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 .
Status of Claims
The following final office action in response to the communications received 6/24/2026. Claims 1 and 5 have been amended. Claim 21 has been added. Claims 1-15 and 21 are pending.
Response to Arguments
Applicant’s arguments on page 8 with respect to the 35 U.S.C. § 101 rejection, specifically regarding step 2A prong 2, have been fully considered and are persuasive. The 35 U.S.C. § 101 rejections have been withdrawn.
Applicant’s arguments with regards to the 35 U.S.C. § 103 rejections have been fully considered. A further search has been performed and the 35 U.S.C. § 103 rejection has been updated to include Carrington (US 2023/0098595), as necessitated by amendment.
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.
Claims 1-9 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Fink et al. (US 2024/0111927) in view of Carrington (US 2023/0098595) in further view of Cantwell et al. (WO 2021/174060).
As per claim 1, Fink et al. teaches a method comprising:
causing presentation, by communications hardware, of a builder project management user interface (UI) (See paragraphs 37, 56, 92, where a user interface is presented. See also figures 2 and 9);
receiving, by the communications hardware, a blueprint dataset for a structure (See at least paragraphs 22, 29, and 40, where blueprint information for a structure is received);
classifying, by classifier circuitry and using a classifier model, portions of the blueprint dataset (See at least paragraphs 28, 31, 33, 45, 66, where blueprints are provided to a machine learning model such as a neural network where information is extracted and classified);
processing, by a processor and using trained models, aspects of the blueprint dataset (See at least paragraphs 22, 33, 45, where a trained model is used to process aspects extracted from the blueprints);
generating, by modeling circuitry and using one or more models, digitized feature datasets for the classified portions of the blueprint dataset (See at least paragraphs 28, 31, 33, 41, 52, and 60, where information and blueprint data is digitized);
compiling, by an engine and based on the digitized feature datasets, one or more material pack datasets (See paragraphs 27, 95-96, and 104, where data representing materials needed for building a portion of a structure are compiled from the information and shown as an inventory list on a screen);
causing presentation, by the communications hardware, of a visual representation of the one or more material pack datasets via the builder project management UI (See at least paragraphs 27, 30, 95-96, and 104, where data representing materials needed for building a portion of a structure are compiled from information and shown as an inventory list on a screen).
While Fink et al. teaches generating digitized feature datasets for the classified portions of the blueprint dataset, Fink et al. does not teach and Carrington teaches:
classifying, by classifier circuitry and using a classifier model, portions of the blueprint dataset into a plurality of portions corresponding to different portion types of the structure (See at least paragraphs 2, 20, 32, 35, where a second machine learning model, which can be a classifier, is used to determine a type for a portion of a blueprint document. The model distinguishes between different types of plans);
processing, by a processor and using each of a plurality of independently trained models, a respective diagram of the blueprint dataset corresponding to the respective portion type of the independently train model to detect features in the respective diagram (See at least paragraphs 35, 37, 38, 47, where different pages may have different plans and portions of different types. Machine learning models of different types are implemented and selected based on the type of plan, and multiple types of plans are included such that multiple models are used. See specifically paragraphs 37 and 47);
generating, by modeling circuitry and using the plurality of independently trained models, digitized feature datasets for the classified portions of the blueprint dataset based on an output of the processing, wherein each of the plurality of independently trained models is independently trained to recognize and label features and to determine measurements and sizing information for the respective portion type, and further wherein the digitized feature datasets generated by each independently trained model collectively form a complete digitized plan for the structure (See paragraphs 31, 37-38, 47-48, 56, where produced digitized data sets include recognized features and elements and applied labels. Measurement and sizing (Heights, positions, locations, size) are determined as well as other information for the overall plan);
Carrington further discloses indicating materials for elements in the portions of the blueprints (See at least paragraphs 37, 39, 48).
Both Fink et al. and Carrington are in the field of building and construction and involve processing blueprints and construction documents about a structure to extract information using trained models. It would have been obvious to one of ordinary skill in the art before the effective filing date to include the specific techniques taught by Carrington to classify, process and generate information from blueprints and construction documents in the system of Fink et al. in order to increase the accuracy of identified types and/or information by dividing the analysis across multiple models. See paragraph 56 of Carrington.
Further, Fink et al. teaches compiling, based on the digitized feature datasets, one or more material pack datasets using vendor specifications and information that includes any information that is relevant to the structure being constructed, pursuant to blueprints, such as inventory lists of various supplies, and building materials (See paragraph 30). However, Fink et al. does not explicitly generate the one or more material pack datasets by a material calculation engine.
Cantwell specifically discloses generating the one or more material pack datasets by a material calculation engine (See paragraphs 98-104, with emphasis on paragraphs 101-103. A material takeoff is generated using the computer, that includes quantities and a materials list).
Fink et al., Carrington and Cantwell et al. are concerned with converting and extracting information from images in the construction space. Fink et al. extracts and compiles information about materials needed as an inventory list. Additionally, Carrington indicates materials for items and elements when processing the blueprints. Cantwell et al. specifically discusses generating a materials pack using the computer system. It would have been obvious before the effective filing date of the invention to include the specifics of generating the materials pack from Cantwell et al. in the system of Fink et al. (and the combination of Fink et al. and Carrington) in order to more efficiently and effectively generate material takeoffs with lists of materials that are more accurate and reflect adjustments. See paragraphs 101-103 of Cantwell et al.
Per claim 2, Fink et al. teaches the method of claim 1, further comprising:
pre-processing, by input analysis circuitry, the blueprint dataset prior to classifying the portions of the blueprint dataset (See at least paragraphs 31, 43, 46, 67, and 79 which process the file type of the blueprints).
Per claim 3, Fink et al. teaches the method of claim 2, wherein pre-processing the blueprint dataset comprises:
converting, by the input analysis circuitry, the blueprint dataset from a first file format to a second file format (See at least paragraphs 31, 43, 46, 67, and 79 which process the file type of the blueprints).
Per claim 4, Fink et al. teaches the second file format comprises a rasterized image file format (See paragraphs 68-69, disclosing a higher resolution image with pixels/elements. All images defined by pixels are considered raster images). While not relied upon, please also see paragraph 29 of Carrington and paragraphs 97, 102-103 of Cantwell et al.
Per claim 5, Fink et al. teaches the method of claim 1, further comprising:
receiving, by the communications hardware and prior to generating the one or more material pack datasets, one or more updated digitized feature datasets (See paragraphs 33 and 45, where results are received); and
causing, by the modeling circuitry, re-training of at least one of the models based on the updated digitized feature datasets (See paragraphs 33 and 45, where the results are fed back into the initially trained model to retrain and enhance subsequent classifications),
wherein the one or more material pack datasets are compiled based further on the one or more updated digitized feature datasets (See paragraph 30).
Fink et al. teaches retraining models based on the updated digitized feature datasets, but does not explicitly disclose a plurality of independent models.
As discussed above, Carrington teaches a plurality of independent models (See at least paragraphs 35, 37, 38, 47, 56, where machine learning models of different types are implemented based on the type of plan, and multiple plan types are included thus using multiple models).
Both Fink et al. and Carrington are in the field of building and construction, and involve processing blueprints and construction documents about a structure to extract information using trained models. It would have been obvious to one of ordinary skill in the art before the effective filing date to include the specific techniques taught by Carrington in the system of Fink et al. in order to increase the accuracy of identified types and/or information by dividing the analysis across multiple models. See paragraph 56 of Carrington.
Neither Fink et al. or Carrington disclose and Cantwell specifically discloses generating the one or more material pack datasets by a material calculation engine (See paragraphs 98-104, with emphasis on paragraphs 101-103. A material takeoff is generated using the computer, that includes quantities and a materials list).
Fink et al., Carrington, and Cantwell et al. are concerned with converting and extracting information from images in the construction space. Finks et al. extracts and compiles information about materials needed as an inventory list. Carrington indicates materials for items and elements when processing the blueprints. Cantwell et al. specifically discusses generating a materials pack using the computer system. It would have been obvious before the effective filing date of the invention to include the specifics of generating the materials pack from Cantwell et al. in the system of Fink et al. and Carrington in order to more efficiently and effectively generate material takeoffs with lists of materials that are more accurate and reflect adjustments. See paragraphs 101-103 of Cantwell et al.
Per claim 6, Fink et al. teaches the method of claim 5, wherein a respective material pack dataset comprises data representing materials needed for building a portion of the structure associated with a respective digitized feature dataset (See at least paragraphs 27, 30, 95-96, and 104, where data representing materials needed for building a portion of a structure are shown).
Per claim 7, Fink et al. discloses a method of claim 1, further comprising:
generating, by three-dimensional modeling circuitry, a three-dimensional (3D) model of the structure based on the digitized feature datasets (See paragraphs 24, 35, 46, 54, where a 3D model is generated from the data extracted from the blueprint); and
causing presentation, by the communications hardware, of the 3D model of the structure via the builder project management UI (See paragraphs 88, 100, and 101, where the 3D model is presenting in the interface. See also figure 6).
As per claim 8, Fink et al. teaches wherein the digitized feature datasets comprise line and measurement data for respective portions of the blueprint dataset (See paragraphs 67, 69-70, 75, 94, wherein data is extracted from the blueprints including scale, line and measurement).
As per claim 9, Fink et al. and Carrington do not expressly disclose and Cantwell discloses wherein generating the one or more material pack datasets comprises:
determining, by the material calculation engine and using one or more optimized subroutines, an optimal amount of material needed for a respective portion of the structure based on the line and measurement data (See paragraphs 102-104, 106 that discloses techniques for increasing accuracy in amounts through more accurate dimension determination).
Fink et al., Carrington, and Cantwell et al. are concerned with converting and extracting information from images in the construction space. Finks et al. extracts and compiles information about materials needed as an inventory list, and extracts data from blueprints including scale, line and measurement. Cantwell et al. specifically discusses generating a materials pack using the computer system, and further increased accuracy in determining dimensions so that enhanced and context-rich takeoffs can be generated. It would have been obvious before the effective filing date of the invention to include the enhanced and context-rich takeoffs and the more accurate dimensions of Cantwell et al. in the system of Fink et al. and Carrington in order to increase accuracy and better validate information for quicker, higher quality, and improve services. See paragraphs 104 and 106 of Cantwell et al.
As per claim 21, Fink et al. further comprises: generating, by multi-dimensional modeling circuitry, a multi-dimensional model of the structure based on the digitized feature datasets (See at least paragraphs 46 where a digital, virtual model of the structure is rendered in a three-dimensional view); and causing presentation, by the communications hardware, of the multi-dimensional model of the structure via the builder project management UI (see figure 6, 57, 61, 88, 100, where the digital, virtual model is interactive and presented on a user interface). While not relied upon, see at least paragraph 38 of Carrington.
Claims 10-13 are rejected under 35 U.S.C. 103 as being unpatentable over Fink et al. (US 2024/0111927) in view of Carrington (US 2023/0098595) in view of Cantwell et al. (WO 2021/174060) and in further view of Bradt et al. (WO 01/67346).
As per claim 10, neither Fink et al., Carrington, nor Cantwell et al. disclose, and Bradt et al. discloses:
assigning, by the material calculation engine and for a respective digitized feature set, a base stock keeping unit (SKU) to each material needed for building a portion of the structure (See page 11, lines 10-12, page 39, lines 20-24, and page 41, lines 23-27, wherein SKU are assigned to materials. See also figure 25); and
mapping, by the material calculation engine, the base SKU to one or more supplier SKUs based on a user preference set (See page 11, lines 10-12, page 39, lines 20-24, page 40, lines 5-11 and 17-27, and page 41, lines 23-27, where the supplier has the power to manage its product catalog including details such as the stock keeping units (SKU) and the ability to set preferred pricing per customer based upon volume or other factors. Availability is able to be determined and price can be set or varied based upon particularly agreements or arrangements with certain builders or similar customers).
Fink et al., Carrington, and Cantwell et al. are combined for the reasons set forth above with respect to claim 1. Bradt et al. also discloses homebuilders and construction, and the use of floor plans / construction documents to determine materials that will be used in construction. It would have been obvious to one of ordinary skill in the art before the effective filing date to include the particulars of Bradt’s ordering and scheduling management systems and interfaces, including the use of SKUs, in the construction management system of Fink et al. which includes purchasing links with vendor information and automatically ordering supplies, as combined with Carrington and Cantwell et al., in order to allow the user to more efficiently manage orders associated with the construction project. See for example abstract and page 11 of Bradt et al.
As per claim 11, Fink et al. teaches the method of claim 1, further comprising: Providing purchasing links with vendor information to allow for automated ordering and quick access to construction plans, inventory lists, and other vendor/contractor specifications or information (See paragraphs 95-96 and 106). Cantwell et al. discloses the concept of price and formatting a bid (see at least paragraphs 97-99).
However, neither reference, nor Carrington, explicitly discloses and Bradt discloses applying, by supplier bid circuitry, pricing information to the one or more material pack datasets based on supplier inventory data (See page 11, lines 1-12, page 40, lines 5-11 and 17-27, where the supplier has the power to manage its product catalog including details such as the stock keeping units (SKU) and the ability to set preferred pricing per customer based upon volume or other factors. Availability is able to be determined and price can be set or varied based upon particularly agreements or arrangements with certain builders or similar customers).
Fink et al., Carrington, and Cantwell et al. are combined for the reasons set forth above with respect to claim 1. Bradt et al. also discloses homebuilders and construction, and the use of floor plans / construction documents to determine materials that will be used in construction. It would have been obvious to one of ordinary skill in the art before the effective filing date to include the particulars of Bradt’s ordering and scheduling management systems and interfaces, including the use of pricing information from the supplier, in the construction management system of Fink et al., which includes purchasing links with vendor information and automatically ordering supplies, as combined with Carrington and Cantwell et al., in order to allow the user to more efficiently manage orders associated with the construction project. See for example abstract and page 11 of Bradt et al.
As per claim 12, Fink et al. teaches the method of claim 11, further comprising providing purchasing links with vendor information and automatically ordering supplies based on status information (See paragraphs 95-96 and 106). However, none of Fink et al., Carrington, or Cantwell et al. disclose, and Bradt et al. discloses:
receiving, by the communications hardware, a user order indication of at least one material pack dataset via the builder project management UI, wherein the user order indication comprises a requested delivery date (see figure 23, page 37, line 25-page 38, line 4, wherein an order is received in the system);
executing, by ordering circuitry, an order of materials associated with the at least one material pack dataset (See page 37, lines 13-24);
scheduling, by a scheduling engine, a delivery of the order of materials based at least on the requested delivery date (See abstract; figure 23, page 38, lines 5-10, where information includes requested delivery);
causing presentation, by the communications hardware, of a visual representation of an order status for the at least one material pack dataset. (Figures 24 and 25, page 38, lines 12-20 and line 28-page 39, line 5, where and order detail page is presented including an order status).
Fink et al., Carrington, and Cantwell et al. are combined as set forth above with respect to claim 1. Bradt et al. also discloses homebuilders and construction, and the use of floor plans / construction documents to determine materials that will be used in construction. It would have been obvious to one of ordinary skill in the art before the effective filing date to include the particulars of Bradt’s ordering and scheduling management systems and interfaces, including tracking order status, in the construction management system of Fink et al., which includes purchasing links with vendor information and automatically ordering supplies, as combined with Carrington and Cantwell et al., in order to allow the user to more efficiently manage orders associated with the construction project. See for example abstract and page 11 of Bradt et al.
As per claim 13, neither Fink et al. nor Cantwell et al. disclose, and Bradt et al. discloses wherein causing presentation of the visual representation of the one or more material pack datasets via the builder project management UI comprises simultaneously displaying order statuses of the one or more material pack datasets within the builder project management UI (See figures 25, 26, 28, where the order status of each material pack is displayed along with what has been ordered and shipped).
Fink et al., Carrington, and Cantwell et al. are combined for the reasons set forth above. Bradt et al. also discloses homebuilders and construction, and the use of floor plans / construction documents to determine materials that will be used in construction. It would have been obvious to one of ordinary skill in the art before the effective filing date to include the particulars of Bradt’s ordering and scheduling management systems and interfaces, including display of order statuses, in the construction management system of Fink et al., which includes purchasing links with vendor information and automatically ordering supplies, as combined with Carrington and Cantwell et al., in order to allow the user to more efficiently manage orders associated with the construction project. See for example abstract and page 11 of Bradt et al.
Claims 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Fink et al. (US 2024/0111927) in view of Carrington (US 2023/0098595) in view of Cantwell et al. (WO 2021/174060) in view of Bradt et al. (WO 01/67346) and in further view of Adesh (US 2023/0394400).
As per claim 14, Fink discloses materials associated with one or more material pack datasets based on the blueprint dataset and builder profile information associated with the received blueprint dataset (See paragraphs 27, 95-96, and 104). However, none of Fink et al., Carrington, or Cantwell et al. disclose generating, by a scheduling engine, a delivery schedule for materials.
Bradt et al. discloses generating a delivery schedule for materials (See abstract; figure 23, page 38, lines 5-10, where information includes requested delivery) but does not explicitly disclose a generating, by a scheduling engine, a recommended delivery schedule for materials.
Adesh et al. discloses generating, by a scheduling engine, a recommended delivery schedule for materials (See at least abstract, paragraphs 79 and 88, where weather risks impact scheduling recommendations).
Fink et al., Carrington, Cantwell et al. and Bradt et al. are analogous because they all involve the homebuilding and construction space as well as determining and acquiring needed materials. Bradt et al. specifically includes order management systems and interfaces for managing and scheduling material delivery. Adesh et al. discloses risk and impact to scheduling related to weather. It would have been obvious to one of ordinary skill in the art before the effective filing date to include the scheduling risks, such as weather, of Adesh et al. when scheduling delivery dates in Bradt et al. in order to efficiently complete a series of tasks and manage the workflow and supplies of construction jobs in a cost-effective manner by scheduling tasks and delivery of materials using a variety of job reports. See at least abstract of Bradt et al.
As per claim 15, none of Fink et al., Carrington or Cantwell et al. disclose the recommended delivery schedule is generated based further on one or more parameters, the parameters including: forecasted weather data, regional building practice and code information, calendar event data, supplier restriction data, and builder restriction data.
Bradt et al. discloses generating a delivery schedule for materials (See abstract; figure 23, page 38, lines 5-10, where information includes requested delivery) but does not explicitly disclose a recommended delivery schedule generated based further on one or more parameters, the parameters including: forecasted weather data, regional building practice and code information, calendar event data, supplier restriction data, and builder restriction data.
Adesh et al. discloses the parameters including: forecasted weather data, (See at least abstract, paragraphs 79 and 88, where weather risks impact scheduling recommendations).
Fink et al., Carrington, Cantwell et al. and Bradt et al. are analogous because they all involve the homebuilding and construction space as well as determining and acquiring needed materials. Bradt et al. specifically includes order management systems and interfaces for managing and scheduling material delivery. Adesh et al. discloses risk and impact to scheduling related to weather. It would have been obvious to one of ordinary skill in the art before the effective filing date to include the scheduling risks, such as weather, of Adesh et al. when scheduling delivery dates in Bradt et al. in order to efficiently complete a series of tasks and manage the workflow and supplies of construction jobs in a cost-effective manner by scheduling tasks and delivery of materials using a variety of job reports. See at least abstract of Bradt et al.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Cetintas et al. (US 2023/0394729) discloses determining rooms in a CAD drawing of a building using machine learning algorithms.
Caamano et al. (US 2023/0206557) teaches using multi-dimensional models on received images (such as blueprints) and classifying architectural element types.
Lee et al. (US 2024/0061967) teaches classifying elements in construction or architectural drawings using training and AI modules.
Martindale (US 2025/0272655) teaches machine learning techniques in construction including classifying a construction document and generating a bill of materials associated with the project.
Wang et al. (US 2024/0428351) discloses detecting and classifying construction elements in construction drawings using AI.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BETH V BOSWELL whose telephone number is (571)272-6737. The examiner can normally be reached M-F 8AM - 4:30PM.
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, Tariq Hafiz can be reached at (571) 272-5350. 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.
/BETH V BOSWELL/ Supervisory Patent Examiner, Art Unit 3625
Prosecution Insights