Contextual Routing Optimization for Voice and Text Interactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current user interaction platforms, such as IVR systems and chatbots, face inefficiencies in routing interactions due to complex navigation and high error rates, leading to increased costs and user frustration.
Innovation Solution
The system processes interaction problem statements to generate summaries, which are used as input for machine learning models to predict optimal routes for voice-based and textual-based interactions, enabling automated and efficient routing to live agents or automated flows.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional IVR systems use hundreds of potential routes for interactions, then the system can handle diverse interaction types, but the user experience becomes difficult and time-consuming
Solution Approach 1:
The patent introduces an intermediary component (routing optimization system) that sits between the user interaction and the complex routing system. This intermediary analyzes interaction problem statements, generates summaries, and determines optimal routes, thereby shielding users from the underlying complexity of hundreds of potential routes while maintaining the system's ability to handle diverse interaction types
2Adaptability or versatility
If traditional routing systems use complex navigation structures, then they can accommodate various interaction outcomes, but routing errors increase significantly
Solution Approach 1:
The patent replaces the traditional mechanical routing system (based on predefined navigation structures and keyword matching) with an AI-based system that uses natural language processing and machine learning models. This substitution analyzes the semantics and context of interaction problem statements to determine optimal routes, significantly reducing routing errors while maintaining comprehensive coverage of various interaction types
3Ease of operation
If the system provides detailed context to live agents for all interactions, then user experience improves, but processing time and computational resources increase
Solution Approach 1:
The patent applies partial action by providing detailed context summaries only when necessary - specifically for complex interactions that require live agent assistance. For simpler interactions that can be resolved through automated flows, minimal or no context preparation is performed. This selective approach maintains high agent assistance quality when needed while avoiding unnecessary processing time and computational resource consumption
Data Source
AI summary
Methods, apparatus, systems, computing devices, computing entities, and/or the like for contextually optimizing routings for interactions. This may include receiving an interaction, wherein the interaction is selected from the group consisting of a voice-based interaction and a textual-based interaction; receiving an interaction problem statement for the interaction; generating, based at least in part on the interaction problem statement, an interaction problem statement summary, wherein the interaction problem statement comprises the context of the interaction; identifying one or more features for the interaction, wherein the features are input for one or more machine learning models; predicting an optimal route for the interaction, wherein the optimality of each route, hence, the optimal route is determined by the one or more machine learning models; and routing the interaction to the optimal route.