# US 2026/0073121 A1 · Systems and methods for automated messaging management

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

- Number: US 2026/0073121 A1
- Document ID: US20260073121A1
- Status: Published application
- Kind: A1
- Application number: 18/826,271
- Filed: 2024-09-06
- Published: 2026-03-12
- Earliest claimed: 2024-09-06
- Assignees: Yahoo Assets LLC
- Applicants: Yahoo Assets LLC
- Inventors: Sanika SHIRWADKAR; Rofaida ABDELAAL; Vignesh GANAPATHIRAMAN; Bhopal SINGH; Kenneth SEBASTIAN
- Web page: https://patentgrep.com/patent/US20260073121A1

## CPC

- G06F 40/166: Editing, e.g. inserting or deleting
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- H04L 51/42: Mailbox-related aspects, e.g. synchronisation of mailboxes
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Disclosed are systems and methods that provide a decision-intelligence (DI)-based, computerized framework for determining and implementing the mechanisms for compiling and/or displaying a summary of an electronic message within an inbox. The disclosed framework provides novel mechanisms for triaging messaging, in that mechanism for how they are pre-, post- and/or in real-time processed by the server, sender and/or recipient devices pursuant to providing summarizations for an improved user consumption experience. The framework operates to determine which messages are candidates for specific forms of triaging, then queues such messages for summarization according to the mechanism for which it will be delivered. Such determination and summarization can effectuate an improved messaging experience as it relates to how messages are handled by inboxes and/or displayed for interaction by recipient users.

## Claims

### Claim 1

A method comprising:
identifying, by an application, an electronic message addressed to an inbox of a recipient;
analyzing, by the application executing a messaging triaging model, the electronic message; and
determining, by the application, based on the analysis, whether the electronic message is a triaging candidate, the determination further comprising:
causing delivery of the electronic message to the inbox according to a delivery protocol defined by a message platform hosting the inbox when the application determines the electronic message is not a candidate for triaging, and
causing delivery of at least an email summary of the electronic message to the inbox when the application determines the electronic message is a candidate for triaging.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
calling, upon identifying of the electronic message, the message triaging model.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
sampling data from a set of electronic messages;
sampling data from a set of inboxes;
analyzing the sampled data from the set of electronic messages and the sampled data from the set of inboxes; and
performing fine-tuning of the message triaging model based on the analysis of the sampled data.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
extracting message information from the electronic message; and
performing model-fine tuning of the message triaging model based on the electronic message and information related to the triaging determination.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
calling and executing a summarization LLM model, such that the electronic message is input to the summarization LLM model; and
generating the email summary.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
performing the delivery of the email summary by sending a message inbox item with the summary as part of an inbox for display within the inbox.

### Claim 7 (depends on 1)

The method of claim 1, wherein the message triaging model performs the analysis of the electronic message based on information selected from: sender identifier (ID), sender domain, content, category of content, type of content, number of recipients, recipient ID, message type, message format, a time, date and a location.

### Claim 8 (depends on 1)

The method of claim 1, further comprising the application executing on a device of the recipient.

### Claim 9 (depends on 1)

The method of claim 1, further comprising the application executing on a cloud.

### Claim 10 (depends on 1)

The method of claim 1, further comprising the application being associated with a mail platform.

### Claim 11

A system comprising:
a processor configured to:
identify, by an application, an electronic message addressed to an inbox of a recipient;
analyze, by the application executing a messaging triaging model, the electronic message; and
determine, by the application, based on the analysis, whether the electronic message is a triaging candidate, the determination further comprising:
cause delivery of the electronic message to the inbox according to a delivery protocol defined by a message platform hosting the inbox when the application determines the electronic message is not a candidate for triaging, and
cause delivery of at least an email summary of the electronic message to the inbox when the application determines the electronic message is a candidate for triaging.

### Claim 12 (depends on 11)

The system of claim 11, such that the processor is further configured to:
call, upon identifying of the electronic message, the message triaging model.

### Claim 13 (depends on 11)

The system of claim 11, such that the processor is further configured to:
sample data from a set of electronic messages;
sample data from a set of inboxes;
analyze the sampled data from the set of electronic messages and the sampled data from the set of inboxes; and
perform fine-tuning of the message triaging model based on the analysis of the sampled data.

### Claim 14 (depends on 11)

The system of claim 11, such that the processor is further configured to:
extract message information from the electronic message; and
perform model-fine tuning of the message triaging model based on the electronic message and information related to the triaging determination.

### Claim 15 (depends on 11)

The system of claim 11, such that the processor is further configured to:
call and execute a summarization LLM model, such that the electronic message is input to the summarization LLM model;
generate the email summary; and
perform the delivery of the email summary by sending a message inbox item with the summary as part of an inbox for display within the inbox.

### Claim 16

A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions that when executed by a device, perform a method comprising:
identifying, by an application, an electronic message addressed to an inbox of a recipient;
analyzing, by the application executing a messaging triaging model, the electronic message; and
determining, by the application, based on the analysis, whether the electronic message is a triaging candidate, the determination further comprising:
causing delivery of the electronic message to the inbox according to a delivery protocol defined by a message platform hosting the inbox when the application determines the electronic message is not a candidate for triaging, and
causing delivery of at least an email summary of the electronic message to the inbox when the application determines the electronic message is a candidate for triaging.

### Claim 17 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, further comprising:
calling, upon identifying of the electronic message, the message triaging model.

### Claim 18 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, further comprising:
sampling data from a set of electronic messages;
sampling data from a set of inboxes;
analyzing the sampled data from the set of electronic messages and the sampled data from the set of inboxes; and
performing fine-tuning of the message triaging model based on the analysis of the sampled data.

### Claim 19 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, further comprising:
extracting message information from the electronic message; and
performing model-fine tuning of the message triaging model based on the electronic message and information related to the triaging determination.

### Claim 20 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, further comprising:
calling and executing a summarization LLM model, such that the electronic message is input to the summarization LLM model;
generating the email summary; and
performing the delivery of the email summary by sending a message inbox item with the summary as part of an inbox for display within the inbox.
