Content generation and targeting using machine learning

Patent metadata

Field	Value
Publication number	US-10671680-B2
Application number	US-201615247075-A
Country	US
Kind code	B2
Filing date	Aug 25, 2016
Priority date	Aug 25, 2016
Publication date	Jun 2, 2020
Grant date	Jun 2, 2020

Abstract

A system and method for content generation and targeting using machine learning are provided. In example embodiments, a probability that a user will visit a webpage based on historical data is calculated. A probability that the user will engage with a particular content category based on past user engagement is calculated. In response to the probability of the user engaging with the particular content category being equal to or greater than a first threshold, the content is generated. Further, in response to the probability of the user not visiting a webpage meeting or exceeding a second threshold, the generated content is sent to the user.

First claim

What is claimed is:

1. A system comprising:
one or more hardware processors, and a computer-readable memory including instructions, which when executed by the one or more hardware processors, configure the system to perform a plurality of operations comprising:
calculating a probability that a user will not visit a webpage with a predetermined period of time, based on historical data about past visits to the webpage;
calculating a probability that the user will engage with a particular content category based on past user engagement;
in response to the probability of the user engaging with the particular content category being equal to or greater than a first threshold, generating content from the particular content category;
in response to the probability of the user not visiting a webpage meeting or exceeding a second threshold, sending the generated content to the user.

2. The system of claim 1 , wherein:
the calculating of the probability that the user will visit a webpage is further based on user profile information associated with the user.

3. The system of claim 1 , further comprising:
identifying other members of a social network service based on a comparison between the user profile and other members profiles associated with the other members; and
wherein the historical data includes historical data of the user and other members identified to be similar to the user.

4. The system of claim 1 , wherein:
the historical data include activities that indicate the user engaged with a social network service.

5. The system of claim 1 , wherein:
the calculating of the probability that the user will engage with a particular content category is further based on information specific to the user.

6. The system of claim 1 , wherein:
the calculating of the probability that the user will engage with a particular content category is further based on a content feature that elicited past user action.

7. The system of claim 1 , wherein:
the calculating of the probability that the user will visit a webpage is based on machine learning using a logistic regression model.

8. The system of claim 1 wherein:
the probability of the user visiting the webpage is further based on the user visiting the webpage within a predetermined time period.

9. The system of claim 1 , wherein:
the user engaging with the content includes the user clicking on the content and is redirected to a corresponding webpage.

10. The system of claim 1 , further comprising:
determining a communication channel to interact with the user based on past user engagement with the communication channel selected from a plurality of communication channels; and
wherein, the sending the generated content is sent via the determined communication channel.

11. A method comprising:
using one or more computer processors:
calculating a probability that a user will not visit a webpage with a predetermined period of time, based on historical data about past visits to the webpage;
calculating a probability that the user will engage with a particular content category based on past user engagement;
in response to the probability of the user engaging with the particular content category being equal to or greater than a first threshold, generating content from the particular content category; and
in response to the probability of the user not visiting a webpage meeting or exceeding a second threshold, sending the generated content to the user.

12. The method of claim 11 , wherein:
the historical data includes a user profile for the user and member profiles of other members; and
identifying similar members that are similar to the user by comparing the user profile with respective member profiles of the other members.

13. The method of claim 11 , wherein:
the calculating of the probability that the user will engage with a particular content category is further based on information specific to the user.

14. The method of claim 11 , wherein:
the calculating of the probability that the user will engage with a particular content category is further based on a content feature that elicited past user action.

15. The method of claim 11 , wherein:
the calculating of the probability that the user will visit a webpage is based on machine learning using a logistic regression model.

16. The method of claim 11 , wherein:
the probability of the user visiting the webpage is further based on the user visiting the webpage within a predetermined time period.

17. The method of claim 11 , wherein:
the user engaging with the content includes the user clicking on the content and is redirected to a corresponding webpage.

18. The method of claim 11 , further comprising:
determining a communication channel to interact with the user based on past user engagement with the communication channel selected from a plurality of communication channels; and
wherein, the sending the generated content is sent via the determined communication channel.

19. A machine-readable medium not having any transitory signals and storing instructions that, when executed by at least one processor of a machine, cause the machine to perform operations comprising:
calculating a probability that a user will not visit a webpage based on historical data;
calculating a probability that a user will not visit a webpage with a predetermined period of time, based on historical data about past visits to the webpage;
in response to the probability of the user engaging with the particular content category being equal to or greater than a first threshold, generating content from the particular content category;
in response to the probability of the user not visiting a webpage meeting or exceeding a second threshold, sending the generated content to the user.

20. The machine-readable medium of claim 19 , wherein the operations further comprise:
determining a communication channel to interact with the user based on past user engagement with the communication channel selected from a plurality of communication channels; and
wherein, the sending the generated content is sent via the determined communication channel.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Yan Jinyun
• Tseng Hsiao-Ping
• Chen Xiaoyu
• Gupta Rupesh
• Rosales Romer E

Classifications

• G06Q10/067

  Enterprise or organisation modelling · CPC title

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06Q50/01

  Physics · mapped topic

• G06N20/00

  Machine learning · CPC title