Method for connecting users with agents based on user values dynamically determined according to a set of rules or algorithms

• US 10,044,866 B2
• Filed: 09/25/2017
• Issued: 08/07/2018
• Est. Priority Date: 10/23/2014
• Status: Active Grant

• Current Assignee: Teletech Holdings Incorporated
• Original Assignee: Teletech Holdings Incorporated
• Inventors: Sharpe, Bruce A., Shrader, Anthony G., Cumberland, William T.
• Primary Examiner(s): ADDY, THJUAN KNOWLIN
• Application Number:
  US15/714,980
• Publication Number:
  US 20180027118A1
• Time in Patent Office: 316 Days
• Field of Search: 37926509, 37926511, 37926512, 37926513, 37926501, 37926505, 379 8812, 379 8811, 379 8813
• CPC Class Codes: G06Q 30/0257 User requested
• CPC Class Codes: G06Q 30/0261 based on user location
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04M 2203/551 Call history recording a computer conference H04L12/1831
• CPC Class Codes: H04M 2203/556 Statistical analysis and interpretation
• CPC Class Codes: H04M 2203/558 Databases
• CPC Class Codes: H04M 3/42068 where the identifier is used to access a profile
• CPC Class Codes: H04M 3/4878 Advertisement messages
• CPC Class Codes: H04M 3/5133 Operator terminal details
• 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 3/5232 Call distribution algorithms
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution
• CPC Class Codes: H04M 7/0021 Details of Application Programming Interfaces
• CPC Class Codes: H04M 7/003 Click to dial services
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

A request is received for connecting a user with an agent, the request identifying a user interaction with content. A second server is accessed to determine a first score of the user representing a benefit the user has generated for a client that provides the content. A third server is accessed to determine a second score of the user representing overall burden to provide services to the user by the client based on an interaction history of the user with the client. A user value is dynamically determined based on the first score and the second score using a user value determination algorithm that is specifically configured for the client. A list of agent candidates is identified from a pool of agents based on the user value and the collection of real-time data. A first communication session is established between the user and one of the agent candidates.

Claims

1. A computer-implemented method for connecting users with agents based on user interactions of a browsing session, the method comprising:

capturing and recording in an interaction context object, by an interaction monitor hosted by a first server, a browsing history of one or more Web pages during a browsing session, the one or more Web page being presented to a user via a user device of the user;

in response to a request initiated from the user device for connecting with an agent associated with the first server during the browsing session, passing the interaction context object to a user profile compiler;

obtaining and storing by the user profile compiler static user data and dynamic user data in the interaction context object, wherein the dynamic user data is obtained in real time from a plurality of external data sources;

passing the interaction context object having the compiled static user data and the dynamic user data to a matching logic;

determining, by the matching logic, a list of one or more agent candidates from a pool of a plurality of agents by matching the static user data and the dynamic user data stored in the interaction context object with agent profiles of the agents; and

passing the interaction context object to an agent connect system to establish a communication session between the user device and an agent device of an agent selected from the agent candidates.

2. The method of claim 1, further comprising:

receiving, at the first server via a first application programming interface (API), an initial user interaction with one of the one or more Web pages during the browsing session; and

in response to the initial user interaction, generating the interaction context object specifically corresponding to the browsing session, wherein the interaction context object records all activities occur during the browsing session.

3. The method of claim 1, wherein capturing and recording the browsing history in the interaction context object comprises:

determining one or more universal resource locators (URLs) of the one or more Web pages accessed by the user device; and

storing the URLs in the interaction context object during the browsing session.

4. The method of claim 1, wherein determining the list of one or more agent candidates comprises:

passing the interaction context object to a user intent determination module hosted by the first server;

determining, by the user intent determination module, a user intent of the user based on the browsing history of the browsing session stored in the interaction context object; and

determining a first set of agent candidates from the pool of agents by matching the user intent and an expertise attribute of agent profiles of the agents in the pool.

5. The method of claim 4, further comprising:

passing the interaction context object to a user value calculator hosted by the first server;

calculating, by the user value calculator, a user value of the user based on the static user data and the dynamic user data stored in the interaction context object; and

determining a second set of agent candidates from the first set of agent candidates by matching the user value with a value range attribute of agent profiles of the first set of agent candidates.

6. The method of claim 5, wherein calculating a user value comprises:

computing a revenue score based on a total of revenue the user has generated for a client that provides the Web pages;

computing a cost score based on overall costs of the client to provide services to the user; and

calculating the user value based on the revenue score and the cost score using a predetermined formula associated with the client.

7. The method of claim 6, wherein calculating a user value further comprises:

computing a loyalty score representing how loyal the user is with respect to the client;

computing an adoption score representing an adoption rate of the user with respect to new services of the client;

computing an influence score representing a social influence of the user with respect to other users; and

calculating the user value based on the loyalty score, the adoption score, and the influence score using the predetermined formula associated with the client.

8. The method of claim 5, further comprising matching a first predetermined set of user attributes obtained from the static user data and the dynamic user data with a second predetermined set of agent attributes of the agent profiles of the second set of agent candidates to derive a third set of agent candidates, using a matching rule associated with the client.

9. The method of claim 8, further comprising, for each of the agents in the third set, determining one or more communication channels, using a channel mapping table associated with the client, based on an agent type of the agent from a corresponding agent profile, wherein the list of agent candidates includes the third set of agent candidates, each being associated with the determined communication channels.

10. The method of claim 1, wherein determining a list of one or more agent candidates from a pool of a plurality of agents comprises:

passing the interaction context object to a user classification module;

determining, by the user classification module, a user type of the user by matching each of the predetermined user attributes obtained from the static user information and dynamic user information against a corresponding one defined in a user classification rule associated with the client; and

determining, by an agent classification module, an agent type based on the user type by matching the user type with agent types defined in an agent classification rule associated with the client, wherein the list agents is determined by matching the agent type with an agent type specified in each of the agent profiles.

11. The method of claim 10, wherein the user classification rule defines a plurality of user types based on conditions of a set of predetermined user attributes.

12. The method of claim 10, wherein the agent classification rule maps a plurality of user types to a plurality of agent types, respectively.

13. The method of claim 1, further comprising:

passing the interaction context object to a user classification module;

determining, by the user classification module, a user type of the user by matching each of the predetermined user attributes obtained from the static user information and dynamic user information against a corresponding one defined in a user classification rule associated with the client; and

determining, by a treatment classification module, a treatment type based on the user type by matching the user type with a plurality of treatment types defined in a treatment classification rule associated with the client, wherein each treatment type corresponds to one of a plurality of treatment profiles having information describing how a user is to be serviced.

14. The method of claim 13, wherein a treatment profile includes a predetermined set of agent attributes and conditions to be satisfied in order for an agent to be selected for a treatment represented by the treatment profile, and wherein the agents of the list are selected based on their respective agent profiles having the predetermined set of agent attributes matching the conditions specified in the treatment profile.

15. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform a method of connecting users with agents based on user interactions of a browsing session, the method comprising:

capturing and recording in an interaction context object, by an interaction monitor hosted by a first server, a browsing history of one or more Web pages during a browsing session, the one or more Web page being presented to a user via a user device of the user;

in response to a request initiated from the user device for connecting with an agent associated with the first server during the browsing session, passing the interaction context object to a user profile compiler;

obtaining and storing by the user profile compiler static user data and dynamic user data in the interaction context object, wherein the dynamic user data is obtained in real time from a plurality of external data sources;

passing the interaction context object having the compiled static user data and the dynamic user data to a matching logic;

determining, by the matching logic, a list of one or more agent candidates from a pool of a plurality of agents by matching the static user data and the dynamic user data stored in the interaction context object with agent profiles of the agents; and

passing the interaction context object to an agent connect system to establish a communication session between the user device and an agent device of an agent selected from the agent candidates.

16. The machine-readable medium of claim 15, wherein the method further comprises:

receiving, at the first server via a first application programming interface (API), an initial user interaction with one of the one or more Web pages during the browsing session; and

in response to the initial user interaction, generating the interaction context object specifically corresponding to the browsing session, wherein the interaction context object records all activities occur during the browsing session.

17. The machine-readable medium of claim 15, wherein capturing and recording the browsing history in the interaction context object comprises:

determining one or more universal resource locators (URLs) of the one or more Web pages accessed by the user device; and

storing the URLs in the interaction context object during the browsing session.

18. A data processing system, comprising:

a processor; and

a memory to store instructions, which when executed by the processor, cause the processor to perform a method, the method including

capturing and recording in an interaction context object, by an interaction monitor hosted by a first server, a browsing history of one or more Web pages during a browsing session, the one or more Web page being presented to a user via a user device of the user,

in response to a request initiated from the user device for connecting with an agent associated with the first server during the browsing session, passing the interaction context object to a user profile compiler,

obtaining and storing by the user profile compiler static user data and dynamic user data in the interaction context object, wherein the dynamic user data is obtained in real time from a plurality of external data sources,

passing the interaction context object having the compiled static user data and the dynamic user data to a matching logic,

determining, by the matching logic, a list of one or more agent candidates from a pool of a plurality of agents by matching the static user data and the dynamic user data stored in the interaction context object with agent profiles of the agents, and

passing the interaction context object to an agent connect system to establish a communication session between the user device and an agent device of an agent selected from the agent candidates.

19. The system of claim 18, wherein the method further comprises:

receiving, at the first server via a first application programming interface (API), an initial user interaction with one of the one or more Web pages during the browsing session; and

in response to the initial user interaction, generating the interaction context object specifically corresponding to the browsing session, wherein the interaction context object records all activities occur during the browsing session.

20. The system of claim 18, wherein capturing and recording the browsing history in the interaction context object comprises:

determining one or more universal resource locators (URLs) of the one or more Web pages accessed by the user device; and

storing the URLs in the interaction context object during the browsing session.