Contextually optimizing routings for interactions

A computer program product comprising a non-transitory computer readable medium having computer program instructions stored therein, the computer program instructions when executed by a processor, cause the processor to:

• receive from a user computing device, an interaction problem statement that is input by a user via the user computing device during an interaction, wherein the interaction is at least one of a voice-based interaction with the user via the user computing device or a textual-based interaction with the user via the user computing device;
• generate, based at least in part on the interaction problem statement, an interaction problem statement summary, wherein the interaction problem statement summary (a) is generated (i) using at least one of keyword extraction, machine learning, abstractive summarization, or natural language processing, and (ii) during the interaction, and (b) comprises a reason for the interaction;
• identify based at least in part on the interaction problem statement summary, one or more features associated with the interaction;
• generate, using one or more machine learning models, an optimal route prediction for the interaction, wherein (a) the one or more features are provided as input to the one or more machine learning models, and (b) the optimal route prediction is based at least in part on the one or more features;
• route the interaction to an optimal route indicated by the optimal route prediction;
• monitor (a) a result of the interaction and (b) one or more target metrics;
• and
• store, in association with the interaction, (a) the result of the interaction and (b) the one or more target metrics.

A computing system comprising a non-transitory computer readable storage medium and one or more processors, the computing system configured to:

• receive from a user computing device, an interaction problem statement that is input by a user via the user computing device during an interaction, wherein the interaction is at least one of a voice-based interaction with the user via the user computing device or a textual-based interaction with the user via the user computing device;
• generate, based at least in part on the interaction problem statement, an interaction problem statement summary, wherein the interaction problem statement summary (a) is generated (i) using at least one of keyword extraction, machine learning, abstractive summarization, or natural language processing, and (ii) during the interaction, and (b) comprises a reason for the interaction;
• identify based at least in part on the interaction problem statement summary, one or more features associated with the interaction;
• generate, using one or more machine learning models, an optimal route prediction for the interaction, wherein (a) the one or more features are provided as input to the one or more machine learning models, and (b) the optimal route prediction is based at least in part on the one or more features;
• route the interaction to an optimal route indicated by the optimal route prediction;
• monitor (a) a result of the interaction and (b) one or more target metrics;
• and
• store, in association with the interaction, (a) the result of the interaction and (b) the one or more target metrics.