Providing user-specific previews within text
Examples described herein include systems and methods for providing user-specific previews for terms within text. An example method can include receiving tracked user behavior reflecting terms selected by a user and entered into a search. A representation of known words can be created based on the tracked user behavior. By training machine-learning models for each individual user, personalized previews can be presented when each user encounters a new body of text, such as in a webpage or email. The preview can apply to a term not previously known to the user but likely to be searched by the user, relying on content gathered from a search on a search medium that the user was likely to use. The content can be presented to the user in a graphical user interface allowing for interaction and feedback.
1. A method for providing user-specific previews for terms within text, comprising:
displaying an email on a graphical user interface (GUI) page of an email application executing on a user device;
parsing the text of the email;
inputting the parsed text to a machine-learning model, wherein the machine-learning model is trained at a management server based on tracked user behavior of the user of the user device;
based on the output of the machine-learning model:
identifying a candidate term from the parsed text; and
predicting an enterprise application most likely to be used by the user to search for the candidate term, wherein the enterprise application stores data at a secure server accessible to the user; and
displaying a card based on the prediction, wherein the card:
is displayed in the foreground of the first GUI page;
includes at least a first selectable element a second selectable element;
includes at least a first page corresponding to the first selectable element and a second page corresponding to the second selectable element,
wherein the first page and the second page display different visualizations of data relating to the enterprise application, and
wherein the card initially displays the first page with the first selectable element selected.
2. The method of claim 1 , further comprising, in response to user selection of the second selectable element, displaying the second page on the card.
3. The method of claim 1 , wherein the user can interact with the card while the card remains on the foreground of the first GUI page.
4. The method of claim 1 , wherein the candidate term is identified based on the user selecting a term from the text.
5. The method of claim 1 , wherein the candidate term is identified based on the user hovering a cursor above a term from the text.
6. The method of claim 1 , wherein the machine-learning model is trained based on term categories, source categories, and search-medium categories extracted from the tracked user behavior.
7. The method of claim 1 , further comprising, in response to user feedback indicating that the first card is not helpful, displaying a second card on the GUI page, wherein the second card replaces the first card in the foreground of the GUI page and includes a first page and a second page, the pages displaying different visualizations of data relating to a second enterprise application.
8. A non-transitory, computer-readable medium containing instructions that, when executed by a hardware-based processor, cause the processor to perform stages for providing user-specific previews for terms within text, the stages comprising:
displaying an email on a graphical user interface (GUI) page of an email application executing on a user device;
parsing the text of the email;
inputting the parsed text to a machine-learning model, wherein the machine-learning model is trained at a management server based on tracked user behavior of the user of the user device;
based on the output of the machine-learning model:
identifying a candidate term from the parsed text; and
predicting an enterprise application most likely to be used by the user to search for the candidate term, wherein the enterprise application stores data at a secure server accessible to the user; and
displaying a card based on the prediction, wherein the card:
is displayed in the foreground of the first GUI page;
includes at least a first selectable element a second selectable element;
includes at least a first page corresponding to the first selectable element and a second page corresponding to the second selectable element,
wherein the first page and the second page display different visualizations of data relating to the enterprise application, and
wherein the card initially displays the first page with the first selectable element selected.
9. The non-transitory, computer-readable medium of claim 8 , the stages further comprising, in response to user selection of the second selectable element, displaying the second page on the card.
10. The non-transitory, computer-readable medium of claim 8 , wherein the user can interact with the card while the card remains on the foreground of the first GUI page.
11. The non-transitory, computer-readable medium of claim 8 , wherein the candidate term is identified based on the user selecting a term from the text.
12. The non-transitory, computer-readable medium of claim 8 , wherein the candidate term is identified based on the user hovering a cursor above a term from the text.
13. The non-transitory, computer-readable medium of claim 8 , wherein the machine-learning model is trained based on term categories, source categories, and search-medium categories extracted from the tracked user behavior.
14. The non-transitory, computer-readable medium of claim 8 , the stages further comprising, in response to user feedback indicating that the first card is not helpful, displaying a second card on the GUI page, wherein the second card replaces the first card in the foreground of the GUI page and includes a first page and a second page, the pages displaying different visualizations of data relating to a second enterprise application.
15. A system for providing user-specific previews for terms within text, comprising:
a memory storage including a non-transitory, computer-readable medium comprising instructions; and
a user device including a processor that executes the instructions to carry out stages comprising:
displaying an email on a graphical user interface (GUI) page of an email application executing on a user device;
parsing the text of the email;
inputting the parsed text to a machine-learning model, wherein the machine-learning model is trained at a management server based on tracked user behavior of the user of the user device;
based on the output of the machine-learning model:
identifying a candidate term from the parsed text; and
predicting an enterprise application most likely to be used by the user to search for the candidate term, wherein the enterprise application stores data at a secure server accessible to the user; and
displaying a card based on the prediction, wherein the card:
is displayed in the foreground of the first GUI page;
includes at least a first selectable element a second selectable element;
includes at least a first page corresponding to the first selectable element and a second page corresponding to the second selectable element,
wherein the first page and the second page display different visualizations of data relating to the enterprise application, and
wherein the card initially displays the first page with the first selectable element selected.
16. The system of claim 15 , the stages further comprising, in response to user selection of the second selectable element, displaying the second page on the card.
17. The system of claim 15 , wherein the user can interact with the card while the card remains on the foreground of the first GUI page.
18. The system of claim 15 , wherein the candidate term is identified based on the user selecting a term from the text.
19. The system of claim 15 , wherein the candidate term is identified based on the user hovering a cursor above a term from the text.
20. The system of claim 15 , wherein the machine-learning model is trained based on term categories, source categories, and search-medium categories extracted from the tracked user behavior.