Extract conceptual graphs from plain texts in patent claims

This paper develops techniques to extract conceptual graphs from a patent claim using syntactic information (POS, and dependency tree) and semantic information (background ontology). Due to plenteous technical domain terms and lengthy sentences prevailing in patent claims, it is difficult to apply a NLP Parser directly to parse the plain texts in the patent claim. This paper combines techniques such as finite state machines, Part-Of-Speech tags, conceptual graphs, domain ontology and dependency tree to convert a patent claim into a formally defined conceptual graph. The method of a finite state machine splits a lengthy patent claim sentence into a set of shortened sub-sentences so that the NLP Parser can parse them one by one effectively. The Part-Of-Speech and dependency tree of a patent claim are used to build the conceptual graph based on the pre-established domain ontology. The result shows that 99% sub-sentences split from 1700 patent claims can be efficiently parsed by the NLP Parser. There are two types of nodes in a conceptual graph, the concept and the relation nodes. Each concept or relation can be extracted directly from a patent claim and each relation can link with a fixed number of concepts in a conceptual graph. From 100 patent claims, the average precision and recall of a concept class mapping from the patent claim to domain ontology are 96% and 89%, respectively, and the average precision and recall for Real relation class mapping are 97% and 98%, respectively. For the concept linking of a relation, the average precision is 79%. Based on the extracted conceptual graphs from patents, it would facilitate automated comparison and summarization among patents for judgment of patent infringement.     

AUTOMATIC COMPLEXITY REDUCTION IN REINFORCEMENT LEARNING

High dimensionality of state representation is a major limitation for scale-up in reinforcement learning (RL). This work derives the knowledge of complexity reduction from partial solutions and provides algorithms for automated dimension reduction in RL. We propose the cascading decomposition algorithm based on the spectral analysis on a normalized graph Laplacian to decompose a problem into several subproblems and then conduct parameter relevance analysis on each subproblem to perform dynamic state abstraction. The elimination of irrelevant parameters projects the original state space into the one with lower dimension in which some subtasks are projected onto the same shared subtasks. The framework could identify irrelevant parameters based on performed action sequences and thus relieve the problem of high dimensionality in learning process. We evaluate the framework with experiments and show that the dimension reduction approach could indeed make some infeasible problem to become learnable.     

Combining Cooperative and Non-Cooperative Automated Negotiations

Automated negotiation is a key issue to facilitate e-Business. It is an on-going research area and attracts attention from both research communities and industry. In this paper, we propose a multiple-stage co-operative automated negotiation architecture, including a sophisticated negotiation strategy and protocol, to resolve the agents' conflicts. This proposed architecture attempts to address the search for joint efficiency for negotiating agents in large and complex problem spaces using a co-evolutionary method. A game theoretic method is adapted to distribute the payoffs generated from the co-evolutionary method. The architecture supports interactions between the two methods to demonstrate that high-quality solutions can be found through their complimentary functions. Using the structure it is possible to refine and explore potential agreements through an iterated process. This article also reports some experimental results and discussions. Jen-Hsiang Chen obtained his MSc degree in Management of Information Technology from Sunderland University. He is a Ph.D. student within the Distributed Systems and Modelling Research Group in the School of Mathematical and Information Sciences at Coventry University. His research project is related to game theory and heuristic approaches in automated negotiation. Kuo-Ming Chao obtained both of his MSc and Ph.D. degrees from Sunderland University, UK. After getting his Ph.D. degree, he has been working at Engineering Design Centre, Newcastle University, UK as research associate. He joined School of Mathematical and Information Sciences, Coventry University as senior lecturer in 2000. He is currently the leader of Distributed System and Modelling Research Group within the school. His research interests include Multi-Agent systems, Web Services, and Grid Computing. Nick Godwin graduated in Mathematics at London University. He obtained a masters degree and a doctorate through the Mathematics Institute at Warwick University. Since that time he has worked at Coventry University, participating in a number of research projects associated with the application of Computing to Manufacturing. Recently he has been working with the Distributed Systems and Modelling Research Group in the School of Mathematical and Information Sciences at Coventry University. Von-Wun Soo graduated from Electrical Engineering from National Taiwan University. He got his master degree in Biomedical Engineering and Ph.D. degree in Computer Science from the State University of New Jersey, Rutgers, USA. After getting his PhD degree, he has been doing research and teaching as a faculty in Department of Computer Science at National Tsing Hua University, Hsin Chu, Taiwan. Recently, he has been working with coordination and ontology for multi-agent systems in various application domains such as context aware travelling information service, historical information extraction, biological and genomic knowledge management, and creative engineering design.     

A cooperative multi-agent platform for invention based on patent document analysis and ontology

We propose a cooperative multi-agent platform to support the invention process based on the patent document analysis. It helps industrial knowledge managers to retrieve and analyze existing patent documents and extract structure information from patents with the aid of ontology and natural language processing techniques. It allows the invention process to be carried out through the cooperation and coordination among software agents delegated by the various domain experts in the complex industrial R&D environment. Furthermore, it integrates the patent document analysis with the inventive problem solving method known as TRIZ method that can suggest invention directions based on the heuristics or principles to resolve the contradictions among design objectives and engineering parameters. We chose the patent invention for chemical mechanical polishing (CMP) as our case study. However, the platform and techniques could be extended to most cooperative invention domains.