Methods and system for providing real-time business intelligence using natural language queries

• US 10,657,125 B1
• Filed: 05/05/2017
• Issued: 05/19/2020
• Est. Priority Date: 06/13/2013
• Status: Active Grant

• Current Assignee: Progress Software Corporation
• Original Assignee: Progress Software Corporation
• Inventors: Gautam, Shyamantak, Phukan, Ruban, Sanghavi, Sundeep, Katkar, Vishal
• Primary Examiner(s): Park, Grace
• Assistant Examiner(s): Cheung, Hubert
• Application Number:
  US15/587,751
• Time in Patent Office: 1,110 Days
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/26 Visual data mining; Browsing structured data
• CPC Class Codes: G06F 16/3328 using graphical result space presentation or visualisation
• CPC Class Codes: G06F 16/903 Querying for retrieval from the web G06F16/953
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

The methods and systems for providing real-time business intelligence using national language queries facilitate a user to search within a data warehouse using a natural language question. Such business intelligence platform may receive a natural language based question, extract one or more key words from the natural language based question, determine a first dependency graph of the one or more key words based on a relationship among the one or more key words, determine a second dependency graph of the one or more key words based on previously stored search indices, merge the first and the second dependency graphs to generate an integrated dependency graph, and generate a formatted search string based on the integrated dependency graph.

Claims

1. A system, comprising:

a processor; and

a memory operatively coupled to the processor, the memory storing instructions executable by the processor to;

extract a plurality of key words from a natural-language-based question, the plurality of key words including a first key word;

generate a data dependency graph based on, and including, relationships between the plurality of key words and a plurality of data field names in a plurality of data sources, wherein the data dependency graph maps the first key word in the natural-language-based question to a first data field name and a second data field name in the plurality of data sources;

generate a language dependency graph based on, and including, relationships between the plurality of key words of the natural-language-based question-using sentence structure rules;

generate an inter-dependency graph from the language dependency graph and the data dependency graph by;

merging the language dependency graph and the data dependency graph;

determining that a mapping between the first key word in the natural-language-based question and the first data field name in the plurality of data sources does not satisfy a cross-functional dependency between the language dependency graph and the data dependency graph; and

eliminating the mapping between the first key word in the natural-language-based question and the first data field name in the plurality of data sources from the inter-dependency graph; and

translate the natural-language-based question into a formatted query string based on the inter-dependency graph.

2. The system of claim 1, wherein the inter-dependency graph includes one or more mappings between the plurality of key words and (1) a set of data field names and (2) a set of operational commands based on the relationships included in the data dependency graph and the relationships included in the language dependency graph, and wherein the formatted query string based on the inter-dependency graph is based on a computational operation mapped to a key word of the natural-language-based question in the inter-dependency graph and a data field name mapped to another key word of the natural-language-based question in the inter-dependency graph.

3. The system of claim 1, wherein the plurality of key words are extracted by parsing the natural-language-based question into phrases and eliminating ancillary phrases based on heuristics.

4. The system of claim 1, wherein the inter-dependency graph is defined based on a context and a sentence structure of the natural-language-based question.

5. The system of claim 1, wherein the instructions are further executable by the processor to:

compare the data dependency graph and the language dependency graph to eliminate inaccurate mappings.

6. The system of claim 1, wherein the instructions are further executable by the processor to:

instantiate a scoring mechanism to prioritize different mappings when there are multiple data field names mapped to one key word.

7. The system of claim 1, wherein the data dependency graph and the language dependency graph are generated in parallel.

8. The system of claim 1, wherein the inter-dependency graph is saved in an index file linked to the plurality of data sources.

9. The system of claim 1, wherein the relationships between the plurality of key words of the natural-language-based question are grammatical relationships.

10. The system of claim 1, wherein the instructions are further executable by the processor to:

send a query based on the formatted query string to a data source from the plurality of data sources;

obtain a query result from the data source in response to the query; and

derive an output value for a user-desired analytics variable based on the query result and a computational operation.

11. A method comprising:

extracting, using one or more processors, a plurality of key words from a natural-language-based question, the plurality of key words including a first key word;

generating, using the one or more processors, a data dependency graph based on, and including, relationships between the plurality of key words and a plurality of data field names in a plurality of data sources, wherein the data dependency graph maps the first key word in the natural-language-based question to a first data field name and a second data field name in the plurality of data sources;

generating, using the one or more processors, a language dependency graph based on, and including, relationships between the plurality of key words of the natural-language-based question using sentence structure rules;

generating, using the one or more processors, an inter-dependency graph from the language dependency graph and the data dependency graph by;

merging, using the one or more processors, the language dependency graph and the data dependency graph;

determining, using the one or more processors, that a mapping between the first key word in the natural-language-based question and the first data field name in the plurality of data sources does not satisfy a cross-functional dependency between the language dependency graph and the data dependency graph; and

eliminating, using the one or more processors, the mapping between the first key word in the natural-language-based question and the first data field name in the plurality of data sources from the inter-dependency graph; and

translating, using the one or more processors, the natural-language-based question into a formatted query string based on the inter-dependency graph.

12. The method of claim 11, wherein the inter-dependency graph includes one or more mappings between the plurality of key words and (1) a set of data field names and (2) a set of operational commands based on the relationships included in the data dependency graph and the relationships included in the language dependency graph, and wherein the formatted query string based on the inter-dependency graph is based on a computational operation mapped to a key word of the natural-language-based question in the inter-dependency graph and a data field name mapped to another key word of the natural-language-based question in the inter-dependency graph.

13. The method of claim 11, wherein the plurality of key words are extracted by parsing the natural-language-based question into phrases and eliminating ancillary phrases based on heuristics.

14. The method of claim 11, wherein the inter-dependency graph is defined based on a context and a sentence structure of the natural-language-based question.

15. The method of claim 11, wherein merging the data dependency graph and the language dependency graph includes:

comparing the data dependency graph and the language dependency graph to eliminate inaccurate mappings.

16. The method of claim 11, wherein merging the data dependency graph and the language dependency graph includes:

instantiating a scoring mechanism to prioritize different mappings when there are multiple data field names mapped to one key word.

17. The method of claim 16, wherein the scoring mechanism ranks the different mappings based at least in part on user feedback.

18. The method of claim 11, wherein the data dependency graph and the language dependency graph are generated in parallel.

19. The method of claim 11, wherein the inter-dependency graph is saved in an index file linked to the plurality of data sources.

20. The method of claim 11, further including:

send a query based on the formatted query string to a data source from the plurality of data sources;

obtain a query result from the data source in response to the query; and

derive an output value for a user-desired data analytics variable based on the query result and a computational operation.