Data processing for multi-objective communication engagement

Patent metadata

Field	Value
Publication number	US-11425084-B2
Application number	US-201916506773-A
Country	US
Kind code	B2
Filing date	Jul 9, 2019
Priority date	Apr 3, 2019
Publication date	Aug 23, 2022
Grant date	Aug 23, 2022

Abstract

A cloud platform supports a digital communication system that identifies recommended communication frequencies based on past communication data. The cloud platform may support blending of weights applied to different engagement rates. Based on the weights, the system identifies recommended frequency ranges to maximize engagement rates, including the blended engagement rate using a redistribution simulation process.

First claim

What is claimed is:

1. A method for data processing, comprising:
receiving, at a client system, a selection of a first weight corresponding to a first engagement rate, a selection of a second weight corresponding to a second engagement rate, and a selection of a third weight corresponding to a third engagement rate, wherein the first engagement rate and the second engagement rate correspond to positive engagement rates and wherein the third engagement rate corresponds to a negative engagement rate;
receiving a set of transmission frequency groups for a plurality of digital communications, a number of users corresponding to each transmission frequency group of the set of transmission frequency groups such that the number of users for a transmission frequency group have received a digital communication of the plurality of digital communications at a respective receive rate for the transmission frequency group, and the first engagement rate, the second engagement rate, and the third engagement rate for the set of transmission frequency groups, wherein the first engagement rate, the second engagement rate, and the third engagement rate are based at least in part on user engagement metadata corresponding to the plurality of digital communications processed by a server;
calculating a blended reward rate for the transmission frequency group of the set of transmission frequency groups based on the first weight, the first engagement rate, the second weight, and the second engagement rate corresponding to the transmission frequency group;
scaling, for the transmission frequency group, the third engagement rate to generate a magnified penalty ratio for the transmission frequency group based on the third weight; and
calculating, for the transmission frequency group, a blended target rate based on the blended reward rate and the magnified penalty ratio for the transmission frequency group.

2. The method of claim 1 , wherein scaling the third engagement rate for the transmission frequency group further comprises:
calculating, for the transmission frequency group, a penalty ratio between the blended reward rate and the third engagement rate;
calculating, for the transmission frequency group, a scaling factor by shifting the penalty ratio for each frequency group based on the third weight to generate a shifted engagement rate ratio; and
generating the magnified penalty ratio for the transmission frequency group based on the scaling factor and the third engagement rate for the transmission frequency group.

3. The method of claim 1 , further comprising:
calculating, at the client system, for the transmission frequency group, a predicted blended target number increase based on a redistribution of the number of users corresponding to the transmission frequency group based on the blended target rate for the transmission frequency group.

4. The method of claim 3 , wherein calculating based on the redistribution further comprises:
selecting a plurality of transmission frequency ranges from the set of transmission frequency groups;
redistributing, for each transmission frequency range of the plurality of transmission frequency ranges, a number of digital communication messages from each transmission frequency group of the set of transmission frequency groups outside of a transmission frequency range to transmission frequency groups within the transmission frequency range; and
calculating, for each transmission frequency range of the plurality of transmission frequency ranges, a predicted target count based at least in part on the redistributed number of digital communication messages into the transmission frequency range and the blended target rate for each transmission frequency group in the transmission frequency range.

5. The method of claim 1 , further comprising:
receiving a selection of a range of frequency groups, wherein the set of transmission frequency groups corresponds to the selected range.

6. The method of claim 1 , further comprising:
receiving an adjustment of one or more of the first weight, the second weight, and the third weight; and
recalculating, at the client system the blended target rate based on the adjustment.

7. The method of claim 1 , wherein the third engagement rate comprises a blended penalty rate comprising two or more negative engagement rates and corresponding weights.

8. The method of claim 1 , wherein the first engagement rate corresponds to an open rate and the second engagement rate corresponds to a click rate.

9. The method of claim 1 , wherein the third engagement rate corresponds to an unsubscribe rate.

10. An apparatus for data processing, comprising:
a processor,
memory coupled with the processor; and
instructions stored in the memory and executable by the processor to cause the apparatus to:
receive, at a client system, a selection of a first weight corresponding to a first engagement rate, a selection of a second weight corresponding to a second engagement rate, and a selection of a third weight corresponding to a third engagement rate, wherein the first engagement rate and the second engagement rate correspond to positive engagement rates and wherein the third engagement rate corresponds to a negative engagement rate;
receive a set of transmission frequency groups for a plurality of digital communications, a number of users corresponding to each transmission frequency group of the set of transmission frequency groups such that the number of users for a transmission frequency group have received a digital communication of the plurality of digital communications at a respective receive rate for the transmission frequency group, and the first engagement rate, the second engagement rate, and the third engagement rate for the set of transmission frequency groups, wherein the first engagement rate, the second engagement rate, and the third engagement rate are based at least in part on user engagement metadata corresponding to the plurality of digital communications processed by a server;
calculate a blended reward rate for the transmission frequency group of the set of transmission frequency groups based on the first weight, the first engagement rate, the second weight, and the second engagement rate corresponding to the transmission frequency group;
scale, for the transmission frequency group, the third engagement rate to generate a magnified penalty ratio for the transmission frequency group based on the third weight; and
calculate, for the transmission frequency group, a blended target rate based on the blended reward rate and the magnified penalty ratio for the transmission frequency group.

11. The apparatus of claim 10 , wherein the instructions to scale the third engagement rate for the transmission frequency group further are executable by the processor to cause the apparatus to:
calculate, for the transmission frequency group, a penalty ratio between the blended reward rate and the third engagement rate;
calculate, for the transmission frequency group, a scaling factor by shifting the penalty ratio for each frequency group based on the third weight to generate a shifted engagement rate ratio; and
generate the magnified penalty ratio for the transmission frequency group based on the scaling factor and the third engagement rate for the transmission frequency group.

12. The apparatus of claim 10 , wherein the instructions are further executable by the processor to cause the apparatus to:
calculate, at the client system, for the transmission frequency group, a predicted blended target number increase based on a redistribution of the number of users corresponding to the transmission frequency group based on the blended target rat

Assignees

• Salesforce Com Inc
• Salesforce Inc

Inventors

• Zhang Yuxi
• Xie Kexin
• Su Sheng Loong
• Basu Mallick Shrestha

Classifications

• H04L51/52

  for supporting social networking services · CPC title

• G06Q30/0242 Primary

  Determining effectiveness of advertisements · CPC title

• H04L51/56

  Unified messaging, e.g. interactions between e-mail, instant messaging or converged IP messaging [CPM] · CPC title

• H04L51/234 Primary

  for tracking messages · CPC title

• H04L51/36

  Electricity · mapped topic