Automatic insights for spreadsheets
Automatically identifying insights from a dataset and presenting the insights graphically and in natural language text ranked by importance is provided. Different data types and structures in the dataset are automatic recognized and matched with a corresponding specific analysis type. The data is analyzed according to the determined corresponding analysis types, and insights from the analysis are automatically identified. The insights within a given insight type and between insight types are ranked and presented in order of importance in automatically generate charts that visually describe each insight and in natural language text that describes each insight in such a way that it may be understandable to a general audience who may not have a familiarity with statistics.
1. A computer-implemented method for generating insights, the method comprising:
receiving a dataset, the dataset comprising a plurality of data points;
identifying, using a processor, characteristics of the dataset;
determining, based at least in part on the characteristics of the dataset, a structure of the dataset;
performing analyses according to the structure of the dataset;
identifying, from the results of the analyses, one or more insights;
ranking the one or more insights according to a strength of each insight within a given insight type and between insight types; and
presenting the one or more insights according to the ranking of each of the one or more insights.
2. The method of claim 1 , wherein receiving data comprises receiving semi-structured data from a spreadsheet or other data source.
3. The method of claim 1 , wherein determining a structure of the dataset comprises determining one or more of:
a numerical dataset;
a time series;
an ordinal series;
a hierarchy; or
a category.
4. The method of claim 1 , wherein presenting the one or more insights comprises:
generating a chart visually describing each insight;
generating natural language text describing each insight; and
presenting the one or more insights in a sequenced list.
5. The method of claim 4 , further comprising:
receiving an indication of a selection of an insight from the sequenced list; and
displaying the chart visually describing the insight and the natural language text describing the insight.
6. The method of claim 5 , further comprising highlighting the data to which the insight pertains in a spreadsheet.
7. The method of claim 5 , further comprising:
receiving an indication of a selection to insert the chart; and
inserting the chart into a spreadsheet.
8. A system for providing insights, the system comprising:
one or more processors; and
a memory coupled to the one or more processors, the one or more processors operable to:
receive a dataset, the dataset comprising a plurality of data points;
identify characteristics of the dataset;
determine, based at least in part on the characteristics of the dataset, a structure of the dataset;
perform analyses according to the structure of the dataset;
identify, from the results of the analyses, one or more insights;
rank the one or more insights according to a strength of each insight within a given insight type and between insight types; and
present the one or more insights according to the ranking of each of the one or more insights.
9. The system of claim 8 , wherein the dataset comprises semi-structured data from a spreadsheet or other data source.
10. The system of claim 8 , wherein in presenting the one or more insights, the one or more processors are further operable to:
generate a chart visually describing each insight;
generate natural language text describing each insight; and
present the one or more insights in a sequenced list.
11. The system of claim 10 , wherein the one or more processors are further operable to:
receive an indication of a selection of an insight from the sequenced list; and
display the chart visually describing the insight and the natural language text describing the insight.
12. The system of claim 11 , wherein the one or more processors are further operable to:
receive an indication of a selection to insert the chart; and
insert the chart into a spreadsheet.
13. A computer storage media containing computer executable instructions which, when executed by a computer, perform a method for providing insights, the method comprising:
receiving semi-structured data;
identifying characteristics of the data;
determining, based at least in part on the characteristics of the data, a structure of the data;
performing a set of analyses according to the structure of the data;
identifying, from results of the analyses, one or more insights;
ranking the one or more insights according to a strength of each insight within a given insight type and between insight types;
generating a chart visually describing each insight;
generating natural language text describing each insight; and
presenting the one or more insights in a sequenced list according to the ranking of the insight.
14. The computer storage media of claim 13 , wherein determining a structure of the data comprises determining one or more of:
a numerical dataset;
a time series;
an ordinal series;
a hierarchy; or
a category.
15. The computer storage media of claim 13 , further comprising:
receiving an indication of a selection of an insight from the sequenced list; and
displaying the chart visually describing the insight and the natural language text describing the insight.
16. The computer storage media of claim 15 , further comprising:
receiving an indication of a selection to insert the chart; and
inserting the chart into a spreadsheet.