NLP Engine for Voice Response Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional IVR systems are inefficient in processing voice responses that do not match predetermined responses, leading to strain on computing and network resources and misrouting of calls, resulting in bottlenecks and inefficiencies.
Innovation Solution
A system that uses a natural language processing engine to analyze user utterances with a pre-defined statistical language model, identifying keywords and generating a service tag to determine the intended action, even when responses do not match pre-defined options, thereby reducing the need for users to repond with matching responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional IVR systems use predetermined responses to handle calls, then call processing is efficient for matching responses, but calls with non-matching responses cause resource strain and bottlenecks
Solution Approach 1:
The patent introduces an NLP engine as an intermediary component between the IVR system and the call routing mechanism. This NLP engine analyzes user utterances that do not match predetermined responses, extracting intent and entities to enable intelligent routing. The intermediary processes only the non-matching cases, while matching cases continue through the traditional efficient path, thus resolving the contradiction between handling flexibility and resource efficiency.
Solution Approach 2:
The call processing system is segmented into two distinct pathways: a traditional IVR path for predetermined response matching and an NLP-based intelligent path for non-matching responses. This segmentation allows the system to maintain high efficiency for common queries while applying advanced processing only when necessary, reducing overall resource strain while improving handling of diverse queries.
2Ease of operation
If traditional IVR systems request users to provide pre-defined responses, then call routing is straightforward, but it creates network bottlenecks and requires additional responses from users
Solution Approach 1:
The system performs preliminary NLP analysis on the user's first utterance before requiring any follow-up responses. The NLP engine extracts intent and entities from the initial query, enabling the system to determine routing destination or perform actions without forcing users to rephrase or select from predefined options. This preliminary processing eliminates the need for additional response-exchange cycles.
Solution Approach 2:
The patent replaces the mechanical keyword-matching mechanism with an NLP-based semantic understanding system. Instead of requiring users to match predetermined response patterns, the NLP engine interprets the meaning and intent behind diverse user utterances, enabling more natural and efficient interaction while reducing network overhead from multiple exchange cycles.
3Productivity
If traditional IVR systems misroute calls to wrong recipients, then calls are processed, but significant computing and networking resources are wasted
Solution Approach 1:
The NLP engine serves as an intermediary analysis layer that processes user utterances before final routing decisions are made. By extracting intent and entities from the query, the NLP engine provides enriched information to the routing system, enabling more accurate destination determination and reducing misrouting while maintaining processing throughput.
Data Source
AI summary
A system for processing voice responses is disclosed. The system is configured to store a correlation table identifying relationships between self-service routines, tags, and corresponding actions. The system receives a call from a user and issues a query in response to the call. The system receives an utterance from the user in response to the user and determines whether the utterance matches a pre-defined response. If there is no match, the system analyzes the utterance with a pre-defined statistical language model and identifies a service tag for the utterance. The system then associates the utterance with the service tag and a self-service routine that is associated with the call. The system identifies an action from the correlation table that correlates to the service tag and the self-service routine.