Combining natural language processing techniques and algorithms LSA, word2vec and WMD for technological forecasting and similarity analysis in patent documents

Rezende, João Marcos de; Rodrigues, Izabella Martins da Costa; Resendo, Leandro Colombi; Komati, Karin Satie

doi:10.1080/09537325.2022.2110054

Cited by 8 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their approach utilized a combination of rule-based and ML techniques to identify entities such as products, processes, organizations, and locations. Rezende et al (2022) combined NLP techniques with algorithms such as latent semantic analysis (LSA), word2vec, and word mover's distance (WMD) to analyze patent similarity and technology trends [27].…”

Section: Nlp In Patent Analysismentioning

confidence: 99%

Alignment of Unsupervised Machine Learning with Human Understanding: A Case Study of Connected Vehicle Patents

Bridgelall

2024

Applied Sciences

View full text Add to dashboard Cite

As official public records of inventions, patents provide an understanding of technological trends across the competitive landscape of various industries. However, traditional manual analysis methods have become increasingly inadequate due to the rapid expansion of patent information and its unstructured nature. This paper contributes an original approach to enhance the understanding of patent data, with connected vehicle (CV) patents serving as the case study. Using free, open-source natural language processing (NLP) libraries, the author introduces a novel metric to quantify the alignment of classifications by a subject matter expert (SME) and using machine learning (ML) methods. The metric is a composite index that includes a purity factor, evaluating the average ML conformity across SME classifications, and a dispersion factor, assessing the distribution of ML assigned topics across these classifications. This dual-factor approach, labeled the H-index, quantifies the alignment of ML models with SME understanding in the range of zero to unity. The workflow utilizes an exhaustive combination of state-of-the-art tokenizers, normalizers, vectorizers, and topic modelers to identify the best NLP pipeline for ML model optimization. The study offers manifold visualizations to provide an intuitive understanding of the areas where ML models align or diverge from SME classifications. The H-indices reveal that although ML models demonstrate considerable promise in patent analysis, the need for further advancements remain, especially in the domain of patent analysis.

show abstract

Section: Nlp In Patent Analysismentioning

confidence: 99%

Alignment of Unsupervised Machine Learning with Human Understanding: A Case Study of Connected Vehicle Patents

Bridgelall

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Furthermore, to determine patent similarity, methods such as LSA, Word2vec, and WMD were compared with the Jaccard index. LSA and WMD showed comparable results, whereas Jaccard's indications differed from the aforementioned methods [14]. Gim et al, introduced a trend analysis method, leveraging ETI relations to discern patterns from patent datasets.…”

Section: Literature Reviewmentioning

confidence: 99%

The Climate of Innovation: AI’s Growing Influence in Weather Prediction Patents and Its Future Prospects

Cheon,

Mun

2023

Sustainability

View full text Add to dashboard Cite

As the severity of climate change intensifies, understanding and predicting weather patterns have become paramount. Major firms worldwide have recognized this urgency, focusing their innovative efforts on weather prediction. In line with this trend, this research delves into the intricate patterns of patent data within the realm of weather prediction from 2010 to 2023. The study unveils a standard timeline for patent grants in this domain, particularly noting a distinctive peak in grant durations between 1500 and 2000 days. The global landscape of weather prediction innovation is highlighted, pinpointing the United States, China, and Japan as pivotal contributors. A salient finding is the ascendant influence of artificial intelligence (AI) in this sector, underscored by the prevalence of AI-centric keywords such as “machine learning” and “neural network”. This trend exemplifies the ongoing paradigm shift toward data-driven methodologies in weather forecasting. A notable correlation was identified between patent trends and academic trends on platforms such as arXiv, especially concerning keywords such as “machine learning” and “deep learning”. Moreover, our findings indicate that the transformer network, given its rising prominence in deep learning realms, is predicted to be a future keyword trend in weather prediction patents. However, despite its insights, the study also grapples with limitations in its predictive modeling component, which aims at forecasting patent grant durations. Overall, this research offers a comprehensive understanding of the patent dynamics in weather prediction, illuminating the trajectory of technological advancements and the burgeoning role of AI. It holds implications for academia, industry, and policymaking in navigating the future of weather prediction technologies.

show abstract

Methodology and Empirical Strategy

Nuccio¹,

Mogno²

2023

Contributions to Management Science

View full text Add to dashboard Cite

Combining natural language processing techniques and algorithms LSA, word2vec and WMD for technological forecasting and similarity analysis in patent documents

Cited by 8 publications

References 24 publications

Alignment of Unsupervised Machine Learning with Human Understanding: A Case Study of Connected Vehicle Patents

Alignment of Unsupervised Machine Learning with Human Understanding: A Case Study of Connected Vehicle Patents

The Climate of Innovation: AI’s Growing Influence in Weather Prediction Patents and Its Future Prospects

Methodology and Empirical Strategy

Contact Info

Product

Resources

About