Natural language query resolution for high dimensionality data
Techniques are disclosed herein for resolving a natural language query. Input (e.g., text input, audio input) corresponding to a query requesting data is received. A type of the query is determined based on a natural language analysis on the query. A form of response to the query is identified based on the type of the query. A visualization associated with the form of response is identified. The visualization is presented via a user interface. The presented visualization includes the requested data.
1. A method for resolving a natural language query, comprising:
receiving a user query, via a user interface, requesting a subset of data from a set of data hierarchies;
generating a syntax parse tree that separates the user query into a set of grammatical components;
assigning a part-of-speech tag to each respective grammatical component in the set of grammatical components;
identifying a set of mappings to a database component based on an evaluation of the set of grammatical components to determine relationships between grammatical components;
generating, based on the set of mappings, a database query corresponding to the user query;
executing the database query;
receiving the subset of data responsive to the database query;
determining, based on a natural language analysis of the user query, a query type of the user query;
identifying a visualization type based on the determined query type; and
displaying, via the user interface, a visualization based on the visualization type, wherein the displayed visualization includes the requested subset of data from the set of data hierarchies.
2. The method of claim 1 , further comprising:
prior to receiving the user query, retrieving a set of data from a public source; and
processing the set of data to identify the set of data hierarchies in the retrieved set of data.
3. The method of claim 1 , wherein the received user query is an audio input from a microphone controlled by an API.
4. The method of claim 3 , further comprising: converting the audio input to a text input.
5. The method of claim 1 , wherein the received user query is a text input.
6. The method of claim 1 , wherein executing the database query further comprises: determining the database query is valid based on a determination the requested subset of data exists in the set of data hierarchies.
7. The method of claim 1 , wherein executing the database query further comprises:
determining the database query is invalid based on a determination the requested subset of data does not exist; and
displaying an error message via the user interface.
8. A non-transitory computer-readable storage medium storing instructions for a method for resolving a natural language query, comprising:
receiving a user query, via a user interface, requesting a subset of data from a set of data hierarchies;
generating a syntax parse tree that separates the user query into a set of grammatical components;
assigning a part-of-speech tag to each respective grammatical component in the set of grammatical components;
identifying a set of mappings to a database component based on an evaluation of the set of grammatical components to determine relationships between grammatical components;
generating, based on the set of mappings, a database query corresponding to the user query;
executing the database query;
receiving the subset of data responsive to the database query;
determining, based on a natural language analysis of the user query, a query type of the user query;
identifying a visualization type based on the determined query type; and
displaying, via the user interface, a visualization based on the visualization type, wherein the displayed visualization includes the requested subset of data from the set of data hierarchies.
9. The non-transitory computer-readable storage medium of claim 8 , further comprising:
prior to receiving the user query, retrieving a set of data from a public source; and
processing the set of data to identify the set of data hierarchies in the retrieved set of data.
10. The non-transitory computer-readable storage medium of claim 8 , wherein the received user query is an audio input from a microphone controlled by an API.
11. The non-transitory computer-readable storage medium of claim 10 , further comprising: converting the audio input to a text input.
12. The non-transitory computer-readable storage medium of claim 8 , wherein the received user query is a text input.
13. The non-transitory computer-readable storage medium of claim 8 , wherein executing the database query further comprises: determining the database query is valid based on a determination the requested subset of data exists in the set of data hierarchies.
14. The non-transitory computer-readable storage medium of claim 8 , wherein executing the database query further comprises:
determining the database query is invalid based on a determination the requested subset of data does not exist; and
displaying an error message via the user interface.
15. A system, comprising:
a processor; and
a memory storing instructions which when executed by the processor perform a method for resolving a natural language query, comprising:
receiving a user query, via a user interface, requesting a subset of data from a set of data hierarchies;
generating a syntax parse tree that separates the user query into a set of grammatical components;
assigning a part-of-speech tag to each respective grammatical component in the set of grammatical components;
identifying a set of mappings to a database component based on an evaluation of the set of grammatical components to determine relationships between grammatical components;
generating, based on the set of mappings, a database query corresponding to the user query;
executing the database query;
receiving the subset of data responsive to the database query;
determining, based on a natural language analysis of the user query, a query type of the user query;
identifying a visualization type based on the determined query type; and
displaying, via the user interface, a visualization based on the visualization type,
wherein the displayed visualization includes the requested subset of data from the set of data hierarchies.
16. The system of claim 15 , further comprising:
prior to receiving the user query, retrieving a set of data from a public source; and
processing the set of data to identify the set of data hierarchies in the retrieved set of data.
17. The system of claim 15 , wherein the received user query is an audio input from a microphone controlled by an API.
18. The system of claim 17 , further comprising: converting the audio input to a text input.
19. The system of claim 15 , wherein the received user query is a text input.
20. The system of claim 15 , wherein executing the database query further comprises: determining the database query is valid based on a determination the requested subset of data exists in the set of data hierarchies.