# US 2025/0148512 A1 · Systems and methods for identification of corporate targets based on social media content

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

- Number: US 2025/0148512 A1
- Document ID: US20250148512A1
- Status: Published application
- Kind: A1
- Application number: 18/933,544
- Filed: 2024-10-31
- Published: 2025-05-08
- Earliest claimed: 2023-11-03
- Applicants: Telemetry, LLC
- Inventors: David Freeman Ford; Laura Baldwin Flowerree; Jonathan Chung-Yin Wu; Lauren Ashlee Schwarz
- Web page: https://patentgrep.com/patent/US20250148512A1

## CPC

- G06Q 30/0282: Rating or review of business operators or products
- G06Q 10/40: Business processes related to social networking or social networking services
- G06Q 10/48: using social graphs
- 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

Systems and methods for identifying corporate targets based on social media content are disclosed. Users of a social media platform include individuals and companies. Each user has a user profile. For each individual, processor(s) generate individual data terms from the user profile and identify a current employer. For each company, the processor(s) generate company data terms from the user profile and add the individual data terms of the individuals for which the company is identified as the current employer to the company data terms. For each combination of company and company data term, the processor(s) generate a frequency score. The processor(s) identify seed companies, candidate companies, and data-type(s)-of-interest. For each data-type-of-interest, the processor(s) calculate a respective similarity score for each combination of seed company and candidate company. The processor(s) determine the target companies based on similarity scores of each candidate company.

## Claims

### Claim 1

A system for selecting corporate targets based on social media content, the system comprising:
one or more databases configured to store social media data of users of a social media platform, wherein the users include individuals and companies, and wherein each user has a user profile on the social media platform; and
one or more processors configured to:
for each individual, generate individual data terms from the user profile of the individual and identify a current employer based on the user profile;
for each company:
generate company data terms from the user profile of the company; and
add the individual data terms of the individuals for which the company is identified as the current employer to the company data terms of the company;
for each combination of company and company data term, generate a frequency score for the company that is indicative of how often the company data term is used with respect to the company;
identify one or more seed companies and a pool of candidate companies from the companies on the social media platform;
identify one or more data-types-of-interest for determining one or more target companies from the pool of candidate companies;
for each data-type-of-interest, calculate a respective similarity score for each combination of seed company and candidate company;
determine the one or more target companies based on similarity scores of each candidate company; and
generate and transmit a report for the one or more target companies.

### Claim 2 (depends on 1)

The system of claim 1, wherein the one or more databases are further configured to store each frequency score and each similarity score.

### Claim 3 (depends on 1)

The system of claim 1, wherein each frequency score includes at least one of an n-gram count or a term frequency-inverse document frequency (TF-IDF) score.

### Claim 4 (depends on 1)

The system of claim 1, wherein the one or more processors are configured to identify the pool of candidate companies by determining which of the companies of the social media platform satisfies one or more prerequisites for comparison to the one or more seed companies.

### Claim 5 (depends on 1)

The system of claim 1, wherein, for each combination of company and data type, the one or more processors are configured to generate a ranking of the company data terms based on the respective frequency scores.

### Claim 6 (depends on 5)

The system of claim 5, wherein, to calculate the similarity score for each combination of seed company and candidate company, the one or more processors are configured to only compare a predetermined number of the company data terms that are highest ranked in the ranking of the respective seed company.

### Claim 7 (depends on 1)

The system of claim 1, wherein each similarity score includes at least one of an n-gram overlap score or a cosine similarity score.

### Claim 8 (depends on 1)

The system of claim 1, wherein, to determine the target companies, the one or more processors are configured to:
select a predetermined number of the candidate companies with respective highest similarity scores; or
select each of the candidate companies that have a similarity score greater than a threshold score.

### Claim 9

A method for selecting corporate targets based on social media content, the method comprising:
storing, via one or more databases, social media data of users of a social media platform, wherein the users include individuals and companies, and wherein each user has a user profile on the social media platform;
generating, for each individual via one or more processors, individual data terms from the user profile of the individual and identify a current employer based on the user profile;
generating, for each company via the one or more processors, company data terms from the user profile of the company;
adding, for each company via the one or more processors, the individual data terms of the individuals for which the company is identified as the current employer to the company data terms of the company;
generating, for each combination of company and company data term via the one or more processors, a frequency score for the company that is indicative of how often the company data term is used with respect to the company;
identifying, via the one or more processors, one or more seed companies and a pool of candidate companies from the companies on the social media platform;
identifying, via the one or more processors, one or more data-types-of-interest for determining one or more target companies from the pool of candidate companies;
calculating, for each data-type-of-interest via the one or more processors, a respective similarity score for each combination of seed company and candidate company;
determining, via the one or more processors, the one or more target companies based on similarity scores of each candidate company; and
generating and transmitting, via the one or more processors, a report for the one or more target companies.

### Claim 10 (depends on 9)

The method of claim 9, wherein each frequency score includes at least one of an n-gram count or a term frequency-inverse document frequency (TF-IDF) score.

### Claim 11 (depends on 9)

The method of claim 9, further comprising generating a ranking of the company data terms based on the respective frequency scores for each combination of company and data type, and wherein calculating the similarity score for each combination of seed company and candidate company includes only comparing a predetermined number of the company data terms that are highest ranked in the ranking of the respective seed company.

### Claim 12 (depends on 9)

The method of claim 9, wherein each similarity score includes at least one of an n-gram overlap score or a cosine similarity score.

### Claim 13 (depends on 9)

The method of claim 9, wherein determining the target companies includes:
selecting a predetermined number of the candidate companies with respective highest similarity scores; or
selecting each of the candidate companies that have a similarity score greater than a threshold score.

### Claim 14

A computer readable medium comprising instructions, which, when executed, cause a machine to:
store social media data of users of a social media platform, wherein the users include individuals and companies, and wherein each user has a user profile on the social media platform;
generate, for each individual, individual data terms from the user profile of the individual and identify a current employer based on the user profile;
generate, for each company, company data terms from the user profile of the company;
add, for each company, the individual data terms of the individuals for which the company is identified as the current employer to the company data terms of the company;
generate, for each combination of company and company data term, a frequency score for the company that is indicative of how often the company data term is used with respect to the company;
identify one or more seed companies and a pool of candidate companies from the companies on the social media platform;
identify one or more data-types-of-interest for determining one or more target companies from the pool of candidate companies;
calculate, for each data-type-of-interest, a respective similarity score for each combination of seed company and candidate company;
determine the one or more target companies based on similarity scores of each candidate company; and
generate and transmit a report for the one or more target companies.

### Claim 15 (depends on 14)

The computer readable medium of claim 14, wherein each frequency score includes at least one of an n-gram count or a term frequency-inverse document frequency (TF-IDF) score.

### Claim 16 (depends on 14)

The computer readable medium of claim 14, wherein, to identify the pool of candidate companies, the instructions, when executed, cause the machine to determine which of the companies of the social media platform satisfies one or more prerequisites for comparison to the one or more seed companies.

### Claim 17 (depends on 14)

The computer readable medium of claim 14, wherein, the instructions, when executed, further cause the machine to generate, for each combination of company and data type, a ranking of the company data terms based on the respective frequency scores.

### Claim 18 (depends on 17)

The computer readable medium of claim 17, wherein, to calculate the similarity score for each combination of seed company and candidate company, the instructions, when executed, cause the machine to only compare a predetermined number of the company data terms that are highest ranked in the ranking of the respective seed company.

### Claim 19 (depends on 14)

The computer readable medium of claim 14, wherein each similarity score includes at least one of an n-gram overlap score or a cosine similarity score.

### Claim 20 (depends on 14)

The computer readable medium of claim 14, wherein, to determine the target companies, the instructions, when executed, cause the machine to:
select a predetermined number of the candidate companies with respective highest similarity scores; or
select each of the candidate companies that have a similarity score greater than a threshold score.
