Abstract: Smart information retrieval is provided via artificial intelligence. Content stored in documents in a database is accessed and contextual chunks of individual ones of the documents are identified, wherein the contextual chunks include portions of content stored in the individual ones of the documents. Embeddings associated with the contextual chunks are generated and stored in a vector database. A plurality of relationships are defined among at least some of the contextual chunks and generates relational embeddings using the plurality of identified relationships. The relational embeddings are stored in a database. A query is received for information associated with at least some of the content and an embedding representing the query is generated. The embedding representing the query is transmitted to at least one large language model, and a response including at least some of the contextual chunks is received. The response is transmitted to a device associated with the query.

Abstract: A method includes: in response to receiving opt-in consent from a student, obtaining, by a processor set, student data associated with the student; monitoring, by the processor set, performance of the student in a course using a predictive machine learning model that predicts a score in the course based on the student data; detecting, by the processor set, a negative trend in the performance of the student based on the monitoring; and in response to detecting the negative trend, matching, by the processor set, the student with a mentor for the course using a matching model.

Abstract: Methods, systems, and computer program products for automatically modifying communication content using artificial intelligence techniques are provided herein. A computer-implemented method includes identifying one or more portions of communication content within a group communication session to be modified by processing the communication content and one or more items of contextual information associated with the group communication session; generating at least one item of modified communication content related to at least a portion of the one or more identified portions of communication content by processing the one or more identified portions of communication content using one or more artificial intelligence techniques; and performing one or more automated actions based at least in part on the at least one item of modified communication content.

Abstract: A computer-implemented method for efficiently dispatching one or more autonomous vehicles to deliver medical supplies to a destination. The method determines a level of emergency and a disease condition at the destination via a user communication interface on the one or more autonomous vehicles. The method prioritizes dispatching the one or more autonomous vehicles based on the level of emergency and the disease condition at the destination. The method optimizes a route of the one or more autonomous vehicles to the destination. The method further integrates a plurality of available data sources across multiple locations, compares these data sources, and builds deep learning (DL) forecasting models to predict several different medicines required, corresponding to a distribution of the disease condition, across the multiple locations.

Abstract: Method, computer program product, and computer system are provided. Questions are extracted from a chat in real-time during an online meeting and are aggregated into groups of duplicate questions. The groups are presented to a subset of attendees whose question is in the group. Feedback is received and applied to the group from the subset of attendees. Whether a question is answerable is predicted. For answerable questions an amount of time to answer the question is predicted. The answerable questions are sequenced, filtered, prioritized, and presented to an attendee interface and a presenter interface.

Abstract: Method, computer program product, and computer system are provided. A model is trained, in real-time to identify likely duplicate questions. A level of duplication is identified between a question and a previously asked question in a meeting transcript. An asker is pointed to where in the meeting transcript the question was the previously asked. All duplicate questions are arranged in a single point question by topic. A new meeting transcript is generated and displayed to attendees, including each individual question and each single point question.

Abstract: Methods and systems for using machine learning to identify extremely rare events in high-dimensional space are disclosed. A method includes: identifying, by a computing device, a plurality of derived attributes using an external data source; selecting, by the computing device, a plurality of key performance indicators from the plurality of derived attributes using a neural network and based on an extremely rare event being modeled; constructing, by the computing device, a linear model using the plurality of key performance indicators; and predicting, by the computing device, occurrences of the extremely rare event using the linear model.

Abstract: Methods and systems for using machine learning to identify extremely rare events in high-dimensional space are disclosed. A method includes: identifying, by a computing device, a plurality of derived attributes using an external data source; selecting, by the computing device, a plurality of key performance indicators from the plurality of derived attributes using a neural network and based on an extremely rare event being modeled; constructing, by the computing device, a linear model using the plurality of key performance indicators; and predicting, by the computing device, occurrences of the extremely rare event using the linear model.

Abstract: In an approach for improving the virtual meeting user experience, a processor detects a user disengaging from a virtual meeting having at least two participants for a pre-set period of time or for a pre-set percentage of a total allotted time of a pre-scheduled virtual meeting. A processor retrieves data from a database. A processor prepares a summary that is tailored to a profile of the user and that covers a portion of the virtual meeting during which the user was disengaged. A processor detects the user reconnecting to the virtual meeting. A processor determines whether the user will review the summary before rejoining the virtual meeting. Responsive to determining the user will review the summary before rejoining the virtual meeting, a processor prompts the user with a set of default user preferences to review the summary. A processor outputs the summary to the user.

Abstract: A method including: analyzing, by a computing device, a plurality of portions of a document; determining, by the computing device and based on the analyzing, a concept of each of the portions of the document; comparing, by the computing device, a title of the document with the concept of each of the portions of the document; determining, by the computing device and based on the comparing, an alignment of the concept of each of the portions of the document with the title; generating, by the computing device and based on the alignment, a propensity score for each of the portions of the document; and reordering, by the computing device and based on the propensity scores, the portions of the document from most aligned with the title to least aligned with the title.

Abstract: In an approach for improving the virtual meeting user experience, a processor detects a user disengaging from a virtual meeting having at least two participants for a pre-set period of time or for a pre-set percentage of a total allotted time of a pre-scheduled virtual meeting. A processor retrieves data from a database. A processor prepares a summary that is tailored to a profile of the user and that covers a portion of the virtual meeting during which the user was disengaged. A processor detects the user reconnecting to the virtual meeting. A processor determines whether the user will review the summary before rejoining the virtual meeting. Responsive to determining the user will review the summary before rejoining the virtual meeting, a processor prompts the user with a set of default user preferences to review the summary. A processor outputs the summary to the user.

Abstract: A circuit for suppressing undesired sub-harmonics includes a plurality of mixers, wherein the plurality of mixers are connected in parallel; a plurality of local oscillator signals (LO), wherein each of the plurality of LOs is associated with one of the plurality of mixers; an input to receive a plurality of phases of a driving clock, wherein each of the plurality of phases is a sub-harmonic of the driving clock, and wherein each phase of the driving clock is distributed to one of the plurality of mixers; wherein the plurality of mixers are configured to suppress one or more of the plurality of phases of the driving clock and amplify a desired phase of the driving clock.

Abstract: Embodiments minimize downtime involved in moving a PDB between CDBs by allowing read-write access to the PDB through most of the moving operation, and by transparently forwarding connection requests, for the PDB, from the source CDB to the destination CDB. The files of a source PDB are copied from a source CDB to a destination CDB, during which the source PDB may be in read-write mode. The source PDB is then closed to write operations so that changes to the source PDB cease. Another round of recovery is performed on the PDB clone, which applies all changes that have been performed on the source PDB during the copy operation and the PDB clone is opened for read and write operations. Forwarding information is registered with the source location, which information is used to automatically forward connection requests, received at the source location for the moved PDB, to the destination location.

Abstract: A method including: analyzing, by a computing device, a plurality of portions of a document; determining, by the computing device and based on the analyzing, a concept of each of the portions of the document; comparing, by the computing device, a title of the document with the concept of each of the portions of the document; determining, by the computing device and based on the comparing, an alignment of the concept of each of the portions of the document with the title; generating, by the computing device and based on the alignment, a propensity score for each of the portions of the document; and reordering, by the computing device and based on the propensity scores, the portions of the document from most aligned with the title to least aligned with the title.

Abstract: Provided herein are data cloud administration techniques that achieve autonomy by using a rules engine that reacts to a database system event by autonomously submitting an asynchronous job to reconfigure a database. In an embodiment, a rules engine receives an event from a DBMS. Based on the event, the rules engine executes a rule to generate a request that indicates configuration details for a database. The rules engine sends the request to a request broker. The request broker dispatches an asynchronous job based on the request. The asynchronous job configures the database based on the configuration details. Thus, databases in a cloud, data grid, or data center may be administered autonomously (without human intervention) base on dynamic conditions that are foreseen and unforeseen.

Abstract: Provided herein are workload management techniques that asynchronously configure pluggable databases within a compute cloud. In an embodiment, the compute cloud receives an administrative request that indicates configuration details for a pluggable database. The compute cloud generates a configuration descriptor that specifies an asynchronous job based on the configuration details of the request. The compute cloud accesses hosting metadata to detect at least one of: a) a current container database that already hosts the pluggable database, b) a target container database that will host the pluggable database, or c) a particular computer that hosts at least one of: the current container database, or the target container database. The compute cloud executes the asynchronous job to configure the pluggable database based on at least one of: the hosting metadata, or the configuration descriptor.

Abstract: A method, computer system, and computer program product for dynamic digital channel journey analysis are provided. The embodiment may include obtaining information related to user page accesses and flows. The embodiment may also include creating a period graph for a measurement period. The embodiment may further include computing an initial yield leakage value for the measurement period. The embodiment may also include creating a temporal reference. The embodiment may further include updating the period graph based on the yield leakage value and the temporal reference. The embodiment may also include identifying a link where the yield leakage value is high and where the link leads to.

Abstract: Techniques are provided for using a sparse file to create a hot archive of a pluggable database of a container database. In an embodiment and while a source pluggable database is in service, a source database server creates a clone of the source pluggable database. Also while the source pluggable database is in service, the source database server creates an archive of the source pluggable database that is based on the clone. Eventually, a need arises to consume the archive. A target database server (which may also be the source database server) creates a target pluggable database based on the archive.

Abstract: Embodiments minimize downtime involved in moving a PDB between CDBs by allowing read-write access to the PDB through most of the moving operation, and by transparently forwarding connection requests, for the PDB, from the source CDB to the destination CDB. The files of a source PDB are copied from a source CDB to a destination CDB, during which the source PDB may be in read-write mode. The source PDB is then closed to write operations so that changes to the source PDB cease. Another round of recovery is performed on the PDB clone, which applies all changes that have been performed on the source PDB during the copy operation and the PDB clone is opened for read and write operations. Forwarding information is registered with the source location, which information is used to automatically forward connection requests, received at the source location for the moved PDB, to the destination location.

Abstract: Embodiments create a clone of a PDB while the PDB accepts write operations. While the PDB remains in read-write mode, the DBMS copies the data of the PDB and sends the data to a destination location. The DBMS performs data recovery on the PDB clone based on redo entries that record changes made to the source PDB while the DBMS copied the source PDB files. This data recovery makes all changes, to the PDB clone, that occurred to the source PDB during the copy operation. The redo information, on which the data recovery is based, is foreign to the PDB clone since the redo entries were recorded for a different PDB. In order to apply foreign redo information to perform recovery on the PDB clone, a DBMS managing the PDB clone maintains mapping information that maps PDB source reference information to corresponding information for the PDB clone.