Microsoft Technology Licensing, LLC

Paul B Koch

Eric J Horvitz

Raman Kumar Sarin

Sridhar Srinivasan

Christopher A Meek

Mehmet Iyigun

John Charles Krumm

Arun Upadhyaya Kishan

Hari R Pulapaka

Michael Richard Fortin

Johnson T Apacible

Moises Goldszmidt

Asela J Gunawardana

Ahmad Bilal

Ajoy Nandi

Murugesan S Subramani

Melissa Nicole Lim

David L Racz

Christopher Peter Kleynhans

Jason T Creighton

Rich Caruana

Dawn Woodard

Galina Nogin

Amol Wankhede

Mangesh Deshpande

Milos Kralj

Severin Hacker

Jason Robarts

The system comprises a cooling garment that is intended to cool the user of the garment. In one embodiment, the cooling garment is worn under a body armor. In one embodiment, the cooling garment is worn under any other garment or in any situation or environment where the user desires a cooling effect. In one embodiment the cooling garment comprises an outer layer and an inner layer. The inner layer has a plurality of perforations that allow air to flow therethrough. The outer layer is solid, so that air is urged toward the perforations and does not exit the garment away from the user, but instead towards the user. A flexible hose is coupled between the first and second layer and extends outward from the garment. The hose terminates in a quick release coupling that allows it to be removably attached to an air source, such as from a pump or other cooling system. In one embodiment, the quick release coupling is magnetic and is detached by pulling on the coupling or by the user of the cooling garment stepping away from the connection. In one embodiment, the system is used in a vehicle with a pump coupled to the electrical system of the vehicle.

Cooling apparatus

A system for predicting variability of travel time for a trip at a particular time may utilize a machine learning model including latent variables that are associated with the trip. The machine learning model may be trained from historical trip data that is based on location-based measurements reported from mobile devices. Once trained, the machine learning model may be utilized for predicting variability of travel time. A process may include receiving an origin, a destination, and a start time associated with a trip, obtaining candidate routes that run from the origin to the destination, and predicting, based at least in part on the machine learning model, a probability distribution of travel time for individual ones of the candidate routes. One or more routes may be recommended based on the predicted probability distribution, and a measure of travel time for the recommended route(s) may be provided.

Predicting and utilizing variability of travel times in mapping services

Calendar and scheduling applications organize and display user events and provide event reminders. A method of triggering a reminder includes accessing a reminder which describes an event. An individual associated with the event, other than the user, is identified. A future time is predicted when the user will be within proximity of the individual. A time to trigger the reminder for presentation to the user is determined, such that the time to trigger the reminder occurs in advance of the predicted future time when the user will be within proximity of the individual. Based on a determination that the time for triggering the reminder has occurred, the reminder is triggered to be presented to the user.

Intelligent surfacing of reminders

Systems and methods of pre-launching applications in a computer system, said applications being likely to be activated by a user from a terminated and/or suspended process state, are disclosed. The pre-launching of an application may be based on the assessed probability of the application being activated&#x2014;as well as the level of availability of system resources to affect such pre-launching. Applications may be pre-launched based on these and other conditions/considerations, designed to improve the user's experience of a quick launch of applications in the background. Several prediction models are presented to provide a good estimate of the likelihood of an application being activated by a user. Such prediction models may comprise an adaptive predictor (based on past application usage situations) and/or a switch rate predictor (based on historic data of an application being switched and, possibly, having a decay rate applied to such switch rate measure).

Predictive pre-launch for applications

Methods are described for ideally joining human and machine computing resources to solve tasks, based on the construction of predictive models from case libraries of data about the abilities of people and machines and their collaboration. Predictive models include methods for folding together human contributions, such as voting, with machine computation, such as automated visual analyses, as well as the routing of tasks to people based on prior performance and interests. An optimal distribution of tasks to selected participants of the plurality of participants is determined according to a model that considers the demonstrated competencies of people based on a value of information analysis that considers the value of human computation and the ideal people for providing a contribution.

Combining human and machine intelligence to solve tasks with crowd sourcing

Sensing, learning, inference, and route analysis methods are described that center on the development and use of models that predict road speeds. In use, the system includes a receiver component that receives a traffic system representation, the traffic system representation includes velocities for a plurality of road segments over different contexts. A predictive component analyzes the traffic system representation and automatically assigns velocities to road segments within the traffic system representation, thereby providing more realistic velocities for different contexts where only statistics and/or posted speed limits were available before. The predictive component makes predictions about velocities for road segments at a current time or at specified times in the future by considering available velocity information as well as such information as the properties of roads, geometric relationships among roads of different types, proximal terrain and businesses, and other resources near road segments, and/or contextual information.

Inferring road speeds for context-sensitive routing

Learning, inference, and decision making with probabilistic user models, including considerations of preferences about outcomes under uncertainty, may be infeasible on portable devices. The subject invention provides systems and methods for pre-computing and storing policies based on offline preference assessment, learning, and reasoning about ideal actions and interactions, given a consideration of uncertainties, preferences, and/or future states of the world. Actions include ideal real-time inquiries about a state, using pre-computed value-of-information analyses. In one specific example, such pre-computation can be applied to automatically generate and distribute call-handling policies for cell phones. The methods can employ learning of Bayesian network user models for predicting whether users will attend meetings on their calendar and the cost of being interrupted by incoming calls should a meeting be attended.

Precomputation of context-sensitive policies for automated inquiry and action under uncertainty

The present invention relates to a system and methodology to facilitate collaboration and communications between entities such as between parties to a communication, automated applications and components, and/or combinations thereof. The systems and methods of the present invention include a service that supports collaboration and communication by learning predictive models that provide forecasts of one or more aspects of a user's presence and availability. Presence forecasts include a user's current location or future locations at different levels of location precision and of the availability to users of different devices or applications. Availability assessments include inferences about the cost of interrupting a user in different ways and a user's current or future access to one or more communication channels that may be supported by one or more devices with appropriate capabilities. The predictive models are constructed via statistical learning methods from data collected by considering user activity and proximity from multiple devices, in addition to analysis of the content of users' calendars, the time of day, and day of week, for example. Beyond ambient data collection, users can provide input via batch input tools or via intermittent probes of their situation and context. Various applications are provided that employ the presence and availability information supplied by the models in order to facilitate collaboration and communications between entities.

Composable presence and availability services

A system and methodology is provided for improving directory operations within a system providing an electronic hierarchical directory of items. The system includes a component which analyzes probabilities and utilities associated with determining potential target directories for storing and accessing data, and a component for building a subset of the potential target directories that are predicted to be the target directory. The probabilities and/or utilities are functions of expected navigation costs associated with traversing from a displayed directory to at least one of the potential target directories. Methods in accordance with the present invention can be coupled with displays of substructures that format the substructures into a coherent hierarchical view.

Decision-theoretic methods for identifying relevant substructures of a hierarchical file structure to enhance the efficiency of document access, browsing, and storage

Gun shell holder

Growing community of inventors

Seattle, WA, United States of America

Paul B Koch