Patents by Inventor Intaik Park
Intaik Park 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: 11991531Abstract: A method is provided. The method includes receiving a first dimension set, extracting a first latent feature set from the first dimension set, training a first base predictor based on the first feature set, generating a second dimension set based on the first dimension set, the second dimension set having fewer dimensions than the first dimension set, extracting a second latent feature set from the second dimension set, training a second base predictor based on the second feature set, and generating a traffic prediction based on the first base predictor and the second base predictor.Type: GrantFiled: January 7, 2022Date of Patent: May 21, 2024Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Chengming Hu, Xi Chen, Ju Wang, Hang Li, Jikun Kang, Yi Tian Xu, Xue Liu, Di Wu, Seowoo Jang, Intaik Park, Gregory Lewis Dudek
-
Patent number: 11930414Abstract: Hybrid use of dual policies is provided to improve a communication system. In a multiple access scenario, when an inactive user equipment (UE) transitions to an active state, it may be become a burden to a radio cell on which it was previously camping. In some embodiments, hybrid load balancing is provided using a hierarchical machine learning paradigm based on reinforcement learning in which an LSTM generates a goal for one policy influencing cell reselection so that another policy influencing handover over active UEs can be assisted. The communication system as influenced by the policies is modeled as a Markov decision process (MDP). The policies controlling the active UEs and inactive UEs are coupled, and measureable system characteristics are improved. In some embodiments, policy actions depend at least in part on energy saving.Type: GrantFiled: April 12, 2023Date of Patent: March 12, 2024Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Jikun Kang, Xi Chen, Di Wu, Yi Tian Xu, Xue Liu, Gregory Lewis Dudek, Taeseop Lee, Intaik Park
-
Patent number: 11825371Abstract: An apparatus distributing communication load over a plurality of communication cells may select action centers from random cell reselection values, based on a standard deviation of an internet protocol (IP) throughout over the plurality of communication cells; input a first vector indicating a communication state of a communication system and a second vector indicating the standard deviation of the IP throughout of the plurality of communication cells, to a neural network to output a sum of the action centers and offsets as cell reselection parameters; and transmit the cell reselection parameters to the communication system to enable a base station of the communication system to perform a cell reselection based on the cell reselection parameters.Type: GrantFiled: May 28, 2021Date of Patent: November 21, 2023Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Di Wu, Jikun Kang, Yi Tian Xu, Jimmy Li, Michael Jenkin, Xue Liu, Xi Chen, Gregory Lewis Dudek, Intaik Park, Taeseop Lee
-
Publication number: 20230292142Abstract: Transfer learning based on prediction determines a similarity between a source base station and a target base station. Importance of parameters is determined and training is adjusted to respect the importance of parameters. A lack of historical data is compensated by selecting a base station as source base station which has a larger amount of historical data.Type: ApplicationFiled: May 19, 2023Publication date: September 14, 2023Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Xi CHEN, Ju WANG, Hang LI, Yi Tian XU, Di WU, Xue LIU, Gregory Lewis DUDEK, Taeseop LEE, Intaik PARK
-
Patent number: 11751115Abstract: Hybrid use of dual policies is provided to improve a communication system. In a multiple access scenario, when an inactive user equipment (UE) transitions to an active state, it may be become a burden to a radio cell on which it was previously camping. In some embodiments, hybrid load balancing is provided using a hierarchical machine learning paradigm based on reinforcement learning in which an LSTM generates a goal for one policy influencing cell reselection so that another policy influencing handover over active UEs can be assisted. The communication system as influenced by the policies is modeled as a Markov decision process (MDP). The policies controlling the active UEs and inactive UEs are coupled, and measureable system characteristics are improved. In some embodiments, policy actions depend at least in part on energy saving.Type: GrantFiled: June 30, 2021Date of Patent: September 5, 2023Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Jikun Kang, Xi Chen, Di Wu, Yi Tian Xu, Xue Liu, Gregory Lewis Dudek, Taeseop Lee, Intaik Park
-
Publication number: 20230247509Abstract: Hybrid use of dual policies is provided to improve a communication system. In a multiple access scenario, when an inactive user equipment (UE) transitions to an active state, it may be become a burden to a radio cell on which it was previously camping. In some embodiments, hybrid load balancing is provided using a hierarchical machine learning paradigm based on reinforcement learning in which an LSTM generates a goal for one policy influencing cell reselection so that another policy influencing handover over active UEs can be assisted. The communication system as influenced by the policies is modeled as a Markov decision process (MDP). The policies controlling the active UEs and inactive UEs are coupled, and measureable system characteristics are improved. In some embodiments, policy actions depend at least in part on energy saving.Type: ApplicationFiled: April 12, 2023Publication date: August 3, 2023Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Jikun KANG, Xi Chen, Di Wu, Yi Tian Xu, Xue Liu, Gregory Lewis Dudek, Taeseop Lee, Intaik Park
-
Patent number: 11696153Abstract: Transfer learning based on prediction determines a similarity between a source base station and a target base station. Importance of parameters is determined and training is adjusted to respect the importance of parameters. A lack of historical data is compensated by selecting a base station as source base station which has a larger amount of historical data.Type: GrantFiled: August 2, 2021Date of Patent: July 4, 2023Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Xi Chen, Ju Wang, Hang Li, Yi Tian Xu, Di Wu, Xue Liu, Gregory Lewis Dudek, Taeseop Lee, Intaik Park
-
Patent number: 11481616Abstract: To obtain one or more recommendations for the migration of a database to a cloud computing system, information about performance of the database operating under a workload may be obtained. A first machine learning model (e.g., a neural network-based autoencoder) may be used to generate a compressed representation of characteristics of the database operating under the workload. The compressed representation may then be provided as input to a second machine learning model (e.g., a neural network-based classifier), which outputs a recommendation regarding a characteristic (e.g., size, configuration, level of service) of the cloud database to which the database should be migrated. This type of recommendation may be made prior to migration, thereby making it easier to properly estimate the cost of running the cloud database and plan the migration accordingly.Type: GrantFiled: November 21, 2018Date of Patent: October 25, 2022Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Mitchell Gregory Spryn, Intaik Park, Felipe Vieira Frujeri, Vijay Govind Panjeti, Ashok Sai Madala, Ajay Kumar Karanam
-
Publication number: 20220338019Abstract: A method is provided. The method includes receiving a first dimension set, extracting a first latent feature set from the first dimension set, training a first base predictor based on the first feature set, generating a second dimension set based on the first dimension set, the second dimension set having fewer dimensions than the first dimension set, extracting a second latent feature set from the second dimension set, training a second base predictor based on the second feature set, and generating a traffic prediction based on the first base predictor and the second base predictor.Type: ApplicationFiled: January 7, 2022Publication date: October 20, 2022Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Chengming HU, Xi CHEN, Ju WANG, Hang Li, Jikun KANG, Yi Tian XU, Xue LIU, Di WU, Seowoo JANG, Intaik PARK, Gregory Lewis DUDEK
-
Publication number: 20220150786Abstract: Hybrid use of dual policies is provided to improve a communication system. In a multiple access scenario, when an inactive user equipment (UE) transitions to an active state, it may be become a burden to a radio cell on which it was previously camping. In some embodiments, hybrid load balancing is provided using a hierarchical machine learning paradigm based on reinforcement learning in which an LSTM generates a goal for one policy influencing cell reselection so that another policy influencing handover over active UEs can be assisted. The communication system as influenced by the policies is modeled as a Markov decision process (MDP). The policies controlling the active UEs and inactive UEs are coupled, and measureable system characteristics are improved. In some embodiments, policy actions depend at least in part on energy saving.Type: ApplicationFiled: June 30, 2021Publication date: May 12, 2022Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Jikun KANG, Xi CHEN, Di WU, Yi Tian XU, Xue LIU, Gregory Lewis DUDEK, Taeseop LEE, Intaik PARK
-
Publication number: 20220150785Abstract: An apparatus distributing communication load over a plurality of communication cells may select action centers from random cell reselection values, based on a standard deviation of an internet protocol (IP) throughout over the plurality of communication cells; input a first vector indicating a communication state of a communication system and a second vector indicating the standard deviation of the IP throughout of the plurality of communication cells, to a neural network to output a sum of the action centers and offsets as cell reselection parameters; and transmit the cell reselection parameters to the communication system to enable a base station of the communication system to perform a cell reselection based on the cell reselection parameters.Type: ApplicationFiled: May 28, 2021Publication date: May 12, 2022Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Di WU, Jikun KANG, Yi Tian XU, Jimmy LI, Michael JENKIN, Xue LIU, Xi CHEN, Gregory Lewis DUDEK, Intaik PARK, Taeseop LEE
-
Publication number: 20220053341Abstract: Transfer learning based on prediction determines a similarity between a source base station and a target base station. Importance of parameters is determined and training is adjusted to respect the importance of parameters. A lack of historical data is compensated by selecting a base station as source base station which has a larger amount of historical data.Type: ApplicationFiled: August 2, 2021Publication date: February 17, 2022Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Xi CHEN, Ju WANG, Hang Li, Yi Tian Xu, Di WU, Xue LIU, Gregory Lewis DUDEK, Taeseop LEE, Intaik PARK
-
Publication number: 20220051135Abstract: Rapid and data-efficient training of an artificial intelligence (AI) algorithm are disclosed. Ground truth data are not available and a policy must be learned based on limited interactions with a system. A policy bank is used to explore different policies on a target system with shallow probing. A target policy is chosen by comparing a good policy from the shallow probing with a base target policy which has evolved over other learning experiences. The target policy then interacts with the target system and a replay buffer is built up. The base target policy is then updated using gradients found with respect to the transition experience stored in the replay buffer. The base target policy is quickly learned and is robust for application to new, unseen, systems.Type: ApplicationFiled: December 31, 2020Publication date: February 17, 2022Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Di Wu, Jikun Kang, Hang Li, Xi Chen, Yi Tian Xu, Dmitriy Rivkin, Taeseop Lee, Intaik Park, Michael Jenkin, Xue Liu, Gregory Lewis Dudek
-
Publication number: 20200005136Abstract: To obtain one or more recommendations for the migration of a database to a cloud computing system, information about performance of the database operating under a workload may be obtained. A first machine learning model (e.g., a neural network-based autoencoder) may be used to generate a compressed representation of characteristics of the database operating under the workload. The compressed representation may then be provided as input to a second machine learning model (e.g., a neural network-based classifier), which outputs a recommendation regarding a characteristic (e.g., size, configuration, level of service) of the cloud database to which the database should be migrated. This type of recommendation may be made prior to migration, thereby making it easier to properly estimate the cost of running the cloud database and plan the migration accordingly.Type: ApplicationFiled: November 21, 2018Publication date: January 2, 2020Inventors: Mitchell Gregory SPRYN, Intaik PARK, Felipe VIEIRA FRUJERI, Vijay Govind PANJETI, Ashok Sai MADALA, Ajay Kumar KARANAM
-
Patent number: 9898457Abstract: Examples for detecting and removing non-natural language within natural language to enhance performing content analysis on the natural language are provided herein. A plurality of terms is identified in a phrase, and a sliding window having a defined length is placed over a first sequence of terms from the plurality of terms. The first sequence of terms includes a first term, a second term, and a third term, the first term and the third term being adjacent to the second term. Based on the first term, the second term, and the third term, a determination is made as to whether the second term represents non-natural language. Upon determining that the second term is non-natural language, the second term is labeled as non-natural language and is removed from the plurality of terms based on determining the second term as non-natural language.Type: GrantFiled: October 3, 2016Date of Patent: February 20, 2018Assignee: Microsoft Technology Licensing, LLCInventors: Pranab Mohanty, Intaik Park, Kieran Brantner-Magee, Lucas Lin, Saikat Sen, Korhan Ileri