Patents by Inventor Jinchao Li
Jinchao Li 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: 11964655Abstract: The present invention discloses a backward anti-collision driving decision-making method for a heavy commercial vehicle. Firstly, a traffic environment model is established, and movement state information of a heavy commercial vehicle and a vehicle behind the heavy commercial vehicle is collected. Secondly, a backward collision risk assessment model based on backward distance collision time is established, and a backward collision risk is accurately quantified. Finally, a backward anti-collision driving decision-making problem is described as a Markov decision-making process under a certain reward function, a backward anti-collision driving decision-making model based on deep reinforcement learning is established, and an effective, reliable and adaptive backward anti-collision driving decision-making policy is obtained.Type: GrantFiled: April 12, 2021Date of Patent: April 23, 2024Assignee: SOUTHEAST UNIVERSITYInventors: Xu Li, Weiming Hu, Jinchao Hu, Xuefen Zhu
-
Patent number: 11875787Abstract: This document relates to machine learning. One example includes a method or technique that can be performed on a computing device. The method or technique can include obtaining a task-semantically-conditioned generative model that has been pretrained based at least on a first training data set having unlabeled training examples and semantically conditioned based at least on a second training data set having dialog act-labeled utterances. The method or technique can also include inputting dialog acts into the semantically-conditioned generative model and obtaining synthetic utterances that are output by the semantically-conditioned generative model. The method or technique can also include outputting the synthetic utterances.Type: GrantFiled: October 11, 2022Date of Patent: January 16, 2024Assignee: Microsoft Technology Licensing, LLCInventors: Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Nanshan Zeng, Jianfeng Gao
-
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: 20230153348Abstract: Systems and methods are provided for determining a response to a query in a dialog. An entity extractor extracts rules and conditions associated with the query and determines a particular task. The disclosed technology generates a transformer-based dialog embedding by pre-training a transformer using dialog corpora including a plurality of tasks. A task-specific classifier generates a first set of candidate responses based on rules and conditions associated with the task. The transformer-based dialog embedding generates a second set of candidate responses to the query. The classifier accommodates changes made to a task by an interactive dialog editor as machine teaching. A response generator generates a response based on the first and second sets of candidate responses using an optimization function.Type: ApplicationFiled: November 15, 2021Publication date: May 18, 2023Applicant: Microsoft Technology Licensing, LLCInventors: Jinchao LI, Lars H. LIDEN, Baolin PENG, Thomas PARK, Swadheen Kumar SHUKLA, Jianfeng GAO
-
Publication number: 20230076095Abstract: This document relates to machine learning. One example includes a method or technique that can be performed on a computing device. The method or technique can include obtaining a task-adapted generative model that has been tuned using one or more task-specific seed examples. The method or technique can also include inputting dialog acts into the task-adapted generative model and obtaining synthetic utterances that are output by the task-adapted generative model. The method or technique can also include populating a synthetic training corpus with synthetic training examples that include the synthetic utterances. The synthetic training corpus may be suitable for training a natural language understanding model.Type: ApplicationFiled: October 11, 2022Publication date: March 9, 2023Applicant: Microsoft Technology Licensing, LLCInventors: Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Nanshan Zeng, Jianfeng Gao
-
Patent number: 11508360Abstract: This document relates to machine learning. One example includes a method or technique that can be performed on a computing device. The method or technique can include obtaining a task-adapted generative model that has been tuned using one or more task-specific seed examples. The method or technique can also include inputting dialog acts into the task-adapted generative model and obtaining synthetic utterances that are output by the task-adapted generative model. The method or technique can also include populating a synthetic training corpus with synthetic training examples that include the synthetic utterances. The synthetic training corpus may be suitable for training a natural language understanding model.Type: GrantFiled: September 15, 2020Date of Patent: November 22, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Nanshan Zeng, Jianfeng Gao
-
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: 20220084510Abstract: This document relates to machine learning. One example includes a method or technique that can be performed on a computing device. The method or technique can include obtaining a task-adapted generative model that has been tuned using one or more task-specific seed examples. The method or technique can also include inputting dialog acts into the task-adapted generative model and obtaining synthetic utterances that are output by the task-adapted generative model. The method or technique can also include populating a synthetic training corpus with synthetic training examples that include the synthetic utterances. The synthetic training corpus may be suitable for training a natural language understanding model.Type: ApplicationFiled: September 15, 2020Publication date: March 17, 2022Applicant: Microsoft Technology Licensing, LLCInventors: Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Nanshan Zeng, 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: 10579430Abstract: Generally discussed herein are devices, systems, and methods for task routing. A method can include receiving, from a resource, a request for a task, in response to receiving the request, determining whether to retrieve a new task of new tasks stored in a first queue or a backlog task of backlog tasks stored in a second queue based on a combined amount of backlog tasks and new tasks relative to a capacity of the resource or the resources, retrieving the new task or the backlog task from the determined first queue or second queue, respectively, based on the determination, and providing the retrieved task to the resource.Type: GrantFiled: May 7, 2018Date of Patent: March 3, 2020Assignee: Microsoft Technolog Licensing, LLCInventors: Xinying Song, Jaideep Sarkar, Karan Srivastava, Jianfeng Gao, Prabhdeep Singh, Hui Su, Jinchao Li, Andreea Bianca Spataru
-
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: 20190340030Abstract: Generally discussed herein are devices, systems, and methods for task routing. A method can include receiving, from a resource, a request for a task, in response to receiving the request, determining whether to retrieve a new task of new tasks stored in a first queue or a backlog task of backlog tasks stored in a second queue based on a combined amount of backlog tasks and new tasks relative to a capacity of the resource or the resources, retrieving the new task or the backlog task from the determined first queue or second queue, respectively, based on the determination, and providing the retrieved task to the resource.Type: ApplicationFiled: May 7, 2018Publication date: November 7, 2019Inventors: Xinying Song, Jaideep Sarkar, Karan Srivastava, Jianfeng Gao, Prabhdeep Singh, Hui Su, Jinchao Li, Andreea Bianca Spataru
-
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
-
Patent number: 9891734Abstract: The present disclosure relates to a mobile terminal display structure and a mobile terminal. The display structure may include: a terminal housing; a display module, including a display screen and a glass panel attached to the display screen; wherein the glass panel has a touch region and extension regions bending and extending along both lateral sides of the touch region, an exterior surface of each extension region being located in a same plane with a corresponding edge of the terminal housing. The mobile terminal display structure according to the present disclosure is provided with the glass panel which at least covers both the lateral sides of the whole front surface thereof, and at least the packaging regions on both the lateral sides of the display screen are bended and extended into the housing. A real visual frameless design for the mobile terminal is achieved, while the screen occupying proportion is increased.Type: GrantFiled: February 17, 2016Date of Patent: February 13, 2018Assignee: Xiaomi Inc.Inventors: Lixin Al, Kesheng Yan, Jinchao Li, Shaoxing Hu
-
Patent number: 9888101Abstract: A mobile device is disclosed. The mobile device includes a frame structure including a side edge frame and a horizontal baffle, the side edge frame forming side edges of the mobile device, the horizontal baffle including a rim connected with interior walls of the side edge frame; and a screen module including side edges sized to fit in a space surrounded by the interior walls of the side edge frame, a bottom surface of the screen module being connected with an upper surface of the horizontal baffle, each of the side edges of the screen module being attached to a corresponding interior wall of the side edge frame.Type: GrantFiled: April 19, 2016Date of Patent: February 6, 2018Assignee: Xiaomi Inc.Inventors: Lixin Al, Kesheng Yan, Jinchao Li, Shaoxing Hu