# US 11,909,699 B1 · System and method for automatic short message generation

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

- Number: US 11,909,699 B1
- Document ID: US11909699B1
- Status: Granted
- Kind: B1
- Application number: 18/099,133
- Filed: 2023-01-19
- Granted: 2024-02-20
- Earliest claimed: 2023-01-19
- Assignees: Klaviyo, Inc
- Applicants: Klaviyo, Inc
- Inventors: Charles T. Natoli; Devin Patel; Sofiane Hadji; Gal Gila Korcia; Nick Vessella; Robert Huselid; Andrew Piliero; Tristan Mills; Harsh Mehta
- Web page: https://patentgrep.com/patent/US11909699B1

## CPC

- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- H04L 51/063: Content adaptation, e.g. replacement of unsuitable content
- H04L 51/212: using filtering or selective blocking
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- 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

## Abstract

Apparatuses, methods, and systems for generating short messages for electronic messages of electronic marketing messages. One method includes receiving, by a server, information related to the electronic marketing message, receiving, by the server, a plurality of N short messages (text) generated based on the received information from a generative text engine model, reducing, by the server, the plurality of N short messages down to M short messages, displaying messages based on the M short messages to a merchant user, identifying merchant actions in response to the displaying of the messages based on the M short messages, and fine-tuning, by the server, the generative text engine model based on the identified merchant actions.

## Claims

### Claim 1

A computer-implemented method for generating text for short messages for electronic marketing messaging, comprising:
receiving, by a server, information related to the electronic marketing message;
receiving, by the server, a plurality of N short messages generated based on the received information from a generative text engine model;
reducing, by the server, the plurality of N short messages down to M short messages;
displaying messages based on the M short messages to a merchant user;
identifying merchant actions in response to the displaying of the messages based on the M short messages;
fine-tuning, by the server, the generative text engine model based on the identified merchant actions;
displaying at least a portion of the messages based on the M short messages to one or more customers of the merchant user;
identifying customer actions in response to the displaying of the at least the portion of the messages based on the M short messages; and
further fine-tuning, by the server, the generative text engine model based on the sensed customer actions.

### Claim 2 (depends on 1)

The method of claim 1, wherein a filtering discriminator model performs at least a portion of the reducing of the plurality of N short messages down to the M short messages.

### Claim 3 (depends on 2)

The method of claim 2, further comprising fine-tuning, by the server, the filtering discriminator model based on the identified merchant actions.

### Claim 4 (depends on 1)

The method of claim 1, wherein a filtering discriminator model performs at least a portion of the reducing of the N short messages down to the M short messages, and further comprising fine-tuning, by the server, the filtering discriminator model based on the sensed customer actions.

### Claim 5 (depends on 1)

The method of claim 1, wherein identifying merchant actions comprises:
tracking, by the server, actions of the merchant user at the merchant server based on the messages based on the M short messages displayed;
and wherein fine-tuning the generative text engine model comprises:
assigning a quality rating to at least a portion of the messages based on the M short messages; and
supplementing data used to train the generative text engine model with quality ratings of the at least the portion of the messages based on the M short messages.

### Claim 6 (depends on 5)

The method of claim 5, further comprising continuously updating the generative text engine model based on continuously generated quality ratings.

### Claim 7 (depends on 5)

The method of claim 5, wherein tracking the merchant actions comprises sensing selections by the merchant user of one or more of the short messages displayed to the merchant user.

### Claim 8 (depends on 1)

The method of claim 1, wherein tuning the generative text engine model comprises:
assigning a second quality rating for each of the short messages displayed to the one or more customers based on the tracked customer actions; and
supplementing data used to train the generative text engine model with the second quality ratings of the short messages displayed to the one or more customers.

### Claim 9 (depends on 8)

The method of claim 8, wherein tracking the customer actions comprises sensing the customer actions at the customer devices.

### Claim 10 (depends on 9)

The method of claim 9, wherein the sensing the customer actions comprises sensing online action of the one or more customers.

### Claim 11 (depends on 1)

The method of claim 1, further comprising reducing the plurality of N short messages down to M short messages, comprising
generating similarity scores between each of the N short messages and eliminating one or more short messages based on a similarity with one or more other short messages.

### Claim 12 (depends on 11)

The method of claim 11, wherein generating similarity scores between each of the N short messages and eliminating one or more short messages based on a similarity with one or more other short messages comprises prioritizing diversity across displayed short messages based on pairwise similarity scores.

### Claim 13 (depends on 1)

The method of claim 1, further comprising reducing the N short messages down to M short messages, comprising
generating similarity scores between each of the N short messages and the received information and eliminating one or more short messages based on a similarity with the received information.

### Claim 14 (depends on 1)

The method of claim 1, wherein filtering the N short message to eliminate short messages comprises filtering the N short message to eliminate short messages based on content, including eliminating short messages that include inappropriate and politically sensitive words.

### Claim 15 (depends on 1)

The method of claim 1, wherein filtering the N short message to eliminate short messages comprises filtering the N short message to eliminate short messages based on content, including eliminating short messages that include identified prohibited context.

### Claim 16 (depends on 1)

The method of claim 1, further comprising applying a fine-tuned enhancer model to enhance existing content for a selected one or more of the M short messages, wherein enhancing the content includes modifying or updating the existing content to include a branding voice of the merchant user, comprising personalizing the content for the merchant user to include the branding voice of the merchant user as determined by analyzing previous or past samples of short messages of the merchant user.

### Claim 17 (depends on 16)

The method of claim 16, wherein personalizing the content for the merchant user includes personalizing the information related to the electronic marketing message before generating the N short messages, or personalizing content of the generated N short messages.