Report template generation based on user intent
The present disclosure relates generally to tools to determine a user's intent and, more particularly, to a system, method and computer program product to generate a report template based on user's intent. The method includes: extracting, by a computer system, text and user selected features from one or more reports built in a reporting application; classifying, by the computer system, keywords in the text and the select features; identifying, by the computer system, common keywords and associated selected features within the one or more reports; determining, by the computer system, an intent of the user based on the common keywords and associated selected features; and generating, by the computer system, a report template with prepopulated features of the selected features based on the intent of the user.
1 . A method, comprising:
receiving, by a computer system from a plurality of disparate computing systems, a plurality of output data objects generated by one or more applications executed on the plurality of disparate computing systems, the plurality of output data objects including a plurality of fields;
providing, by the computer system, for display via an interface, a drop down menu containing the plurality of fields;
receiving, by the computer system, a first input from a user selecting a first field of the plurality of fields displayed via the interface;
extracting, by the computer system, text from a set of output data objects of the plurality of output data objects, the set of output data objects including the first field;
identifying, by the computer system, keywords in the text and the first field that are common to similar output data objects of the set of output data objects, wherein the similar output data objects share one or more fields;
grouping, by the computer system, the keywords that are shared across the similar output data objects of the set of output data objects into one or more clusters;
determining, by the computer system, an intent of the user based on the keywords of the one or more clusters and the first field;
generating, by the computer system, a suggested title based on the keywords of the one or more clusters;
generating, by the computer system, a template based on the intent, the template including the suggested title and the first field;
transmitting, by the computer system, for display via the interface, the template; and
transmitting, by the computer system, for display via the interface, in response to receiving a second input from the user selecting the template, an output data object generated using the template, the output data object including the suggested title and the first field.
2 . The method of claim 1 , wherein the text includes a description of the plurality of output data objects.
3 . The method of claim 1 , wherein the plurality of fields include underlying data from different domains.
4 . The method of claim 1 , wherein the intent is determined by an intent classifier.
5 . The method of claim 4 , wherein the intent classifier comprises machine learning and natural language processing to automatically group the keywords shared across the similar output data objects.
6 . The method of claim 1 , wherein the suggested title and the first field can be manipulated by a user.
7 . The method of claim 1 , further comprising the template in a library which can be retrieved by users.
8 . A computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:
receive, from a plurality of disparate computing systems, a plurality of output data objects generated by one or more applications executed on the plurality of disparate computing systems, the plurality of output data objects including a plurality of fields;
provide, for display via an interface, a drop down menu containing the plurality of fields;
receive a first input from a user selecting a first field of the plurality of fields displayed via the interface;
extract text from a set of output data objects of the plurality of output data objects, the set of output data objects including the first field;
identify keywords in the text and the first field that are common to similar output data objects of the set of output data objects, wherein the similar output data objects share one or more fields;
group together the keywords that are shared across the similar output data objects of the set of output data objects into one or more clusters;
determine an intent of the user based on the keywords of the one or more clusters and the first field;
generate a suggested title based on the keywords of the one or more clusters;
create a template based on the intent of the user, the template including the suggested title and the first field;
transmit, for display via the interface, the template; and
transmit, for display via the interface, in response to receiving a second input from the user selecting the template, an output data object generated using the template, the output data object including the suggested title and the first field.
9 . The computer program product of claim 8 , wherein grouping the keywords comprises applying a heuristic algorithm for finding partitions.
10 . The computer program product of claim 9 , wherein the heuristic algorithm comprises a Kernighan-Lin algorithm implemented to provide classifications.
11 . The computer program product of claim 8 , wherein the intent is determined by an intent classifier comprising machine learning and natural language processing to automatically group the keywords shared across the similar output data objects.
12 . The computer program product of claim 8 , wherein the template includes prepopulated features which are obtained from one or more previous output data objects of one or more users that have a similar intent.
13 . The computer program product of claim 8 , further comprising saving the template in a library which can be retrieved by one or more users.
14 . A system comprising:
a processor, a computer readable memory, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:
receive, from a plurality of disparate computing systems, a plurality of output data objects generated by one or more applications executed on the plurality of disparate computing systems, the plurality of output data objects including a plurality of fields;
provide, for display via an interface, a drop down menu containing the plurality of fields;
receive a first input from a user selecting a first field of the plurality of fields displayed via the interface;
extract text from a set of output data objects of the plurality of output data objects, the set of output data objects including the first field;
identify keywords in the text and the first field that are common to by similar output data objects of the set of output data objects, wherein the similar output data objects share one or more fields;
group the keywords that are shared across the similar output data objects of the set of output data objects into one or more clusters;
determine an intent of the user based on the keywords of the one or more clusters and the first field;
generate a suggested title based on the keywords of the one or more clusters;
generate a template based on the intent of the user, the template including the suggested title and the first field;
transmit, for display via the interface, the template; and
transmit, for display via the interface, in response to receiving a second input from the user selecting the template, a report generated using the template, the report including the suggested title and the first field.
15 . The system of claim 14 , wherein the template includes prepopulated features obtained from one or more previous output data objects generated by one or more users that have a similar intent.