International Business Machines Corporation

Eric Donald Wayne

Kevin Patrick McAuliffe

Billy R Rowe, Jr

David Michael Enyeart

Saloni Potdar

Zhe Zhang

Michael D Whitley

Kyle Croutwater

Haode Qi

Vikrant Verma

Scott Dilworth Johnson

Christopher M Ketchuck

Yingxin Xing

Stephanie Lee Walter

Ladislav Kunc

Cheng Qian

Caroline Cross Daughtrey

A method, a structure, and a computer system for OOD sentence detection in dialogue systems. The exemplary embodiments may include receiving, for a domain corresponding to a particular topic, one or more on-topic text inputs and one or more off-topic text inputs. The exemplary embodiments may further include encoding the one or more on-topic text inputs and the one or more off-topic text inputs into a latent space, as well as decoding the one or more on-topic text inputs and the one or more off-topic text inputs from the latent space. The exemplary embodiments may additionally include minimizing a reconstruction error between the encoded one or more on-topic text inputs and the decoded one or more on-topic text inputs, and maximizing a reconstruction error between the encoded one or more off-topic text inputs and the decoded one or more off-topic text inputs.

Out of domain sentence detection

A method, system, and computer-usable medium are disclosed for identifying areas to improve an interactive conversational system, such as a chatbot. A stream of stream of conversational interactions C (C, C, . . . , C) between users and the interactive conversational system is received. An intent clustering model is periodically applied to the stream to form an incremental clustering based on a set of derived intents to form a mapping from a first set of conversational characteristics to a first set of intents and a second set of conversational characteristics to a first set of unclear intents. Information is provided related to the second set of conversation characteristics.

System and method for alerts for missing coverage of chatbot conversation messages

A performance bookmark of a dashboard view is created, e.g., in response to a triggering event. The performance bookmark includes a name, a timestamp, a reference to the visual properties of the dashboard view at the time that the performance bookmark is created and a reference to relationships of information displayed by the dashboard view at the time the performance bookmark is created. When a performance bookmark is recalled, the dashboard view is configured to correspond with the visual properties and relationships of information recorded at the time the select performance bookmark was created. Performance bookmarks are instances and relationships, and are not limited to snap shots captured of a static visual image of a dashboard screen from a corresponding dashboard user interface. As such, a retrieved dashboard view of a performance bookmark that is recalled from the bookmark system is live and supports user interaction.

Business performance bookmarks

The present invention can include a solution that dynamically manages electronic calendar events based upon the key performance indicators (KPIs) of a business process monitoring (BPM) system. Such a system can include a BPM system, an electronic calendar software application, and a dynamic calendar event manager. The BPM system can be configured to manage data for many user-defined KPIs. The electronic calendar software application can be configured to manage the calendar data of various calendar events for many users. The dynamic calendar event definition can be configured to define a condition for modifying the calendar data of a user-specified calendar event. The dynamic calendar event definition can consist of a KPI threshold value, a calendar action, and an applicable attendee list. The dynamic calendar event manager can be configured to dynamically and automatically handle the modification of the calendar data in accordance with the dynamic calendar event definition.

Dynamically managing electronic calendar events based upon key performance indicators (KPIS) within a business process monitoring (BPM) system

Growing community of inventors

Raleigh, NC, United States of America

Eric Donald Wayne