International Business Machines Corporation

Matthew Scott Davis

David Robert Draeger

Russell Blake Wright

Elizabeth Daly

Oznur Alkan

Biplav Srivastava

Adi Ionel Botea

Howard Justin Glaser

Vera Liao

James Andrew McCright

Akihiro Kishimoto

Radu Marinescu

Yunfeng Zhang

Kartik Talamadupula

Rachel K E Bellamy

Werner Geyer

Yasaman Khazaeni

Marco Patricio Crasso

Christian Muise

Praveen C Ravichandran

Using a natural language analysis, it is determined that a compendium requires a natural language response to a natural language query, the compendium comprising a set of stored natural language responses to natural language queries. A relevance of a portion of narrative text to the natural language query is scored according to a query relevance measure, the portion extracted from a corpus of narrative text. The compendium is enhanced according to the query relevance score with information in the portion.

Improving the accuracy of a compendium of natural language responses

Various embodiments are provided for integrating multiple domain learning and personalization in a dialog system for a user in a computing environment by a processor. One or more problem instances may be defined for multiple domains according to a problem instance template, identified user intent, links to one or more problem solvers associated with the multiple domains, or a combination thereof. A dialog plan may be determined to further define the one or more problem instances in response to user input. A solution may be provided to the user for the one or more problem instances.

Integrating multiple domain problem solving in a dialog system for a user

Various embodiments are provided for using a dialog system for integrating multiple domain learning and problem solving for a user in a computing environment by a processor. One or more problem instances may be defined for one or more selected domains in a multi-domain database according to a problem instance template, identified user intent, links to one or more problem solvers associated with the one or more selected domains, or a combination thereof. A dialog plan may be determined for the one or more problem instances using a dialog system associated with the multi-domain database, wherein each record in the multi-domain database corresponds to a selected database for the one or more selected domains. A solution may be provided to the user for the one or more problem instances. One or more preferences of a user may be learned according to the solution.

Using a dialog system for integrating multiple domain learning and problem solving

Embodiments for building domain models from dialog interactions by a processor. A domain knowledge may be elicited from one or more dialog interactions with one or more users according to one or more dialog strategies. One or more domain models may be built and/or enhanced according to the domain knowledge.

Building domain models from dialog interactions

Various embodiments are provided for understanding user sentiment in a dialog system in a computing environment by a processor. A sentiment of a user may be detected according to a sentiment analysis and user feedback during a dialog with the user. One or more reasons for the sentiment of the user may be identified. Behavior of the dialog system may be adjusted according to the one or more reasons.

Understanding user sentiment using implicit user feedback in adaptive dialog systems

Provided a method, system, and article of manufacture for updating workflow nodes in a workflow. A workflow program processes user input at one node in a workflow comprised of nodes and workflow paths connecting the nodes, wherein the user provides user input to traverse through at least one workflow path to reach the current node. The workflow program transmits information on a current node to an analyzer. The analyzer processes the information on the current node to determine whether there are modifications to at least one subsequent node following the current node over at least one workflow path from the current node. The analyzer transmits to the workflow program an update including modifications to the at least one subsequent node in response to determining the modifications.

Updating workflow nodes in a workflow

Provided are a method, system, and article of manufacture for updating a workflow when a user reaches an impasse in the workflow. A workflow program processes user input at a current node in a workflow comprised of nodes and workflow paths connecting the nodes, and wherein the user provides user input to traverse through at least one workflow path to reach the current node. The workflow program processes user input at the current node to determine whether there is a next node in the workflow for the processed user input. The workflow program transmits information on the current node to an analyzer in response to determining that there is no next node in the workflow. The analyzer processes the information on the current node to determine whether there are modifications to the current node. The analyzer transmits to the workflow program an update including the determined modifications to the current node in response to determining the modification.

Updating a workflow when a user reaches an impasse in the workflow

Provided are a method, system, and article of manufacture for updating a workflow when a user reaches an impasse in the workflow. A workflow program processes user input at a current node in a workflow and provides user input to traverse through at least one workflow path to reach the current node. The workflow program processes user input at the current node to determine whether there is a next node in the workflow for the processed user input. The workflow program transmits information on the current node to an analyzer in response to determining that there is no next node in the workflow. If there are modifications to the current node, then the analyzer transmits to the workflow program an update including the determined modifications to the current node in response to determining the modification.

Provided are a method, system, and article of manufacture for generating templates of nodes to structure content objects and steps to process the content objects. A template is generated having a plurality of first level nodes representing a flow of tasks. A set of second level nodes representing a flow of steps is generated for at least one of the first level nodes to collectively perform the task represented by the first level node. A content object including information for a step represented by the node is associated with at least one node in the second level. Links are generated among the first level nodes and in each set of second level nodes indicating a logical ordering of the nodes and a direction of the flow of the tasks represented by the first level nodes and the flow of steps represented by the second level nodes. An end-user graphical user interface is generated from the generated nodes and links to direct an end user through the flow of tasks and steps represented by the nodes.

Growing community of inventors

Durham, NC, United States of America

Matthew Scott Davis