Abstract: Intelligent agents (IA) for automatically generating responses to content within a communication session (CS) are disclosed. An IA is trained to target the responses to a user and the user's context within the CS. An IA receives CS content that includes natural language expressions encoding users' conversations and determines content features based on natural language models. The content features indicate intended semantics of the expressions. The IA identifies likely-relevant content to the targeted user, to generate a response for. Identifying such content includes determining a relevance of the content based on content features, a context of the CS, a user-interest model, and a content-relevance model. Identifying the likely-relevant content to respond to is based on the determined relevance of the content and relevance thresholds. Various responses to the identified portions of the content are automatically generated and provided based on a natural language response-generation model targeted to the user.

Abstract: Implementations described herein disclose an informed join recommendation system that allows users to make informed decision about joining various information sources such as a feed, an application, a group, a blog, a news source, etc., based on an activity grade of the information sources. The informed join recommendation system analyzes information dissemination activity of information sources over a predetermined time period to determine an activity grade of the information source, and in response to the request from a user to join the information source, provides the user the activity grade of the information source.

Abstract: One or more techniques and/or systems are provided for constructing a complementary calendar and/or a shadow calendar. A user may maintain a primary calendar within which the user may schedule user specified tasks and/or meetings, but may inadvertently omit other entries. Accordingly, a complementary calendar may be constructed based upon inferences derived from user signal data (e.g., information used to identify/infer activities of the user, such as social network profile information, messages, temporal information, locational information, documents, etc.). The complementary calendar may be automatically populated with entries corresponding to inferences derived from user signals and/or real-time conditions (e.g., weather, store hours, traffic conditions, etc.). The primary calendar and the complementary calendar may be merged to create a shadow calendar.

Abstract: Implementations described herein disclose a road hazard detection method including receiving a plurality of mobile device sensor signals from one or more sensors located on a mobile device within a vehicle, determining the road hazard encountered by the vehicle by analyzing the plurality of mobile device sensor signals, and reporting the existence of the road hazard to other users. In one implementation, the road hazard detection method also uses sensor signals from various sensors located on the vehicle and/or sensor signals from mobile devices of users on other vehicles to determine the road hazard.

Abstract: One or more techniques and/or systems are provided for constructing a complementary calendar and/or a shadow calendar. A user may maintain a primary calendar within which the user may schedule user specified tasks and/or meetings, but may inadvertently omit other entries. Accordingly, a complementary calendar may be constructed based upon inferences derived from user signal data (e.g., information used to identify/infer activities of the user, such as social network profile information, messages, temporal information, locational information, documents, etc.). The complementary calendar may be automatically populated with entries corresponding to inferences derived from user signals and/or real-time conditions (e.g., weather, store hours, traffic conditions, etc.). The primary calendar and the complementary calendar may be merged to create a shadow calendar.

Abstract: In various implementations, routing factors are identified based on a routing request associated with a user, where the routing factors include route preferences of the user. Routes are generated based on the routing request. Preference weights are determined for the route preferences, where the preference weights correspond to machine learning models based on sensor data provided by one or more sensors in association with the user. Route scores are determined for the routes based on the preference weights. A suggested route is provided to a user device associated with the user, where the suggested route corresponds to a selected route of the routes and is provided based on the route score of the selected route.

Abstract: A wearable electronic device is capable of changing its appearance or physical characteristics or creating output that is entertaining or useful to the user. An inference engine collects context data inputs from a variety of source to output new inferred insights to update a persistent inferred state describing the situational context of the user. A situational context predictor accepts data sensed from the wearable device and/or environmental data to predict a situational context that is likely to describe the user's current situational context. A controller transmits control commands to the wearable electronic device to cause the wearable electronic device to provide services or to change it appearance or physical characteristics based on the inferred insights.

Abstract: A computer-implemented technique is described herein by which a first user can forward notification information to one or more other users, including a second user. The first user can interact with the notification information via a first computing device, while the second user can interact with the notification information using a second computing device. In some implementations, both the first computing device and the second computing device have access to an application which has generated the notification information or to which the notification information otherwise pertains. In other implementations, the second computing device may lack access to the application. In some implementations, the first user receives the notification information and then explicitly and manually controls the forwarding of the notification information (or a version of the notification information) to the second user.

Abstract: A logical location of a user may be inferred using semantics of the user's computing device(s). The logical locations may correspond to venues visited by the user, such as frequently visited venues, referred to as hubs. Logical hubs, representing logical locations, may be tagged to the computing device by classifying the device as being associated with a logical hub. Classification may be based on signals or features of the device, such as device usage or device characteristics. The device may be monitored to detect user activity. Based on analysis of the user activity and associated logical hub, the user's logical location may be inferred. A computer user-experience may be personalized to the user based on the user's inferred logical location or logical hub(s) associated with the device. In some cases, geographical location information is not used to determine the logical hubs or infer a user's logical location.

Abstract: Technology for interoperability is disclosed by enabling the sharing of user context or preferences for a computing experience across computing devices, operating systems, applications, or locations. A platform and application programming interface (API) are provided for computer applications and services to store and retrieve context data associated with a computing experience. Access to the context data for sharing may be managed by an access controller, which enables a user to manage access permissions for the sharing of the context data. The context data may be defined according to a common schema, which specifies the information for sharing and may be communicated using common communication channels or protocols. Thus context data may be shared across nearly any application or service including those developed in different computer programming languages or operating on different types of computing devices or devices running different operating systems or by different software developers.

Abstract: In various implementations, routing factors are identified based on a routing request associated with a user, where the routing factors include route preferences of the user. Routes are generated based on the routing request. Preference weights are determined for the route preferences, where the preference weights correspond to machine learning models based on sensor data provided by one or more sensors in association with the user. Route scores are determined for the routes based on the preference weights. A suggested route is provided to a user device associated with the user, where the suggested route corresponds to a selected route of the routes and is provided based on the route score of the selected route.

Abstract: Pooling computing resources based on inferences about a plurality of hardware devices. The method includes identifying inference information about the plurality of devices. The method further includes based on the inference information optimizing resource usage of the plurality of hardware devices.

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: 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 provide improved user experiences, such as personalization, modifying functionality of user devices, or providing more efficient consumption of bandwidth or power.

Abstract: A logical location of a user may be inferred using semantics of the user's computing device(s). The logical locations may correspond to venues visited by the user, such as frequently visited venues, referred to as hubs. Logical hubs, representing logical locations, may be tagged to the computing device by classifying the device as being associated with a logical hub. Classification may be based on signals or features of the device, such as device usage or device characteristics. The device may be monitored to detect user activity. Based on analysis of the user activity and associated logical hub, the user's logical location may be inferred. A computer user-experience may be personalized to the user based on the user's inferred logical location or logical hub(s) associated with the device. In some cases, geographical location information is not used to determine the logical hubs or infer a user's logical location.

Abstract: A most probable physical meeting location is provided to a user or third-party in response to receiving a subjective reference to the physical meeting location. A collection of physical meeting location values, or objective references to one or more physical meeting locations, are collected based at least in part on sensor data associated with the user. For each subjective reference to a physical meeting location, one or more location clusters comprising objective references to one or more physical meeting locations is generated. As a response to receiving the subjective reference to the physical meeting location, a probable meeting location generated based on cluster density associated with each of the one or more location clusters is provided to the user or third-party.

Abstract: Aspects of the technology described herein provide a personalized computing experience for a user based on a predicted future semantic location of the user. In particular, a likely future location (or sequences of future locations) for a user may be determined, including contextual information about the future location. Using information from the current context of the user's current location with historical observations about the user and expected user events, out-of-routine events, or other lasting or ephemeral information, a prediction of one or more future semantic locations and corresponding confidences may be determined and used for providing personalized computing services to the user. The prediction 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 prediction information by an application or service.

Abstract: Methods, computer systems, and computer storage media are provided for inferring sleep-related aspects for a user based, in part, on sensor data reflecting user activity detected by one or more sensors. In an embodiment, a user sleep model is trained using a dataset that includes previously-sensed data, descriptive information associated with the previously-sensed data, and/or interpretive data extracted from the previously-sensed data describing circumstances surrounding users when the data was acquired. In an embodiment, services providing time-sensitive recommendations personalized for a user's sleeping pattern using the inferred sleep-related aspects.

Abstract: Many devices are configured to present alerts notifying a user of device events, but the user may not notice the alert due to a noisy environment. A user may mitigate missed alerts by increasing the alert volume or choosing a vibration mode, but such techniques depend upon the knowledge, attention, and memory of the user to adjust the device before the alert. Instead, a device may compare the noise level of the environment with a noise level threshold. If the noise level is below the threshold, the device presents the alert; but if the noise level is above the threshold, the device defers the presentation of the alert until the noise level diminishes below the threshold, and then presents the alert. The device may also send an automated response to the message, notifying a sender that the user may return the message upon leaving the noisy environment.

Abstract: A user experience (UX) that enables viewing and identification of other people in the user network of friends, that received a group coupon, and the participation status of the friends. The UX enables the user to chat with the people in the user's network of friends about a specific coupon that was received, enables the creation of a group of friends and the adding of another friend with high density friendship of shared common interests and/or location based on specific offer content, enables granularity on a sub-group of friends based on joint interests, the controlled exposure to the user that received the group coupon offer, the identity of other users in his group that got this coupon offer, controlled exposure to the user that received the group coupon offer, the identity of other users in his group that committed to buy the coupon, and if the group will redeem the coupon.