Microsoft Technology Licensing, LLC

Ajoy Nandi

Zain Aziz

Sapna Daryanomal Jeswani

Jason T Creighton

Eric J Horvitz

John Charles Krumm

Ryen William White

Hosam Adel Khalil

Nikrouz Ghotbi

Paul B Koch

Christopher Hakan Basoglu

Sayan Dev Pathak

Melissa Nicole Lim

Chun Hin Nelson Siu

Carmen Quan

Vinay Bhat

Denis Fisenko

Min Hu

Md Nizam Uddin Chy

Amol Wankhede

Mangesh Deshpande

Jason Timothy Creighton

Paul Koch

A computer-implemented technique is described herein for facilitating a user's repeated execution of the same computer-implemented actions. The technique performs this task by determining patterns in the manner in which the user repeats requests associated with certain computer-implemented actions. For example, the technique determines context-dependent patterns in the manner in which the user submits search requests to a search system. The technique then leverages those patterns by proactively providing a request-assistance tool to the user in those context-specific circumstances in which the user is likely to perform the repetitive computer-implemented actions. The digital action-assistance tool provides various kinds of assistance to the user in performing the repetitive computer-implemented actions.

Context-dependent digital action-assistance tool

Techniques are provided for early processing of a part of a user input to produce a response to the entire or final user input. While the user input is being received, a partial user input, which is a part of the final user input, is processed to produce a response. The response is a candidate response for the final user input. After the final user input is received, and if the partial user input is determined to match or be equivalent to the final user input, the first response, which is already available, is provided to one or more output devices for presentation. If the final user input is determined to differ from the partial user input, the final user input is processed to produce a second response to the final user input, and the second response is provided for presentation. In some instances, multiple partial user inputs are received and processed.

Processing part of a user input to produce an early response

Interaction between a user and a conversational digital assistant executing on a computing device is controlled. Multiple interaction pairs are stored in one or more datastores accessible by the conversational digital assistant. Each interaction pair includes an interaction query and an associated assistance operation. An interactive engagement event is detected between the user and the conversational digital assistant, responsive to the storing operation. An interaction pair is selected from the one or more datastores, responsive to the operation of detecting an interactive engagement event. The interaction query of the selected interaction pair is communicated to the user. The assistance operation associated with the communicated interaction query is executed, responsive to receipt of a response from the user to the interaction query.

Controlling conversational digital assistant interactivity

In representative embodiments, a digital assistant is extended by service activities. A service activity executes as a service as part of the digital assistant. A service activity specifies a set of user data to be provided when invoked, at least one insight used to invoke the service activity in a proactive way and at least one intent used to invoke the service activity in a reactive way, and executable code that is executed when the service activity is invoked. A development environment provides templates to ease development of service activities. Service activities in development can be deployed alongside production services with access to service activities in development restricted to a set of authorized users.

Service actions for digital assistants

Task assignments are identified. A dataset that includes one or more electronic messages is received. Then, one or more pending tasks in the dataset are identified, and each of a plurality of people who are mentioned in the dataset is also identified. Then, for each of the pending tasks, one or more of the identified people are identified as potentially being people who are assigned to complete the pending task, and the pending task is associated with these identified one or more of the identified people. For each of the pending tasks, one or more of the identified people are also identified as potentially being people for whom the pending task is to be completed, and the pending task is also associated with these identified one or more of the identified people.

Identifying task assignments

Representative embodiments disclose mechanisms to utilize navigation routes in order to avoid or minimize sun glare along the navigation route. Some embodiments first estimate whether it is likely that sun glare will be perceived while navigating between a starting location and an ending location. If sun glare is likely, the navigation route is calculated using sun glare as part of a cost function. If sun glare is not likely, the navigation route is calculated without regard to sun glare. Real-time sun glare feedback can be received from one user device and used in sun glare calculations for another user device. In some embodiments a trained machine learning model can be utilized as part of the sun glare calculation. Other embodiments include digital assistants that use sun glare information to recommend actions and/or take actions on behalf of a user.

Navigation with sun glare information

In representative embodiments, a digital assistant provides actionable information to a user regarding one or more vehicles owned by a user. Actionable information is typically provided in a 'tip' which is a mechanism for presenting information to a user and may be presented in text, audible, or other form. The tips provided by the digital assistant are directed to helping the user with tasks associated with vehicles such as knowing when to obtain service such as oil changes, tire inflation, light replacement, brake replacement, fluid level check/fill, or other service. The digital assistant can utilize user information to automatically book service appointments, recommend times for service or other vehicle actions, route changes and so forth. Tips can also include links to a marketplace where recommended services can be obtained.

Digital assistant for vehicle related activities

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

Growing community of inventors

Redmond, WA, United States of America

Ajoy Nandi