US 10,592,505 B2Granted

Natural language interfaces for databases using autonomous agents and thesauri

AssigneeOracle International Corporation

InventorBoris Galitsky

Life of this patent

Estimating the term…

Loading patent…

Abstract

An aspect of the present disclosure relate to translating natural language queries into native database queries. For example, a database application receives a natural language query from a user, divides the query into clauses, determines keywords from the clauses, and maps keywords in the query to native query that can query a database. In the case that the natural language query includes keywords that are not mapped, the application resolves an ambiguity by communicating with a user device. In the case that a keyword cannot be mapped, the application can map the keyword to a custom index that includes synonyms derived using pair-wise generalization or other techniques. Once all keywords are mapped, the database application generates a native database query and obtains results from a database.

Claims20

Dependent claims

A method for servicing a natural language query via a database, the method comprising:

accessing a database with tables, wherein each table comprises a label identifying the table, and fields, each field comprising an attribute;
accessing a custom database index comprising entities, the entities comprising the fields, attributes of the fields, and a set of connected nodes including a root node and at least one terminal node that indicates a synonym for the root node;
forming a search query comprising a path from the root node to a respective terminal node;
obtaining a set of search results by providing the search query to a search engine;
adding additional synonyms to the custom database index based at least in part on common terms identified from the set of search results;
accessing a natural language search query;
constructing a parse tree from the natural language search query, wherein the parse tree comprises at least one terminal node comprising a word type and at least one terminal node that represents a word or phrase of the natural language search query, wherein the parse tree identifies syntactic information of the natural language search query;
identifying, from the parse tree, one or more clauses, wherein a clause comprises keywords and wherein each keyword is a noun or a verb;
performing one or more of the following:
matching each keyword to either (i) a label of one of the tables or (ii) a field of one of the tables or (iii) an attribute of a field, and
determining a threshold level of a match between a keyword and the custom database index;
generating a database query from the matched keywords;
obtaining a result from the database by providing the database query to the database;
and
displaying the result to a user device.

12 more elements

A system comprising:

a computer-readable medium storing non-transitory computer-executable program instructions;
and
a processing device communicatively coupled to the computer-readable medium for executing the non-transitory computer-executable program instructions, wherein executing the non-transitory computer-executable program instructions configures the processing device to perform operations comprising:
accessing a database with tables, wherein each table comprises a label identifying the table, and fields, each field comprising an attribute;
accessing a custom database index comprising entities, the entities comprising the fields, attributes of the fields, and a set of connected nodes including a root node and at least one terminal node that indicates a synonym for the root node;
forming a search query comprising a path from the root node to a respective terminal node;
obtaining a set of search results by providing the search query to a search engine;
adding additional synonyms to the custom database index based at least in part on common terms identified from the set of search results;
accessing a natural language search query;
constructing a parse tree from the natural language search query, wherein the parse tree comprises at least one terminal node comprising a word type and at least one terminal node that represents a word or phrase of the natural language search query, wherein the parse tree identifies syntactic information of the natural language search query;
identifying, from the parse tree, one or more clauses, wherein a clause comprises keywords and wherein each keyword is a noun or a verb;
performing one or more of the following:
matching each keyword to either (i) a label of one of the tables or (ii) a field of one of the tables or (iii) an attribute of a field, and
determining a threshold level of a match between a keyword and the custom database index;
generating a database query from the matched keywords;
obtaining a result from the database by providing the database query to the database;
and
displaying the result to a user device.

15 more elements

A non-transitory computer-readable storage medium storing computer-executable program instructions, wherein when executed by a processing device, the program instructions cause the processing device to perform operations comprising:

accessing a database with tables, wherein each table comprises a label identifying the table, and fields, each field comprising an attribute;
accessing a custom database index comprising entities, the entities comprising the fields, attributes of the fields, and a set of connected nodes including a root node and at least one terminal node that indicates a synonym for the root node;
forming a search query comprising a path from the root node to a respective terminal node;
obtaining a set of search results by providing the search query to a search engine;
adding additional synonyms to the custom database index based at least in part on common terms identified from the set of search results;
accessing a natural language search query;
constructing a parse tree from the natural language search query, wherein the parse tree comprises at least one terminal node comprising a word type and at least one terminal node that represents a word or phrase of the natural language search query, wherein the parse tree identifies syntactic information of the natural language search query;
identifying, from the parse tree, one or more clauses, wherein a clause comprises keywords and wherein each keyword is a noun or a verb;
performing one or more of the following:
matching each keyword to either (i) a label of one of the tables or (ii) a field of one of the tables or (iii) an attribute of a field, and
determining a threshold level of a match between the keyword and the custom database index;
generating a database query from the matched keywords;
obtaining a result from the database by providing the database query to the database;
and
displaying the result to a user device.

12 more elements

Dependencies are inferred from the claim text.