Engineering systems are increasingly characterized by large, heterogeneous collections of technical documentation, including specifications, interface descriptions, and contribution records. While artificial intelligence techniques have been applied to document analysis, many existing approaches rely on opaque models that limit transparency and human trust. This paper presents a structured AI-based approach for deriving systemlevel understanding from engineering documentation by combining semantic abstraction, modular reasoning, confidence-aware outputs, and analyst validation. The approach emphasizes transparency and evidence-linked reasoning, enabling users to inspect intermediate representations and validate inferred relationships. A case study using a large-scale wireless systems documentation corpus and a focused Wi-Fi Aware worked example demonstrates how source-anchored reasoning can scale across extensive document sets while preserving human oversight.
Amrutha Moorthy· International Symposium on C...· 0 citations
Patent valuation frameworks typically rely on affirmative indicators such as standard declarations, clause-level mapping, citation activity, product implementation, and licensing history. Yet in litigation, licensing negotiations, and essentiality assessments, valuation outcomes are often shaped by what the record lacks. Missing standard mapping, absent teardown evidence, deployment opacity, or the absence of licensing comparables can materially narrow valuation confidence. This paper formalizes evidentiary absence as a first-class input to patent valuation. Using IN218255, IN240893, Wi-Fi/mmWave SEP examples, and judicial reasoning including Optis $v$ Apple, we develop an absence-aware framework across technical, deployment, and economic evidence layers. The framework introduces ordinal evidence states, absent, semantic proximity, structured evidence, and corroborated evidence, to guide valuation responses ranging from full valuation to constrained range, high uncertainty, or abstention. The approach improves transparency, reproducibility, and auditability in patent value assessment.
Amrutha Moorthy, Raghuram M S· 2026 ITU Kaleidoscope - AI a...· 0 citations
