US 9,319,367 B2Granted

Email optimization for predicted recipient behavior: determining a likelihood that a particular receiver-side behavior will occur

AssigneeInsideSales.com, Inc.

InventorsXinchuan Zeng, Kalyan Penta, David Randal Elkington

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques are described herein for predicting one or more behaviors by an email recipient and, more specifically, to machine learning techniques for predicting one or more behaviors of an email recipient, changing one or more components in the email to increase the likelihood of a behavior, and determining and/or scheduling an optimal time to send the email. Some advantages of the embodiments disclosed herein may include, without limitation, the ability to predict the behavior of the email recipient and suggest the characteristics of an email which will increase the likelihood of a positive behavior, such as a reading or responding to the email, visiting a website, calling a sales representative, or opening an email attachment.

Claims22

Dependent claims

A system comprising:

a memory;
one or more processors coupled to the memory and configured to:
obtain feedback, for each previously sent message in a plurality of previously sent messages, that indicates whether a receiver-side behavior occurred relative to the previously sent message;
train a machine learning model based on one or more features associated with each previously sent message in the plurality of previously sent messages, and whether the receiver-side behavior occurred relative to the previously sent message;
present on a display, to a message creating user, an interface for drafting messages;
receive user input through the interface, from the message creating user, that specifies textual content for a draft message;
and
before the message creating user has sent the draft message drafted by the message creating user:
predict, based on the machine learning model and one or more features associated with the draft message, a first likelihood that a particular receiver-side behavior will occur relative to the draft message;
generate an indication that conveys the first likelihood that the particular receiver-side behavior will occur relative to the draft message;
and
cause the indication with the draft message to be presented on the display to the message creating user;
predict, based on the machine learning model and one or more features associated with a modified draft message, a second likelihood that the particular receiver-side behavior will occur relative to the modified draft message, wherein the modified draft message is produced by performing a modification to the draft message;
generate a second indication that conveys the second likelihood that the particular receiver-side behavior will occur relative to the modified draft message;
and
cause the second indication with the modified draft message to be presented on the display to the message creating user.

13 more elements

A method comprising:

obtaining, for each previously sent message in a plurality of previously sent messages, whether a receiver-side behavior occurred relative to the previously sent message;
training a machine learning model based on one or more features associated with each previously sent message in the plurality of previously sent messages, and whether the receiver-side behavior occurred relative to the previously sent message;
presenting on a display, to a message creating user, an interface for drafting messages;
receiving user input through the interface, from the message creating user, that specifies textual content for a draft message;
and
before a message creating user has sent a draft message drafted by the message creating user:
predicting, based on the machine learning model, a first likelihood that a particular receiver-side behavior will occur relative to the draft message;
generating an indication that conveys to the message creating user the first likelihood that the particular receiver-side behavior will occur relative to the draft message;
and
causing the indication with the draft message to be presented on the display to the message creating user;
predicting, based on the machine learning model and one or more features associated with a modified draft message, a second likelihood that the particular receiver-side behavior will occur relative to the modified draft message, wherein the modified draft message is produced by performing a modification to the draft message;
generating a second indication that conveys the second likelihood that the particular receiver-side behavior will occur relative to the modified draft message;
and
causing the second indication with the modified draft message to be presented on the display to the message creating user
wherein the method is performed by one or more computing devices.

12 more elements

Dependencies are inferred from the claim text.

Facts

Application: 14/503,149Filed 30 Sep 2014 · us provisional application
Priority: 12 Sep 2004
Published: US 2015/0347924 A13 Dec 2015
Granted: 19 Apr 2016
Term ends: Not estimatedThe source records don’t support an estimate.

Classification14 codes

G06N 20/00
Machine learning
G06N 7/01
Computing arrangements based on specific mathematical models: probabilistic graphical models, e.g. probabilistic networks
G06Q 10/067
Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling: enterprise or…
G06Q 10/087
Logistics, e.g. warehousing, loading or distribution; Inventory or stock management: inventory or stock management, e.g. order filling,…