Knowledge Graph has become a dominant research field in graph theory, but its incompleteness and sparsity hinder its application in various fields. Knowledge Graph Reasoning aims to alleviate these problems by deducin...
详细信息
Knowledge Graph has become a dominant research field in graph theory, but its incompleteness and sparsity hinder its application in various fields. Knowledge Graph Reasoning aims to alleviate these problems by deducing new knowledge or identifying false knowledge from existing knowledge. Recently, the Graph Convolution Network (GCN) based method is one of the most advanced methods to realize knowledge graph reasoning. However, it still suffers from some problems such as incomplete neighbor information aggregation and slow training speed. This paper proposes a knowledge graph reasoning model named GK for the link prediction task, which obtains better performance than existing GCN-based methods by introducing Graphormer into knowledge reasoning. The GK first proposes that nodes and their surroundings can be regarded as a hierarchical architecture that enables the model to capture more practical reasoning information to improve prediction accuracy. In addition, to accelerate the training speed of the model on the large-scale Knowledge Graph, we present a faster shortest path-finding method F-SPF in the edge coding process. Extensive experimental results show that the GK model can obtain the state-of-the-art prediction results of current GCN-based methods and can improve the training speed.
Users worldwide widely use cloud storage because of its efficiency, convenience, and high availability. Multi-cloud storage is usually selected to ensure the high availability of data. Unfortunately, when data is migr...
详细信息
Users worldwide widely use cloud storage because of its efficiency, convenience, and high availability. Multi-cloud storage is usually selected to ensure the high availability of data. Unfortunately, when data is migrated and replicated between multi-cloud data centers, it is not easy to guarantee data con-sistency. This paper proposes an efficient, secure, and new data consistency verification scheme using blockchain technology. In order to reduce the computation and communication overhead in the verification process, our scheme uses encrypted tags to build Merkle hash tree to generate unique and lightweight verification proofs and does not use third-party auditors. The final theoretical and experimental analysis shows that our scheme has higher security and a faster verification process in multi-cloud storage.
Named Entity Recognition (NER) is one of the contents of Knowledge Extraction (KE) that transforms data into knowledge representation. However, Chinese NER faces the problem of lacking clear word boundaries that limit...
详细信息
ISBN:
(数字)9798350349184
ISBN:
(纸本)9798350349191
Named Entity Recognition (NER) is one of the contents of Knowledge Extraction (KE) that transforms data into knowledge representation. However, Chinese NER faces the problem of lacking clear word boundaries that limit the effectiveness of the KE. Although the flat lattice Transformer (FLAT) framework, which converts lattice structure into a flat structure including a set of spans, can effectively improve this problem and obtain advanced results, there still exist the problems of insensitivity to entity importance weights and insufficient feature learning. This paper proposes a weighted flat lattice Transformer architecture for Chinese NER, namely WFLAT. The WFLAT first adds a weight matrix into self-attention calculation, which can obtain finer-grained partitioning of entities to improve experimental performance, and then adopts a multi-layer Transformer encoder with each layer using a multi-head self-attention mechanism. Extensive experimental results on benchmarks demonstrate that our proposed KE model can obtain state-of-the-art performance for the Chinese NER task.
With the increasing competition in intellectual property rights, patent value prediction has become a hot research issue in the field of intellectual property rights. Most of the current research on patent value eithe...
详细信息
ISBN:
(数字)9798350359312
ISBN:
(纸本)9798350359329
With the increasing competition in intellectual property rights, patent value prediction has become a hot research issue in the field of intellectual property rights. Most of the current research on patent value either predicts some structural indicators (e.g., citations) or the intrinsic value of patents, but there is relatively little work on predicting the actual value of patents. Patent value prediction faces the following challenges, including: (1)data: the amount of actual transaction data of patents is small and difficult to collect, so the amount of training data and test data can be used is small; (2)features: how to extract the valuation features of the patent, especially technical features from unstructured patent texts; (3)model and validation: how to build a model for predicting patent prices and how to verify the accuracy of our experimental results. To solve these problems, we propose a regularized artificial neural network based patent value interval prediction model: (1) in terms of data, we extract the value data of patents from the official websites of several universities in China, the oceantomo patent trading platform in the United States, and the Patsnap platform, which come with information such as the actual transaction price or the bidding and asking price. (2) in terms of features, we extract the unstructured textual features of patent portfolios, technical features, and structured features of fifteen patents as the valuation features of patents; (3) in terms of model and validation, we use regularized artificial neural networks to give prediction intervals and prediction uncertainty, and validate the model with a measure of numerical intervals. We compare the model with the baseline model and the results show that our model achieves good results.
As the largest source of technical information around the world, patents are regarded as an essential crystallization and carrier of knowledge and technological innovation. Patent transformation is conducive not only ...
As the largest source of technical information around the world, patents are regarded as an essential crystallization and carrier of knowledge and technological innovation. Patent transformation is conducive not only to enhancing economic efficiency, but also to improving productivity and the rational utilization of resources. There is an imbalance between high patent ownership and low transformation rates. We try to predict the occurrence of transformation events from the patent assignment. However, there are some challenges in predicting patent transformation: (1) how to capture transformation features of patents, especially combined with the transfer time factor. (2) how to predict patent transfer time effectively. To address these challenges, a Patent Transfer Time Forecasting Model (PTTFM) is proposed. The model includes: (1) extraction of time-varying features of patents. (2) the patent transfer time is forecast using a Neural Temporal Point Process. By testing the model on patents under different classifications, the experimental results are obtained to show that the proposed model is applicable to predict the timing of patent assignment within a certain time frame, especially one month. Our work may facilitate patent transformation while interpretability is ensured for transformation events.
As medical insurance continues to grow in size, the losses caused by medical insurance fraud cannot be underestimated. Current data mining and predictive techniques have been applied to analyze and explore the health ...
详细信息
Intellectual property transactions have shown a strong growth momentum in recent years, but the patent transaction market has been plagued by the matching degree of consumers and sellers, resulting in frequent problem...
Intellectual property transactions have shown a strong growth momentum in recent years, but the patent transaction market has been plagued by the matching degree of consumers and sellers, resulting in frequent problems such as low patent transformation efficiency and poor transaction quality. This paper proposes a method of recommending patents to consumers by experts to improve the environment of patent transactions. Through the analysis of the past transaction information of the patent, the effective path information of the target is extracted. The graph neural network is used to describe the characteristics and semantics among experts, patents and consumers, and then capture the potential weight among them through the common attention mechanism, and then dynamically integrate them to predict the occurrence of recommendation behavior. The paper makes reasonable use of social information and expert information in the transaction, which significantly improves the rationality and accuracy of expert recommendation.
Fuzzing is increasingly being utilized as a method to test the reliability of Deep Learning (DL) systems. In order to detect more errors in DL systems, exploring the internal logic of more DNNs has become the main obj...
详细信息
ISBN:
(数字)9798350349184
ISBN:
(纸本)9798350349191
Fuzzing is increasingly being utilized as a method to test the reliability of Deep Learning (DL) systems. In order to detect more errors in DL systems, exploring the internal logic of more DNNs has become the main objective of fuzzing. Despite advancements in the seed selection aspect of fuzzing, considerable opportunities still exist for improving testing efficiency. Current research has issues with the repeated consideration of neurons in the model that will be covered in the future by other seeds, leading to redundant seeds and lower testing efficiency. Additionally, there is a lack of a method to measure the potential of seeds to increase coverage, making it difficult to select the most worthy seeds for mutation in each iteration. We propose an uncovered neurons information based (UNIB) fuzzing method for DNN. UNIB uses clustering methods to organize the seed queue based on initial seed data, aiming to enhance the coverage rate improved in each iteration. It also integrates coverage information from the testing phase to identify the seeds with the greatest potential. The experimental results show that UNIB achieved a higher NC than the second-best method by 1.1% and 3% in LetNet-4 and LetNet-5, respectively. UNIB consistently required the fewest number of iterations to reach the same NC as other methods. For both LetNet-4 and LetNet-5, the adversarial test case sets generated by UNIB exhibited the highest diversity.
The standard essential patents are some patents for which the patent technology solutions are adopted by the technological standard. The identification of standard essential patents is an important task in the standar...
The standard essential patents are some patents for which the patent technology solutions are adopted by the technological standard. The identification of standard essential patents is an important task in the standardization. With the sharply increasing number of patents and much more diversity of standard domains, the manual standard essential patents identification methods to check the patent by word for word, are not applicable for the big patent dataprocessing. The automatic standard essential patents identification methods face some challenges from the extraction and representation of features to the construction and learning of models. To solve the above issues, we develop a graph convolutional network based standard essential patents identification. We propose a hypothesis that the standard essential patents under the same standard are structure-association and the associated relations can be used in standard essential patents identification. Herein, we extract the co-occurrence relations including keyword-keyword relation, document-keyword relation. We construct a heterogeneous graph consisting of patent nodes, keyword nodes and their co-occurrence relations, which include rich structural information for the identification of standard essential patents. Thereafter, a graph convolutional network is developed to identify the potential standard essential patents. Since the number of standard essential patents and nonstandard essential patents is imbalance in practice, we utilize the sampling method to alleviate the imbalanced issue on the graph. To validate the effectiveness of the proposed model, we conduct experiments on five datasets of patent in the real world and the experimental results show that the proposed model outperforms existing research in the identification of standard essential patents.
Fractal represents a special feature of nature and functional objects. However, fractal based computing can be applied to many research domains because of its fixed property resisted deformation, variable parameters a...
详细信息
Fractal represents a special feature of nature and functional objects. However, fractal based computing can be applied to many research domains because of its fixed property resisted deformation, variable parameters and many unpredictable changes. Theoretical research and practical application of fractal based computing have been hotspots for 30 years and will be continued. There are many pending issues awaiting solutions in this domain, thus this thematic issue containing 14 papers publishes the state-of-the-art developments in theorem and application of fractal based computing, including mathematical analysis and novel engineering applications. The topics contain fractal and multifractal features in application and solution of nonlinear odes and equation.
暂无评论