Patents by Inventor Yang Liang

Yang Liang 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: 20250252245
    Abstract: A process monitors contextual information of human-computer interactions (HCI) in a computing environment for reformatting formatted papers. The process integrates the monitored contextual information into a data structure via a formatting application. The process generates a paper that is formatted in accordance with predetermined formatting requirements of a publication, wherein the generated paper is uploaded to a page upload storage that stores the paper for the publication.
    Type: Application
    Filed: February 2, 2024
    Publication date: August 7, 2025
    Inventors: Jun Su, YANG LIANG, Su Liu, MICHAEL DAVIS
  • Publication number: 20250252862
    Abstract: Provided are a computer program product, system, and method for using and training an engagement score initializer to determine an initial engagement score for content to present to a user. A request is received, from a requesting user, for a content instance in a requested domain. An engagement score initializer determines an initial engagement score, for the requesting user, based on the requested domain, a complexity level of the content instance and a knowledge level of the user. A determination is made as to whether the initial engagement score, for the requesting user, exceeds an engagement threshold. The content instance is provided to render at a client system of the requesting user in response to the initial engagement score exceeding the engagement threshold.
    Type: Application
    Filed: February 7, 2024
    Publication date: August 7, 2025
    Inventors: Su Liu, Jun Su, Douglas Brian Mueller, YANG LIANG
  • Publication number: 20250245331
    Abstract: Provided are techniques for providing security with a Web Extension Control Bot (WEC-Bot). A request is transmitted for analysis of a web page that is associated with an extension and with a Uniform Resource Locator (URL). A sensitive sub web page with sensitive content and a non-sensitive sub web page with non-sensitive content for the web page are received. The non-sensitive sub web page is sent to the extension. Output is received from the extension for the non-sensitive sub web page. The sensitive sub web page is modified to hide the sensitive content. The web page is displayed with the output from the extension for the non-sensitive sub web page and with the modified sensitive sub web page.
    Type: Application
    Filed: January 31, 2024
    Publication date: July 31, 2025
    Inventors: Jun Su, Su Liu, Yang Liang, Li Li
  • Patent number: 12361714
    Abstract: An embodiment for detecting the danger of an object in close proximity of a subject is provided. The embodiment may include receiving real-time data from one or more IoT devices in a surrounding environment. The embodiment may also include detecting and classifying one or more subjects and one or more objects in an image from the one or more IoT devices. The embodiment may further include identifying one or more risk factors associated with each object. The embodiment may also include correlating the one or more risk factors associated with each object with the one or more subjects in the image. The embodiment may further include identifying relative positions of the one or more subjects and the one or more objects in the image. The embodiment may also include in response to determining a current position of at least one subject is dangerous, notifying a user of the danger.
    Type: Grant
    Filed: August 9, 2022
    Date of Patent: July 15, 2025
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Nageswara Sastry Renduchintala, Hamid Majdabadi, Su Liu, Yang Liang
  • Publication number: 20250220269
    Abstract: Provided are a computer program product, system, and method for determining play speeds for rendering video content in a video player. A determination is made of segment complexity scores of segments of a video are determined. A determination is made of user comprehension score for a viewer of the video with respect to a category of the video. A preferred speed predictor machine learning model receives input comprising the segment complexity scores and the user comprehension scores for the categories of the video to output predicted play speeds for the segments of the video. The segments of the video in the video player are rendered according to the predicted play speeds of the segments.
    Type: Application
    Filed: January 2, 2024
    Publication date: July 3, 2025
    Inventors: Jun Su, YANG LIANG, Su Liu, Shunguo Yan
  • Patent number: 12326830
    Abstract: A method for automatically setting addresses suitable for an RS485 system is provided. The RS485 system includes a host device and a plurality of slave devices. The method includes the following stages. The host device confirms that there are no addresses of the slave devices in a database. The slave devices are turned on in sequence. The slave devices calculate their own respective power-on times. The slave device enter an idle state during the period associated with the power-on time. Only one of the slave devices sends the power-on time to the host device when said slave device leaves the idle state. The host device sets the address of said slave device according to the power-on time when said slave device leaves the idle state.
    Type: Grant
    Filed: July 31, 2023
    Date of Patent: June 10, 2025
    Assignee: NUVOTON TECHNOLOGY CORPORATION
    Inventors: Shu-Hui Liu, Chia-Yang Liang
  • Publication number: 20250174249
    Abstract: According to one embodiment, a method, computer system, and computer program product for wrong phrase replacement is provided. The embodiment may include, in response to identifying an error spoken by a presenter in a multimedia file, generating a plan to correct the error. The embodiment may also include generating a corrected audio segment based on the plan. The embodiment may further include replacing an original audio segment in the multimedia file containing the error with the corrected audio segment. The embodiment may also include modifying a lip movement in a video segment of the multimedia file so lip movements of the presenter correspond to respective phonetics in the corrected audio segment. The embodiment may further include replacing an original lip movement with the modified lip movement so that the modified lip movement corresponds with the corrected audio segment.
    Type: Application
    Filed: November 28, 2023
    Publication date: May 29, 2025
    Inventors: Jun Su, YANG LIANG, Su Liu, Fan Yang
  • Publication number: 20250157351
    Abstract: A computer-implemented method, according to one embodiment, includes obtaining a plurality of answers to a chatbot question. The answers are generated by different AI chatbots. The method further includes analyzing the answers to determine updated first domain expertise scores of the AI chatbots, and selecting, based on the updated first domain expertise scores, one of the answers. The selected answer are caused to be provided to a first user device. A computer program product, according to another embodiment, includes a computer readable storage medium having program instructions embodied therewith. The program instructions are readable and/or executable by a computer to cause the computer to perform any combination of features of the foregoing methodology.
    Type: Application
    Filed: November 9, 2023
    Publication date: May 15, 2025
    Inventors: Jun Su, Yang Liang, Su Liu, Michael Davis
  • Patent number: 12282981
    Abstract: Aspects of the present disclosure relate to augmentation for web conference participants. An augmentation rule set defining mappings between augmentations and participant characteristics can be received, where the augmentation rule set is implemented for a web conference to determine augmentations to apply onto participant video feeds within the web conference. A plurality of participants within the web conference can be identified. The web conference can be analyzed to determine participant characteristics of each participant of the plurality within the web conference. Augmentation can be applied on respective video feeds of each participant according to the augmentation rule set based on the determined characteristics of each participant.
    Type: Grant
    Filed: September 14, 2022
    Date of Patent: April 22, 2025
    Assignee: International Business Machines Corporation
    Inventors: Su Liu, Jill S. Dhillon, Luis Osvaldo Pizana, Yang Liang
  • Patent number: 12278999
    Abstract: A computer-implemented method, in accordance with one embodiment, includes detecting cultural context and accents of speakers portrayed in a video stream and/or an audience of the video stream. Accent tags are selected for the speakers according to the cultural context and accents of the speakers and/or the audience of the video stream. A textual representation of spoken words of the speakers is translated from a source language to a target language. The accent tags are applied to the textual representation of the spoken words in the target language according to the speakers corresponding to the textual representation of the spoken words in the target language. Speech lip movements of the speakers portrayed in the video stream are modified to match the target language and the locale accent tags. A translated video stream having the speakers appearing to speak in the target language with the modified lip movements is output.
    Type: Grant
    Filed: June 21, 2023
    Date of Patent: April 15, 2025
    Assignee: International Business Machines Corporation
    Inventors: Jun Su, Yang Liang, Luis Osvaldo Pizana, Su Liu
  • Publication number: 20250095032
    Abstract: Dynamic vehicle assessment is provided. A baseline value of a vehicle is determined based on current market values of a set of vehicles similar to the vehicle with regard to similar year, make, model, and mileage. A percentage of deviation from the baseline value of the vehicle is determined based on a cost to repair a set of given parts of the vehicle predicted to fail within a defined time period. A real time actual market value of the vehicle is determined based on the percentage of deviation from the baseline value of the vehicle according to the cost to repair the set of given parts of the vehicle predicted to fail within the defined time period. The real time actual market value of the vehicle is sent to a requester via a network in response to receiving a request for an assessment of the vehicle.
    Type: Application
    Filed: September 19, 2023
    Publication date: March 20, 2025
    Inventors: Neil Delima, Su Liu, Hamid Majdabadi, Yang Liang
  • Publication number: 20250077740
    Abstract: Mechanisms are provided for simulating operating systems. The mechanisms train, for each operating system, a corresponding artificial intelligence (AI) computer model that learns, by way of machine learning training, patterns of input features of inputs to the operating system and corresponding responses from the operating system. A request to simulate a requested operating system is received along with a simulation input whose processing by the requested operating system is to be simulated. An AI computer model corresponding to the requested operating system is executed on the simulation input to simulate processing the simulation input to generate a simulated response. The simulated response is returned as a simulated output of the requested operating system responsive to the input.
    Type: Application
    Filed: September 5, 2023
    Publication date: March 6, 2025
    Inventors: Jun Su, Yang Liang, Su Liu, Jennifer Sparks
  • Publication number: 20250080696
    Abstract: Provided are a computer program product, system, and method for processing participant input in a virtual meeting to determine effects to render in the virtual meeting. A natural language processor (NLP) processes a sentence to determine a structural representation of the sentence comprising a subject and object, which is processed to determine whether the object of the sentence comprises an object of recognition and the subject of the sentence is a participant in the virtual meeting. The structural representation of the sentence is processed to determine an attention level in response to determining that the structural representation of the sentence includes the object of recognition and the subject comprises a participant in the virtual meeting. In response to the attention level exceeding a threshold, a recognition attention effect is rendered in the virtual meeting associated with the attention level, observable by the participants of the virtual meeting.
    Type: Application
    Filed: August 29, 2023
    Publication date: March 6, 2025
    Inventors: Jun Su, YANG LIANG, Su Liu, James Nash
  • Publication number: 20250068843
    Abstract: Provided are techniques for training Machine Learning (ML) models to automatically detect and correct contextual and logical errors. A plurality of machine learning models are trained. In response to receiving content, the content is parsed into different elements. One or more knowledge graphs are built based on the different elements. One or more machine learning models are selected from the plurality of machine learning models based on the one or more knowledge graphs and custom criteria in a user profile. The selected one or more machine learning models are used to identify at least one of a contextual error and a logical error and a correction for the at least one of the contextual error and the logical error. The correction for the at least one of the contextual error and the logical error is applied to generate corrected content. The corrected content is rendered.
    Type: Application
    Filed: August 24, 2023
    Publication date: February 27, 2025
    Inventors: Jun Su, Su Liu, Yang Liang, Richard Anthony LaFrance
  • Publication number: 20250061347
    Abstract: Providing individualized answers to questions including receiving a question input by a user, identifying a topic of the question and a user's reading level, mapping the topic to an answer generator and knowledge graph according to the user's reading level. Also including generating a response to the question according to the knowledge graph and providing the response to the user.
    Type: Application
    Filed: August 17, 2023
    Publication date: February 20, 2025
    Inventors: Jun Su, YANG LIANG, Su Liu, James Nash
  • Publication number: 20250062909
    Abstract: A method for detecting content generated by artificial intelligence is disclosed. In one embodiment, such a method includes monitoring interaction between a user and a generative AI model. The method intercepts a response returned from the generative AI model to the user and embeds, within the response prior to its return to the user, codes that are invisible to the user when viewing the response. In certain embodiments, these codes are embedded within the response in a particular invisible code insertion pattern to indicate that the response was generated by the generative AI model. The method returns the response to the user for viewing. A third party may utilize the embedded codes to determine whether the response was generated by the generative AI model. A corresponding system and computer program product are also disclosed herein.
    Type: Application
    Filed: August 18, 2023
    Publication date: February 20, 2025
    Applicant: International Business Machines Corporation
    Inventors: Jun Su, Yang Liang, Su Liu, Jennifer Sparks
  • Patent number: 12229577
    Abstract: VM file management includes detecting a user request to access to a virtual machine (VM) and searching a pre-defined list to determine whether the user requesting access is identified on the list. If so, a file-level snapshot is generated prior to enabling modification of a VM file by the user. The file-level snapshot includes a user attribute and is added as the top layer of a stack. The user attribute indicates a role of the user for whom the file-level snapshot is created. Each layer of the stack contains one or more other file-level snapshots. The VM file is written in the file's entirety to the snapshot in response to the user modifying the VM file. Based on the user attribute of each snapshot, a set of snapshots is selected from the stack, and the VM is modified by merging the VM files belonging to the set of snapshots selected.
    Type: Grant
    Filed: April 23, 2021
    Date of Patent: February 18, 2025
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Da Long Wang, Qin Yue Chen, Xue Lian Feng, Yang Liang, Yang Yang Feng, Bin Xiong
  • Publication number: 20250037721
    Abstract: According to one embodiment, a method, computer system, and computer program product for context-aware voice self-authorization is provided. The embodiment may include identifying a speaker in audio data using two or more authentication techniques. The embodiment may also include capturing contextual information related to the audio data. The embodiment may further include encoding the contextual information into an audible voice. The embodiment may also include converting the audible voice to an inaudible sound frequency. The embodiment may further include embedding the inaudible sound frequency voice with audio data.
    Type: Application
    Filed: July 26, 2023
    Publication date: January 30, 2025
    Inventors: Su Liu, Yang Liang, Terry James Hoffman, Paul Llamas Virgen
  • Patent number: 12191281
    Abstract: The present disclosure is directed to semiconductor packages, and methods for making them, which includes a substrate with a top surface and a bottom surface, a substrate recess in the bottom surface of the substrate, a first device positioned over the top surface of the substrate, which has the first device at least partially overlapping the substrate recess, a mold material in the substrate recess, which has the mold material overlapping the bottom surface of the substrate adjacent to the substrate recess, a second device positioned in the substrate recess, and a plurality of interconnect vias in the substrate, which has at least one of the plurality interconnect vias coupled to the first and second devices to provide a direct signal connection therebetween that minimizes signal latency.
    Type: Grant
    Filed: June 16, 2021
    Date of Patent: January 7, 2025
    Assignee: Intel Corporation
    Inventors: Bok Eng Cheah, Yang Liang Poh, Seok Ling Lim, Jenny Shio Yin Ong, Jackson Chung Peng Kong
  • Publication number: 20250006188
    Abstract: An anti-spambot application that incorporates mechanisms for human-computer interaction is configured. In response to determining that a telephonic call from a caller to a callee is a spam call, the process switches to a mode in which the anti-spambot application initiates a conversation with the caller. A script is selected from a predetermined set of scripts based on content included in the telephonic call. Synthesized speech is generated from the script, based on voice characteristics of the callee, where the synthesized speech is used for conversing with the caller.
    Type: Application
    Filed: June 28, 2023
    Publication date: January 2, 2025
    Inventors: YANG LIANG, Jun Su, Demetrice L Browder, Su Liu