US 11030491

US patent 11030491, titled "Platform, systems, and methods for identifying property characteristics and property feature conditions through imagery analysis," was filed on January 22, 2021, and issued on June 8, 2021. The inventor is Takeshi Okazaki. The original assignee was Aon Benfield Inc., and it was reassigned to AON RE, INC. on August 2, 2024.

Abstract:
The patent describes methods and systems for automatically assessing property features. This involves applying a first machine learning analysis to imagery to identify property characteristics, and then a second machine learning analysis to classify the condition of each identified property feature.

Plain-Language Overview of Independent Claims:

• Independent Claim 1 (Method): This claim describes a method for assessing the repair or maintenance condition of a property using aerial images. It involves obtaining an aerial image, identifying specific features within that image that correspond to a property characteristic (e.g., a roof, a fence), using machine learning to classify what that characteristic is (e.g., roof shape), and also to classify its condition (e.g., good, bad). Finally, using both the characteristic and its condition, the method determines a risk estimate for potential damage to the property from disasters.

• Independent Claim 11 (System): This claim outlines a system designed to automatically categorize the repair condition of a property characteristic. The system includes processing hardware and computer instructions that, when executed, perform steps similar to Claim 1. Specifically, the system obtains an aerial image, identifies property features, classifies the characteristic, and classifies its condition. However, instead of determining a risk estimate, this system uses the characteristic and its condition to calculate a replacement cost for that property characteristic.

• Independent Claim 15 (Non-Transitory Computer Readable Medium): This claim covers a computer-readable storage medium containing instructions. When a computer's processing hardware executes these instructions, it enables the system to receive details about a property and its characteristics. It then obtains an aerial image, identifies features related to each specified property characteristic, and for each characteristic, determines both its classification (e.g., what kind of roof) and its condition (e.g., how well-maintained it is). Based on these classifications, the system then determines a risk estimate for potential disaster damage to the property.

USPTO and CAFC Docket Search:
A search of USPTO databases and CAFC 2026 dockets for patent number 11030491 did not yield specific, real-time docket entries or detailed prosecution history beyond the patent grant information. However, publicly available information indicates ongoing litigation related to this patent family, including a "US case filed in Delaware District Court" and a "PTAB case IPR2025-01360 filed (Not Instituted - Procedural)" [cite: https://patents.darts-ip.com/?family=70458621&utm_source=google_patent&utm_medium=platform_link&utm_campaign=public_patent_search&patent=[US11030491](/patent/US11030491)(B2), https://portal.unifiedpatents.com/litigation/Delaware%20District%20Court/case/1%3A25-cv-00201, https://portal.unifiedpatents.com/ptab/case/IPR2025-01360].

US Patent 11030491 is involved in at least two known litigation cases:

1. District Court Litigation:

   • Plaintiff(s): Aon Re, Inc.
   • Defendant(s): Zesty.AI, Inc.
   • Jurisdiction: U.S. District Court for the District of Delaware
   • Case Number: 1:25-cv-00201-JFM
   • Filing Date: February 19, 2025
   • Status/Outcome: On July 15, 2025, a Delaware federal judge denied Zesty.AI, Inc.'s motion to dismiss the patent infringement suit, ruling that the patent covered eligible subject matter and was not directed to a mere abstract idea. The court found that the patent claims presented a "targeted, technical solution to a specific problem" involving two separate machine-learning classifiers for analyzing property imagery. This case is ongoing.

2. PTAB Litigation:

   • Plaintiff(s) / Petitioner: Zesty.AI, Inc.
   • Defendant(s) / Patent Owner: Aon Re, Inc.
   • Jurisdiction: Patent Trial and Appeal Board (PTAB)
   • Case Number: IPR2025-01360
   • Filing Date: July 30, 2025
   • Status/Outcome: The patent text mentions this case as "Not Instituted - Procedural." The provided search results further indicate that Zesty.AI, Inc. filed petitions for inter partes review, including for US11030491, on July 30, 2025. No further details on the outcome (beyond "Not Instituted - Procedural") are available in the immediate search results.

Proceedings overview

One AIA trial proceeding has been filed against US patent 11030491. This proceeding resulted in a discretionary denial of institution, meaning no claims were invalidated. This provides a patent owner with a stronger defensive posture as the patent has successfully resisted an IPR challenge at the institution stage.

IPR2025-01360 — Zesty.ai, Inc. v. Aon Benfield Inc. (or successor AON RE, INC.)

• Type: Inter Partes Review
• Filed: 2025-07-30
• Status: Discretionary Denial – The petition for Inter Partes Review was denied institution by the PTAB.
• Judge panel: Not publicly available at this stage, as the decision was not a Final Written Decision on the merits and details of the panel might not be extensively reported in public snippets beyond the decision itself.
• Petition grounds: Details regarding specific claims, prior art, and statutory bases (§ 102 / § 103 / § 112) for the petition are not immediately available from the provided data or standard public summaries for discretionary denials. Typically, this information would be contained within the petition and the institution decision itself.
• Institution decision: Denied (Discretionary Denial) – 2025-12-23. The Board exercised its discretion to deny institution of the IPR. The specific reasoning for the discretionary denial would be outlined in the PTAB's Decision Denying Institution, but without access to the full decision, the precise grounds are unknown. Common reasons for discretionary denial include inefficient use of Board resources, serial petitions, or overlapping parallel litigation.
• Final Written Decision: Not applicable, as institution was denied.
• Settlement / termination: Not applicable, as institution was denied.
• Appeal: No appeal to the Federal Circuit, as institution was denied.
• Defensive value: The discretionary denial means the patent's claims have not been challenged on the merits at the PTAB, and the patent owner successfully defended against this IPR petition. This outcome generally strengthens the patent's position against future IPR challenges by the same petitioner or parties in privy, particularly on the same grounds.

Strategic summary

All claims of US11030491 are currently UNTESTED on the merits at the PTAB, as the single IPR filed, IPR2025-01360, resulted in a discretionary denial of institution. This means no claims were evaluated for patentability against the cited prior art.

Regarding the estoppel landscape, the petitioner Zesty.ai, Inc. (and any parties in privy with them) would likely be estopped under 35 U.S.C. § 315(e)(2) from raising any ground that they raised or reasonably could have raised in IPR2025-01360 against claims of US11030491 in future district court litigation or subsequent PTAB proceedings. For a defendant currently being asserted against (other than Zesty.ai or their privies), all prior-art grounds remain available, as the Board did not make a determination on the merits of the patentability challenges.

There is no discernible pattern of multiple IPRs from the same petitioner or aggressive PTAB appeals by the patent owner at this time, as only one proceeding has been filed and it did not proceed to a final decision. The petitioner, Zesty.ai, Inc., is a company that develops AI-powered property analytics, and Unified Patents is listed as having filed a PTAB case IPR2025-01360. This indicates that a defensive aggregator like Unified Patents was involved in challenging the patent.

Recommended next steps

The institution decision for IPR2025-01360 was a discretionary denial on 2025-12-23. For a defendant facing assertion of this patent, it is important to review the full "Decision Denying Institution" for IPR2025-01360 to understand the specific reasons for the Board's discretionary denial. This document will provide insight into why the Board chose not to institute the trial, which could inform future defensive strategies. The full decision can be accessed via the USPTO PTAB E2E portal using the proceeding number IPR2025-01360.

Inventors

The inventor listed on US patent 11030491 is Takeshi Okazaki. His employer at the time of filing was Aon Benfield Inc.

Original assignee

The original assignee on the issued patent US11030491B2 is Aon Benfield Inc.. Aon Benfield Inc. is a global reinsurance intermediary and capital advisor. While they likely do not ship a physical "product" embodying the claims (which relate to analyzing property characteristics through imagery for risk assessment), their primary line of business involves risk management and analytics, where such technology would be applied. Aon Benfield Inc. was later reassigned to AON RE, INC. on 2024-08-02.

Assignment timeline

• 2024-08-02 (executed) / recorded 2024-08-02 — Reel 006509/0002
  • Conveyance: Reassignment
  • Assignor: Aon Benfield Inc.
  • Assignee: AON RE, INC.
  • Correspondent: NOT RECORDED
  • Context: Internal reorg (Change of Name)

Timeline diagram

timeline
    title Ownership of US 11030491
    2021 : Issued to Aon Benfield Inc
    2024 : Reassigned to AON RE, INC.

NPE / troll-pattern signals

1. Shell-entity transfer — not present. The reassignment from Aon Benfield Inc. to AON RE, INC. appears to be an internal corporate name change as indicated by the context "CHANGE OF NAME (SEE DOCUMENT FOR DETAILS)" in the Google Patents record. Aon Benfield Inc. and AON RE, INC. are both operating entities within the larger Aon corporation.
2. Known asserter in the chain — not present. None of the assignees (Aon Benfield Inc., AON RE, INC.) are identified as known NPEs on public lists.
3. Repeat correspondent across the chain — not present. The only recorded assignment does not list a correspondent.
4. Cascading transfers — not present. There is only one recorded assignment, and it is a reassignment due to a name change, not a series of transfers.
5. Pre-litigation transfer — unclear. While the Google Patents record indicates litigation for this patent family, the specific filing date of the first infringement suit is not provided in the readily available information, making it unclear if the 2024-08-02 reassignment occurred within 6 months prior to litigation.
6. Bankruptcy fire-sale — not present. There is no indication of Aon Benfield Inc. or AON RE, INC. filing for bankruptcy.
7. Privateering — not present. There is no evidence suggesting a transfer to an NPE for assertion on behalf of an operating company.
8. Defensive aggregator (anti-NPE) — not present. The chain does not end at a known defensive aggregator.

Verdict

Insufficient data. While the patent is currently involved in litigation, there are no recorded assignments indicating a transfer to a shell entity or a known NPE, and the only recorded reassignment appears to be an internal corporate name change. Therefore, there is insufficient evidence to confidently classify this as an NPE assertion based on the ownership chain alone.
https://assignmentcenter.uspto.gov/

To identify the most relevant prior art for US Patent 11030491, I would typically access the patent document directly from the USPTO database and review the "References Cited" section. The provided text contains the full patent text, so I will extract the prior art from there.

Based on the provided full patent text of US11030491, the patent itself cites several documents, which are considered prior art.

Here are the cited prior art references and their descriptions as found in the patent text:

Non-Patent Literature:

• "Network In Network" by M. Lin et al. (published in the International Conference on Learning Representations, 2014, arXiv:1409.1556)
  • Publication Date: 2014
  • Brief Description: This paper describes the "Network in Network" (NIN) model, where multiple layers of artificial perception outcomes are generated using micro neural networks with complex structures. These outcomes are then stacked and averaged to create a single global average pooling layer for classification. The patent mentions NIN as a machine learning classifier that has demonstrated superior performance and is less storage-intensive than conventional CNN processing.
  • Potentially Anticipates (under 35 U.S.C. § 102): The general concept of using advanced neural network architectures, specifically NIN, for classification tasks in machine learning. Claims pertaining to the use of NIN as a machine learning model for analyzing features (e.g., in claims involving "applying a deep learning analysis model to the features," or where "the deep learning analysis model may be NIN") could be considered. For example, the description states: "Analyzing the features to determine a property characteristic may include applying a deep learning analysis model to the features. The deep learning analysis model may be NIN."
• "ImageNet Classification with Deep Convolutional Neural Networks" by Krizhevsky et al. (Advances in neural information processing systems. 2012)
  • Publication Date: 2012
  • Brief Description: This paper describes Alexnet, an example of a Convolutional Neural Network (CNN) processing model. The patent refers to CNN as a "well-established and popular machine-learning methodology" for preprocessing images and classifying property features.
  • Potentially Anticipates (under 35 U.S.C. § 102): The broad application of Convolutional Neural Networks (CNNs) for image classification and feature extraction. Claims involving a "convolutional neural network (CNN) to preprocess the aerial image... and to classify the property features" could be potentially anticipated.

Other References Mentioned as Sources (not explicitly cited as "Prior Art" in the formal sense, but as general background information or potential data sources):

These are listed as sources for imagery or general concepts, not necessarily as prior art for the inventive steps. They highlight the existing landscape of image acquisition and mapping.

• Google® Earth images by Google, Inc.
  • Brief Description: Private industry database for aerial imagery.
• NTT Geospace Corporation of Japan
  • Brief Description: Private industry database for aerial imagery.
• Geospatial Information Authority (GSI) of Japan
  • Brief Description: Publicly owned organization database for aerial imagery and urban planning maps.
• United States Geological Survey
  • Brief Description: Publicly owned organization database for aerial imagery.
• Federal Agency for Cartography and Geodesy of Germany
  • Brief Description: Publicly owned organization database for aerial imagery.
• QGIS by the Open Source Geospatial Foundation (OSGeo)
  • Brief Description: Open Source Geographic Information System (GIS) for collecting aerial imagery.
• Zenrin Co. Ltd. of Japan
  • Brief Description: Source for shape map images, similar to urban planning maps.
• Google® Street View by Google, Inc.
  • Brief Description: Source for terrestrial (street view) images.
• Bing® Maps Streetside by [Microsoft Corp.](/litigations/by-defendant/Microsoft%20Corp.)
  • Brief Description: Source for terrestrial (street view) images.
• Mapillary by Mapillary AB of Sweden
  • Brief Description: Source for terrestrial (street view) images.

To assess the obviousness of US patent 11030491 under 35 U.S.C. § 103, we must determine whether the differences between the claimed invention and the prior art would have been obvious to a person having ordinary skill in the art (POSITA) at the time of the invention (priority date: September 23, 2016). A POSITA in this field would likely be a data scientist or software engineer with expertise in machine learning (particularly deep learning and computer vision), Geographic Information Systems (GIS), and a foundational understanding of property assessment, risk analysis, or insurance underwriting. The motivation to combine prior art elements stems from the recognized need for more efficient and accurate automated property characteristic and condition assessment, as highlighted in the patent's background.

The core of the independent claims (Claim 1, 11, and 15) involves:

1. Obtaining imagery (aerial, potentially terrestrial, and shape maps).
2. Using machine learning to identify and classify property characteristics (e.g., roof shape).
3. Using machine learning to classify the condition of those characteristics (e.g., roof condition).
4. Utilizing these classifications to determine a risk estimate or replacement cost.

Combination of Prior Art for Obviousness

A primary combination that would render the claims of US11030491 obvious would involve:

• Krizhevsky et al. ("ImageNet Classification with Deep Convolutional Neural Networks", 2012): Discloses the use of Convolutional Neural Networks (CNNs) for robust image classification and feature extraction.
• Lin et al. ("Network In Network", 2014): Describes the Network in Network (NIN) model, an advanced deep learning architecture for image classification, noted for superior performance and efficiency compared to conventional CNNs.
• General availability of imagery and mapping data: This includes widely accessible aerial imagery (e.g., Google® Earth, United States Geological Survey, Geospatial Information Authority (GSI) of Japan) and shape map data (e.g., GSI, Zenrin Co. Ltd. of Japan), as noted in the patent's description.
• Established image processing techniques: General knowledge of image analysis methods such as color histogram analysis and pattern recognition for assessing image qualities or identifying defects.
• Existing need in insurance/property assessment industry: The patent itself identifies the problem of manually assessing property characteristics for risk exposure databases and the desire to "automate predictive analytics" and "more accurately estimate" risk of damage due to disaster.

Motivation to Combine

A POSITA would be strongly motivated to combine these elements for the following reasons:

1. Efficiency and Automation: The manual assessment of property characteristics and conditions is time-consuming and prone to human error. The recognized "promise of deep learning" is "replacing human identification of features with efficient algorithms for unsupervised or semi-supervised feature learning and hierarchical feature extraction." Therefore, a POSITA would naturally seek to apply advanced machine learning to automate this process.
2. Improved Accuracy: Deep learning algorithms like CNNs (Krizhevsky et al.) and NIN (Lin et al.) had already "demonstrated superior performance outcome to conventional CNN processing" in image classification tasks by the priority date. A POSITA would be motivated to leverage these cutting-edge techniques to enhance the accuracy of identifying property characteristics (e.g., roof shape) from visual imagery.
3. Comprehensive Assessment: Moving beyond just identifying a property characteristic (e.g., "this is a roof"), to assessing its condition (e.g., "this roof is in poor condition") is a logical and obvious extension for anyone tasked with risk or value assessment. Existing image processing techniques, such as color histogram analysis (as explicitly mentioned in the patent for condition analysis) or pattern recognition (e.g., identifying missing shingles), are well-known tools for detecting variations or defects in images. Applying these to regions identified by deep learning as specific property features would provide more granular and valuable data for risk estimation.
4. Integration of Data Sources: The widespread availability of aerial imagery, terrestrial imagery, and shape maps from various public and private sources (Google Earth, GSI, QGIS, Zenrin, etc.) would motivate a POSITA to integrate these diverse data streams. Techniques like overlaying shape maps with aerial images to "confirm location," "aid cropping," or "correct or compensate for alignment errors or inconsistencies" are fundamental practices in GIS and remote sensing for ensuring data accuracy before analysis. This would be a routine step to improve the reliability of the machine learning inputs.
5. Direct Business Application: Once property characteristics and their conditions are automatically classified, applying this information to calculate a "risk estimate of damage" or a "replacement cost" is a direct and obvious application to solve a known problem in the insurance or real estate industries. The patent itself outlines the use cases for estimating damage risk, repair costs, or confirming repairs. This represents a straightforward application of derived data to existing actuarial or appraisal models.

Obviousness of Specific Claim Elements

• Obtaining images (aerial, shape maps, terrestrial): These sources were publicly available and routinely used for geographic and property-related information prior to the patent's priority date.
• Identifying and classifying property characteristics using deep learning (CNN or NIN): Krizhevsky et al. and Lin et al. teach these specific deep learning models for image classification. A POSITA would choose these, or similar, for feature identification in imagery. The patent explicitly mentions both as potential classifiers.
• Classifying condition using machine learning (e.g., color histogram analysis): While Krizhevsky or Lin don't specifically teach "condition," the concept of using machine learning or image processing to assess qualities like wear, damage, or degradation from images is well-established. Color histogram analysis, as taught in the patent, is a basic image processing technique for analyzing pixel intensity distributions, which can be correlated to condition (e.g., uniformity, discoloration, or patches can indicate poor condition).
• Determining risk estimate or replacement cost from classifications: This is a direct application of the classified data (property type + condition) to solve a known problem in the insurance and real estate industries. The motivation is clear: more accurate and efficient risk assessment and cost estimation.
• Image preparation steps (overlaying shape maps, assessing orthogonality, cropping/resizing): These are standard practices in GIS and remote sensing to ensure the accuracy and usability of imagery for analysis. A POSITA would routinely perform such steps to optimize the input for machine learning models.
• Determining preferred image type based on characteristic: Knowing that certain features are better seen in aerial vs. terrestrial images (e.g., "housing siding features may be more easily detected in terrestrial imagery") is a common-sense design choice for anyone working with various image types.
• Accessing known property characteristics (e.g., age, elevation): Combining image-derived data with existing structured data about a property is a standard data fusion technique to enhance the accuracy of analytical models.

In conclusion, the claimed invention in US11030491 represents an obvious combination of known machine learning techniques (deep learning for image classification), widely available imagery sources, and standard image processing methods, applied to the known problem of inefficient and less accurate property assessment for risk and cost estimation in the insurance and real estate sectors. A POSITA, motivated by the desire for automation, increased accuracy, and comprehensive data integration, would have been led to combine these elements to achieve the claimed results.