Cognitive System for Event Veracity via Hidden Markov Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cognitive systems for determining the veracity of events, particularly in fields like insurance and marketing, face challenges due to the subjective and manual process of selecting predictor variables, which can lead to less rigorous and accurate predictive models, exacerbated by the rapidly growing research base and instantaneous information flow.
Innovation Solution
A system that retrieves predictor variables from a selected use case and generates hidden predictor variables using a hidden Markov model based on unstructured documents, combining these with existing predictors to provide a determination of event veracity, thereby automating the variable selection process and improving model accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual variable selection is used, then ease of operation is improved, but measurement precision and model accuracy deteriorate
Solution Approach 1:
The system enables self-service by allowing the cognitive system to automatically select and generate predictor variables without requiring manual intervention from domain experts. The hidden Markov model autonomously processes unstructured documents and identifies relevant variables, making the system self-sufficient in variable selection while maintaining high accuracy.
Solution Approach 2:
The patent replaces the mechanical manual process of variable selection with an automated computational system. The hidden Markov model uses algorithms to process unstructured documents and generate predictor variables, substituting human expertise with an automated intelligent system that achieves both ease of operation and high precision.
2Measurement precision
If more predictor variables are used, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system extracts only the most relevant predictor variables from the vast amount of available unstructured documents using the hidden Markov model. By extracting and selecting only the necessary variables rather than using all available data, the system maintains high measurement precision while managing device complexity through selective variable identification.
Solution Approach 2:
The patent changes the parameter of variable generation from static predefined lists to dynamic extracted variables from unstructured documents. The hidden Markov model adapts to different domains and use cases by extracting relevant variables on-demand, allowing the system to maintain precision across different applications without proportionally increasing complexity.
3Ease of operation
If manual research is performed to generate predictor lists, then ease of operation is improved, but productivity deteriorates
Solution Approach 1:
The system performs preliminary action by pre-processing and indexing large volumes of unstructured documents before they are needed for model development. The hidden Markov model can then quickly extract relevant predictor variables from this pre-processed data, dramatically increasing productivity while maintaining ease of operation through automated access to relevant variables.
Solution Approach 2:
The patent enables continuity of useful action by allowing the cognitive system to continuously process unstructured documents and generate predictor variables as needed, rather than requiring discrete manual research steps. The system maintains continuous operation in extracting insights from documents, accelerating model development productivity while keeping the interface simple for users.
Data Source
AI summary
An approach for determining a veracity of a reported event is provided. In an embodiment, a set of predictor variables is retrieved from a selected use case. Each of these predictor values is a condition that indicates the veracity of the reported event. In addition, a set of hidden predictor variables is generated from a set of unstructured documents related to the reported event using a hidden Markov model that is based on the predictor variables using a cognitive system. These hidden predictor variables are combined with the set of predictor variables to generate a set of updated predictor variables. These updated predictor variables are used by the cognitive system to return a determination of the veracity of the reported event.