Abstract: A method of deep learning from real world and digital exemplars includes determining, by one or more processors of a computer system, a style component of a digital environment of a game platform, combining, by the one or more processors of the computer system, the style component with content derived from a real world exemplar, morphing, by one or more processors of a computer system, the real world exemplar to an augmented digital exemplar of the game platform, and adapting, by the one or more processors of the computer system, at least one deep learning algorithm to accomplish at least one of the determining, combining and morphing.

Abstract: A transitive closure data structure is constructed for a pair of features represented in a vector space corresponding to an input dataset. The data structure includes a set of entries corresponding to a set of all possible paths between a first feature in the pair and a second feature in the pair in a graph of the vector space. The data structure is reduced by removing a subset of the set of entries such that only a single entry corresponding to a single path remains in the transitive closure data structure. A feature cross is formed from a cluster of features remaining in a reduced ontology graph resulting from the reducing the transitive closure data structure. A layer is configured in a neural network to represent the feature cross, which causes the neural network to produce a prediction that is within a defined accuracy relative to the dataset.

Abstract: In an approach for predictive forecasting of food allocation, a first data is received from one or more sensors. The amount and condition of available food is determined from the first data. The number and location of people is determined from the first data. The received data is modified to create a second data. One or more food requirements for the people are predicted based on the number and location of people and the second data. An optimal food allocation for the people is predicted based on the amount and condition of food available and the one or more food requirements. The optimal food allocation is reported.

Abstract: Systems and methods for automated resolution of over-specification and under-specification in a knowledge graph are disclosed. In embodiments, a method includes: determining, by a computing device, that a size of an object cluster of a knowledge graph meets a threshold value indicating under-specification of a knowledge base of the knowledge graph; determining, by the computing device, sub-classes for objects of the knowledge graph; re-initializing, by the computing device, the knowledge graph based on the sub-classes to generate a refined knowledge graph, wherein the size of the object cluster is reduced in the refined knowledge graph; and generating, by the computing device, an output based on information determined from the refined knowledge graph.

Abstract: Techniques for probabilistic analysis of chemicals are provided. An indication of a proposed chemical composition is received. A predicted toxicity score is generated for the proposed chemical composition by performing probabilistic analysis on the proposed chemical composition. The probabilistic analysis includes identifying, based on a knowledge graph, at least one similar composition that is structurally similar to the proposed chemical composition. The analysis also includes identifying a set of chemical reactions that include the at least one similar composition, and determining one or more products of the identified set of chemical reactions. The probabilistic analysis further includes determining a toxicity of at least one of the one or more products. Finally, the predicted toxicity score is returned.

Abstract: Systems and methods for displaying an image on an image-enabled clothing article are disclosed. A method that can be used with the systems include determining, by a computing device, that at least a first advertisement and a second advertisement are acceptable for a participant. The computing device sends an option to select one of the first advertisement and second advertisement to a participant computing device via a computer network, wherein the option including payment terms for each of the first advertisement and second advertisement. The computing device also receives an indication from the participant computing device of a selected advertisement via the computer network, and sends instructions to the participant computing device to display the selected advertisement on an image-enabled clothing article of the participant via the computer network.

Abstract: A computer-implemented method includes: receiving, by a computing device, a container from a data requester server for processing data as part of an inference analysis; attaching, by the computing device, an input data volume and an output data volume associated with the container; processing, by the computing device, input data stored in the input data volume to produce output data; attaching, by the computing device, the output data in the output data volume; detaching, by the computing device, the input data volume based on attaching the output data to the output data volume; determining, by the computing device, whether sensitive data exists in the output data volume; and providing, by the computing device, the output data volume to the data requester server based on the determining that sensitive data does not exist in the output data volume.

Abstract: A method of deep learning from real world and digital exemplars includes determining, by one or more processors of a computer system, a style component of a digital environment of a game platform, combining, by the one or more processors of the computer system, the style component with content derived from a real world exemplar, morphing, by one or more processors of a computer system, the real world exemplar to an augmented digital exemplar of the game platform, and adapting, by the one or more processors of the computer system, at least one deep learning algorithm to accomplish at least one of the determining, combining and morphing.

Abstract: Identifying private information and preventing privacy violations is provided by a process that evaluates digital information obtained by an organization as part of a digital information stream from a user. The evaluating identifies a user utterance, including keyword(s), entity/ies, and intent(s), and applies natural language understanding to the digital information to ascertain a contextual understanding for the user utterance. The process selects training set(s) of historical information from available training sets that includes vocabulary used in varying contexts. The process compares the identified user utterance to an ontology based on the selected training set(s), and determines a confidence level that the digital information includes digital private information. The process also flags for the organization an action to take with respect to handling of the digital information. The flagging is based on the determined confidence level that the digital information includes digital private information.

Abstract: Data security across data residency restriction boundaries is provided by profiling a dataset on which a desired analysis is to be performed, with some results of the desired analysis to be transferred from one location to another, the dataset subject to data residency restrictions that restrict transfer of the dataset across a boundary to the another location, and the profiling identifying a profile level for the dataset, automatically generating, based on the profile level and the data residency restrictions that restrict the transfer of the dataset across the boundary, a container for processing the dataset into a reformatted dataset not restricted by the data residency restrictions for transfer across the boundary, instantiating the generated container on a data processing system at the one location, and processing the dataset into the reformatted dataset using the instantiated generated container, and transferring the reformatted dataset to the another location.

Abstract: Systems and methods for dynamic camouflaging are disclosed. A computer-implemented method can be used with the system including determining, by a computing device, if current environment image data is available for a location of one or more users, and instructing, by the computing device, at least one image-enabled clothing system of the one or more users to display a camouflage image based on the determining. The camouflage image is based on the current environment image data when the current environment image data is available, and the camouflage image is based on historic image data associated with the location of the one or more users when the current environment image data is not available.

Abstract: Systems and methods for dynamic camouflaging are disclosed. A computer-implemented method can be used with the system including determining, by a computing device, if current environment image data is available for a location of one or more users, and instructing, by the computing device, at least one image-enabled clothing system of the one or more users to display a camouflage image based on the determining. The camouflage image is based on the current environment image data when the current environment image data is available, and the camouflage image is based on historic image data associated with the location of the one or more users when the current environment image data is not available.

Abstract: Aspects of the present invention manage event metrics as a function of service management analytics. In response to determining that a version of record associated with a service level management agreement should be saved (versioned), aspects capture the presence of reference attributes of the record, and summarize and aggregate values of organizing dimensions of the reference attributes of each of a plurality of records that includes the versioned record. Aspects generate a snapshot that comprises a subset of the summarized and aggregated, final values of the organizing dimensions of the reference attributes that are selected as having values that are associated with an event occurrence, and attach the summarized and aggregated values of the organizing dimensions of to the snapshot.

Abstract: A method and system for managing queries in business intelligence platforms. It is determined that at least one requirement to complete a first query exceeds a threshold and in response, a redacted report failing to exceed the threshold is generated. The first query requests data from at least one business intelligence content from a first geographical region. In response to detecting a rejection, by a user, of the redacted report after the user had been prompted, to accept or reject the redacted report: (i) the first query is converted to a second query configured to be used by an Extract, Transform, and Load (ETL) program from a second geographical region; and (ii) a report responsive to the first query is generated.

Abstract: A method is provided for managing queries in business intelligence platforms. The method includes receiving, by a processor, a first query requesting data from at least one business intelligence content, the first query having a first format. The method further includes determining, by the processor, at least one requirement to complete the first query. The method further includes converting, by the processor, the first query to a second query configured to be used by an Extract, Transform, and Load (ETL) program, in response to determining that the at least one requirement exceeds a threshold, the second query having a second format.

Abstract: A method of managing event metrics for service management analytics. The method includes: determining, by a computer processor, whether a record associated with service level management needs to be versioned based on metric metadata; if so, capturing, by the computer processor, present state of the record; versioning, by the computer processor, the captured present state of the record; summarizing and aggregating, by the computer processor, the versioned record; generating, by the computer processor, snapshots of the summarized and aggregated records; and attaching, by the computer processor, reference attributes to the snapshots.

Abstract: Embodiments of the present invention disclose a method, computer program product, and system for user interface customization. A computer records activity of a first computer on a user interface. The computer determines one or more repetitive activities of the first computer utilizing the recorded activity of the first computer. The computer determines a customized user interface for the first computer corresponding to the one or more repetitive activities of the first computer. In another embodiment, the computer initiates display of the customized user interface to the first computer. In another embodiment, the recorded activity of the first computer includes navigation through links in the user interface, applying filters to data in the user interface, and accessing data on the user interface.

Abstract: A method is provided for managing queries in business intelligence platforms. The method includes receiving, by a processor, a first query requesting data from at least one business intelligence content, the first query having a first format. The method further includes determining, by the processor, at least one requirement to complete the first query. The method further includes converting, by the processor, the first query to a second query configured to be used by an Extract, Transform, and Load (ETL) program, in response to determining that the at least one requirement exceeds a threshold, the second query having a second format.

Abstract: A method, system and program product for using access-control lists to control access to categorized computer files. Two or more computer files are each associated with one of a set of possible classifications that fall within a single category and an access-control list associates a user with a subset of these classifications. In response to the user's request for access to one of these files, where the request specifies the requested file but does not specify the category of the requested file, the processor identifies the requested file's category based on that file's associated classifications, checks the access-control list to determine that the user is authorized to access files of the identified category, and then grants the requesting user access to the requested file.

Abstract: Embodiments of the present invention disclose a method, computer program product, and system for user interface customization. A computer records activity of a first computer on a user interface. The computer determines one or more repetitive activities of the first computer utilizing the recorded activity of the first computer. The computer determines a customized user interface for the first computer corresponding to the one or more repetitive activities of the first computer. In another embodiment, the computer initiates display of the customized user interface to the first computer. In another embodiment, the recorded activity of the first computer includes navigation through links in the user interface, applying filters to data in the user interface, and accessing data on the user interface.