Automated Reasoning Engine Provenance Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated decision systems face challenges in explaining changes in query result values over time due to changes in explicit facts and rules, leading to user uncertainty and increased resource consumption in validating results.
Innovation Solution
The system provides a historical explanation of query result value changes by storing provenance information for each knowledge base entity, allowing it to recreate previous results and identify differences in proof trees, and presents explanations in natural language to facilitate user understanding.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If automated decision systems process large amounts of explicit facts from diverse sources, then the system can facilitate medical diagnosis, ensure compliance, and authorize transactions, but the complexity of analyzing result changes over time increases significantly
Solution Approach 1:
The system performs preliminary action by maintaining provenance information that documents the complete history of how each query result value was determined, including all facts, rules, and reasoning steps. This pre-documented provenance data is stored and made accessible for later analysis, eliminating the need to reprocess large amounts of data when users need to understand result changes over time.
2Loss of information
If the system provides detailed explanations of how query result values are derived, then user understanding improves, but the time required for users to validate results increases
Solution Approach 1:
The system extracts and presents only the relevant provenance information needed to explain changes in query result values, rather than displaying all raw facts and rules. By selectively extracting the specific facts, rules, and reasoning steps that caused the result change, the system provides sufficient explanation for user understanding while minimizing the time required to validate results.
3Reliability
If users manually analyze changes in query results over time, then they can validate accuracy, but significant computing resources are consumed
Solution Approach 1:
The system performs self-service by automatically generating and presenting provenance explanations that show how query result values were determined and how they changed over time. This automated explanation generation eliminates the need for users to manually analyze large amounts of data, thereby validating result accuracy while consuming minimal computing resources beyond the initial provenance data collection.
Data Source
AI summary
In general, the disclosure describes various aspects of techniques for explaining results provided by automated decision systems. A device comprising a memory and a computation engine executing one or more processor may be configured to perform the techniques. The memory may store an automated reasoning engine. The computation engine may execute the automated reasoning engine to obtain a query, obtain, from a knowledge base, and responsive to the query, a knowledge base entity representative of an explicit fact or a rule, and determine, based on the knowledge base entity, the query result that provides a decision to the query. The automated reasoning engine may also obtain provenance information that explains a history for the knowledge base entity, determine, based on the provenance information, an explanation that explains a difference between the query result and a previous query result provided with respect to the query, and output the explanation.