# US 2021/0241307 A1 · System and method for dynamic audience mapping and promotion execution

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0241307 A1
- Document ID: US20210241307A1
- Status: Published application
- Kind: A1
- Application number: 16/778,139
- Filed: 2020-01-31
- Published: 2021-08-05
- Earliest claimed: 2020-01-31
- Assignees: salesforce.com, inc.
- Applicants: salesforce.com, inc.
- Inventors: Natalija Pavic; Daniel Thomas Harrison
- Web page: https://patentgrep.com/patent/US20210241307A1

## CPC

- G06Q 30/0224: {based on user history}
- G06N 20/00: Machine learning
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method of targeting a promotion to an appropriate audience includes: performing clustering analysis on anonymized customer data using artificial intelligence to segment the anonymized data into a plurality of audience clusters; applying a matching algorithm to match a personalized promotion to a first audience cluster; sending the personalized promotion using a digital display channel to a plurality of individuals matching characteristics of the first audience cluster; receiving and recording results from the personalized promotion; and iteratively adjusting the personalized promotion based on the results from the personalized promotion. The iteratively adjusting includes: adjusting terms of the personalized promotion, sending the adjusted personalized promotion to a plurality of individuals, recording the success and failure of the adjusted personalized promotion, measuring the success of the adjusted personalized promotion, and repeating the adjusting, sending, recording, and measuring until a desired business result is obtained or a predetermined promotion adjustment ending point has been reached.

## Claims

### Claim 1

A system for executing an advertising campaign that iteratively adjusts a promotion displayed to targets viewers, the system comprising:
a controller comprising at least one processor and a computer-readable storage device encoded with programming instructions for configuring the at least one processor, the controller having access to anonymized data regarding a plurality of individuals who purchase goods and/or services in the marketplace, the anonymized data including demographic information and sales data, the sales data including data regarding purchases made in response to some form of advertising and/or promotion, wherein the controller causes the system to:
generate a plurality of audience clusters from the anonymized data using a segmentation algorithm that is refined over time using machine learning techniques based on sales results reported from past promotions to identify a type of audience cluster to define for a particular type of promotion wherein each audience cluster is partitioned as a coherent group based on buying preferences;
generate a first result including a personalized promotion and a first audience cluster from the plurality of audience clusters using a matching algorithm that is refined using machine learning techniques based on sales results reported from past promotions aimed at a particular audience group to identify a type of promotion to apply to the first audience cluster;
signal using a digital display channel to a plurality of user interfaces for a plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion;
generate a second result including a first measurement of success of the personalized promotion with the plurality of individuals matching characteristics of the first audience cluster, the first measurement of success including one or more of margin, revenue, or market share; and
repeat adjusting one or more terms of the personalized promotion based on the first measurement of success of the personalized promotion signaling to a plurality of user interfaces for another plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion, and generating the second result until the earliest of the first measurement of success reaching a desired measurement of success or a predetermined promotion adjustment ending point being reached.

### Claim 2 (depends on 1)

The system of claim 1, wherein the controller is further configured to:
generate a third result including a second personalized promotion and a second audience cluster from the plurality of audience clusters using the matching algorithm;
signal using a digital display channel to a plurality of individuals matching characteristics of the second audience cluster to display the second personalized promotion;
generate a fourth result including a second measurement of success of the personalized promotion with the plurality of individuals matching characteristics of the second audience cluster, the second measurement of success including one or more of margin, revenue, or market share; and
repeat adjusting one or more terms of the second personalized promotion based on the second measurement of success of the second personalized promotion, signaling to a plurality of user interfaces for another plurality of individuals to display the personalized promotion, and generating the fourth result until the earliest of the second measurement of success reaching a second desired measurement of success or a second predetermined promotion adjustment ending point being reached.

### Claim 3 (depends on 1)

The system of claim 1, wherein the buying preferences include one or more of: preference for the lowest price; preference for special or early access to products; preference for earning loyalty points or a status; or preference for ethical or environmental messaging.

### Claim 4

(canceled)

### Claim 5

(canceled)

### Claim 6 (depends on 1)

The system of claim 1, wherein the controller is further configured to determine a SPP (susceptibility to purchase with a promotion) and degree of SPP for a plurality of audience clusters for a plurality of promotions when repeated adjusting one or more terms of the personalized promotion based on the first measurement of success of the personalized promotion, signaling to a plurality of user interfaces for another plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion, and generating the second result until the earliest of the first measurement of success reaching a desired measurement of success or a predetermined promotion adjustment ending point being reached.

### Claim 7 (depends on 6)

The method of claim 6, wherein the matching algorithm is configured to match a personalized promotion to a particular promotion using the SPP and degree of SPP.

### Claim 8 (depends on 1)

The system of claim 1, wherein the controller is configured to:
refine the matching algorithm using machine learning techniques based on A/B testing, the A/B testing including: sending a first advertisement having a first promotion to a group of individuals matching a third audience cluster and sending a second advertisement without the first promotion to a control group, measuring results from the first advertisement and the second advertisement, and determining the success of the first promotion based on the comparison of results from the first advertisement and the second advertisement.

### Claim 9 (depends on 1)

The system of claim 1, wherein the controller is further configured to record sales results from each iteration of the adjusting one or more terms of the personalized promotion based on the first measurement of success of the personalized promotion and the signaling to a plurality of user interfaces for another plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion in a blockchain data structure.

### Claim 10 (depends on 1)

The system of claim 1, wherein the controller is further configured to retrieve, from a blockchain data structure, sales results reported from past promotions to:
train the segmentation algorithm using machine learning techniques to identify the type of audience cluster to define for a particular type of promotion; and
train the matching algorithm using machine learning techniques to identify the type of promotion to apply to a particular audience cluster.

### Claim 11

A method for executing an advertising campaign that iteratively adjusts a promotion displayed to targets viewers the method comprising:
generating a plurality of audience clusters from anonymized data regarding a plurality of individuals who purchase goods and/or services in the marketplace, the anonymized data including demographic information and sales data, the sales data including data regarding purchases made in response to some form of advertising and/or promotion, wherein each audience cluster is partitioned as a coherent group based on buying preferences;
generating a first result including a personalized promotion to and a first audience cluster from the plurality of audience clusters using a matching algorithm that is refined using machine learning techniques based on sales results reported from past promotions aimed at a particular audience group to identify a type of promotion to apply to the first audience cluster;
signaling using a digital display channel to a plurality of user interfaces for a plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion;
generating a second result including a first measurement of success of the personalized promotion with the plurality of individuals matching characteristics of the first audience cluster, the first measurement of success including one or more of margin, revenue, or market share; and
repeating adjusting one or more terms of the personalized promotion based on the first measurement of the personalized promotion, signaling to a plurality of user interfaces for another plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion, and generating the second result until the earliest of the first measurement of success reaching a desired measurement of success or a predetermined promotion adjustment ending point being reached.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
generating a third result including a second personalized promotion and a second audience cluster from the plurality of audience clusters using the matching algorithm;
signaling using a digital display channel to a plurality of individuals matching characteristics of the second audience cluster to display the second personalized promotion;
generating a fourth result including a second measurement of success of the personalized promotion with the plurality of individuals matching characteristics of the second audience cluster, the second measurement of success including one or more of margin, revenue, or market share; and
repeating adjusting one or more terms of the second personalized promotion based on the second measurement of success of the second personalized promotion, signaling to a plurality of user interfaces for another plurality of individuals to display the personalized promotion, and generating the fourth result until the earliest of the second measurement of success reaching a second desired measurement of success or a second predetermined promotion adjustment ending point being reached.

### Claim 13 (depends on 11)

The method of claim 11, wherein the buying preferences include one or more of: preference for the lowest price; preference for special or early access to products; preference for earning loyalty points or a status; or preference for ethical or environmental messaging.

### Claim 14

(canceled)

### Claim 15

(canceled)

### Claim 16 (depends on 11)

The method of claim 11, further comprising to determine a SPP and degree of SPP (susceptibility to purchase with a promotion) for a plurality of audience clusters for a plurality of promotions when repeating adjusting one or more terms of the personalized promotion based on the first measurement of success of the personalized promotion, signaling to a plurality of user interfaces for another plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion, and generating the second result until the earliest of the first measurement of success reaching a desired measurement of success or a predetermined promotion adjustment ending point being reached.

### Claim 17 (depends on 16)

The method of claim 16, wherein the matching algorithm is configured to match to a personalized promotion to a particular promotion using the SPP and degree of SPP.

### Claim 18 (depends on 11)

The method of claim 11, further comprising:
refining the matching algorithm using machine learning techniques based on A/B testing, the A/B testing including: sending a first advertisement having a first promotion to a group of individuals matching a third audience cluster and sending a second advertisement without the first promotion to a control group, measuring the results from the first advertisement and the second advertisement, and determining the success of the first promotion based on the comparison of results from the first advertisement and the second advertisement.

### Claim 19 (depends on 11)

The method of claim 11, further comprising recording sales results from each iteration of the adjusting one or more terms of the personalized promotion based on the first measurement of success of the personalized promotion and the signaling to a plurality of user interfaces for another plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion in a blockchain data structure.

### Claim 20

Non-transitory computer readable media encoded with programming instructions configurable to cause a controller to perform a method for executing an advertising campaign that iteratively adjusts a promotion displayed to targets viewers, the method comprising:
generating a plurality of audience clusters from anonymized data regarding a plurality of individuals who purchase goods and/or services in the marketplace, the anonymized data including demographic information and sales data, the sales data including data regarding purchases made in response to some form of advertising and/or promotion, wherein each audience cluster is partitioned as a coherent group based on buying preferences;
generating a first result including a personalized promotion and a first audience cluster from the plurality of audience clusters using a matching algorithm that is refined using machine learning techniques based on sales results reported from past promotions aimed at a particular audience group to identify a type of promotion to apply to the first audience cluster;
signaling using a digital display channel to a plurality of user interfaces for a plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion;
generating a second result including a first measurement of success of the personalized promotion with the plurality of individuals matching characteristics of the first audience cluster, the first measurement of success including one or more of margin, revenue, or market share; and
repeating adjusting, one or more terms of the personalized promotion based on the first measurement of success of the personalized promotion, signaling to a plurality of user interfaces for another plurality of individuals matching characteristics of the first audience cluster to display the personalized promotion, and generating the second result until the earliest of the first measurement of success reaching a desired measurement of success or a predetermined promotion adjustment ending point being reached.

### Claim 21 (depends on 20)

The non-transitory computer readable media of claim 20, wherein the method further comprises:
generating a third result including a second personalized promotion and a second audience cluster from the plurality of audience clusters using the matching algorithm;
signaling using a digital display channel to a plurality of individuals matching characteristics of the second audience cluster to display the second personalized promotion;
generating a fourth result including a second measurement of success of the personalized promotion with the plurality of individuals matching characteristics of the second audience cluster, the second measurement of success including one or more of margin, revenue, or market share; and
repeating adjusting one or more terms of the second personalized promotion based on the second measurement of success of the second personalized promotion, signaling to a plurality of user interfaces for another plurality of individuals to display the personalized promotion, and generating the fourth result until the earliest of the second measurement of success reaching a second desired measurement of success or a second predetermined promotion adjustment ending point being reached.

### Claim 22 (depends on 20)

The non-transitory computer readable media of claim 20, wherein the buying preferences include one or more of: preference for the lowest price; preference for special or early access to products; preference for earning loyalty points or a status; or preference for ethical or environmental messaging.

### Claim 23 (depends on 20)

The non-transitory computer readable media of claim 20, wherein the method further comprises retrieving, from a blockchain data structure, sales results reported from past promotions to:
train the segmentation algorithm using machine learning techniques to identify the type of audience cluster to define for a particular type of promotion; and
train the matching algorithm using machine learning techniques to identify the type of promotion to apply to a particular audience cluster.

### Claim 24 (depends on 19)

The method of claim 19, further comprising retrieving, from a blockchain data structure, sales results reported from past promotions to:
train the segmentation algorithm using machine learning techniques to identify the type of audience cluster to define for a particular type of promotion; and
train the matching algorithm using machine learning techniques to identify the type of promotion to apply to a particular audience cluster.
