View source for 18070195. GENERATING, USING A MACHINE LEARNING MODEL, REQUEST AGNOSTIC INTERACTION SCORES FOR ELECTRONIC COMMUNICATIONS, AND UTILIZATION OF SAME simplified abstract (GOOGLE LLC)

=GENERATING, USING A MACHINE LEARNING MODEL, REQUEST AGNOSTIC INTERACTION SCORES FOR ELECTRONIC COMMUNICATIONS, AND UTILIZATION OF SAME=


==Organization Name==

[[:Category:GOOGLE LLC|GOOGLE LLC]]


[[Category:GOOGLE LLC]]

==Inventor(s)==

[[:Category:Archit Gupta of Sunnyvale CA (US)|Archit Gupta of Sunnyvale CA (US)]][[Category:Archit Gupta of Sunnyvale CA (US)]]

[[:Category:Hariharan Chandrasekaran of Sunnyvale CA (US)|Hariharan Chandrasekaran of Sunnyvale CA (US)]][[Category:Hariharan Chandrasekaran of Sunnyvale CA (US)]]

[[:Category:Harish Chandran of Sunnyvale CA (US)|Harish Chandran of Sunnyvale CA (US)]][[Category:Harish Chandran of Sunnyvale CA (US)]]

==GENERATING, USING A MACHINE LEARNING MODEL, REQUEST AGNOSTIC INTERACTION SCORES FOR ELECTRONIC COMMUNICATIONS, AND UTILIZATION OF SAME - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18070195 titled 'GENERATING, USING A MACHINE LEARNING MODEL, REQUEST AGNOSTIC INTERACTION SCORES FOR ELECTRONIC COMMUNICATIONS, AND UTILIZATION OF SAME

==Simplified Explanation==

The patent application describes a method for training a machine learning model to predict the quality of electronic communications, regardless of the specific request they are responding to. This predicted interaction score can then be used to determine how and whether to provide the communication to a client device.

* The machine learning model is trained to generate predicted interaction scores for electronic communications.
* These scores indicate the quality of the communication and are generated independently of the specific request it is responding to.
* The predicted interaction scores are generated offline and assigned to the electronic communication for efficient retrieval and utilization.
* This technology enables fast and efficient retrieval and utilization of the predicted interaction scores when the communication is responsive to a request.

== Potential Applications ==
* Email filtering: The predicted interaction scores can be used to filter and prioritize incoming emails based on their quality.
* Customer service: The scores can help determine which pre-written responses or templates to use when responding to customer inquiries.
* Content recommendation: The predicted interaction scores can be used to recommend relevant and high-quality content to users.

== Problems Solved ==
* Efficient retrieval and utilization: By generating the predicted interaction scores offline and pre-indexing them with the electronic communication, the technology enables fast and efficient retrieval and utilization of the scores.
* Quality assessment: The machine learning model helps assess the quality of electronic communications, providing an indication of their overall value.

== Benefits ==
* Improved communication quality: By predicting the quality of electronic communications, this technology can help ensure that users receive high-quality and relevant information.
* Time-saving: The efficient retrieval and utilization of predicted interaction scores can save time for both users and computing devices.
* Personalized experiences: By utilizing the predicted interaction scores, the technology can provide personalized recommendations and responses based on the quality of the communication.


==Original Abstract Submitted==

Training and/or utilizing a machine learning model to generate request agnostic predicted interaction scores for electronic communications, and to utilization of request agnostic predicted interaction scores in determining whether, and/or how, to provide corresponding electronic communications to a client device in response to a request. A request agnostic predicted interaction score for an electronic communication provides an indication of quality of the communication, and is generated independent of corresponding request(s) for which it is utilized. In many implementations, a request agnostic predicted interaction score for an electronic communication is generated “offline” relative to corresponding request(s) for which it is utilized, and is pre-indexed with (or otherwise assigned to) the electronic communication. This enables fast and efficient retrieval, and utilization, of the request agnostic interaction score by computing device(s), when the electronic communication is responsive to a request.



[[Category:G06N20/00]]
[[Category:G06F16/783]]
[[Category:G06F16/33]]
[[Category:G06F16/9536]]
[[Category:G06F16/583]]
[[Category:G06N7/01]]
[[Category:G06N5/02]]