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, the method comprising:
receiving an audio query, via a user interface, requesting a set of data from a hierarchy;
generating a syntax parse tree that separates the audio query into a set of grammatical components;
assigning a type of part-of-speech tag to each respective grammatical component in the set of grammatical components;
identifying a mapping of a part-of-speech tag to the hierarchy;
generating, based on the mapping, a database query corresponding to the audio query;
executing the database query;
receiving the set of data responsive to the database query;
determining, based on a natural language analysis of the audio query, a query type of the audio 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 set of data from the hierarchy.
2. The method of claim 1 , further comprising: converting the audio query to a text input.
3. The method of claim 1 , wherein the query type includes at least one of a time series query, a comparison query, and an aggregate query.
4. The method of claim 1 , wherein the visualization includes at least one of a time series graph, a pie chart, and a line graph.
5. The method of claim 1 , further comprising:
prior to receiving the audio query, retrieving data from a public source; and
processing the data to identify the hierarchy in the data retrieved.
6. A non-transitory computer-readable storage medium storing instructions, which, when executed on one or more processors, performs an operation for resolving a natural language query, the operation comprising:
receiving an audio query, via a user interface, requesting a set of data from a hierarchy;
generating a syntax parse tree that separates the audio query into a set of grammatical components;
assigning a type of part-of-speech tag to each respective grammatical component in the set of grammatical components;
identifying a mapping of a part-of-speech tag to the hierarchy;
generating, based on the mapping, a database query corresponding to the audio query;
executing the database query;
receiving the set of data responsive to the database query;
determining, based on a natural language analysis of the audio query, a query type of the audio query;
identifying a visualization type based on the determined query type; and
displaying, via the user interface, a visualization based on the visualization type, where the displayed visualization includes the requested set of data from the hierarchy.
7. The non-transitory computer-readable storage medium of claim 6 , wherein the operation further comprises: converting the audio query to a text input.
8. The non-transitory computer-readable storage medium of claim 6 , wherein the query type includes at least one of a time series query, a comparison query, and an aggregate query.
9. The non-transitory computer-readable storage medium of claim 6 , wherein the visualization includes at least one of a time series graph, a pie chart, and a line graph.
10. The non-transitory computer-readable storage medium of claim 6 , further comprising:
prior to receiving the audio query, retrieving data from a public source; and
processing the data to identify the hierarchy in the data retrieved.
11. A system, comprising:
one or more processors; and
a memory storing program code, which, when executed on the one or more processors, performs an operation for resolving a natural language query, the operation comprising:
receiving an audio query, via a user interface, requesting a data from a hierarchy;
generating a syntax parse tree that separates the audio into a set of grammatical components;
assign a type of part-of-speech tag to each respective grammatical component in the set of grammatical components;
identifying a mapping of a part-of-speech tag to the hierarchy;
generating, based on the mapping, a database corresponding to the audio;
executing the database query;
receiving the set of data responsive to the database query;
determining, based on a natural language analysis of the audio query, a query type of the audio query;
identifying a visualization type based on the determined query type; and
displaying, via user interface, a visualization based on the visualization type, where the displayed visualization includes the requested set of data from the hierarchy.
12. The system of claim 11 , wherein the query type includes at least one of a time series query, a comparison query and an aggregate query.
13. The system of claim 11 , wherein the visualization includes at least one of a time series graph, a pie chart, and a line graph.
14. The system of claim 11 , further comprising:
prior to receiving the audio query, retrieving data from a public source; and
processing the data to identify the hierarchy in the data retrieved.
15. The system of claim 11 , wherein the operation further comprises: converting the audio query to a text input.