Imputation Model for Computer-Based Reasoning Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computer-based reasoning systems face challenges with incomplete training data, particularly when older systems lack sensors and data collection mechanisms used in newer systems, leading to sparse data that cannot be effectively utilized for model training.
Innovation Solution
The techniques involve analyzing cases in the reasoning model to determine missing fields, calculating conviction scores, and using an imputation model to fill in missing data, updating the model iteratively until it is complete, and then using this updated model to control systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If data collection mechanisms are added to older systems, then data completeness is improved, but system complexity and cost increase
Solution Approach 1:
The patent applies preliminary action by performing data imputation before training the reasoning model. Missing data in historical cases is filled using imputation models that leverage correlations with other cases, allowing older systems without modern sensors to contribute their data to training sets without requiring physical retrofits.
Solution Approach 2:
The patent introduces an intermediary imputation model that acts as a mediator between incomplete historical data and the training requirements of modern reasoning models. This imputation model fills gaps by inferring missing values from correlated features in available data, enabling data from systems with different sensor configurations to be integrated.
2Loss of time
If data from older systems is used as-is, then processing time is reduced, but model accuracy deteriorates due to sparse data
Solution Approach 1:
The patent applies partial action by selectively imputing only the missing data fields required for training, rather than collecting or processing all possible data. The imputation model focuses specifically on filling gaps in critical features needed for the reasoning model training, avoiding unnecessary processing overhead while improving data completeness.
3Loss of information
If iterative imputation and updating is performed, then data completeness is improved, but computational resources and time increase
Solution Approach 1:
The patent applies continuity of useful action through iterative imputation and model updating. The process continuously refines the imputation model by incorporating newly imputed data, then uses the improved model to impute additional missing values, repeating this cycle until convergence or a stopping criterion is met. This iterative approach progressively improves data completeness while allowing early termination when sufficient improvement is achieved.
Data Source
AI summary
Techniques are provided for imputation in computer-based reasoning systems. The techniques include performing the following until there are no more cases in a computer-based reasoning model with missing fields for which imputation is desired: determining which cases have fields to impute (e.g., missing fields) in the computer-based reasoning model and determining conviction scores and / or imputation order information for the cases that have fields to impute. The techniques proceed by determining for which cases to impute data and, for each of the determined one or more cases with missing fields to impute data is imputed for the missing field, and the case is modified with the imputed data. Control of a system is then caused using the updated computer-based reasoning model.