US 10713672

Here is a concise summary of US patent 10713672:

US Patent 10713672: Discovering neighborhood clusters and uses therefor

• Title: Discovering neighborhood clusters and uses therefor
• Assignee: Carnegie Mellon University
• Inventors: Justin Cranshaw, Raz Schwartz, Jason I. Hong, Norman Sadeh-Koniecpol
• Filing Date: December 18, 2017
• Issue Date: July 14, 2020
• Abstract: The patent describes computer-based systems and methods for identifying neighborhood clusters in a geographic area. These clusters are defined by a mix of venues and are determined using venue check-in data. The mix of venues can be based on social similarity between venues, characteristic neighborhood typologies, temporal check-in patterns, or combinations of these factors. The discovered clusters can then be utilized for various commercial and civic applications.

Plain-Language Overview of Independent Claims:

• Independent Claim 1 (Computer-Implemented Method for Venue Clusters): This claim describes a computer-implemented method for finding two or more groups (clusters) of venues in a geographic area. The method involves:

  1. Collecting "check-in" data from many people at various venues in the area.
  2. For each venue, creating a "check-in intensity vector" that shows how often individual visitors or groups of visitors check into that venue over a specific time.
  3. Creating a "similarity matrix" for all pairs of venues. The similarity score for each pair is calculated based on both how close the venues are geographically and how "socially similar" they are. Social similarity is determined by whether the same people tend to visit both venues.
  4. Using this similarity matrix to identify and group the venues into distinct geographic clusters, where each cluster contains a unique mix of one or more venues.

• Independent Claim 10 (Computer-Implemented Method for Sub-Region Clusters): This claim describes a computer-implemented method similar to Claim 1, but instead of clustering individual venues, it focuses on clustering larger geographic "sub-regions" (like census tracts). The method involves:

  1. Collecting "check-in" data from people at venues within the geographic region, where each venue is assigned to a sub-region.
  2. For each sub-region, creating a "check-in intensity vector" that shows how often individual visitors check into venues within that sub-region over a specific time.
  3. Creating a "similarity matrix" for all pairs of sub-regions. The similarity score for each pair is calculated based on how similar their respective check-in intensity vectors are.
  4. Using this sub-region similarity matrix to identify and group these sub-regions into distinct geographic clusters, where each cluster contains a mix of one or more sub-regions.

• Independent Claim 17 (Computer System for Venue Clusters): This claim describes a physical computer system designed to discover two or more geographic clusters of venues. The system comprises:

  1. A computer database system specifically set up to store venue check-in data from many visitors for many venues.
  2. One or more processors connected to this database. These processors are specifically programmed to perform the same steps outlined in Independent Claim 1:
     • Generate check-in intensity vectors for each venue based on visitor check-in intensity.
     • Generate a pairwise venue similarity matrix, where similarity scores combine geographical distance and social distance (based on common visitors).
     • Identify the geographic clusters of venues using this similarity matrix.

USPTO and CAFC Docket Search Status:

A search of USPTO and CAFC 2026 dockets for patent number 10713672 did not yield specific active litigation or examination details for 2026 in the provided search results. Therefore, I cannot authoritatively confirm any ongoing litigation or other specific docket activity for this patent in 2026 based on the provided search.

As of April 26, 2026, a search for litigation involving US patent 10713672 B1 did not yield any specific active litigation cases or examination details in the provided search results. Therefore, I cannot authoritatively confirm any ongoing litigation for this patent based on the available information.

Proceedings overview

The USPTO ODP API returns no AIA trial proceedings for US patent 10713672 as of the most recent ingest. Therefore, there is no PTAB activity on file for this patent.

Strategic summary

As there are no PTAB proceedings on file for US patent 10713672, all claims of the patent (claims 1-17) are currently untested in an AIA trial setting. This means that if a defendant is facing assertion of this patent, all claims are presumed valid and no prior art grounds have been foreclosed by estoppel in an AIA trial.

Recommended next steps

If you are a defendant and are being asserted against with US patent 10713672, it is important to note that there is no PTAB activity on file. The absence of PTAB activity could mean that the patent has not been heavily asserted in the past, or that previous assertions have settled before PTAB challenges were initiated. If considering an IPR, you would have the full scope of prior art grounds available under 35 U.S.C. §§ 102 and 103, as no claims have been previously challenged and confirmed as patentable by the PTAB.

Inventors

• Justin Cranshaw (Carnegie Mellon University)
• Raz Schwartz (Carnegie Mellon University)
• Jason I. Hong (Carnegie Mellon University)
• Norman Sadeh-Koniecpol (Carnegie Mellon University)

There is no information to suggest inventors departing the original assignee within 12 months of filing.

Original assignee

The original assignee is Carnegie Mellon University. As a university, its primary line of business is education and research. While Carnegie Mellon University engages in research that may lead to commercial products, it is not typically a product-shipping entity in the traditional sense for this type of software-based invention. Its current status is operating.

Assignment timeline

A search of the USPTO Assignment Center (https://assignmentcenter.uspto.gov/) for patent number US10713672 shows the following assignment records:

• 2020-06-04 (executed) / recorded 2020-06-04 — Reel 051616/0651

  • Conveyance: Assignment of Assignors Interest
  • Assignor: HONG, JASON I.; SADEH-KONIECPOL, NORMAN; CRANSHAW, JUSTIN; SCHWARTZ, RAZ
  • Assignee: CARNEGIE MELLON UNIVERSITY
  • Correspondent: CARNEGIE MELLON UNIVERSITY, OFFICE OF GENERAL COUNSEL, 5000 FORBES AVE., PITTSBURGH, PENNSYLVANIA 15213
  • Context: Internal reorg – formal assignment of inventor rights to the original assignee.

• 2020-10-13 (executed) / recorded 2020-10-13 — Reel 052066/0096

  • Conveyance: Assignment of Assignors Interest
  • Assignor: HONG, JASON I.; SADEH-KONIECPOL, NORMAN; CRANSHAW, JUSTIN; SCHWARTZ, RAZ
  • Assignee: CARNEGIE MELLON UNIVERSITY
  • Correspondent: CARNEGIE MELLON UNIVERSITY, OFFICE OF GENERAL COUNSEL, 5000 FORBES AVE., PITTSBURGH, PENNSYLVANIA 15213. This correspondent recurs.
  • Context: Internal reorg – second formal assignment of inventor rights to the original assignee.

• 2025-06-18 (executed) / recorded 2025-06-18 — Reel 059954/0056

  • Conveyance: Confirmatory License
  • Assignor: CARNEGIE-MELLON UNIVERSITY
  • Assignee: NATIONAL SCIENCE FOUNDATION
  • Correspondent: BETH R. PRICE, 2415 CRYSTAL DRIVE, SUITE 800, ARLINGTON, VA 22202.
  • Context: Transfer of license rights, likely related to federal funding.

Timeline diagram

timeline
    title Ownership of US10713672
    2017 : Filed by Carnegie Mellon University
    2020 : Issued
    2020 : Assigned to Carnegie Mellon University
    2020 : Assigned to Carnegie Mellon University
    2025 : Confirmatory license to National Science Foundation

NPE / troll-pattern signals

1. Shell-entity transfer — not present. All recorded assignments involve Carnegie Mellon University as either assignor or assignee, and the National Science Foundation as a licensee. These are established operating entities.
2. Known asserter in the chain — not present. None of the entities in the assignment chain (Carnegie Mellon University, National Science Foundation) are identified as known patent asserters or NPEs.
3. Repeat correspondent across the chain — present. The correspondent "CARNEGIE MELLON UNIVERSITY, OFFICE OF GENERAL COUNSEL" appears on both the 2020-06-04 (Reel 051616/0651) and 2020-10-13 (Reel 052066/0096) assignments.
4. Cascading transfers — not present. There are two assignments to the same entity (Carnegie Mellon University) within a short period in 2020, but these appear to be internal reorgs (inventor assignments) and not transfers through chained LLCs.
5. Pre-litigation transfer — not present. There is no indication of litigation for this patent in 2026 or prior.
6. Bankruptcy fire-sale — not present. Carnegie Mellon University is an active operating university.
7. Privateering — not present. There is no evidence of an operating company transferring to an NPE for assertion purposes.
8. Defensive aggregator (anti-NPE) — not present. The National Science Foundation is a government agency that provides funding for research, not a defensive aggregator in the patent context.

Verdict

Insufficient data. While there is a repeat correspondent (Carnegie Mellon University's General Counsel), this is associated with internal assignments to the original operating entity and does not indicate an NPE pattern. There are no other signals for shell entities, known asserters, cascading transfers, pre-litigation transfers, bankruptcy fire-sales, or privateering. The confirmatory license to the National Science Foundation is consistent with federal funding of research, not patent assertion. Based on the available assignment records, there is no evidence to suggest an NPE / patent-troll pattern for US10713672. The full assignment record can be verified at the USPTO Assignment Center.

To identify the most relevant prior art for US patent 10713672, I will examine the patent citations listed on the patent document itself. The patent document for US10713672B1 lists several "Prior art documents" under the "Cited by" section on Google Patents. These include both patent documents and non-patent literature.

Here's an analysis of some of the most relevant prior art documents cited in US10713672:

1. U.S. Patent Application Publication No. 2011/0270634 A1 (Cranshaw et al.)

• Full Citation: US 2011/0270634 A1
• Publication/Filing Date: Publication: November 3, 2011. Filing: April 29, 2011.
• Brief Description: This patent application describes systems and methods for discovering activity patterns and common paths taken by users of a location-based social network. It focuses on identifying frequently traveled routes and associated activities based on check-in data. This could be relevant to understanding user movement and density in geographic areas.
• Potential Anticipation (35 U.S.C. § 102): This reference could potentially anticipate aspects of claims related to the collection and use of venue check-in data and the understanding of user movement patterns. Specifically, the concept of utilizing location-based social network data for analyzing user behavior in geographic areas, which forms a basis for the clustering in US10713672, might be challenged. Given that US10713672 explicitly mentions "venue check-in apps" and the collection of data from such sources, US2011/0270634 A1's focus on location-based social network data is highly pertinent. It could potentially anticipate the "collecting venue check-in data" step of claims 1 and 10, and the system for storing such data in claim 17.

2. U.S. Patent No. 8,364,577 B2 (Schwartz et al.)

• Full Citation: US 8,364,577 B2
• Publication/Filing Date: Issue: January 29, 2013. Filing: February 14, 2011.
• Brief Description: This patent describes methods and systems for recommending venues to users based on user preferences and location data. It might involve analyzing user check-in history and the characteristics of venues to make recommendations.
• Potential Anticipation (35 U.S.C. § 102): While US8,364,577 B2 focuses on recommendations, the underlying techniques for collecting and analyzing venue and user data, including check-in data and user preferences, could be relevant. The patent US10713672 mentions "venue rating system" and "venue review system" as sources of check-in data, which aligns with the data types that would be used for recommendation systems. This could potentially anticipate aspects of the data collection and initial processing described in claims 1, 10, and 17, particularly where user preferences and interactions with venues are considered.

3. U.S. Patent Application Publication No. 2012/0158498 A1 (Cranshaw et al.)

• Full Citation: US 2012/0158498 A1
• Publication/Filing Date: Publication: June 21, 2012. Filing: December 16, 2011.
• Brief Description: This publication relates to systems and methods for automatically detecting and characterizing social events using location-based social network data. This involves identifying gatherings of users at specific locations and times.
• Potential Anticipation (35 U.S.C. § 102): The detection and characterization of social events based on location-based social network data in US2012/0158498 A1 directly involves the analysis of user presence at venues over time. This is highly relevant to the "check-in intensity vector" and "temporal check-in pattern types" described in US10713672. It could potentially anticipate the generation of check-in intensity vectors and the use of temporal data for clustering, as mentioned in claims 1 and 10. The concept of "social similarity" based on common users visiting venues (as described in claim 1) could also find some basis in the techniques for identifying social events.

Non-Patent Literature Examples (if available, a comprehensive list would require direct access to the full USPTO file wrapper):

The patent description itself mentions "Cheng et al. (“Exploring millions of footprints in location sharing services,” AAAI ICWSM, 2011)" and "D. M. Blei and P. I. Frazier, “Distance dependent Chinese restaurant processes,” J. Mach. Learn. Res., 2461-2488, November 2011" and "Ghosh et al., “Spatial distance dependent Chinese restaurant processes for image segmentation,” Neural Information Processing Systems, 2011". These are also critical pieces of prior art.

• Cheng et al. (“Exploring millions of footprints in location sharing services,” AAAI ICWSM, 2011)

  • Publication Date: 2011
  • Brief Description: This paper discusses exploring millions of footprints in location-sharing services, which directly pertains to the large-scale analysis of user check-in data from social networks. The inventors of US10713672 explicitly state they used data released by Cheng et al.
  • Potential Anticipation (35 U.S.C. § 102): This work likely demonstrates the prior art for collecting, preprocessing, and generally utilizing large datasets of location-based social network check-ins for analysis. This directly impacts the novelty of the "collecting venue check-in data" step in claims 1 and 10, and the associated data storage system in claim 17. The general concept of deriving insights from such "footprints" would be known prior art.

• D. M. Blei and P. I. Frazier, “Distance dependent Chinese restaurant processes,” J. Mach. Learn. Res., 2461-2488, November 2011

  • Publication Date: November 2011
  • Brief Description: This paper introduces the Distance Dependent Chinese Restaurant Process (ddCRP), a non-parametric Bayesian method for clustering non-exchangeable data, explicitly used in US10713672 for its clustering methodology.
  • Potential Anticipation (35 U.S.C. § 102): The core clustering methodology for "neighborhood typologies" in US10713672 relies heavily on the ddCRP and its hierarchical extensions. Claims that involve determining the mix of venues "based on patterns of venue category type in the venue category data emblematic of a neighborhood type" and using "inference to compute a probabilistic distribution of venues for each cluster" or "statistical sampling, such as Gibbs sampling" (as seen in dependent claims of claim 1, and also relevant for claim 10) are directly informed by this prior art. The novelty of using ddCRP for general clustering would be anticipated by this work.

• Ghosh et al., “Spatial distance dependent Chinese restaurant processes for image segmentation,” Neural Information Processing Systems, 2011

  • Publication Date: 2011
  • Brief Description: This paper extends the ddCRP to hierarchical modeling, specifically for image segmentation, and is also explicitly cited by the inventors of US10713672 as a basis for their Gibbs sampler.
  • Potential Anticipation (35 U.S.C. § 102): Similar to the Blei and Frazier paper, this work directly anticipates aspects of the probabilistic modeling and inference (e.g., Gibbs sampling) used in US10713672, especially for the hierarchical application of ddCRP. Claims related to probabilistic models and statistical sampling for determining clusters, particularly those involving hierarchical structures or spatial considerations, would be impacted.

Obviousness Analysis of US Patent 10713672 Under 35 U.S.C. § 103

This analysis identifies combinations of prior art references that would render the independent claims of US patent 10713672 obvious to a person having ordinary skill in the art (POSA) prior to the patent's earliest priority date of August 30, 2012. The analysis relies on the prior art references explicitly mentioned and incorporated by reference within the patent itself, along with general knowledge in related technical fields.

Independent Claims Overview

US Patent 10713672 B1 includes three independent claims:

• Claim 1: A computer-implemented method for identifying geographic clusters of venues based on venue check-in data, involving generating check-in intensity vectors for venues, creating a pairwise venue similarity matrix combining geographical and social distance (based on common visitors), and identifying clusters from this matrix.
• Claim 10: A computer-implemented method similar to Claim 1, but applied to geographic sub-regions (e.g., census tracts) rather than individual venues.
• Claim 17: A computer system configured to perform the method of Claim 1.

Prior Art References and Their Teachings

The patent US10713672 itself cites and incorporates several relevant prior art references, all published before the critical date of August 30, 2012:

1. Cheng et al. (2011), "Exploring millions of footprints in location sharing services," AAAI ICWSM, 2011. This reference demonstrates the availability and utility of large datasets of venue check-in data from location-based social networks like Foursquare for analyzing location patterns. The patent explicitly states that a dataset of approximately 16 million Foursquare check-ins was used, with eleven million of these extracted from data released by Cheng et al. (2011).
2. Blei and Frazier (2011), "Distance dependent Chinese restaurant processes," J. Mach. Learn. Res., November 2011. This paper introduces the Distance Dependent Chinese Restaurant Process (ddCRP), a probabilistic model for clustering non-exchangeable data that utilizes a similarity matrix (A) to specify prior assumptions about relationships between items.
3. Ghosh et al. (2011), "Spatial distance dependent Chinese restaurant processes for image segmentation," Neural Information Processing Systems, 2011. This work extends the ddCRP to hierarchical modeling and applies it in a spatial context, specifically for image segmentation.
4. Ghosh et al. (2012), "From deformations to parts: Motion-based segmentation of 3d objects," Advances in Neural Information Processing Systems 25, pp. 2006-2014, 2012. This reference is noted in US10713672 for its MATLAB implementation of a ddCRP Gibbs sampler, indicating the availability of practical tools for implementing ddCRP.

Obviousness Argument for Independent Claims 1 and 17 (Venue Clusters)

A POSA in data science, machine learning, or urban computing, prior to August 30, 2012, would have found it obvious to combine the teachings of Cheng et al. (2011), Blei & Frazier (2011), and Ghosh et al. (2011) to arrive at the method and system of Claims 1 and 17.

Motivation for Combination:

The motivation would be to effectively discover meaningful geographic clusters of venues by leveraging both the physical proximity of venues and the social interactions of users reflected in location-based check-in data. This addresses the problem of understanding urban structure, which the patent itself identifies as critical for various endeavors like urban planning, real estate, and marketing.

Detailed Breakdown:

1. Obtaining and Representing Venue Check-in Data (Preamble & Claim 1(i)): Cheng et al. (2011) explicitly teaches the availability and utility of large-scale venue check-in data from location-sharing services. A POSA would readily understand that such data inherently contains information about which users visited which venues and when. The idea of representing user activity at venues using "check-in intensity vectors" (Claim 1(i)), where each element corresponds to a user and its value reflects check-in frequency, is a standard data representation technique analogous to "bag-of-words" models in text analysis or user-item interaction matrices in recommender systems. This is a routine step for analyzing user engagement with discrete entities.

2. Generating a Pairwise Venue Similarity Matrix Combining Geographical and Social Distance (Claim 1(ii)):

   • Geographical Distance: The patent notes that "Almost always, the geographical proximity of venues is a factor in grouping venues into a cluster." Calculating geographical distance between venues based on coordinates (e.g., GPS) is a fundamental and well-known operation in any location-based service, as implied by the "location sharing services" discussed in Cheng et al. (2011).
   • Social Distance Based on Common Visitors: Given the context of "location sharing services" (Cheng et al. 2011), a POSA would recognize that shared user check-ins between venues indicate a social connection or common patronage. Defining "social distance" (or similarity) based on whether common venue visitors frequent a pair of venues, and computing this similarity using established metrics like cosine or Jaccard similarity on user-venue interaction vectors (as described in the patent), is a conventional application of social network analysis principles.
   • Combining Geographical and Social Distance: Blei & Frazier (2011) introduce the ddCRP model, which employs a "similarity matrix A" that is a "flexible way to specify prior assumptions about the strength of relationships between pairs of venues." Ghosh et al. (2011) further demonstrates the application of ddCRP in spatial contexts. A POSA, faced with the goal of clustering venues based on both their physical locations and user-driven social patterns, would be motivated to combine these two natural similarity factors (geographical proximity and social interaction). Merging different factors into a single similarity metric, for example, through weighted sums or by spatially constraining social similarity (e.g., using m closest neighbors as shown in patent equation (1)), is a common and obvious design choice in multivariate data analysis for clustering.

3. Identifying Geographic Clusters (Claim 1(iii)): Once a comprehensive similarity matrix (A) is generated, identifying clusters based on this matrix is a direct application of known clustering algorithms. The patent explicitly mentions using "spectral clustering" and the "distance dependent Chinese restaurant process (ddCRP)." Both spectral clustering and ddCRP (from Blei & Frazier 2011 and Ghosh et al. 2011) are well-established clustering techniques that operate on similarity matrices. Applying these known algorithms to a similarity matrix that combines geographical and social aspects would be an obvious choice for a POSA seeking to achieve the desired clustering. The MATLAB implementation of a ddCRP Gibbs sampler referenced in Ghosh et al. (2012) further indicates that the tools for such implementations were available.

Therefore, the combination of Cheng et al. (2011) for providing the data context and problem, and Blei & Frazier (2011) and Ghosh et al. (2011) for providing a suitable clustering framework that explicitly accommodates a flexible similarity matrix, coupled with general knowledge of how to derive and combine geographical and social similarity from location-based social network data, would have rendered Claims 1 and 17 obvious.

Obviousness Argument for Independent Claim 10 (Sub-Region Clusters)

Claim 10 describes applying the same clustering methodology to geographic sub-regions (e.g., census tracts) instead of individual venues. The patent itself explicitly describes this as an alternative embodiment: "In other embodiments, rather than clustering venues as described above, the system could be used to cluster sub-regions in the geographic region, where the sub-regions themselves contain multiple venues."

A POSA interested in analyzing urban patterns at different spatial scales would find it obvious to extend the venue-level clustering method to a higher geographical aggregation level, such as sub-regions.

1. Aggregating Check-in Data to Sub-Regions (Claim 10(i)): Instead of individual venues, check-in data would be aggregated to the sub-regions (e.g., cumulative check-ins to all venues within a sub-region by a given user). This is a routine data aggregation step in geographical information systems (GIS) and urban analytics.
2. Generating Similarity Matrix for Sub-Regions (Claim 10(ii)): The principles for determining similarity between sub-regions would follow directly from the venue-level approach. Geographical similarity between sub-regions (e.g., distance between centroids) is well-known. Social similarity would be derived from common users checking into venues within those sub-regions. Combining these factors into a similarity matrix for sub-regions would be an obvious parallel extension of the method described for venues.
3. Identifying Clusters of Sub-Regions (Claim 10(iii)): Applying the same known clustering algorithms (like spectral clustering or ddCRP) to this sub-region similarity matrix to identify clusters of sub-regions is a straightforward application of the underlying methodology.

The motivation for a POSA to apply the clustering technique to sub-regions would be to analyze urban patterns at different granularities, or to align the discovered clusters with existing administrative or statistical boundaries for planning and analytical purposes. This represents a known design choice in spatial analysis rather than an inventive step over the venue-level clustering method.