International Business Machines Corporation

Ami H Dewar

Jonathan Frederick Brunn

Robert Charles Leah

Ethan A Geyer

Scott E Chapman

Rogelio Vazquez-Rivera

Dennis Jinlone Chen

Rachael M Dickens

Jonathan D Dunne

Peter C Yim

Nicholas E Poore

Rachael M H Dickens

Thomas J Blanchflower

Rui Zhang

Heiko Hary Ludwig

Bo Jiang

Rachael Marie Huston Dickens

Michael Celedonia

John Kurt Muller

Katelyn Applegate

Jason T Clark

Kimberly A Brantley

Nicolas E Poore

Provided are a computer program product, system, and method for generation of tasks and retraining machine learning modules to generate tasks based on feedback for the generated tasks. A machine learning module processes an input text message sent in the communication channel to output task information including an intended action and a set of associated users. A task message is generated including the output task information of a task to perform. The task message is sent to a user interface panel in a user computer. Feedback is received from the user computer on the output task information in the task message. The machine learning module is retrained to output task information from the input text message based on the feedback to reinforce likelihood correct task information is outputted and reinforce lower likelihood incorrect task information is outputted.

Automatic generation of tasks and retraining machine learning modules to generate tasks based on feedback for the generated tasks

Identification of content classes deemed important by users is received. Classifiers are trained on user communication text to recognize content matching content classes. A composite classifier is applied to text of communication among users of a second set of users, including tagging, by the composite classifier, content in text of communication among the users of the second set. The tagging is responsive to the classifiers recognizing their respective content classes in text of communication among the users of the second set.

Composable natural language lenses for collaborative streams

A computer-implemented system, method and computer program product to transform content and to generate a visual indicator of that transformation, by: performing the transformation on the content, wherein the content is transformed from one state to another state; and displaying the visual indicator representative of the transformation adjacent the content; wherein the visual indicator is selected to display the content in a state that existed prior to or at a time when the transformation was performed. As subsequent transformations are performed, additional visual indicators are listed in the order performed. The visual indicator acts as a user interface element that allows a user to view or revert the content to a state that existed prior to or at a time that the transformation was performed. Selection of the visual indicator follows the control to the destination. The visual indicator also serves to relay information sent from the destination.

System and method to transform content and to generate a visual indicator of that transformation

A method, a computer system, and a computer program product are provided for delivering notifications to users of a messaging platform. A mention directed to a specific context of users is received from a user of a messaging platform. A subset of users is dynamically determined from the specific context of users such that each user of the subset of users is more likely to engage with a notification associated with the mention than users of the specific context of users outside of the subset of users. The notification associated with the mention is sent to only the subset of users from the specific context of users.

Mentions with automated goal optimization

A method, computer system, and computer program product for cognitively summarizing one or more collaborative moments is provided. An embodiment may include receiving a plurality of communications sent during a collaborative session. The embodiment may also include grouping the plurality of received communications into one or more bursts. The embodiment may further include assigning one or more keywords or one or more entities to each burst. The embodiment may also include generating a summary for each burst using one or more natural language processing techniques based on the assigned one or more keywords or one or more entities. The embodiment may further include transmitting the generated summary to each user participating in the collaborative session.

Cognitive collaborative moments

An apparatus, system, and method are disclosed to collect metrics from a non-monolithic website having external content. The method includes monitoring a pointer movement in a web page. The web page displays a content feed of the external content. The method also includes identifying a pointer movement representative of an interaction gesture. The interaction gesture is indicative of a type of interaction with the content feed of the external content. The method also includes generating a score for the content feed in response to the pointer movement including an interaction gesture. The score includes a quantity of each of the reported types of interaction with the content feed.

Apparatus, system, and method for collecting metrics from a non-monolithic website

A server to implement human response tests of graduated difficulty can suppress access by spambots. The server includes a network interface and a test controller. The network interface connects the server to a network and facilitates electronic communications between the server and a client computer coupled to the network. The test controller is coupled to the network interface. The test controller implements a human response test with a level of difficulty on the client computer in response to an access request by the client computer. The level of difficulty of the human response test is dependent on a determination whether the access request is deemed to originate from a spambot.

System, method, and apparatus for graduated difficulty of human response tests

Methods and systems for providing an option to auto-generate a thread on a web forum in response to a change in topic are described. When a post is received on a thread in the web forum, wherein the thread includes one or more thread keywords and wherein each of the one or more thread keywords are associated with a relevancy score, the post is searched for the one or more thread keywords. The relevancy scores of any of the one or more thread keywords located within the post are added together to obtain a post total relevancy score. A query is then provided, to a user, for example, to auto-generate a new thread on the web forum when the post total relevancy score is less than a threshold relevancy score.

System and method for providing an option to auto-generate a thread on a web forum in response to a change in topic

Methods and systems for auto-generating threads on web forums are described. Comments are received on web content contained on a web page within a web site, where the web site further includes a web forum. The comments can be monitored to determine if a comment threshold is reached, and a web content thread can be auto-generated in the web forum when the comment threshold is reached.

Growing community of inventors

Durham, NC, United States of America

Ami H Dewar