Machine learning based supervised user experience for an application monitored by multiple secondary applications
Disclosed is a system for managing content generated by bots for presentation to a user in association with a chat application. The system receives content items generated by bots monitoring a chat application for display to a user at a user interface (UI). The system provides input based on the received one or more content items and associated contextual information to a trained machine learning (ML) model, and receives, from the trained ML model, for each of the content items, at least one score value based on at least one predicted user response associated with potentially displaying the content item to the user at the UI. The system selects a subset of content items from the received content items based on the received score values and causes a display of this selected subset of content items in addition to a display of content generated by the chat application.
1 . A computer-implemented method for managing content, the method comprising:
monitoring of a primary application by a plurality of secondary applications, wherein the plurality of secondary applications generate content items for display at a user interface (UI) of the primary application in response to detecting an event;
for the content items, providing as input to a trained machine learning model, contextual information by which the content items were generated, comprising: information describing the primary application and information describing the plurality of secondary applications;
predicting a user response including one or more of dismissing, approval and disapproval signal indicators;
receiving, from the trained machine learning model, for the content items, score values based on the predicted user response associated with potentially displaying the content items to the user via the UI and based on a type of the UI from among a plurality of applications in which the content items will be displayed;
selecting a subset of the content items based on the score values; and
causing a display of the subset of the content items at the UI in addition to a display of content generated by the primary application,
wherein the plurality of secondary applications are AI powered or rule powered bots.
2 . The computer-implemented method of claim 1 , wherein the contextual information comprises one or more of:
geographical information associated with the primary application;
language information associated with the primary application; and
contextual information associated with one or more other users associated with the primary application.
3 . The computer-implemented method of claim 1 , wherein the contextual information further comprises:
contextual information associated with the user.
4 . The computer-implemented method of claim 3 , wherein the contextual information associated with the user comprises:
profile information stored for the user; and
a prior history associated with the user, the prior history including previous actions of the user in response to displayed content items.
5 . The computer-implemented method of claim 1 , wherein the contextual information comprises one or more of:
one or more content items received previously; and
user actions in response to the one or more content items.
6 . The computer-implemented method of claim 1 , wherein the displaying the subset of the content items at the UI to the user further comprises:
receiving an indication from the user regarding the displaying the subset of the content items on the UI; and
modifying the display of the subset of the content items based on the indication.
7 . The computer-implemented method of claim 1 , further comprising providing feedback information to a secondary application that provided a particular content item of the content items, the feedback information regarding a display of the particular content item on the UI.
8 . The computer-implemented method of claim 7 , wherein the feedback information regarding the display of the particular content item comprises as least one of:
the particular content item displayed at the UI;
the particular content item displayed in a particular position in an ordered display on the UI; and
the particular content item not selected for display at the UI.
9 . A non-transitory computer readable storage medium for storing instructions that when executed by a computer processor cause the computer processor to perform steps for managing content, the steps comprising:
monitoring of a primary application by a plurality of secondary applications, wherein the plurality of secondary applications generate content items for display at a user interface (UI) of the primary application in response to detecting an event;
for the content items, providing as input to a trained machine learning model, contextual information by which the content items were generated, comprising: information describing the primary application and information describing the plurality of secondary applications;
predicting a user response including one or more of dismissing, approval and disapproval signal indicators;
receiving, from the trained machine learning model, for the content items, score values based on the predicted user response associated with potentially displaying the content items to the user via the UI and based on a type of the UI from among a plurality of applications in which the content items will be displayed;
selecting a subset of the content items based on the score values; and
causing a display of the subset of the content items at the UI in addition to a display of content generated by the primary application,
wherein the plurality of secondary applications are Al powered or rule powered bots.
10 . The non-transitory computer readable storage medium of claim 9 , wherein the contextual information comprises one or more of:
geographical information associated with the primary application;
language information associated with the primary application; and
contextual information associated with one or more other users associated with the primary application.
11 . The non-transitory computer readable storage medium of claim 9 , wherein the contextual information further comprises:
contextual information associated with the user.
12 . The non-transitory computer readable storage medium of claim 11 , wherein the contextual information associated with the user comprises:
profile information stored for the user; and
a prior history associated with the user, the prior history including previous actions of the user in response to displayed content items.
13 . The non-transitory computer readable storage medium of claim 9 , wherein the contextual information comprises one or more of:
one or more content items received previously; and
user actions in response to the one or more content items.
14 . The non-transitory computer readable storage medium of claim 9 , wherein the displaying the subset of the content items at the UI to the user further comprises:
receiving an indication from the user regarding the displaying the subset of the content items on the UI; and
modifying the display of the subset of the content items based on the indication.
15 . The non-transitory computer readable storage medium of claim 9 , further comprising providing feedback information to a secondary application that provided a particular content item of the content items, the feedback information regarding a display of the particular content item on the UI.
16 . The non-transitory computer readable storage medium of claim 15 , wherein the feedback information regarding the display of the particular content item comprises as least one of:
the particular content item displayed at the UI;
the particular content item displayed in a particular position in an ordered display on the UI; and
the particular content item not selected for display at the UI.
17 . A computer system comprising:
a computer processor; and
a non-transitory computer readable storage medium for storing instructions that when executed by a computer processor cause the computer processor to perform steps for managing content, the steps comprising:
monitoring of a primary application by a plurality of secondary applications, wherein the plurality of secondary applications generate content items for display at a user interface (UI) of the primary application in response to detecting an event;
for the content items, providing as input to a trained machine learning model, contextual information by which the content items were generated, comprising: (1) information describing the primary application and (2) information describing the plurality of secondary applications that generated the content items;
predicting a user response including one or more of dismissing, approval and disapproval signal indicators;
receiving, from the trained machine learning model, for the content items, score values based on the predicted user response associated with potentially displaying the content items to the user via the UI and based on a type of the UI from among a plurality of applications in which the content items will be displayed;
selecting a subset of the content items based on the score values; and
causing a display of the subset of the content items at the UI in addition to a display of content generated by the primary applications
wherein the plurality of secondary applications are AI powered or rule powered bots.
18 . The computer system of claim 17 , wherein the displaying the subset of the content items at the UI to the user further comprises:
receiving an indication from the user regarding the displaying the subset of the content items on the UI; and
modifying the display of the subset of the content items based on the indication.
19 . The computer system of claim 17 , further comprising providing feedback information to a secondary application that provided a particular content item of the content items, the feedback information regarding a display of the particular content item on the UI.
20 . The computer system of claim 19 , wherein the feedback information regarding the display of the particular content item comprises as least one of:
the particular content item displayed at the UI;
the particular content item displayed in a particular position in an ordered display on the UI; and
the particular content item not selected for display at the UI.