International Business Machines Corporation

Debarun Bhattacharjya

Dharmashankar Subramanian

Arun Hampapur

Hongfei Li

Qing He

Dhaivat P Parikh

Florian Pinel

Jeffrey Owen Kephart

Yuan-Chi Chang

Kush Raj Varshney

Maryam Ashoori

Lav Raj Varshney

Long H Vu

Venkata Nagaraju Pavuluri

Tian Gao

Timothy Rea Dinger

Nicholas Mattei

Techniques for multi-attribute evaluation of narratives are provided. Inputs are obtained representing: (i) at least one historical dataset of events; (ii) a set of candidate narratives, wherein each candidate narrative is a potential future event sequence; and (iii) a query, wherein the query comprises one or more events of interest to a user. Attribute scores are computed for at least a subset of the candidate narratives based on at least a portion of the obtained input. One of the attribute scores comprises a plausibility attribute score representing a measure estimating the likelihood that a given candidate narrative will occur in the future. Another one of the attribute scores comprises a surprise attribute score representing a measure estimating how surprising a given candidate narrative will be to the user.

Multi-attribute evaluation of narratives using event datasets

A graphical event model method, system, and computer program product, include learning statistical and causal co-occurrence relationships among multiple event-types of data, requiring no complex input, and generating a representation that explains a mutual dynamic of the multiple event-types in a form of a graphical event model.

Proximal graphical event model of statistical learning and causal discovery with event datasets

A method, computer program product, and/or computer system improves a future efficiency of a specific system. One or more processors receive multiple historical data snapshots that describe past operational states of a specific system. The processor(s) identify a time series pattern for the time series of data in the multiple historical snapshots and calculate their variability. The processor(s) then determine that the variability in a first sub-set of the time series pattern is larger than a predefined value, and determine that future values of the first set of the time series pattern are a set of non-forecastable future values. The processor(s) also determine that the variability in a second sub-set of the time series pattern for the data is smaller than the predefined value, and utilizes this second sub-set to modify the specific system at a current time.

Modifying a particular physical system according to future operational states

A system, computer program product, and method is described to provide a visualization tool which portrays the certain equivalent for one or more hypothetical (i.e. synthetic) or real probability distributions p(m), and optionally allows the user to manipulate that representation, resulting in associated changes to the underlying utility function u(m). In a first example, the risk preference visualization tool allows one to explore how the certain equivalent depends upon the probability distribution p(m), for a fixed utility function u(m). In a second example, the risk preference visualization tool allows one to explore how the certain equivalent depends upon the utility function u(m), assuming one or more fixed probability distributions p(m), p(m), etc. In a third example, the decision maker can provide feedback through the visualization tool that would cause their utility function to be modified.

Dual interactive visualization system for sensitivity analysis to risk preferences for decision support

A method includes predicting availability of a plurality of constituents for one or more future epochs, obtaining one or more metrics for each of a plurality of existing work products, each of the plurality of existing work products using at least one constituent, and generating at least one work product for each of the one or more future epochs based in part on the predicted availability of the constituents and the one or more metrics for the existing work products. The metrics for the existing work products may include quality metrics and novelty metrics.

Generating work products using work product metrics and predicted constituent availability

A method includes receiving a given work product plan specifying a set of constituents to be used in forming a given work product, each constituent having one or more properties, the given work product being associated with a given class of work products. The method also includes obtaining information associated with one or more existing work product plans for one or more existing work products in the given class from a knowledge database and selecting proportions of the set of constituents to be used in forming the given work product based at least in part on distributions of characteristics associated with types of constituents used in forming existing work products in the given class and of properties of constituents used in forming existing work products in the given class. The method further includes generating an updated work product plan for the given work product specifying the selected proportions of the set of constituents to be used in forming the given work product.

Generating work product plans specifying proportions of constituents to be used in forming a work product

Geo-defect repair modeling is provided. A method includes logically dividing a railroad network according to spatial and temporal dimensions with respect to historical data collected. The spatial dimensions include line segments of a specified length and the temporal dimensions include inspection run data for inspections performed for each of the line segments over a period of time. The method also includes creating a track deterioration model from the historical data, identifying geo-defects occurring at each inspection run from the track deterioration model, calculating a track deterioration condition from the track deterioration model by analyzing quantified changes in the geo-defects measured at each inspection run, and calculating a derailment risk based on track conditions determined from the inspection run data and the track deterioration condition. The method further includes determining a repair decision for each of the geo-defects based on the derailment risk and costs associated with previous comparable repairs.

Growing community of inventors

New York, NY, United States of America

Debarun Bhattacharjya