System and method for generating a network of contact center agents and customers for optimized routing of interactions

1. A system for routing interactions to contact center agents, the system comprising:

a processor; and

a memory, wherein the memory has stored therein instructions that, when executed by the processor, cause the processor to:

identify a network of agents and customers, wherein each node of the network represents either an agent or a customer, and a connection is made between the node representing the agent and the node representing the customer;

display the network of agents and customers including the nodes and the connections as a graph on a display screen;

adjust a value associated with each of the connections, wherein the value is indicative of a fit between a customer and agent pair in the network of agents and customers;

store the adjusted value in association with the connection;

select a current interaction to be routed;

identify a first group of agents based on one or more constraints for determining one or more candidate agents;

determine a fit between a current customer and each of the candidate agents based on the value associated with the corresponding connections;

select a particular agent of the candidate agents with a best fit; and

transmit a signal for routing the current interaction to the particular agent.

2. The system of claim 1 , wherein the instructions that cause the processor to determine the fit between the current customer and each of the candidate agents include instructions that cause the processor to predict sentiment to be expected during the current interaction.

3. The system of claim 2 , wherein the instructions that cause the processor to predict sentiment include instructions that cause the processor to:

analyze substance of each of a plurality of prior interactions;

for each of the prior interactions, identify sentiment from the analyzed substance;

learn agent or customer properties that resulted in the identified sentiments; and

identify an expected sentiment for the current interaction based on the learned properties.

4. The system of claim 1 , wherein the fit between the current customer and a particular agent of the candidate agents is based on attributes of the customer that are compatible with attributes of the particular agent.

5. The system of claim 4 , wherein the attributes of the particular agent include skills of the agent that are dynamically added or deleted in response to detecting respectively increase or decrease of interactions of a particular topic.

6. The system of claim 4 , wherein the attributes of the particular agent and the current customer are stored respectively in agent and customer profile records.

7. The system of claim 4 , wherein the attributes of the current customer are obtained from interaction of the customer with an automated response system.

8. The system of claim 1 , wherein the fit between the current customer and each of the candidate agents is based on prior interactions between the current customer and each of the candidate agents.

9. The system of claim 1 , wherein the fit is expressed as a numeric value indicative of an amount of fit between the current customer and each of the candidate agents.

10. The system of claim 9 , wherein the numeric value is based on a value obtained as a result of a prior interaction between the current customer and each of the candidate agents.

11. The system of claim 9 , wherein the numeric value is based on each expected value to be obtained as a result of routing the current interaction to each of the candidate agents.

12. The system of claim 11 , wherein the expected value is calculated based on a profile of each of the candidate agents, the profile of the current customer, and intent of the current interaction.

13. The system of claim 12 , wherein the profile of each of the candidate agents includes a preference of the agent in handling interactions, and the instructions further cause the processor to:

generate a routing offer to one or more of the candidate agents based on the preference of the corresponding agents.

14. The system of claim 12 , wherein the profile of each of the candidate agents includes a dynamically added skill, wherein the dynamically added skill is ignored or mapped to another skill, for calculating the expected value.

15. The system of claim 14 , wherein a proficiency level is associated with the skill, wherein the proficiency level is adjusted based on analysis of call transfers for each of the candidate agents.

16. The system of claim 1 , wherein the interactions are real-time interactions.

17. The system of claim 1 , wherein the one or more constraints are skills for handling the plurality of interactions.

18. The system of claim 1 , wherein the target performance objective for the contact center includes one of a desired business outcome or optimizing first call resolution, and wherein selecting the current interaction from the plurality of interactions to be routed based on determining the target performance objective for the contact center comprises:

selecting the current interaction to maximize the target performance objective across the plurality of interactions.

19. The system of claim 1 , wherein selecting the particular agent with the best fit comprises selecting the particular agent to maximize the target performance objective.

20. The system of claim 19 , wherein selecting the particular agent comprises one of:

selecting an agent with a best expected reward to achieve the target performance objective, or

making a random selection of an agent from a plurality of agents within a tolerance limit.

21. The system of claim 1 , wherein selecting the particular agent with the best fit comprises selecting an agent with a lower amount of existing performance data compared to an agent with a greater amount of existing performance data.

22. The system of claim 1 , wherein determining the target performance objective for the contact center comprises:

providing a graphical user interface (GUI) accessible by an administrator;

receiving, through the GUI, values for one or more parameters provided by the administrator; and

determining the target performance objective based on the one or more parameters.

23. The system of claim 1 , wherein the adjusting of the value is upon termination of an interaction between the particular one of the customers and a particular one of the agents involved in the interaction.

24. The system of claim 1 , wherein a plurality of connections and associated values are established and maintained between the customers and the agents, wherein each of the connections is representative of a different attribute evaluated for determining the fit between the current customer and each of the candidate agents.