Automated Knowledge Acquisition (AKA)

Abstract

The Automated Knowledge Acquisition (AKA) program will develop technologies to automate the integration of diverse sources of data and information into a unified whole. A number of technologies now exist to extract, transform, and load diverse source data into a structured knowledge base. However, each time a new source of data is encountered, a human engineer is required to map that source's metadata and schema to the metadata and schema of the target knowledge base. Performing this mapping is difficult even when design documentation for the source is available, and so it represents a significant barrier to data interoperability and knowledge acquisition. AKA will leverage advances in semantic technology and machine learning to enable machines to perform the entire data integration function without human intervention. AKA technology will automatically learn the semantics of a new data source, characterize source content, align source schema to the target, transform and load values, and reconcile inconsistencies by learning from previously integrated sources. AKA technologies will automatically create and maintain, in real-time, broad knowledge of local and regional military, political, economic, social, and cultural information for warfighters in theater.

Document Details

Document Type
Accomplishment
Publication Date
Oct 01, 2020
Source ID
b2931054a73151e2f889f42f6e3e2d31

Tags

Readers

  • Database Systems and Applications
  • Distributed Systems and Data Platform Development

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Information Retrieval

Related Documents