Cross-User Dashboard Behavior Analysis and Dashboard Recommendations

Abstract

Mechanisms are provided for performing cross-user dashboard behavior analysis and dashboard recommendation generation. Dashboard interfaces are presented to a user and the user inputs are tracked. Cognitive analysis of the user dashboard behavior pattern data is performed to determine a reason for user dashboard behavior represented by the user dashboard behavior pattern data. Cross-user correlation analysis operations are performed based on the user dashboard behavior pattern data and dashboard behavior pattern data of other users of a different user type to identify an intersection point. A recommendation output is generated and output that recommends at least one of a particular dashboard interface to access or a modification to the one or more dashboard interfaces to be performed, based on the identification of the intersection point and the determined reason for the user dashboard behavior.

1 . A method, in a data processing system comprising at least one memory and at least one processor, wherein the at least one memory comprises instructions that are executed by the at least one processor to configure the at least one processor to implement the method comprising:
 presenting, by the data processing system, one or more dashboard interfaces to a user via a client computing device;   tracking, by the data processing system, user inputs to the client computing device at least during and after presentation of each of the one or more dashboard interfaces to the user via the client computing device to generate user dashboard behavior pattern data;   performing, by behavior pattern reasoning logic of a cognitive computing system, cognitive analysis of the user dashboard behavior pattern data to determine a reason for user dashboard behavior represented by the user dashboard behavior pattern data;   performing, by the behavior pattern reasoning logic of the cognitive computing system, cross-user correlation analysis operations based on the user dashboard behavior pattern data and dashboard behavior pattern data of one or more other users of a different user type to identify at least one intersection point where the user dashboard behavior of the user intersects with user dashboard behaviors of the one or more other users at least by executing a predefined set of computer executed rules mapping each dashboard behavior pattern to one or more corresponding candidate reasons for the dashboard behavior pattern and ranking the one or more corresponding candidate reasons based on a cognitive computing processing of evidence data in support of each candidate reason in the one or more corresponding candidate reasons; and   outputting, by the data processing system, a recommendation output that recommends at least one of a particular dashboard interface to access or a modification to the one or more dashboard interfaces to be performed, to the user via the client computing device, based on the identification of the intersection points and the determined reason for the user dashboard behavior.   
     
     
         2 . The method of  claim 1 , wherein tracking user inputs to the client computing device at least during and after presentation of each of the one or more dashboard interfaces to the user via the client computing device to generate user dashboard behavior pattern data further comprises applying predictive analytics, by predictive analytics logic of the data processing system, to the tracked user inputs to predict information needs of the user. 
     
     
         3 . The method of  claim 1 , wherein the behavior pattern reasoning logic is trained to analyze attributes of user dashboard behavior pattern data, to identify corresponding candidate reasons for user dashboard behavior represented by the user dashboard behavior pattern data and to identify correlations between candidate reasons for user dashboard behavior across a plurality of different user types. 
     
     
         4 . The method of  claim 1 , wherein performing, by behavior pattern reasoning logic of a cognitive computing system, cognitive analysis of the user dashboard behavior pattern data to determine a reason for user dashboard behavior represented by the user dashboard behavior pattern data comprises:
 generating a set of candidate reasons for the user dashboard behavior based on application, by the cognitive computing system, of one or more trained algorithms to the user dashboard behavior data to correlate attributes of the user dashboard behavior data to candidate reasons for the user dashboard behavior;   generating, for each of the candidate reasons in the set of candidate reasons, a confidence score associated with the candidate reason based on cognitive analysis of evidence data corresponding to the candidate reason; and   selecting a reason for user dashboard behavior from the set of candidate reasons based on the confidence scores associated with each of the candidate reasons.   
     
     
         5 . The method of  claim 1 , wherein performing cross-user correlation analysis operations based on the user dashboard behavior pattern data and dashboard behavior pattern data of one or more other users of a different user type to identify at least one intersection point where the user dashboard behavior of the user intersects with user dashboard behaviors of the one or more other users comprises:
 generating a set of candidate correlations between the user dashboard behavior and user dashboard behaviors of the one or more other users based on application, by the cognitive computing system, of one or more trained algorithms to the user dashboard behavior data and user dashboard behavior data of the one or more other users to map attributes of the user dashboard behavior data with attributes of the user dashboard behavior data of the one or more other users that represent candidate correlations;   generating, for each of the candidate correlations in the set of candidate correlations, a confidence score associated with the candidate correlation based on cognitive analysis of evidence data corresponding to the candidate correlation; and   selecting a correlation, specifying the at least one intersection point, from the set of candidate correlations based on the confidence scores associated with each of the candidate correlations.   
     
     
         6 . The method of  claim 1 , wherein performing cross-user correlation analysis comprises identifying, by the behavior pattern reasoning logic of the cognitive computing system, portions of the one or more dashboard interfaces interacted with by the user and at least one of the one or more other users, that present the same or similar information. 
     
     
         7 . The method of  claim 1 , wherein the recommendation output is a cross-user recommendation for modifying an existing dashboard interface or generating a new dashboard interface that comprises at least one portion of the dashboard interface directed to the at least one intersection point. 
     
     
         8 . The method of  claim 1 , wherein performing cognitive analysis of the user dashboard behavior pattern data to determine a reason for user dashboard behavior represented by the user dashboard behavior pattern data comprises applying one or more algorithms having rules that map dashboard usage conditions present in tracked user dashboard behavior pattern data with a particular reason for such tracked user dashboard behavior pattern data. 
     
     
         9 . The method of  claim 1 , wherein performing the cognitive analysis of the user dashboard behavior pattern data, performing the cross-user correlation analysis operations, and outputting the recommendation output are performed in response to a request to perform cross-user cognitive analysis of user dashboard behavior patterns. 
     
     
         10 . The method of  claim 9 , wherein the request is automatically generated by the data processing system based on results of predictive analytics logic of the data processing system indicating that cross-user cognitive analysis is to be performed. 
     
     
         11 . A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a data processing system, causes the data processing system to be specifically configured to implement a cognitive computing system, and to:
 present one or more dashboard interfaces to a user via a client computing device;   track user inputs to the client computing device at least during and after presentation of each of the one or more dashboard interfaces to the user via the client computing device to generate user dashboard behavior pattern data;   perform, by behavior pattern reasoning logic of the cognitive computing system, cognitive analysis of the user dashboard behavior pattern data to determine a reason for user dashboard behavior represented by the user dashboard behavior pattern data;   perform, by the behavior pattern reasoning logic of the cognitive computing system, cross-user correlation analysis operations based on the user dashboard behavior pattern data and dashboard behavior pattern data of one or more other users of a different user type to identify at least one intersection point where the user dashboard behavior of the user intersects with user dashboard behaviors of the one or more other users at least by executing a predefined set of computer executed rules mapping each dashboard behavior pattern to one or more corresponding candidate reasons for the dashboard behavior pattern and ranking the one or more corresponding candidate reasons based on a cognitive computing processing of evidence data in support of each candidate reason in the one or more corresponding candidate reasons; and   output a recommendation output that recommends at least one of a particular dashboard interface to access or a modification to the one or more dashboard interfaces to be performed, to the user via the client computing device, based on the identification of the intersection points and the determined reason for the user dashboard behavior.   
     
     
         12 . The computer program product of  claim 11 , wherein the computer readable program further causes the data processing system to track user inputs to the client computing device at least during and after presentation of each of the one or more dashboard interfaces to the user via the client computing device to generate user dashboard behavior pattern data further at least by applying predictive analytics, by predictive analytics logic of the data processing system, to the tracked user inputs to predict information needs of the user. 
     
     
         13 . The computer program product of  claim 11 , wherein the behavior pattern reasoning logic is trained to analyze attributes of user dashboard behavior pattern data, to identify corresponding candidate reasons for user dashboard behavior represented by the user dashboard behavior pattern data and to identify correlations between candidate reasons for user dashboard behavior across a plurality of different user types. 
     
     
         14 . The computer program product of  claim 11 , wherein the computer readable program further causes the data processing system to perform cognitive analysis of the user dashboard behavior pattern data to determine a reason for user dashboard behavior represented by the user dashboard behavior pattern data at least by:
 generating a set of candidate reasons for the user dashboard behavior based on application, by the cognitive computing system, of one or more trained algorithms to the user dashboard behavior data to correlate attributes of the user dashboard behavior data to candidate reasons for the user dashboard behavior;   generating, for each of the candidate reasons in the set of candidate reasons, a confidence score associated with the candidate reason based on cognitive analysis of evidence data corresponding to the candidate reason; and   selecting a reason for user dashboard behavior from the set of candidate reasons based on the confidence scores associated with each of the candidate reasons.   
     
     
         15 . The computer program product of  claim 11 , wherein the computer readable program further causes the data processing system to perform cross-user correlation analysis operations based on the user dashboard behavior pattern data and dashboard behavior pattern data of one or more other users of a different user type to identify at least one intersection point where the user dashboard behavior of the user intersects with user dashboard behaviors of the one or more other users at least by:
 generating a set of candidate correlations between the user dashboard behavior and user dashboard behaviors of the one or more other users based on application, by the cognitive computing system, of one or more trained algorithms to the user dashboard behavior data and user dashboard behavior data of the one or more other users to map attributes of the user dashboard behavior data with attributes of the user dashboard behavior data of the one or more other users that represent candidate correlations;   generating, for each of the candidate correlations in the set of candidate correlations, a confidence score associated with the candidate correlation based on cognitive analysis of evidence data corresponding to the candidate correlation; and   selecting a correlation, specifying the at least one intersection point, from the set of candidate correlations based on the confidence scores associated with each of the candidate correlations.   
     
     
         16 . The computer program product of  claim 11 , wherein the computer readable program further causes the data processing system to perform cross-user correlation analysis at least by identifying, by the behavior pattern reasoning logic of the cognitive computing system, portions of the one or more dashboard interfaces interacted with by the user and at least one of the one or more other users, that present the same or similar information. 
     
     
         17 . The computer program product of  claim 11 , wherein the recommendation output is a cross-user recommendation for modifying an existing dashboard interface or generating a new dashboard interface that comprises at least one portion of the dashboard interface directed to the at least one intersection point. 
     
     
         18 . The computer program product of  claim 11 , wherein the computer readable program further causes the data processing system to perform cognitive analysis of the user dashboard behavior pattern data to determine a reason for user dashboard behavior represented by the user dashboard behavior pattern data at least by applying one or more algorithms having rules that map dashboard usage conditions present in tracked user dashboard behavior pattern data with a particular reason for such tracked user dashboard behavior pattern data. 
     
     
         19 . The computer program product of  claim 11 , wherein performing the cognitive analysis of the user dashboard behavior pattern data, performing the cross-user correlation analysis operations, and outputting the recommendation output are performed in response to an automatically generated request to perform cross-user cognitive analysis of user dashboard behavior patterns, which is automatically generated by the data processing system based on results of predictive analytics logic of the data processing system indicating that cross-user cognitive analysis is to be performed. 
     
     
         20 . An apparatus comprising:
 at least one processor; and   at least one memory coupled to the at least one processor, wherein the at least one memory comprises instructions which, when executed by the at least one processor, cause the at least one processor to be specifically configured to implement a cognitive computing system and to:   present one or more dashboard interfaces to a user via a client computing device;   track user inputs to the client computing device at least during and after presentation of each of the one or more dashboard interfaces to the user via the client computing device to generate user dashboard behavior pattern data;   perform, by behavior pattern reasoning logic of the cognitive computing system, cognitive analysis of the user dashboard behavior pattern data to determine a reason for user dashboard behavior represented by the user dashboard behavior pattern data;   perform, by the behavior pattern reasoning logic of the cognitive computing system, cross-user correlation analysis operations based on the user dashboard behavior pattern data and dashboard behavior pattern data of one or more other users of a different user type to identify at least one intersection point where the user dashboard behavior of the user intersects with user dashboard behaviors of the one or more other users at least by executing a predefined set of computer executed rules mapping each dashboard behavior pattern to one or more corresponding candidate reasons for the dashboard behavior pattern and ranking the one or more corresponding candidate reasons based on a cognitive computing processing of evidence data in support of each candidate reason in the one or more corresponding candidate reasons; and   output a recommendation output that recommends at least one of a particular dashboard interface to access or a modification to the one or more dashboard interfaces to be performed, to the user via the client computing device, based on the identification of the intersection points and the determined reason for the user dashboard behavior.