International Business Machines Corporation

Kent C B Steer

Timothy Michael Lynar

John Michael Wagner

Cristian Vecchiola

Jan Richter

Ermyas Abebe

Jorge A M Ortiz

Training a machine to learn and to identify time slots to select in a user's electronic calendar, in one aspect, may include receiving an invitee list and meeting meta data associated with a meeting via an electronic calendar application. Candidate timeslots for the meeting may be determined and a database associated with the electronic calendar application analyzed to obtain user factors associated with the candidate timeslots and invitees in the invitee list. Based on the user factors, a predictive model may be generated that is associated with an invitee in the invitee list by a machine learning algorithm. The predictive model may be executed to determine a time slot to select for the invitee.

Machine learning system for intelligently identifying suitable time slots in a user's electronic calendar

A system configured to manage battery energy of a mobile device includes a primary mobile device and at least one peer device. The primary mobile device includes a power unit, a main communication module to electrically communicate with a peer device, and a peer assisted module in electrical communication with the power unit and the main communication module. The peer assisted module determines an energy level of the energy unit, and determines a task to be executed by the peer device. The peer device receives the task transmitted from the primary mobile device. The peer device further includes a peer process management module that executes at least one computation that completes the task, and communicates a completed task to the primary mobile device.

Mobile device offloading task to a peer device and receiving a completed task when energy level is below a threshold level

Mobile device offloading its task to a peer device when available power is below a threshold level

An optimal vehicle battery recommendation system includes at least one sensor to detect a manipulation of the vehicle. A driver behavior module determines a driving behavior of a driver of the vehicle. A vehicle consumption module determines battery information of an on-board battery currently connected to the vehicle, and determines energy consumption of the vehicle. A battery capacity advisor module is in electrical communication with the driver behavior module and the vehicle consumption module. The battery capacity module determines a replacement battery option that changes at least one battery characteristic of the on-board battery based on the driver behavior model and the vehicle consumption model.

Optimal electric vehicle battery recommendation system

Growing community of inventors

Brunswick, Australia

Kent C B Steer