Patents by Inventor Yasaman KHAZAENI
Yasaman KHAZAENI 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).
-
Publication number: 20240220898Abstract: Embodiments of the invention are directed to a programmable computer system that includes a processor system operable to perform processor system operations. The processor system operations include using a workflow composer to perform an automated workflow composition process that generates a composed workflow that is operable to, when executed by a host device, satisfy a target logical goal. Performing the automated workflow composition process includes using a workflow-metric model to control the automated workflow composition process such that the composed workflow is operable to, when executed by the host device, satisfy the target logical goal in a manner that optimizes a target metric goal. The target metric goal quantifies a performance feature of the composed workflow.Type: ApplicationFiled: December 29, 2022Publication date: July 4, 2024Inventors: Sarath Sreedharan, Tathagata Chakraborti, Vinod Muthusamy, Yara Rizk, Yasaman Khazaeni
-
Patent number: 11934787Abstract: Computer-implemented methods, computer program products, and computer systems for improving intent determination in a messaging dialog manager system. The computer-implemented method for improving intent determination in a messaging dialog manager system may include one or more processors configured for receiving first agent entry data corresponding to a first agent communicating in a messaging dialog interface, determining that the first agent entry data expects a response that is within a first response domain, determining that a first user entry entered in the messaging dialog interface is not within the first response domain. Further, the computer-implemented may include identifying a second agent configured with a second response domain that includes the first user entry and transmitting the first user entry to the second agent to facilitate a seamless transition of an established communicational flow between the first agent and a first user.Type: GrantFiled: April 29, 2021Date of Patent: March 19, 2024Assignee: International Business Machines CorporationInventors: Yara Rizk, Shubham Agarwal, Yasaman Khazaeni, Calvin Phung
-
Patent number: 11836615Abstract: In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. A Bayesian nonparametric framework is presented for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled through our framework. An inference approach is presented that allows us to synthesize a more expressive global network without additional supervision, data pooling and with as few as a single communication round. The efficacy of the present invention on federated learning problems simulated from two popular image classification datasets is shown.Type: GrantFiled: September 20, 2019Date of Patent: December 5, 2023Assignee: International Business Machines CorporationInventors: Kristjan Herbert Greenewald, Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh, Trong Nghia Hoang, Yasaman Khazaeni
-
Patent number: 11748559Abstract: A conversational interface generation method, system, and computer program product that includes determining a conversational artifact for a computer program from a specification of the computer program and generating a conversational interface for the computer program based on the conversational artifact for the computer program included in the specification.Type: GrantFiled: March 24, 2021Date of Patent: September 5, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Yara Rizk, Vatche Isahagian, Yasaman Khazaeni, Scott Boag, Falk Pollok
-
Patent number: 11645097Abstract: The present disclosure describes systems and methods for a command line interface with artificial intelligence integration. Embodiments of the disclosure provide a command line orchestration component (e.g., including a reinforcement learning model) that provides a generic command line interface environment (e.g., that researchers can interface using a simple sense-act application programming interface (API)). For instance, a command line orchestration component receives commands (e.g., text input) from a user via a command line interface, and the command line orchestration component can identify command line plugins and candidate response from the command line plugins. Further, the command line orchestration component may select a response from the candidate responses based on user preferences, user characteristics, etc., thus providing a generic command line interface environment for various users (e.g., including artificial intelligence developers and researchers).Type: GrantFiled: February 24, 2021Date of Patent: May 9, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Tathagata Chakraborti, Mayank Agarwal, Zhongshen Zeng, Yasaman Khazaeni, Sohini Upadhyay
-
Publication number: 20230081598Abstract: A data visualization method, system, and computer program product that includes identifying an intent from a natural language query in a conversation with a conversational system, utilizing verbiage from the natural language query and the intent to determine one or more data columns for visualization of results of the natural language query, and displaying a visualization of the determined one or more data columns.Type: ApplicationFiled: September 10, 2021Publication date: March 16, 2023Inventors: Yara Rizk, Zilu Tang, Yasaman Khazaeni, Vatche Isahagian
-
Publication number: 20230071362Abstract: A computer-implemented method of generating explanations for a sequence of actions performed by an aggregated assistant includes receiving a request from a user equipment (UE) to execute a sequence of actions. A decision is rendered on whether to execute the requested sequence of actions. An explanation regarding the rendered decision is provided including a user data upon which the decision is based.Type: ApplicationFiled: September 8, 2021Publication date: March 9, 2023Inventors: Sarath Sreedharan, Tathagata Chakraborti, Yara Rizk, Vinod Muthusamy, Yasaman Khazaeni
-
Patent number: 11580416Abstract: 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.Type: GrantFiled: August 14, 2019Date of Patent: February 14, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Matthew Davis, Marco Patricio Crasso, Yasaman Khazaeni, Praveen C. Ravichandran, Werner Geyer
-
Patent number: 11508480Abstract: A feature vector characterizing a system to be analyzed via online partially rewarded machine learning is obtained. Based on the feature vector, a decision is made, via the machine learning, using an online policy. The system is observed for environmental feedback. In at least a first instance, wherein the observing indicates that the environmental feedback is available, the environmental feedback is obtained. In at least a second instance, wherein the observing indicates that the environmental feedback is missing, the environmental feedback is imputed via an online imputation method. the online policy is updated based on results of the obtained environmental feedback and the online imputation method. A decision is output based on the updated online policy.Type: GrantFiled: August 28, 2019Date of Patent: November 22, 2022Assignee: International Business Machines CorporationInventors: Sohini Upadhyay, Mikhail Yurochkin, Mayank Agarwal, Djallel Bouneffouf, Yasaman Khazaeni
-
Publication number: 20220350970Abstract: Computer-implemented methods, computer program products, and computer systems for improving intent determination in a messaging dialog manager system. The computer-implemented method for improving intent determination in a messaging dialog manager system may include one or more processors configured for receiving first agent entry data corresponding to a first agent communicating in a messaging dialog interface, determining that the first agent entry data expects a response that is within a first response domain, determining that a first user entry entered in the messaging dialog interface is not within the first response domain. Further, the computer-implemented may include identifying a second agent configured with a second response domain that includes the first user entry and transmitting the first user entry to the second agent to facilitate a seamless transition of an established communicational flow between the first agent and a first user.Type: ApplicationFiled: April 29, 2021Publication date: November 3, 2022Inventors: Yara Rizk, Shubham Agarwal, Yasaman Khazaeni, Calvin Phung
-
Publication number: 20220327449Abstract: An optimization method, system, and computer program product for a number of tasks within a business process that can be automated that includes receiving access to an electronic representation of the business process, optimizing the business process to develop an optimized business process, displaying the optimized business process as a storyboard using storyboarding, and receiving an edit of the optimized business process, and automatically making a further edit to the optimized business process.Type: ApplicationFiled: April 9, 2021Publication date: October 13, 2022Inventors: Tathagata Chakraborti, Sarath Sreedharan, Shubham Agarwal, Yasaman Khazaeni, Yara Rizk, Vatche Isahagian
-
Publication number: 20220309240Abstract: A conversational interface generation method, system, and computer program product that includes determining a conversational artifact for a computer program from a specification of the computer program and generating a conversational interface for the computer program based on the conversational artifact for the computer program included in the specification.Type: ApplicationFiled: March 24, 2021Publication date: September 29, 2022Inventors: Yara Rizk, Vatche Isahagian, Yasaman Khazaeni, Scott Boag, Falk Pollok
-
Publication number: 20220269519Abstract: The present disclosure describes systems and methods for a command line interface with artificial intelligence integration. Embodiments of the disclosure provide a command line orchestration component (e.g., including a reinforcement learning model) that provides a generic command line interface environment (e.g., that researchers can interface using a simple sense-act application programming interface (API)). For instance, a command line orchestration component receives commands (e.g., text input) from a user via a command line interface, and the command line orchestration component can identify command line plugins and candidate response from the command line plugins. Further, the command line orchestration component may select a response from the candidate responses based on user preferences, user characteristics, etc., thus providing a generic command line interface environment for various users (e.g., including artificial intelligence developers and researchers).Type: ApplicationFiled: February 24, 2021Publication date: August 25, 2022Inventors: Tathagata Chakraborti, Mayank Agarwal, Zhongshen Zeng, Yasaman Khazaeni, Sohini Upadhyay
-
Publication number: 20220208018Abstract: Providing electronic media content to a user. An educational path and content are recommended to a user based on a user's current knowledge level. A first data set in a data structure representing a knowledge base is identified. The first data set represents a current knowledge point of a user in the knowledge base. A target data point is identified, outside the first data set, in the data structure, the target data point representing a target knowledge point for the user in the knowledge base. A path is generated between the first data set and the target data point via one or more other data points in the data structure.Type: ApplicationFiled: December 31, 2020Publication date: June 30, 2022Inventors: Yasaman Khazaeni, Elizabeth Daly, Christian Muise, Mikhail Yurochkin
-
Patent number: 11133006Abstract: In one or more embodiments described herein, device, computer-implemented methods, and/or computer program products that facilitate enhancing test coverage of dialogue models. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a conversation processing component that receives and processes a first conversation. The computer executable components can further comprise a node marking component that tags a first node of a node map as an accessed node if the first node was accessed during processing of the first conversation. The computer executable components can further comprise a reporting component that generates a report comprising a list of nodes, wherein the list of nodes comprises one or more second nodes that were not accessed during processing of the first conversation.Type: GrantFiled: July 19, 2019Date of Patent: September 28, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Pablo Jesus Pedemonte, Christian Muise, Marco Patricio Crasso, Zhongshen Zeng, Yasaman Khazaeni
-
Publication number: 20210089878Abstract: In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. A Bayesian nonparametric framework is presented for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled through our framework. An inference approach is presented that allows us to synthesize a more expressive global network without additional supervision, data pooling and with as few as a single communication round. The efficacy of the present invention on federated learning problems simulated from two popular image classification datasets is shown.Type: ApplicationFiled: September 20, 2019Publication date: March 25, 2021Applicant: International Business Machines CorporationInventors: Kristjan Herbert GREENEWALD, Mikhail YUROCHKIN, Mayank AGARWAL, Soumya GHOSH, Trong Nghia HOANG, Yasaman KHAZAENI
-
Publication number: 20210065897Abstract: A feature vector characterizing a system to be analyzed via online partially rewarded machine learning is obtained. Based on the feature vector, a decision is made, via the machine learning, using an online policy. The system is observed for environmental feedback. In at least a first instance, wherein the observing indicates that the environmental feedback is available, the environmental feedback is obtained. In at least a second instance, wherein the observing indicates that the environmental feedback is missing, the environmental feedback is imputed via an online imputation method. the online policy is updated based on results of the obtained environmental feedback and the online imputation method. A decision is output based on the updated online policy.Type: ApplicationFiled: August 28, 2019Publication date: March 4, 2021Inventors: Sohini Upadhyay, Mikhail Yurochkin, Mayank Agarwal, Djallel Bouneffouf, Yasaman Khazaeni
-
Publication number: 20210049476Abstract: 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.Type: ApplicationFiled: August 14, 2019Publication date: February 18, 2021Applicant: International Business Machines CorporationInventors: Matthew Davis, Marco Patricio Crasso, Yasaman Khazaeni, Praveen C. Ravichandran, Werner Geyer
-
Publication number: 20210034926Abstract: A novel formulation called the Context-Attentive Bandit with Observations (CABO) is described, where only a limited number of features can be accessed by the learner. The present invention is applicable to many problems including problems arising in clinical settings and dialog systems where it is not possible to reveal the whole feature set. The present invention adapts the standard contextual bandit algorithm known as Thompson Sampling with a novel algorithm, we call Context-Attentive Thompson Sampling with Observations (CATSO). Experimental results are included to demonstrate its effectiveness including a regret analysis and an empirical evaluation demonstrating advantages of the disclosed novel approach on several real-life datasets.Type: ApplicationFiled: July 29, 2019Publication date: February 4, 2021Inventors: Sohini UPADHYAY, Yasaman KHAZAENI, Djallel BOUNEFFOUF, Mayank AGARWAL
-
Publication number: 20210020172Abstract: In one or more embodiments described herein, device, computer-implemented methods, and/or computer program products that facilitate enhancing test coverage of dialogue models. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a conversation processing component that receives and processes a first conversation. The computer executable components can further comprise a node marking component that tags a first node of a node map as an accessed node if the first node was accessed during processing of the first conversation. The computer executable components can further comprise a reporting component that generates a report comprising a list of nodes, wherein the list of nodes comprises one or more second nodes that were not accessed during processing of the first conversation.Type: ApplicationFiled: July 19, 2019Publication date: January 21, 2021Inventors: Pablo Jesus Pedemonte, Christian Muise, Marco Patricio Crasso, Zhongshen Zeng, Yasaman Khazaeni