Tiziano Montecchi

Searching in Cooperative Patent Classification: Comparison between keyword and concept-based search

International patent corpus is a gigantic source containing today about 80million of documents. Every patent is manually analyzed by patent officers and then classified by a specific code called Patent Class (PC). Cooperative Patent Classification CPC is the new classification system introduced since January 2013 in order to standardize the classification systems of all major patent offices. Like keywords for papers, PCs point to the core of the invention, describing concisely what they contain inside. Most of patents strategies are based on PC as filter for results therefore the selection of relevant PCs is often a primary and crucial activity. This task is considered particularly challenging and only few tools have been specially developed for this purpose. The most efficient tools are provided by patent offices of EPO and WIPO. This paper analyzes their PCs search strategy (mainly based on keyword-based engines) in order to identify main limitations in terms of missing relevant PCs (recall) and non-relevant results (precision). Patents have been processed by KOM, a semantic patent search tool developed by the authors. Unlike all other PC search tools, KOM uses semantic parser and many knowledge bases for carrying out a conceptual patent search. Its functioning is described step by step through a detailed analysis pointing out the benefits of a concept-based search vis-a-vis a keyword-based search. An exemplary case is proposed dealing with CPCs describing the sterilization of contact lenses. Comparison could be likewise conducted on other PCs such as International (IPC), European (ECLA) or United States (USPC) patent classification codes.

Functional-Based Search for Patent Technology Transfer

Patent literature contains over 70 million patent documents, so the amount of information available to companies and the opportunity to derive business value and market new products from this collection is huge. However, presently an effective information extraction is a difficult task because patentees typically write using their own lexicon, style and strategy in describing their inventions. This paper presents a discussion about open problems and a way to overcome them by a new functional search based on Function-Behaviour-Physical effect-Structure ontology. This ontology is used for a technology transfer activity by patents, with the aim of making users aware of how technologies, not yet exploited in their own field, have already been patented in other domains and exactly for achieving their same desired goal. To reach this objective a multidisciplinary approach is proposed, combining design ontologies with information retrieval tools. A case study has been presented to demonstrate how the conceived framework is strategic to search for patents and automatically classify them according to the proposed ontology.

A function-behaviour oriented search for patent digging

Patents are an important source of technical knowledge which is increasing its fundamental role in supporting design activity. Analogical thinking, for example, is based on a fruitful and previously unnoticed analogy with an existing solution and patent in another area. Patents reveal solutions to technical problems, and they represent an inexhaustible source of information: more than 80 percent of man’s technical knowledge is described in patent literature [1]. Therefore automation of systems for patent retrieval, especially for commercial use, is in great demand. Manual extraction of desired patents is very costly and time consuming. This article proposes an inventive procedure to create a thesaurus, identifying the pool of keywords related to a given product based on a combination of creativity methods and a pre-built thesaurus of physical effects. Keywords are classified into a hierarchical tree diagram according to the FBS Function/Behaviour/Structure classification [2]. This classification, called KOM® - Knowledge Organizing Module [3], can be used for building a state of the art, problem solving activity support, carrying out technological transfer and forecasting activities. In this work, the algorithm for automatic patent digging aimed at building the state of the art of a system or of a technology is presented. Novel and key points are widely illustrated in this paper, together with an explanatory case study.Copyright

Methodological enhancements for concept exploration in product design

The paper discloses a method for conceptual design oriented to generation of new product concepts based on in-depth knowledge and experience of systematic innovation methods and tools, but that does not require specific advanced skills to be performed. The method has been freely inspired by TRIZ Laws of Technical System Evolution (LTSE). It is structured as a sequence of practical guidelines and operative rules that guide designers through an unconventional paradigm leading to breakthrough ideas and new solutions. It has been checked through a set of test cases offered by local companies and performed by engineering students.

A new patent-based approach for technology mapping in the pharmaceutical domain

The key factor in decision-making is the quality of information collected and processed in the problem analysis. In most cases, patents represent a very important source of information. The main problem is how to extract such information from the huge corpus of documents with a high recall and precision, and in a short time. This article demonstrates a patent search and classification method, called Knowledge Organizing Module, which consists of creating, almost automatically, a pool of patents based on polysemy expansion and homonymy disambiguation. Since the pool is done, an automatic patent technology landscaping is provided for fixing the state of the art of our product, and exploring competing alternative treatments and/or possible technological opportunities. An exemplary case study is provided, it deals with a patent analysis in the field of verruca treatments.