Interactive and conversational data exploration
Example embodiments are disclosed where a narrative generation platform is integrated with a conversational interface such as a Chatbot to support interactive and dynamic narrative generation in response to speech inputs from users. Such a system can be further integrated with a visualization platform to allow the speech input through the conversational interface to interactively and dynamically focus and control visualizations and/or narratives that accompany the visualizations.
1 . A narrative generation artificial intelligence platform system comprising:
a processor configured to execute a conversational interface configured to receive a series of natural language inputs relating to a data set including structured numeric data and to determine a plurality of commands and one or more communication goals based on the series of natural language inputs;
a memory to store narrative data determined based, at least in part, on the plurality of commands and the one or more communication goals;
the processor being further configured to execute the narrative data with respect to the data set to determine content about the data set for a series of natural language narrative responses to the series of natural language inputs, and to generate the series of natural language narrative responses based on the determined content and corresponding with the series of natural language inputs so that the series of natural language narrative responses address the one or more communication goals and express the content in natural language; and
the processor being further configured to transmit the series of natural language narrative responses for dynamic presentation at a remote computing device, and the processor being further configured to interactively generate additional natural language narrative responses in response to additional natural language inputs received via the conversational interface.
2 . The narrative generation artificial intelligence platform system recited in claim 1 , wherein the content includes a characterization of the data set derived from execution of at least some of the narrative data.
3 . The narrative generation artificial intelligence platform system recited in claim 1 , wherein the one or more communication goals include a communication goal to evaluate, explain, or track a performance of an entity.
4 . The narrative generation artificial intelligence platform system recited in claim 1 , wherein the plurality of commands include a focus task or a drill down task.
5 . The narrative generation artificial intelligence platform system recited in claim 1 , wherein the data set includes visualization parameter data, and wherein the series of natural language inputs include a request to focus on an aspect of a visualization derived from the visualization parameter data.
6 . The narrative generation artificial intelligence platform system recited in claim 1 , wherein at least one of the plurality of commands includes a specification of an entity.
7 . The narrative generation artificial intelligence platform system recited in claim 1 , wherein at least one of the plurality of commands includes a specification of an entity that is notionally identified as a notional entity in at least one of the series of natural language inputs, and wherein the narrative data is determined based on the specification of the notional entity.
8 . The narrative generation artificial intelligence platform system recited in claim 7 , wherein the processor is further configured to determine a specific entity to which the notional entity refers based on an analysis of the data set using the narrative data that is determined based on the specification of the notional entity, and wherein at least one of the series of natural language narrative responses refers to the specific entity.
9 . The narrative generation artificial intelligence platform system recited in claim 7 , wherein the processor is further configured to determine a natural language expression for referring to the specific entity in at least one of the series of natural language narrative responses.
10 . The narrative generation artificial intelligence platform system recited in claim 1 , wherein the at least one of the series of natural language inputs includes speech input.
11 . The narrative generation artificial intelligence platform system recited in claim 1 , wherein at least one of the series of natural language narrative responses includes speech output.
12 . A method performed at a narrative generation artificial intelligence platform, the method comprising:
receiving, using one or more processors, a series of natural language inputs relating to a data set including structured numeric data via a conversational interface;
determining, using the one or more processors, a plurality of commands and one or more communication goals based on the series of natural language inputs;
storing, using the one or more processors, in a memory a narrative data determined based, at least in part, on the plurality of commands and the one or more communication goals;
executing, using the one or more processors, the narrative data with respect to the data set via to determine content about the data set for a series of natural language narrative responses to the series of natural language inputs;
generating, using the one or more processors, the series of natural language narrative responses based on the determined content and corresponding with the series of natural language inputs so that the series of natural language narrative responses address the one or more communication goals and express the content in natural language; and
transmitting, using the one or more processors, the series of natural language narrative responses for dynamic presentation at a remote computing device, and the processor being further configured to interactively generate additional natural language narrative responses in response to additional natural language inputs received via the conversational interface.
13 . The method recited in claim 12 , wherein the content includes a characterization of the data set derived from execution of at least some of the narrative data.
14 . The method recited in claim 12 , wherein the one or more communication goals include a communication goal to evaluate, explain, or track a performance of an entity.
15 . The method recited in claim 12 , wherein the plurality of commands include a focus task or a drill down task.
16 . The method recited in claim 12 , wherein the data set includes visualization parameter data, and wherein the series of natural language inputs include a request to focus on an aspect of a visualization derived from the visualization parameter data.
17 . The method recited in claim 12 , wherein at least one of the plurality of commands includes a specification of an entity.
18 . The method recited in claim 12 , wherein at least one of the plurality of commands includes a specification of an entity that is notionally identified as a notional entity in at least one of the series of natural language inputs, and wherein the narrative data is determined based on the specification of the notional entity.
19 . The method recited in claim 18 , wherein the processor is further configured to determine a specific entity to which the notional entity refers based on an analysis of the data set using the narrative data that is determined based on the specification of the notional entity, and wherein at least one of the series of natural language narrative responses refers to the specific entity.
20 . A computer memory having instructions stored thereon that when executed by a processor perform a method at a narrative generation artificial intelligence platform, the method comprising:
receiving a series of natural language inputs relating to a data set including structured numeric data via a conversational interface;
determining a plurality of commands and one or more communication goals based on the series of natural language inputs;
storing in a memory narrative data based, at least in part, on the plurality of commands and the one or more communication goals;
executing the narrative data with respect to the data set via a processor to determine content about the data set for a series of natural language narrative responses to the series of natural language inputs;
generating the series of natural language narrative responses via the processor based on the determined content and corresponding with the series of natural language inputs so that the series of natural language narrative responses address the one or more communication goals and express the content in natural language; and
transmitting the series of natural language narrative responses for dynamic presentation at a remote computing device, and the processor being further configured to interactively generate additional natural language narrative responses in response to additional natural language inputs received via the conversational interface.