Terrorizer: a novel algorithm for patent assignee name disambiguation

Grazia Sveva Ascione, Valerio Sterzi and Andrea Vezzulli
Additional contact information
Grazia Sveva Ascione: BSE - Bordeaux sciences économiques - UB - Université de Bordeaux - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement
Valerio Sterzi: BSE - Bordeaux sciences économiques - UB - Université de Bordeaux - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement
Andrea Vezzulli: Uninsubria - Universitá degli Studi dell’Insubria = University of Insubria [Varese]

Post-Print from HAL

Abstract: The problem of disambiguation of company names poses a significant challenge in extracting useful information from patents. This issue biases research outcomes as it mostly underestimates the number of patents attributed to companies, particularly multinational corporations which file patents under a plethora of names, including alternate spellings of the same entity and, eventually, companies' subsidiaries. To date, addressing these challenges has relied on labor-intensive dictionary based or string matching approaches, leaving the problem of patents' assignee harmonization on large datasets mostly unresolved. To bridge this gap, this paper describes the Terrorizer algorithm, a text-based algorithm that leverages natural language processing (NLP), network theory, and rule-based techniques to harmonize the variants of company names recorded as patent assignees. In particular, the algorithm follows the tripartite structure of its antecedents, namely parsing, matching and filtering stage, adding an original "knowledge augmentation" phase which is used to enrich the information available on each assignee name. We use Terrorizer on a set of 325'917 company names who are assignees of patents granted by the USPTO from 2005 to 2022. The performance of Terrorizer is evaluated on four gold standard datasets. This validation step shows two main advantages of Terrorizer: the first is that its performance is similar over different kinds of datasets, proving that our algorithm generalizes well. Second, it performs better than other existing algorithms currently used in patent data analysis. We use the Tree-structured Parzen Estimator (TPE) optimization algorithm for the hyperparameters' tuning. Our final result is a reduction in the initial set of names of over 42%. Finally, we show an application of our algorithm by analyzing patent transactions registered at the USPTO and identifying the most important intermediaries in the transaction network of ICT patents.

Keywords: Entity linking; Patent assignee; Natural language processing; Network theory (search for similar items in EconPapers)
Date: 2026-01-18
References: Add references at CitEc
Citations:

Published in Scientometrics, 2026, 130 (12), pp.7303-7342. ⟨10.1007/s11192-025-05510-z⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-05472787

DOI: 10.1007/s11192-025-05510-z

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().