Abstract: Systems and methods for contextual memory capture and recall are provided. The contextual memory capture and recall systems and methods help a user create, store, and recall memory information associated with an identified activity. The contextual memory capture and recall systems and methods are capable of identifying user activities where a memory inquiry may be desirable, creating a memory inquiry with a recommended memory action based on the activity, providing the memory inquiry to the user, and automatically linking an accepted memory action, along with any received memory information for the memory action, with the identified activity.

Abstract: Systems and methods for intelligent memory sharing and contextual retrieval across multiple devices and multiple applications are provided. The systems and methods do not just show a user what he or she has stored across his or her different devices but intelligently suggests relevant topics and/or information based on what is contained in a shared working memory compiled from the temporary memories on all of the user devices.

Abstract: An intelligent assistant leverages private data specific to users and data available publically on one or more networks to improve the functionality of devices used to present content. A user's actions in a content authoring application are observed by the intelligent assistant and used to predict the user's actions. The public data related to the content in the presentation are also used to augment the presentation and to suggest best practices in presenting the content. In some aspects, a “practice” presentation is given by the user to provide the intelligent assistant a baseline to which to assist the user in realtime comply with during a “live” presentation or to receive suggestions in how to improve the presentation prior to presenting it “live”.

Abstract: Systems and methods for creating and/or using an artificial intelligence memory system that models human memory are provided. The AI memory system creates and/or uses a user centric memory graph. The user centric memory graph implicitly links memory elements of a user utilizing relationships created in space, time, and cognitive dimensions similar to how the human brain stores and recalls different memory elements. The user centric memory graph is used by searching and/or constraining the user centric memory graph based on a determined user context and/or a user query.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for providing contextualized SMS data from one or more SMS messages to a client are presented. SMS data from SMS messages may be filtered and relevant information from the filtered SMS data may be extracted. The extracted information from the SMS data may be categorized into one or more contextual categories in a tiered contextual content hierarchy. The categorization of the SMS data may include analyzing world knowledge related to the extracted information and associating searchable context metadata with the categorized information. An indication to provide feedback related to the SMS data may be received and feedback related to the received SMS data may then be provided to the client.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for providing enriched location trail recall are presented. Location coordinates for a plurality of locations comprising a location trail may be received. The location trail may be enriched with user information and world knowledge. A request for a location-based recommendation may also be received. The request may be analyzed with a language-based model for ranking user intent and one or more constraints of the request may be evaluated. The one or more constraints may be evaluated against the enriched location trail data and a plurality of results for task completion may be filtered and ranked. The ranking may incorporate the enriched content for the location trail in categorizing the plurality of results.

Abstract: Providing cues from a personal digital assistant to a user. A method includes identifying at least one of a contextual condition or piece of personal information applying to a user. The method further includes, based on the at least one of a contextual condition or piece of personal information, identifying a cue indicating a computing action that the user can request be performed by the computing device. The method further includes providing to the user, at a computing device, the cue.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for assisting with task continuation and completion are provided. First data from a device received from a first context may be received. The first data may be ranked in a clustered intent index, the clustered index comprising a plurality of categorical hierarchies related to the first data. Second data from the device may be received from a second context, the second data providing an indication to assist with task continuation. The relevance of the second data to the clustered first data may be determined, the determining comprising evaluating extracted information from the second data with a threshold related to at least one of the plurality of categorical hierarchies. Content related to the first data may then be sent to the device.

Abstract: Automatic enrichment of a data collection with contextually relevant activity/intent suggestions for task completion is provided. The system extracts data from a data collection, identifies one or more intents associated with the data collection, structures the data collection into one or more meaningful groupings, and determines and provides contextually relevant suggestions for task completion for display in a user interface. The contextually relevant suggestions can be augmented in the data collection or surfaced at contextually relevant times on various output surfaces or on various computing devices.

Abstract: Intelligent capture, storage, and retrieval of information for task completion are provided. A user can explicitly request to capture information, or user information is implicitly captured from one or more data streams. Semantic understanding of captured information is provided, wherein offline processes are run that analyze captured information to bucket them into a set of pre-defined high value scenarios. Whenever a capture falls into such scenarios, additional structured information about the capture is extracted. Further, aspects provide for storing and indexing information in a data repository. Users are enabled to explicitly retrieve the stored information using a natural language interface, or stored information can be proactively provided to the user based on context to enable task completion.

Abstract: Aspects of the technology described herein can analyze user data from multiple computing devices to ascertain a user's energy level and detect anomalies. When an anomaly is detected, the technology described herein can make suggestions to increase the user's energy level. The suggestions can be generated by analyzing user data from the crowd to determine what worked for similarly situated users.

Abstract: Personalized experiences based on leisure interest identification are provided to a user. An enriched entity and attribute graph is created based on leisure entities or attributes extracted from digital data signals. The user data signals may include browser history, queries in searches, social media signals, or click data. Global data is utilized to crawl the enriched entity and attribute graph to infer entities or attributes. Based on the inferred entities or attributes, leisure suggestions can be ranked and provided to the user via a user device. Completion suggestions may additionally be provided to the user via the user device that enable the user to complete an activity associated with one or more of the leisure suggestions.

Abstract: Methods, systems, and computer-storage media for intelligently creating and using routing connections between on-premises servers within a client and nodes of a data center are provided. When routing connections being requested by the client are not presently established, a caching service within the data center is programmed to direct a client's cache request over available routing connections, thereby scaling out storage capacity across the data center. When routing connections being requested by the client are established, a load balancer within the data center is programmed to direct the cache request over a requested routing connection, thereby bypassing intervening hops within the data center, such as gateway nodes that host instances of the caching service. To bypass intervening hops, the client network is provided with access to a client-side routing table for identifying an appropriate network key and a connection table for identifying a routing connection mapped to the network key.

Abstract: Aspects of the technology described herein provide a more efficient user interface by providing coupons that are tailored to a specific user's interests. The coupons may be provided by a personal assistant or some other application running on a user's computing device. A goal of the technology described herein is to provide relevant coupons when the user can and actually wants to use them. The coupons are designed for goods or services the user intends to purchase.

Abstract: Various techniques for diagnostics, troubleshooting, and root-cause analysis are disclosed herein. In one embodiment, a method includes receiving operational data from a computing system and identifying an operational pattern based on the operational data. The operational pattern includes a temporal sequence of operations, events, or system states related to the computing system. The method also includes receiving an annotation and associating the received annotation with the identified operational pattern. The annotation identifies a reason, a cause, or a corrective suggestion corresponding to a violation of the temporal sequence.

Abstract: Aspects of the technology described herein provide a more efficient user interface by providing suggestions that are tailored to a specific user's interests. The suggestions may be provided by a personal assistant or some other application running on a user's computing device. A goal of the technology described herein is to provide relevant suggestions when the user can and actually wants to use them. The suggestions are designed to provide information or services the user wants to use.

Abstract: In one embodiment, a code analytic platform may use a novel combination of information retrieval and program analysis techniques to develop a code relationship graph 514 to perform various code applications, such as intent based searches on a source code set, the documentation of undocumented code, risk analyses, natural language semantic searches, and others. A source code analytics platform may perform a code analysis of a source code set 410. The source code analytics platform may perform a metadata analysis of a code production data set 430 associated with the source code set 410. The source code analytics platform may create a code relationship graph 514 associating the source code set 410 with a descriptive metadata set.

Abstract: Software debugging recommendation technique embodiments are presented that generally entails creating a database of characterized software bug descriptions and providing software debugging recommendations from the database in response to a query. This can employ a two-phased approach in the search for similar software bugs. The first is a search phase that takes a query as input and returns a ranked list of software bug descriptions that match the query. These bug descriptions can contain a mix of structured and unstructured data. The second phase is a related-information phase that uses the output of the first phase to retrieve a set of related recommendations such as for people, source files, functions and binaries.

Abstract: Gathering tenant usage data of server resources. A method includes a server in a cluster providing server resources for one or more tenants of the server. Data is stored in a local usage cache at the server. The data characterizes the resources provided to the one or more tenants of the server. At the server, data stored in the local usage cache is aggregated on a tenant basis, such that data is aggregated for given tenants. The aggregated data is sent to a distributed cache. At the server, aggregated data from other servers in the cluster is received from the distributed cache. The aggregated data from other servers in the cluster is globally aggregated and stored at an aggregated usage cache at the server in the globally aggregated form.

Abstract: In one embodiment, a code analytic platform may use a novel combination of information retrieval and program analysis techniques to develop a code relationship graph 514 to perform various code applications, such as intent based searches on a source code set, the documentation of undocumented code, risk analyses, natural language semantic searches, and others. A source code analytics platform may perform a code analysis of a source code set 410. The source code analytics platform may perform a metadata analysis of a code production data set 430 associated with the source code set 410. The source code analytics platform may create a code relationship graph 514 associating the source code set 410 with a descriptive metadata set.