Conversational analytics
Natural language can be used to conduct a conversation that yields analytic results. An interactive user interface can present suggestive content associated with a natural language input to a user. The suggestive content can guide assist the user in obtaining analytic data/information relating to a business, industry, and/or the like. An ontology comprising one or more content items associated with the natural language input can generated. The ontology can be represented as and/or associated with a data structure that temporal correlates a plurality of content items to the natural language input.
1. A method comprising:
determining, by a computing device, based on a first natural language input received via a user interface during an analytics session, a keyword, wherein the first natural language input comprises the keyword;
generating, during the analytics session, at least one first content items comprising analytic content associated with the keyword;
generating, based on the first natural language input and the at least one first content item, a first data structure, wherein the first data structure associates the keyword and the at least one first content item with a first temporal value that is based on a time the at least one first content item was generated during the analytics session;
generating, based on a second natural language input associated with the first natural language input, a second data structure, wherein the second data structure associates the keyword and at least one second content item, comprising analytic content associated with the keyword, with a second temporal value that is based on a time the at least one second content item was generated during the analytics session, and wherein the second natural language input excludes the keyword; and
causing, based on the first data structure and the second data structure, the at least one first content item and the at least one second content item to be output at the user interface, wherein the output comprises a chronological arrangement of the at least one first content item and the at least one second content item based on the first temporal value and the second temporal value.
2. The method of claim 1 , further comprising receiving the second natural language input.
3. The method of claim 2 , further comprising:
determining that a correlation between the second natural language input and the at least one second content item exists; and
causing, based on the correlation, an output of the at least one second content item.
4. The method of claim 3 , wherein receiving the second natural language input is based on a recommendation.
5. The method of claim 4 , wherein the recommendation comprises natural language that is output via the user interface.
6. The method of claim 1 , further comprising receiving, via the user interface, the first natural language input during the analytics session.
7. The method of claim 1 , wherein the analytic content comprises one or more of a chart or a graph associated with the keyword.
8. A method comprising:
determining, by a computing device, based on a first natural language input received via a user interface during an analytics session, a keyword, wherein the first natural language input comprises the keyword;
generating, during the analytics session, at least one first content items associated with a first correlation value that indicates an amount of data associated with the keyword;
generating, based on the first natural language input and the at least one first content item, a first data structure, wherein the first data structure associates the keyword and the at least one first content item with the first correlation value;
generating, based on a second natural language input associated with the first natural language input, a second data structure, wherein the second data structure associates the keyword and at least one second content item with a second correlation value, and wherein the second natural language input excludes the keyword; and
causing, based on the first data structure and the second data structure, the at least one first content item and the at least one second content item to be output at the user interface, wherein the output comprises an ordered arrangement of the at least one first content item and the at least one second content item based on the first correlation value and the second correlation value.
9. The method of claim 8 , further comprising receiving the second natural language input.
10. The method of claim 9 , further comprising:
determining that a correlation between the second natural language input and the at least one second content item exists.
11. The method of claim 10 , wherein receiving the second natural language input is based on a recommendation.
12. The method of claim 10 , further comprising causing output of at least one of: the at least one first content item or the at least one second content item at the user interface.
13. The method of claim 10 , wherein the at least one first content item comprises a chart or a graph associated with the keyword.
14. An apparatus comprising:
one or more processors; and
memory storing processor-executable instructions that, when executed by the one or more processors, cause the apparatus to:
determine, by a computing device, based on a first natural language input received via a user interface during an analytics session, a keyword, wherein the first natural language input comprises the keyword;
generate, during the analytics session, at least one first content items comprising analytic content associated with the keyword;
generate, based on the first natural language input and the at least one first content item, a first data structure, wherein the first data structure associates the keyword and the at least one first content item with a first temporal value that is based on a time the at least one first content item was generated during the analytics session;
generate, based on a second natural language input associated with the first natural language input, a second data structure, wherein the second data structure associates the keyword and at least one second content item, comprising analytic content associated with the keyword, with a second temporal value that is based on a time the at least one second content item was generated during the analytics session, and wherein the second natural language input excludes the keyword; and
cause, based on the first data structure and the second data structure, the at least one first content item and the at least one second content item to be output at the user interface, wherein the output comprises a chronological arrangement of the at least one first content item and the at least one second content item based on the first temporal value and the second temporal value.
15. The apparatus of claim 14 , wherein the processor-executable instructions further cause the apparatus to receive the second natural language input.
16. The apparatus of claim 15 , wherein the processor-executable instructions further cause the apparatus to:
determine that a correlation between the second natural language input and the at least one second content item exists.
17. The apparatus of claim 15 , wherein the second natural language input is received based on a recommendation.
18. The apparatus of claim 17 , wherein the recommendation comprises natural language that is output via the user interface.
19. The apparatus of claim 14 , wherein the analytic content comprises one or more of a chart or a graph associated with the keyword.
20. The apparatus of claim 14 , wherein the processor-executable instructions further cause the apparatus to receive, via the user interface, the first natural language input during the analytics session.