Abstract: A user activity pattern may be ascertained using signal data from a set of computing devices. The activity pattern may be used to infer user intent with regards to a user interaction with a computing device or to predict a likely future action by the user. In one implementation, a set of computing devices is monitored to detect user activities using sensors associated with the computing devices. Activity features associated with the detected user activities are determined and used to identify an activity pattern based on a plurality of user activities having similar features. Examples of user activity patterns may include patterns based on time, location, content, or other context. The inferred user intent or predicted future actions may be used to facilitate understanding user speech or determining a semantic understanding of the user.

Abstract: 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.

Abstract: 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.

Abstract: Systems and methods are provided for associating meetings with projects. Some implementations include evaluating a similarity between a conversation between two or more users and a set of keywords characterizing at least one project associated with a user of the two or more users, where the conversation is captured by sensor data. Based on the similarity, a listening mode is activated on a user device associated with the user. Contextual information associated with the conversation is generated from portions of the sensor data provided by the activated listening mode. A meeting corresponding to the conversation is assigned to a project associated with the user based on the contextual information. Content is personalized to the user based on the assignment of the meeting to the project.

Abstract: A user activity pattern may be ascertained using signal data from a set of computing devices. The activity pattern may be used to infer user intent with regards to a user interaction with a computing device or to predict a likely future action by the user. In one implementation, a set of computing devices is monitored to detect user activities using sensors associated with the computing devices. Activity features associated with the detected user activities are determined and used to identify an activity pattern based on a plurality of user activities having similar features. Examples of user activity patterns may include patterns based on time, location, content, or other context. The inferred user intent or predicted future actions may be used to facilitate understanding user speech or determining a semantic understanding of the user.

Abstract: 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.

Abstract: 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.

Abstract: Computerized systems for providing a personalized computing experience are provided through enriched calendar event data. The enriched calendar event data provides an event type, additional location data for the calendar event, and the likely user attendance. To determine the enriched calendar event data, a user location pattern, and a calendar event pattern are determined. As future calendar events are detected, a set of features for the future calendar events is determined. Past calendar events having features similar to the detected future calendar event can then be determined. A user location for the similar past calendar events can be determined to form a user behavior pattern model indicating a user location for the similar past calendar events. A predicted user location for the future calendar event can be determined based upon the similar past calendar events and the user behavior pattern model.

Abstract: Pieces of location history data corresponding to an identified place of interest are obtained. Each piece of the obtained location history data references one or more signals detected at the identified place of interest and also references temporal data that corresponds to the detected signal(s). Some of the obtained pieces of location history data that represent one or more short, pass-through visits at the identified place of interest are identified. Based on the identified pieces that represent the short visit(s), conditions for determining the intent of future detected location visits at the identified place of interest are generated. The generated conditions can then be employed to determine that a detected location visit of a particular computing device determined to be at the identified place of interest is an extended visit as opposed to a short visit.

Abstract: 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.

Abstract: Personalized notifications are provided to a user. The notifications correspond to events, which can include information items, unaddressed or unnoticed by a user. The unaddressed events may be determined based on sensor data provided by a user device associated with the user including user activity pattern information. Further, an urgency level of the unaddressed event and user availability for responding to the event may be determined. The availably may comprise a model with score(s) corresponding to the user's capability for carrying out tasks associated with addressing the event. Additionally, notification content may be generated based on information about availability and the unaddressed event, and used to provide notification(s). The notification content may include a recommendation to present a notification to the user at a time determined likely to be convenient for the user to be notified of the event or where the user likely has capacity to address the event appropriately.

Abstract: 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.

Abstract: 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. It is inferred that 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.

Abstract: 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.

Abstract: 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.

Abstract: Aspects of the technology described herein provide visual representations of future user events for improved graphical user interfaces and improved computing services provided to a computer user. In one particular embodiment, using the one or more sensors, information about a current event, which may include a current location of the user, is determined. Based on at least the current event, a prediction of future events or event patterns in association with the user is determined. Each user event pattern can include one or more future events, such as activities, meetings, or location visits, corresponding with the user. Thereafter, the user event patterns can be presented via a graphical user interface. Each user event pattern can be visually represented as a sequence of events in which the user might partake over a timeframe, and may include a corresponding probability of the user's likelihood of partaking in the event.

Abstract: 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.

Abstract: Aspects of the technology described herein provide visual representations of future user events for improved graphical user interfaces and improved computing services provided to a computer user. In one particular embodiment, using the one or more sensors, information about a current event, which may include a current location of the user, is determined. Based on at least the current event, a prediction of future events or event patterns in association with the user is determined. Each user event pattern can include one or more future events, such as activities, meetings, or location visits, corresponding with the user. Thereafter, the user event patterns can be presented via a graphical user interface. Each user event pattern can be visually represented as a sequence of events in which the user might partake over a timeframe, and may include a corresponding probability of the user's likelihood of partaking in the event.

Abstract: Technology is disclosed for controlling the presentation of electronic messages on personal computing devices (i.e., user devices). The technology reviews a first electronic message to be sent. The technology determines any of a set of previously received electronic messages that are related to the first electronic message, and comparing the first electronic message to be sent to the determined set of previously received electronic messages related to the first electronic message. Based at least on the comparing, the technology compares the propriety of sending the first electronic message. The previously received electronic messages may be, in some embodiments, a user message model or a group message model. Embodiments also include generating an alert of the potential for the first electronic message to be outside the parameters of the user model, the message model or the group message model.

Abstract: Personalized notifications are provided to a user. The notifications correspond to events, which can include information items, unaddressed or unnoticed by a user. The unaddressed events may be determined based on sensor data provided by a user device associated with the user including user activity pattern information. Further, an urgency level of the unaddressed event and user availability for responding to the event may be determined. The availably may comprise a model with score(s) corresponding to the user's capability for carrying out tasks associated with addressing the event. Additionally, notification content may be generated based on information about availability and the unaddressed event, and used to provide notification(s). The notification content may include a recommendation to present a notification to the user at a time determined likely to be convenient for the user to be notified of the event or where the user likely has capacity to address the event appropriately.