Patents by Inventor Bong-Jun Ko

Bong-Jun Ko 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: 20190318268
    Abstract: A training process of a machine learning model is executed at the edge node for a number of iterations to generate a model parameter based at least in part on a local dataset and a global model parameter. A resource parameter set indicative of resources available at the edge node is estimated. The model parameter and the resource parameter set are sent to a synchronization node. Updates to the global model parameter and the number of iterations are received from the synchronization node based at least in part on the model parameter and the resource parameter set of edge nodes. The training process of the machine learning model is repeated at the edge node to determine an update to the model parameter based at least in part on the local dataset and updates to the global model parameter and the number of iterations from the synchronization node.
    Type: Application
    Filed: April 13, 2018
    Publication date: October 17, 2019
    Inventors: Shiqiang Wang, Tiffany Tuor, Theodoros Salonidis, Christian Makaya, Bong Jun KO
  • Publication number: 20190272299
    Abstract: A data mining method, system, and non-transitory computer readable medium, include defining a set of filter constraints as a filter function for clustering users' private records of data of a private domain, selecting a subset of users' public records of data from a filtered set of data from a public domain that is common with the users' private records of data, and creating a data file including the matched user of the private domain to the public records of the user of the private domain, where the set of the filter constraints comprises a function that captures the subset of the users' public records of data who are of interest to the private domain, and only performs data mining with that set of information from the public domain.
    Type: Application
    Filed: May 10, 2019
    Publication date: September 5, 2019
    Inventors: Nirmit V. Desai, Bong Jun Ko, Jorge J. Ortiz, Swati Rallapalli, Theodores Salonidis, Rahul Urgaonkar, Dinesh C. Verma
  • Patent number: 10394912
    Abstract: A data mining method, system, and non-transitory computer readable medium, include defining a set of filter constraints as a filter function for clustering users' private records of data of a private domain, obtaining a set of data from a public domain by applying the filter function to users' public records of data of the public domain, selecting a subset of the users' public records of data that is common with the users' private records of data, and performing data mining on the selected subset of the users' public records of data in combination with the users' private records of data to match a user of the private domain to public records of the user of the private domain.
    Type: Grant
    Filed: June 20, 2016
    Date of Patent: August 27, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Nirmit V. Desai, Bong Jun Ko, Jorge J. Ortiz, Swati Rallapalli, Theodoros Salonidis, Rahul Urgaonkar, Dinesh C. Verma
  • Patent number: 10255453
    Abstract: Embodiments of the present invention may involve a method, system, and computer program product for controlling privacy in a face recognition application. A computer may receive an input including a face recognition query and a digital image of a face. The computer may identify a target user associated with a facial signature in a first database based at least in part on a statistical correlation between a detected facial signature and one or more facial signatures in the first database. The computer may extract a profile of the target user from a second database. The profile of the target user may include one or more privacy preferences. The computer may generate a customized profile of the target user. The customized profile may omit one or more elements of the profile of the target user based on the one or more privacy preferences and/or a current context.
    Type: Grant
    Filed: January 22, 2018
    Date of Patent: April 9, 2019
    Assignee: International Business Machines Corporation
    Inventors: Seraphin B. Calo, Bong Jun Ko, Kang-Won Lee, Theodoros Salonidis, Dinesh C. Verma
  • Patent number: 10111121
    Abstract: Various embodiments manage service issues within a wireless communication network. In one embodiment, a one or more call detail records associated with a set of wireless communication devices of a wireless communication network is received. A set of information within each of the one or more call detail records is compared to a baseline statistical model. The baseline statistical model identifies a normal operating state of the wireless communication network. At least one outlier call detail record in the one or more call detail records is identified based on the comparison. The at least one outlier call detail record indicates that at least one wireless communication device associated with the at least one outlier call detail record experienced one or more service issues.
    Type: Grant
    Filed: April 25, 2017
    Date of Patent: October 23, 2018
    Assignee: International Business Machines Corporation
    Inventors: Bong Jun Ko, Kang-Won Lee, Ramya Raghavendra, Murtaza Zafer
  • Patent number: 10097510
    Abstract: The present disclosure relates generally to the field of identifying network flows (e.g., IP flows) under network address translation. In various examples, identifying network flows (e.g., IP flows) under network address translation may be implemented in the form of methods and/or algorithms.
    Type: Grant
    Filed: August 14, 2013
    Date of Patent: October 9, 2018
    Assignee: International Business Machines Corporation
    Inventors: Dakshi Agrawal, Bong Jun Ko, Thai Franck Le, Robert B. Nicholson, Vasileios Pappas, Dinesh C. Verma
  • Patent number: 10084696
    Abstract: Systems, methods and computer program products for aliasing of named data objects (in named data networks) and entities for named data networks (e.g., named graphs for named data networks). In various examples, aliasing of named data objects may be implemented in one or more named data networks in the form of systems, methods and/or algorithms. In other examples, named graphs may be implemented in one or more named data networks in the form of systems, methods and/or algorithms.
    Type: Grant
    Filed: July 19, 2016
    Date of Patent: September 25, 2018
    Assignee: International Business Machines Corporation
    Inventors: Raheleh B. Dilmaghani, Bong Jun Ko, Kang-Won Lee, Vasileios Pappas, Ramya Raghavendra, Yang Song
  • Publication number: 20180255123
    Abstract: Status information associated with a set of cloud servers is received. Each cloud server in the set has an associated cloud agent, and the status information includes available computing resources and associated resource compensation information. Aggregated status information is determined for the one or more cloud servers, and the aggregated status information is forwarded to one or more of the cloud agents. A request for performing a computation is received in which the request includes a request specification. A selected cloud agent associated with one or more cloud servers most likely to accept the request based upon the aggregated status information and request specification is determined.
    Type: Application
    Filed: March 3, 2017
    Publication date: September 6, 2018
    Applicant: International Business Machines Corporation
    Inventors: Nirmit V. Desai, Douglas M. Freimuth, Bong Jun Ko, Theodoros Salonidis, Shiqiang Wang
  • Publication number: 20180225357
    Abstract: An approach for self-improving classification. The approach receives sensor data of a machine, wherein the sensor data is collected during operation of the machine. The approach defines one or more categories, wherein each category of the one or more categories is associated with one or more parameters. The approach determines whether the sensor data matches one or more parameters of a first category of the one or more categories. Responsive to a determination that the sensor data matches the one or more parameters of the first category, the approach classifies the sensor data into the first category. The approach applies a first category label to the sensor data, wherein the first category label is associated with the first category.
    Type: Application
    Filed: February 15, 2018
    Publication date: August 9, 2018
    Inventors: Nancy A. Greco, Bong Jun Ko, Maroun Touma, Dinesh C. Verma, David A. Wood
  • Publication number: 20180225355
    Abstract: An approach for self-improving classification. The approach receives sensor data of a machine, wherein the sensor data is collected during operation of the machine. The approach defines one or more categories, wherein each category of the one or more categories is associated with one or more parameters. The approach determines whether the sensor data matches one or more parameters of a first category of the one or more categories. Responsive to a determination that the sensor data matches the one or more parameters of the first category, the approach classifies the sensor data into the first category. The approach applies a first category label to the sensor data, wherein the first category label is associated with the first category.
    Type: Application
    Filed: February 7, 2017
    Publication date: August 9, 2018
    Inventors: Nancy A. Greco, Bong Jun Ko, Maroun Touma, Dinesh C. Verma, David A. Wood
  • Publication number: 20180144151
    Abstract: Embodiments of the present invention may involve a method, system, and computer program product for controlling privacy in a face recognition application. A computer may receive an input including a face recognition query and a digital image of a face. The computer may identify a target user associated with a facial signature in a first database based at least in part on a statistical correlation between a detected facial signature and one or more facial signatures in the first database. The computer may extract a profile of the target user from a second database. The profile of the target user may include one or more privacy preferences. The computer may generate a customized profile of the target user. The customized profile may omit one or more elements of the profile of the target user based on the one or more privacy preferences and/or a current context.
    Type: Application
    Filed: January 22, 2018
    Publication date: May 24, 2018
    Inventors: SERAPHIN B. CALO, BONG JUN KO, KANG-WON LEE, THEODOROS SALONIDIS, DINESH C. VERMA
  • Publication number: 20180121858
    Abstract: Embodiments include methods, systems, and computer program products for scheduling service personnel. Aspects include obtaining observational data for a plurality of service individuals. Aspects also include developing a personality profile for each of the plurality of service individuals based on the observational data. Aspects include receiving a service request from a customer. Then, aspects include obtaining attribute data about the customer to determine one or more inferred personality traits of the customer and analyzing the one or more personality traits of the customer and the personality profile of each of the plurality of service individuals to determine a personality matching score for each of the plurality of service individuals.
    Type: Application
    Filed: October 28, 2016
    Publication date: May 3, 2018
    Inventors: DOUGLAS M. FREIMUTH, BONG JUN KO, DINESH C. VERMA, SHIQIANG WANG
  • Patent number: 9934397
    Abstract: Embodiments of the present invention may involve a method, system, and computer program product for controlling privacy in a face recognition application. A computer may receive an input including a face recognition query and a digital image of a face. The computer may identify a target user associated with a facial signature in a first database based at least in part on a statistical correlation between a detected facial signature and one or more facial signatures in the first database. The computer may extract a profile of the target user from a second database. The profile of the target user may include one or more privacy preferences. The computer may generate a customized profile of the target user. The customized profile may omit one or more elements of the profile of the target user based on the one or more privacy preferences and/or a current context.
    Type: Grant
    Filed: December 15, 2015
    Date of Patent: April 3, 2018
    Assignee: International Business Machines Corporation
    Inventors: Seraphin B. Calo, Bong Jun Ko, Kang-Won Lee, Theodoros Salonidis, Dinesh C. Verma
  • Patent number: 9894559
    Abstract: Various embodiments estimate network load in a wireless communication network. In one embodiment, at least one call detail record associated with a wireless communication network is received. A topology representing the network is analyzed. The topology includes a plurality of nodes each representing a network element within the wireless communication network. The topology also includes a plurality of edges between two or more of the plurality of nodes. Each of the plurality of edges indicates that the two or more plurality of nodes are communicatively coupled to each other within the network. A set of paths is identified between two or more nodes in the plurality of nodes corresponding to a set of call flow information within the at least one call detail record. A state of each network element represented by the two or more nodes in the set of paths is determined based on the call detail record.
    Type: Grant
    Filed: March 31, 2016
    Date of Patent: February 13, 2018
    Assignee: International Business Machines Corporation
    Inventors: Bong Jun Ko, Vinay Kumar Kolar, Kang-Won Lee, Ramya Raghavendra, Dinesh Verma, Murtaza Zafer
  • Publication number: 20180033074
    Abstract: A recipe recommendation method, system, and non-transitory computer readable medium, include inferring a fine-grained user food profile from user data, recommending a recipe for the user based on a fitness score associated with a user-recipe pairing according to the fine-grained user food profile and recipe data, extracting ingredients from the recommended recipe, and creating a shopping list from the extracted ingredients.
    Type: Application
    Filed: July 31, 2016
    Publication date: February 1, 2018
    Inventors: Keith William Grueneberg, Bong Jun Ko, Christian Makaya, Mikhil Nandkishore MasIi, Jorge Jose Ortiz, Swati Rallapalli, Theodoros Salonidis, Rahul Urgaonkar, Dinesh C. Verma, Xiping Wang
  • Patent number: 9858404
    Abstract: Embodiments of the present invention may involve a method, system, and computer program product for controlling privacy in a face recognition application. A computer may receive an input including a face recognition query and a digital image of a face. The computer may identify a target user associated with a facial signature in a first database based at least in part on a statistical correlation between a detected facial signature and one or more facial signatures in the first database. The computer may extract a profile of the target user from a second database. The profile of the target user may include one or more privacy preferences. The computer may generate a customized profile of the target user. The customized profile may omit one or more elements of the profile of the target user based on the one or more privacy preferences and/or a current context.
    Type: Grant
    Filed: January 11, 2017
    Date of Patent: January 2, 2018
    Assignee: International Business Machines Corporation
    Inventors: Seraphin B. Calo, Bong Jun Ko, Kang-Won Lee, Theodoros Salonidis, Dinesh C. Verma
  • Publication number: 20170371718
    Abstract: Methods are provided. A method includes announcing to a network meta information describing each of a plurality of distributed data sources. The method further includes propagating the meta information amongst routing elements in the network. The method also includes inserting into the network a description of distributed datasets that match a set of requirements of the analytics task. The method additionally includes delivering, by the routing elements, a copy of the analytics task to locations of respective ones of the plurality of distributed data sources that include the distributed datasets that match the set of requirements of the analytics task.
    Type: Application
    Filed: June 22, 2016
    Publication date: December 28, 2017
    Inventors: Bong Jun Ko, Theodoros Salonidis, Rahul Urgaonkar, Dinesh C. Verma
  • Publication number: 20170364595
    Abstract: A data mining method, system, and non-transitory computer readable medium, include defining a set of filter constraints as a filter function for clustering users' private records of data of a private domain, obtaining a set of data from a public domain by applying the filter function to users' public records of data of the public domain, selecting a subset of the users' public records of data that is common with the users' private records of data, and performing data mining on the selected subset of the users' public records of data in combination with the users' private records of data to match a user of the private domain to public records of the user of the private domain.
    Type: Application
    Filed: June 20, 2016
    Publication date: December 21, 2017
    Inventors: Nirmit V. Desai, Bong Jun Ko, Jorge J. Ortiz, Swati Rallapalli, Theodoros Salonidis, Rahul Urgaonkar, Dinesh C. Verma
  • Publication number: 20170364820
    Abstract: A provenance method, system, and non-transitory computer readable medium for a plurality of eidetic systems having logs, include a log-segment clustering circuit configured to crawl the logs of each of the eidetic systems to cluster segments across the logs of temporally correlated events into clustered segments, a probabilistic interleaving circuit configured to analyze the correlated segments to interleave an order of processes in the logs and assign a probability to the order of the processes occurring, and a probabilistic linearization circuit configured to create a probability tree which includes a total probability that a process in the clustered segments causes a next process in the clustered segments until an end of the temporal event of the clustered segments for each of the interleaved order of processes interleaved by the probabilistic interleaving circuit.
    Type: Application
    Filed: June 20, 2016
    Publication date: December 21, 2017
    Inventors: Bong Jun Ko, Christian Makaya, Jorge J. Ortiz, Swati Rallapalli, Dinesh C. Verma, Xiping Wang
  • Patent number: 9800542
    Abstract: The present disclosure relates generally to the field of identifying network flows (e.g., IP flows) under network address translation. In various examples, identifying network flows (e.g., IP flows) under network address translation may be implemented in the form of systems and/or algorithms.
    Type: Grant
    Filed: March 14, 2013
    Date of Patent: October 24, 2017
    Assignee: International Business Machines Corporation
    Inventors: Dakshi Agrawal, Bong Jun Ko, Thai Franck Le, Robert B. Nicholson, Vasileios Pappas, Dinesh C. Verma