Patents by Inventor Ziyi Zhu
Ziyi Zhu 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: 20240339040Abstract: A digital instrument tutorial system is introduced herein, which enables the authoring and provision of augmented reality (AR) tutorials for operating digital instruments. The digital instrument tutorial system provides an automated authoring workflow for users (e.g., an expert user and/or author) to create sequential AR tutorials for digital instruments by intuitive embodied demonstration. The digital instrument tutorial system advantageously utilizes a multimodal approach that combines finger pressure and gesture tracking to translate the author's operations into AR visualizations. Aside from recording a tutorial for a task, the digital instrument tutorial system also provides an access mode, in which the AR tutorial is provided to a novice user.Type: ApplicationFiled: March 25, 2024Publication date: October 10, 2024Inventors: Karthik Ramani, Zhengzhe Zhu, Ziyi Liu
-
Publication number: 20240290089Abstract: A method for extracting forest parameters of a wetland with high canopy density based on a consumer-grade unmanned aerial vehicle (UAV) image is provided, which belongs to the technical field of wetland forest investigation. The method includes: collecting image data using a consumer-grade UAV; processing the collected UAV image, and generating a digital surface model and a digital orthophoto map; performing land use classification based on a UAV DOM image; obtaining a canopy height model with an accurate elevation based on classification of different land types of the wetland, and obtaining an accurate tree height and a tree number by means of a neighborhood extraction tool through the canopy height model; and obtaining an accurate canopy range by means of a multi-foreground marker watershed algorithm based on image filtering.Type: ApplicationFiled: November 9, 2023Publication date: August 29, 2024Inventors: Jianyu CHEN, Haibo HU, Weibo SHI, Ziyi ZHU
-
Patent number: 12073180Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: GrantFiled: April 17, 2023Date of Patent: August 27, 2024Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITEDInventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
-
Publication number: 20240281601Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: ApplicationFiled: April 29, 2024Publication date: August 22, 2024Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul BENN, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
-
Patent number: 12067362Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: GrantFiled: April 17, 2023Date of Patent: August 20, 2024Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITEDInventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
-
Patent number: 12008333Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: GrantFiled: November 21, 2023Date of Patent: June 11, 2024Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITEDInventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
-
Patent number: 11989527Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: GrantFiled: April 17, 2023Date of Patent: May 21, 2024Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITEDInventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
-
Patent number: 11989507Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: GrantFiled: April 17, 2023Date of Patent: May 21, 2024Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITEDInventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
-
Patent number: 11977854Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: GrantFiled: April 17, 2023Date of Patent: May 7, 2024Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITEDInventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
-
Publication number: 20240095468Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: ApplicationFiled: November 21, 2023Publication date: March 21, 2024Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul BENN, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
-
Publication number: 20230316006Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: ApplicationFiled: April 17, 2023Publication date: October 5, 2023Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul DARIAS, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
-
Publication number: 20230274094Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: ApplicationFiled: April 17, 2023Publication date: August 31, 2023Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul DARIAS, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
-
Publication number: 20230274086Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: ApplicationFiled: April 17, 2023Publication date: August 31, 2023Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul DARIAS, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
-
Publication number: 20230274089Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: ApplicationFiled: April 17, 2023Publication date: August 31, 2023Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul DARIAS, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
-
Publication number: 20230259705Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.Type: ApplicationFiled: April 17, 2023Publication date: August 17, 2023Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul DARIAS, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
-
Patent number: 11709097Abstract: An apparatus measures the transverse profile of vectorial optical field beams, including both the phase and the polarization spatial profile. The apparatus contains a polarization separation module, a weak perturbation module, and a detection module. Characterizing the transverse profile of vector fields provides an optical metrology tool for both fundamental studies of vectorial optical fields and a wide spectrum of applications, including microscopy, surveillance, imaging, communication, material processing, and laser trapping.Type: GrantFiled: July 19, 2021Date of Patent: July 25, 2023Assignee: University of South FloridaInventors: Zhimin Shi, Darrick Hay, Ziyi Zhu, Yiyu Zhou, Robert W. Boyd
-
Publication number: 20220011163Abstract: An apparatus measures the transverse profile of vectorial optical field beams, including both the phase and the polarization spatial profile. The apparatus contains a polarization separation module, a weak perturbation module, and a detection module. Characterizing the transverse profile of vector fields provides an optical metrology tool for both fundamental studies of vectorial optical fields and a wide spectrum of applications, including microscopy, surveillance, imaging, communication, material processing, and laser trapping.Type: ApplicationFiled: July 19, 2021Publication date: January 13, 2022Applicants: The University of Rochester, University of South FloridaInventors: Zhimin Shi, Darrick Hay, Ziyi Zhu, Yiyu Zhou, Robert W. Boyd
-
Patent number: 11067450Abstract: An apparatus measures the transverse profile of vectorial optical field beams, including both the phase and the polarization spatial profile. The apparatus contains a polarization separation module, a weak perturbation module, and a detection module. Characterizing the transverse profile of vector fields provides an optical metrology tool for both fundamental studies of vectorial optical fields and a wide spectrum of applications, including microscopy, surveillance, imaging, communication, material processing, and laser trapping.Type: GrantFiled: May 6, 2019Date of Patent: July 20, 2021Assignee: University of South FloridaInventors: Zhimin Shi, Darrick Hay, Ziyi Zhu, Yiyu Zhou, Robert W. Boyd
-
Patent number: D1037681Type: GrantFiled: December 6, 2023Date of Patent: August 6, 2024Inventors: Qiaoduo Zhu, Ziyi Long
-
Patent number: D1041208Type: GrantFiled: May 20, 2024Date of Patent: September 10, 2024Assignee: HK LOST HORIZON INTERNATIONAL ELECTRONIC COMMERCE LIMITEDInventors: Ziyi Long, Qiaoduo Zhu