• Lumenci

This Week in AI - 11 June

Welcome to our first bi-weekly series on patents in Artificial Intelligence. Here our aim is to bring to you the latest, interesting, weird and path-breaking inventions that got published over the last few week or so. Here we begin !!

US20190168122A1 - Automated artificial intelligence (ai) personal assistant

Have you ever quit a video game before completion? Sony Interactive Entertainment Inc patent on Game Play Assistant aims to solve the problem of low-engagement with their recently published patent. The patent claims a personalized assistant for monitoring game play of users playing a gaming application, learn the various paths available within the gaming application and how those users play along those paths, and provide assistance to a user based on past performance of the user, current performance of the user, and historical performance of other users playing the gaming application. It claims to provide for a better gaming experience for users participating in a gaming application because instead of struggling through hard sections of the gaming application, or quitting the gaming application, recommendations are provided in the form of gaming assistance to help guide the user. Who knows this might could become a feature in long-awaited PS5.

US20190171467A1 - Anatomy-aware adaptation of graphical user interface

One thing we like the most about Image Processing Applications is that they are practical. With current state-of-art in Deep Learning, almost everything has become feasible. This patent is related to medical imaging which makes it even better. Today there are large number of Medical Imaging Reports that are generated. High-resolution computed tomography (HRCT), x-ray radio-graphs, MRI, PET (positron emission tomography), PET-CT, SPECT, SPECT-CT, MR-PET, 3D ultrasound images are few examples. Siemens Healthcare GmbH patent provides a framework for anatomy-aware adaptation of a graphical user interface. Landmarks are detected by passing one or more current images through a trained machine learning model. A body section is then inferred based on the detected landmarks. One or more user interface elements are determined based on the inferred body section. A graphical user interface is adapted with the determined one or more user interface elements.

US20190171549A1 - Extraction of problem diagnostic knowledge from test cases

IBM has applied for a patent that enable users to extract knowledge from testing scenarios performed during application development, and later employ that knowledge to interpret application usage scenarios to enhance serviceability of applications by expediting identification and resolution of problems. This helps to supplement knowledge extracted during application development and/or document new knowledge.

US20190171552A1 -

Test Plan Generation Using Machine Learning

Continuing on the earlier theme of AI in Enterprise Software, here is one from SAP. This one relates to testing of the software systems including the use of machine learning to generate test plans, which when executed, are used to characterize software systems prior to their deployment and, in some cases, during deployment.

US20190171755A1 - Systems and methods for determining relevance of place data

Have you ever wondered why you are not able to get an Uber when you need one? Then, here is the answer. Blame machine learning (ML) for it as Uber's ML algorithms does not believe that your location is a relevant place. This patent from Uber uses machine learning for establishing relevance of a place. Example, a given place record is processed by at least one classifier, which receives as input a set of features of the given place record and outputs a prediction score indicating the certainty or probability that the given place record is associated with, or belongs to, a particular class (e.g., class label). With respect to use by a ride or ride-sharing service, for example, a given place record may be relevant if the given place record describes a place on a map that is open to the public and that a rider would want to go to. Examples of such places could include a restaurant, a hotel or motel, a public transit station, an airport, a venue etc.

We will bring more insights on the development of AI in our next edition.