Patent Domain Research Articles

Patents in metaverse: an analysis of scope and challenges

ABSTRACT ‘Metaverse’ is set to be the disruptive technology which is about to bring an overhaul in the functioning of myriad sectors ranging from education, entertainment, health care, businesses amongst others. The key feature of this technology is the immersion of physical world into a virtual world. Metaverse in a way finds its roots on the technologies of Virtual/ Augmented Reality (VR/AR) which essentially are about simulating real world and augmenting the real – world experience in the digital world. Intellectual Property Rights which exist for protection of intangible assets, hence are vital in perspective of Metaverse. This research analyses the IP form of Patents in reference to Metaverse. Patents are an attractive choice due to the commercial advantage and the higher level of protection it offers compared to other IP forms. The trend of surge in patent applications seen with emerging technologies like AI and Blockchain is likely to be reflected with metaverse. The article views the metaverse and patent domain through an overarching lens gauging the possible scope and challenges. The analysis is based on US, EU and Indian patent laws to get a comprehensive picture across the world.

MOID: Many-to-One Patent Graph Embedding Base Infringement Detection Model

With the increasing number of patent applications over the years, instances of patent infringement cases have become more frequent. However, traditional manual patent infringement detection models are no longer suitable for large-scale infringement detection. Existing automated models mainly focus on detecting one-to-one patent infringements, but neglect the many-to-one scenarios. The many-to-one patent infringement detection model faces some major challenges. First, the diversity of patent domains, complexity of content and ambiguity of features make it difficult to extract and represent patent features. Second, patent infringement detection relies on the correlation between patents and the comparison of contextual information as the key factors, but modeling the process and drawing conclusions present challenges. To address these challenges, we propose a many-to-one patent graph (MPG) embedding base infringement detection model. Our model extracts the relationship between keywords and patents, as well as association relation between keywords from many-to-one patent texts (MPTs), to construct a MPG. We obtain patent infringement features through graph embedding of MPG. By using these embedding features as input, the many-to-one infringement detection (MOID) model outputs the conclusion on whether a patent is infringed or not. The comparative experimental results indicate that our model improves accuracy, precision and F-measure by 3.81%, 11.82% and 5.37%, respectively, when compared to the state-of-the-art method.

Rethinking the patent domains: An application to wind energy

Wind energy patents are conventionally defined using Cooperative Patent Classification (CPC) and International Patent Classification (IPC) codes that represent wind motors (F03D) and wind energy (Y02E 10/70). This study examines whether these codes sufficiently represent the wind energy patent domain. Using a combination of keywords and classification codes identified through expert input and manual review, we construct an expanded domain with a 7.5% increase in patent count, a 6% increase in recall, and only a 1% decrease in precision for wind energy patents. We also found that the conventional domain is not unbiased; it underrepresents patenting from China and patents published since 2010. This is important because an improved patent domain allows for a holistic patent data set, which is necessary to complete a thorough analysis of the wind industry. Through this wind energy application, we extend our methodology to form a generalized patent search process that can be used to target technology domains within a patent data set.

Quantifying 30 Years of Technological Innovation in Total Hip Arthroplasty

AbstractTechnological innovation in total hip arthroplasty (THA) is a critical component of health care delivery for improving patient outcomes. Analyzing the content of patents and trends in their activity over time can leverage insight into innovations in THA; however, these investigations remain underutilized. We aimed to quantify patent activity and relative growth pertaining to technologies in THA over a 30-year period. A query for patents relating to “hip replacement” or “hip arthroplasty” between 1989 and 2019 using an open-source patent database yielded 24,071 unique patents for analysis. These were grouped into 12 independent technology clusters using Cooperative Patent Classification codes. Annual patent activity for each cluster was normalized with a validated formula to control for exponential growth. The 5-, 10-, and 30-year compound annual growth rates (CAGR) for each cluster were quantified and compared between clusters. Annual cumulative patent activity increased from 151 patents in 1989 to 1,182 patents in 2019, representing a 682.8% increase. The largest technology clusters concerned “drugs” (n = 6,429 patents), “instruments” (n = 4,014 patents), “materials” (n = 2,037 patents), and “components” (n = 1,946 patents). One-half of the identified clusters concerned developments in technology-assisted THA (patient-specific instrumentation, navigation, robotics, design/manufacturing, instruments, and computer modeling). The most rapidly growing technology within the past 5, 10, and 30 years was robotics (CAGR = 15.82%, 20.11%, and 9.50%, respectively). Within the past 5- and 10-year trial prostheses (CAGR = 10.76%) and design/manufacturing processes (CAGR = 10.27%), computer modeling (CAGR = 12.91%) and navigation (CAGR = 11.25%) were among the most rapidly growing clusters, respectively. The majority of patents pertaining to THA over the past 30 years have concerned developments in drugs, instruments, materials, and components. Within the past 10-years, substantial growth has been observed in patent domains related to technology-assisted THA. Monitoring of emerging technologies through patent metrics may provide valuable information for regulatory bodies and assess progress in the field of THA. This is a cross-sectional study with level of evidence IV.

Evaluating generative patent language models

Generative language models are promising for assisting human writing in various domains. This manuscript aims to build generative language models in the patent domain and evaluate model performance from a human-centric perspective. The perspective is to measure the ratio of keystrokes that can be saved by autocompletion based on generative patent language models. A higher ratio means a more effective model which can save more keystrokes. This metric can be used to benchmark model performance. The metric is keystroke-based and different from conventional machine-centric metrics that are token-based. In terms of model size, the largest model built in this manuscript is PatentGPT-J-6B, which is state-of-the-art in the patent domain. Based on the metric, it is found that the largest model is not necessarily the best for the human-centric metric. The finding means that keeping increasing model sizes in the patent domain might be unnecessary if the purpose is to assist human writing with autocompletion. Several patent language models are pre-trained from scratch in this research. The pre-trained models are released for future researchers. Several visualization tools are also provided. The importance of building a generative language model in the patent domain is its potential to facilitate creativity and innovations in the future.

Embedding knowledge graph of patent metadata to measure knowledge proximity

AbstractKnowledge proximity refers to the strength of association between any two entities in a structural form that embodies certain aspects of a knowledge base. In this work, we operationalize knowledge proximity within the context of the US Patent Database (knowledge base) using a knowledge graph (structural form) named “PatNet” built using patent metadata, including citations, inventors, assignees, and domain classifications. We train various graph embedding models using PatNet to obtain the embeddings of entities and relations. The cosine similarity between the corresponding (or transformed) embeddings of entities denotes the knowledge proximity between these. We compare the embedding models in terms of their performances in predicting target entities and explaining domain expansion profiles of inventors and assignees. We then apply the embeddings of the best‐preferred model to associate homogeneous (e.g., patent–patent) and heterogeneous (e.g., inventor–assignee) pairs of entities.

기계번역의 특허 전문용어 한영번역에서 나타나는 오류 양상 분석 – 구글 번역 결과를 중심으로

Terminology translation plays a key role in technical machine translation. This paper conducts quantitative and qualitative evaluation and presents a comprehensive error analysis on terminology translation from Korean to English. For this study, 637 terms are selected from a patent domain corpus. Among them, 425 terms are translated correctly while other 212 terms have one or more errors. Those identified errors are classified into seven error categories which include addition, omission, lexical errors, order errors, morphological errors, partial errors, and miscellanies. Among them, partial errors and morphological errors are the two top error categories, and lexical errors and omission cases are also high. The study also presents n-gram wise error rates. The calculation of n-gram wise terminology translation error rates shows that the curve for the Google Translation results goes upwards with the increasing size of n. This shows that neural machine translation can be vulnerable in translating a higher-order of n-gram terms. This study has implications for Korean-English machine translation research, in that it classifies error cases spotted in machine translation of terminology which is critical in securing accuracy of translations.

Detecting Multi Word Terms in patents the same way as entities

In English patent document information retrieval, Multi Word Terms (MWTs) are an important factor in determining how relevant a patent document is for a particular search query. Detecting the correct boundaries for these MWTs is no trivial task and often complicated by the special writing style of the patent domain. In this paper we describe a method for detecting MWTs in patent sentences based on a method for detecting technical entities using deep learning. On our annotated dataset of 22 patents, our method achieved an average precision of 0.75, an average recall of 0.74 and an average F1 score of 0.74. Further, we argue for the use of domain specific word embedding resources and suggest that our model mostly learns whether individual words should be included in MWTs or not.

Deep learning based pipeline with multichannel inputs for patent classification

This work introduces a deep learning pipeline for automatic patent classification with multichannel inputs based on LSTM and word vector embeddings. Sophisticated text mining methods are used to extract the most important segments from patent texts, and a domain-specific pre-trained word embeddings model for the patent domain is developed; it was trained on a very large dataset of more than five million patents. The deep learning pipeline is using multiple parallel LSTM networks that read the source patent document using different input dimensions namely embeddings of different segments of patent texts, and sparse linear input of different metadata. Classifying patents into corresponding technical fields is selected as a use case. In this use case, a series of patent classification experiments are conducted on different patent datasets, and the experimental results indicate that using the segments of patent texts as well as the metadata as multichannel inputs for a deep neural network model, achieves better performance than one input channel.

A survey on deep learning for patent analysis

Patent document collections are an immense source of knowledge for research and innovation communities worldwide. The rapid growth of the number of patent documents poses an enormous challenge for retrieving and analyzing information from this source in an effective manner. Based on deep learning methods for natural language processing, novel approaches have been developed in the field of patent analysis. The goal of these approaches is to reduce costs by automating tasks that previously only domain experts could solve. In this article, we provide a comprehensive survey of the application of deep learning for patent analysis. We summarize the state-of-the-art techniques and describe how they are applied to various tasks in the patent domain. In a detailed discussion, we categorize 40 papers based on the dataset, the representation, and the deep learning architecture that were used, as well as the patent analysis task that was targeted. With our survey, we aim to foster future research at the intersection of patent analysis and deep learning and we conclude by listing promising paths for future work.

A knowledge graph approach for recommending patents to companies

Online platforms have emerged to facilitate patent transfer between academia and industry, but a recommendation method that matches patents with company needs is missing in the literature. Previous patent recommendation methods were designed mainly for query-driven patent search contexts, where user needs are given. However, company needs are implicit in the patent transfer context. The problem of profiling the needs and recommending patents accordingly remains unsolved. This research proposes a knowledge graph approach to address the problem. The proposed approach defines and constructs a patent knowledge graph to capture the semantic information between keywords in the patent domain. Then, it profiles patents and companies as weighted graphs based on the patent knowledge graph. Finally, it generates recommendations by comparing the weighted graphs based on the graph edit distance measure. During the recommendation process, three recommendation strategies (i.e., supplementary, complementary, and hybrid recommendation strategies) are proposed to profile different company needs and make recommendations accordingly. The proposed approach has been implemented and tested on a knowledge transfer platform in Jiangxi province, R.P. China. A pretest experiment shows that the proposed approach outperforms several baseline methods in terms of precision, recall, F-score, and mean average precision. User feedback from an online experiment further demonstrates the usability and the effectiveness of the proposed approach for recommending patents to companies.

Patents information for humanities research: Could there be something?

Latour and co-authors proposed, in the Science and Technology Translation theory, to target the many SHS (Social and Human Science) questions addressed by social studies of sciences by considering, in complement to traditional academic matters, the complete social environment (political, economic or societal). Patents obviously are a potential primary information source to do so. We propose to extend this considering that recent changes have evolved in our capacity to do so. We propose three preliminary steps: (a) patent documents as providing a structured information source, (b) a patent database as a technical encyclopedia and (c) the recent expansion of the variety of uses and users in patent domains. We underline, furthermore, that minority research in the academic space does effectively use patent information, especially in SHS compared to other disciplines. We deliver an experiment to estimate the amount of data unconsidered by not questioning the huge database of the European Patent Office. By comparatively considering the terminology of the two branches of the Unesco thesaurus, namely the micro thesauri “Social and Human Sciences" and the “Information and Communication Science” branches, we evaluate a database response to the whole vocabulary. An in-depth analysis of one selected concept will complete the study. Results show that patent information may provide a quantity of documents for a wide range of academic research questions, from strategic to state of the art, and position advances aside from the Social Studies of Science. The free open source tool is also a way to practice digital humanities expected skills on real world corpora.

A Feasible Dashboard to predict Patent Mining Using Classification Algorithms

The number of patents that are being filed across the world is increasing day by day. With the increase in patents being filed the process of segregating the patents based on their class becomes even more difficult. There are a set of features that are extracted from the dataset that is previously present. The features that are being extracted will vary for each document. Patents documents are issued as legal rights by the government for protecting the owner of invention. This exclusive right helps in protecting the invention to be used by others from using, selling, developing another, etc for some period of time. After the feature extraction is done there are two steps that need to be carried out, namely: Classification and prediction. For this purpose, decision tree algorithm is used which makes use of the most prominent feature and classification is done using those features. Therefore, for classification a hierarchical decision tree algorithm is used along with the probability of patent conversion. Based on the classification that is done a model will be created and whenever a new entity is brought it is compared with the model file that was created using the available datasets and is predicted as a particular class. Thus, both classification of existing dataset and the prediction for any new dataset based on previous inputs can be achieved thereby facilitating the patent mining process In proposed system this paper mainly concentrating on the prediction of the patent using data mining techniques. Decision tree algorithm for the classification of the patent mining is applied. And also classification of the data using some attributes is done, namely; association frequency, grant or applicant, patent country, patent status, grant patent using these attributes prediction of patent mining using Naive Bayes algorithm is done. The proposed algorithm gives best result for patent mining. The patent status is checked whether he got grant access of the patent in prediction which is the best patent mining in all over the country. The graph is plotted for to find the accuracy. Based on this if the new tuple is add to dataset it has to classify in which patent domain it belongs to.

Intelligent compilation of patent summaries using machine learning and natural language processing techniques

Patents are a type of intellectual property with ownership and monopolistic rights that are publicly accessible published documents, often with illustrations, registered by governments and international organizations. The registration allows people familiar with the domain to understand how to re-create the new and useful invention but restricts the manufacturing unless the owner licenses or enters into a legal agreement to sell ownership of the patent. Patents reward the costly research and development efforts of inventors while spreading new knowledge and accelerating innovation. This research uses artificial intelligence natural language processing, deep learning techniques and machine learning algorithms to extract the essential knowledge of patent documents within a given domain as a means to evaluate their worth and technical advantage. Manual patent abstraction is a time consuming, labor intensive, and subjective process which becomes cost and outcome ineffective as the size of the patent knowledge domain increases. This research develops an intelligent patent summarization methodology using artificial intelligence machine learning approaches to allow patent domains of extremely large sizes to be effectively and objectively summarized, especially for cases where the cost and time requirements of manual summarization is infeasible. The system learns to automatically summarize patent documents with natural language texts for any given technical domain. The machine learning solution identifies technical key terminologies (words, phrases, and sentences) in the context of the semantic relationships among training patents and corresponding summaries as the core of the summarization system. To ensure the high performance of the proposed methodology, ROUGE metrics are used to evaluate precision, recall, accuracy, and consistency of knowledge generated by the summarization system. The Smart machinery technologies domain, under the sub-domains of control intelligence, sensor intelligence and intelligent decision-making provide the case studies for the patent summarization system training. The cases use 1708 training pairs of patents and summaries while testing uses 30 randomly selected patents. The case implementation and verification have shown the summary reports achieve 90% and 84% average precision and recall ratios respectively.

Does Antitrust Regulation of Patent Monopoly Promote Innovation?

One of the prominent questions across the patent and antitrust policy domains is whether the antitrust intervention into a formation of patent monopoly promotes or discourages innovation. This stud...

Domain-specific word embeddings for patent classification

PurposePatent offices and other stakeholders in the patent domain need to classify patent applications according to a standardized classification scheme. The purpose of this paper is to examine the novelty of an application it can then be compared to previously granted patents in the same class. Automatic classification would be highly beneficial, because of the large volume of patents and the domain-specific knowledge needed to accomplish this costly manual task. However, a challenge for the automation is patent-specific language use, such as special vocabulary and phrases.Design/methodology/approachTo account for this language use, the authors present domain-specific pre-trained word embeddings for the patent domain. The authors train the model on a very large data set of more than 5m patents and evaluate it at the task of patent classification. To this end, the authors propose a deep learning approach based on gated recurrent units for automatic patent classification built on the trained word embeddings.FindingsExperiments on a standardized evaluation data set show that the approach increases average precision for patent classification by 17 percent compared to state-of-the-art approaches. In this paper, the authors further investigate the model’s strengths and weaknesses. An extensive error analysis reveals that the learned embeddings indeed mirror patent-specific language use. The imbalanced training data and underrepresented classes are the most difficult remaining challenge.Originality/valueThe proposed approach fulfills the need for domain-specific word embeddings for downstream tasks in the patent domain, such as patent classification or patent analysis.

Does Analogical Distance Affect Performance of Ideation?

Identifying relevant stimuli that help generate solutions of desired novelty and quality is challenging in analogical design. To quell this challenge, the multifaceted effects of using stimuli which are located at various analogical distances to the design problem on the novelty and quality of concepts generated using the stimuli are studied in this research. Data from a design project involving 105 student designers, individually generating 226 concepts of spherical rolling robots, are collected. From these data, 138 concepts generated with patents as stimuli and the patents used are analyzed. Analogical distance of a patent is measured in terms of knowledge similarity between technology classes constituting the patent and design problem domain of spherical rolling robots. The key observations are (a) technology classes in closer than farther distances from the design problem are used more frequently to generate concepts, (b) as analogical distance increases the novelty of concepts increases, and (c) as analogical distance decreases the quality of concepts increases.

Hierarchy-based projection of high-dimensional labeled data to reduce visual clutter

Visualizing high-dimensional labeled data on a two-dimensional plane can quickly result in visual clutter and information overload. To address this problem, the data usually needs to be structured, so that only parts of it are displayed at a time. We present a hierarchy-based approach that projects labeled data on different levels of detail on a two-dimensional plane, whilst keeping the user׳s cognitive load between the level changes as low as possible. The approach consists of three steps: First, the data is hierarchically clustered; second, the user can determine levels of detail; third, the levels of detail are visualized one at a time on a two-dimensional plane. Animations make transitions between the levels of detail traceable, while the exploration on each level is supported by several interaction techniques, including halos, a darts view, and a magic lens. We demonstrate the applicability and usefulness of the approach with use cases from the patent domain and a question-and-answer website. In addition, we conducted a qualitative evaluation to assess the usefulness and comprehensibility of our approach.

Development of Novel Patent Classification Framework by Exploiting Semantic Deep Learner

Knowledge documents are growing remarkably to serve the organization for information processing and various management tasks. Text mining is hard but important research topic in knowledge discovery where hidden information is extracted from unstructured and semi-structured data. Patents are rich knowledge source needed to be organized efficiently and conveniently. Patent documents are used for gathering business intelligence and identifying key trends in technology development. The main focus of this study is to propose a electrical patent classification framework based on Semantic Deep Learner (SDL). In this framework, initially key terms of the patent documents are extracted and represented using Vector Space Model (VSM), the importance of the key terms are weighted based up on their frequencies using TF-IDF. The semantic similarity between the key features is computed using cosine measure. Terms with higher correlations are synthesized into a smaller set of features. Finally the semantic deep learner is trained using the correlated features and accordingly patents are classified. The target output identifies the category of a patent document based on a hierarchical classification scheme of the International Patent Classification (IPC) standard. Our approach is new to the patent domain and shows some improvement in the classification accuracy when compared to the other state of art classifier.

Multilayer source selection as a tool for supporting patent search and classification

In this paper we present a method that can be used to attain specific objectives in a typical prior art search process. The objectives are first to assist patent searchers in understanding the underlying technical concepts of a patent by identifying relevant international patent classification (IPC) codes and second to help them conduct a filtered search based on automatically selected IPCs. We view the automated selection of IPCs as a collection selection problem from the domain of distributed information retrieval (DIR) that can be addressed using existing DIR methods, which we extend and adapt for the patent domain. Our work exploits the intellectually assigned classifications codes that are used to categorize patents and to facilitate patent searches. In our method, manually assigned IPC codes of patent documents are used to cluster, distribute and index patents through hundreds or thousands of sub-collections. We propose a new multilayer collection selection method that effectively suggests classification codes exploiting the hierarchical classification schemes such as IPC/CPC. The new method in addition to utilizing the topical relevance of IPCs at a particular level of interest exploits the topical relevance of their ancestors in the IPC hierarchy and aggregates those multiple estimations of relevance to a single estimation. Experimental results on the CLEF-IP 2011 dataset show that the proposed approach outperforms state-of-art methods from the DIR domain not only in identifying relevant IPC codes but also in retrieving relevant patent documents given a patent query.