International Business Machines Corporation

Salesforce Com, Inc.

Other

Envirotest Systems Corporation

Environmental Systems Products Holdings Inc.

Varian Medical Systems, Inc.

Varian Medical Systems Technologies, Inc.

Sun Electric Corporation

Colorado Seminary

Globalfoundries Inc.

Olin Corporation

Dropbox, Inc.

Conoco Inc.

Envirotest Systems Holdings Corp.

Envirotest Syst. Corp.

James Johnson

Daniel James Winarski

Nils Haustein

Allen Keith Bates

Craig Anthony Klein

Robert J Snell

Casey Dugan

Timothy J Barker

Jonathan Levine

Michael Muller

Anna Wanda Topol

Stephen Leonard Schwartz

Werner Geyer

Aabhas Sharma

Madhu Prabaker

Shai Alfandary

John DiDomenico

David Goldbrenner

Scott Keith Springer

Qian Pan

Dennis L Smith

James Edward Clayton

Ulf Troppens

Donald Hugh Stedman

Thorsten Krause

David Michael Davis

Samuel William Bailey

Paul Bjorkholm

Nathan Edward Lipke

John D Didomenico

Hugh Francis Cockburn

Zahra Ashktorab

Richard Quimby Williams

Kenneth W Michaels

Dakuo Wang

Josef S Watts

Steven John Baumgartner

Craig S Rendahl

Sungjae Lee

David M Onsongo

Jason K Webster

Paul A Hyde

Yara Rizk

Gary Allen Bishop

Arunima Chaudhary

Miko Arnab Bose

Tathagata Chakraborti

Ranjitha Gurunath Kulkarni

Rainer Thoma

Lan Luo

Burak Aksar

Rajkumar Janakiraman

Jason Teller

Yanqing Deng

Karl R Bahnick

Michelle Brachman

Todd G McKenzie

Anvitha Jaishankar

W John Williams

Yucheng Wang

Peter S Shifflett

John Di Domenico

Emil Bergner

Arnold L Fowler

Julius E Brooks

Harvey H Friend

James E Greene

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating responses to prompts by utilizing a context engine and a logic engine. In one or more embodiments, the disclosed systems can determine a prompt received from a client device involves one or more logical problems with a prompt classification model. Based on identifying the one or more logical problems, the disclosed systems can generate a logic code segment by processing the prompt with one or more large language models within a context engine. The disclosed systems can generate a logic result for the prompt by processing the logic code segment with a logic engine that solves one or more logical problems within the prompt according to the structure of the logic code segment. The disclosed systems can generate a response to the prompt based, at least in part, on the logic result.

Generating responses using a context engine coupled with a logic engine and time phrase resolution

Embodiments are provided that related to a computer system, a computer program product, and a computer-implemented method for dynamically managing knowledge graphs and their corresponding datasets. Embodiments include identifying a neologism from a virtual environment, and leveraging a virtual environment exploration to resolve a meaning of the identified neologism. The resolved meaning of the neologism is applied to a dynamic expansion of a dataset and a corresponding knowledge graph.

Knowledge graph driven content generation

A method, computer program, and computer system are provided for explaining generation of a flow from natural language utterances. Data corresponding to a natural language utterance is received. One or more constraints corresponding to a flow to be generated are determined based on the received natural language utterance. A flow is constructed based on the determined constraints. An explanation associated with the constructed flow is provided, and the explanation identifies parameters corresponding to constructing the flow.

Explaining natural-language-to-flow pipelines

A method, a computer program product, and a computer system generate an accurate mental model of an automated agent. The method includes receiving an input from a user device associated with a user during a communication session between the user and the automated agent. The method includes determining a response to the input. The method includes determining a confidence score of the response relative to a confidence threshold. The method includes determining an assertiveness feature associated with the response, the assertiveness feature comprising an expression of the automated agent based on the confidence score. The method includes transmitting the response and the assertiveness feature to the user device, the expression configured to update anthropomorphic characteristics of a graphical representation of the automated agent shown on a graphical user interface of the communication session displayed on a display device of the user device.

Assertiveness module for developing mental model

Crowdsourced solutions are provided that can prevent and/or reduce dissemination of selected digital content in a social media platform. In one embodiment, a system can include at least one memory device having computer-executable components stored therein, and at least one processor configured to execute the computer-executable components. Such computer-executable components can include a selection component that identifies multiple reviewer accounts using a selection criterion corresponding to a user account in the social media platform. The multiple reviewer accounts can evaluate presence of particular digital content in the social media platform directed to the user account. The computer-executable components also can include a routing component that can provide portions of digital content directed to the user account to respective reviewer accounts. The computer-executable components can further include a feedback component that receives rating information indicative of ratings for the portions of the second digital content.

Crowdsourced prevention or reduction of dissemination of selected content in a social media platform

A reminder method, system, and computer program product include collecting information and an activity of a user, determining an optimum time to send the reminder to the user based on the information and the activity of the user and an optimal platform to deliver the reminder to the user based on the information and the activity of the user.

Cognitive agent for persistent multi-platform reminder provision

A method for sharing documents between on-demand services is provided. In an embodiment, a user of a first on-demand service may be able to view a list of content that includes content stored at the first on-demand service and content stored at a second on-demand service. The content of the second on-demand service may be associated with information about the content, allowing the content to be shared among multiple users of the first on-demand service. The user wanting to view the content, select or click on an indicator identifying the content, a connection to the second on-demand service is established, and images of the content are sent from the second on-demand service to the first on-demand service.

Method and system for sharing documents between on-demand services

A cognitive request management method, system, and computer program product include scanning a stream of incoming messages among at least two users to identify a request sent to a first user, storing the identified request in a list of unfulfilled requests, identifying a response of the first user to the request by backtracking within a message thread of the stream of incoming messages and when the response to a request is detected, the request is moved from the user's unfulfilled request list to a list of fulfilled requests, and displaying the list of unfulfilled requests and the list of fulfilled requests.

Cognitive request management

A processor can cause operation tracking screens to be presented on a display. The operation tracking screens can include first and second screen areas. Some of the first screen areas can have graphical control elements configured to receive information associated with actions associated with a sequence of operations. The actions can include first and second actions performed concurrently. The second screen areas can have a graphical representation of stages of the sequence of operations. The graphical representation of the stages can be of a default sequence of the stages, in response to an initiation of the sequence of operations, and can be modified to include a graphical representation of an additional stage in response to a determination of a result of a condition being a specific value. The processor can receive signals associated with the information associated with the actions and can cause the sequence of operations to be processed.

Processing a sequence of operations using operation tracking screens

Systems, methods, and apparatuses for implementing dynamic creation of an external code segment within a cloud based computing environment. For instance, an exemplary system having at least a processor and a memory therein includes means for executing object code comprising software instructions that when executed create an instance of an external segment of software instructions that is to perform business logic, wherein a name of the external segment of software instructions is to be first received during runtime of the object code.

Systems, methods, and apparatuses for dynamic creation of an external code segment within a cloud based computing environment

Disclosed are methods, apparatus, systems, and computer readable storage media for providing a reference to a content object in a user interface using an on-demand database service. A computing device can receive data regarding identification of a content object, where the content object is stored in a data repository external to the on-demand database service. The data regarding the content object can be stored in a persistent object in a database of the on-demand database service. A reference can be provided representing the persistent object to a display device operable to display the reference in a user interface when the display device accesses the on-demand database service. One or more graphical representations can be exposed regarding the content object for display in the user interface by the display device, where the exposed graphical representations depend at least in part on the data repository.

Third party files in an on-demand database service

Embodiments of the disclosure relate to methods of storing and using biosamples with a cartridge that includes slots for storing biosample capillary tubes. The methods include providing access to a holder inside an enclosure of the cartridge, the enclosure having a same form factor as a data tape cartridge used in an automated tape library. The holder is configured to receive a plurality of capillary tubes in the holder, the capillary tubes including one or more biosamples. Exemplary methods may also include receiving capillary tubes in the cartridge, withdrawing capillary tubes from the cartridge, scanning and/or analyzing the capillary tubes and/or biosamples. Exemplary methods may additionally or alternatively include retrieving the cartridge from a storage slot of the automated tape library, loading the cartridge onto a drive of the automated tape library, and/or receiving and/or exporting a cartridge to/from the automated tape library via a mail slot.

Cartridge for storing biosample capillary tubes and use in automated data storage systems

Growing community of inventors

San Francisco, CA, United States of America

James Johnson