Contextual modeling using application metadata
Provided is a system and method for building context from software applications and applying the context to visual settings in a graphical user interface. In one example, the method may include receiving an identification of actions performed by a user with respect to a user interface of a software application, receiving application metadata of the actions from the software application, the application metadata providing context associated with the actions, training one or more predictive models to predict user interface preferences for the user based on the actions and the application metadata, and storing the one or more trained predictive models via a storage device.
1. A computing system comprising:
a processor to:
receive metadata indicating user interactions of a user with respect to one or more parameters or settings of a user interface of a software application, and
train one or more predictive models based on the user interactions with respect to the one or more parameters or settings of the user interface, wherein the training of the one or more predictive models is to predict measures and dimensions for display via the user interface based on the user interactions and differences indicated by the metadata, between current visual settings of the user interface and default user interface settings; and
a storage device to store the one or more trained predictive models.
2. The computing system of claim 1 , wherein the processor is configured to train the one or more predictive models based on a difference between current visual settings of the user interface when the user interactions are performed with respect to default visual settings of the user interface.
3. The computing system of claim 1 , wherein the metadata comprises user interface settings of measures and user interface settings of dimensions being viewed via the user interface.
4. The computing system of claim 1 , wherein the processor is configured to train a first plurality of contextual models which are associated with a plurality of dimensions of data, respectively, which are capable of being viewed via the user interface.
5. The computing system of claim 1 , wherein the processor is configured to train a second plurality of contextual models which are associated with a plurality of measures of data, respectively, which are capable of being viewed via the user interface.
6. The computing system of claim 1 , wherein the processor is further configured to receive a request from the user for a visualization of a type of data, and predict a chart type from among a plurality of chart types for viewing the type of data based on the one or more trained predictive models.
7. The computing system of claim 6 , wherein the processor is further configured to predict a drill-down level of the user interface for viewing hierarchical attributes of the type of data via execution of the one or more trained predictive models.
8. The computing system of claim 6 , wherein the processor is further configured to predict one or more data filters to apply to the type of data for removing unwanted attributes of the type of data via execution of the one or more trained predictive models.
9. A method comprising:
receiving an identification of user interactions actions of a user with respect to a user interface of a software application;
receiving metadata indicating the user interactions with respect to one or more parameters or settings of a user interface of a software application;
training one or more predictive models based on the user interactions with respect to the one or more parameters or settings of the user interface, wherein the training of the one or predictive models is to predict measures and dimensions for display via the user interface based on the user interactions and differences indicated by the metadata, between current visual settings of the user interface and default user interface settings; and
storing the one or more trained predictive models via a storage device.
10. The method of claim 9 , wherein the training comprises training the one or more predictive models based on a difference between current visual settings of the user interface when the user interactions are performed with respect to default visual settings of the user interface.
11. The method of claim 9 , wherein the metadata comprises user interface settings of measures and user interface settings of dimensions being viewed via the user interface.
12. The method of claim 9 , wherein the training comprises training a first plurality of contextual models which are associated with a plurality of dimensions of data, respectively, which are capable of being viewed via the user interface.
13. The method of claim 9 , wherein the training comprises training a second plurality of contextual models which are associated with a plurality of measures of data, respectively, which are capable of being viewed via the user interface.
14. The method of claim 9 , further comprising receiving a request from the user for a visualization of a type of data, and predicting a chart type from among a plurality of chart types for viewing the type of data based on a trained predictive model associated with the type of data.
15. The method of claim 14 , wherein the predicting further comprises predicting a drill-down level of the user interface for viewing hierarchical attributes of the type of data.
16. The method of claim 14 , wherein the predicting further comprises predicting one or more data filters to apply to the type of data for removing unwanted attributes of the type of data.
17. A non-transitory computer-readable medium storing program instructions which when executed by a processor cause a computer to perform a method comprising:
receiving an identification of user interactions of a user with respect to a user interface of a software application;
training one or more predictive models based on the user interactions with respect to one or more parameters or settings of the user interface, wherein the training of the one or more predictive models is to predict measures and dimensions for display via the user interface based on the user interactions and differences indicated by the metadata, between current visual settings of the user interface and default user interface settings; and
storing the one or more trained predictive models via a storage device.
18. The non-transitory computer-readable medium of claim 17 , wherein the method further comprises receiving a request from the user for a visualization of a type of data, and predicting a chart type from among a plurality of chart types for viewing the type of data based on the one or more trained predictive models.
19. The non-transitory computer-readable medium of claim 17 , wherein the predicting further comprises predicting a drill-down level of the user interface for viewing hierarchical attributes of the type of data.
20. The non-transitory computer-readable medium of claim 17 , wherein the predicting further comprises predicting one or more data filters to apply to the type of data for removing unwanted attributes of the type of data.