Abstract: A computer-implemented method, system and computer program product for generating a user interface. A sketch (e.g., wireframe) of a portion of a user interface is received. The sketch is analyzed to predict a set of intended sketches using artificial intelligence based on historical data and/or the user's asset library. A set of intended final sketch renderings of the user interface is then generated and displayed using the set of predicted intended sketches based on historical data or a model trained to extract visual characteristics from existing user interface screens. If the user selects one of the intended final sketch renderings of the user interface as being directed to the intended design of the user interface and indicates that the selected intended final sketch rendering of the user interface corresponds to the final intended design, then code is generated to render the selected final sketch rendering of the user interface.

Abstract: One embodiment provides automatically learning shared resource environment solution design rules from a collection of requirement-solution pairs including obtaining requirement-solution pairs for a shared resource environment from a data store. A processor iteratively generates a candidate design rule set from each requirement-solution pair. Each generating iteration uses an input including the candidate design rule set output from a previous generating iteration. Evidence scores of each candidate design rule are calculated and candidate design rules having higher evidence score than an evidence score threshold are retained to obtain a learned design rule set. Candidate rules of a next iteration are constructed based on an addition of new attributes to rules of the learned design rule set.

Abstract: A computer-implemented method according to one embodiment includes receiving input data for a plurality of entities and locations; defining constraints for a group-based allocation model; mapping a distance matrix to a plurality of distance levels to obtain a distance-level formulation; defining a group-level objective function for the group-based allocation model; applying the distance-level formulation to the group-level objective function; solving the group-based allocation model to obtain a group-level assignment; and mapping the group-level assignment to an entity-level assignment.

Abstract: One embodiment provides a method comprising receiving training data and experts' intuition, training a machine learning model based on the training data, predicting a class label for a new data input based on the machine learning model, estimating a degree of similarity of a target attribute of the new data input relative to the training data, and selectively applying a correction to the class label for the new data input based on the degree of similarity prior to providing the class label as an output. The target attribute is an attribute related to the experts' intuition.

Abstract: Embodiments provide a computer implemented method of evaluating one or more IR systems, the method including: providing, by a processor, a pre-indexed knowledge-based document to a pre-trained sentence identification model; identifying, by the sentence identification model, a predetermined number of query-worthy sentences from the pre-indexed knowledge-based document, wherein the query-worthy sentences are ranked based on a prediction probability value of each query-worthy sentence; providing, by the sentence identification model, the query-worthy sentences to a pre-trained query generation model; generating, by the query generation model, a query for each query-worthy sentence; and evaluating, by the processor, the one or more IR systems using the generated queries, wherein one or more searches are performed via the one or more IR systems, and the one or more searches are performed in a set of knowledge-based documents including the pre-indexed knowledge-based document.

Abstract: One embodiment provides a method that includes receiving adjusted labeled data based on emotional tone factors. Words are analyzed using a tone latent Dirichlet allocation (T-LDA) model that models tone intensity using the emotional tone factors and integrating the adjusted labeled data. Representative words are provided for each emotional tone factor based on using the T-LDA model. The representative words are obtained using the T-LDA model based on determining posterior probabilities and adjusting the posterior probabilities based on an auxiliary topic.

Abstract: Embodiments relate to systematic explanation of neural model behavior and effective deduction of its vulnerabilities. Input data is received for the neural model and applied to the model to generate output data. Accuracy of the output data is evaluated with respect to the neural model, and one or more neural model vulnerabilities are identified that correspond to the output data accuracy. An explanation of the output data and the identified one or more vulnerabilities is generated, wherein the explanation serves as an indicator of alignment of the input data with the output data.

Abstract: A method and system of evaluating a user experience (UX) design are provided. A UX design is received. All objects that are identified to be part of a background of the input UI screen are removed to create a filtered input UI screen. The input UI screen is assigned to a cluster. A target UI screen of the input screen is determined and its background removed, to create a filtered target UI cluster. The target UI screen is assigned to a cluster. The filtered input UI screen is used as an input to a deep learning model to predict a target UI cluster. The predicted target UI cluster is compared to the filtered target UI cluster based on the clustering. Upon determining that the filtered target UI cluster is similar to the target UI screen, the UX design is classified as being successful.

Abstract: In one general aspect, a computer-implemented method includes identifying current choices with different verbosity levels for a current turn in a conversation; normalizing multi-dimensional verbosity vectors for each of the current choices to obtain a normalized value for each of the current choices; determining a state definition for the current turn in the conversation, utilizing the normalized values for each of the current choices; providing the state definition for the current turn in the conversation and the normalized values for each of the current choices to a trained reinforcement learning module; receiving, from the trained reinforcement learning module, a score associated with each of the current choices for the current turn in the conversation; and selecting one of the current choices to be entered for the current turn in the conversation, based on the score associated with each of the current choices for the current turn in the conversation.

Abstract: One embodiment provides model-driven and automated generation of information technology (IT) solutions including obtaining a set of business and technical requirements for IT infrastructure and applications. A client business and technical requirement model is generated based on generic model constructs and extending with constructs specific to capturing client requirements. A draft IT solution is generated using an automated model-driven process to generate the draft IT solution configuration for client requirements for a target shared resource environment offering. The generated draft IT solution is translated into a language of a constraint satisfaction engine that propagates values of chosen attributes in the draft solution to identify valid values for unset attributes, and identifies conflicts. An IT solutions interface is generated based on auto-population of verified attribute results.

Abstract: One embodiment provides a method comprising mapping project attributes for past projects to a first parameter set associated with a first model that models distribution of event types of project events, and a second parameter set associated with a second model that models distribution of the time intervals of project events. Specifically, machine learning is applied to a set of historical data for the past projects to obtain a first and a second set of learned weights. The method further comprises predicting information relating to a next project event for an ongoing project by generating a first probability distribution for a set of possible event types for the next project event utilizing the first model, and, for each possible event type, generating a corresponding probability distribution for time intervals of occurrence of the possible event type utilizing the first model and the second model in a pipelined fashion.

Abstract: One embodiment provides automatically learning shared resource environment solution design rules from a collection of requirement-solution pairs including obtaining requirement-solution pairs for a shared resource environment from a data store. A processor iteratively generates a candidate design rule set from each requirement-solution pair. Each generating iteration uses an input including the candidate design rule set output from a previous generating iteration. Evidence scores of each candidate design rule are calculated and candidate design rules having higher evidence score than an evidence score threshold are retained to obtain a learned design rule set. Candidate rules of a next iteration are constructed based on an addition of new attributes to rules of the learned design rule set.

Abstract: A computer-implemented method according to one embodiment includes receiving historical sales data, transforming a nonlinear, non-convex optimization model for weighting optimization into a linear optimization model, determining a number of historical periods of the historical sales data and weights to be applied to a historical conversion rate and a historical growth rate for the number of historical periods of the historical sales data, utilizing the nonlinear, non-convex optimization model or the linear optimization model, predicting a future optimal conversion rate and a future optimal growth rate by applying the weights to the historical conversion rate and the historical growth rate for the number of historical periods of the historical sales data, and applying the future optimal growth rate and the future optimal conversion rate to current sales pipeline data to determine future sales data.

Abstract: A system for cognitive assessment of the competitiveness of deals may include a memory having stored thereon historical deal information for historical deals with each historical deal including a historical deal component. A historical deal component may include a historical work scope and associated historical work pricing. The system may also include a processor cooperating with the memory and configured to compare current deal information with the historical deal information. The current deal information may include a current deal component that may include a current work scope and associated current work pricing. The processor may use machine learning to determine whether the current deal component is non-competitive based upon the historical deal information, and for each non-competitive current deal component generate an alternative current deal component. The alternative current deal component may have at least one of a different current work scope and different associated current work pricing.

Abstract: One embodiment provides automatically learning shared resource environment solution design rules from a collection of requirement-solution pairs including obtaining requirement-solution pairs. A processor iteratively generates a candidate design rule set from each requirement-solution pair. Candidate design rules from the candidate rule set are filtered to obtain a learned design rule set. The learned design rule set is optimized based on merging design rules.

Abstract: A system for cognitive deal pricing may include a memory having stored thereon historical deal information that includes historical deal components and historical deal communication associated therewith for historical deals. The system may also include a processor cooperating with the memory and configured to use machine learning to analyze the historical deal information to determine a predicted client type for each current deal component of a current deal, and generate the deal pricing based upon the predicted client type for each current deal component of the current deal.

Abstract: A method and system of evaluating a user experience (UX) design are provided. A UX design is received. All objects that are identified to be part of a background of the input UI screen are removed to create a filtered input UI screen. The input UI screen is assigned to a cluster. A target UI screen of the input screen is determined and its background removed, to create a filtered target UI cluster. The target UI screen is assigned to a cluster. The filtered input UI screen is used as an input to a deep learning model to predict a target UI cluster. The predicted target UI cluster is compared to the filtered target UI cluster based on the clustering. Upon determining that the filtered target UI cluster is similar to the target UI screen, the UX design is classified as being successful.

Abstract: One embodiment provides a method comprising receiving training data and experts' intuition, training a machine learning model based on the training data, predicting a class label for a new data input based on the machine learning model, estimating a degree of similarity of a target attribute of the new data input relative to the training data, and selectively applying a correction to the class label for the new data input based on the degree of similarity prior to providing the class label as an output. The target attribute is an attribute related to the experts' intuition.

Abstract: In one general aspect, a computer-implemented method includes identifying current choices with different verbosity levels for a current turn in a conversation; normalizing multi-dimensional verbosity vectors for each of the current choices to obtain a normalized value for each of the current choices; determining a state definition for the current turn in the conversation, utilizing the normalized values for each of the current choices; providing the state definition for the current turn in the conversation and the normalized values for each of the current choices to a trained reinforcement learning module; receiving, from the trained reinforcement learning module, a score associated with each of the current choices for the current turn in the conversation; and selecting one of the current choices to be entered for the current turn in the conversation, based on the score associated with each of the current choices for the current turn in the conversation.