Jojic

Oliver Jojic, Annandale, VA US

Patent application number	Description	Published
20100158470	IDENTIFICATION OF SEGMENTS WITHIN AUDIO, VIDEO, AND MULTIMEDIA ITEMS - The invention pertains to methods, systems, and apparatus for identifying segments within a media item, the media segment including at least one of audio content and video content, comprising segmenting the media item into a plurality of segments as a function of subject matter, storing data identifying each segment and its subject matter, and organizing each segment within an ontology based on its subject matter.	06-24-2010
20100161580	METHOD AND APPARATUS FOR ORGANIZING SEGMENTS OF MEDIA ASSETS AND DETERMINING RELEVANCE OF SEGMENTS TO A QUERY - The invention pertains to methods, systems, and apparatus for identifying media items relevant to a selected subject matter, the method comprising determining the subject matter of a first media item, the first media item comprising at least one of audio content and video content, determining the classification within an ontology of the subject matter of the first media item, analyzing the ontology to identify other subject matter related to the subject matter of the first media item, and performing a search for other media items relevant to the subject matter of the first media item as a function of at least the other related subject matter according to the ontology.	06-24-2010

Patent application number	Description	Published
20090171640	POPULATION SEQUENCING USING SHORT READ TECHNOLOGIES - The claimed subject matter provides systems and/or methods that facilitate generating population sequences of strain variants included in a sample. Sequencing can be based on high throughput of short reads. Further, site variants exhibited in the short reads can be linked to reconstruct multiple full strains of a targeted gene, including low concentration variants in the sample. Cues in the short read data can be utilized to perform multi-strain assembly. For example, the cues can include different strain concentrations that lead to more frequently seen strains being responsible for more frequent reads and quilting of overlapping reads to infer mutation linkage over long stretches of DNA.	07-02-2009

Patent application number	Description	Published
20080282108	PROGRAM SYNTHESIS AND DEBUGGING USING MACHINE LEARNING TECHNIQUES - One embodiment is directed to synthesizing code fragments in a software routine using known inputs and corresponding expected outputs. A computer system provides a software routine with known inputs and corresponding expected outputs, infers software routine instructions based on the known inputs and corresponding expected outputs, and synthesizes a correctly functioning code fragment based on the inferred instructions. Another embodiment is directed to automatically resolving semantic errors in a software routine. A computer system provides the software routine with known inputs and corresponding expected outputs for portions of a program fragment where an error has been localized. The computer system learns a correctly functioning program fragment from pairs of input-output descriptions of the program fragment, determines the program statements that can transform given input states into given output states after execution of those program statements, and alters portions of the software routine with the learned program fragments.	11-13-2008