Method, apparatus and non-transitory medium for customizing speed of interaction and servicing on one or more interactions channels based on intention classifiers

An apparatus, comprising:

• at least one processor;
• and
• a memory having stored therein machine executable instructions, that when executed by the at least one processor, cause the apparatus to:
• define a plurality of categories for classifying customer interaction data comprising information related to static customer attributes and information related to dynamic customer attributes, the plurality of categories comprising:
• at least one action category for classifying information related to customer actions on one or more interaction channels, the information related to the customer actions configuring at least in part the customer interaction data, wherein the at least one action category is defined based on the dynamic customer attributes associated with the customer interaction on the one or more interaction channels, and wherein the dynamic customer attributes associated with the customer interaction correspond to attributes of the customer interaction whose values are likely to change during the customer interaction;
• and
• at least one non-action category configured to facilitate classifying of the information related to the static customer attributes associated with the customer interaction on the one or more interaction channels, wherein the information related to the static customer attributes comprises:
• interaction timing information or interaction frequency information, and at least one of device information, browser information, and operating system information;
• receive data signals corresponding to a customer interaction on the one or more interaction channels, the data signals comprising information related to at least one customer action on the one or more interaction channels, said information comprising binary values where a ‘0’ value indicates a no-customer action corresponding to a particular action category and where a ‘1’ value indicates a customer action corresponding to the particular action category;
• configure the at least one action category and the at least one non-action category to classify together as intention classifiers for the customer interaction data;
• generate a sequence of values for each customer action from among the at least one customer action for classifying information related to the each customer action comprising a binary vector corresponding to each customer action associated with a fixed length, wherein a value is generated corresponding to each action category from among the at least one action category to configure the sequence of values, the sequence of values associated with the fixed length equal to a number corresponding to the at least one action category;
• predict with one or more conventional, static intention classifiers that process only fixed length inputs comprising a fixed number of predictors, an intention of a customer by using the sequence of values generated for the each customer action from among the at least one customer action, wherein the fixed length of the sequence of values facilitates use of the intention classifiers with said one or more conventional, static intention classifiers to predict the intention of the customer;
• and
• based on the predicted customer intent, automatically customizing a speed of interaction with the customer and/or customizing on the one or more interaction channels a speed of interaction with the customer and customizing a speed of servicing information.

A non-transitory computer-readable medium storing a set of instructions that when executed cause a computer to perform a method comprising:

• defining a plurality of categories for classifying customer interaction data comprising information related to static customer attributes and information related to dynamic customer attributes, the plurality of categories comprising:
• at least one action category for classifying information related to customer actions on one or more interaction channels, the information related to the customer actions configuring at least in part the customer interaction data, wherein the at least one action category is defined based on the dynamic customer attributes associated with the customer interaction on the one or more interaction channels, and wherein the dynamic customer attributes associated with the customer interaction correspond to attributes of the customer interaction whose values are likely to change during the customer interaction;
• and
• at least one non-action category configured to facilitate classifying of the information related to the static customer attributes associated with the customer interaction on the one or more interaction channels, wherein the information related to the static customer attributes comprises:
• interaction timing information or interaction frequency information, and at least one of device information, browser information, and operating system information;
• receiving data signals corresponding to a customer interaction on the one or more interaction channels, the data signals comprising information related to at least one customer action on the one or more interaction channels, said information comprising binary values where a ‘0’ value indicates a no-customer action corresponding to a particular action category and where a ‘1’ value indicates a customer action corresponding to the particular action category;
• configuring the at least one action category and the at least one non-action category to classify together as intention classifiers for the customer interaction data;
• generating a sequence of values for each customer action from among the at least one customer action for classifying information related to the each customer action comprising a binary vector corresponding to each customer action associated with a fixed length, wherein a value is generated corresponding to each action category from among the at least one action category to configure the sequence of values, the sequence of values associated with the fixed length equal to a number corresponding to the at least one action category;
• predicting with one or more conventional, static intention classifiers that process only fixed length inputs comprising a fixed number of predictors, an intention of a customer by using the sequence of values generated for the each customer action from among the at least one customer action, wherein the fixed length of the sequence of values facilitates use of the intention classifiers with said one or more conventional, static intention classifiers to predict the intention of the customer;
• and
• based on the predicted customer intent, automatically customizing on the one or more interaction channels a speed of interaction with the customer and customizing a speed of servicing information.