International Business Machines Corporation

Marco Luca Sbodio

Natalia Mulligan

Joao H Bettencourt-Silva

Vanessa Lopez Garcia

Spyros Kotoulas

Pierpaolo Tommasi

Theodora Brisimi

Aris Gkoulalas-Divanis

Thanh Lam Hoang

Yufang Hou

Gabriele Picco

Martin Stephenson

Michele Berlingerio

Alessandra Pascale

Sebastian Lehrig

Natasha Mulligan

Vanessa Lopez

Larisa Shwartz

Stefano Braghin

Adi Ionel Botea

Anastasios Kementsietsidis

Akihiro Kishimoto

Radu Marinescu

Lam Nguyen

Dzung Tien Phan

Spyridon Antonatos

Seshu Tirupathi

Hiroshi Kajino

Francesco Calabrese

Michele Gazzetti

Inge Lise Vejsbjerg

Nagesh Yadav

Joao H Bettencourt Da Silva

Mattia Chiari

Caroline A O'Connor

Omar O'Sullivan

Denisa Claudia Moga

Giusy Di Lorenzo

Daniel Rejniak

James Shannon

The present inventive concept provides for a method for automated decision modelling from text including obtaining a text corpus including a policy. Terms and syntax are identified within the text corpus related to the policy. Sentence similarities and co-references based on the terms and syntax are identified. Discourse and sentence level semantic parsing is performed based on the terms and the sentence similarities and the co-references using machine learning. A decision model template is generated based on the discourse and semantic parsing, and the decision model template is transformed into an automated decision model.

Automated decision modelling from text

Embodiments are provided for providing predictive computing and data analytics for project management in a computing system by a processor. A lifecycle of each of a plurality of objects may be monitored based on data received from a plurality of data sources. Predictive analytics for project management of each of the plurality of objects may be provide based on monitoring the lifecycle of each of the plurality of objects.

Predictive computing and data analytics for project management

Embodiments are provided for unsupervised learning of domain specific knowledge graph from textual data and language generation from knowledge graph via reinforcement learning in a computing system by a processor. Unstructured data is automatically parsed into one or more knowledge graphs based on the unstructured data and a list of candidate relations using a first machine learning model. Text data is generated from the one or more knowledge graphs using a second machine learning model.

Providing a semantic encoding and language neural network

Embodiments for intelligent application scenario testing and error detection by a processor. One or more modified application scenarios may be automatically generated from an initial application scenario having configuration data and a plurality of operations relating to an error. The one or more modified application scenarios are variations of the initial application. The one or more modified application scenarios may be executed to detect the existence or non-existence of the error in the one or more modified application scenarios.

Intelligent application scenario testing and error detection

Embodiments for providing intelligent land use planning recommendations using heterogeneous temporal datasets in a computing environment. One or more positive land-use interventions, one or more negative land-use interventions, or a combination thereof may be recommended for a selected geographical region from heterogeneous chronological data.

Land use planning recommendations using heterogeneous temporal datasets

Embodiments for providing clinical practice guidelines by a processor. One or more clinical practice guidelines (CPGs) may be automatically generated according for one or more cohorts using evidence data and patient data from one or more data sources.

Providing clinical practical guidelines

Embodiments for providing an intelligent media data service in a computing environment by a processor. One or more sections of media data are identified and annotated (e.g., tagged) for a user based on a degree of relevancy between a user profile and the media data, wherein the media data include media classification, topic detection, speaker detection and noise detection. The one or more sections of media data are selected for the user based on the tagging of the or more sections.

Intelligent media data explorer

A system and method for analyzing and explaining the temporal evolution of policies. The analysis of the temporal evolution of policies includes determining semantically related changes in the text of the corresponding policies over time and across the different versions of the (two or more) policy documents. An explanation of the temporal evolution of policies is provided consisting of human interpretable information relating each change to one or more events and/or contextual data. A next steps policy change is also suggested that includes a set of policy conditions based on potential future changes of similar policies and contextual data and event data. The suggestions are related to the policy relevant to the target cohort or individual. The system adapts machine learned models by receiving user feedback provided on an analysis of the correctness of the temporal evolution of policies, corresponding explanations and suggestions of the next actions.

Analyzing and explaining a temporal evolution of policies and suggesting next steps

Systems, computer-implemented methods, and computer program products to facilitate contextual comparison of semantics in conditions of different policies are provided. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a comparison component that contextually compares semantics of conditions in policy data of different policies based on a feature of at least one entity. The computer executable components further comprise a contextualization component that employs a model to provide a contextual explanation of how a first condition in first policy data of a first policy is semantically different from a second condition in second policy data of a second policy based on the feature of the at least one entity.

Contextual comparison of semantics in conditions of different policies

Embodiments for intelligent collaborative generation or enhancement of useful medical actions to a user by a processor. One or more useful medical actions may be recommended, with evidence in support thereof, for positively impacting a health state of a user according to data relating to similar users. One or more of the recommended user medical actions may be matched to one or more selected portions of clinical practice guidelines (CPGs). The one or more of the recommended user medical actions may be added as an additional CPG or as an enhancement to one or more of the matching portions of the recommended user medical actions.

Intelligent collaborative generation or enhancement of useful medical actions

Embodiments for implementing intelligent ranking of sections of clinical practice guidelines by a processor. One or more clinical practice guidelines (CPGs) may be identified and analyzed. A score may be assigned to one or more sections of the CPGs according evidential data identified in one or more data sources. The one or more sections of the CPGs may be ranked according to the scoring.

Intelligent ranking of sections of clinical practical guidelines

A neural network is trained with patient historical data including features of patient pathways and labels characterizing a type of the patient pathways. During a runtime phase, the trained neural network matches a current patient profile with the patient historical data to extract selected portions of clinical practice guidelines (CPGs) identified according to one or more generated CPG models, the patient pathway models, and the current patient profile.

Intelligent identification of appropriate sections of clinical practical guideline

Embodiments are disclosed for a method. The method includes generating statistical models of circadian rhythms based on circadian rhythm data generated by mobile computing devices of occupants of a building having a building automation system. The method also includes identifying room occupants of a room disposed within the building. Additionally, the method includes determining ambient settings for an ambient system operated by the building automation system based on a subset of the statistical models, wherein the subset corresponds to the identified room occupants. The method further includes determining a trade-off ambient setting based on the ambient settings.

Determining ambient controls

Embodiments for intelligent generation of customized questions or questionnaires by a processor. One or more customized questions or questionnaires may be generated according to a user profile, similar profiles of alternative users, one or more historical interactions with the alternative users, one or more goals defined by a domain experts, domain knowledge, historical questions or questionnaires, or a combination thereof using a machine learning operation.

Growing community of inventors

Dublin, Ireland

Marco Luca Sbodio