Abstract: Embodiments are disclosed for a method. The method includes receiving an annotation set for a machine learning model. The annotation set includes multiple data points relevant to a task for the machine learning model. The method also includes determining total weights corresponding to the data points. The total weights are determined based on multiple ordering constraints indicating multiple data classes and corresponding weights. The corresponding weights represent a relative priority of the data classes with respect to each other. The method further includes generating an ordered annotation set from the annotation set. The ordered annotation set includes the data points in a sequence based on the determined total weights.

Abstract: Provided is a method, computer program product, and system for automatically assigning robotic devices to users based on need using predictive analytics. A processor may monitor activities performed by one or more users. The processor may determine, based on the monitoring, a set of activities that require assistance from a robotic device when being performed by the one or more users. The processor may match the set of activities to a set of capabilities related to a plurality of robotic devices. The processor may identify, based on the matching, a first robotic device that is capable of assisting the one or more users in performing a first activity of the set of activities. The processor may deploy the first robotic device to assist the one or more users in performing the first activity.

Abstract: A first device may provide, via a global digital twin of the first device, a communication mode assignment, of a communication mode, to a local digital twin of a second device. The communication mode assignment is to cause the local digital twin to communicate with the global digital twin via the communication mode. The first device may generate, via the global digital twin, a task assignment, and may provide, via the global digital, the task assignment to the local digital twin. The first device may update, via the global digital twin, a model based on the task assignment, and may receive, via the global digital twin and from the local digital twin, a model update associated with the local digital twin. The first device may update, via the global digital twin, the model based on the model update.

Abstract: A method for detection of a corrupted sensor including providing a first sensor; identifying one or more correlating sensors to the first sensor; determining a correlation between the first sensor and the correlating sensors according to historical sensor values; obtaining a calculated value of the first sensor based on values of the correlating sensors and the correlation; obtaining a measured value of the first sensor; and determining whether the first sensor is corrupted according to a difference between the calculated value and the measured value of the first sensor.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: training of a machine learning model for predicting a rating in certain content rating systems based on training data. The machine learning model includes a plurality of maturity classifiers corresponding to individual features of the previously rated contents. An input content is obtained and features of the input content are extracted by use of respective content analysis tools and subsequently classified by the maturity classifiers of the machine learning model.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: predicting an exhibited sentiment of a certain user on being presented one or more candidate education segment, wherein the predicting is in dependence on historical sentiment parameter values of one or more user on being exposed to presented educational content, the historical sentiment parameter values being stored in a data repository, wherein the presented education segments comprise digital media content adapted for playing by a digital media player; selecting at least one of the one or more candidate education segment in dependence on a result of the predicting so that a selected at least one of the one or more candidate education resulting from the selecting is personalized for the certain user; and presenting to the certain user the selected at least one of the one or more candidate education segment.

Abstract: A method, a computer program product, and a system of dynamically managing permissions of storage blocks. The method includes predicting at least one storage block that will be accessed by a user on a storage device and predicting a time window when the storage block will be accessed the user. The predictions can be performed by a machine learning model trained using the historical accesses and access times of the user. The method also includes granting the user an access to the storage block during the time window and monitoring whether the storage block is accessed by the user. The method also includes determining, based on the monitoring, that the user accessed the storage block, and revoking the access to the storage block granted to the user after a predetermined access time.

Abstract: In some implementations, a digital twin system may receive, from one or more sensors and at an interface associated with a digital twin, a first input associated with a first event. The digital twin system may determine that the first event is associated with one or more probable second events. Accordingly, the digital twin system may refrain from processing the first input for a period of time. The digital twin system may further update a prediction associated with the digital twin using the first input based on expiry of the period of time or may update a prediction associated with the digital twin using second input associated with the one or more probable second events based on receiving the second input.

Abstract: A method and system for cloud distributed hybrid data storage and normalization are disclosed. The method may include obtaining a data set comprising data entities. A data entity may comprise data fields each containing a data element. The method may further include determining policy constraint meta-data for each of the data elements based on the storage policy constraint. The policy constraint meta-data may include a first meta-tag indicating the storage policy constraint for the data element. The method may further include determining whether a server satisfies the storage policy constraint based on the first meta-tag for the data element. When the server satisfies the storage policy constraint, the method may further include transmitting the data element to the server to store the data element on the server. When the server fails to satisfy the storage policy constraint, the method may further include, storing the data element on the client.

Abstract: A device may generate a knowledge model based on a knowledge model schema, data residency constraints, and a data classification ontology associated with a cloud application, and may perform a dynamic flow analysis of the cloud application data and the data source identifiers to generate a data flow graph. The device may process the data flow graph, with the knowledge model, to determine sensitive attributes in the data flow graph, and may identify sensitive data sources that include the sensitive attributes and sensitive assets based on the data flow graph and the sensitive data sources. The device may process the sensitive data sources and the sensitive assets, with a machine learning model, to determine methods for identifying misconfigurations, and may utilize the methods to identify misconfigurations and severities of the misconfigurations. The device may generate remediation actions for correcting the cloud application based on the severities of the misconfigurations.

Abstract: The present disclosure provides systems and methods supporting dynamic migration of jobs (e.g., workloads, containers, service requests, etc.) between execution environments. The disclosed systems and methods may utilize monitoring techniques to determine when a migration should occur and/or forecasting techniques to predict optimal times when a migration should occur. Upon determining a migration should occur, a target execution environment for a job may be identified and a migration process may be initiated. In some aspects, the migration may be performed partway through processing of the job and the migration may resume processing the job after the migration is completed in a manner that enables the processing to resume at the point where processing stopped prior to the migration.

Abstract: Systems and methods supporting discovery and quantification of vulnerabilities in software code are disclosed. The systems and methods provide functionality for using software code analysis and other types of tools to analyze the software code and determine whether it can be trusted. The software code tools may be able to discover various hidden issues in the software code and the outputs of such tools may be normalized to quantify the risk associated with vulnerabilities identified by the different tools. A labeling strategy is provided to label the software code to enable users to identify the best software among various available software options based on the label(s) and a set of criteria.

Abstract: Embodiments can include receiving, by a data processing system, digital teaching content monitoring, by the data processing system, user gaze of the digital teaching content.

Abstract: Digital teaching content ordering includes receiving, by a data processing system, digital teaching content and any corresponding annotations and content heuristic(s) from a teacher or other presenter, the digital teaching content including text and/or image(s). The data processing system monitors student gaze of the digital teaching content during a class and can cognitively skip some of the digital teaching content during the class based on the monitored student gaze and content heuristic(s). The system can also cognitively modify the digital teaching content outside of class based, in part, on the monitoring and the content heuristic(s). A hypergraph of the digital teaching content may also be received, the cognitively skipping being further based on the hypergraph, and the cognitively modifying being further based on a heat map built using the hypergraph and the student gaze.

Abstract: One or more computer processors determine a storage strategy for each chunked data block in a training dataset based on a respective computed usefulness score and a series of usefulness thresholds, wherein the storage strategy comprises RAID strategies that include striping, mirroring, parity, and double parity. The one or more computer processors distribute each data block in the training dataset according to the respective determined storage strategy.

Abstract: An embodiment of the invention may include a method, computer program product and system for deployment of microservices within a shared pool of configurable computing resources. An embodiment may include creating a dependency map for a plurality of microservices of an application deployed on the shared pool of configurable computing resources. An embodiment may include identifying attributes, with associated values, for each microservice of the plurality of microservices and identifying eligible deployment locations within the shared pool of configurable computing resources. An embodiment may include creating a bipartite graph based on the plurality of microservices and the identified eligible deployment locations. An embodiment may include applying bipartite matching to the shared pool of configurable computing resources based on the created bipartite graph.

Abstract: A system and method is provided to selectively process and store tables of a relational database by calculating an overall data sensitivity score for each table based on predefined attribute rules; performing column-wise splitting of at least one of the tables into a first table and a second table based on the overall data sensitivity score of each table, thereby generating a total number of relational database tables; storing a first subset of the total number of relational database tables in a private cloud storage database in a distributed storage environment based on the overall data sensitivity scores of each of the total number of relational database tables; and storing a second subset of the total number of relational database tables in a public cloud storage database of the distributed storage environment based on the overall data sensitivity scores of each of the total number of relational database tables.

Abstract: Aspects of the present invention provide an approach for reducing bias in active learning. In an embodiment, a data point is selected from a training dataset for a current training iteration while monitoring for data bias at each addition of data to a virtual training dataset. In addition, a machine learning model is examined for bias after adding the selected data point to the virtual training dataset. When data bias and/or model bias is detected, the data point is considered for potential label modification. The selected data point is modified and, if the raw value of the modified data point is within a predefined tolerance and within a bin of a desired class, the modified data point having a label of the target class is retained. Otherwise, it can be discarded.

Abstract: Aspects of the present invention disclose a method, computer program product, and system for management and usage of shared authentication credentials. The method includes one or more processors updating usage information associated with an authentication credential with a media access control address (MAC address) that corresponds to a computing device that corresponds to using the authentication credential. The method further includes one or more processors receiving a login request that includes the authentication credential from a computing device. The method further includes one or more processors fetching a MAC address of the computing device that sent the login request. The method further includes one or more processors validating the authentication credentials and the MAC address.

Abstract: One embodiment of the invention provides a method of training a chatbot. The method comprises identifying one or more chat logs that exhibit a trait. The method further comprises identifying one or more labels associated with the trait based on the one or more chat logs. The method further comprises training the chatbot to generate a response that models the trait based on the one or more chat logs. The method further comprises labeling the chatbot with the one or more labels.