Method and apparatus for notifying customers of agent's availability

1. A computer-implemented method comprising:

receiving, by a processor, an input indicative of a customer seeking an interaction with an agent of an enterprise, the input provided by the customer using a first interaction channel;

responsive to said received input, said processor predicting, using a prediction model, an intention of the customer for seeking the interaction with the agent based on a current journey and past journeys of the customer on interaction channels associated with the enterprise, wherein the predicting comprises (1) normalizing interaction data related to the current journey and the past journeys of the customer into one or more dusters; (2) extracting feature vectors from one or more dusters of the normalized data based on co-occurrence of terms or a contiguous sequence of terms; and (3) determining a prediction of the intention based on classifying the feature vectors, said classifying comprising one or more models based on logistic regression, an artificial neural network (ANN), and a Support Vector Machine (SVM) with Platt scaling:

subsequent to predicting the intention, said processor determining if at least one agent among a plurality of agents of the enterprise is available for interacting with the customer based on the prediction;

if no agent is available for interacting with the customer, said processor provisioning a status message to the customer, the status message comprising an estimate of a waiting time for the interaction with the agent;

subsequent to the provisioning of the status message, said processor tracking availability of the at least one agent, the tracking performed for at least a time period equal to the estimate of the waiting time specified in the status message;

subsequent to detecting the availability of the agent, said processor provisioning a notification to the customer informing the customer of the availability of the agent, the notification provided using the first interaction channel or a second interaction channel different than the first interaction channel;

wherein responsive to said provisioning the processor:

with a Virtual Assistant (VA) in an electronic device associated with the customer, provisioning the status message in form of a spoken input to the customer, and/or

displaying a chat application user interface (UI) on a display screen of an electronic device associated with the customer for establishing the interaction between the customer and the agent; and

establishing the interaction between the customer and the agent by the processor subsequent to providing the notification to the customer, the interaction established on the first interaction channel or the second interaction channel.

2. The method as claimed in claim 1 , wherein the first interaction channel corresponds to a native mobile application associated with the enterprise and, wherein the second interaction channel corresponds to one of a chat interaction channel and a voice interaction channel.

3. The method as claimed in claim 1 , wherein the interaction with the agent is established on an electronic device different than a device used by the customer for provisioning the input.

4. The method as claimed in claim 1 , further comprising:

detecting, by the apparatus, attention of the customer in at least one interaction channel from among a plurality of enterprise interaction channels, wherein an interaction channel associated with the attention of the customer is selected as the second interaction channel for at least one of provisioning of the notification and facilitating the interaction with the agent.

5. The method as claimed in claim 1 , further comprising:

identifying, by the apparatus, an agent type suitable for handling the interaction with the customer, wherein the identification of the suitable agent type is performed based on the predicted intention of the customer.

6. The method as claimed in claim 5 , wherein the suitable agent type corresponds to an agent type associated with specialized skill in handling interactions related to the intention of the customer.

7. The method as claimed in claim 5 , wherein the suitable agent type corresponds to an agent type associated with persona matching a persona of the customer.

8. The method as claimed in claim 1 , wherein the notification is provided to the customer based on a customer preference for receiving notifications.

9. An apparatus comprising:

a memory for storing instructions; and

a processor configured to execute the instructions and thereby cause the apparatus to perform at least:

receive an input indicative of a customer seeking an interaction with an agent of an enterprise, the input provided by the customer using a first interaction channel;

predict, using a prediction model, an intention of the customer for seeking the interaction with the agent, the intention predicted based on at least one of a current journey and past journeys of the customer on interaction channels associated with the enterprise, wherein the intention is predicted based on (1) normalizing interaction data related to the current journey and the past journeys of the customer into one or more clusters; (2) extracting feature vectors from one or more clusters of the normalized data based on co-occurrence of terms or a contiguous sequence of terms; and (3) determining a prediction of the intention based on classifying the feature vectors, said classifying comprising one or more models based on logistic regression, an artificial neural network (ANN), and a Support Vector Machine (SVM) with Platt scaling;

subsequent to receiving the input, determine if at least one agent among a plurality of agents of the enterprise is available for interacting with the customer;

if no agent is available for interacting with the customer, cause a provisioning of a status message to the customer, the status message comprising an estimate of a waiting time for the interaction with the agent;

subsequent to the provisioning of the status message, track availability of the at least one agent, the tracking performed for at least a time period equal to the estimate of the waiting time specified in the status message;

subsequent to detecting the availability of the agent, cause a provisioning of a notification to the customer for informing the customer of the availability of the agent, the notification provided using the first interaction channel or a second interaction channel different than the first interaction channel;

wherein the apparatus:

with a Virtual Assistant (VA) in an electronic device associated with the customer, provisions the status message in form of a spoken input to the customer; and/or

displays a chat application user interface (UI) on a display screen of an electronic device associated with the customer for establishing the interaction between the customer and the agent; and

establish the interaction between the customer and the agent subsequent to providing the notification to the customer, the interaction established on the first interaction channel or the second interaction channel.

10. The apparatus as claimed in claim 9 , wherein the first interaction channel corresponds to a native mobile application associated with the enterprise and, wherein the second interaction channel corresponds to one of a chat interaction channel and a voice interaction channel.

11. The apparatus as claimed in claim 9 , wherein the apparatus is further caused to identify an agent type suitable for handling the interaction with the customer, wherein the identification of the suitable agent type is performed based on the predicted intention of the customer.

12. A computer-implemented method comprising:

receiving, by a processor, an input indicative of a customer seeking an interaction with an agent of an enterprise, the input provided by the customer using a native mobile application on an electronic device associated with the customer;

predicting, by the processor using a prediction model, an intention of the customer for seeking the interaction with the agent; the intention predicted based on at least one of a current journey and past journeys of the customer on interaction channels associated with the enterprise, wherein the predicting comprises (1) normalizing interaction data related to the current journey and the past journeys of the customer into one or more dusters; (2) extracting feature vectors from one or more dusters of the normalized data based on co-occurrence of terms or a contiguous sequence of terms; and (3) determining a prediction of the intention based on classifying the feature vectors, said classifying comprising one or more models based on logistic regression, an artificial neural network (ANN), and a Support Vector Machine (SVM) with Platt scaling;

subsequent to receiving the input, determining by the processor, if at least one agent among a plurality of agents of the enterprise is available for interacting with the customer;

if no agent is available for interacting with the customer, causing by the processor, a provisioning of a status message to the customer in form of a spoken input, the status message comprising an estimate of a waiting time for the interaction with the agent;

subsequent to the provisioning of the status message, tracking by the processor, availability of the at least one agent, the tracking performed for at least a time period equal to the estimate of the waiting time specified in the status message;

subsequent to detecting the availability of the agent, causing by the processor, provisioning of a notification to the customer for informing the customer of the availability of the agent, the notification provided using a different interaction channel than the native mobile application channel;

wherein responsive to said provisioning the processor:

with a Virtual Assistant (VA) in an electronic device associated with the customer, provisioning the status message in form of a spoken input to the customer, and/or

displaying a chat application user interface (UI) on a display screen of an electronic device associated with the customer for establishing the interaction between the customer and the agent; and

establishing, by the processor the interaction between the customer and the agent.

13. The method as claimed in claim 12 , further comprising:

identifying, by the apparatus, an agent type suitable for handling the interaction with the customer, wherein the identification of the suitable agent type is performed based on the predicted intention of the customer.