Mark Giereth

Iterative integration of visual insights during patent search and analysis

Patents are an important economic factor in todays globalized markets. Therefore, the analysis of patent information has become an inevitable task for a variety of interest groups. The retrieval of relevant patent information is an integral part of almost every patent analysis scenario. Unfortunately, the complexity of patent material inhibits a straightforward retrieval of all relevant patent documents and leads to iterative, time-consuming approaches in practice. With ‘PatViz’, a new system for interactive analysis of patent information has been developed to leverage iterative query refinement. PatViz supports users in building complex queries visually and in exploring patent result sets interactively. Thereby, the visual query module introduces an abstraction layer that provides uniform access to different retrieval systems and relieves users of the burden to learn different complex query languages. By establishing an integrated environment it allows for interactive reintegration of insights gained from visual result set exploration into the visual query representation. We expect that the approach we have taken is also suitable to improve iterative query refinement in other Visual Analytics systems.

Making sense of collocations

Lexico-semantic collocations (LSCs) are a prominent type of multiword expressions. Over the last decade, the automatic compilation of LSCs from text corpora has been addressed in a significant number of works. However, very often, the output of an LSC-extraction program is a plain list of LSCs. Being useful as raw material for dictionary construction, plain lists of LSCs are of a rather limited use in NLP-applications. For NLP, LSCs must be assigned syntactic and, especially, semantic information. Our goal is to develop an ‘‘off-the-shelf’’ LSC-acquisition program that annotates each LSC identified in the corpus with its syntax and semantics. In this article, we address the annotation task as a classification task,viewing it as a machine learning problem. The LSC-typology we use are the lexical functions from the Explanatory Combinatorial Lexicology; as lexico-semantic resource, EuroWordnet has been used. The applied machine learning technique is a variant of the nearest neighbor-family, which is defined over lexico-semantic features of the elements of LSCs. The technique has been tested on Spanish verb–noun bigrams. � 2005 Elsevier Ltd. All rights reserved.

Visualization Enhanced Semantic Wikis for Patent Information

In this paper we present a new approach for using semantic wikis for collaborative patent search and annotation. We describe an extension that allows integrating interactive visualizations into semantic wikis for getting deeper insights into the classificatory, geographical, and temporal distribution of large patent sets. This approach differs from typical wiki usage scenarios in the sense that it combines automatic content generation based on patent search activities of the users with user driven semantic annotation of patent information, e.g. patent rating, linking with prior art, reviews, translations, discussions, etc. The content generation involves a semantic model that is described in terms of different ontologies for patent information. A modern wiki system is used for semantic annotation, comments, discussions, versioning, notification, and full-text search. Our approach is motivated by using available functionalities of a modern wiki system in combination with visualization techniques to directly implement major user requirements for supporting the knowledge-intensive tasks of patent search and understanding.

Visual Analytics: Semantic lenses: Seamless augmentation of web pages with context information from implicit queries

We propose a novel method to support analytical processes by visually integrating context information directly into web pages. The context information is obtained from knowledge bases or services that provide additional information about certain concepts and instances of a knowledge domain. The approach performs implicit queries on the underlying information sources using the key phrases of the web page and visually presents the results to the user in a seamless way. The technique aims at improving the integration of different information sources into the users task. The method has two phases, an augmentation and an interaction phase. In the augmentation phase, for each key phrase the availability of additional context information is checked. All phrases for which context information is available are highlighted by adding special markups and scripts to the web page. In the interaction phase, the user can click on a highlighted phrase to receive the associated context information. The information is displayed directly in the web page in an overlay that we call a semantic lens.

A 3D treemap approach for analyzing the classificatory distribution in patent portfolios

Due to the complexity of the patent domain and the huge amount of data, advanced interactive visual techniques are needed to support the analysis of large patent collections and portfolios. In this paper we present a new approach for visualizing the classificatory distribution of patent collections among the International Patent Classification (IPC) - todaypsilas most important internationally agreed patent classification system with about 70.000 categories. Our approach is based on an interactive three-dimensional treemap overlaid with adjacency edge bundles.

Design Patterns for Rapid Visualization Prototyping

In this paper we present three software design patterns for rapid prototyping of information visualization applications. The first pattern describes a mapping of object oriented models to relational data tables used in many visualization frameworks. The second pattern describes a script based approach for the configuration of visualization applications. The third pattern addresses the problem of performing online changes on the visual mapping by enhancing fine-grained mapping operators with scripting capabilities. We present an implementation of the patterns, which is based on the Prefuse toolkit. Finally we discuss some experimental results according to performance issues.

Web Based Visual Exploration of Patent Information

Patents are an invaluable source of scientific and technological information. Due to the strongly increasing number of patent applications and the broadening of the objectives of patent analysis, there is a great demand for ubiquitous access to patent information and for flexible visualizations meeting the requirements of different groups of users. In this paper we propose new visualization techniques for patent information and approaches for interactively exploring this information in web based environments. We show how these visualizations can be integrated into existing web portals by using a new paradigm that we call Semantic Lens.