US 11935082

Summary of US Patent 11935082

• Title: Discovering neighborhood clusters and uses therefor
• Assignee: Carnegie Mellon University
• Inventors: Justin Cranshaw, Raz Schwartz, Jason I. Hong, Norman Sadeh-Koniecpol
• Filing Date: January 10, 2022
• Issue Date: March 19, 2024
• Abstract: The patent describes computer-based systems and methods for identifying neighborhood clusters in a geographic region. These clusters feature a specific mix of venues, determined by analyzing venue check-in data. The mix of venues can be based on social similarity between venues, characteristic neighborhood typologies, temporal check-in patterns, or a combination of these factors. The discovered neighborhood clusters have various potential commercial and civic applications.

Plain-Language Overview of Independent Claims:

US Patent 11935082 includes several independent claims, outlining different embodiments of the invention.

• Claim 1 (System-based on social and geographical similarity): This claim describes a computer system that identifies geographic clusters of venues. It works by:

  1. Storing venue check-in data from many users across multiple venues in a geographic area. This data can come from mobile check-in apps, point-of-sale transactions, venue rating systems, or review systems.
  2. Using one or more processors to create a pairwise venue similarity matrix. This matrix assigns a similarity score to every pair of venues. This score considers both the geographical distance and the social distance between the venues. The social distance is determined by whether common users (or groups of users) visit both venues.
  3. Identifying at least two geographic clusters of venues based on this similarity matrix. Each cluster consists of a mix of one or more venues.

• Claim 9 (Method-based on social and geographical similarity): This claim describes a computer-implemented method for identifying geographic clusters of venues, mirroring the functionality of Claim 1. The method involves:

  1. Storing venue check-in data.
  2. Generating a check-in intensity vector for each venue, indicating how often different users checked into that venue.
  3. Generating a pairwise venue similarity matrix, where each score reflects both geographical and social distance (based on common visitors).
  4. Identifying geographic clusters of venues based on this matrix.

• Claim 17 (System-based on sub-regions): This claim describes a computer system for identifying geographic clusters of sub-regions (e.g., census tracts, school districts) within a larger geographic area. It operates by:

  1. Storing venue check-in data for multiple venues located within these sub-regions.
  2. Using one or more processors to generate a check-in intensity vector for each sub-region. This vector measures how intensely users checked into venues within that sub-region over time.
  3. Generating a pairwise sub-region similarity matrix. Each element in this matrix is a similarity score between a pair of sub-regions, based on the similarity of their check-in intensity vectors.
  4. Identifying at least two geographic clusters of sub-regions using this matrix, where each cluster comprises a mix of one or more sub-regions.

• Claim 20 (Method-based on sub-regions): This claim describes a computer-implemented method for identifying geographic clusters of sub-regions, similar to the system of Claim 17. The steps are:

  1. Storing venue check-in data where venues are in sub-regions.
  2. Generating a check-in intensity vector for each sub-region.
  3. Generating a pairwise sub-region similarity matrix.
  4. Identifying geographic clusters of sub-regions based on this matrix.

CAFC 2026 Docket Search:
A search of CAFC 2026 dockets for the specific patent number 11935082 did not return any direct results in the provided snippets. Therefore, there is no authoritative information from this search indicating any active litigation or status updates for this patent in the U.S. Court of Appeals for the Federal Circuit dockets as of April 26, 2026.