# US 2026/0094124 A1 · Generative Model for Generating Personalized Newsletters for a Publisher

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

- Number: US 2026/0094124 A1
- Document ID: US20260094124A1
- Status: Published application
- Kind: A1
- Application number: 18/900,058
- Filed: 2024-09-27
- Published: 2026-04-02
- Earliest claimed: 2024-09-27
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Justin Lewis Kosslyn; Mathias Jean René Sallé; Idan Avraham; Ziv Hodak
- Web page: https://patentgrep.com/patent/US20260094124A1

## CPC

- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- G06F 16/337: {Profile generation, learning or modification}
- G06F 16/345: {Summarisation for human users}
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems and methods for generating a personalized newsletter. The system can include a database storing a plurality of content items and a machine-learned model that is configured to generate the personalized newsletter. The system can process a plurality of content items of a publisher to generate an attribute for each content item in the plurality of content items. Additionally, the system can select, based on the attribute for each content item in the plurality of content items, a subset of content items from the plurality of content items. Moreover, the system can process the subset of content items, using the machine-learned model, to generate a summary. Furthermore, the system can generate a newsletter based on the summary and the subset of content items.

## Claims

### Claim 1

A computing system for generating a newsletter, comprising:
one or more processors; and
one or more non-transitory computer-readable media that collectively store:
a database storing a plurality of content items, the plurality of content items being associated a publisher; and
a machine-learned model, wherein the machine-learned model is configured to generate the newsletter; and
instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
processing the plurality of content items to generate an attribute for each content item in the plurality of content items;
selecting, based on the attribute for each content item in the plurality of content items, a subset of content items from the plurality of content items;
processing the subset of content items, using the machine-learned model, to generate a summary; and
generating a newsletter based on the summary and the subset of content items.

### Claim 2 (depends on 1)

The computing system of claim 1, the operations comprising:
obtaining user data associated with a first user;
selecting the subset of content items from the plurality of content items based on the user data;
processing the subset of content items and the user data, using the machine-learned model, to generate the summary; and
generating the newsletter using the summary, the subset of content items, and the user data; and
transmitting the newsletter to an email account associated with the first user.

### Claim 3 (depends on 1)

The computing system of claim 1, wherein the newsletter is transmitted at a first time interval, and wherein the first time interval is based on user data.

### Claim 4 (depends on 1)

The computing system of claim 1, wherein the plurality of content items are processed by the machine-learned model to generate a plurality of attributes for each content item in the plurality of content items.

### Claim 5 (depends on 4)

The computing system of claim 4, wherein the selecting of the subset of content items from the plurality of content items further comprises:
determining a relevance score for each content item in the plurality of content items based on the plurality of attributes for each content item in the plurality of content items;
ranking each content item in the plurality of content items based on the relevance score for each content item, and
wherein the subset of content items are selected based on the ranking of each content item.

### Claim 6 (depends on 1)

The computing system of claim 1, the operations further comprising:
obtaining weather data associated with a location of a specific user;
processing, using the machine-learned model, the weather data and the subset of content items to generate the summary, and
wherein the newsletter is personalized for the specific user.

### Claim 7 (depends on 1)

The computing system of claim 1, the operations further comprising:
determining trend data based on interest of similar users; and
processing, using the machine-learned model, the trend data, the summary, and the subset of content items to generate the newsletter.

### Claim 8 (depends on 1)

The computing system of claim 1, the operations further comprising:
determine a voice of the publisher, the voice of the publisher having a specific tone; and
processing, using the machine-learned model, the voice of the publisher, the summary, and the subset of content items to generate the newsletter.

### Claim 9 (depends on 1)

The computing system of claim 1, wherein the attribute is a relevance score for a specific topic.

### Claim 10 (depends on 1)

The computing system of claim 1, wherein the attribute is a relevance score for a specific group of users.

### Claim 11 (depends on 1)

The computing system of claim 1, wherein the attribute is associated with a topic.

### Claim 12 (depends on 1)

The computing system of claim 1, wherein the attribute is associated with a publication date.

### Claim 13 (depends on 1)

The computing system of claim 1, wherein the database further includes a plurality of newsletter templates, the operations comprising:
selecting, based on the subset of content items, a first template from the plurality of newsletter template, and
wherein the newsletter is generated using the selected template.

### Claim 14 (depends on 1)

The computing system of claim 1, the operations comprising:
obtaining group data associated with a first group of users;
selecting the subset of content items from the plurality of content items based on the group data;
determining a first template for the newsletter based on the group data; and
generating the newsletter for the first group of users using the first template.

### Claim 15 (depends on 1)

The computing system of claim 1, wherein the first template has a content plan that is determined based on the group data, and wherein the first template has a content structure that is determined based on the group data.

### Claim 16 (depends on 1)

The computing system of claim 1, the operations further comprising:
fetching a first content item from a server of the publisher;
determining that the first content item is a non-sponsored content item; and
storing the first content item in the database to be included in the plurality of content items.

### Claim 17 (depends on 1)

The computing system of claim 1, the operations further comprising:
receiving user input associated a selected content item in the newsletter; and
updating, a parameter of the machine-learned model, based on the user input.

### Claim 18 (depends on 17)

The computing system of claim 17, the operations further comprising:
generating an updated newsletter, wherein the updated newsletter is generated based on the user input associated with the selected content item.

### Claim 19

A computer-implemented method, comprising:
obtaining, by a computing system comprising one or more processors, a plurality of content items, the plurality of content items being associated with a publisher;
processing the plurality of content items to generate an attribute for each content item in the plurality of content items;
selecting, based on the attribute for each content item in the plurality of content items, a subset of content items from the plurality of content items;
processing the subset of content items, using the machine-learned model, to generate a summary; and
generating a newsletter based on the summary and the subset of content items.

### Claim 20

One or more non-transitory computer-readable media that collectively store instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations, the operations comprising:
obtaining, a plurality of content items, the plurality of content items being associated with a publisher;
processing the plurality of content items to generate an attribute for each content item in the plurality of content items;
selecting, based on the attribute for each content item in the plurality of content items, a subset of content items from the plurality of content items;
processing the subset of content items, using the machine-learned model, to generate a summary; and
generating a newsletter based on the summary and the subset of content items.
