Multi-Language Emotion Aggregation for Customer Experience Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting customer net experience scores fail to accurately consider complex emotions and code-mixed content in customer interactions, leading to incomplete modeling of customer experiences.
Innovation Solution
A computer-implemented method that detects languages in interaction data, translates and processes text across multiple languages, determines emotion scores, and aggregates them to model customer interaction experiences based on an aggregate emotion score.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sentiment analysis methods are used to predict net experience scores, then the prediction process is simple and fast, but the accuracy is insufficient because complex emotions and code-mixed content are not considered
Solution Approach 1:
The patent segments the emotion analysis process into distinct modules: language detection module, translation module, emotion score determination module for each language, and aggregation module. This segmentation allows the system to handle complex multi-language emotions systematically while maintaining manageable complexity at each stage.
Solution Approach 2:
The patent introduces translation as an intermediary step that converts code-mixed content into separate language components. This intermediary process enables the system to analyze emotions in each language independently before aggregating them, thereby improving accuracy without requiring a single complex multi-language emotion model.
2Measurement precision
If emotion analysis is performed on code-mixed content in multiple languages, then the accuracy of customer experience modeling improves, but the processing time and computational resources increase
Solution Approach 1:
The patent performs language detection and translation as preliminary actions before emotion analysis. By identifying languages and translating code-mixed content upfront, the system prepares the data in a standardized format that enables parallel emotion score determination across multiple languages, reducing overall processing time.
Solution Approach 2:
The patent determines emotion scores for each detected language separately and then aggregates them, rather than attempting to analyze code-mixed content as a single unified language. This partial action approach processes each language component independently, which is more efficient than creating a comprehensive multi-language emotion model from scratch.
3Ease of operation
If only the original detected language is analyzed for emotion scores, then the processing is faster and simpler, but code-mixed content and multiple languages are not adequately considered
Solution Approach 1:
The patent creates a universal emotion analysis framework that handles both single-language and multi-language content through the same process. The system detects languages, translates to a common set of target languages, determines emotion scores for each, and aggregates them - this multi-functional approach ensures no language information is lost while maintaining process consistency.
Solution Approach 2:
The patent merges emotion scores from multiple languages into an aggregate emotion score that represents the overall customer sentiment. This combining process integrates information from code-mixed content and multiple languages while producing a unified metric that can be used for customer experience modeling.
Data Source
AI summary
A computer-implemented method and an apparatus for modeling customer interaction experiences receives interaction data corresponding to one or more interactions between a customer and a customer support representative. At least one language associated with the interaction data is detected. Textual content in a plurality of languages is generated corresponding to the interaction data based at least in part on translating the interaction data using two or more languages different than the at least one language. At least one emotion score is determined for text corresponding to each language from among the plurality of languages. An aggregate emotion score is determined using the at least one emotion score for the text corresponding to the each language. An interaction experience of the customer is modeled based at least in part on the aggregate emotion score.