# US 2025/0232118 A1 · System for machine-learning based identification and filtering of electronic network communication

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

- Number: US 2025/0232118 A1
- Document ID: US20250232118A1
- Status: Published application
- Kind: A1
- Application number: 19/095,104
- Filed: 2025-03-31
- Published: 2025-07-17
- Earliest claimed: 2022-04-18
- Assignees: Bank of America Corporation
- Applicants: Bank of America Corporation
- Inventors: George Anthony Albero; Maharaj Mukherjee; Elijah Clark; Madhavi Mendu; Michael B. Jones, JR.; Michael Ogrinz
- Web page: https://patentgrep.com/patent/US20250232118A1

## CPC

- G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking
- G06F 40/30: Semantic analysis
- G06F 16/325: {Hash tables}
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system is provided for machine-learning based identification and filtering of electronic network communication. In particular, the system may continuously monitor and pull electronic communications data from one or more networked computing systems in an enterprise environment. Based on the electronic communications data, the system may use machine learning algorithms to generate a database of associations between one or more users and one or more topics of interest. The system may then output one or more recommendations to one or more users for transmitting communications associated with the one or more topics of interest. In this way, the system may improve the efficiency of communications received and transmitted within a network.

## Claims

### Claim 1

A system for machine-learning based identification and filtering of electronic network communication, the system comprising:
a memory device with computer-readable program code stored thereon;
a communication device; and
a processing device operatively coupled to the memory device and the communication device, wherein the processing device is configured to execute the computer-readable program code to:
continuously track electronic communications data within a network environment;
generate, using a machine learning process, one or more concept identifiers from the electronic communications data;
generate one or more links between one or more users and the one or more concept identifiers, wherein the one or more links comprise network security and programming languages;
detect interaction levels between the one or more users and the one or more concept identifiers using a natural language processing algorithm;
store the one or more links within an associations database;
based on the associations database, generate one or more recommended recipients for a first instance of electronic communication;
present the one or more recommended recipients to a user on a user computing device;
detect that the user has deselected at least one recipient from the one or more recommended recipients;
based on detecting that the user has deselected the at least one recipient, refine a machine learning algorithm associated with the machine learning process; and
execute, using the machine learning algorithm, a filtering of the electronic communications on behalf of the at least one recipient, wherein the filtering comprises automatically unsubscribing from other electronic communications and blocking the electronic communications.

### Claim 2 (depends on 1)

The system according to claim 1, wherein generating the one or more concept identifiers comprises:
analyzing and parsing the electronic communications data using the natural language processing algorithm;
identify one or more key words or key phrases from the electronic communications data; and
associating each of the one or more key words or key phrases with the one or more concept identifiers.

### Claim 3 (depends on 2)

The system according to claim 2, wherein the one or more concept identifiers are stored as hash values.

### Claim 4 (depends on 1)

The system according to claim 1, wherein generating the one or more links between the one or more users comprises computing a weight value for each of the one or more links, wherein computing the weight value is based on historical user activity associated with the one or more users and an identity or role of the one or more users.

### Claim 5 (depends on 4)

The system according to claim 4, wherein the historical user activity comprises previous electronic communications sent or received by the one or more users and browsing history of the one or more users.

### Claim 6 (depends on 1)

The system according to claim 1, wherein generating the one or more recommended recipients comprises:
analyzing the first instance of electronic communication using the natural language processing algorithm;
detecting that a content of the electronic communication is associated with the one or more concept identifiers; and
detecting that a weight value associated with the one or more links exceeds a predetermined threshold.

### Claim 7 (depends on 1)

The system according to claim 1, wherein generating the one or more recommended recipients comprises automatically populating a recipient field within a user application on a user computing system associated with the first instance of electronic communication.

### Claim 8

A computer program product for machine-learning based identification and filtering of electronic network communication, the computer program product comprising at least one non-transitory computer readable medium having computer-readable program code portions embodied therein, the computer-readable program code portions comprising executable portions for:
continuously tracking electronic communications data within a network environment;
generating, using a machine learning process, one or more concept identifiers from the electronic communications data;
generating one or more links between one or more users and the one or more concept identifiers, wherein the one or more links comprise network security and programming languages;
detecting interaction levels between the one or more users and the one or more concept identifiers using a natural language processing algorithm;
storing the one or more links within an associations database;
based on the associations database, generating one or more recommended recipients for a first instance of electronic communication;
presenting the one or more recommended recipients to a user on a user computing device;
detecting that the user has deselected at least one recipient from the one or more recommended recipients;
based on detecting that the user has deselected the at least one recipient, refining a machine learning algorithm associated with the machine learning process; and
executing, using the machine learning algorithm, a filtering of the electronic communications on behalf of the at least one recipient, wherein the filtering comprises automatically unsubscribing from other electronic communications and blocking the electronic communications.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein generating the one or more concept identifiers comprises:
analyzing and parsing the electronic communications data using the natural language processing algorithm;
identify one or more key words or key phrases from the electronic communications data; and
associating each of the one or more key words or key phrases with the one or more concept identifiers.

### Claim 10 (depends on 9)

The computer program product of claim 9, wherein the one or more concept identifiers are stored as hash values.

### Claim 11 (depends on 8)

The computer program product of claim 8, wherein generating the one or more links between the one or more users comprises computing a weight value for each of the one or more links, wherein computing the weight value is based on historical user activity associated with the one or more users and an identity or role of the one or more users.

### Claim 12 (depends on 11)

The computer program product of claim 11, wherein the historical user activity comprises previous electronic communications sent or received by the one or more users and browsing history of the one or more users.

### Claim 13 (depends on 8)

The computer program product of claim 8, wherein generating the one or more recommended recipients comprises:
analyzing the first instance of electronic communication using the natural language processing algorithm;
detecting that a content of the electronic communication is associated with the one or more concept identifiers; and
detecting that a weight value associated with the one or more links exceeds a predetermined threshold.

### Claim 14

A computer-implemented method for machine-learning based identification and filtering of electronic network communication, the computer-implemented method comprising:
continuously tracking electronic communications data within a network environment;
generating, using a machine learning process, one or more concept identifiers from the electronic communications data;
generating one or more links between one or more users and the one or more concept identifiers, wherein the one or more links comprise network security and programming languages;
detecting interaction levels between the one or more users and the one or more concept identifiers using a natural language processing algorithm;
storing the one or more links within an associations database;
based on the associations database, generating one or more recommended recipients for a first instance of electronic communication;
presenting the one or more recommended recipients to a user on a user computing device;
detecting that the user has deselected at least one recipient from the one or more recommended recipients;
based on detecting that the user has deselected the at least one recipient, refining a machine learning algorithm associated with the machine learning process; and
executing, using the machine learning algorithm, a filtering of the electronic communications on behalf of the at least one recipient, wherein the filtering comprises automatically unsubscribing from other electronic communications and blocking the electronic communications.

### Claim 15 (depends on 14)

The computer-implemented method of claim 14, wherein generating the one or more concept identifiers comprises:
analyzing and parsing the electronic communications data using the natural language processing algorithm;
identify one or more key words or key phrases from the electronic communications data; and
associating each of the one or more key words or key phrases with the one or more concept identifiers.

### Claim 16 (depends on 15)

The computer-implemented method of claim 15, wherein the one or more concept identifiers are stored as hash values.

### Claim 17 (depends on 14)

The computer-implemented method of claim 14, wherein generating the one or more links between the one or more users comprises computing a weight value for each of the one or more links, wherein computing the weight value is based on historical user activity associated with the one or more users and an identity or role of the one or more users.

### Claim 18 (depends on 17)

The computer-implemented method of claim 17, wherein the historical user activity comprises previous electronic communications sent or received by the one or more users and browsing history of the one or more users.

### Claim 19 (depends on 14)

The computer-implemented method of claim 14, wherein generating the one or more recommended recipients comprises:
analyzing the first instance of electronic communication using the natural language processing algorithm;
detecting that a content of the electronic communication is associated with the one or more concept identifiers; and
detecting that a weight value associated with the one or more links exceeds a predetermined threshold.

### Claim 20 (depends on 14)

The computer-implemented method of claim 14, wherein generating the one or more recommended recipients comprises automatically populating a recipient field within a user application on a user computing system associated with the first instance of electronic communication.
