Patents by Inventor Songyun Duan
Songyun Duan 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: 20130332466Abstract: Data elements from data sources and having a data value set are linked by using hash functions to determine a dimensionally reduced instance signature for each data element based on all data values associated with that data element to yield a plurality of dimensionally reduced instance signatures of equivalent fixed size such that similarities among the data values in the data value sets across all data elements is maintained among the plurality of instance signatures. Candidate pairs of data elements to link are identified using the plurality of instance signatures in locality sensitive hash functions, and a similarity index is generated for each candidate pair using a pre-determined measure of similarity. Candidate pairs of data elements having a similarity index above a given threshold are linked.Type: ApplicationFiled: June 8, 2012Publication date: December 12, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Mihaela Ancuta Bornea, Songyun Duan, Achille Belly Fokoue-Nkoutche, Oktie Hassanzadeh, Anastasios Kementsietsidis, Kavitha Srinivas, Michael J. Ward
-
Publication number: 20130332467Abstract: Data elements from data sources and having a data value set are linked by using hash functions to determine a dimensionally reduced instance signature for each data element based on all data values associated with that data element to yield a plurality of dimensionally reduced instance signatures of equivalent fixed size such that similarities among the data values in the data value sets across all data elements is maintained among the plurality of instance signatures. Candidate pairs of data elements to link are identified using the plurality of instance signatures in locality sensitive hash functions, and a similarity index is generated for each candidate pair using a pre-determined measure of similarity. Candidate pairs of data elements having a similarity index above a given threshold are linked.Type: ApplicationFiled: July 8, 2012Publication date: December 12, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Mihaela Ancuta Bornea, Songyun Duan, Achille Belly Fokoue-Nkoutche, Oktie Hassanzadeh, Anastasios Kementsietsidis, Kavitha Srinivas, Michael J. Ward
-
Patent number: 8589331Abstract: A method for predictive analytics in a semi-structured process including receiving traces of the semi-structured process, at least one of the traces including a document content value, determining a process model from the traces, the process model comprising tasks at nodes of the semi-structured process and embodies all possible execution sequences in the process, determining a probabilistic graph including a probability at each of the tasks of the semi-structured process advancing from one task to another task, and combining the process model and probabilistic graph to determine a probabilistic process model including probabilities and strengths of transitions between tasks.Type: GrantFiled: October 22, 2010Date of Patent: November 19, 2013Assignee: International Business Machines CorporationInventors: Songyun Duan, Paul T. Keyser, Rania Yousef Khalaf, Geetika T. Lakshmanan, Davood Shamsi
-
Patent number: 8442863Abstract: A “Real-Time-Ready Analyzer” combines a data stream management system (DSMS) with a map-reduce (M-R) framework to construct a streaming map-reduce framework that is suitable for real-time Behavioral Targeting (BT) (or other temporal queries). The Real-Time-Ready Analyzer allows users to write “dual-intent” temporal analysis queries for BT. These queries are succinct and easy to express, scale well on large-scale offline data, and can also work over real-time data. Further, the Real-Time-Ready Analyzer uses the aforementioned streaming map-reduce framework to provide dual-intent algorithms for end-to-end BT phases. Experiments using real data from an advertisement system show that the Real-Time-Ready Analyzer is very efficient and incurs orders-of-magnitude lower development effort than conventional systems.Type: GrantFiled: June 17, 2010Date of Patent: May 14, 2013Assignee: Microsoft CorporationInventors: Badrish Chandramouli, Jonathan Goldstein, Xin Jin, Balan Sethu Raman, Songyun Duan
-
Patent number: 8370359Abstract: Computer-implemented methods for mapping an element of a source information model to an element of a target information model, forming a cluster of elements for mapping across information models, and evaluating a mapping of elements across information models, and a system and computer program product thereof. The method of mapping an element of a source information model to an element of a target information model includes: receiving information for mapping a first element in a source cluster to an element in the target information model; mapping the first element to the target element using the received information for mapping the first element to the target element; and mapping all other elements in the source cluster to the target element.Type: GrantFiled: October 21, 2010Date of Patent: February 5, 2013Assignee: International Business Machines CorporationInventors: Brian Patrick Byrne, Songyun Duan, Achille Fokoue-Nkoutche, Brendan O'Sullivan, Kavitha Srinivas
-
Publication number: 20130006984Abstract: According to an aspect of the present principles, a method is provided for generating resource description framework benchmarks. The method includes deriving a resultant benchmark dataset with a user specified size and a user specified coherence from and with respect to an input dataset of a given size and a given coherence by determining which triples of subject-property-object to add to the input dataset or remove from the input dataset to derive the resultant benchmark dataset.Type: ApplicationFiled: September 10, 2012Publication date: January 3, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: SONGYUN DUAN, ANASTASIOS KEMENTSIETSIDIS, KAVITHA SRINIVAS, OCTIVIAN UDREA
-
Publication number: 20120259792Abstract: Systems and methods are provided for the automatic detection of different types of changes in a business process. A system includes a transformer for performing a transformation on data derived from process traces or models extracted from the processes traces to generate transformed data. The process traces are for a business process corresponding to a set of related tasks for a specified goal. Each of the models has at least a transition matrix of dimension N×N, where N is a total number of the related tasks. The system further includes a change detector for performing change detection on the transformed data to identify at least one of when a change occurs in the business process and a degree of the change.Type: ApplicationFiled: April 6, 2011Publication date: October 11, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Songyun Duan, Paul T. Keyser, Geetika T. Lakshmanan, Davood Shamsi
-
Publication number: 20120246154Abstract: Methods and systems for aggregating search query results include receiving search query results and schema information for the query results from multiple heterogeneous sources, determining types for elements of the query results based on the schema information, determining potential aggregations for the query results based on the types, which are based on accumulated information from the plurality of heterogeneous resources, and aggregating the query results according to one or more of the potential aggregations.Type: ApplicationFiled: March 23, 2011Publication date: September 27, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Songyun Duan, Achille B. Fokoue-Nfoutche, Oktie Hassanzadeh, Anastasios Kementsietsidis, Kavitha Srinivas, Michael J. Ward
-
Publication number: 20120246175Abstract: Methods and systems for determining schema element types are shown that include pooling potential annotations for an element of an unlabeled schema from a plurality of heterogeneous sources, scoring the pool of potential annotations according to relevancy using information using instance information from the plurality of heterogeneous sources to produce a relevancy score, and annotating the element of the unlabeled schema using the most relevant potential annotations.Type: ApplicationFiled: March 23, 2011Publication date: September 27, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Songyun Duan, Achille B. Fokoue-Nkoutche, Oktie Hassanzadeh, Anastasios Kementsietsidis, Kavitha Srinivas, Michael J. Ward
-
Publication number: 20120197884Abstract: According to an aspect of the present principles, a method is provided for generating resource description framework benchmarks. The method includes deriving a resultant benchmark dataset with a user specified size and a user specified coherence from and with respect to an input dataset of a given size and a given coherence by determining which triples of subject-property-object to add to the input dataset or remove from the input dataset to derive the resultant benchmark dataset.Type: ApplicationFiled: January 28, 2011Publication date: August 2, 2012Applicant: International Business Machines CorporationInventors: SONGYUN DUAN, ANASTASIOS KEMENTSIETSIDIS, KAVITHA SRINIVAS, OCTAVIAN UDREA
-
Publication number: 20120101974Abstract: A method for predictive analytics in a semi-structured process including receiving traces of the semi-structured process, at least one of the traces including a document content value, determining a process model from the traces, the process model comprising tasks at nodes of the semi-structured process and embodies all possible execution sequences in the process, determining a probabilistic graph including a probability at each of the tasks of the semi-structured process advancing from one task to another task, and combining the process model and probabilistic graph to determine a probabilistic process model including probabilities and strengths of transitions between tasks.Type: ApplicationFiled: October 22, 2010Publication date: April 26, 2012Applicant: International Business Machines CorporationInventors: Songyun Duan, Paul T. Keyser, Rania Yousef Khalaf, Geetika T. Lakshmanan, Davood Shamsi
-
Publication number: 20120102032Abstract: Computer-implemented methods for mapping an element of a source information model to an element of a target information model, forming a cluster of elements for mapping across information models, and evaluating a mapping of elements across information models, and a system and computer program product thereof. The method of mapping an element of a source information model to an element of a target information model includes: receiving information for mapping a first element in a source cluster to an element in the target information model; mapping the first element to the target element using the received information for mapping the first element to the target element; and mapping all other elements in the source cluster to the target element.Type: ApplicationFiled: October 21, 2010Publication date: April 26, 2012Applicant: International Business Machines CorporationInventors: Brian Byrne, Songyun Duan, Achille Fokoue-Nkoutche, Brendan O'Sullivan, Kavitha Srinivas
-
Publication number: 20120066166Abstract: A method for predictive analytics for a process includes receiving at least one trace of the process, building a probabilistic graph modeling the at least one trace, determining content at each node of the probabilistic graph, wherein a node represents an activity of the process and at least one node is a decision node, modeling each decision node as a respective decision tree, and predicting, for an execution of the process, a path in the probabilistic graph from any decision node to a prediction target node of a plurality of prediction target nodes given the content.Type: ApplicationFiled: September 10, 2010Publication date: March 15, 2012Applicant: International Business Machines CorporationInventors: Francisco Phelan Curbera, Songyun Duan, Paul Keyser, Rania Khalaf, Geetika T. Lakshmanan
-
Publication number: 20120047114Abstract: A method of performing a graph query issued by a user is provided. The method includes performing on a processor, receiving a user graph query; rewriting the user graph query as a new query based on a query policy expressed in a graph query language; and performing the new query on graph data to obtain a result.Type: ApplicationFiled: August 17, 2010Publication date: February 23, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Songyun Duan, Anastasios Kementsietsidis, Wangchao Le, Min Wang
-
Publication number: 20120047124Abstract: A method of processing a query is provided. The method includes performing on a processor: receiving a database query that includes a plurality of predicates that associate a subject with an object, where one or more of the predicates is a variable predicate; generating at least one new query by selectively replacing the at least one variable predicate in the database query with a non-variable predicate; and performing the at least one new database query on a database to obtain a query result.Type: ApplicationFiled: August 17, 2010Publication date: February 23, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Songyun Duan, Anastasios Kementsietsidis, Wangchao Le, Min Wang
-
Publication number: 20110313844Abstract: A “Real-Time-Ready Analyzer” combines a data stream management system (DSMS) with a map-reduce (M-R) framework to construct a streaming map-reduce framework that is suitable for real-time Behavioral Targeting (BT) (or other temporal queries). The Real-Time-Ready Analyzer allows users to write “dual-intent” temporal analysis queries for BT. These queries are succinct and easy to express, scale well on large-scale offline data, and can also work over real-time data. Further, the Real-Time-Ready Analyzer uses the aforementioned streaming map-reduce framework to provide dual-intent algorithms for end-to-end BT phases. Experiments using real data from an advertisement system show that the Real-Time-Ready Analyzer is very efficient and incurs orders-of-magnitude lower development effort than conventional systems.Type: ApplicationFiled: June 17, 2010Publication date: December 22, 2011Applicant: MICROSOFT CORPORATIONInventors: Badrish Chandramouli, Jonathan Goldstein, Xin Jin, Balan Sethu Raman, Songyun Duan