Chun-Yi Wu

A patent quality analysis for innovative technology and product development

Enterprises evaluate intellectual property rights and the quality of patent documents in order to develop innovative products and discover state-of-the-art technology trends. The product technologies covered by patent claims are protected by law, and the quality of the patent insures against infringement by competitors while increasing the worth of the invention. Thus, patent quality analysis provides a means by which companies determine whether or not to customize and manufacture innovative products. Since patents provide significant financial protection for businesses, the number of patents filed is increasing at a fast pace. Companies which cannot process patent information or fail to protect their innovations by filing patents lose market competitiveness. Current patent research is needed to estimate the quality of patent documents. The purpose of this research is to improve the analysis and ranking of patent quality. The first step of the proposed methodology is to collect technology specific patents and to extract relevant patent quality performance indicators. The second step is to identify the key impact factors using principal component analysis. These factors are then used as the input parameters for a back-propagation neural network model. Patent transactions help judge patent quality and patents which are licensed or sold with intellectual property usage rights are considered high quality patents. This research collected 283 patents sold or licensed from the news of patent transactions and 116 patents which were unsold but belong to the technology specific domains of interest. After training the patent quality model, 36 historical patents are used to verify the performance of the trained model. The match between the analytical results and the actual trading status reached an 85% level of accuracy. Thus, the proposed patent quality methodology evaluates the quality of patents automatically and effectively as a preliminary screening solution. The approach saves domain experts valuable time targeting high value patents for R&D commercialization and mass customization of products.

Develop a Formal Ontology Engineering Methodology for Technical Knowledge Definition in R&D Knowledge Management

In recent years, many technical disciplines systematically develop standardized ontology that domain experts agree upon and apply to share and annotate information in their fields. The formal ontological representation facilitates R&D knowledge sharing and re-use by both knowledge workers and application systems. In this research, a system engineering approach for creating and managing domain ontology (called ontology engineering, OE) is proposed. The proposed methodology describes an integrated approach in five steps. The approach combining with XML representation schema is adopted to develop a computer-aided ontology engineering (CAOE) tool for effective engineering knowledge construction. The application of the methodology and OE tool application for R&D knowledge management is then investigated through a case study. The case study depicts the ontology engineering for R&D of the monetary bill inspection machine. The machine design knowledge ontology is applied to the related patent search analysis and synthesis to support knowledge management during the machine design and development.

A Negotiation Strategy of Collaborative Maintenance Chain and Its Multi-Agent System Design and Development

The common maintenance methods in the electrical power system relies on the emergent maintenance and periodic maintenance, which is lacking to avoid the equipment shutdown. To enrich the maintenance efficiency and system benefit, this reseach uses the electrical power systems as case example to propose a negotiation model of collaborative maintenance chain. Meanwhile, to flexibly adopt new information technology and new methodologies for expert systems, this research applies multi-agent system (MAS) technology to enable the integration of different systems and databases. Via wrapping the systems and databases into agents with certain degree of authorities, these agents are able to assist humans in information communication, discussion and negotiation, and finally the generation of decisions. Finally, this research implements a prototype system based on MAS architecture. And the MAS technology with characteristics such as pro-activity, reactivity, social ability, and autonomy into this collaborative maintenance chain is applied to enhance the communication efficiency. Moreover, this research applies game theory to design a negotiation game scenario and provides a platform for asset operation site, system provider and first-tier collaborator to negotiate their maintenance decisions. The objectives of different departments plan their resources allocation efficiently and effectively for the maintenance jobs planned and scheduled to ensure the best utilization. Consequently, this research is a devoted to develop the optimize functions as the basis for further agent-based enterprise resources negotiation.

A Semantic Based Approach for Automatic Patent Document Summarization

With the rapid increase of patent documents, patent analysis becomes an important issue for creating innovative products and reducing time-to-market. A critical task for R&D groups is the analysis of existing patents and the synthesis of existing product knowledge. In order to increase knowledge visibility and sharing among R&D groups, a conconcurrent engineering approach is used to facilitate patent document summarization and sharing. The purpose of this research is to automate patent docment summarization as a key step toward efficient patent analysis and knowledge management. The goal of this research is to develop a semantic-based methodology for capturing patents and to summarize this content for design team collaboration. The system automatically marks, annotates, and highlights the nodes of an ontology tree which correspond to words and provides a visual figure summary. Patents for power hand tools and chemical mechanical polishing tools were downloaded to evaluate the automatic summarization system. For these cases, the accuracy of classification reached 93% and 92% respectively demonstrating 20% summarization improvements over previous methods.

Applying BPANN and hierarchical ontology to develop a methodology for binary knowledge document classification and content analysis

Nowadays many companies rely on patent engineers to search patent documents and offer recommendation and advice to R&D engineers. Given the great number of patent documents, new means to effectively and efficiently identify and manage the technology-specific patent documents are required. This research applies back-propagation artificial neural network (BPANN), a hierarchical ontology, and Normalized term frequency (NTF) method for binary document classification and content analysis. This approach helps to minimize inappropriate patent document classification. Hence, the approach reduces the effort to search and select patents for analysis. Finally, this paper use the design of exposure machines as a case study to illustrate and verify the efficacy of the approach proposed in this paper.

Develop Non-Exhaustive Overlapping Partitioning Clustering for Patent Analysis Based on the Key Phrases Extracted Using Ontology Schema and Fuzzy Adaptive Resonance Theory

Patent documents are an ample source of innovative, technical and commercial knowledge. Thus patent analysis has been considered a useful vehicle for R&D management and knowledge sharing. However, the number of patents in recent years has expanded noticeably. It is a challenge to interpret the knowledge contents and their relationship between patents, because many different types of expression may be presented in patents. Therefore, various clustering methods, e.g., partitioning clustering (K-means, K-medoids) or competitive clustering (Self-Organizing Maps, Adaptive Resonance Theory), have been developed to elucidate the characteristic of expression pattern. Nevertheless, patent documents can be partitioned into a number of clusters, where each cluster represents the documents in a certain area. The traditional clustering algorithms do not allow an object to belong to multiple clusters. In this research, we develop a novel non-exhaustive overlapping partitioning clustering (OPC) algorithm, a type of fuzzy partitioning approach, to the patent documents to overcome the exclusive clustering methods. The proposed algorithm considers the dissimilarity among cluster centers and an object can simultaneously belong to multiple clusters if the distances from this object to the cluster centers are no more than the given threshold value. Finally, the experiment uses radio frequency identification (RFID) technology related patent documents to evaluate the performance of the proposed clustering method, which combine non-exhaustive OPC algorithm with fuzzy adaptive resonance theory (ART) for effictive patent clustering.

Dynamic Patent Analysis of Wind Power Systems and Engineering Asset Development

Patent analysis of new technology development can be focused on various aspects, e.g., identifying the competitiveness of a specific country or the technical advances of a firm in the given domain. The offshore wind power (OWP) has been promoted and encouraged by many countries for their renewable energy development. This research focuses on systematically discover the profile of OWP technology innovation extracted, analysed and synthesized from world patent databases dynamically using text and data mining techniques. In real time, all related patents are searched and collected. Afterward, the research builds an OWP ontology schema by identifying the OWP technical domain structure, the core concepts, and the relationships between the concepts. The ontology schema is constructed and refined dynamically using key phrases automatically extracted from patents and verified by domain experts. The research also emphasizes on the control of risk and reliable factors when evaluating the offshore wind power development. Thus, the research applies patent indicators, i.e., the patent family, the growth rates of domain technologies, the reference and citation network, the technology and function matrix, and the patent litigation information, to derive the OWP R&D landscape and strategy. After building the OWP patent knowledge base (KB), the potentials of OWP development opportunities for a specific region can be clearly identified with reliable measures based on patent map informatics.

Using Patent Ontology Engineering for Intellectual Property Defense Support System

With the growth of the knowledge-based economy, intellectual property right (IPR) is recognized as a key factor to develop and protect the strategic competitiveness and innovation of an enterprise. Patents are used to encourage and protect inventions and to stimulate commercial development complying with legal IPRs. Due to growing number of patents, most patent information management systems lack advanced analytical and decision support methodologies and tools. The purpose of this research is to develop a patent defense system using the combination of ontology engineering and improved overlapping clustering method. The ontology engineering approach analyzes patent claims while structuring and extracting patent characteristics for technical domain schema construction. The research uses the overlapping clustering method to analyze related patents and compare their claim elements based on the patent ontology and infringement rules. The research also studies actual patent litigation cases to demonstrate the effectiveness and applicability of the research solutions.