Oracle International Corporation

Prashant Pandey

Eakta Aggarwal

Richard Yungning Liu

Robert Cooke Zwiebach

Techniques for generating a multidimensional database query are disclosed. A system receives a user-supplied natural language query and performs natural language processing to extract a literal from the natural language query. The system performs a lookup of the literal in one or more dictionary data structures associated with a multidimensional database, to determine that the literal is associated with a particular dimension of multiple dimensions in the multidimensional database. The system performs a lookup of the literal and the dimension in the one or more dictionary data structures, to determine that the literal is associated with a particular member of the dimension. The system generates a multidimensional database query to satisfy the user-supplied natural language query. The multidimensional database query includes a query clause that references the particular member of the dimension.

Generating multidimensional database queries

Techniques for generating a report recommendation are disclosed. A system receives a request to display a report. The system computes report relevancy scores for other reports, based at least in part on a set of rules including one or more report relevancy criteria. Each report relevancy score measures relevancy of a particular report to the requested report. The system determines that a particular report relevancy score, associated with one of the other reports, satisfies one or more report recommendation criteria. Responsive to the request to display the requested report, the system displays the requested report and, based on the particular report relevancy score satisfying the one or more report recommendation criteria, also displays a recommendation corresponding to the other report.

Report recommendation engine

Techniques for processing a natural language query are provided. The techniques include obtaining a set of statistics representing a contextual significance of a set of words in a data model for a data set. Next, the set of statistics is used to match a set of semantic intents for a natural language query of the data set to one or more data elements in the data model. The data element(s) and the data set are then to generate a result of the natural language query, and the result is provided in a response to the natural language query.

Growing community of inventors

Jhansi, India

Prashant Pandey