Method for interpretation of charts using statistical techniques and machine learning and creating automated summaries in natural language
Disclosed subject matter relates to data analytics including a method and system for generating a contextual summary of one or more charts. A summary generating system extracts chart data associated with each chart received from one or more sources and determines context of the chart data. The summary generating system computes statistical data of each chart by analyzing chart data based on predefined rules corresponding to the context. The form of analysis to be performed depends on the context of the chart data. Furthermore, insights of each chart are generated by mapping the statistical data with predefined narratives corresponding to the context. Finally, the summary generating system, automatically generates the contextual summary of the charts corresponding to the context of the chart data in a predefined template format using the generated insights of each of the one or more charts. The contextual summary provides holistic information of the interpreted charts.
1. A method of generating a contextual summary of one or more charts, the method comprising:
extracting, by a summary generating system ( 107 ), chart data ( 209 ) associated with each of the one or more charts received from one or more sources ( 103 );
determining, by the summary generating system ( 107 ), context of the chart data ( 209 ) based on one or more attributes of the chart data ( 209 ) and one or more characteristics corresponding to each of the one or more attributes;
computing, by the summary generating system ( 107 ), statistical data ( 215 ) of each of the one or more charts by analysing the chart data ( 209 ) based on one or more predefined rules corresponding to the context of the chart data ( 209 );
generating, by the summary generating system ( 107 ), insights of each of the one or more charts by mapping the statistical data ( 215 ) with one or more predefined narratives corresponding to the context of the chart data ( 209 ); wherein the one or more predefined narratives provide a description of the statistical data ( 215 ); and
generating, by the summary generating system ( 107 ), the contextual summary of the one or more charts in a predefined template format corresponding to the context of the chart data ( 209 ) using the generated insights of each of the one or more charts.
2. The method as claimed in claim 1 , wherein the one or more charts comprise at least one of bar graph, pie chart, stacked chart, tree map, scatter plot chart, and trend analysis chart.
3. The method as claimed in claim 1 , wherein the one or more attributes of the chart data ( 209 ) comprises at least one of numerical variables and categorical variables.
4. The method as claimed in claim 1 , wherein the analysis of the chart data ( 209 ) comprises at least one of distribution analysis, inferential analysis, predictive analysis and prescriptive analysis.
5. The method as claimed in claim 1 , wherein the analysing of the chart further comprises determining form of analysis to be performed on the chart data ( 209 ) based on the context of the chart data ( 209 ).
6. The method as claimed in claim 1 , wherein the one or more predefined rules are updated based on requirement.
7. A summary generating system ( 107 ) for generating a contextual summary of one or more charts, the summary generating system ( 107 ) comprising:
a processor ( 109 );
a memory ( 113 ) communicatively coupled to the processor ( 109 ), wherein the memory ( 113 ) stores the processor-executable instructions, which, on execution, causes the processor ( 109 ) to:
extract chart data ( 209 ) associated with each of the one or more charts received from one or more sources ( 103 );
determine context of the chart data ( 209 ) based on one or more attributes of the chart data ( 209 ) and one or more characteristics corresponding to each of the one or more attributes;
compute statistical data ( 215 ) of each of the one or more charts by analysing the chart data ( 209 ) based on one or more predefined rules corresponding to the context of the chart data ( 209 );
generate insights of each of the one or more charts by mapping the statistical data ( 215 ) with one or more predefined narratives corresponding to the context of the chart data ( 209 ); wherein the one or more predefined narratives provide a description of the statistical data ( 215 ); and
generate the contextual summary of the one or more charts in a predefined template format corresponding to the context of the chart data ( 209 ) using the generated insights of each of the one or more charts.
8. The summary generating system ( 107 ) as claimed in claim 7 , wherein the one or more charts comprise at least one of bar graph, pie chart, stacked chart, tree map, scatter plot chart, and trend analysis chart.
9. The summary generating system ( 107 ) as claimed in claim 7 , wherein the one or more attributes of the chart data ( 209 ) comprises at least one of numerical variables and categorical variables.
10. The summary generating system ( 107 ) as claimed in claim 7 , wherein the analysis of the chart data ( 209 ) comprises at least one of distribution analysis, inferential analysis, predictive analysis and prescriptive analysis.
11. The summary generating system ( 107 ) as claimed in claim 7 , wherein to analyse the charts, the instructions further cause the processor ( 109 ) to determine form of analysis to be performed on the chart data ( 209 ) based on the context of the chart data ( 209 ).
12. The summary generating system ( 107 ) as claimed in claim 7 , wherein processor ( 109 ) updates the one or more predefined rules based on requirement.