Patents by Inventor Ran Han

Ran Han 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: 20250225052
    Abstract: An embodiment includes detecting an application availability metric and a performance data metric of a system by a Tracing Policy Analyzer, responsive to detecting the application availability metric and the performance data metric, training a Bayesian optimization model of the Tracing Policy Analyzer based on the application availability metric and the performance data metric where the Bayesian optimization model outputs an optimal tracing policy. The embodiment includes detecting the optimal tracing policy by a Tracing Level Determination Module of an application of the system, responsive to detecting the optimal tracing policy, computing a computed tracing level by the Tracing Level Determination Module executing a k-nearest neighbors algorithm based on the optimal tracing policy. The embodiment also includes tracing of the application of the system by a Tracer based on the computed tracing level.
    Type: Application
    Filed: January 8, 2024
    Publication date: July 10, 2025
    Applicant: International Business Machines Corporation
    Inventors: Yong Hu Sun, Xiao Juan Niu, Li Jian Wang, Pei Ran Han, Xing Tian, Shao Rong Li
  • Patent number: 12217185
    Abstract: A knowledge increasing method includes calculating uncertainty of knowledge obtained from a neural network using an explicit memory, determining the insufficiency of the knowledge on the basis of the calculated uncertainty, obtaining additional data (learning data) for increasing insufficient knowledge, and training the neural network by using the additional data to autonomously increase knowledge.
    Type: Grant
    Filed: May 27, 2021
    Date of Patent: February 4, 2025
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Hyun Woo Kim, Jeon Gue Park, Hwa Jeon Song, Yoo Rhee Oh, Byung Hyun Yoo, Eui Sok Chung, Ran Han
  • Publication number: 20240423149
    Abstract: The present disclosure relates to the technical field of breeding, in particular to an environmental-friendly and efficient breeding method of high-yield and high-quality wheat cultivars. In the present disclosure, the breeding method can improve a breeding efficiency of excellent new cultivars, further realize large-scale production, and further increase a planting area of the excellent cultivars. In addition, the breeding method can increase the number of products for the new cultivars, further increase a diversity of early-generation materials, and further increase a diversity of hybrid samples through the innovation of hybridization and breeding methods. The environmental-friendly and efficient breeding method of high-yield and high-quality wheat cultivars can increase a richness of excellent characteristics of the new cultivars through high-generation materials, hybridization, and off-site identification, thereby further improving an effect of breeding.
    Type: Application
    Filed: October 6, 2023
    Publication date: December 26, 2024
    Applicant: Crop Research Institute, SAAS
    Inventors: Jianmin SONG, Yan ZI, Jianjun LIU, Haosheng LI, Dungong CHENG, Aifeng LIU, Xinyou CAO, Jun GUO, Wei JU, Canguo WANG, Shengnan ZHAI, Faji LI, Cheng LIU, Ran HAN, Xiaolu WANG, Zhendong ZHAO
  • Publication number: 20240330649
    Abstract: Provided is an inference method employing a prompt-based meta-learning network and a computer system. The inference method includes selecting a task, generating a prompt key for the selected task using a prompt-embedding network (PEN), calculating similarities between the prompt key for the selected task and prompt keys included in a prompt key pool (PKP), acquiring a prompt value for the selected task using a memory network (MN), and generating an inference result for the selected task using a model-agnostic meta-learning (MAML)-based pre-trained model (MPM).
    Type: Application
    Filed: March 20, 2024
    Publication date: October 3, 2024
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Jeongmin YANG, Hyun Woo KIM, Hwajeon SONG, Byunghyun YOO, Euisok CHUNG, Ran HAN
  • Publication number: 20240256885
    Abstract: Provided is an exploration method based on reward decomposition in multi-agent reinforcement learning. The exploration method includes: generating a positive reward estimation model through neural network training based on training data including states of all agents, actions of all the agents, and a global reward true value; generating, for each of the agents, a first individual utility function based on the global reward true value and generating a second individual utility function using the positive reward estimation model; and determining an action of each of the agents using the first individual utility function and the second individual utility function based on the state of each of the agents.
    Type: Application
    Filed: November 22, 2023
    Publication date: August 1, 2024
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Byunghyun YOO, Hyun Woo KIM, Hwajeon SONG, Jeongmin YANG, Sungwon YI, Euisok CHUNG, Ran HAN
  • Publication number: 20240232648
    Abstract: Disclosed herein are a multimodal unsupervised meta-learning method and apparatus. The multimodal unsupervised meta-learning method includes training, by a multimodal unsupervised feature representation learning unit, an encoder configured to extract features of individual single-modal signals from a source multimodal dataset, generating, by a multimodal unsupervised task generation unit, a source task based on the features of individual single-modal signals, deriving, by a multimodal unsupervised learning method derivation unit, a learning method from the source task using the encoder, and training, by a target task performance unit, a model based on the learning method and features extracted from a small number of target datasets by the encoder, thus performing the target task.
    Type: Application
    Filed: December 12, 2023
    Publication date: July 11, 2024
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Hyun-Woo KIM, Hwa-Jeon SONG, Jeong-Min YANG, Byung-Hyun YOO, Eui-Sok CHUNG, Ran HAN
  • Publication number: 20240202454
    Abstract: A domain adaptation procedure, such as fine-tuning training, is required to utilize a large-capacity PLM for a specific domain. Attempts in existing research have been made to improve performance of a PLM through domain adaptor technology based on an N-gram in order to reduce errors on the basis of the results of domain text error analysis of the PLM. Proposed is a method of selecting a semantic chunk through a domain semantic chunk graph and PageRank based on the existing domain adaptor research, with an N-gram as the semantic chunk. Proposed is also a method of domain-adapting a large-capacity PLM using semantic chunk dynamic weight masking, which reflects an output value of a PLM rather than simply integrating embedding values of semantic chunks, in a semantic chunk domain adaptor technology.
    Type: Application
    Filed: September 21, 2023
    Publication date: June 20, 2024
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Euisok CHUNG, Hyun Woo KIM, Hwajeon SONG, Jeongmin YANG, Byunghyun YOO, Ran HAN
  • Publication number: 20240160859
    Abstract: The present invention relates to a multi-modality system for recommending multiple items using an interaction and a method of operating the same. The multi-modality system includes an interaction data preprocessing module that preprocesses an interaction data set and converts the preprocessed interaction data set into interaction training data; an item data preprocessing module that preprocesses item information data and converts the preprocessed item information data into item training data; and a learning module that includes a neural network model that is trained using the interaction training data and the item training data and outputs a result including a set of recommended items using a conversation context with a user as input.
    Type: Application
    Filed: November 13, 2023
    Publication date: May 16, 2024
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Eui Sok CHUNG, Hyun Woo KIM, Jeon Gue PARK, Hwa Jeon SONG, Jeong Min YANG, Byung Hyun YOO, Ran HAN
  • Publication number: 20240081352
    Abstract: The present disclosure provides a blending method of high-quality and dual-purpose flour for bread and noodles, belonging to the technical field of flour processing. The method includes: selecting flour of a high-quality and dual-purpose wheat variety for bread and noodles as a high-quality basic flour for blending; according to a large gradient experimental design, selecting a gradient range ratio with a sedimentation value ?46.0 mL and a dough development time ?9.6 min, followed by subdividing for small gradient experiments; selecting a ratio with flour sedimentation value and dough development time that reach an ideal value to blend a large amount of flour; and making bread and noodles for scoring, followed by determining a blending ratio if a scoring result reaches an ideal value.
    Type: Application
    Filed: September 11, 2022
    Publication date: March 14, 2024
    Inventors: Yan Zi, Jianmin Song, Xiao Ma, Aifeng Liu, Wei Ju, Haosheng Li, Dungong Cheng, Canguo Wang, Jun Guo, Jianjun Liu, Xinyou Cao, Cheng Liu, Shengnan Zhai, Faji Li, Ran Han, Zhendong Zhao
  • Publication number: 20230274127
    Abstract: A concept based few-shot learning method is disclosed. The method includes estimating a task embedding corresponding to a task to be executed from support data that is a small amount of learning data; calculating a slot probability of a concept memory necessary for a task based on the task embedding; extracting features of query data that is test data, and of the support data; comparing local features for the extracted features with slots of a concept memory to extract a concept, and generating synthesis features to have maximum similarity to the extracted features through the slots of the concept memory; and calculating a task execution result from the synthesis feature and the extracted concept by applying the slot probability as a weight.
    Type: Application
    Filed: December 23, 2022
    Publication date: August 31, 2023
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Hyun Woo KIM, Jeon Gue PARK, Hwajeon SONG, Jeongmin YANG, Byunghyun YOO, Euisok CHUNG, Ran HAN
  • Publication number: 20230186154
    Abstract: An exploration method used by an exploration apparatus in multi-agent reinforcement learning to collect training samples during the training process is provided. The exploration method includes calculating the influence of a selected action of each agent on the actions of other agents in a current state, calculating a linear sum of the value of a utility function representing the action value of each agent and the influence on the actions of the other agent calculated for the selected action of each agent, and obtaining a sample to be used for training an action policy of each agent by probabilistically selecting the action in which the linear sum is the maximum, and the random action.
    Type: Application
    Filed: August 23, 2022
    Publication date: June 15, 2023
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Byunghyun YOO, Hyun Woo KIM, Jeon Gue PARK, Hwa Jeon SONG, Jeongmin YANG, Sungwon YI, Euisok CHUNG, Ran HAN
  • Patent number: 11661594
    Abstract: The present disclosure discloses a mutant of a lycopene epsilon cyclase (Lcye) gene crucial in a wheat carotenoid synthesis pathway and use thereof. The present disclosure provides the following proteins: (1) a protein obtained by substituting serine at position 253 of an Lcye-D1 protein with phenylalanine; (2) a derived protein that is obtained by subjecting the protein in (1) to substitution and/or deletion and/or addition of one or more amino acid residues and has the same ability as the protein in (1); (3) a protein that has a homology of more than 99%, more than 95%, more than 90%, more than 85%, or more than 80% with the amino acid sequence defined in any one of (1) and (2) and has the same function as the amino acid sequence; and (4) a fusion protein obtained by attaching a tag to N-terminus and/or C-terminus of the protein in any one of (1) to (3).
    Type: Grant
    Filed: March 8, 2021
    Date of Patent: May 30, 2023
    Assignee: Crop Research Institute, Shandong Academy of Agricultural Sciences
    Inventors: Shengnan Zhai, Jianjun Liu, Haosheng Li, Jianmin Song, Aifeng Liu, Xinyou Cao, Dungong Cheng, Zhendong Zhao, Cheng Liu, Jun Guo, Ran Han, Yan Zi, Faji Li, Xiaolu Wang
  • Publication number: 20220346335
    Abstract: Disclosed is a molecular marker polymerization wheat breeding method for Fusarium head blight-resistance. The method uses an intermediate material for Fusarium head blight-resistance as a resistance source, and excellent varieties (strains) in a northern part of Huanghuai wheat production area as agronomic parents, and uses molecular marker-assisted selection and conventional breeding techniques. The molecular markers are a linked marker LJJT-1 of a Fusarium head blight-resistant gene Fhb1 and linked markers LJJ-2 and LJJ-3 of a Fusarium head blight-resistant gene Fhb2, so as to create a semi-winter Fusarium head blight-resistant breeding material with outstanding target traits and excellent comprehensive traits, which lays a material foundation for cultivating Fusarium head blight-resistant wheat varieties suitable for planting in the Huanghuai wheat production area.
    Type: Application
    Filed: March 4, 2022
    Publication date: November 3, 2022
    Inventors: JIANJUN LIU, WENJING HU, HAOSHENG LI, XUEYAN CHEN, SHENGNAN ZHAI, XINYOU CAO, JIANMIN SONG, JUN GUO, CHENG LIU, AIFENG LIU, DUNGONG CHENG, XIUSHENG CHU, FAJI LI, RAN HAN, YAN ZI, XIAOLU WANG
  • Patent number: 11432165
    Abstract: A method includes: obtaining user equipment distribution information of a beam domain, where there are at least two beam domains, and the beam domain is a vertical area in a physically vertical dimension of a cell coverage area; determining information about a concentrated beam domain based on the user equipment distribution information, where the concentrated beam domain is a beam domain in which a quantity of covered user equipments exceeds a quantity threshold; and compared with information about a historical concentrated beam domain, if the information about the concentrated beam domain satisfies a preset condition, adjusting a broadcast beam domain based on the information about the concentrated beam domain, so that a main lobe direction of the broadcast beam domain is adjusted to a beam domain corresponding to the concentrated beam domain.
    Type: Grant
    Filed: April 21, 2020
    Date of Patent: August 30, 2022
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Ran Han, Ji Xia, Hongyan Yu
  • Publication number: 20220180071
    Abstract: Provided are a system and method for adaptive masking and non-directional language understanding and generation. The system for adaptive masking and non-directional language understanding and generation according to the present invention includes an encoder unit including an adaptive masking block for performing masking on training data, a language generator for restoring masked words, and an encoder for detecting whether or not the restored sentence construction words are original, and a decoder unit including a generation word position detector for detecting a position of a word to be generated next, a language generator for determining a word suitable for the corresponding position, and a non-directional training data generator for decoder training.
    Type: Application
    Filed: December 2, 2021
    Publication date: June 9, 2022
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Eui Sok CHUNG, Hyun Woo KIM, Gyeong Moon PARK, Jeon Gue PARK, Hwa Jeon SONG, Byung Hyun YOO, Ran HAN
  • Patent number: 11222445
    Abstract: Embodiments of the disclosure relate to an input apparatus and a controlling method thereof, more particularly, to an input device for displaying a graphic in a detected color and an input touch form by detecting a color and a touch shape of an input tool for inputting a touch command. An input apparatus according to an embodiment includes a display: a first sensor configured to detect a touch position of a touch command input to the display from an input tool; a second sensor configured to detect a color of the input tool; and a controller configured to control a graphic corresponding to the input touch command to be displayed in the detected color at the detected touch position.
    Type: Grant
    Filed: October 26, 2018
    Date of Patent: January 11, 2022
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jeong Hyun Park, Young Ran Han
  • Publication number: 20210398004
    Abstract: Provided are a method and apparatus for online Bayesian few-shot learning. The present invention provides a method and apparatus for online Bayesian few-shot learning in which multi-domain-based online learning and few-shot learning are integrated when domains of tasks having data are sequentially given.
    Type: Application
    Filed: June 21, 2021
    Publication date: December 23, 2021
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Hyun Woo KIM, Gyeong Moon PARK, Jeon Gue PARK, Hwa Jeon SONG, Byung Hyun YOO, Eui Sok CHUNG, Ran HAN
  • Publication number: 20210374545
    Abstract: A knowledge increasing method includes calculating uncertainty of knowledge obtained from a neural network using an explicit memory, determining the insufficiency of the knowledge on the basis of the calculated uncertainty, obtaining additional data (learning data) for increasing insufficient knowledge, and training the neural network by using the additional data to autonomously increase knowledge.
    Type: Application
    Filed: May 27, 2021
    Publication date: December 2, 2021
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Hyun Woo KIM, Jeon Gue PARK, Hwa Jeon SONG, Yoo Rhee OH, Byung Hyun YOO, Eui Sok CHUNG, Ran HAN
  • Patent number: 11189468
    Abstract: The present invention discloses a magnetic filter tube, and relates to the technical field of magnetic filters. The magnetic filter tube includes a first rectangular tube and a second rectangular tube, where one end of the first rectangular tube is fixedly connected to one end of the second rectangular tube; the other end of the first rectangular tube forms an inlet of the magnetic filter tube; the inlet of the magnetic filter tube is connected with a cathode target flange; the other end of the second rectangular tube forms an outlet of the magnetic filter tube; the outlet of the magnetic filter tube is connected with a vacuum chamber; an inner wall of the first rectangular tube and an inner wall of the second rectangular tube are each provided with a protrusion and a groove; the protrusion is filled with cold water.
    Type: Grant
    Filed: May 26, 2020
    Date of Patent: November 30, 2021
    Assignees: Beijing Normal University, Wenli (Guangdong) Technology Co., Ltd.
    Inventors: Bin Liao, Xiaoping Ouyang, Qingsong Hua, Jun Luo, Lin Chen, Xu Zhang, Xianying Wu, Pan Pang, Ran Han, Minju Ying, Weifeng He, Guangyu He
  • Publication number: 20210355477
    Abstract: The present disclosure discloses a mutant of a lycopene epsilon cyclase (Lcye) gene crucial in a wheat carotenoid synthesis pathway and use thereof. The present disclosure provides the following proteins: (1) a protein obtained by substituting serine at position 253 of an Lcye-D1 protein with phenylalanine; (2) a derived protein that is obtained by subjecting the protein in (1) to substitution and/or deletion and/or addition of one or more amino acid residues and has the same ability as the protein in (1); (3) a protein that has a homology of more than 99%, more than 95%, more than 90%, more than 85%, or more than 80% with the amino acid sequence defined in any one of (1) and (2) and has the same function as the amino acid sequence; and (4) a fusion protein obtained by attaching a tag to N-terminus and/or C-terminus of the protein in any one of (1) to (3).
    Type: Application
    Filed: March 8, 2021
    Publication date: November 18, 2021
    Inventors: Shengnan ZHAI, Jianjun LIU, Haosheng LI, Jianmin SONG, Aifeng LIU, Xinyou CAO, Dungong CHENG, Zhendong ZHAO, Cheng LIU, Jun GUO, Ran HAN, Yan ZI, Faji LI, Xiaolu WANG