Project Name:

Data Access Alternatives: Artificial Intelligence Supported Interfaces

Contractor: BrightQuery, Inc.

Lessons Learned

• Back-End Setup: The complex AI back-end setup required in-depth collaboration, but this has now been documented and streamlined for future installations.
• SDR Dataset Knowledge: The experience gained in analyzing and processing SDR data will improve efficiency in handling similar datasets moving forward.
• Agency Engagement: Early and sustained communication with external agencies is essential to avoid potential delays.

  • Statistical vs. Conversational Chatbot Approaches:
    • Statistical report-based approaches offer greater certainty and structure, while conversational chatbots provide a more interactive and engaging experience, allowing users the flexibility to explore specific areas of interest in greater detail. In the latest version, we have combined the strengths of both approaches, delivering a solution that integrates the reliability of statistical designs with the adaptability and engagement of conversational systems.
  • Questions and Answers:
    • Questions and answers play a pivotal role in shaping a comprehensive and well-rounded application. They contribute significantly to both the breadth and depth of topic coverage, ensuring that responses are insightful and contextual, meeting a wide range of user needs effectively. We are collecting Q&A’s from all sources including partners and stakeholders to improve the application.
  • Data Availability and Format
    • Consolidated historical data and revisions are critical for accessibility and usability.
  • AI and ML Challenges
    • Commercial AI tools struggle with statistical and time-series data, particularly revisions.
    • Time must be treated as multidimensional, capturing both the period and the timestamp.
  • Standards and Discoverability
    • Schema.org and Croissant standards enhance data discoverability but require additional depth for analytics.
  •  Knowledge Graph Development
    • Triplification is essential for building knowledge graphs but lacks standardization for entity definitions and time-series data representation.
  • Granularity and Interoperability
    • More granular data enhances interoperability but may be affected by changes in methodology or categorization.

Disclaimer: America’s DataHub Consortium (ADC), a public-private partnership, implements research opportunities that support the strategic objectives of the National Center for Science and Engineering Statistics (NCSES) within the U.S. National Science Foundation (NSF). These results document research funded through ADC and is being shared to inform interested parties of ongoing activities and to encourage further discussion. Any opinions, findings, conclusions, or recommendations expressed above do not necessarily reflect the views of NCSES or NSF. Please send questions to ncsesweb@nsf.gov.