International Business Machines Corporation

Kyndryl, Inc.

Mary E Rudden

Craig M Trim

Rhonda L Childress

Arun Balasubramanyan

Aaron K Baughman

Daniel S Riley

Thanh V Lam

Bernard Freund

Jeremy R Fox

Shikhar Kwatra

Michael Bender

Karen Cheng

Yuntao Liu

Pamela K Prinz

Timothy J Forshee-Lee

Martin G Keen

Mauro Marzorati

Dennis Anthony Perpetua, Jr

Stefan A G Van Der Stockt

Leo Kluger

Donald Eugene Schaefer

William G Dusch

Augustina Monica Ragwitz

John A Tobasco

Sarbajit Kumar Rakshit

John Michael Ganci, Jr

Hernan A Cunico

Raghuveer Prasad Nagar

Sarah K Czaplewski-Campbell

Adam Lee Griffin

Munish Goyal

Gray Franklin Cannon

Melissa K Miller

Ahmed M Nassar

Reji Jose

Rebecca Nadeau Morones

Abhishek Basu

Aman Buttan

Anthony Stevens

Christopher D Scott

Stacey Heeley Ronaghan

Venkatesh A R Rao

From an unstructured content using an ontology, a forward materialization graph is generated. The forward materialization graph is converted to a set of vector representations comprising multidimensional numbers representing elements of the forward materialization graph. A set of inference paths is computed for the set of vector representations. An inference path in the set of inference paths connecting a first vector representation with a second vector representation. Based on a set of features, the set of vector representations is formed into clusters, a feature in the set of features comprising a relevance probability, the relevance probability corresponding to a relevance of a portion of the unstructured content according to a relevance metric. A structured representation of the unstructured content is placed at an edge location of a content delivery network determined using the set of clusters.

Phrase based unstructured content parsing

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.

Automated transitive read-behind analysis in big data toxicology

Data security across data residency restriction boundaries is provided by obtaining and 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, then automatically generating a container image based on the profile level and the data residency restrictions that restrict the transfer of the dataset across the boundary, the container image configured for instantiation and execution to process the dataset into a reformatted dataset not restricted by the data residency restrictions for transfer across the boundary, and storing the container image to a container registry.

Data security across data residency restriction boundaries

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.

Feature engineering in neural networks optimization

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.

Predictive forecasting of food allocation

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.

Automated resolution of over and under-specification in a knowledge graph

An embodiment includes identifying metadata attached to a first node of a graph, where the metadata satisfies an ontological condition. The embodiment also includes transforming the graph such that the transforming results in the graph having a new graph structure, where the transforming of the graph comprises removing the metadata from the first node and adding a second node representative of the metadata removed from the first node to the graph such that the second node is connected to the first node by a first edge.

Metadata decomposition for graph transformation

A computer-implemented method for generating a description of a target skill set using domain specific language, a computer program product, and a system. Embodiments may comprise, on a processor, ingesting a data set related to the target skill from a data store, semantically analyzing the data set to generate a skill ontology, generating a hyperplane to separate one or more priority skills from among the plurality of related skills, generating a description for the target skill from the one or more priority skills, and presenting the generated description to a user. The skill ontology may include relationships between the target skill and a plurality of related skills.

Hyperplane optimization in high dimensional ontology

A method of analyzing one or more asset repositories to determine a developer's competency and ability to collaborate in a team environment. The method includes obtaining metadata artifacts as documents from one or more asset repositories. The documents are represented using a tree structure that has nodes to form a knowledge graph that is suitable for input vectorization. Each node is configured in the tree structure to represent a content region within the one or more documents, with a root node representing the entire document and each node representing an aggregation of all its children nodes. One or more computing devices are used to receive an input vector that includes a set of descriptive statistics about data in asset repositories and a vectorized form of one or more concepts. The developer's competency and ability to collaborate in a team environment is automatically estimated using output values of a trained neural network.

System and method for analysis of workplace churn and replacement

By analyzing video, audio, and statistical data of a real-world activity, a real-world scenario is identified that is within a threshold similarity of the analyzed video, audio, and statistical data of the real-world activity. The real-world scenario is applied to a game application that uses the real-world activity as a data source, the applying comprising adjusting a portion of a physics engine, the physics engine simulating a physical phenomenon portrayed in the game application.

Real-world activity simulation augmentation with real-world data of the activity

Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises generating a context-based query through based on a received input; finding a result of the generated query using link prediction algorithm coupled with link prefetching algorithm; and generating a specific link that illustrates and matches the generated context-based query.

Context based URL resource prediction and delivery

By executing a natural language processing model on a set of natural language text describing a first engagement, a set of characteristics of the first engagement is generated. By executing the natural language processing model on a set of natural language text describing a future engagement, a set of characteristics of the future engagement is generated. The first engagement is determined to be above a threshold similarity with the future engagement. Using the skillset used in performing the first engagement, a required skillset of the future engagement is forecasted. By executing the natural language processing model on a set of natural language text describing a current skillset, a set of characteristics of the current skillset is generated. Using the required skillset of the future engagement and the set of characteristics of the current skillset, a learning path is generated.

Identifying related messages in a natural language interaction

Growing community of inventors

Denver, CO, United States of America

Mary E Rudden