International Business Machines Corporation

Shane M Kilmon

Paul R Bastide

Fang Lu

Andrew Ronald Freed

Alaa Abou Mahmoud

Ralph E LeBlanc, Jr

Robert E Loredo

Matthew E Broomhall

Victor Povar

Lalit Agarwalla

Joseph M Jaquinta

Craig Richard Wolpert

Marco Noel

Rebecca Rose James

Leo Mazzoli

A method, system, and computer program product for recognizing, and training to recognize, alphanumeric speech data inputs. The method may include segmenting a data input into a sequential n-gram chunks based on a predetermined rule, where the data input is received through speech recognition. The method may also include receiving metadata regarding characteristics of the data input. The method may also include generating a language model based on the metadata. The method may also include generating a first set of language model variations of the data input. The method may also include training the language model based on at least the first set of language model variations. The method may also include generating one or more alternatives for the data input using the trained language model. The method may also include transmitting an output including the one or more alternatives for the data input.

Speech recognition and training for data inputs

A dialog change service builds a directed graph of nodes, each described by code for a conversational agent stored in source control, the code comprising one or more dialog-based features. The dialog change service, responsive to receiving a request for a dialog change to a particular node of the conversational agent, evaluates the directed graph to identify an additional selection of nodes that require a similar changes as the dialog change based on textual and structural content. The dialog change service updates the code for the particular node and the additional selection of nodes to propagate the dialog change in the conversational agent stored in source control.

Efficiently managing predictive changes for a conversational agent

An optimized content navigation system includes a display device including a touch screen user interface and a navigation adjustor engine coupled to the display device. The navigation adjustor engine is configured to display navigable content on the touch screen user interface. The navigation adjustor engine is further configured to determine from the content at least one preferred path of navigation through the content. The preferred path of navigation is based on the content. The navigation adjustor engine is further configured to receive a user input that defines a path of navigation and adjust the user defined path of navigation to follow the preferred path of navigation in response to detection of the user defined path of navigation to be within a tolerance level of the preferred path of navigation. The navigation adjust engine is further configured to navigate through the content along the adjusted path of navigation.

Optimized non-grid based navigation

Personalizing travel route planning based on past actual user travel behavior and reasons that the user deviated from planned routings. The route planning algorithm is revised based on analysis of user input related to a deviation from a planned routing. If a new trip in the planning stage entails considerations similar to those that caused the user's deviation on a previous trip, then the revised route planning algorithm can take these considerations into account when planning the route for the new trip. Changes in route planning may apply when the user: (i) plans to make a trip similar to a previous trip when the deviation occurred; (ii) plans to make a different trip, but the trip entails considerations that lead to the deviation on the prior trip; (iii) is using the same vehicle as for the previous trip with the deviation; and/or (iv) is using a different vehicle.

Personalized optimal travel route planning

A system and method for visual importance indication enhancement for collaborative environments comprises a processor for establishing a set of attributes for a primary participant based on attributes obtained from data sources accessible by the primary participant, generating a dynamic rule in accordance with the set of attributes, applying the dynamic rule to an activity stream comprising one or more messages to obtain points of commonality between a participant and the primary participant and determining an importance level of at least one of the one or more messages, and visually indicating the points of commonality and the importance level of the at least one message as a display on a display device. The system can further comprise computer readable storage medium for storing data including the set of attributes.

Visual importance indication enhancement for collaboration environments

Growing community of inventors

Tyngsborough, MA, United States of America

Shane M Kilmon