DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement(s) (IDS) submitted on September 25th, 2024 has been considered and the listed references were noted.
Drawings
The drawings are objected to because of the following minor informalities:
In Figure 3, "roof" should be capitalized in the "roof property extraction" and "roof surrounds extraction" blocks
In Figure 5, "Date/ date range" should read "Date / date range"
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The disclosure is objected to because it contains an embedded hyperlink and/or other form of browser-executable code. Applicant is required to delete the embedded hyperlink and/or other form of browser-executable code; references to websites should be limited to the top-level domain name without any prefix such as http:// or other browser-executable code. See MPEP § 608.01.
The disclosure is objected to because of the following informalities:
In Paragraph [0020]
" …accessible by the machine learning…" should read "…accessible by the machine learning model…"
"…one or more building one the property…" should read "… one or more buildings on the property…"
In Paragraphs [0032], [0033], and [0057] "swimming pools features" should read "swimming pool features"
In Paragraph [0057], "swimming pool features regions" should read "swimming pool feature regions"
In Paragraph [0054], "4 zones" should read "four zones"
Appropriate correction is required.
Claim Objections
Claim 1 objected to because of the following informalities:
"…data accessed by the machine learning…” should read "…data accessed by the machine learning model…"
"…the one or more building one the property…" should read "…the one or more buildings on the property…"
Appropriate correction is required.
Claim 2 objected to because of the following informalities:
"…a property further comprising…" should read "…a property further comprises…".
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 1-18 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim(s) recite(s) a method directed to automatically determining the fire risk of a property by identifying a property based upon input data, retrieving an aerial image to identify features and buildings associated with the property, calculate a fire score, and output a fire score. With respect to the analysis of independent method claim 1:
STEP 1:
With regard to Step 1: the instant claim is directed to a method; and therefore, the claim is directed to one of the statutory categories of invention.
STEP 2A, Prong One:
With regard to 2A, Prong One, the limitations “identifying a property based upon input data received by the computer”, “identifying features associated with the property based on the analysis of the aerial image and based on data accessible by the machine learning stored in the storage”, “identifying one or more buildings on the property”, and “calculating a fire score based on the identification of features and the one or more buildings on the property” as drafted, recite an abstract idea, such as a process that, under its broadest reasonable interpretation, covers the identification of key features (such as vegetation, moisture, or flammable materials) and buildings on a property to allow a user to calculate a fire score to determine its wildfire risk through observation, evaluation, judgement, opinion. This is the concept that falls under the grouping of abstract idea mental processes for monitoring and determination (evaluation, judgement, and/or opinion of calculating and outputting the fire score for the property based on the aerial image).
STEP 2A, Prong Two:
The 2019 PEG defines the phrase "evaluate whether the claim recites additional elements that integrate the exception into a practical application of the exception". Therefore, additional elements, or a combination of additional elements in the claim, are required to apply, rely on, or use the judicial exception. In the instant case, in this instance, the additional limitations are "retrieving at least one aerial image corresponding to the property for at least one epoch" and “outputting the fire score”, which are essentially considered insignificant extra-solution activities of acquiring input. Therefore, the additional limitation does not apply, rely on, or use the judicial exception as an indication of integration of the judicial exception into a practical application. In addition, the method in Claim 1 recites additional elements of a computer having a network connection and connected to a storage, considered generic computer components, which do not integrate the above-described abstract idea into a practical application. Accordingly, claim 1 recites an abstract idea.
Step 2B:
Because the claim fails under Step 2A, the claim is further evaluated under Step 2B. The claim herein does not include additional elements that are sufficient to amount to significantly more than the judicial exception, because as discussed above with respect to the integration of the abstract idea into practical application, the additional elements in the claim are merely insignificant extra-solution activities, which does not amount to significantly more than an abstract idea. Therefore, claim 1 is not patent eligible.
In addition, with regard to dependent claims 2-18 viewed individually, these additional elements, under their broadest reasonable interpretation, cover features expanding upon the limitations as an abstract idea (mental processes or in certain dependent claims, introducing mathematical calculations such as calculating a total fire risk from the fire score and fire hazard), and do not provide meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that the claims amount to significantly more than the abstract idea itself.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-5 and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Ton-That et al. (US 2022/0215744).
Regarding Claim 1, Ton-That discloses “A method for automatically determining fire risk of a property with a computer having a network connection and connected to a storage and utilizing machine learning, the method comprising the steps of” (Ton-That, Paragraph [0021], discloses “a system for wildfire risk analysis using image processing and supplemental data is provided. The system may be used for various practical applications of extracting information from image data in combination with one or more data sources. By using image data and accessing one or more related data sources, many wildfire risk factors can be determined for a geographic area. The wildfire risk data can be used to predict wildfire spread patterns, predictively alert parties in a likely fire spread path, and/or alert responders. Some types of data can be discovered from a single viewing perspective, such as an overhead view from aerial imagery data, using artificial intelligence/machine learning to locate features of interest in a large volume of data.”; Paragraph [0031] discloses “The user systems 106 may each be implemented using a computer executing one or more computer programs for carrying out processes described herein. In one embodiment, the user systems 106 may each be a personal computer (e.g., a laptop, desktop, etc.), a network server-attached terminal (e.g., a thin client operating within a network), or a portable device (e.g., a tablet computer, personal digital assistant, smart phone, etc.).”; Paragraph [0032] discloses “Each of the data processing server 102, user systems 106, data storage servers 110, third-party servers 116, and remote user systems 125 can include a local data storage device, such as a memory device.”; Paragraph [0074] discloses “It will be appreciated that aspects of the present invention may be embodied as a system, method, or computer program product”); “identifying a property based upon input data received by the computer” (Ton-That, Paragraph [0063], discloses: “the data processing server 102 can identify one or more neighboring properties 805A-805D that share at least one of the property boundaries 802, 1106.”; Paragraph [0030], discloses “each of the data processing server 102, user systems 106, data storage servers 110, third-party servers 116, and remote user systems 125 can include one or more processors (e.g., a processing device, such as one or more microprocessors, one or more microcontrollers, one or more digital signal processors) that receives instructions (e.g., from memory or like device), executes those instructions, and performs one or more processes defined by those instructions. Instructions may be embodied, for example, in one or more computer programs and/or one or more scripts.”); “retrieving at least one aerial image corresponding to the property for at least one epoch” (Ton-That, Paragraph [0068], discloses “In some embodiments, the data processing server 102 can access a plurality of datasets from an archive including the aerial imagery data and the infrared data associated with the geographic area and collected over a period of time”); “identifying features associated with the property based on an analysis of the aerial image and based on data accessible by the machine learning stored in the storage” (Ton-That, Paragraph [0022], discloses “Further, a group of machine-learning models can be developed that looks for specific features, groups of features, and various characteristics associated with properties viewed at a wider scale (e.g., a neighborhood) and a detailed lower-level scale, such as roofing or siding material type. The use of supplemental property data can enhance the visual data, such as identifying features that are not directly visible in the image data (e.g., property boundaries).”); “identifying one or more buildings on the property” (Ton-That, Abstract, discloses “…Based on the first dataset and constrained by the property boundaries, a building detection model can be applied to identify a building…”); “calculating a fire score based on the identification of the features and the one or more building one the property; and outputting the fire score” (Ton-That, Paragraph [0054] and Figure 11, discloses “FIG. 11 depicts a user interface 1100 according to some embodiments. In the example of FIG. 11, the user interface 1100 can be used to allow a user to select details of an image of the aerial imagery data 119 of FIG. 1 through the user application 132 of FIG. 1 as part of a wildfire risk map to analyze. The user interface 1100 can provide a graphical user interface 1102 to select commands, provide address input, and control image viewing, such as zoom controls and making different features or layers visible on the user interface 1100. The example of FIG. 11 illustrates a plurality of properties 1104 with property boundaries 1106 and wildfire risk scores 1108, such as defensible space adherence scores for a selected geographic area. The wildfire risk scores 1108 can indicate whether an underlying property 1104 is at higher or lower risk of wildfire impact to dwellings or other structures, for instance based on meeting a defensible space guideline 726 and/or other factors that impact fire spread. For instance, wildfire risk scores 1108 may also incorporate a fire risk adjustment based on moisture content of vegetation in proximity to buildings, structures, and/or other objects. Other features and derived characteristics may also or alternatively be displayed through the user interface 1100.”).
PNG
media_image1.png
545
520
media_image1.png
Greyscale
It is important to note that although the paragraph does not explicitly disclose outputting the fire score, Ton-That uses a user-interface to display all the fire scores of different areas across the entire aerial image map based on a variety of factors. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to use the techniques for determining the fire risk of a property with a computer seen in Ton-That to improve the fire risk determination method in the same way. By using the techniques seen in Ton-That, one of ordinary skill in the art can effectively allow for a holistic analysis of the property area from the aerial image to incorporate multiple factors to determine which areas are more susceptible to wildfire damage. Therefore, it would have been obvious for one of ordinary skill in the art to use the Ton-That reference to achieve the same method seen in Claim 1.
Regarding Claim 2, Ton-That discloses “The method of claim 1, wherein the step of identifying a property further comprising the steps of: displaying the aerial image on a display coupled to the computer” (Ton-That, Paragraph [0035], discloses: “The computer 201 can further include a display controller 225 coupled to a display 230.”); “accepting a selection of a property from said aerial image; and identifying the property based on the selection” (FIG. 11 depicts a user interface 1100 according to some embodiments. In the example of FIG. 11, the user interface 1100 can be used to allow a user to select details of an image of the aerial imagery data 119 of FIG. 1 through the user application 132 of FIG. 1 as part of a wildfire risk map to analyze. The user interface 1100 can provide a graphical user interface 1102 to select commands, provide address input, and control image viewing, such as zoom controls and making different features or layers visible on the user interface 1100. The example of FIG. 11 illustrates a plurality of properties 1104 with property boundaries 1106 and wildfire risk scores 1108, such as defensible space adherence scores for a selected geographic area.).
PNG
media_image1.png
545
520
media_image1.png
Greyscale
Regarding Claim 3, Ton-That discloses “The method of claim 1, wherein the features associated with the property are selected from the group consisting of: vegetation, debris, structures, paved roadways, unpaved roadways, flammable, inflammable materials, and combinations thereof” (Ton-That, Paragraph [0022], discloses “Further, a group of machine-learning models can be developed that looks for specific features, groups of features, and various characteristics associated with properties viewed at a wider scale (e.g., a neighborhood) and a detailed lower-level scale, such as roofing or siding material type. The use of supplemental property data can enhance the visual data, such as identifying features that are not directly visible in the image data (e.g., property boundaries). The height and relative health of vegetation can be determined using the imagery, which can then be used to determine a predicted level of combustibility of the vegetation along with other factors. Ground covering, relative moisture, heat retention, natural fire barriers (e.g., bodies of rock or water), and other such features may be identified and used in wildfire risk analysis, as further described herein.”)
Regarding Claim 4, Ton-That discloses “The method of claim 3, further comprising the step of: determining a date of when the aerial image was captured” (Ton-That, Paragraph [0028], discloses “If the user application 132 requests a location analysis for a location that already has associated data in the data cache 120, the process controller 128 may check a date/time stamp associated with the datasets 122 and location specific data 124 to determine whether more recent data is available in the aerial imagery data 119 or property data 121.”); “wherein when the feature comprises vegetation, determining if the vegetation is leaf-on or leaf-off” (Ton-That, Paragraph [0045], discloses “The vegetation detection model 712 can identify vegetation position, a vegetation outline, type, health, and other such features with seasonal adjustments, such as summer condition versus winter condition.”; From nature, we know that vegetation grows or loses leaves depending on the season, especially when it comes to specific trees and flowers, so this passage demonstrates that the invention can identify whether vegetation is leaf-on or leaf-off).
Regarding Claim 5, Ton-That discloses “The method of claim 3, further comprising the step of: determining a moisture level of identified vegetation features” (Ton-That, Paragraph [0059], discloses “At step 1310, the data processing server 102 can apply a vegetation detection model 712 to identify one or more vegetation areas (such as trees 806 or other plant life) based on the first dataset and constrained by the property boundaries 802, 1106. A moisture content of the one or more vegetation areas can be identified by the vegetation detection model 712 based on the infrared data of the first dataset in combination with classifying vegetation type of the one or more vegetation areas.”); “filtering vegetation features with respect to the identified moisture levels” (Ton-That, Paragraph [0065], discloses “the data processing server 102 can output a vegetation pruning recommendation with the wildfire risk map 800 to illustrate the predicted reduction in the wildfire risk score by performing a size reduction of the vegetation 408, for instance on the remote user interface 1000 or user interface 1100. Where portions of the vegetation 408 are identified as dead, dying, or low on moisture content, the impact of pruning recommendations can be more substantial. In some embodiments, subsequent images can be captured for the same location at a later time to determine whether the recommendations were followed and if the wildfire risk score changed.”; As shown in Paragraph [0065], in addition to the vegetation being identified, the vegetation is filtered in the sense of determining where there are dead or neglected areas in terms of moisture to redirect a user to see where to prune and water to be able to recover that area for any additional damage from drought or wildfires); “wherein the filtering provides a moisture-weighting for the vegetation features based on the identified moisture in each vegetation feature” (Ton-That, Paragraph [0065], discloses “...A future fire risk of the geographic area or a neighboring geographic area can be predicted based on identifying the one or more areas of change and change trends or patterns over the period of time. An alert notification can be triggered based on the future fire risk exceeding an alert threshold. The alert threshold can be established by examining data from previously observed wildfires and/or other information determined to have a causal relationship with fire spread risk. Further aspects can include identifying one or more dead spots in the one or more vegetation areas based on the moisture content and determining the fire risk adjustment based on a distance of the one or more dead spots to a building.”; Here, moisture content is being analyzed and weighted based on how much moisture is present in specific areas of the image); “in determining the fire score” (Ton-That, Paragraph [0054], discloses “The wildfire risk scores 1108 can indicate whether an underlying property 1104 is at higher or lower risk of wildfire impact to dwellings or other structures, for instance based on meeting a defensible space guideline 726 and/or other factors that impact fire spread. For instance, wildfire risk scores 1108 may also incorporate a fire risk adjustment based on moisture content of vegetation in proximity to buildings, structures, and/or other objects. Other features and derived characteristics may also or alternatively be displayed through the user interface 1100.”).
Regarding Claim 9, Ton-That discloses “The method of claim 3, further comprising the steps of: determining zones relative to a footprint of any identified buildings on the property, the zones being determined based on a distance from the footprint of an identified building” (Ton-That, Paragraph [0046], discloses “In embodiments, the building detection model 710 can be created based on a building footprint dataset, which may be extracted from the property data 121 of FIG. 1 associated with a geographic area defined in the training data 704. Building footprints in the training data 704 can overlay image data extracted from the aerial imagery data 119 of FIG. 1 associated with the geographic area defined in the training data 704. An expert can view the alignment and make adjustments to fix skewed alignment results as an adjusted training set in the training data 704. The adjusted training set in the training data 704 can be used for the building detection model 710. The training process 702 can train the building detection model 710 using machine-learning techniques, such as image segmentation with masking and regions with convolutional neural networks or other such techniques to support building footprint detection based on image data from the aerial imagery data 119.”; Paragraph [0049] discloses: “The result postprocessing 724 can cross-compare results of the model predictions 722 to make a final determination of the most likely feature and/or condition captured by a pixel or group of pixels. The result postprocessing 724 can summarize results to highlight regions, such as pixels collectively grouped as a roof of a single structure, as well as other associated data or a tree canopy, for example. The result postprocessing 724 may also perform comparisons and computations of results between the model predictions 722, such as determining an estimated distance between one or more vegetation areas and a building (e.g., nearest portion of a building footprint) as separation data 725.”; Paragraph [0050] discloses “The result postprocessing 724 can also compare the separation data 725 to a defensible space guideline 726 to determine a defensible space adherence score 728. Further processes managed by the process controller 128 of FIG. 1 can take additional actions, such as generating a wildfire risk map (e.g., wildfire risk map 800 of FIG. 8) including the defensible space adherence score 728 associated with a geographic area and constrained by property boundaries”); “wherein a fire risk weighting assigned to a feature is related, in part, to the zone in which the feature is located; wherein features located in a zone closer to the building receive a higher zone-weighting than feature located in a zone further from the building” (Ton-That, Figure 8 and Paragraph [0051], discloses “FIG. 8 depicts a wildfire risk map 800 according to some embodiments. The wildfire risk map 800 can be generated by the data processing server 102 of FIG. 1 responsive to the process controller 128 of FIG. 1. In the example of FIG. 8, the wildfire risk map 800 includes property boundaries 802 with building footprints 804, including building footprint 804A, 804B, 804C, and 804D for properties 805A, 805B, 805C, and 805D. The building footprints 804 can be any type of structure, such as a house, a multi-family dwelling, an apartment building, a commercial building, and the like. The wildfire risk map 800 can also depict a plurality of trees 806 as examples of vegetation. Separation distances between trees 806 (or other vegetation) and building footprints 804 can be computed as separation data, but may not be visible on the wildfire risk map 800. For example, an estimated distance between each of the one or more trees 806 and a nearest portion of the building footprint 804 can be determined as separation data. Neighboring tree pairs 807 (or other vegetation) can be analyzed to determine distances between multiple trees 806. The separation data can be compared to a defensible space guideline to determine a defensible space adherence score 808A, 808B, 808C, 808D associated with each of the properties 805A, 805B, 805C, 805D. The wildfire risk map 800 can be generated with the defensible space adherence scores 808A, 808B, 808C, 8080D associated with a geographic area and constrained by the property boundaries 802. Data in the wildfire risk map 800 can be used for various purposes, such as predicting a fire path spread pattern 810 between the one or more neighboring properties 805A-805D based on geographic features in combination with building footprints 804A-804D, trees 806, other objects, structures, vegetation, and other such data.”
PNG
media_image2.png
668
533
media_image2.png
Greyscale
Here, it is important to note from this invention that the higher-zone weighting stems from the determination of the fire spread path pattern, as the areas that the model is predicting to have a faster/slower spread most likely have a higher wildfire risk score, so those zones would be heavily weighted and would give the user a clear idea as in where the fire will spread at a specific property via the wildfire risk map seen in Figure 8 and the user interface with the aerial image showing the wildfire risk scores in Figure 1 (see above in the analysis for Claims 1 and 2)); “in determining the fire score” (Ton-That, Paragraph [0054], discloses “The wildfire risk scores 1108 can indicate whether an underlying property 1104 is at higher or lower risk of wildfire impact to dwellings or other structures, for instance based on meeting a defensible space guideline 726 and/or other factors that impact fire spread. For instance, wildfire risk scores 1108 may also incorporate a fire risk adjustment based on moisture content of vegetation in proximity to buildings, structures, and/or other objects. Other features and derived characteristics may also or alternatively be displayed through the user interface 1100.”).
Regarding Claim 10, Ton-That discloses “The method of claim 9, further comprising the steps of: filtering features with respect to the determined zones and a parcel boundary associated with the property” (Ton-That, Paragraph [0058], discloses “At step 1306, the data processing server 102 can identify a plurality of property boundaries 802, 1106 associated with the geographic area based on the property boundary data. At step 1308, the data processing server 102 can apply a building detection model 710 to identify a building (for instance, as a building footprint 804) based on the first dataset and constrained by the property boundaries 802, 1106.”); “wherein the filtering provides a feature-weighting for an identified feature based on an identification of the feature” (Ton-That, Paragraph [0059], discloses “At step 1310, the data processing server 102 can apply a vegetation detection model 712 to identify one or more vegetation areas (such as trees 806 or other plant life) based on the first dataset and constrained by the property boundaries 802, 1106. A moisture content of the one or more vegetation areas can be identified by the vegetation detection model 712 based on the infrared data of the first dataset in combination with classifying vegetation type of the one or more vegetation areas.”; Here, moisture content is the feature being observed and weighted based on how much moisture is present in specific areas of the image); “in determining the fire score” (Ton-That, Paragraph [0054], discloses “The wildfire risk scores 1108 can indicate whether an underlying property 1104 is at higher or lower risk of wildfire impact to dwellings or other structures, for instance based on meeting a defensible space guideline 726 and/or other factors that impact fire spread. For instance, wildfire risk scores 1108 may also incorporate a fire risk adjustment based on moisture content of vegetation in proximity to buildings, structures, and/or other objects. Other features and derived characteristics may also or alternatively be displayed through the user interface 1100.”).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Sha et al. (US 2020/0151538).
Regarding Claim 6, Ton-That discloses “The method of claim 3” (Please refer to the above-described analysis for Claim 3), (Sha, Paragraph [0052]). As seen in the above paragraph, classification labels are used for creating classes of content depending on if the data provided is correct or not to appropriately analyze the image. Sha also discloses that “In the DNN 610, the feature vector layer 618 is the hidden layer before the output layer 616. The feature vector layer 618 includes neurons 620 and the output of the feature vector layer 618 is deemed, in this case to represent feature vectors of the aerial image 330 that is input to the DNN 610” (Sha, Paragraph [0053]). Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the method seen in Ton-That with the technique of having vector layers associated with the aerial image as seen in Sha to have an improved fire risk determination method. By combining the method seen in Ton-That with the Sha technique of incorporating vector layers associated with aerial images, one of ordinary skill in the art can enable the invention to have a detailed analysis due to the vector layers being able to divide different layers of information that each image provides. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Ton-That and Sha references to achieve the same method described in Claim 6.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Vianello et al. (US 2024/0265630 w/ an EFD of February 2nd, 2023).
Regarding Claim 7, Ton-That discloses “The method of claim 3, further comprising the steps of:” (Please refer to the above-described analysis for Claim 3) (Ton-That, Paragraph [0054], discloses “The wildfire risk scores 1108 can indicate whether an underlying property 1104 is at higher or lower risk of wildfire impact to dwellings or other structures, for instance based on meeting a defensible space guideline 726 and/or other factors that impact fire spread. For instance, wildfire risk scores 1108 may also incorporate a fire risk adjustment based on moisture content of vegetation in proximity to buildings, structures, and/or other objects. Other features and derived characteristics may also or alternatively be displayed through the user interface 1100.”). Ton-That does not explicitly disclose “determining a geometry of a feature; filtering features with respect to the identified geometry of the feature; wherein the filtering provides a geometry-weighting for an identified feature based on the identified geometry of the feature”. However, in an analogous field of endeavor, Vianello discloses for determining a geometry of a feature that “Determining property component parameter values based on property information S300 can function to detect key parameter values that define the property component geometry. The parameters are preferably features (e.g., property component features), but can additionally or alternatively include attributes, geometric parameters (e.g., position, orientation, dimensions, pose, size, scale, rotation, etc.), type, and/or other parameters.” (Vianello, Paragraph [0080]). Vianello further discloses for filtering features with respect to the identified geometry of the feature that “property component features can include a set of constituent geometric shapes, wherein the set of constituent geometric shapes cooperatively form the property component geometry” (Vianello, Paragraph [0084]) whereas “A set of candidate shapes (e.g., candidate polyhedrons) can include a set of shape classes (e.g., polyhedron classes) and/or any other subspace of geometric shapes (e.g., subspace of polyhedrons). Examples are shown in FIG. 10A and FIG. 10B. The set of candidate shapes (e.g., 3D primitives) can be learned, predetermined, manually determined, and/or otherwise determined. In an example, polyhedrons can be fit to 3D geometric representations (e.g., DSM, 3D model, etc.) of a set of training property components (e.g., during training of a parameter model, before training a parameter model, etc.), wherein the set of candidate polyhedrons can be determined based on the fit polyhedrons.” (Vianello, Paragraph [0085] and Figures 10A and 10B).
PNG
media_image3.png
489
352
media_image3.png
Greyscale
PNG
media_image4.png
239
565
media_image4.png
Greyscale
It is important to note that the shapes are being filtered based on their geometry in the form of being separated into classes. Furthermore, the shapes can be filtered this way through machine learning to make this process easier as we will see in the next limitation. Vianello finally discloses for the filtering providing geometry weighting that “Models can be trained, learned, fit, predetermined, and/or can be otherwise determined. The models can be learned or trained (e.g. pre-trained) using: self-supervised learning, semi-supervised learning (e.g., positive-unlabeled learning), supervised learning, unsupervised learning, reinforcement learning, transfer learning, Bayesian optimization, positive-unlabeled learning, using backpropagation methods (e.g., by propagating a loss calculated based on a comparison between the predicted and actual training target back to the model; by updating the architecture and/or weights of the model based on the loss; etc.), fitting, interpolation and/or approximation (e.g., using gaussian processes), and/or otherwise learned. Models can be learned or trained on: labeled data (e.g., data labeled with the target label), unlabeled data, positive training sets (e.g., a set of data with true positive labels), negative training sets (e.g., a set of data with true negative labels), and/or any other suitable set of data” (Vianello, Paragraph [0051]) whereas “property component parameter values are preferably determined automatically by one or more models (e.g., a parameter model, object detector, etc.), but can additionally and/or alternatively be determined manually (e.g., entered into an interface, selected on an image, etc.), and/or otherwise determined” (Vianello, Paragraph [0086]). From this, we see that the machine learning model assigns weights to the model to better fit the shapes that they are analyzing in order to adequately identify the geometry of the shape. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the method seen in Ton-That with the technique of determining, filtering, and weighting the geometry of a feature as seen in Vianello to achieve an improved analysis of different objects within the property within the fire risk determination method. By combining the geometry techniques seen in Vianello with the method seen in Ton-That, one of ordinary skill in the art can ensure an effective overview of various objects, vegetation, and architecture that may be present on the property in the aerial image. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Ton-That and Vianello references to achieve the same method described in Claim 7.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Vianello, and further in view of Wall et al. (US 20230023808).
Regarding Claim 8, the combination of Ton-That and Vianello discloses “The method of claim 7, further comprising the steps of: (Ton-That, Paragraph [0054], discloses “The wildfire risk scores 1108 can indicate whether an underlying property 1104 is at higher or lower risk of wildfire impact to dwellings or other structures, for instance based on meeting a defensible space guideline 726 and/or other factors that impact fire spread. For instance, wildfire risk scores 1108 may also incorporate a fire risk adjustment based on moisture content of vegetation in proximity to buildings, structures, and/or other objects. Other features and derived characteristics may also or alternatively be displayed through the user interface 1100.”). The combination of Lee and Vianello does not explicitly disclose “The wildfire risk scores 1108 can indicate whether an underlying property 1104 is at higher or lower risk of wildfire impact to dwellings or other structures, for instance based on meeting a defensible space guideline 726 and/or other factors that impact fire spread. For instance, wildfire risk scores 1108 may also incorporate a fire risk adjustment based on moisture content of vegetation in proximity to buildings, structures, and/or other objects. Other features and derived characteristics may also or alternatively be displayed through the user interface 1100.”. However, in an analogous field of endeavor, Wall discloses the following in Paragraphs [0258]-[0266].
PNG
media_image5.png
572
464
media_image5.png
Greyscale
PNG
media_image6.png
253
475
media_image6.png
Greyscale
As shown, the failure items overlap due to the presence of multiple fuel items, therefore determining an overlap within the aerial image with Wall’s invention. In terms of filtering features with respect to the overlap, note that for each failure item that is noted to have overlap, they are each put in their respective home ignition zones, where they are weighted when evaluating the risk score to determine how much the overlap causes the zone to be at high or low risk of being severely damaged by wildfires. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the method seen in the combination of Ton-That and Vianello with the technique of determining, filtering, and weighting overlap between two or more features seen in Wall to achieve a more complete fire risk determination method. By combining the Wall technique of determining and weighting overlap between two or more features with the method seen in the combination of Ton-That and Vianello, one of ordinary skill in the art allows for a user to identify the areas that may be at greater risk for being decimated to wildfires due to the amount of overlap that may exist between two or more features within them. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Ton-That, Vianello, and Wall references to achieve the same method described in Claim 8.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Shu et al. (US 20240233086 w/ an EFD of January 10th, 2023).
Regarding Claim 11, Ton-That discloses “The method of claim 3, further comprising the steps of:” (Please refer to the above-described analysis for Claim 3) determining if a feature is within the parcel boundary (Ton-That, Paragraph [0051], discloses “Neighboring tree pairs 807 (or other vegetation) can be analyzed to determine distances between multiple trees 806. The separation data can be compared to a defensible space guideline to determine a defensible space adherence score 808A, 808B, 808C, 808D associated with each of the properties 805A, 805B, 805C, 805D. The wildfire risk map 800 can be generated with the defensible space adherence scores 808A, 808B, 808C, 8080D associated with a geographic area and constrained by the property boundaries 802.”);Ton-That, Paragraph [0054], discloses: “The wildfire risk scores 1108 can indicate whether an underlying property 1104 is at higher or lower risk of wildfire impact to dwellings or other structures, for instance based on meeting a defensible space guideline 726 and/or other factors that impact fire spread. For instance, wildfire risk scores 1108 may also incorporate a fire risk adjustment based on moisture content of vegetation in proximity to buildings, structures, and/or other objects. Other features and derived characteristics may also or alternatively be displayed through the user interface 1100.”).
Ton-That does not explicitly disclose “filtering features based on whether the feature is fully in-parcel, fully out-of-parcel, or partly in-parcel and partly out-of-parcel; wherein the filtering provides a parcel-weighting for an identified feature based on the determination of the location of the feature relative to the parcel boundary”. However, in an analogous field of endeavor, Shu discloses “As a result, a complete raster map of the area is generated containing pixels that are attributed as belonging inside, outside, or on the border of a parcel, along with a distance to the nearest border for those pixels inside and outside of a parcel. Pixels contained inside a legal land parcel may be assigned a particular sign (e.g., negative or positive), whereas the pixels contained outside of any legal land parcel may possess the opposite sign. Pixels that lie on the boundary between legal land parcels (or between a legal land parcel and an area for which no parcel data is available) may be attributed as zero. In some examples, distance attributes may be truncated at a threshold value (e.g., from −10 to +10), to simplify machine learning. Depending on the configuration of the machine learning model, an offset may be applied to the distance transform so that a positive range of distance attributes reflect the full range of distances inside and outside parcel boundaries (e.g., −10/+10 offset by 10 to 0/+20), which may simplify the machine learning process.” (Shu, Paragraph [0058]). It is important to note in this paragraph that pixels represent the feature, as they encompass areas that are inside, partially in, partially out, or outside of the parcel boundary overall. Furthermore, the paragraph clearly shows how the pixels are filtered depending on their status, whereas if they are partially in or out of the parcel boundary (or in this case, “pixels that lie on the boundary between land parcels”) they get removed from the raster map with an attribute of zero. This is also seen with pixels inside or outside the parcel boundary, where a positive or negative sign is applied depending on their status. Finally, the parcel-weighting can be synonymous to the offset, as they are weighted depending on whether the pixels are a certain distance inside or outside of the parcel boundaries.
Shu further expands upon this by disclosing “FIG. 6B further shows a distance-transform raster map 624 generated by converting the training parcel data 622 in the manner described above. As can be seen, pixels corresponding to the boundary between adjacent pixels are labeled as zero, and pixels inside parcels are labeled with positive integers indicating the distance, measured in pixels, to the nearest parcel boundary. Since the geospatial image 620 is entirely filled with parcel data, there are no negatively-attributed pixels indicating areas without parcel coverage. The resulting geospatial image 620 and distance-transform raster map 624 may be provided as training data for a machine learning model” (Shu, Paragraph [0060]).
PNG
media_image7.png
406
841
media_image7.png
Greyscale
This further explains how the parcel weighting can be used based on the location of the feature, where we can now see a visual idea of what Shu’s invention is performing in order to filter features within, between, or outside of the parcel boundary. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the method seen in Ton-That with the technique of determining whether the parcel is inside, between, or outside the parcel boundary seen in Shu to achieve a more improved fire risk determination method. By combining the feature-parcel boundary technique with the method seen in Ton-That, one of ordinary skill in the art allows for a user of the invention to have the ability to distinctly identify separate areas where there may be areas with features in specific locations within various boundaries to mitigate the risk of error and accurately determine the fire risk of those areas having overlapping features. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Ton-That and Shu references in order to achieve the same method described in Claim 11.
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Wu et al. (Fire Risk Assessment of Heritage Villages: A Case Study on Chengkan Village in China).
Regarding Claim 12, Ton-That discloses “The method of claim 3, further comprising the steps of:” (Please refer to the above-described analysis for Claim 3) (Ton-That, Paragraph [0054], discloses “The wildfire risk scores 1108 can indicate whether an underlying property 1104 is at higher or lower risk of wildfire impact to dwellings or other structures, for instance based on meeting a defensible space guideline 726 and/or other factors that impact fire spread. For instance, wildfire risk scores 1108 may also incorporate a fire risk adjustment based on moisture content of vegetation in proximity to buildings, structures, and/or other objects. Other features and derived characteristics may also or alternatively be displayed through the user interface 1100.”). Ton-That does not explicitly disclose “determining a topology of the property; filtering features with respect to the identified topology; wherein the filtering provides a topology-weighting based on the identified topology of the property”. However, in an analogous field of endeavor, Wu describes a study aimed to “establish a fire risk assessment system and model to assess fire safety for heritage villages” (Wu, Abstract) discloses the following in Section 3.3.2 and Figures 6 and 7:
PNG
media_image8.png
426
613
media_image8.png
Greyscale
PNG
media_image9.png
313
622
media_image9.png
Greyscale
PNG
media_image10.png
505
674
media_image10.png
Greyscale
PNG
media_image11.png
336
702
media_image11.png
Greyscale
As seen in the aforementioned section and figures, topology is used here for the property, which is in this case the historical fire risk data for these heritage villages. The network is also filtered through the division of the fire dynamic layer to focus on specific elements that deal with the fire risk of the villages. As with any neural-network, the Bayes topological network allows for the determination of objective weight, which would be synonymous to topological weighting in the described limitations. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the method seen in Ton-That with the Wu technique for determining and weighting the topology to achieve an effective analysis for determining fire risks of a property. By combining the Wu technique of determining and weighting of the topology with the method seen in Ton-That, one of ordinary skill in the art can analyze how different components within various features such as building or landscapes can affect the spread of wildfires across various properties throughout the world. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Ton-That and Wu references to achieve the same method described in Claim 12.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Wall.
Regarding Claim 13, Ton-That discloses “The method of claim 3, further comprising the steps of” (Please refer to the above-described analysis for Claim 3); obtaining the fire hazard associated with the property that “Risk scoring may be based on one or more known risk scoring approaches, such as failure mode effects analysis, tailored to the assessment of fire risk for buildings such as structure 102. Risk scoring may take the output of the PIM (Property Ignition Model) and calculate or compute the risk that a particular property, or amount of a portfolio, may ignite. In a risk assessment, surplus heat may be the characteristic that is primarily used” (Wall, Paragraph [0253]) whereas “All failure items may be compiled into a modified Failure Mode Effect Analysis (FMEA) framework, and the relative risk of each item may be quantified in a risk priority number (see 818 in method 800)” (Wall, Paragraph [0257]). As we can recall from Claim 8, Wall also discloses the following for combining the fire score to generate and output a total fire risk in Paragraphs [0258]-[0263]:
PNG
media_image5.png
572
464
media_image5.png
Greyscale
It is evident from these aforementioned paragraphs that the hazards, described as failure items, are incorporated within the calculation for the risk scores. Furthermore, the risk score is combined into a cumulative risk score and outputted for a user to analyze further. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the method seen in Ton-That with the Wall technique of obtaining the fire hazard as well as generating and outputting a total fire risk to improve the fire risk determination method in the same way.
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Wall, and further in view of Farley (US 20230342526 A1).
Regarding Claim 14, the combination of Ton-That and Wall discloses “The method of claim 13” (Please refer to the above-described analysis for Claim 13), (Farley, Paragraph [0061]). Farley further discloses that “In the example embodiment score for each is a function of the type of issue, local topography, local weather, and topological relationships with nearby structures. Fine-scale variations in structure density, weather, wind, and topography produce a high resolution risk assessment dataset that can be used for numerous applications to wildfire prevention and preparedness. The score for each is computed using a suite of four component models, where each component model provides an independent measure of that risk’s contribution to structure ignition probability through a different potential fire pathway. For each discovery, component scores are aggregated together to create an aggregate score in the range of 0 to 100 that reflects its overall influence on community safety, regardless of parcel or other administrative boundaries. FIG. 22 illustrates an overview of an example embodiment of the risk framework and the flow of data between on-site inspection, component models, risk scores, efficiency calculation, prioritization analysis, and the API system that facilitates interaction by an end user. In the top portion of FIG. 22, an on-site inspection is performed, which generates findings of potential wildfire hazards. These findings are geolocated and augmented with a data processing module. In the right side of FIG. 22, component hazard models are used to provide measures of fire hazard according to different fire hazard pathways and create an overall risk score.” (Farley, Paragraph [0160] and Figure 22 (see below).
PNG
media_image12.png
631
476
media_image12.png
Greyscale
There are many parallels with Wall in terms of having an overall risk score, but it is important to note the fact that many of the elements associated with the fire hazard mentioned in the limitation is mentioned in these two paragraphs adjacent to the parcel boundary. By accounting for these elements, users can effectively determine what the fire hazards are within the property when using the invention. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the method seen in the combination of Ton-That and Wall with the Farley technique of accounting for fire hazard elements seen in Farley to improve the fire risk determination method in the same way. By combining the method seen in Ton-That with the Farley technique for accounting for fire hazard elements, one of ordinary skill in the art allows for a holistic overview to be made by the invention to ensure a fire hazard can be appropriately identified. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Ton-That, Wall, and Farley references to achieve the same method described in Claim 14.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Shree et al. (WO 2022165082 A1).
Regarding Claim 15, Ton-That discloses “The method of claim 1”; (Shree, Paragraph [0147]). Here, although it does not explicitly disclose a file is being interpreted as the aerial image collection, as an aerial image is within this collection while having at least two images taken of the same object that could potentially be combined to form one aerial image due to it being related to the same object. Therefore, it would have been obvious for one of ordinary skill in the art to combine the method seen in Ton-That with the technique of having a file derived from at least two images seen in Shree to have a more improved fire risk determination method. By combining the Shree technique with the method seen in Ton-That, one of ordinary skill in the art can select an aerial image that has a combination of property areas to get larger overview of various landscapes, cites, or forests when performing an analysis of wildfire risk. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Ton-That and Shree references to achieve the same method described in Claim 15.
Claims 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Sugawara et al. (JP 7345035 B1).
Regarding Claim 16, Ton-That discloses “The method of claim 1”; aerial images being aerial images of the same region as the first aerial images” (Sugawara, Abstract). Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the method seen in Ton-That with the Sugawara technique of using aerial images associated with epochs to improve the fire risk determination method in the same way.
Regarding Claim 17, the combination of Ton-That and Sugawara discloses “The method of claim 16, wherein the at least one aerial image associated with each of the at least two epochs comprises a plurality of images” (Sugawara, Paragraph [0042], discloses “The N images of the target divided area in the period before the change acquired in step S12 correspond to the first aerial photographed image in the present invention, and the images of the M target divided areas in the period after the change acquired in step S12 correspond to the first aerial photographed image in the present invention.”; Here, N images and M images are referencing a plurality of images).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Ton-That in view of Sugawara and in further view of Nayak et al. (US 20240169508 A1 w/ an EFD of November 18th, 2022).
Regarding Claim 18, the combination of Ton-That and Sugawara discloses “The method of claim 16, discloses “wherein a user may access an aerial image associated with an epoch, which is filtered by a date or a date range”. However, in an analogous field of endeavor, Nayak discloses that “the system 100 comprises a user equipment (UE) 101 that may include or be associated with an application 103. In one embodiment, the UE 101 has connectivity to the assessment platform 123 via the communication network 121. The assessment platform 123 performs one or more functions associated with assessing geospatial aerial images for image processing.” (Nayak, Paragraph [0028]). Nayak further discloses that “one or more geospatial aerial images included within the bounding zone will be referred as a subset. Each of the plurality of geospatial aerial images may indicate a region within a map and may be characterized by one or more attributes. Such attributes may be: (1) a shape of the region depicted by said geospatial aerial image; (2) dimensions of the region depicted by said geospatial aerial image; (3) a resolution of said geospatial aerial image; (4) temporal information including a timestamp, date, month, and/or year in which said geospatial aerial image was acquired; (5) light attributes of the region during the timestamp; (6) one or more weather conditions of the region during the timestamp; (7) other relevant information; or (8) a combination thereof. In one embodiment, the attributes of geospatial aerial images may be acquired by the image acquisition unit 105, one or more detection entities 113, or a combination thereof.” (Nayak, Paragraph [0038]). In both of these paragraphs, we can see the aerial images being accessed by a user via the user equipment and the aerial images being associated with an epoch (through the timestamp, date, month, and/or year the aerial image was acquired). Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the method seen in the combination of Ton-That and Sugawara with the technique for a user accessing an aerial image associated with an epoch to improve the fire risk determination method in the same way.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Hedges et al. (US 2024/0087290 w/ an EFD of June 16th, 2022) teaches a method for environmental evaluation of a property (e.g., determining a hazard score for a property).
Dillon et al. (Wildland Fire Potential: A Tool for Assessing Wildfire Risk and Fuels Management Needs) teaches of two wildland fire potential (WFP) maps created using spatial estimates of wildfire likelihood and intensity from 2012 to depict the relative potential for wildfire that would be difficult for suppression resources to contain.
Pais et al. (Deep fire topology: Understanding the role of landscape spatial patterns in wildfire occurrence using artificial intelligence) teaches a deep learning framework to estimate and predict wildfire ignition risk.
Surya (Risk Analysis Model That Uses Machine Learning to Predict the Likelihood of a Fire occurring at a Given Property) teaches an analysis and description of property fire prediction methods based on machine learning, as well as a novel machine learning algorithm for property fire risk prediction.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SORIE I KOROMA JR whose telephone number is (571)272-9259. The examiner can normally be reached Monday - Friday 8AM-6:00PM; Alternate Fridays Off.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Amandeep Saini can be reached at 571-272-3382. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SORIE I KOROMA JR/Examiner, Art Unit 2662
/AMANDEEP SAINI/Supervisory Patent Examiner, Art Unit 2662
Prosecution Insights