Segmented Communication Analysis With LLMs for Fine-Grained Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication analysis systems lack the ability to provide fine-grained feedback on the quality and content of interactions, such as virtual conferences, chats, and emails, limiting the effectiveness of performance evaluation and future engagement.
Innovation Solution
A system that segments communication records into smaller pieces and uses large language models (LLMs) to generate embeddings and evaluate segments based on analytical parameters, providing detailed feedback and justifications for the quality of interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If communication records are analyzed in full detail, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent segments communication records into smaller units (utterances, turns, or topical segments) before analysis. This segmentation enables the system to process and evaluate specific portions of communications independently, improving both the precision of analysis for each segment and the overall processing efficiency by avoiding analysis of entire communication records at once.
2Measurement precision
If fine-grained analysis is provided, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system segments communications into analyzable units and applies multiple analytical parameters (relevance, clarity, completeness, etc.) to each segment. This segmentation approach enables fine-grained feedback without requiring a single monolithic complex system, as each segment can be evaluated independently against multiple criteria.
Solution Approach 2:
The patent employs multiple analytical parameters (relevance, clarity, completeness, conciseness, etc.) to evaluate communication segments. By changing and applying multiple evaluation parameters rather than a single metric, the system achieves fine-grained analysis while maintaining manageable complexity through standardized parameter frameworks.
3Measurement precision
If comprehensive evaluation metrics are used, then measurement precision is improved, but productivity decreases
Solution Approach 1:
By segmenting communications into smaller units, the system can apply comprehensive evaluation metrics to each segment independently and in parallel. This segmentation enables thorough evaluation without proportionally increasing total processing time, as segments can be processed concurrently rather than requiring sequential analysis of entire communications.
Data Source
AI summary
One example method for communication analysis using LLMs includes receiving a set of communication records, the set of communication records representing one or more communications between a first person and a second person; receiving a set of analytical parameters associated with the set of communication records; generating a plurality of segments from the communication records; for each analytical parameter in the set of analytical parameters: determining a subset of segments semantically associated with the respective analytical parameter; generating, using a trained large language model (“LLM”), an evaluation of each segment of the respective subset of segments with respect to the respective analytical parameter; and generating, using the trained LLM, a response to the analytical parameter based on the evaluations of the segments; and outputting a full evaluation of the set of communication records based on the set of analytical parameters and the respective generated responses to the analytical parameters.