Urgency Driven Dynamic Explainability for AI Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern complex artificial intelligence systems, such as deep learning and genetic algorithms, are opaque and lack explainability, making it difficult to provide relevant and efficient explanations for decisions, especially in urgent situations where concise information is needed.
Innovation Solution
A computer-implemented method using explainable artificial intelligence that determines the urgency level of a query and adjusts the amount of explanation provided, delivering detailed explanations only when necessary, thereby reducing unnecessary explanation details and conserving computer resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If detailed explanations are provided for all AI decisions, then explainability is improved, but information overload and resource consumption increase
Solution Approach 1:
The patent applies local quality by providing different amounts of explanation details based on the specific urgency level of each query. High-urgency queries receive concise explanations while low-urgency queries receive detailed explanations, making the explanation quality adaptive to local needs rather than uniformly applied
2Loss of information
If comprehensive explanations are provided for all queries, then user understanding is improved, but response time increases
Solution Approach 1:
The patent implements dynamics by making the explanation length and detail level variable based on the urgency level of the query. The system dynamically adjusts the amount of information provided in real-time, matching the user's need for information against the time sensitivity of the situation
3Loss of information
If full explanations are provided for all decisions, then transparency is improved, but resource consumption increases
Solution Approach 1:
The patent applies parameter changes by modifying the explanation parameters (length, detail level, complexity) based on the urgency level parameter. This allows the system to maintain transparency when needed while conserving resources when urgency is high, effectively changing the explanation parameters to match situational requirements
Data Source
AI summary
A computer-implemented method includes: receiving, by a computing device, a query from a user device; generating, by the computing device and using a machine learning model, an answer to the query; determining, by the computing device, an urgency level of the query; generating, by the computing device, an explanation of the answer based on the determined urgency level; and presenting, by the computing device, the answer and the explanation to a user via the user device.