DATA PROCESSING SYSTEM, DATABASE MANAGEMENT SYSTEM, AND DATA PROCESSING METHOD

摘要

A DBMS manages a database including a structured data group capable of communicating with a plurality of execution nodes that manage an unstructured data group and execute parallel distributed processing. Each of the plurality of execution nodes is capable of creating data to be processed based on at least one structured data of the structured data group managed by the DBMS and at least one unstructured data of the unstructured data group managed by the plurality of execution nodes, and performing processing using the data to be processed. Based on control information (information about controlling the provision of two or more structured data designated in a reference request sent to the DBMS), the two or more structured data are acquired by the DBMS from the database, and provided from the DBMS to two or more execution nodes among the plurality of execution nodes.

主权项

1. A data processing system, comprising:
a database management system (called “DBMS,” hereinafter) configured to be capable of communicating with a plurality of execution nodes that manage an unstructured data group which is a set of one or more unstructured data and execute parallel distributed processing, and configured to manage a database including a structured data group which is a set of one or more structured data; and a management node configured to be capable of communicating with the plurality of execution nodes and the DBMS, and configured to transmit a reference request to the DBMS, each of the plurality of execution nodes being configured to be capable of creating data to be processed based on at least one structured data of the structured data group managed by the DBMS and at least one unstructured data of the unstructured data group managed by the plurality of execution nodes, and performing processing using the data to be processed, and based on control information, which is information about controlling the provision of two or more structured data designated in the reference request, the two or more structured data being configured to be acquired by the DBMS from the database and provided from the DBMS to two or more execution nodes among the plurality of execution nodes.