International Business Machines Corporation

Octavian Udrea

Anton Viktorovich Riabov

Shirin Sohrabi Araghi

Anand Ranganathan

Kavitha Srinivas

Mark David Feblowitz

Nagui Halim

Oktie Hassanzadeh

Bishwaranjan Bhattacharjee

Yuan-Chi Chang

Deepak Srinivas Turaga

Anastasios Kementsietsidis

Songyun Duan

Edward John Pring

Stuart S Horn

Edward W Shay

Fang Yuan

Peter Zimmer

Julian Timothy Dolby

Eric P Bouillet

Patrick Dantressangle

Mihaela Ancuta Bornea

Michael Katz

Hanhua Feng

Peter L Coetzee

Embodiments are provided that relate to a computer system, a computer program product, and a computer-implemented method for automating scenario planning. Embodiments involve machine learning (ML) and an artificial intelligence (AI) planner to capture a general scenario planning (GSP) problem and provide a solution to the GSP problem in the form of trajectories.

Method and system for automating scenario planning

A method for improving performance of at least one hardware processor solving a top-k planning problem includes obtaining, in a memory coupled to the at least one processor, a specification of the planning problem in a planning language; obtaining, in a first iteration carried out by the at least one processor, at least one solution to the planning problem; and modifying the planning problem, in the first iteration carried out by the at least one processor, to forbid the at least one solution. The method further includes repeating, by the at least one processor, the obtaining of the at least one solution and the modifying to forbid the at least one solution, for a plurality of additional iterations, after the first iteration, until a desired number, k, of solutions to the planning problem are found or until no further solutions exist, whichever comes first.

Iterative generation of top quality plans in automated plan generation for artificial intelligence applications and the like

Techniques for solving a multi-agent plan recognition problem are provided. In one example, a computer-implemented method comprises transforming, by a device operatively coupled to a processor, a problem model and an at least partially ordered sequence of observations into an artificial intelligence planning problem through a transform algorithm. The problem model can comprises a domain description from a plurality of agents and a durative action. Furthermore, at least one of the observations of the at least partially ordered sequence of observations can be a condition that changes over time. The computer-implemented method further comprises determining, by the device, plan information using an artificial intelligence planner on the artificial intelligence planning problem. The computer-implemented method further comprises translating, by the device, the plan information into information indicative of a solution to the artificial intelligence planning problem.

Multi-agent plan recognition

Techniques for translating graphical representations of domain knowledge are provided. In one example, a computer-implemented method comprises receiving, by a device operatively coupled to a processor, a graphical representation of domain knowledge. The graphical representation comprises information indicative of a central concept and at least one chain of events associated with the central concept. The computer-implemented method further comprises translating, by the device, the graphical representation into an artificial intelligence planning problem. The artificial intelligence planning problem is expressed in an artificial intelligence description language. The translating comprises parsing the graphical representation into groupings of terms. A first grouping of terms of the grouping of terms comprises an event from the at least one chain of events and a second grouping of terms of the grouping of terms comprises the information indicative of the central concept. The computer-implemented method also comprises validating, by the device, the artificial intelligence planning problem.

Translation of artificial intelligence representations

Techniques for scenario planning are provided. In one example, a computer-implemented method can comprise analyzing, by a device operatively coupled to a processor, content using a topic model. The content can be associated with a defined source and is related to one or more current events. The computer-implemented method can also comprise determining, by the device, one or more portions of the analyzed content that are relevant to one or more key risk drivers using a risk driver model. The computer-implemented method can also comprise aggregating, by the device, the determined one or more portions into one or more emerging storylines based on values of one or more attributes of the topic model.

Scenario planning and management

Scenario planning and risk management

A mechanism is provided for computing a solution to a plan recognition problem. The plan recognition problem includes the model and a partially ordered sequence of observations or traces. The plan recognition is transformed into an AI planning problem such that a planner can be used to compute a solution to it. The approach is general. It addresses unreliable observations: missing observations, noisy observations (or observations that need to be discarded), and ambiguous observations). The approach does not require plan libraries or a possible set of goals. A planner can find either one solution to the resulting planning problem or multiple ranked solutions, which maps to the most plausible solution to the original problem.

Plan recognition with unreliable observations

In at least one embodiment, a method and a system for determining a set of plans that best match a set of preferences. The method may include receiving into a goal specification interface at least one goal to be accomplished by the set of plans; receiving into a preference engine a pattern that includes preferences; generating a planning problem by using the preference engine; generating a set of plans by at least one planner; and providing the set of plans for selection of one plan to deploy. In a further embodiment, the preferences may be an occurrence or non-occurrence of at least one component, an occurrence of one component over another component, an ordering between at least two components, an existence or non-existence of at least one tag in a final stream, an existence of one tag over another tag in the final stream.

Goal-driven composition with preferences method and system

In at least one embodiment, a method and a system include receiving a trace into a hypotheses generator from a source a trace, translating the trace and a state transition model into a planning problem using the hypotheses generator, producing a set of plans for the trace using at least one planner, translating each plan into hypothesis using the hypotheses generator and/or the planner, and returning the hypotheses from the hypotheses generator. In a further embodiment, the trace includes at least one of a future observation and a past observation. In at least one embodiment, the system includes at least one planner that develops a set of plans, a hypothesis generator, a database, at least one analytic, and at least one sensor where the hypotheses generator and/or the at least one planner converts each plan into a respective hypothesis.

Predictive hypothesis exploration using planning

Growing community of inventors

Ossining, NY, United States of America

Octavian Udrea