In the landscape of publicly available patent retrieval datasets, the need for explicit indomain and out-of-domain labeling, multi-jurisdiction coverage, balanced query domain representation and manageable sizes that support sub document level experiments on moderate computational resources is often overlooked. To address these gaps, we propose DAPFAM, a new open access domain-aware patent retrieval dataset constructed at the simple-family level. The dataset contains 1,247 domain balanced full text query families and 45,336 full text target families. The dataset is enriched by clear relevance judgments (forward/backward citations as positive links, random negatives), as well as explicit in-domain or out-of-domain relationships via a novel proposed labelling scheme based on via International Patent Classification (IPC) codes, resulting in 49,869 evaluation pairs. The dataset is multi jurisdictional, requires little to no preprocessing for retrieval evaluation, and remains of a size manageable for entities with limited ressources allowing for sub document level retrieval experiments without excessive computational costs. We describe our three-step data-curation pipeline, present comprehensive dataset statistics, and provide baseline experiments using lexical and neural retrieval methods. Our baseline experiments highlight significant challenges in crossdomain patent retrieval. The dataset will be publicly available (for now the access link is this repository: https://osf.io/vbyzd/?view_only=1a40242e0d1941a58aa854af3e50cf6b).
Aiming at the problems of cross-modal feature fusion, low efficiency of long text modeling and lack of hierarchical semantic coherence in patent text semantic mining, this study proposes HGM-Net, a deep learning framework that integrates Hierarchical Comparative Learning (HCL), Multi-modal Graph Attention Network (M-GAT) and Multi-Granularity Sparse Attention (MSA), which builds a dynamic mask, contrast and cross-structural similarity constraints on the word, sentence and paragraph hierarchies through HCL. Contrast and cross-structural similarity constraints are constructed at the word and paragraph levels by HCL to strengthen the local semantic and global thematic consistency of patent text; M-GAT models patent classification codes, citation relations and text semantics as heterogeneous graph structures, and achieves dynamic fusion of multi-source features by cross-modal gated attention; MSA adopts a hierarchical sparsity strategy to optimize the computational efficiency of long text modeling at word, phrase, sentence and paragraph granularity. Experiments show that the framework demonstrates significant advantages over existing deep learning methods in tasks such as patent classification and similarity matching, and provides a solution with both theoretical innovation and practical value for solving the problems of patent examination efficiency improvement and technology relevance mining.
Green patents are a key indicator to track technological efforts aimed at fighting climate change. Using an original dataset that merges different Patstat releases, we identify three mechanisms that may bias green patent statistics, potentially leading to contradictory findings. First, patent reclassifications due to updates in (green) classification codes result in an 9.2\% increase in the number of green patents when using the most recent classification structure. Second, delays in the adoption of the Cooperative Patent Classification (CPC) system introduce regional biases, as approximately 10\% of green patents from late-adopting countries remain undetected in less recent versions of the database. Third, we provide evidence that quality thresholds used to identify high-value inventions significantly shape observed trends in green patenting. Analyzing these mechanisms, our paper reveals that in many studies a substantial number of green patents is systematically overlooked, with the strongest effects observed for recent years and patents originating from Asian patent offices. These findings lead to relevant policy implications. Our results indicate not only that the global rate of green innovation has accelerated, but also that its epicenter has shifted, with an increasing share of green patents originating from emerging technological leaders, particularly in Asia.
Microsoft's acquisition of Activision Blizzard valued at $68.7 billion has drastically altered the landscape of the video game industry. At the time of the takeover, the intellectual properties of Activision Blizzard included World of Warcraft, Diablo, Hearthstone, StarCraft, Overwatch, Battle.net, Candy Crush Saga, and Call of Duty. This article aims to explore the patenting activity of Activision Blizzard between 2008 (the original merger) and 2023 (the Microsoft acquisition). Four IPC code co-occurrence networks (co-classification maps) are constructed and analyzed based on the patent data downloaded from the WIPO Patentscope database. International Patent Classification (IPC) codes are a language agnostic system for the classification of patents. When multiple IPC codes co-occur in a patent, it shows that the technologies are connected. These relationships can be used for patent mapping. The analysis identifies the prolific and bridging technologies of Activision Blizzard and explores its synergistic role as a subsidiary of Microsoft Corporation.
Recently, many studies have increasingly explored the use of large language models (LLMs) to generate research ideas and scientific hypotheses. However, real-world research and development often require solving complex, interdisciplinary challenges where solutions may not be readily found through existing knowledge related to the problem. Therefore, it is desirable to leverage the vast, comprehensive knowledge of LLMs to generate effective, breakthrough solutions by integrating various perspectives from other disciplines. Here, we propose SELLM (Solution Enumeration via comprehensive List and LLM), a framework leveraging LLMs and structured guidance using MECE (Mutually Exclusive, Collectively Exhaustive) principles, such as International Patent Classification (IPC) and the periodic table of elements. SELLM systematically constructs comprehensive expert agents from the list to generate cross-disciplinary and effective solutions. To evaluate SELLM's practicality, we applied it to two challenges: improving light extraction in organic light-emitting diode (OLED) lighting and developing electrodes for next-generation memory materials. The results demonstrate that SELLM significantly facilitates the generation of effective solutions compared to cases without specific customization or effort, showcasing the potential of SELLM to enable LLMs to generate effective solutions even for challenging problems.
Patents are the currency of innovation, and like any currency, they need to be managed and protected (Gavin Potenza). Patents, as legal documents that secure intellectual property rights, play a critical role in technological innovation. The growing complexity of patent documents and the surge in patent applications have created a need for automated solutions in patent analysis. In this work, we present PatExpert, an autonomous multi-agent conversational framework designed to streamline and optimize patent-related tasks. The framework consists of a metaagent that coordinates task-specific expert agents for various patent-related tasks and a critique agent for error handling and feedback provision. The meta-agent orchestrates specialized expert agents, each fine-tuned for specific tasks such as patent classification, acceptance, claim generation, abstractive summarization, multi-patent analysis, and scientific hypothesis generation. For multi-patent analysis, the framework incorporates advanced methods like Graph Retrieval-Augmented Generation (GRAG) to enhance response accuracy and relevance by combining semantic similarity with knowledge graphs. Error handling is managed by critique agents (Gold-LLM-as-a-Judge and Reward-LLM-as-a-Judge), which evaluate output responses for accuracy and provide iterative feedback. The framework also prioritizes explainability, ensuring transparent justifications for decisions made during patent analysis. Its comprehensive capabilities make it a valuable tool for automating complex patent workflows, enhancing efficiency, accuracy, and compliance in patent-related tasks. Empirical evidence demonstrates significant improvements in patent processing tasks, concluding that the framework offers a robust solution for automating and optimizing patent analysis.
Patents and scientific papers provide an essential source for measuring science and technology output, to be used as a basis for the most varied scientometric analyzes. Authors' and inventors' names are the key identifiers to carry out these analyses, which however, run up against the issue of disambiguation. By extension identifying inventors who are also academic authors is a non-trivial challenge. We propose a method using the International Patent Classification (IPC) and the IPCCAT API to assess the degree of similarity of patents and papers abstracts of a given inventor, in order to match both types of documents. The method is developed and manually qualified based on three corpora of patents extracted from the international EPO database Espacenet. Among a set of 4679 patents and 7720 inventors, we obtain 2501 authors. The proposed algorithm solves the general problem of disambiguation with an error rate lower than 5%.
In the realm of patent document analysis, assessing semantic similarity between phrases presents a significant challenge, notably amplifying the inherent complexities of Cooperative Patent Classification (CPC) research. Firstly, this study addresses these challenges, recognizing early CPC work while acknowledging past struggles with language barriers and document intricacy. Secondly, it underscores the persisting difficulties of CPC research. To overcome these challenges and bolster the CPC system, This paper presents two key innovations. Firstly, it introduces an ensemble approach that incorporates four BERT-related models, enhancing semantic similarity accuracy through weighted averaging. Secondly, a novel text preprocessing method tailored for patent documents is introduced, featuring a distinctive input structure with token scoring that aids in capturing semantic relationships during CPC context training, utilizing BCELoss. Our experimental findings conclusively establish the effectiveness of both our Ensemble Model and novel text processing strategies when deployed on the U.S. Patent Phrase to Phrase Matching dataset.
Recent technological advancements have led to a large number of patents in a diverse range of domains, making it challenging for human experts to analyze and manage. State-of-the-art methods for multi-label patent classification rely on deep neural networks (DNNs), which are complex and often considered black-boxes due to their opaque decision-making processes. In this paper, we propose a novel deep explainable patent classification framework by introducing layer-wise relevance propagation (LRP) to provide human-understandable explanations for predictions. We train several DNN models, including Bi-LSTM, CNN, and CNN-BiLSTM, and propagate the predictions backward from the output layer up to the input layer of the model to identify the relevance of words for individual predictions. Considering the relevance score, we then generate explanations by visualizing relevant words for the predicted patent class. Experimental results on two datasets comprising two-million patent texts demonstrate high performance in terms of various evaluation measures. The explanations generated for each prediction highlight important relevant words that align with the predicted class, making the prediction more understandable. Explainable systems have the potential to facilitate the adoption of complex AI-enabled methods for patent classification in real-world applications.
Accurate prediction of what types of patents that companies will apply for in the next period of time can figure out their development strategies and help them discover potential partners or competitors in advance. Although important, this problem has been rarely studied in previous research due to the challenges in modelling companies' continuously evolving preferences and capturing the semantic correlations of classification codes. To fill in this gap, we propose an event-based dynamic graph learning framework for patent application trend prediction. In particular, our method is founded on the memorable representations of both companies and patent classification codes. When a new patent is observed, the representations of the related companies and classification codes are updated according to the historical memories and the currently encoded messages. Moreover, a hierarchical message passing mechanism is provided to capture the semantic proximities of patent classification codes by updating their representations along the hierarchical taxonomy. Finally, the patent application trend is predicted by aggregating the representations of the target company and classification codes from static, dynamic, and hierarchical perspectives. Experiments on real-world data demonstrate the effectiveness of our approach under various experimental conditions, and also reveal the abilities of our method in learning semantics of classification codes and tracking technology developing trajectories of companies.
Patent classification aims to assign multiple International Patent Classification (IPC) codes to a given patent. Recent methods for automatically classifying patents mainly focus on analyzing the text descriptions of patents. However, apart from the texts, each patent is also associated with some assignees, and the knowledge of their applied patents is often valuable for classification. Furthermore, the hierarchical taxonomy formulated by the IPC system provides important contextual information and enables models to leverage the correlations between IPC codes for more accurate classification. However, existing methods fail to incorporate the above aspects. In this paper, we propose an integrated framework that comprehensively considers the information on patents for patent classification. To be specific, we first present an IPC codes correlations learning module to derive their semantic representations via adaptively passing and aggregating messages within the same level and across different levels along the hierarchical taxonomy. Moreover, we design a historical application patterns learning component to incorporate the corresponding assignee's previous patents by a dual channel aggregation mechanism. Finally, we combine the contextual information of patent texts that contains the semantics of IPC codes, and assignees' sequential preferences to make predictions. Experiments on real-world datasets demonstrate the superiority of our approach over the existing methods. Besides, we present the model's ability to capture the temporal patterns of assignees and the semantic dependencies among IPC codes.
Patent similarity analysis plays a crucial role in evaluating the risk of patent infringement. Nonetheless, this analysis is predominantly conducted manually by legal experts, often resulting in a time-consuming process. Recent advances in natural language processing technology offer a promising avenue for automating this process. However, methods for measuring similarity between patents still rely on experts manually classifying patents. Due to the recent development of artificial intelligence technology, a lot of research is being conducted focusing on the semantic similarity of patents using natural language processing technology. However, it is difficult to accurately analyze patent data, which are legal documents representing complex technologies, using existing natural language processing technologies. To address these limitations, we propose a hybrid methodology that takes into account bibliographic similarity, measures the similarity between patents by considering the semantic similarity of patents, the technical similarity between patents, and the bibliographic information of patents. Using natural language processing techniques, we measure semantic similarity based on patent text and calculate technical similarity through the degree of coexistence of International patent classification (IPC) codes. The similarity of bibliographic information of a patent is calculated using the special characteristics of the patent: citation information, inventor information, and assignee information. We propose a model that assigns reasonable weights to each similarity method considered. With the help of experts, we performed manual similarity evaluations on 420 pairs and evaluated the performance of our model based on this data. We have empirically shown that our method outperforms recent natural language processing techniques.
Patent classification is an essential task in patent information management and patent knowledge mining. It is very important to classify patents related to artificial intelligence, which is the biggest topic these days. However, artificial intelligence-related patents are very difficult to classify because it is a mixture of complex technologies and legal terms. Moreover, due to the unsatisfactory performance of current algorithms, it is still mostly done manually, wasting a lot of time and money. Therefore, we present a method for classifying artificial intelligence-related patents published by the USPTO using natural language processing technique and deep learning methodology. We use deformed BERT and sentence attention overcome the limitations of BERT. Our experiment result is highest performance compared to other deep learning methods.
Patent classification is the task that assigns each input patent into several codes (classes). Due to its high demand, several datasets and methods have been introduced. However, the lack of both systematic performance comparison of baselines and access to some datasets creates a gap for the task. To fill the gap, we introduce two new datasets in English and Japanese collected by using CPC codes. The English dataset includes 45,131 patent documents with 425 labels and the Japanese dataset contains 54,657 documents with 523 labels. To facilitate the next studies, we compare the performance of strong multi-label text classification methods on the two datasets. Experimental results show that AttentionXML is consistently better than other strong baselines. The ablation study is also conducted in two aspects: the contribution of different parts (title, abstract, description, and claims) of a patent and the behavior of baselines in terms of performance with different training data segmentation. We release the two new datasets with the code of the baselines.
This paper presents an automatic approach to creating taxonomies of technical terms based on the Cooperative Patent Classification (CPC). The resulting taxonomy contains about 170k nodes in 9 separate technological branches and is freely available. We also show that a Text-to-Text Transfer Transformer (T5) model can be fine-tuned to generate hypernyms and hyponyms with relatively high precision, confirming the manually assessed quality of the resource. The T5 model opens the taxonomy to any new technological terms for which a hypernym can be generated, thus making the resource updateable with new terms, an essential feature for the constantly evolving field of technological terminology.
Data-driven conceptual design methods and tools aim to inspire human ideation for new design concepts by providing external inspirational stimuli. In prior studies, the stimuli have been limited in terms of coverage, granularity, and retrieval guidance. Here, we present a knowledge based expert system that provides design stimuli across the semantic, document and field levels simultaneously from all fields of engineering and technology and that follows creativity theories to guide the retrieval and use of stimuli according to the knowledge distance. The system is centered on the use of a network of all technology fields in the patent classification system, to store and organize the world's cumulative data on the technological knowledge, concepts, and solutions in the total patent database according to statistically estimated knowledge distance between technology fields. In turn, knowledge distance guides the network-based exploration and retrieval of inspirational stimuli for inferences across near and far fields to generate new design ideas by analogy and combination. With two case studies, we showcase the effectiveness of using the system to explore and retrieve multilevel inspirational stimuli and generate new design ideas for both problem solving and open ended innovation. These case studies also demonstrate the computer aided ideation process, which is data-driven, computationally augmented, theoretically grounded, visually inspiring, and rapid.
There are many general purpose benchmark datasets for Semantic Textual Similarity but none of them are focused on technical concepts found in patents and scientific publications. This work aims to fill this gap by presenting a new human rated contextual phrase to phrase matching dataset. The entire dataset contains close to $50,000$ rated phrase pairs, each with a CPC (Cooperative Patent Classification) class as a context. This paper describes the dataset and some baseline models.
Patent data is an important source of knowledge for innovation research, while the technological similarity between pairs of patents is a key enabling indicator for patent analysis. Recently researchers have been using patent vector space models based on different NLP embeddings models to calculate the technological similarity between pairs of patents to help better understand innovations, patent landscaping, technology mapping, and patent quality evaluation. More often than not, Text Embedding is a vital precursor to patent analysis tasks. A pertinent question then arises: How should we measure and evaluate the accuracy of these embeddings? To the best of our knowledge, there is no comprehensive survey that builds a clear delineation of embedding models' performance for calculating patent similarity indicators. Therefore, in this study, we provide an overview of the accuracy of these algorithms based on patent classification performance and propose a standard library and dataset for assessing the accuracy of embeddings models based on PatentSBERTa approach. In a detailed discussion, we report the performance of the top 3 algorithms at section, class, and subclass levels. The results based on the first claim of patents show that PatentSBERTa, Bert-for-patents, and TF-IDF Weighted Word Embeddings have the best accuracy for computing sentence embeddings at the subclass level. According to the first results, the performance of the models in different classes varies, which shows researchers in patent analysis can utilize the results of this study to choose the best proper model based on the specific section of patent data they used.
Many thousands of patent applications arrive at patent offices around the world every day. One important subtask when a patent application is submitted is to assign one or more classification codes from the complex and hierarchical patent classification schemes that will enable routing of the patent application to a patent examiner who is knowledgeable about the specific technical field. This task is typically undertaken by patent professionals, however due to the large number of applications and the potential complexity of an invention, they are usually overwhelmed. Therefore, there is a need for this code assignment manual task to be supported or even fully automated by classification systems that will classify patent applications, hopefully with an accuracy close to patent professionals. Like in many other text analysis problems, in the last years, this intellectually demanding task has been studied using word embeddings and deep learning techniques. In this paper we shortly review these research efforts and experiment with similar deep learning techniques using different feature representations on automatic patent classification in the level of sub-classes. On top of that, we present an innovative method of ensemble classifiers trained with different parts of the patent document. To the best of our knowledge, this is the first time that an ensemble method was proposed for the patent classification problem. Our first results are quite promising showing that an ensemble architecture of classifiers significantly outperforms current state-of-the-art techniques using the same classifiers as standalone solutions.
With the growing impact of ESG on businesses, research related to renewable energy is receiving great attention. Solar cells are one of them, and accordingly, it can be said that the research value of solar cell patent analysis is very high. Patent documents have high research value. Being able to accurately analyze and classify patent documents can reveal several important technical relationships. It can also describe the business trends in that technology. And when it comes to investment, new industrial solutions will also be inspired and proposed to make important decisions. Therefore, we must carefully analyze patent documents and utilize the value of patents. To solve the solar cell patent classification problem, we propose a keyword extraction method and a deep neural network-based solar cell patent classification method. First, solar cell patents are analyzed for pretreatment. It then uses the KeyBERT algorithm to extract keywords and key phrases from the patent abstract to construct a lexical dictionary. We then build a solar cell patent classification model according to the deep neural network. Finally, we use a deep neural network-based solar cell patent classification model to classify power patents, and the training accuracy is greater than 95%. Also, the validation accuracy is about 87.5%. It can be seen that the deep neural network method can not only realize the classification of complex and difficult solar cell patents, but also have a good classification effect.