Systems and methods relating to customer experience automation

1. A computer-implemented method related to routing incoming interactions of contact centers via an intermediary platform, the incoming interactions being instigated by customers for communicating with the contact centers, wherein each of the contact centers comprises agents between which the incoming interactions are routed, and wherein the intermediary platform is maintained as a separate entity from both customer-side systems of the customers and contact center systems of the contact centers, the intermediary platform configured as a neutral arbitrator for arriving at a routing recommendation that balances customer-side preferences of the customers with contact center-side performance objectives of the contact centers, the method comprising the steps of:

receiving initial data identifying a first one of the incoming interactions (hereinafter “first incoming interaction”), wherein the first incoming interaction is instigated by a first one of the customers (hereinafter “first customer”) for contacting a first one of the contact centers (hereinafter “first contact center”), wherein the initial data includes information disclosing at least an intent of the first incoming interaction;

performing, by the intermediary platform, a first subprocess to generate a personalized routing profile, the personalized routing profile specifically tailored to facilitate routing the first incoming interaction in accordance with one or more preferences of the first customer, wherein the first subprocess comprises the steps of:

accessing data from a database, the database including at least a first customer profile storing data relating to the first customer;

based on the accessed data and the intent of the first incoming interaction, determining preferred agent characteristics data of the first customer for the first incoming interaction; and

generating the personalized routing profile so to include the preferred agent characteristics data of the first customer;

performing, by the intermediary platform, a second subprocess related to deriving a routing recommendation, wherein the second subprocess comprises the steps of:

deriving the routing recommendation for the first incoming interaction based on the preferred agent characteristics data of the first customer; and

transmitting the routing recommendation to the first contact center for routing the first incoming interaction in accordance therewith.

2. The computer-implemented method according to claim 1 , wherein the customer profile of the first customer comprises interaction data relating to past interactions that occurred between the first customer and a plurality of the contact centers;

wherein agent criteria are defined as a set of agent criterion, each of the agent criterion defining a basis by which a characteristic of an agent can be rated; and

wherein:

the preferred agent characteristics data of the first customer is defined as data describing the preferences of the first customer in relation to the agent criteria; and

actual agent characteristics data is defined as data describing how a particular one of the agents is rated in relation to the agent criteria.

3. The computer-implemented method according to claim 2 , further comprising the step of transmitting the personalized routing profile to a routing engine for use in deriving a routing recommendation for the first incoming interaction.

4. The computer-implemented method according to claim 2 , wherein a more-detailed enumeration of one or more of the steps of the second subprocess includes:

receiving contact center-side data from the first contact center relating to the first incoming interaction, the contact center-side data disclosing at least:

candidate agents, the candidate agents comprising at least two of the agents of the first contact center that qualify for handling the incoming interaction;

actual agent characteristics data for each of the candidate agents;

preferred agent characteristics data of the first contact center, the preferred agent characteristics data comprising data that describes preferences of the first contact center in relation to the agent criteria based on a contact center performance objective;

generating combined preferred agent characteristics data by combining via a weighted average the preferred agent characteristics data of the first customer and the preferred agent characteristics data of the first contact center;

calculating an agent favorableness score for each of the candidate agents, the agent favorableness score comprising a mathematical representation indicative of how closely a match is between the actual agent characteristics data for a particular one of the candidate agents and the combined preferred agent characteristics data;

identifying a most favored candidate agent as a one of the candidate agents producing the agent favorable score indicating a closest match between the actual agent characteristics data and the combined preferred agent characteristics data;

generating the routing recommendation that recommends routing the first incoming interaction to the most favored candidate agent; and

transmitting the routing recommendation to the first contact center.

5. The computer-implemented method according to claim 3 , wherein a more-detailed enumeration of one or more of the steps of the first subprocess includes:

identifying, from the past interactions of the first customer, qualifying examples in which:

an intent matches the intent of the first incoming interaction; and

a desired outcome is achieved;

determining one or more consistencies across the actual agent characteristics data of the agents in the qualifying examples of the past interactions; and

basing the preferred agent characteristics data for the first incoming interaction on the one or more consistencies across the actual agent characteristics data.

6. The computer-implemented method according to claim 3 , wherein a more-detailed enumeration of one or more of the steps of the first subprocess includes:

applying a machine learning algorithm across the interaction data from the past interactions to identify patterns correlating one or more factors to a desired outcome for a given type of interaction, wherein, in performing this step:

the one or more factors are defined as the actual agent characteristics data of the agents in the past interactions;

the desired outcome is defined as ones of the past interactions receiving positive customer feedback or achieving a successful resolution;

the type of interaction is defined as an interaction having an intent that matches the intent of the first incoming interaction;

basing the preferred agent characteristics data for the first incoming interaction on the actual agent characteristics data found to correlate to the desired outcome;

wherein the machine learning algorithm comprises a neural network.

7. The computer-implemented method according to claim 3 , wherein the customers include the first customer and a plurality of other customers (hereinafter “other customers”), and the database further includes one or more customer databases that store data relating to the other customers;

wherein the one or more customer databases includes interaction data relating to past interactions that occurred between the other customers and a plurality of the contact centers; and

wherein one of the agent criteria rates a personality characteristic.

8. The computer-implemented method according to claim 7 , wherein a more-detailed enumeration of one or more of the steps of the first subprocess includes:

identifying, from the past interactions of the other customers, qualifying examples in which:

an intent matches the intent of the first incoming interaction;

a desired outcome is achieved; and

a predetermined similarity is found to exist between the first customer and a particular one of the other customers involved in the past interaction;

determining one or more consistencies across the actual agent characteristics data of the agents in the qualifying examples of the past interactions; and

basing the preferred agent characteristics data for the first incoming interaction on the one or more consistencies across the actual agent characteristics data.

9. The computer-implemented method according to claim 7 , wherein a more-detailed enumeration of one or more of the steps of the first subprocess includes:

applying a machine learning algorithm across the interaction data from the past interactions to identify patterns correlating one or more factors to a desired outcome relevant to a type of customer given the type of interaction, wherein, in performing this step:

the one or more factors are defined as the actual agent characteristics data of the agents in the past interactions;

the desired outcome is defined as ones of the past interactions receiving positive customer feedback or achieving a successful resolution;

the type of interaction is defined as an interaction having an intent that matches the intent of the first incoming interaction; and

the type of customer is defined as one that shares one or more common characteristics with the first customer;

basing the preferred agent characteristics data for the first incoming interaction on the actual agent characteristics data found to correlate to the desired outcome.

10. The computer-implemented method according to claim 9 , wherein the customer profile and the one or more customer databases store biographical personal data relating to the first customer and the other customers, respectively;

wherein the one or more common characteristics comprise one or more characteristics stored within the biographical personal data.

11. The computer-implemented method according to claim 7 , wherein the interaction data of the other customers comprises feedback data, the feedback data comprising an evaluation provided by a particular one of the other customers in relation to a particular one of the past interactions;

wherein a more-detailed enumeration of one or more of the steps of the first subprocess includes:

applying a machine learning algorithm across the interaction data from the past interactions to identify patterns correlating one or more factors to a desired outcome relevant to a type of customer given a type of interaction, wherein, in performing this step:

the one or more factors are defined as the actual agent characteristics data of the agents in the past interactions;

the desired outcome is defined as ones of the past interactions wherein the feedback data is classified as being positive;

the type of interaction is defined as an interaction having an intent that matches the intent of the first incoming interaction; and

the type of customer is defined by a shared similarity with the first customer;

basing the preferred agent characteristics data for the first incoming interaction on the actual agent characteristics data found to correlate to the desired outcome.

12. The computer-implemented method according to claim 11 , wherein the feedback data includes feedback inferred from one or more statements made by the other customers within a concluding portion of the past interactions.

13. The computer-implemented method according to claim 7 , wherein the interaction data of the other customers comprises choice data, the choice data comprising data relating to selections the other customers make when allowed to select an agent (hereinafter “selected agent”) from a plurality of offered agents;

wherein a more-detailed enumeration of one or more of the steps of the first subprocess includes:

applying a machine learning algorithm across the interaction data from the past interactions to identify patterns correlating one or more factors to a desired outcome relevant to a type of customer given a type of interaction, wherein, in performing this step:

the one or more factors are defined as the actual agent characteristics data of the selected agents;

the desired outcome is defined as ones of the past interactions receiving positive customer feedback or achieving a successful resolution;

the type of interaction is defined as an interaction having an intent that matches the intent of the first incoming interaction; and

the type of customer is defined as one that shares a predetermined similarity with the first customer;

basing the preferred agent characteristics data for the first incoming interaction on the actual agent characteristics data found to correlate to the desired outcome.

14. The computer-implemented method according to claim 3 , wherein a more-detailed enumeration of one or more of the steps of the first subprocess includes:

determining one or more contextual factors relating to the incoming interaction by finding relationships between the initial data and data stored within the customer profile of the first customer; and

based on the one or more contextual factors, determining an interaction predictor, the interaction predictor comprising a prediction applicable to the first customer for the incoming interaction;

wherein the determination of the preferred agent characteristics data of the first customer for the first incoming interaction is also based on the interaction predictor.

15. The computer-implemented method according to claim 14 , wherein the interaction predictor comprises an upselling/cross-selling opportunity rating, the predicted upselling/cross-selling opportunity rating predicting a receptiveness of the first customer to considering offers made by the agent at upselling or cross-selling during the first incoming interaction.

16. The computer-implemented method according to claim 14 , wherein the interaction predictor comprises a severity rating, the severity rating predicting a level of importance that the first customer ascribes to the first incoming interaction.

17. The computer-implemented method according to claim 14 , wherein the interaction predictor comprises a predicted emotional state.

18. The computer-implemented method according to claim 17 , wherein the one or more contextual factors comprises a minimum number of the past interactions of the first customer being instigated by the first customer within a predetermined lookback period measured from when the first customer instigates the first incoming interaction; and

wherein the past interactions instigated by the first customer within the predetermined lookback each comprises:

a subject matter that matches a subject matter of the first incoming interaction; and

an unsuccessful attempt at resolving a customer problem relating to the subject matter.

19. The computer-implemented method according to claim 18 , wherein the predicted emotional state comprises a negative emotional state; and

wherein:

the minimum number comprises two; and

the predetermined lookback period is less than 6 hours.

20. The computer-implemented method according to claim 2 , wherein a more-detailed enumeration of one or more of the steps of the second subprocess includes:

receiving data identifying candidate agents, the candidate agents comprising at least two of the agents of the first contact center that qualify for handling the incoming interaction;

receiving actual agent characteristics data for each of the candidate agents;

calculating an agent favorableness score for each of the candidate agents, the agent favorableness score comprising a mathematical representation indicative of how closely a match is between the actual agent characteristics data for a particular one of the candidate agents and the preferred agent characteristics data of the first customer;

identifying a most favored candidate agent as a one of the candidate agents producing the agent favorable score indicating a closest match between the actual agent characteristics data and the preferred agent characteristics data; and

generating the routing recommendation, wherein the routing recommendation recommends routing the first incoming interaction to the most favored candidate agent.

21. The computer-implemented method according to claim 20 , wherein the second subprocess further comprises the step of transmitting the routing recommendation to the first contact center for use thereby in routing the first incoming interaction.