Patents by Inventor Manju VIJAYAKUMAR
Manju VIJAYAKUMAR has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11769013Abstract: A multi-tenant system performs custom configuration of a tenant-specific chatbot to process and act upon natural language requests. The multi-tenant system configures the tenant-specific chatbots without requiring tenant-specific training. The multi-tenant system providing a user interface for configuring a tenant-specific set of permitted actions. The multi-tenant system determines a set of example phrases for each of the selected permitted actions. The multi-tenant system receives a natural language request from a user and identifies the action that the user wants to perform. The multi-tenant system uses a neural network to compare the natural language request with example phrases to identify an example phrase that matches the natural language request. The multi-tenant system performs the action corresponding to the matching example phrase.Type: GrantFiled: November 11, 2019Date of Patent: September 26, 2023Assignee: Salesforce, Inc.Inventors: Michael Machado, James Douglas Harrison, Caiming Xiong, Xinyi Yang, Thomas Archie Cook, Roojuta Lalani, Jean-Marc Soumet, Karl Ryszard Skucha, Juan Rodriguez, Manju Vijayakumar, Vishal Motwani, Tian Xie, Bryan McCann, Nitish Shirish Keskar, Zhihao Zou, Chitra Gulabrani, Minal Khodani, Adarsha Badarinath, Rohiniben Thakar, Srikanth Kollu, Kevin Schoen, Qiong Liu, Amit Hetawal, Kevin Zhang, Kevin Zhang, Johnson Liu, Rafael Amsili
-
Publication number: 20230244802Abstract: Media, methods, and systems are disclosed for managing permissions for a collaborative document within a group-based communication system. A collaborative document may be created within a group-based communication system. When the collaborative document is created, permissions may be automatically assigned based on the context of collaborative document creation, such as which virtual space the collaborative document creation corresponds to. After creation, the collaborative document may be shared and permissions may be automatically updated based on the sharing context. Users without appropriate permissions will be prevented from accessing the document.Type: ApplicationFiled: January 31, 2022Publication date: August 3, 2023Inventors: Sohom Paul, Manju Vijayakumar, Chaitanya Ravula, Michael Brevoort, Andrew Fong
-
Publication number: 20230214510Abstract: In association with a communication platform, one or more users can create, share, edit, and/or comment on a document. An indicator can be provided to one user that another user is presently interacting with the document. For example, the indicator can indicate information about a respective user, such as a permission level, virtual-space membership, and the manner in which the user is interacting with the document. In addition, the indicator may provide options to change or update information associated with a respective user, such as by inviting the user to join a virtual space of the communication platform and associated with the document or by changing permissions of the user with respect to the document.Type: ApplicationFiled: December 30, 2021Publication date: July 6, 2023Inventors: Manju Vijayakumar, Andrew Fong, Michael Hahn
-
Patent number: 11544465Abstract: Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.Type: GrantFiled: March 24, 2021Date of Patent: January 3, 2023Assignee: SALESFORCE.COM, INC.Inventors: Michael Machado, John Ball, Thomas Archie Cook, Jr., Shashank Harinath, Roojuta Lalani, Zineb Laraki, Qingqing Liu, Mike Rosenbaum, Karl Ryszard Skucha, Jean-Marc Soumet, Manju Vijayakumar
-
Publication number: 20210209305Abstract: Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.Type: ApplicationFiled: March 24, 2021Publication date: July 8, 2021Inventors: Michael MACHADO, John BALL, Thomas Archie COOK, JR., Shashank HARINATH, Roojuta LALANI, Zineb LARAKI, Qingqing LIU, Mike ROSENBAUM, Karl Ryszard SKUCHA, Jean-Marc SOUMET, Manju VIJAYAKUMAR
-
Publication number: 20210141865Abstract: A multi-tenant system performs custom configuration of a tenant-specific chatbot to process and act upon natural language requests. The multi-tenant system configures the tenant-specific chatbots without requiring tenant-specific training. The multi-tenant system providing a user interface for configuring a tenant-specific set of permitted actions. The multi-tenant system determines a set of example phrases for each of the selected permitted actions. The multi-tenant system receives a natural language request from a user and identifies the action that the user wants to perform. The multi-tenant system uses a neural network to compare the natural language request with example phrases to identify an example phrase that matches the natural language request. The multi-tenant system performs the action corresponding to the matching example phrase.Type: ApplicationFiled: November 11, 2019Publication date: May 13, 2021Inventors: Michael Machado, James Douglas Harrison, Caiming Xiong, Xinyi Yang, Thomas Archie Cook, Roojuta Lalani, Jean-Marc Soumet, Karl Ryszard Skucha, Juan Manuel Rodriguez, Manju Vijayakumar, Vishal Motwani, Tian Xie, Bryan McCann, Nitish Shirish Keskar, Armen Abrahamyan, Zhihao Zou, Chitra Gulabrani, Minal Khodani, Adarsha Badarinath, Rohiniben Thakar, Srikanth Kollu, Kevin Schoen, Qiong Liu, Amit Hetawal, Kevin Zhang, Kevin Zhang, Victor Brouk, Johnson Liu, Rafael Amsili
-
Patent number: 10970486Abstract: Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.Type: GrantFiled: September 18, 2018Date of Patent: April 6, 2021Assignee: salesforce.com, inc.Inventors: Michael Machado, John Ball, Thomas Archie Cook, Jr., Shashank Harinath, Roojuta Lalani, Zineb Laraki, Qingqing Liu, Mike Rosenbaum, Karl Ryszard Skucha, Jean-Marc Soumet, Manju Vijayakumar
-
Publication number: 20200089757Abstract: Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.Type: ApplicationFiled: September 18, 2018Publication date: March 19, 2020Inventors: Michael MACHADO, John BALL, Thomas Archie COOK, JR., Shashank HARINATH, Roojuta LALANI, Zineb LARAKI, Qingqing LIU, Mike ROSENBAUM, Karl Ryszard SKUCHA, Jean-Marc SOUMET, Manju VIJAYAKUMAR