Development of a software tool for the automated creation of patent portfolios

The number of patent applications is constantly increasing. In 2011, it surpassed the two million mark for the first time and in 2012 was 2.35 million patent applications worldwide. However, when searching for patents, performing statistical analyses of patents or evaluating patent portfolios, the question arises: Who is the respective applicant and owner of a corresponding property right?

However, answering this question is not always easy. According to a KPMG study, 387,000 mergers and changes of ownership took place worldwide in 2013, with an upward trend of 17%. But other causes also lead to heterogeneous designations of applicant information, which all relate to the same applicant: From different names for the same company - through the filing of different representatives (patent attorneys) - to spelling mistakes, translation or transliteration problems to country-specific peculiarities of the respective patent offices (e. g. only naming of the inventors during the filing phase in the USA). On the other hand, there are cases in which different applicants actually have the same name or parts of the same name, or in which names are very similar and have to be differentiated. In practice, therefore, time-consuming manual searches and comparisons are usually required in order to keep information on applicants and owners uniform and up-to-date.

The aim of the cooperation project is to develop a modular, largely self-sufficient and thus universally applicable software tool for the automation of these work steps. The combination of different methods of semantic information processing is intended to achieve an automated consolidation of patents and the homogenization of proper names, such as company or personal names. In addition to the applicant information (e. g. name, address, representative, inventor), further information (e. g. IPC classes for categorizing inventions, allocation of persons to companies, relationships between companies) and information from the patent content (e. g. typical technologies, industries) should also be taken into account. For this purpose, the project will develop a new interactive software tool that enables users to combine, configure and execute intelligent methods based on machine learning. In the future, the software tool is to be integrated into the existing system world of InTraCoM GmbH, but also sold as an independent new product or integrated into other systems.