Abstract: A method, system, and computer program product to prevent misinterpretation of communications via artificial intelligence assistants. The method includes monitoring an artificial intelligence enabled communication. The method also includes analyzing messages, participants, and actions within the communication. The method also includes identifying critical data within the communication. The method also includes determining critical sequence data, where the critical sequence data is a sequence of conversation elements that contains the critical data. The method also includes predicting an uncertainty level for the critical sequence data, where the uncertainty level indicates an amount of uncertainty that the artificial intelligence correctly interprets the critical sequence data. The method also includes determining that the uncertainty level for the critical sequence data is above a threshold uncertainty value, resulting in critical sequence data that is subject to misinterpretation.

Abstract: A method, computer system, and a computer program product for recommending additional content to an author generating authored content is provided. The present invention may include monitoring a travel location associated with the author. The present invention may include calculating a multi-sensory region based on the travel location and a maximum sense distance value. The present invention may include selecting at least one piece of additional content from a corpus of additional content based on the multi-sensory region. The present invention may include generating a model based on the at least one piece of additional content. The present invention may include selecting a relevant piece of additional content from the data model based on determining a topic associated with the relevant piece of additional content matches an authored topic associated with the authored content. The present invention may include presenting the selected relevant piece of additional content to the author.

Abstract: According to one embodiment, a method, computer system, and computer program product for managing medical events affecting a driver or passenger of a vehicle is provided. The present invention may include detecting, based on sensor data, a medical event affecting a driver of the vehicle; confirming, with a secondary decision maker, the medical event and one or more environmental changes to an internal environment of the vehicle based on the detected medical event; and executing the one or more environmental changes.

Abstract: Document discrepancy determination and mitigation can include marking a fragment of a first document and a corresponding fragment of a second document in response to determining a dependency between the first document and the second document. A discrepancy probability with respect to the first document and the second document can be identified based on a discrepancy measure, which can be determined by comparing the marking of the fragment of the first document and the marking of the corresponding fragment of the second document. One or more discrepancy mitigation procedures can be initiated in response to the discrepancy measure exceeding a predetermined threshold.

Abstract: Dynamic prioritization of an action item can include retrieving an electronically rendered text from one or more sampled text sources in response to recognizing a user-related task conveyed within the electronically rendered text. Dynamic prioritization of an action item can also include generating an action item corresponding to the user-related task and prioritizing the action item by assigning to the action item a priority computed based on one or more priority factors corresponding to the user-related task. Each of the one or more priority factors can be automatically selected from a collection of predetermined priority factors. Additionally, dynamic prioritization of an action item can include recomputing the priority assigned to the action item in response to a change in task-related circumstances, as determined based on other electronically rendered text.

Abstract: Presenting a lens-focused channel can include determining a state of a separate channel hosted on a data communications network. A topic-specific lens for federating a plurality of topic-specific messages conveyed over the data communications network can be configured in response to a predetermined condition indicated by the state of the channel. A lens-focused channel can be generated for presenting the plurality of topic-specific messages, as federated by the topic-specific lens, to a user over the data communications network.

Abstract: A method, a structure, and a computer system for location-driven social network boosting. The exemplary embodiments may include generating a network graph corresponding to a user of a social network and identifying a destined location of the user that differs from a current location of the user. The exemplary embodiments may further include identifying one or more gaps in the social network of the user at the destined location and augmenting the social network to fill the one or more gaps at the destined location.

Abstract: Disclosed are techniques to model when authoritative responses are expected to be received in real-time chat dialogues to facilitate monitoring a live real-time chat and connect a participant to provide an authoritative answer at an appropriate time during the live real-time chat. Historical real-time chat dialogues are used to generate a model for when authoritative responses are expected in real-time chats. A live real-time chat is monitored for an ongoing discussion without an authoritative response, and a response latency window of the model for the live real-time chat is adjusted based on the ongoing discussion in the live real-time chat. In some embodiments, upon entering an optimal window of the ongoing discussion of the live real-time chat indicated by the model where it is determined that no authoritative response is yet received, a new participant is connected to the live real-time chat to provide an authoritative response.

Abstract: A computer system monitors users to capture contextual and environmental data for managing adverse events of those users. A level of risk for occurrence of an adverse event from performing a medical related activity is determined based on the medical related activity, a medical profile, and a risk profile of the user. The user is monitored to capture environmental and contextual information for the adverse event. The captured information is stored to associate the captured information with the adverse event. In response to occurrence of the adverse event, the user is prompted to provide information pertaining to conditions surrounding the adverse event. The stored information for the adverse event is updated with the user-provided information, and is transmitted to a provider associated with the medical related activity. Embodiments of the present invention further include a method and program product for managing adverse events in substantially the same manner described above.

Abstract: One embodiment of the invention provides a method for data lineage and data provenance enhancement. The method comprises arranging a data set into a logical ordering, and partitioning the data set into at least one set of partitions based on the logical ordering. The method further comprises, for each partition of the at least one set of partitions, determining a corresponding score for the partition, and determining a data similarity between the partition and each other partition of each other data set based on the corresponding score for the partition and another score corresponding to the other partition. The method further comprises determining data lineage of the data set based on each data similarity determined.

Abstract: In an approach to longevity management of social network data, a computer detects a posting of a social artifact by a first user of a social network. A computer stores the social artifact with associated identification information. A computer stores activity associated with the social artifact by one or more other users. A computer detects a status change in an account associated with the first user, wherein the status change indicates the first user is not active in the social network. In response to detecting the status change, a computer determines a second user from the one or more other users to which to transfer the social artifact based on the social artifact, the associated identification information, and the activity associated with the social artifact by the one or more other users. A computer transfers the social artifact to an account associated with the second user on the social network.

Abstract: A computer-implemented system and method for a data leakage and misuse detection system comprises receiving an evaluation dataset A, and building a signature of the evaluation dataset A (sig(A)), where A signature of a dataset is a multi-level evaluation data abstraction representation of the dataset. The method further comprises building a signature for each of existing datasets B (B1, B2, . . . , Bn) (sig(Bx)) that are stored in a memory. The method then compares the sig(A) with each of the sig(Bx)s. A similarity score is derived based on the comparing, and responsive to determining the similarity score exceeds a predefined threshold, the method comprises generating an activity related to the determination.

Abstract: Methods, systems, and computer program products are provided. Details of a calendar item may be extracted. A conflict involving the calendar item and a second calendar item may be detected. Plural votes related to an importance of the calendar item may be received on behalf of a trusted crowd. When a vote is not received on behalf of a member of the trusted crowd within a certain time period, a prediction may be made regarding how the member of the trusted crowd would vote based on using machine learning to analyze a voting history of the member of the trusted crowd with respect to calendar items related to a subject of the calendar item. The predicted vote may be submitted on behalf of the member. One of the calendar item and the second calendar item may be altered based on a tally of the plural votes to resolve the conflict.

Abstract: A method, system and computer program product for transitioning between different realities. The distance of the objects from a reference point in the first and second reality environments is determined. For example, the distance of the object's location in the first reality environment from a reference point (e.g., camera system) as well as the distance of the object's location in the second reality environment from the reference point is determined. A determination is made as to whether the likelihood of a transition shock event (e.g., motion sickness) occurring as a user transitions between the first and second reality environments exceeds a threshold value. In response to the likelihood of the transition shock event occurring exceeding the threshold value, the distance of the object from the reference point in the first and/or second reality environments is modified so as to prevent users from experiencing transition shocks when transitioning between realities.

Abstract: A blockchain of transactions may be referenced for various purposes and may be later accessed by interested parties for ledger verification. One example operation may comprise one or more of identifying determining a shared file is being edited by one or more entities, identifying one or more changes to the shared file while the shared file is being edited, signing the one or more changes with one or more public keys, and adding the one or more changes to a blockchain.

Abstract: Interleaved conversation concept flow enhancement can include detecting a topic of an on-going conversation over an electronic communication system. In response to detecting a topic newly introduced into the on-going conversation, a topic-divergence metric (TDM) with respect to the original topic and the newly introduced topic can be determined. A topic-divergence response action can be initiated in response to the newly introduced topic diverging from the original topic by more than a predetermined threshold based on the TDM.

Abstract: A system determines a shape of incoming data, and determines, based on the shape, whether the data should be passed on to support answering a query. If the shape of the data suggests that the data is insufficient or may even be misleading, the system can gate the data or prompt for more.

Abstract: Conversation slipstream propagation can include using machine learning to construct a conversations graph representing conversations conducted over an electronic communications network by a plurality of participants and collected from one or more messaging platforms. A conversation slipstream comprising one or more communications extracted from the conversations can be generated in response to receiving a secondary communication over the electronic communications network. Each of the one or more communications extracted is represented by a sub-graph of the conversations graph, each sub-graph corresponding to a graph of the secondary communication. The conversation slipstream can be presented to at least one participant to the secondary communication.

Abstract: A computer system processes data requests using a data delivery queue. A query received from a client is processed to generate response data, wherein the response data is held in a queue prior to transmitting to the client. The response data in the queue is iteratively divided into a plurality of blocks, wherein each block of the plurality of blocks is compressed prior to transmitting to the client, and wherein a block size of a given block is determined based on an amount of time to compress and transmit a preceding block. The plurality of blocks are transmitted to the client. Embodiments of the present invention further include a method and program product for processing data requests using a data delivery queue in substantially the same manner described above.

Abstract: A method, a structure, and a computer system for engaging user contributions. The exemplary embodiments may include determining whether a detected message includes a need and, based on determining that the message includes the need, identifying one or more contributions a user can contribute to the need. The exemplary embodiments may further include augmenting a reply message with the one or more contributions.