cs.AINov 6, 2026

Large Language Model Consensus and Corpus-Adaptive Topic Modeling for Classifying and Mapping Patent Innovation

Authors: Sercan Ozcan, Enes Ozgozler, C. Okan Sakar

Organizations: School of Strategy, Marketing and Innovation, University of Portsmouth, UK · Innovative Management Center, Azerbaijan State University of Economics (UNEC), Azerbaijan · Faculty of Economics and Administrative Sciences, Piri Reis University, Turkey · Department of Computer Engineering, Bahcesehir University, Istanbul, Turkey

Abstract

Patent analytics increasingly relies on transformer representations and large language models (LLMs), yet linking conceptual classification, topic formation and interpretation requires explicit decisions about model roles and the evidence retained at each stage. In this design-oriented study, we propose and demonstrate a patent analytics pipeline that links these tasks and keeps each decision open to audit. Three LLMs separately classify each patent by novelty (radical or incremental) and innovation type (product, process, service). Radical and innovation-type labels each require two supporting votes, with Incremental used as the fallback novelty label. Topics are discovered by clustering PatentSBERTa embeddings, with parameter ranges scaled to corpus size. A patent-specific stopword list is applied only when topics are represented with class-based term frequency--inverse document frequency (c-TF-IDF), and a second embedding model supports inter-topic similarity, hierarchical refinement and visualization. An LLM then labels each topic from its ranked keywords and representative patents. We demonstrate the pipeline on 30,964 public-sector-related patents retrieved from Lens.org. Across five category corpora ranging from 591 to 29,215 patents, the pipeline produced 74 category-specific topic instances with a macro-average document coverage of 98.1% and topic diversity of 0.900--1.000, and fewer than 1% of classification outputs returned UNKNOWN. Because every model vote and the evidence behind each topic label are retained, analysts can audit and revise the outputs. The demonstration establishes the feasibility and traceability of the pipeline; testing its labels against expert coding and benchmarking it against alternative pipelines are identified as the next steps. The pipeline offers a reusable basis for LLM-assisted patent analysis in technology intelligence.

Explore similar work

CardsList
  1. PatentAgentBench: Benchmarking LLM Agents with Professional Patent Task Suites

    Oct 26, 2026Yijie Hu, Wei Li, Junjie Zhou +6LLM Agent EvaluationAI Agent Benchmarks

  2. Anticipating Innovation Using Large Language Models

    May 6, 2026Enrico Maria Fenoaltea, Filippo Santoro, Giordano De Marzo +2Language Modeling

  3. Is It Novel and Why? Fine-Grained Patent Novelty Prediction Based on Passage Retrieval

    May 4, 2026Valentin Knappich, Anna Hätty, Simon Razniewski +1Legal IR