Patents by Inventor Haiyuan Cao
Haiyuan Cao 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: 12159115Abstract: Examples described herein generate training data for machine learning (ML) for natural language (NL) processing (such as semantic parsing for translating NL). A formula tree is generated based on sampling both a formula grammar and NL templates. Using the formula tree, an ML training data instance pair is generated comprising a formula example and an NL example. A context example may also be used during instantiation of the formula tree. An ML model is trained with training data including the ML training data instance pair, and ML output is generated from NL input. The ML output includes, for example, a machine-interpretable formula, a database querying language command, or a general programming language instruction. Some examples support context-free grammar, probabilistic context-free grammar, and/or non-context-free production rules.Type: GrantFiled: October 19, 2021Date of Patent: December 3, 2024Assignee: Microsoft Technology Licensing, LLC.Inventors: Zeqi Lin, Yu Hu, Haiyuan Cao, Yi Liu, Jian-Guang Lou, Kuralmani Elango, PalaniRaj Kaliyaperumal, Weizhu Chen, Kunal Mukerjee
-
Publication number: 20240264809Abstract: The automatic generation of synthetic training data that can be used to train a language model to generate code examples following a code language based on a natural language input. Thus, new language models may be created, or existing language models may be fine-tuned, to adapt to automatically generate code without having to manually generate bulk quantities of training data. Rather, a many-to-many grammar mapping is navigated to generate training data. Specifically, the many-to-many grammar mapping maps code grammar to natural grammar. Then, each training data is generated by navigating the many-to-many grammar mapping definition to generate a mapping of a respective code expression to a respective natural language expression.Type: ApplicationFiled: February 6, 2023Publication date: August 8, 2024Inventors: Konstantin Andreyevich GOLOBOKOV, Zeqi LIN, Haizhen ZHANG, Yu HU, Yousef Ahmed AL-KOFAHI, Jonathan Richard MALSAN, Haiyuan CAO, Daniel Akintola FATADE
-
Publication number: 20240078092Abstract: A method of assisting a user with the discovery of program features is provided. The method includes detecting a selection of a data structure within a user interface, determining a contextual parameter based on the selected data structure, the contextual parameter associated with a modifiable feature of the selected data structure, determining options for generating program code configured to modify the modifiable feature are available based on the contextual parameter and a predefined inferential relationship between the contextual parameter and the modifiable feature of the selected data structure, and prompting the user in the user interface with information indicating that the determined options for generating the program code are accessible in the user interface.Type: ApplicationFiled: November 9, 2022Publication date: March 7, 2024Inventors: Yi LIU, Kristen OSHIRO, David Boyd LUDWIG, IV, Alexander DROTAR, Niraj YADAV, Yu HU, Haiyuan CAO, Haoran WEI, Jeremiah A. NYMAN
-
Patent number: 11734066Abstract: Generally discussed herein are devices, systems, and methods for scheduling tasks to be completed by resources. A method can include identifying features of the task, the features including a time-dependent feature and a time-independent feature, the time-dependent feature indicating a time the task is more likely to be successfully completed by the resource, converting the features to feature values based on a predefined mapping of features to feature values in a first memory device, determining, by a gradient boost tree model and based on a first current time and the feature values, a likelihood the resource will successfully complete the task, and scheduling the task to be performed by the resource based on the determined likelihood.Type: GrantFiled: January 8, 2020Date of Patent: August 22, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Jinchao Li, Yu Wang, Karan Srivastava, Jianfeng Gao, Prabhdeep Singh, Haiyuan Cao, Xinying Song, Hui Su, Jaideep Sarkar
-
Publication number: 20230119613Abstract: Examples described herein generate training data for machine learning (ML) for natural language (NL) processing (such as semantic parsing for translating NL). A formula tree is generated based on sampling both a formula grammar and NL templates. Using the formula tree, an ML training data instance pair is generated comprising a formula example and an NL example. A context example may also be used during instantiation of the formula tree. An ML model is trained with training data including the ML training data instance pair, and ML output is generated from NL input. The ML output includes, for example, a machine-interpretable formula, a database querying language command, or a general programming language instruction. Some examples support context-free grammar, probabilistic context-free grammar, and/or non-context-free production rules.Type: ApplicationFiled: October 19, 2021Publication date: April 20, 2023Inventors: Zeqi LIN, Yu HU, Haiyuan CAO, Yi LIU, Jian-Guang LOU, Kuralmani ELANGO, PalaniRaj KALIYAPERUMAL, Weizhu CHEN, Kunal MUKERJEE
-
Patent number: 11327726Abstract: A workflow engine tool is disclosed that enables scientists and engineers to programmatically author workflows (e.g., a directed acyclic graph, “DAG”) with nearly no overhead, using a simpler script that needs almost no modifications for portability among multiple different workflow engines. This permits users to focus on the business logic of the project, avoiding the distracting tedious overhead related to workflow management (such as uploading modules, drawing edges, setting parameters, and other tasks). The workflow engine tool provides an abstraction layer on top of workflow engines, introducing a binding function that converts a programming language function (e.g., a normal python function) into a workflow module definition. The workflow engine tool infers module instances and induces edge dependencies automatically by inferring from a programming language script to build a DAG.Type: GrantFiled: July 31, 2020Date of Patent: May 10, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Yu Wang, Yu Hu, Haiyuan Cao, Hui Su, Jinchao Li, Xinying Song, Jianfeng Gao
-
Publication number: 20210224047Abstract: A workflow engine tool is disclosed that enables scientists and engineers to programmatically author workflows (e.g., a directed acyclic graph, “DAG”) with nearly no overhead, using a simpler script that needs almost no modifications for portability among multiple different workflow engines. This permits users to focus on the business logic of the project, avoiding the distracting tedious overhead related to workflow management (such as uploading modules, drawing edges, setting parameters, and other tasks). The workflow engine tool provides an abstraction layer on top of workflow engines, introducing a binding function that converts a programming language function (e.g., a normal python function) into a workflow module definition. The workflow engine tool infers module instances and induces edge dependencies automatically by inferring from a programming language script to build a DAG.Type: ApplicationFiled: July 31, 2020Publication date: July 22, 2021Inventors: Yu WANG, Yu HU, Haiyuan CAO, Hui SU, Jinchao LI, Xinying SONG, Jianfeng GAO
-
Patent number: 11068304Abstract: Systems and methods are disclosed for intelligent scheduling of calls to sales leads, leveraging machine learning (ML) to optimize expected results. One exemplary method includes determining, using a connectivity prediction model, call connectivity rate predictions; determining timeslot resources; allocating, based at least on the call connectivity rate predictions and timeslot resources, leads to timeslots in a first time period; determining, within a timeslot and using a lead scoring model, lead prioritization among leads within the timeslot; configuring, based at least on the lead prioritization, the telephone unit with lead information for placing a phone call; and applying a contextual bandit (ML) process to update the connectivity prediction model, the lead scoring model, or both. During subsequent time periods, the updated connectivity prediction and lead scoring models are used, thereby improving expected results over time.Type: GrantFiled: February 25, 2019Date of Patent: July 20, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Jinchao Li, Xinying Song, Ah Young Kim, Haiyuan Cao, Yu Wang, Hui Su, Shahina Ferdous, Jianfeng Gao, Karan Srivastava, Jaideep Sarkar
-
Patent number: 10768908Abstract: A workflow engine tool is disclosed that enables scientists and engineers to programmatically author workflows (e.g., a directed acyclic graph, “DAG”) with nearly no overhead, using a simpler script that needs almost no modifications for portability among multiple different workflow engines. This permits users to focus on the business logic of the project, avoiding the distracting tedious overhead related to workflow management (such as uploading modules, drawing edges, setting parameters, and other tasks). The workflow engine tool provides an abstraction layer on top of workflow engines, introducing a binding function that converts a programming language function (e.g., a normal python function) into a workflow module definition. The workflow engine tool infers module instances and induces edge dependencies automatically by inferring from a programming language script to build a DAG.Type: GrantFiled: February 25, 2019Date of Patent: September 8, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Yu Wang, Yu Hu, Haiyuan Cao, Hui Su, Jinchao Li, Xinying Song, Jianfeng Gao
-
Publication number: 20200273000Abstract: Systems and methods are disclosed for intelligent scheduling of calls to sales leads, leveraging machine learning (ML) to optimize expected results. One exemplary method includes determining, using a connectivity prediction model, call connectivity rate predictions; determining timeslot resources; allocating, based at least on the call connectivity rate predictions and timeslot resources, leads to timeslots in a first time period; determining, within a timeslot and using a lead scoring model, lead prioritization among leads within the timeslot; configuring, based at least on the lead prioritization, the telephone unit with lead information for placing a phone call; and applying a contextual bandit (ML) process to update the connectivity prediction model, the lead scoring model, or both. During subsequent time periods, the updated connectivity prediction and lead scoring models are used, thereby improving expected results over time.Type: ApplicationFiled: February 25, 2019Publication date: August 27, 2020Inventors: Jinchao LI, Xinying SONG, Ah Young KIM, Haiyuan CAO, Yu WANG, Hui SU, Shahina FERDOUS, Jianfeng GAO, Karan SRIVASTAVA, Jaideep SARKAR
-
Publication number: 20200272433Abstract: A workflow engine tool is disclosed that enables scientists and engineers to programmatically author workflows (e.g., a directed acyclic graph, “DAG”) with nearly no overhead, using a simpler script that needs almost no modifications for portability among multiple different workflow engines. This permits users to focus on the business logic of the project, avoiding the distracting tedious overhead related to workflow management (such as uploading modules, drawing edges, setting parameters, and other tasks). The workflow engine tool provides an abstraction layer on top of workflow engines, introducing a binding function that converts a programming language function (e.g., a normal python function) into a workflow module definition. The workflow engine tool infers module instances and induces edge dependencies automatically by inferring from a programming language script to build a DAG.Type: ApplicationFiled: February 25, 2019Publication date: August 27, 2020Inventors: Yu WANG, Yu HU, Haiyuan CAO, Hui SU, Jinchao LI, Xinying SONG, Jianfeng GAO
-
Publication number: 20200142737Abstract: Generally discussed herein are devices, systems, and methods for scheduling tasks to be completed by resources. A method can include identifying features of the task, the features including a time-dependent feature and a time-independent feature, the time-dependent feature indicating a time the task is more likely to be successfully completed by the resource, converting the features to feature values based on a predefined mapping of features to feature values in a first memory device, determining, by a gradient boost tree model and based on a first current time and the feature values, a likelihood the resource will successfully complete the task, and scheduling the task to be performed by the resource based on the determined likelihood.Type: ApplicationFiled: January 8, 2020Publication date: May 7, 2020Inventors: Jinchao Li, Yu Wang, Karan Srivastava, Jinfeng Gao, Prabhdeep Singh, Haiyuan Cao, Xinying Song, Hui Su, Jaideep Sarkar
-
Patent number: 10579423Abstract: Generally discussed herein are devices, systems, and methods for scheduling tasks to be completed by resources. A method can include identifying features of the task, the features including a time-dependent feature and a time-independent feature, the time-dependent feature indicating a time the task is more likely to be successfully completed by the resource, converting the features to feature values based on a predefined mapping of features to feature values in a first memory device, determining, by a gradient boost tree model and based on a first current time and the feature values, a likelihood the resource will successfully complete the task, and scheduling the task to be performed by the resource based on the determined likelihood.Type: GrantFiled: April 2, 2018Date of Patent: March 3, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Jinchao Li, Yu Wang, Karan Srivastava, Jianfeng Gao, Prabhdeep Singh, Haiyuan Cao, Xinying Song, Hui Su, Jaideep Sarkar
-
Publication number: 20190303197Abstract: Generally discussed herein are devices, systems, and methods for scheduling tasks to be completed by resources. A method can include identifying features of the task, the features including a time-dependent feature and a time-independent feature, the time-dependent feature indicating a time the task is more likely to be successfully completed by the resource, converting the features to feature values based on a predefined mapping of features to feature values in a first memory device, determining, by a gradient boost tree model and based on a first current time and the feature values, a likelihood the resource will successfully complete the task, and scheduling the task to be performed by the resource based on the determined likelihood.Type: ApplicationFiled: April 2, 2018Publication date: October 3, 2019Inventors: Jinchao Li, Yu Wang, Karan Srivastava, Jianfeng Gao, Prabhdeep Singh, Haiyuan Cao, Xinying Song, Hui Su, Jaideep Sarkar