World Patent Information最新文献

{"title":"Structured LLM-based patent comparison across three evaluation dimensions","authors":"Deokjin Choi ,&nbsp;Boeun Park","doi":"10.1016/j.wpi.2026.102430","DOIUrl":"10.1016/j.wpi.2026.102430","url":null,"abstract":"<div><div>Large language models (LLMs) show promise in document-level comparison but often lack transparency and consistency in judgment. These limitations hinder their use in high-stakes tasks such as patent evaluation, where reliable and explainable comparisons are essential. To address this gap, we propose a structured prompting framework that guides LLMs to compare patents across three evaluative dimensions: Functional Purpose (FP), Technical Uniqueness (TU), and Strategic Value (SV). Prompt refinement improves fairness, stability, and interpretability, but its effects vary across technical domains. Together, these findings position structured comparative judgment as a viable and auditable paradigm for deploying LLMs in high-stakes patent evaluation.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"84 ","pages":"Article 102430"},"PeriodicalIF":1.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of the open IP strategies on technology development: Evidence from the low emission vehicles field","authors":"Xiaoyu Zhang,&nbsp;Jing Shi,&nbsp;Lele Kang","doi":"10.1016/j.wpi.2025.102425","DOIUrl":"10.1016/j.wpi.2025.102425","url":null,"abstract":"<div><div>Can open IP strategies promote innovation among competitors, thereby advancing the development of the technology field? This empirical question has remained a central topic of debate in the open innovation literature. To address this question, this study examines how open IP strategies adopted by leading firms affect technological advancement. The patent pledges by Tesla and Toyota serve as exogenous shocks, enabling an empirical analysis of the impact of open IP strategies on technological development in the Low Emission Vehicles (LEVs) industry. We utilized Difference-in-Differences (DID) models analyzing patent data from 2010 to 2019 to measure the effects on technological performance across firms. Our results indicate that open IP strategies significantly enhance technological output, including quantity, quality, and novelty, especially benefiting start-ups, and to a lesser extent, firms with rich knowledge bases. This study contributes to understanding the role of open innovation in fostering technological competition.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"84 ","pages":"Article 102425"},"PeriodicalIF":1.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using trademark data in research","authors":"Tom Willeke ,&nbsp;Jörn Block ,&nbsp;Darius Lambrecht","doi":"10.1016/j.wpi.2026.102431","DOIUrl":"10.1016/j.wpi.2026.102431","url":null,"abstract":"<div><div>Although trademarks are the most widely used intellectual property right (IPR) they remain underrepresented in empirical research compared to other IPRs like patents. While patents capture mainly technological innovation, trademarks are broader and reflect firm strategy, brand positioning, and non-technological innovation. Despite their importance in practice, challenges in data accessibility and preprocessing have limited their application and investigation in (empirical) research. This review examines available trademark data sources, assesses their usability, and discusses key challenges in data integration. It further provides a structured overview of trademark-based measures for studying innovation, product strategy and economic development. We derive a research agenda of opportunities enabled by improved data accessibility and methodological advancements. Our study highlights the potential of trademarks as a data source, empirical measure, and research tool. We provide researchers with methodological guidance to facilitate the broader adoption of trademark data in business and economic studies.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"84 ","pages":"Article 102431"},"PeriodicalIF":1.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FOPNet:A comprehensive functional semantic knowledge graph for deep technical analysis in patents","authors":"Nan Wang ,&nbsp;Ziyi Wan ,&nbsp;Hongyu Zhao ,&nbsp;Chang Wang ,&nbsp;Yake Wang","doi":"10.1016/j.wpi.2026.102427","DOIUrl":"10.1016/j.wpi.2026.102427","url":null,"abstract":"<div><div>Patent text similarity is critical for semantic search, due diligence, infringement detection, and litigation. As global patent filings increase, conventional keyword-, citation-, and classification-based methods fail to capture the contextual and functional semantics of patent documents. Function–Object–Property (FOP) representations offer a promising alternative, but progress is limited by the scarcity of specialized Semantic Text Similarity (STS) datasets and by insufficient evaluations. We propose the FOPNet, a comprehensive framework that decomposes patent text into F–O–P triples, links them to a patent knowledge graph, and produces FOP embeddings augmented by clustering-based weighting and learned re-ranking. We constructed two STS benchmarks from USPTO examination decisions and PTAB appeals: a binary (2-point) similarity set and a ranked retrieval set — the first openly available benchmarks of this type. Experimental evaluations show that the proposed FOP-based framework improves retrieval accuracy by 43 % over keyword-based baselines and by 26 % over standard document embedding methods. Vector-based similarity algorithms incorporating K-means clustering weights achieved a 32 % improvement over unweighted baselines, while a knowledge-based similarity threshold of 0.4–0.6 maximized distinction between similar and dissimilar patents. Ablation analysis identified the optimal configuration as combining FOP embeddings derived from pre-trained patent vectors with clustering-based weighting, similarity thresholds, and semantic knowledge extensions. This configuration reduced the average ranking position of relevant patents from 5.7 to 2.7 and achieved top-3 retrieval in all test cases.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"84 ","pages":"Article 102427"},"PeriodicalIF":1.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Designing tailored patent search approaches – A case study on nursing care technology","authors":"Joe Waterstraat,&nbsp;Lothar Walter","doi":"10.1016/j.wpi.2025.102420","DOIUrl":"10.1016/j.wpi.2025.102420","url":null,"abstract":"<div><div>Patent searches support innovation, legal compliance, and business decisions, but are often complicated by extensive data, diverse systems and linguistic challenges. This paper presents a multi-perspective, keyword-based approach drawing on design theory to address the ‘fuzzy’ nature of complex technology fields. Using the example of Nursing Care Technology (NCT), an interdisciplinary domain lacking a specific patent classification, we develop three search strategies reflecting the perspectives of designers, users, and systems.</div><div>In order to measure the effectiveness of each search perspective in identifying relevant documents, we use a Large Language Model (LLM) to assess the precision of the respective results, including their subsets and intersections. Patents identified from all three design-theory perspectives have the highest precision, suggesting that the combination of viewpoints helps to isolate core innovations. Our analysis of patent classifications and assignees also demonstrates the value of the method for exploring ‘fuzzy’ technology fields.</div><div>By adapting design theory to keyword-based patent searches and using an LLM to assess the precision of tailored search results, we advance both the theory and practice of patent information retrieval. This is especially useful for ‘fuzzy’ technology fields where conventional search methods often fall short.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"84 ","pages":"Article 102420"},"PeriodicalIF":1.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145658455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evolutionary trajectories of biomass energy: Strategic patent analytics through machine learning approaches","authors":"Yigang Wei ,&nbsp;Entong Gao ,&nbsp;Xiaowei Fu ,&nbsp;Yingbo Li ,&nbsp;Zhiwen Wang ,&nbsp;Haoxiang Tang","doi":"10.1016/j.wpi.2026.102432","DOIUrl":"10.1016/j.wpi.2026.102432","url":null,"abstract":"<div><div>Against net-zero targets, policymakers view biomass as indispensable, but systematic foresight on its technology pathways and innovation niches is still scarce. Employing machine learning techniques, this study analyzes 26,865 patents (1970–2022) using topic modeling, document embeddings (Doc2Vec), social-network analysis, and deep neural network to identify technological themes, emerging innovations, and strategic patenting directions. Our analysis identifies 17 core technological themes, pinpointing five significant emerging areas: solid fuel production technologies, biomass drying technologies, biomass fermentation technologies, reactor design, and waste treatment technologies. The study introduces an innovative integrated analytical framework combining patent data analytics and policy semantics, alongside a dynamic four-stage technological lifecycle model, significantly enhancing the accuracy of technological forecasting. These concrete findings offer strategic guidance for policymakers and industry stakeholders, fostering targeted innovations and sustainable biomass energy development.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"84 ","pages":"Article 102432"},"PeriodicalIF":1.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Syntactic anchoring for artificial intelligence patent insight: A lightweight framework for keyword extraction","authors":"Elisa J. Choi,&nbsp;Gyoo Gun Lim","doi":"10.1016/j.wpi.2026.102429","DOIUrl":"10.1016/j.wpi.2026.102429","url":null,"abstract":"<div><div>Compact yet powerful, patent titles embed signals that uncover emerging technological trends. This study introduces a lightweight, syntax-aware method for keyword extraction that identifies functionally meaningful trigrams by leveraging high-frequency prepositions (such as <em>for</em>, <em>on</em>, and <em>using</em>) as structural anchors. Unlike conventional approaches that disregard such function words, the proposed method treats them as semantic pivots, or anchor points in the sentence structure, to capture context-specific expressions, especially in short texts such as patent titles. Applied to 21,100 AI patent titles (2014–2024), the method outperformed six baselines in terms of semantic cohesion (PMI = 11.47), and runtime efficiency, while also demonstrating external validity through alignment with official CPC classification trends (<em>r</em> = 0.73). These results demonstrate the effectiveness of syntactic cues for metadata-level text analysis and highlight the method's practical utility for innovation tracking, patent analytics, and early-stage technology scouting. The study also contributes to the broader discourse on function-oriented innovation by offering a scalable tool for identifying evolving functional expressions in patent corpora.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"84 ","pages":"Article 102429"},"PeriodicalIF":1.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146022549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A large language model-based method for trademark similarity analysis in the Brazilian context","authors":"Igor Bezerra Reis ,&nbsp;Rafael Angelo Santos Leite ,&nbsp;Edilson Araujo Pires ,&nbsp;Francisco José da Silva e Silva ,&nbsp;Luciano Reis Coutinho ,&nbsp;Ariel Soares Teles","doi":"10.1016/j.wpi.2026.102436","DOIUrl":"10.1016/j.wpi.2026.102436","url":null,"abstract":"<div><div>A trademark aims to uniquely and distinctively identify the products and services offered by a company. It is a key intangible asset, acting as a fundamental tool to prevent unfair competition and strengthen a company’s market positioning. However, the increasing number of trademark applications submitted to the Brazilian National Institute of Industrial Property (INPI) has introduced significant challenges, such as longer processing times, inconsistencies in decisions, and greater complexity in identifying conflicts. In this context, automated methods for trademark similarity analysis become essential to improve the efficiency, reliability, and speed of INPI decision-making processes. This study proposes a method based on Large Language Models (LLMs) to classify and explain the similarity between word marks, following INPI criteria: textual, phonetic, ideological, and market-related aspects. The proposed method is structured into two main components: (1) a classification model to identify conflicts between trademarks, and (2) an explanation model that provides detailed justifications for why two marks are considered similar or not. To develop this method, a dataset comprising real cases extracted from INPI official publications was used. Six open-source LLMs were evaluated on their ability to classify and explain trademark conflicts. The results demonstrated high performance for identifying similarity (accuracy <span><math><mo>≈</mo></math></span>99%, F1-score <span><math><mo>&gt;</mo></math></span>98%, AUC <span><math><mo>&gt;</mo></math></span>99%). The explanation reports were rated above 4.0 (on a 0–5 scale) by IP specialists. Therefore, our LLM-based proposed method demonstrates potential to modernize the trademark examination process. Ultimately, this study highlights the potential of LLMs to enhance trademark analysis, reduce subjectivity, increase transparency, and make trademark protection more accessible.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"84 ","pages":"Article 102436"},"PeriodicalIF":1.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Literature listing","authors":"Susan Bates","doi":"10.1016/j.wpi.2025.102397","DOIUrl":"10.1016/j.wpi.2025.102397","url":null,"abstract":"<div><div>Welcome to the latest quarterly Literature Listing intended as a current awareness service for readers indicating newly published books, journal, and conference articles on IP management; Information Retrieval Techniques; Patent Landscapes; Education &amp; Certification; and Legal &amp; Intellectual Property Office Matters. The current Literature Listing was compiled mid-August-2025. Key resources include Scopus, Digital Commons, publishers' RSS feeds, and serendipity! This article gives a selection of interesting references to whet your appetite - the full list of references can be found in the companion datafile.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"83 ","pages":"Article 102397"},"PeriodicalIF":1.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145106777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The role of patent intelligence in demonstrating New Active Substance status","authors":"Paula Juckes ,&nbsp;Catherine Pringalle","doi":"10.1016/j.wpi.2025.102408","DOIUrl":"10.1016/j.wpi.2025.102408","url":null,"abstract":"<div><div>All medicines must be approved by regulatory bodies in the countries where they are to be put on the market. In Europe, this approval is called “marketing authorisation” (MA). To obtain MA, pharmaceutical companies (along with other developers of medicines such as academic institutions, or individual researchers) must submit a comprehensive marketing authorisation application (MAA) and undergo a rigorous multi-step evaluation. For this paper, the word “company or companies” will be used to cover all “medicine developers” and this term also includes individuals and institutions. In Europe, the EMA issues recommendations to the European Commission regarding the potential grant of a MA, who then makes a legally binding decision. To secure these benefits, the company must request what is called “New Active Substance” or NAS designation or status, as part of its marketing authorisation application. NAS designation requires that the medicine meets certain criteria and if adopted, it prevents other parties from bringing a generic version of it to market for 10 years. Although the NAS status is a regulatory concept with defined criteria, demonstrating that an active substance has not been previously authorised in Europe often requires significant support from the Intellectual Property Department, as this is where most research on the product and its novelty has <em>already</em> been conducted for patentability purposes. Further, the criteria for granting NAS status have recently been made more stringent by the EMA. Obtaining market exclusivity for a product can help predict a company's value and growth thus it is important for companies to obtain this NAS status for their products. In this article we explore how different information resources and strategies were used by our company in two case examples to help verify NAS status in Europe. These case studies are based on a presentation given at the CEPIUG conference in 2023 and are not intended to be an in-depth guide.</div></div>","PeriodicalId":51794,"journal":{"name":"World Patent Information","volume":"83 ","pages":"Article 102408"},"PeriodicalIF":1.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145528010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}