Systems and methods for customizing user interfaces using artificial intelligence
Systems and methods are described herein for novel uses and/or improvements for designing user-specific interfaces using machine learning models. When a request to display certain data by an application is received, an application token and a user token may be retrieved and input into a machine learning model to obtain a prediction of a pre-defined user-application interface configuration. A user interface token for the application may then be generated. The user interface token may indicate user interface settings/configuration desired/preferred by a user. The user interface token may then be sent to the application to cause the application to display the data using user interface configurations within the user interface token.
1. A system for providing user interfaces using artificial intelligence, the system comprising:
one or more processors; and
one or more memories configured to store instructions that when executed by the one or more processors perform operations comprising:
receiving a request to display application data to a user of a first application;
retrieving a user token associated with the user, wherein the user token comprises a plurality of user configurations associated with a second application;
decoding the user token into a plurality of user interface settings associated with the second application;
inputting the plurality of user interface settings into a machine learning model to obtain a unique user-application interface configuration for the first application based on user interface settings associated with the second application, wherein the machine learning model is trained to generate a corresponding unique user-application interface configuration of a plurality of unique user-application interface configurations based on a corresponding plurality of user interface settings from a different application;
encoding the unique user-application interface configuration into a user interface token, wherein the user interface token is associated with a pre-defined configuration of a plurality of pre-defined configurations associated with the first application; and
sending a command to display the application data in a user interface of the first application using the user interface token, wherein the command causes initialization of the user interface of the first application with the unique user-application interface configuration.
2. A method for providing user interfaces using artificial intelligence, the method comprising:
receiving a request to display application data of a first application;
retrieving a user token associated with a user, wherein the user token comprises a plurality of user configurations associated with a second application;
inputting a plurality of user interface settings stored within the user token into a machine learning model to obtain a unique user-application interface configuration of a plurality of pre-defined unique user-application interfaces, wherein the machine learning model has been trained to predict the unique user-application interfaces for the first application based on user interface settings associated with the second application;
encoding the unique user-application interface configuration into a user interface token associated with the first application;
generating instructions for displaying a user interface element for selecting configurations, wherein the user interface element comprises a plurality of pre-defined unique user-application interface configurations; and
sending a command to display the application data in a user interface of the first application using the user interface token, wherein the instructions are added to the command, and wherein the command causes initialization of the user interface of the first application with the unique user-application interface configuration.
3. The method of claim 2 , further comprising decoding the user token into the plurality of user interface settings, wherein the plurality of user interface settings is available within an application.
4. The method of claim 2 , wherein the machine learning model is trained to generate a corresponding unique user-application interface configuration of a plurality of unique user-application interface configurations based on a corresponding plurality of user interface settings, and wherein the plurality of unique user-application interface configurations comprises a plurality of pre-defined configurations.
5. The method of claim 2 , further comprising:
receiving a plurality of training datasets, wherein each training dataset is associated with a corresponding application; and
training the machine learning model using the plurality of training datasets to obtain unique user-application interface configurations based on application training data and user data within the plurality of training datasets.
6. The method of claim 2 , wherein the plurality of pre-defined unique user-application interfaces comprises different unique user-application interfaces classified by complexity.
7. The method of claim 6 , further comprising:
receiving a training dataset comprising user data for a plurality of users, wherein the user data comprises user proficiency data associated with one or more user interfaces; and
training the machine learning model using the training dataset to obtain unique user-application interface configurations based on the user proficiency data.
8. The method of claim 2 , wherein encoding the unique user-application interface configuration into the user interface token comprises encoding, based on a template of a plurality of templates, the unique user-application interface configuration into the user interface token, wherein the template is associated with a pre-defined configuration of a plurality of pre-defined configurations.
9. The method of claim 8 , wherein encoding, based on the template of the plurality of templates, the unique user-application interface configuration into the user interface token comprises:
retrieving one or more of color scheme configuration, font configuration, layout configuration, or accessibility configuration from the unique user-application interface configuration; and
merging the one or more of the color scheme configuration, the font configuration, the layout configuration, or the accessibility configuration into the template.
10. The method of claim 2 , further comprising:
monitoring user interactions with the user interface associated with an application, wherein monitoring comprises recording user navigation data, completed action data, and completion timing data;
inputting the user navigation data, the completed action data, and the completion timing data into an interface update machine learning model to obtain a performance score for the user interface, wherein the machine learning model is trained to determine performance of different user interfaces in relation to users; and
based determining that the performance score is below a performance threshold, inputting the user navigation data, the completed action data, the completion timing data, and the unique user-application interface configuration into a configuration update machine learning model to obtain a new unique user-application interface configuration.
11. One or more non-transitory, computer-readable media for providing user interfaces using artificial intelligence, storing instructions thereon that cause one or more processors to perform operations comprising:
receiving a request to display application data of a first application;
retrieving a user token associated with a user, wherein the user token comprises a plurality of user configurations associated with a second application;
inputting a plurality of user interface settings stored within the user token into a machine learning model to obtain a unique user-application interface configuration of a plurality of pre-defined unique user-application interfaces, wherein the machine learning model has been trained to predict the unique user-application interfaces for the first application based on user interface settings associated with the second application;
encoding the unique user-application interface configuration into a user interface token associated with the first application;
generating instructions for displaying a user interface element for selecting configurations, wherein the user interface element comprises a plurality of pre-defined unique user-application interface configurations; and
sending a command to display the application data in a user interface of the first application using the user interface token, wherein the instructions are added to the command, and wherein the command causes initialization of the user interface of the first application with the unique user-application interface configuration.
12. The one or more non-transitory, computer-readable media of claim 11 , wherein the instructions further cause the one or more processors to decode the user token into the plurality of user interface settings, wherein the plurality of user interface settings is available within an application.
13. The one or more non-transitory, computer-readable media of claim 11 , wherein the machine learning model is trained to generate a corresponding unique user-application interface configuration of a plurality of unique user-application interface configurations based on a corresponding plurality of user interface settings, and wherein the plurality of unique user-application interface configurations comprises a plurality of pre-defined configurations.
14. The one or more non-transitory, computer-readable media of claim 11 , wherein the instructions further cause the one or more processors to perform operations comprising:
receiving a plurality of training datasets, wherein each training dataset is associated with a corresponding application; and
training the machine learning model using the plurality of training datasets to obtain unique user-application interface configurations based on application training data and user data within the plurality of training datasets.
15. The one or more non-transitory, computer-readable media of claim 11 , wherein the plurality of pre-defined unique user-application interfaces comprises different unique user-application interfaces classified by complexity.
16. The one or more non-transitory, computer-readable media of claim 15 , wherein the instructions further cause the one or more processors to perform operations comprising:
receiving a training dataset comprising user data for a plurality of users, wherein the user data comprises user proficiency data associated with one or more user interfaces; and
training the machine learning model using the training dataset to obtain unique user-application interface configurations based on the user proficiency data.
17. The one or more non-transitory, computer-readable media of claim 11 , wherein the instructions for encoding the unique user-application interface configuration into the user interface token cause the one or more processors to encode, based on a template of a plurality of templates, the unique user-application interface configuration into the user interface token, wherein the template is associated with a pre-defined configuration of a plurality of pre-defined configurations.
18. The one or more non-transitory, computer-readable media of claim 17 , wherein the instructions for encoding, based on the template of the plurality of templates, the unique user-application interface configuration into the user interface token cause the one or more processors to perform operations comprising:
retrieving one or more of color scheme configuration, font configuration, layout configuration, or accessibility configuration from the unique user-application interface configuration; and
merging the one or more of the color scheme configuration, the font configuration, the layout configuration, or the accessibility configuration into the template.
19. The one or more non-transitory, computer-readable media of claim 11 , wherein the instructions further cause the one or more processors to perform operations comprising:
monitoring user interactions with the user interface associated with an application, wherein monitoring comprises recording user navigation data, completed action data, and completion timing data;
inputting the user navigation data, the completed action data, and the completion timing data into an interface update machine learning model to obtain a performance score for the user interface, wherein the machine learning model is trained to determine performance of different user interfaces in relation to users; and
based determining that the performance score is below a performance threshold, inputting the user navigation data, the completed action data, the completion timing data, and the unique user-application interface configuration into a configuration update machine learning model to obtain a new unique user-application interface configuration.
20. The one or more non-transitory, computer-readable media of claim 11 , wherein the unique user-application interface configuration is pre-selected.