# US 2023/0267156 A1 · Extraction of relevant content from communication networks

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

- Number: US 2023/0267156 A1
- Document ID: US20230267156A1
- Status: Published application
- Kind: A1
- Application number: 17/680,151
- Filed: 2022-02-24
- Published: 2023-08-24
- Earliest claimed: 2022-02-24
- Assignees: Prove Identity, Inc.
- Applicants: Prove Identity, Inc.
- Inventors: Amit Goel; Tarun Bansal; Aditya Khurjekar; Nicolo Petrone; Mehul Desai
- Web page: https://patentgrep.com/patent/US20230267156A1

## CPC

- G06F 16/951: Indexing; Web crawling techniques
- G06F 16/9532: Query formulation
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/9538: Presentation of query results
- G06F 40/205: Parsing
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Briefly, example methods, apparatuses, and/or articles of manufacture may be implemented to receive or obtain, responsive to transmitting the one or more search terms to a search entity, one or more primary content items that include messages that accord with the one or more search terms. The method may additionally include parsing the messages that accord with the one or more search terms to detect one or more relevant secondary search terms and obtaining secondary content items that accord with the one or more relevant secondary search terms. The method may further include generating signals to represent a report of entities that accord with the one or more relevant secondary search terms.

## Claims

### Claim 1

A method comprising:
obtaining, via a user interface, one or more search terms;
receiving, responsive to transmitting the one or more search terms to a search entity, one or more primary content items that include a plurality of messages that accord with the one or more search terms;
parsing the plurality of messages that accord with the one or more search terms to detect one or more relevant secondary search terms;
obtaining secondary content items that accord with the one or more relevant secondary search terms; and
generating signals to represent a report of entities that accord with the one or more relevant secondary search terms.

### Claim 2 (depends on 1)

The method of claim 1, wherein the one or more primary content items correspond to character-limited content items from a character-limited publishing application.

### Claim 3 (depends on 2)

The method of claim 2, wherein the character-limited content items comprise content items limited to messages, of the plurality of messages, which contain between 100 characters and 400 characters.

### Claim 4 (depends on 2)

The method of claim 2, wherein the one or more relevant secondary search terms relate to terms extracted from the messages that contain the between the 100 characters and the 400 characters.

### Claim 5 (depends on 2)

The method of claim 2, wherein obtaining the secondary content items is responsive to receiving output signals from a web crawler that operates to detect content items available via the Internet.

### Claim 6 (depends on 2)

The method of claim 2, wherein the one or more secondary terms correspond to contextual elements of at least one of the plurality of parsed messages from the character-limited publishing application.

### Claim 7 (depends on 1)

The method of claim 1, wherein the secondary content items are obtained from a real-simple-syndication feed or a news feed.

### Claim 8 (depends on 1)

The method of claim 1, further comprising normalizing one or more quantities relating to the one or more secondary terms and/or relating to the one or more search terms.

### Claim 9

An apparatus comprising:
a computing platform comprising a processor coupled to at least one memory device to:
obtain, via a user interface, one or more search terms;
receive, responsive to transmitting the one or more search terms to a search entity, one or more primary content items that include a plurality of messages that accord with the one or more search terms;
parse the plurality of messages that accord with the one or more search terms to detect one or more relevant secondary search terms;
obtain secondary content items that accord with the one or more relevant secondary search terms; and
generate signals to represent a report of entities that accord with the one or more relevant secondary search terms.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein the one or more primary content items correspond to character-limited content items from a character-limited publishing application.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein the character-limited content items comprise content items limited to messages, of the plurality of messages, which contain between 100 characters and 400 characters.

### Claim 12 (depends on 10)

The apparatus of claim 10, wherein the one or more relevant secondary search terms relate to terms extracted from the messages that contain the between the 100 characters and the 400 characters.

### Claim 13 (depends on 10)

The apparatus of claim 10, wherein obtaining the secondary content items is responsive to receiving output signals from a web crawler that operates to detect content items available via the Internet.

### Claim 14 (depends on 10)

The apparatus of claim 10, wherein the one or more secondary terms correspond to contextual elements of at least one of the plurality of parsed messages from the character-limited publishing application.

### Claim 15 (depends on 9)

The apparatus of claim 9, wherein the secondary content items are obtained from a real-simple-syndication feed or a news feed.

### Claim 16 (depends on 9)

The apparatus of claim 9, further comprising normalizing one or more quantities relating to the one or more secondary terms and/or relating to the one or more search terms.

### Claim 17

An article comprising:
a non-transitory storage medium having instructions stored thereon executable by a special-purpose computing platform to:
obtain, via a user interface, one or more search terms;
receive, responsive to transmitting the one or more search terms to a search entity, one or more primary content items that include a plurality of messages that accord with the one or more search terms;
parse the plurality of messages that accord with the one or more search terms to detect one or more relevant secondary search terms;
obtain secondary content items that accord with the one or more relevant secondary search terms; and
generate signals to represent a report of entities that accord with the one or more relevant secondary search terms.

### Claim 18 (depends on 17)

The article of claim 17, wherein obtaining the secondary content items is responsive to receiving output signals from a web crawler that operates to detect content items available via the Internet.

### Claim 19 (depends on 17)

The article of claim 17, wherein the secondary content items are obtained from a real-simple-syndication feed or a news feed.

### Claim 20 (depends on 17)

The article of claim 17, wherein the one or more secondary terms correspond to contextual elements of at least one of the plurality of parsed messages from a character-limited publishing application.
