07/16/2007
• Status: Active Grant

• Current Assignee: Hector Franco
• Original Assignee: Hector Franco
• Inventors: Franco, Hector
• Primary Examiner(s): YU, ARIEL J
• Application Number:
  US14/702,722
• Publication Number:
  US 20150262188A1
• Time in Patent Office: 241 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/1097 Task assignment
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: H04M 3/5158 in combination with automated outdialling systems devices for signalling identity of wanted subscriber H04M1/26

Abstract

The customer is given the option to access customer service through the Internet. A web site provides several convenient alternatives for scheduling a voice session with a customer service agent instead of waiting on the phone. Users are encouraged to search a Selection-Oriented-Knowledge-Base (SOKB) that helps the user'"'"'s thinking process by displaying a sequence of intuitively recognizable multimedia menu selections that eventually lead to what the user has in mind and provide appropriate answers. The SOKB is based upon a Selection-On-Vertex network that provides the infrastructure to expand the level of knowledge of the SOKB by automatically capturing knowledge gained through experience. Customer service agents are seamlessly integrated into the SOKB by a NEED HELP request button that the user can click if difficulties are encountered during the search. A Help Requests Predictor enables customer service agents to respond within seconds to NEED HELP requests initiated by users.

Claims

1. A user support system comprising:

a host system;

a selection oriented knowledge base executing on the host system, the selection oriented knowledge base configured as a user-navigable directed graph comprising a plurality of nodes wherein each node is configured to provide information for display on a web page, and wherein for at least some of the nodes, the web page displays, in association with the information, a user-selectable option to establish a communication session with a live representative;

a navigational archive executing on the host system, the navigational archive configured to log paths through the selection oriented knowledge base traversed by users navigating the selection oriented knowledge base, and in association with the logged paths and nodes within the paths, to log user-selections of options to establish a communication session with a live representative;

a help requests predictor executing on the host system, the help requests predictor configured to;

for each node of a first plurality of nodes within the selection oriented knowledge base, count a number of active users that are browsing the node, and

for each node of a second plurality of nodes within the selection oriented knowledge base;

determine, based upon the logged paths and selections in the navigational archive, at least one probability that a user selects an option at the node to establish a communication session with a live representative, and

provide a predicted demand for service agents at the node based on the at least one probability that a user selects an option at the node to establish a communication session with a live representative and based on at least one of the counts of numbers of active users; and

a service agents scheduler executing on the host system, the service agents scheduler configured to use the predicted demand provided by the help requests predictor for the second plurality of nodes to allocate live service agents to handle user communication sessions for the second plurality of nodes.

2. The user support system of claim 1, wherein the navigational archive is further configured to log:

times at which users transition to nodes, and

times for user-selections of options to establish a communication session with a live representative.

3. The user support system of claim 2, wherein the help requests predictor is further configured to provide the predicted demand for service agents at the node as a function of time.

4. The user support system of claim 1, wherein the help requests predictor is further configured to determine, for each of a plurality of pairs of nodes comprising a first node selected from the first plurality of nodes and a second node from the second plurality of nodes, a likelihood that an active user browsing the first node will traverse the second node.

5. The user support system of claim 4, wherein the help requests predictor is further configured to provide the predicted demand for service agents as a function of time.

6. The user support system of claim 1, wherein:

the navigational archive is further configured to determine a score representative of effort an active user has expended in browsing the selection oriented knowledge base, and

the service agents scheduler is further configured to use the score to prioritize a connection of the active user, over other active users, to a live service agent.

7. The user support system of claim 1, wherein the host system is configured to:

display a reference code on a web page in response to a user request to establish a communication session with a live representative;

receive the reference code in response to a prompt to a user to provide the reference code in association with a setup of a communication session with a live representative; and

use the received reference code to identify a user session associated with the web page.

8. A method for providing user support, the method comprising:

providing a host system;

operating a selection oriented knowledge base on the host system, the selection oriented knowledge base configured as a user-navigable directed graph comprising a plurality of nodes wherein each node is configured to provide information for display on a web page, and wherein for at least some of the nodes, the web page displays, in association with the information, a user-selectable option to establish a communication session with a live representative;

logging paths through the selection oriented knowledge base traversed by users navigating the selection oriented knowledge base;

logging, in association with the logged paths and nodes within the paths, user-selections of options to establish a communication session with a live representative;

for each node of a first plurality of nodes within the selection oriented knowledge base, counting a number of active users that are browsing the node;

for each node of a second plurality of nodes within the selection oriented knowledge base;

determining, based upon the logged paths and selections in the navigational archive, at least one probability that a user selects an option at the node to establish a communication session with a live representative, and

providing a predicted demand for service agents at the node based on the at least one probability that a user selects an option at the node to establish a communication session with a live representative and based on at least one of the counts of numbers of active users; and

using the predicted demand for service agents for the second plurality of nodes to allocate live service agents to handle user communication sessions for the second plurality of nodes.

9. The method of claim 8, further comprising:

logging times at which users transition to nodes, and

logging times for user-selections of options to establish a communication session with a live representative.

10. The method of claim 9, wherein the predicted demand for service agents at the node is provided as a function of time.

11. The method of claim 8, further comprising determining, for each of a plurality of pairs of nodes comprising a first node selected from the first plurality of nodes and a second node from the second plurality of nodes, a likelihood that an active user browsing the first node will traverse the second node.

12. The method of claim 11, wherein the predicted demand for service agents is provided as a function of time.

13. The method of claim 8, further comprising:

determining a score representative of effort an active user has expended in browsing the selection oriented knowledge base, and

using the score to prioritize a connection of the active user, over other active users, to a live service agent.

14. The method of claim 8, further comprising:

displaying a reference code on a web page in response to a user request to establish a communication session with a live representative;

receiving the reference code in response to a prompt to a user to provide the reference code in association with a setup of a communication session with a live representative; and

using the received reference code to identify a user session associated with the web page.