Microsoft Technology Licensing, LLC

Other

Ido Priness

Dikla Dotan-Cohen

Haim Somech

Assaf Avihoo

Adi L Miller

Hadas Bitran

Tomer Hermelin

Shlomi Maliah

Shiraz Jitendra Cupala

Jaime Brooks Teevan

Shira Weinberg

Amir Kantor

Lan Ye

Sagi Hilleli

Ido Cohn

Kevin Michael Carter

Shai Ifrach

Shyam Gupta

Gautam Jain

Xiao Yan Lu

Oded Vainas

Yasemin Cenberoglu

Kumud Ranjan

Eyal Kolman

Gal Lavee

Limor Lahiani

Daniel Avigdor

Lilach Perry

Michael Sterenberg

Matthew Jonathan Gardner

Boaz Sapir

Ran Bernstein

Inbal Budowski Tal

Eleonora Shtotland

Dikla Dotan-cohen

Anat Inon

Gilad Gildin

Ofek David

Amitay Dror

Michal Yarom Zarfati

Tzoof Avny Brosh

Embodiments disclosed herein are directed to computing technology for programmatically sanitizing unwanted content that is shared in a meeting. The unwanted content may be sanitized in real-time and in a meeting presentation. In an implementation, the unwanted content is detected, and a determining a sensitivity mitigation action is determined for the unwanted content. The sensitivity mitigation action is applied to generate a modified presentation of a live meeting presentation such that aspects of the unwanted content are removed. A graphical user interface (GUI) tool is disclosed to enable users to control application of a sensitivity mitigation action. In this manner, embodiments disclosed herein facilitate complying with a privacy policy.

Meeting information sharing privacy tool

A system for providing a personalized assistant within a network-based communication service includes one or more processors and a memory storage device storing instructions thereon. During a network-based communication session, the system receives a query from a computing device of a first communication session participant and processes the query by determining that a second communication session participant has shared content via a content sharing feature of the network-based communication service. In response, the system provides the query and at least a portion of the shared content as input to a model, which dynamically constructs a prompt for use as input with a generative language model. The system then presents the prompt as input to the generative language model, receives a response as output from the generative language model, and causes presentation of the response to be presented to the communication session participant.

Network-based communication session copilot

A system for providing a personalized assistant within a network-based communication session includes a processor and a memory storage device storing instructions. The system determines when a first communication session participant joins the network-based communication session after a threshold duration of time subsequent to the start time of the session. Upon determining the first participant has joined, the system obtains content associated with the session and creates request data for a pre-trained generative language model. The request data includes an instruction requesting a predetermined number of suggested utterances not present in the content, each utterance relating to one or more topics corresponding to the content. The system transforms the request data to a command based on a command template and provides the command to the generative language model. The system receives a response from the model, including the predetermined number of suggested utterances, and presents them to the communication session participant in a graphical user interface while the session is in session.

Computerized systems are provided for automatically determining action items of an event, such as a meeting. The determined action items may be personalized to a particular user, such as a meeting attendee, and may include contextual information enabling the user to understand the action item. In particular, a personalized action item may be determined based in part from determining and utilizing particular factors in combination with an event dialog, such as an event speaker's language style; user role in an organization; historical patterns in communication; event purpose, name, or location; event participants, or other contextual information. Particular statements are evaluated to determine whether the statement likely is or is not an action item. Contextual information may be determined for action items, which then may be provided to the particular user during or following the event.

Automatically determining and presenting personalized action items from an event

Technology is disclosed for improving user privacy and providing user control over user-activity data collected from personal computing devices (i.e., user devices). User devices may be configured to operate in a private mode that enables a user to control, for example, which aspects of user-activity data are provided to applications and services running on their user device; to obscure or modify aspects of user-activity data so that certain applications and services, which may require this information to operate, may still function, but that the obscured information provided to these applications and services preserves user privacy or no longer may be used to identify the user; or to remove evidence of user-activity data created, monitored, reported, or otherwise collected by or on the user device while the user is operating their user device in the private mode setting.

Privacy control operation modes

In some implementations, a method includes extracting message attributes of an email associated with a user from the email. User interaction data is identified that is generated by the user in association with display of the email based on sensor data from one or more sensors. It is determined that the user interaction data corresponds to a routine of the user based on a routine-related aspect generated from a user routine model representing the routine. A time to present a notification of the email is determined based on the routine. The notification is provided to the user on a user device based on the determined time to present the notification.

Notifications based on user interactions with emails

Systems, methods, and computer-readable storage media are provided for sharing user-information with bots. An automated task to be performed on behalf of a user is determined from at least one user message provided to a user interface of a first bot. A second bot is determined that is capable of performing the automated task on behalf of the user. User information of the user to provide to the second bot for the performing of the automated task is determined. Content of the user information is based on a trust level of the second bot and service parameters for completing the automated task. The first bot provides the determined user information to the second bot using one or more network communications.

Sharing user information with and between bots

Aspects of the technology described herein provide a personalized computing experience for a user based on a user-visit-characterized venue profile. In particular, user visits to a venue are determined. For those visits, user characteristics and/or visit characteristics are determined. User similarities and visit features similarities may be determined and associated with the venue to form the user-visit-characterized venue profile. The user-visit-characterized venue profile may be provided to an application or service such as a personal assistant service associated with the user, or may be provided as an API to facilitate consumption of the user-visit-characterized venue profile by an application or service.

Characterizing a place by features of a user visit

In some implementations, a method includes extracting completion criteria of an action item and parameters of the completion criteria from a message portion of a user message between users. In response to determining, from sensor data provided by one or more sensors associated with a user, the user practices a routine; a routine-related aspect is generated from a user routine model of the user for the routine. In is inferred at least one of the extracted completion criteria of the action item is unsatisfied based on the extracted parameters and the identified routine-related aspect. Based on the inferring, a notification is provided to at least one user associated with the action item.

Notifications of action items in messages

Aspects of the technology described herein improve the clarity of information provided in automatically generated notifications, such as reminders, tasks, alerts or other messages or communications provided to a user. The clarity may be improved through augmentations that provide additional information or specificity to the user. For example, instead of providing a notification reminding the user, 'remember to send the slides before the meeting,' the user may be provided with a notification reminding the user 'remember to send the updated sales presentation before the executive committee meeting on Tuesday. The augmentation may take several forms including substituting one word in the notification with another more specific word, adding additional content such as a word or phrase to the notification without altering the existing content, and/or by rephrasing the content for grammatical correctness and/or clarity.

Augmentation of notification details

Systems, methods, and computer-readable storage media are provided for automating personalized out-of-the-box and ongoing in-application settings. A triggering event is detected for an exchange of information between an information service and one or more application or service. A trust level and domain of information of the one or more application or service is determined. Based on the trust level and domain of information, information to be shared with the one or more application or service is identified and the identified information is shared. The information to be shared can be all of the requested information, some of the requested information, or none of the requested information.

Automated personalized out-of-the-box and ongoing in-application settings

Computerized systems for synchronizing multiple calendars are provided. User activity is monitored via sensors and user devices associated with the user. Monitoring user activity includes detecting calendar activity associated with a set of calendars that includes a first calendar. A first calendar event associated with the first calendar is detected. A second calendar included in the set of calendars and associated with the first event is determined. The second calendar is determined based on the user activity, the first calendar, or the first event. The second calendar may be determined based on a synchronization profile associated with the first calendar. The second calendar is updated to include at least a portion of the first event. The first event is synchronized and/or shared with the second calendar. Only selective portions of the event data of the first event may be provided to the second calendar.

Multi-calendar harmonization

Aspects of the technology described herein allocate limited computing resources, such as available bandwidth and battery power, to transferring the most urgent and important data from a client device to an online service. Client devices have enormous amounts of information about the user's activities that could be communicated to the service at any given time. However, the wireless transfer of information uses available battery power and can consume a user's data plan. The technology described herein uses a model to determine how often information should be sent to a service. The model can also determine what information to send. Different models can be implemented in different scenarios. The different models can include different weighting that will produce different decisions given the same inputs.

Signal upload optimization

Technologies described herein improve voice-based interaction technology and provide improved user experiences for computer-performed searching within voice-based applications. After receiving a voice command that involves performing a search operation in order to respond to the command, a more intuitive response may be generated and presented to the user. In particular, certain features or properties related to the search results are determined and utilized as discriminators. A discriminator may be provided in the response to the user to enable the user to distinguish between multiple search results, or to more readily confirm a particular result, provided by the computing system. In some instances, certain details of the search results may be omitted when generating the response. In this way, the computing system may present the user with a limited but more focused set of information that is more useful for making a decision and/or continuing the interaction with the computing system.

Intuitive voice search

The technology described herein manages communications received by a mobile computing device by ascertaining a user's availability to receive an incoming communication. The technology described herein can optimize the use of notification resources on a computing device to provide notifications only when a user is available to respond to a communication the notification announces. The user's availability to receive a communication can be inferred through the analysis of signal data that describes a present context of the mobile device and/or the mobile device's user. Upon determining a present level of availability, the technology described herein can take several different actions. The actions include generating an alternative notification for a newly received communication, generating no notification for a newly received communication, and communicating an automated 'not available' message to the originator of a newly received communication.

Growing community of inventors

Herzliya, Israel

Ido Priness