Bifurcated Sentiment Analysis for Communication Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sentiment analysis systems are limited by the need for large amounts of data, which increases noise and computational resource usage, leading to inaccurate sentiment determination and inefficient resource utilization.
Innovation Solution
The system employs a bifurcated user-specific sentiment analysis, first reducing noise by limiting initial classification to determining positive or negative sentiment values for user-specific utterances, and then categorizing utterances to improve classification accuracy while reducing computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sentiment analysis processes all utterances in a transcript to determine user sentiment, then comprehensive sentiment determination is achieved, but noise from non-user utterances increases and computational resources are wasted
Solution Approach 1:
The patent extracts and processes only user-specific utterances from the transcript, separating them from non-user utterances (such as agent or system responses). This extraction eliminates noise from irrelevant sources while maintaining the integrity of user sentiment data, directly resolving the contradiction between comprehensive analysis and noise reduction
Solution Approach 2:
The patent segments the transcript into distinct user-specific utterances and non-user utterances, then applies sentiment analysis only to the user segment. This segmentation allows the system to focus computational resources on relevant data while ignoring irrelevant portions, reducing processing volume without sacrificing sentiment determination accuracy
2Measurement precision
If sentiment analysis processes large amounts of training data and input data to improve accuracy, then sentiment determination becomes more accurate, but computational resource usage increases significantly
Solution Approach 1:
The patent extracts only the essential user-specific portions from transcripts, eliminating the need to process entire transcripts including agent responses and system messages. This extraction reduces input data volume while maintaining sentiment analysis accuracy by focusing only on data that contains user sentiment information
Solution Approach 2:
The patent applies partial action by processing only a subset of the available data (user-specific utterances) rather than the complete dataset. This partial processing approach achieves sufficient sentiment determination accuracy without the excessive computational resource consumption that would result from processing all utterances
Data Source
AI summary
Routing peer-to-peer communications via telecommunications networks based on bifurcated user-specific sentiment analysis may be facilitated. In some embodiments, a system may generate a sentiment value related to each utterance of a set of utterances associated with a user by providing each utterance of the set of utterances to a sentiment machine learning model. The system may bin each utterance into a set of bins based on the sentiment values. The system may determine a sentiment probability of each bin of the set of bins by randomly sampling a subset of utterances corresponding to a respective bin of the set of bins. The system may determine an overall sentiment probability for a transcript based on the determined sentiment probability of each bin. In response to receiving a communication request, the system may route the communication request to an agent based on the overall sentiment probability satisfying a threshold sentiment probability.