VisPat is an innovative application that allows patent agents and researchers a novel visual search for patent retrieval based on the automatic recognition of image similarities and text-image relations in patent specifications. The image-based search is based on machine learning techniques and is intended to increase the findability and visibility of patents and overcome language and terminology barriers. 

The application is a prototype developed as part of the research project ExpResViP, funded by the German Federal Ministry of Education and Research. The prototype focused on two patent areas: autonomous driving and wind energy. Development was discontinued in mid-2023. The components created for the prototype have partly been integrated into https://service.tib.eu/ipatent/. 

The following video presents some of the app's features as seen by the user.