LLM-based Schema-Guided Extraction and Validation of Missing-Person Intelligence from Heterogeneous Data Sources

TL;DR

This paper presents the Guardian Parser Pack, an AI-driven system that transforms diverse investigative documents into a unified schema for improved missing-person case analysis, combining deterministic and LLM-assisted methods.

Contribution

It introduces a novel schema-guided extraction pipeline integrating multi-engine parsing, rule-based identification, and LLM-assisted extraction with validation, enhancing data quality in investigations.

Findings

LLM-assisted extraction significantly outperforms deterministic methods in quality (F1=0.8664 vs. 0.2578).

The system improves key-field completeness from 93.23% to 96.97%.

Deterministic parsing is much faster (0.03 s/record) than LLM-based methods (3.95 s/record).

Abstract

Missing-person and child-safety investigations rely on heterogeneous case documents, including structured forms, bulletin-style posters, and narrative web profiles. Variations in layout, terminology, and data quality impede rapid triage, large-scale analysis, and search-planning workflows. This paper introduces the Guardian Parser Pack, an AI-driven parsing and normalization pipeline that transforms multi-source investigative documents into a unified, schema-compliant representation suitable for operational review and downstream spatial modeling. The proposed system integrates (i) multi-engine PDF text extraction with Optical Character Recognition (OCR) fallback, (ii) rule-based source identification with source-specific parsers, (iii) schema-first harmonization and validation, and (iv) an optional Large Language Model (LLM)-assisted extraction pathway incorporating validator-guided repair and shared geocoding services. We present the system architecture, key implementation decisions, and output design, and evaluate performance using both gold-aligned extraction metrics and corpus-level operational indicators. On a manually aligned subset of 75 cases, the LLM-assisted pathway achieved substantially higher extraction quality than the deterministic comparator (F1 = 0.8664 vs. 0.2578), while across 517 parsed records per pathway it also improved aggregate key-field completeness (96.97\% vs. 93.23\%). The deterministic pathway remained much faster (mean runtime 0.03 s/record vs. 3.95 s/record for the LLM pathway). In the evaluated run, all LLM outputs passed initial schema validation, so validator-guided repair functioned as a built-in safeguard rather than a contributor to the observed gains. These results support controlled use of probabilistic AI within a schema-first, auditable pipeline for high-stakes investigative settings.