MISCON: A Mission-Driven Conversational Consultant for Pre-Venture Entrepreneurs in Food Deserts

2025-01-24

AI Summary

Small-scale food entrepreneurs in food desert communities face critical challenges—including information scarcity, difficulty aligning with relevant policies, and lack of rigorous site selection and business model evaluation. Method: This paper proposes a mission-driven conversational advisory system featuring a novel state-machine dialogue architecture that integrates heterogeneous knowledge graphs with multi-LLM collaborative reasoning to enable multi-turn dynamic inference. It further incorporates a community-level spatial analytics toolkit for precise policy matching, data-driven site suitability assessment, and feasibility diagnosis of business models. Contribution/Results: The system’s functional architecture and core modules have been fully designed and empirically validated. In real-world community deployments, it significantly improves the accuracy of entrepreneurial consultation responses and the depth of decision support. This work establishes a scalable, interpretable, and operationally robust AI-augmented paradigm for sustainable community-based food entrepreneurship.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This work-in-progress report describes MISCON, a conversational consultant being developed for a public mission project called NOURISH. With MISCON, aspiring small business owners in a food-insecure region and their advisors in Community-based organizations would be able to get information, recommendation and analysis regarding setting up food businesses. MISCON conversations are modeled as state machine that uses a heterogeneous knowledge graph as well as several analytical tools and services including a variety of LLMs. In this short report, we present the functional architecture and some design considerations behind MISCON.

Problem

• Food Insecurity
• Small Restaurant Establishment
• Information Access

Innovation

• MISCON
• Gameified Dialogue Design
• Advanced Language Model