US 11195058

Here is a concise summary of US patent 11195058:

US Patent Number: 11195058

Title: Platform, systems, and methods for identifying property characteristics and property feature conditions through aerial imagery analysis

Assignee:

• Original Assignee: Aon Benfield Inc
• Current Assignee: AON RE, INC. (as of August 2, 2024, due to a change of name from Aon Benfield Inc.)

Inventor: Takeshi Okazaki

Filing Date: May 6, 2020

Issue Date: December 7, 2021

Abstract:
The patent describes methods and systems for automatically categorizing the condition of a property characteristic. This involves obtaining aerial imagery of a geographic region including the property, identifying features within the imagery that correspond to the property characteristic, analyzing these features to classify the property characteristic, and then analyzing a specific region of the image containing that characteristic to determine its condition classification.

Plain-Language Overview of Independent Claims:

• Independent Claim 1 (Method Claim): This claim describes a computer-implemented method for assessing a property's condition. It involves:

  1. Getting an aerial image of a property.
  2. Identifying specific features in the image that belong to a property characteristic (like a roof or fence).
  3. Analyzing these identified features to determine a classification for that property characteristic (e.g., roof shape, material).
  4. Analyzing the area of the image containing the property characteristic to determine its condition (e.g., good or bad).
  5. Using both the characteristic classification and the condition classification to estimate the risk of damage to the property from disasters.

• Independent Claim 10 (System Claim): This claim outlines a system designed for automatically categorizing a property characteristic's repair condition. The system includes processing circuitry and a non-transitory computer-readable medium with instructions that, when executed, cause the system to:

  1. Obtain an aerial image of a property's region.
  2. Identify features within the image corresponding to a property characteristic.
  3. Analyze these features to determine a classification for the property characteristic.
  4. Analyze a region of the image including the characteristic to determine its condition classification.
  5. Using both classifications, determine the replacement cost for that property characteristic.

• Independent Claim 18 (Non-Transitory Computer-Readable Medium Claim): This claim covers a non-transitory computer-readable medium storing instructions. When executed by processing circuitry, these instructions cause the system to:

  1. Receive identification of a property and at least one property characteristic.
  2. Obtain an aerial image of the geographic region containing the property.
  3. Identify specific features in the aerial image that correspond to each of the identified property characteristics.

CAFC 2026 Dockets:
A search for US patent 11195058 in the CAFC 2026 dockets did not yield any specific litigation results directly involving this patent number within the provided search snippets. The snippets found relate to other patent numbers and cases.

Known litigation involving US patent 11195058:

Case 1:

• Plaintiff(s): Aon Re, Inc.
• Defendant(s): Zesty.AI, Inc.
• Jurisdiction: District of Delaware
• Case Number: 1:25-cv-00201-JFM
• Filing Date: Not explicitly stated, but the ruling denying the motion to dismiss was July 15, 2025, implying a filing prior to that date in 2025.
• Outcome/Current Status: Zesty.AI, Inc.'s motion to dismiss the patent infringement suit was denied by a Delaware federal judge on July 15, 2025. The judge found that Aon's patent claims were not directed to an ineligible abstract idea, specifically noting the distinctive structure of the process involving two separate machine-learning classifiers. The case is ongoing.

Proceedings overview

There is one AIA trial proceeding on file for US Patent 11195058, which is currently in a "Discretionary Denial" status. This indicates that the PTAB declined to institute a full review of the challenged claims. For a defendant facing assertion of this patent, this means the patent has survived one IPR attempt and its claims remain unadjudicated on the merits at the PTAB.

IPR2025-01359 — Zesty.ai, Inc. v. Aon Benfield Inc.

• Type: Inter Partes Review
• Filed: 2025-07-30
• Status: Discretionary Denial. The PTAB declined to institute the Inter Partes Review, meaning a full trial on the merits of the patentability challenge will not proceed.
• Judge panel: Not publicly available in the provided information. However, recent USPTO policy indicates the Director makes institution decisions in consultation with at least three PTAB judges.
• Petition grounds: The specific claims challenged and prior art asserted are not publicly available in the provided information. However, Zesty.ai Inc. is involved in a district court patent infringement case with Aon Re Inc. (an assignee of Aon Benfield Inc.) concerning US11195058, where Zesty.ai Inc. has argued that Aon's patents (which cover analyzing aerial imagery using machine learning for property risk assessment) are invalid under 35 U.S.C. § 101 for covering an abstract idea. It is possible the IPR petition included similar grounds, though IPRs typically focus on §§ 102 and 103.
• Institution decision: Denied on 2025-12-23. The denial was discretionary. Since October 20, 2025, the Director of the USPTO has the authority to personally decide whether to institute IPRs, considering discretionary factors, merits, and non-discretionary issues. One common discretionary denial factor is "settled expectations," which considers the length of time the patent has been in force. The patent US11195058 was granted on December 7, 2021, and the IPR was filed on July 30, 2025. This means the patent had been in force for approximately 3.5 years when the IPR was filed, which might have played a role in the discretionary denial, although the specific reasoning for the denial in this case is not detailed in the provided information. Generally, a patent in force for six years or more is more likely to be subject to discretionary denial based on settled expectations.
• Final Written Decision: Not issued, as institution was denied.
• Settlement / termination: Not applicable, as institution was denied.
• Appeal: Not applicable, as institution was denied. Institution decisions are generally unappealable to the Federal Circuit.
• Defensive value: This discretionary denial means that the claims of US11195058 challenged in IPR2025-01359 were not adjudicated on the merits at the PTAB. Therefore, a defendant facing assertion of this patent would need to pursue other avenues for invalidity challenges (e.g., in district court), as these claims were not found unpatentable by the PTAB.

Strategic summary

Only one AIA trial proceeding, IPR2025-01359, has been filed against US Patent 11195058. This IPR was denied institution on discretionary grounds, meaning the PTAB did not reach the merits of the patentability challenge. Therefore, all claims of US11195058 remain untested at the PTAB. Aon Benfield Inc. (or its assignee Aon Re Inc.) is the Patent Owner.

The estoppel landscape remains open for a defendant. Since institution was denied, the petitioner (Zesty.ai, Inc.) and its privies are not estopped under 35 U.S.C. § 315(e)(2) from raising any invalidity ground that was raised or reasonably could have been raised in the IPR. This means that a defendant facing assertion of this patent could still challenge the validity of all claims of US11195058 using any available prior art grounds (§ 102 or § 103) in other forums, such as district court.

The denial of institution in IPR2025-01359 suggests that the PTAB, under its recent policy shifts, may be becoming a less welcoming forum for petitioners, especially concerning older patents or those where "settled expectations" are a factor. While US11195058 is not particularly old, the trend in PTAB discretionary denials can still influence petitioner strategies. It is notable that Zesty.ai, Inc. is also a defendant in a district court patent infringement case brought by Aon Re Inc. (assignee of Aon Benfield Inc.) concerning this patent.

Recommended next steps

Given that the IPR was denied institution, the claims of US11195058 have not been adjudicated for patentability at the PTAB. A defendant would need to pursue invalidity challenges in district court. The district court case Aon Re Inc. v. Zesty.ai, Inc. (Case No. 1:25-cv-00201, D. Del.) is ongoing. Zesty.ai has already filed a motion to dismiss in this case, arguing the patents are invalid under 35 U.S.C. § 101. Defendants can utilize the USPTO Patent Public Search tool to search for prior art.

Inventors

Takeshi Okazaki. Employer at time of filing not determinable from the patent text.

Original assignee

Aon Benfield Inc. Their primary line of business is insurance and reinsurance solutions. The patent text states they are the "Current Assignee" as of the publication date of 2021-12-07 and the filing date of 2020-05-06. They are currently operating. Whether they shipped a product embodying the claims is not determinable from the patent text.

Assignment timeline

• 2024-08-02 (executed) / recorded 2024-08-02 — Reel 006421/1195
  • Conveyance: Change of Name
  • Assignor: AON BENFIELD INC.
  • Assignee: AON RE, INC.
  • Correspondent: MCGARRY BAIR PC, 32 Market Avenue, Suite 500, Grand Rapids, MI, 49503. This correspondent may recur.
  • Context: Change of name only

Timeline diagram

timeline
    title Ownership of US 11195058
    2020 : Application filed by Aon Benfield Inc
    2021 : Granted to Aon Benfield Inc
    2024 : Assigned to AON RE, INC.

NPE / troll-pattern signals

1. Shell-entity transfer — not present. The transfer is a change of name from AON BENFIELD INC. to AON RE, INC., both of which appear to be operating entities in the insurance/reinsurance industry.
2. Known asserter in the chain — not present. Aon Benfield Inc. and AON RE, INC. are not identified as known NPEs.
3. Repeat correspondent across the chain — unclear. MCGARRY BAIR PC is listed as the correspondent for the 2024-08-02 change of name. Without further assignment records for this patent or other patents, it's unclear if this correspondent recurs in an NPE pattern.
4. Cascading transfers — not present. Only one assignment (a change of name) is recorded.
5. Pre-litigation transfer — unclear. While the Google Patents page indicates litigation associated with this patent family (IPR2025-01359 and a US case filed in Delaware District Court), the specific dates of the first infringement suit naming this patent are not provided, making it impossible to determine if the recorded assignment (2024-08-02) falls 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. No evidence of an operating company transferring the patent to an NPE for assertion on its behalf.
8. Defensive aggregator (anti-NPE) — not present. The chain does not terminate at a known defensive aggregator.

Verdict

Insufficient data. Only one assignment (a change of name) is recorded on the USPTO Assignment Center, which does not provide enough information to identify NPE patterns.

USPTO Assignment Center search page: https://assignmentcenter.uspto.gov/

To identify the most relevant prior art for US patent 11195058, I will examine the patent's citations. However, I am unable to directly access and parse the full list of cited prior art from the USPTO database for US11195058 within this environment. The provided patent text does not explicitly list the "Prior Art Citations" section in a parseable format, and direct access to live USPTO search results to extract this specific information is not available to me.

Therefore, I cannot provide a detailed analysis of each prior art reference, including full citation, publication/filing date, brief description, and which claim(s) it potentially anticipates under 35 U.S.C. § 102.

However, based on the Background section of US11195058, it is generally understood that existing "risk exposure databases" compile various building properties and characteristics relevant to insurance, some of which can be measured using visual imagery. The patent also acknowledges the use of deep learning, citing "Network In Network" by M. Lin et al. (published in the International Conference on Learning Representations, 2014) as a model used for deep learning. This indicates that general concepts of deep learning and its application in visual recognition for feature characterization were known prior to this patent's filing.

The core innovation of US11195058, as highlighted in the litigation summary (Aon Re, Inc. v. Zesty.AI, Inc., No. 1:25-cv-00201-JFM (D. Del. July 15, 2025)), lies in its "distinctive structure of the process involving two separate machine-learning classifiers" for analyzing images to determine property characteristic classifications and condition classifications, which then informs risk estimates. This suggests that prior art that only uses a single classifier or lacks this specific two-classifier architecture for both characteristic identification and condition assessment would be less anticipatory of the patent's claims, particularly Claim 1 which covers this method.

Obviousness Analysis of US Patent 11195058 under 35 U.S.C. § 103

This analysis assesses the obviousness of US patent 11195058 (hereinafter '058 patent) under 35 U.S.C. § 103, considering the state of the art as of the priority date of September 23, 2016.

Person Having Ordinary Skill in the Art (POSA)

A person having ordinary skill in the art (POSA) in the field of the '058 patent would likely possess a bachelor's or master's degree in computer science, electrical engineering, or a related field, with several years of experience in machine learning, image processing, remote sensing, and/or geographic information systems (GIS), particularly in applications related to property assessment or risk analysis. This POSA would be familiar with various machine learning models, including neural networks and deep learning architectures, as well as standard image acquisition and processing techniques.

Summary of Core Claims

The '058 patent generally claims a system and method for automatically categorizing property characteristics and their repair/maintenance conditions through aerial imagery analysis. Key aspects include:

• Obtaining aerial imagery of a property.
• Identifying features corresponding to a property characteristic.
• Analyzing features (e.g., using deep learning like NIN) to determine a property characteristic classification (e.g., roof shape).
• Analyzing a region of the image (e.g., using machine learning like color histogram analysis) to determine a condition classification (e.g., good/bad).
• Determining a risk estimate of damage or replacement cost based on both classifications.
• Pre-processing steps such as obtaining and overlaying shape maps, assessing orthogonality, and selecting optimal imagery.
• Integration with other known property data and real-time processing.

Identified Prior Art References (from '058 Patent Text)

The '058 patent's own background and detailed description acknowledge several components of the prior art relevant to the invention:

• [A] Risk Exposure Databases and Visual Imagery for Property Characteristics: The patent explicitly states, "A risk exposure database contains a compilation of as many building properties or characteristics relevant to insurance as possible... Some of these characteristics can only be assessed by on-site inspections or by official documentation, but others can be measured using visual imagery." This establishes the known problem of gathering property data for insurance/risk assessment and that visual imagery was a recognized source. It also highlights the importance of "roof condition, roof shape, roof covering, roof anchors, roof equipment, cladding, and pounding" for these databases.
• [B] Deep Learning for Image Classification: The '058 patent refers to well-established deep learning methodologies for image classification, specifically citing "Alexnet" (Krizhevksy et al., 2012) and "Network in Network (NIN)" (M. Lin et al., 2014) as machine-learning models. It notes that "By using deep learning algorithms and sample datasets, computers can learn to distinguish and classify a wide range of characteristics to high levels of accuracy, often surpassing the recognition levels of human beings." It further states, "One of the promises of deep learning is replacing human identification of features with efficient algorithms for unsupervised or semi-supervised feature learning and hierarchical feature extraction."
• [C] Relationship between Property Characteristics/Condition and Disaster Vulnerability: The patent acknowledges that "Each roof shape has a unique response and damage vulnerability to different natural perils like earthquake or wind." This demonstrates the known motivation to classify characteristics and conditions for risk estimation.
• [D] Geographic Information Systems (GIS) and Sources of Aerial/Shape Map Imagery: The patent describes obtaining aerial imagery from remote databases like "Google® Earth images by Google, Inc." or "NTT Geospace Corporation of Japan," and publicly owned organizations such as "the Geospatial Information Authority (GSI) of Japan" or "the United States Geological Survey." It also mentions "Open Source Geographic Information System (GIS) such as QGIS by the Open Source Geospatial Foundation (OSGeo)" for collecting imagery. For shape maps, it mentions "Geospatial Information Authority of Japan or Zenrin Co. Ltd. of Japan."

Obviousness Combinations and Motivation to Combine

Combination 1: Core Automation for Property Characteristic and Condition Assessment for Risk Estimation (A + B + C + D)

A POSA, as of September 23, 2016, would have been motivated to combine the known elements of prior art [A], [B], [C], and [D] to achieve the automated property characteristic and condition assessment described in the '058 patent.

• [A] Knowledge of Risk Exposure Databases and the Need for Property Data: A POSA would recognize the existing need for efficient and accurate methods to populate risk exposure databases with property characteristics and conditions, traditionally a labor-intensive process involving manual assessment or on-site inspections.
• [B] Deep Learning for Image Classification: With the advancements in deep learning demonstrated by Alexnet (2012) and NIN (2014), a POSA would readily appreciate that these powerful image classification techniques could be applied to automate the extraction of characteristics from visual imagery. The patent itself states the inventors "recognized that deep learning methodology could be applied to risk exposure database population to analyze aerial imagery and automatically extract characteristics of individual properties, providing fast and efficient automated classification of building styles and repair conditions."
• [C] Understanding of Property Feature Vulnerability: The known correlation between property characteristics (like roof shape and condition) and their susceptibility to damage from natural disasters would provide a strong motivation for a POSA to accurately identify and classify these features and their conditions to improve risk estimates.
• [D] Availability of Aerial/Shape Map Imagery and GIS Tools: The widespread availability of aerial imagery from various commercial and public sources, combined with GIS tools for geographic data handling, would make these images a natural and accessible data source for automated analysis.

Motivation to Combine: The motivation for a POSA to combine these references is clear: to automate and improve the efficiency and accuracy of gathering property characteristic and condition data for insurance and risk assessment. By leveraging the proven capabilities of deep learning (B) to analyze readily available aerial imagery (D), the tedious and error-prone manual identification of property features (A) and their conditions could be replaced with an automated system. This automation would directly feed into the known process of estimating damage risk based on these characteristics (C), leading to more accurate and timely risk assessments. The combination represents an obvious application of known technological advances (deep learning) to solve a known problem (efficient property data collection for risk assessment) using readily available data sources (aerial imagery).

Combination 2: Image Pre-processing for Enhanced Machine Learning Analysis (A + B + D + General Image Processing Knowledge)

The '058 patent's pre-processing steps, such as obtaining shape maps, overlaying them with aerial images, determining boundary matches, and assessing orthogonality, would also be obvious to a POSA when applying machine learning to aerial imagery for property analysis.

• [A], [B], [D]: As described in Combination 1, these references establish the context of using machine learning on aerial imagery for property analysis.
• General Image Processing Knowledge: A POSA would have general knowledge of standard image processing techniques used to prepare images for analysis, especially for machine learning applications where input quality can significantly impact results. This includes techniques for geometric correction, alignment, and cropping.

Motivation to Combine:

• Overlaying Shape Maps for Alignment and Cropping: When applying machine learning to analyze features within specific property boundaries, a POSA would be motivated to accurately define the area of interest. Overlaying a known shape map (D) with an aerial image (D) is a standard GIS practice to "confirm location of a particular property" and "to match properties with images." The patent itself states this overlay "can be used in aiding in cropping the aerial image 102 c to focus analysis on a particular property location 102 b." This is a logical step to improve the precision of the input data for the machine learning model (B) and ensure the analysis is focused on the correct property features for the risk exposure database (A).
• Assessing and Correcting Orthogonality: Aerial images often contain perspective distortions. For accurate measurement and feature extraction, especially when comparing against map data or performing detailed condition analysis, correcting these distortions to generate a "true orthophoto" is a well-known process in remote sensing. A POSA seeking to use aerial imagery for precise property characteristic and condition analysis would understand the necessity of geometrically corrected images to ensure accuracy and consistency of the data used for machine learning (B). The patent explicitly mentions that "an aerial image representing a normal orthophoto angle may not be directly centered upon the planning map block" and that "the aerial image can be geometrically corrected to obtain a true orthophoto version of the aerial image." This indicates it was a known problem and solution.
• Selecting Best Quality/Preferred Image Type: When multiple sources of imagery are available (D), it is an obvious engineering choice to select the "best quality image for use in condition analysis," balancing factors like "clarity, completeness, and recency." Similarly, understanding that "Different property characteristics may be discerned based upon whether the aerial image is captured in two-dimensional or three-dimensional format" and that "Housing siding, for example, is more easily detected in terrestrial imagery 102 d and/or three-dimensional aerial imagery 120 c than in two-dimensional aerial imagery 102 c" would motivate a POSA to select the appropriate image type for a given characteristic to optimize the machine learning analysis.

Combination 3: Specific Condition Analysis Techniques (B + General Knowledge of Image Processing Techniques like Color Histogram Analysis)

• [B] Deep Learning for Characteristic Identification: A POSA would use deep learning (B) to identify and classify property characteristics (e.g., roof type).
• General Knowledge of Image Processing Techniques (e.g., Color Histogram Analysis, Pattern Recognition Algorithms): Beyond deep learning, a POSA would be familiar with other standard image processing techniques suitable for analyzing specific attributes like condition. The patent explicitly states that for condition analysis, "the machine learning analysis in some examples, can include two-dimensional color histogram analysis or three-dimensional color histogram analysis. In other embodiments, the machine learning analysis may be performed using pattern recognition algorithms (e.g., determining missing fence posts or missing/misaligned rooftop shingles)." The patent also illustrates how "good condition histograms" differ from "poor condition histograms" for rooftops.

Motivation to Combine: Once a property characteristic (e.g., a roof) has been identified and classified by type (e.g., hipped roof) using deep learning (B), a POSA would be motivated to employ appropriate and efficient image analysis techniques to assess its condition. Color histogram analysis is a well-known technique for analyzing pixel intensity distributions and color uniformity, which are direct indicators of degradation or damage in visual imagery. Similarly, pattern recognition algorithms are standard for detecting specific defects like missing shingles or fence posts. These methods are efficient for assessing condition features after the primary characteristic has been identified. Therefore, applying these known image processing techniques to assess the condition of identified features, potentially in conjunction with or as a distinct step after deep learning for characteristic identification, would be obvious to a POSA.

Conclusion

Considering the knowledge explicitly stated within the '058 patent regarding the state of the art in risk exposure databases, deep learning, image acquisition, and property assessment needs, the claimed methods and systems would have been obvious to a person having ordinary skill in the art as of the priority date of September 23, 2016. The patent describes an obvious application of known machine learning and image processing techniques to a well-understood problem, with clear motivations for each combination of elements to automate and improve existing processes.