Conversational analytics
AssigneeQlik Tech International AB
InventorsElif Tutuk, Bill Kehoe, Vesna Brown
Life of this patent
Estimating the term…
Abstract
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.
Claims20
A method comprising:
- determining, by a computing device, based on a first input comprising natural language, a keyword;
- determining, based on the keyword, a plurality of content items, wherein each content items of the plurality of content items comprises analytic content associated with the keyword;
- and
- determining, based on the plurality of content items, a data structure, wherein the data structure associates each content item of the plurality of content items according to a temporal value.
A method comprising:
- determining, by a computing device, based on a first input comprising natural language, a keyword;
- determining, based on the keyword, a plurality of content items, wherein each content item of the plurality of content items is associated with a respective correlation value;
- determining, for at least one content item of the plurality of content items, that a respective correlation value satisfies a threshold;
- generating, based on the at least one content item, a data structure, wherein, based on one or more attributes associated with the at least one content item, the data structure comprises one or more additional content items;
- and
- causing an output comprising the at least one content item and the one or more additional content items.
A method comprising:
- determining, by a computing device, based on a first input comprising natural language, a keyword;
- determining, based on the keyword and previous input, a plurality of content items;
- determining, based on a selection of a content item of the plurality of content items, a data structure, wherein, based on one or more attributes associated with the content item, the data structure comprises one or more additional content items;
- and
- causing an output comprising the at least a portion of the additional content items.
Dependencies are inferred from the claim text.