公开(公告)号：BRPI0621897B1

公开(公告)日：2018-03-20

申请号：BRPI0621897

申请日：2006-08-03

Applicant: IBM

Inventor： MARTIN G KIENZLE ,  VADIM SHEININ

IPC: G03B17/00 ,  G08B23/00 ,  H04N7/18

Abstract: sistema de vigilancia de video e metodo com reconhecimento de audio e video come inado. a presente invenção, de modo geral, refere-se a sistemas de vigilância e métodos para proporcionar segurança e, mais particularmente, a um novo sistema de reconhecimento de video e áudio on-line (tempo real) e processo para sistemas de vigilância.

公开(公告)号：GB2606920A

公开(公告)日：2022-11-23

申请号：GB202209966

申请日：2020-12-18

Applicant: IBM

Inventor： ELAHE KHORASANI ,  HANGU YEO ,  OCTAVIAN POPESCU ,  VADIM SHEININ

IPC: G06F16/28

Abstract: Methods, systems and computer readable media are provided for automatically creating a semantic model of a relational database for processing natural language queries. A computing device automatically extracts relational database metadata. The computing device prompts a user to enter textual labels for columns of the extracted metadata. The computing device automatically generates a schema annotation file based upon the relational database metadata and the textual labels for the columns. A natural language query is processed for the relational database using the schema annotation file.

公开(公告)号：GB2557535A

公开(公告)日：2018-06-20

申请号：GB201805522

申请日：2016-09-15

Applicant: IBM

Inventor： VADIM SHEININ ,  SIDDHARTH PATWARDHAN ,  BRANIMIR BOGURAEV ,  ELAHE KHORASANI ,  PETROS ZERFOS

IPC: G06F17/30 ,  G06F17/27

Abstract: An embodiment of the invention provides a method wherein a natural language query is received from a user with an interface. An ontological representation of data in a database is received with an input port, including names of concepts and names of concept properties. Template rules are received with the input port, the templates rules being language dependent and ontology independent, the template rules including widely used constructs of a language. Rules are automatically generated with a rule generation engine with the ontological representation of the data in the database and the template rules to identify entities and relations in the natural language query. Entities and relations are identified with a processor, the entities and relations being identified in the natural language query with the rules. The structured data language query is generated with a query generation engine from the entities and relations.