Bias-Adjusted Evaluation Using Communication Interaction Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing evaluation systems are prone to bias, making it difficult to determine and correct for evaluator bias during communication sessions, leading to inaccurate assessments and excessive resource consumption.
Innovation Solution
A system and method that utilize interaction data from communication sessions to determine the degree of evaluator bias, adjusting evaluations using machine learning models to enhance accuracy and consistency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional evaluation systems are used, then the evaluation process is simple, but the evaluation accuracy deteriorates due to evaluator bias
Solution Approach 1:
The patent introduces an intermediary system comprising monitoring components, interaction data generation modules, and machine learning models that act as a mediator between the evaluator and the evaluation process. This intermediary automatically monitors communication sessions, generates interaction data, determines bias degrees, and adjusts evaluations, thereby improving evaluation accuracy without requiring direct changes to the evaluator's behavior or the basic evaluation framework
Solution Approach 2:
The patent replaces the manual/mechanical evaluation process with an automated system using machine learning models and algorithms. Instead of relying on evaluators to consciously eliminate bias, the system uses computational models to objectively monitor interactions, analyze interaction data, determine bias degrees, and automatically adjust evaluations, substituting human judgment with algorithmic processing to improve accuracy
2Reliability
If multiple evaluations are conducted to ensure accuracy, then evaluation reliability improves, but resource consumption increases
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors communication sessions, analyzes interaction data in real-time, determines bias degrees, and adjusts evaluations dynamically. This feedback loop allows the system to achieve reliable evaluations through a single adjusted assessment rather than requiring multiple separate evaluations, thereby reducing resource consumption while maintaining or improving reliability
Solution Approach 2:
The patent changes the parameter being evaluated by introducing a bias degree parameter derived from interaction data. Instead of conducting multiple evaluations with the same parameters, the system modifies the evaluation parameter by factoring in the determined bias degree, allowing a single evaluation to suffice for achieving reliable results and reducing the need for repetitive evaluations
3Measurement precision
If automated bias detection is implemented, then evaluation accuracy improves, but processing complexity increases
Solution Approach 1:
The patent segments the automated bias detection process into distinct modular components: (1) monitoring communication sessions to generate interaction data, (2) analyzing interaction data to determine bias degrees using machine learning models, and (3) adjusting evaluations based on determined bias degrees. This segmentation allows each component to be independently developed, optimized, and maintained, managing processing complexity through modular architecture while achieving accurate bias detection
Data Source
AI summary
In some implementations, a device may obtain interaction data for an evaluator in a communication session with an individual based on interactions of the evaluator with the individual during the communication session, wherein the evaluator is to provide the evaluation of the individual. The device may obtain evaluation information identifying the evaluation of the individual by the evaluator. The device may determine a degree of bias of the evaluator toward the individual during the communication session based on at least the interaction data. The device may adjust the evaluation of the individual based on the degree of bias of the evaluator.