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 .
Claim Objections
Claims 1, 11, 13-14, 16-17 and 19 are objected to because of the following informalities:
Claims 1 and 13, the claims recite that if “the one or more performance characteristics” meet the limit, but earlier in the claim “predicted performance characteristics” was introduced. Perhaps change “the one or more performance characteristics” to “the one or more predicted performance characteristics”?;
Claim 11, “previously saved; used; or rendered viable cement compositions” is oddly written. Perhaps change to “previously saved, previously used, or previously rendered viable cement compositions”?;
Claim 14, “the one or more machine learning models” lacks proper antecedent basis since claim 13 recites only one machine learning model. Change claim 14 to refer to “the trained machine learning model” or amend claim 13 to introduce one or more machine learning models;
Claims 16 and 17, “the one or more predictive model” lacks proper antecedent basis since claim 13 recites a predictive model and the trained predictive model. Perhaps change to “the trained predictive model” or amend claim 13 to introduce one or more predictive models; and
Claim 19, “each associated at least one type of analytical data” is missing the word “with” and therefore is currently grammatically incorrect.
Appropriate corrections are required.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 1-2, 4-8 and 10-12 are rejected under 35 U.S.C. 103 as being unpatentable over Singh, U.S. Patent Application Publication No. 2021/0147305 A1 (hereinafter: ‘305), in view of FAHIM, U.S. Patent Application Publication No. 2025/0208014 A1 (hereinafter: ‘014).
As per claim 1, ‘305 in view of ‘014 discloses a method of producing a sustainable pipeline of pozzolanic materials (e.g., See ‘305; [0012], which discloses a method for identifying and categorizing silica sources and other materials for use in cement compositions) comprising:
gathering unstructured and/or structured data publicly available on a network (e.g., See ‘014; [0101 and [0381], which disclose network connected materials databases, regulatory databases, websites, and Internet services, and acquiring an unstructured construction material document for processing);
identifying analytical data of a pozzolanic material using one or more machine learning models, wherein the analytical data is present within at least the unstructured and/or structured data (e.g., See ‘305; [0039], which discloses physicochemical properties of a cement component including fly ash, and also See ‘014; [0393] and [0394], which disclose using AI or machine learning to identify content in the construction material document, including fly ash and measured construction material properties);
extracting the analytical data from the unstructured and/or structured data (e.g., See ‘014; [0381], which discloses extracting the identified content from the unstructured construction material document);
predicting, using one or more predictive models, one or more performance characteristics of the pozzolanic material based at least in part on the analytical data, to form one or more predicted performance characteristics (e.g., See ‘305; [0038], which discloses using data concerning the physicochemical properties to predict cement slurry properties and blend mechanical properties);
comparing the predicted one or more performance characteristics to one or more minimum acceptable performance characteristics (e.g., See ‘305; [0129] and [0130], which disclose a predictive cement algorithm that uses required engineering parameters, and outputs one or more predicted material properties, and generates a cement slurry that conforms to the engineering parameters);
storing the extracted analytical data and the one or more predicted performance characteristics in a database if the one or more performance characteristics meets or exceeds the minimum acceptable performance characteristic (e.g., See ‘305; [0128] -[0130] and ‘014; [0381], which collectively disclose storing raw physicochemical data and predictive models in a predictive model database, adding the cement slurry that conforms to the engineering parameters to the predictive model database, and storing the extracted content in remote database); and
preparing a cement composition comprising the pozzolanic material if the predicted one or more performance characteristics meets or exceeds the one or more minimum acceptable performance characteristics (e.g., See ‘305; [0063] and [0112], which disclose generating a cement composition to meet a desired compressive strength and preparing the cement slurry based on the cement composition).
Although ‘014 discloses websites, regulatory databases, search engines, and other Internet sources, ‘014 does not specifically disclose that the gathered construction material information is publicly available. However, it would have been obvious to one of ordinary skill in the art at the time the invention was made to use publicly available sources because they would provide readily accessible construction material information for collection and processing without requiring access to a private data source.
Further, although ‘305 and ‘014 disclose storing the raw physicochemical data, the cement slurry, and the extracted content, they do not specifically disclose storing the predicted material properties with the extracted content when the engineering requirements are met. However, it would have been obvious to one of ordinary skill in the art at the time the invention was made to store the predicted material properties with the extracted content because retaining the information associated with a conforming cement slurry would preserve the data used for future calculations, as described by ‘305 (e.g., See [0130]).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to incorporate the teachings of ‘014 into ‘305 for the purpose of supplying ‘305’s predictive system with automatically identified and extracted construction material data, thereby reducing manual data preparation and increasing available input data.
As per claim 2, ‘305 in view of ‘014 further discloses that the unstructured and/or structured data comprises documentation containing analytical and/or performance information relating to one or more pozzolanic materials (e.g., See ‘014;[0394], which discloses a Mix Certificate containing fly ash and performance information including design strength and measured slump for the construction material containing the fly ash).
As per claim 4, ‘305 in view of ‘014 further discloses that the one or more machine learning models comprise a convolutional neural network (e.g., See ‘014; [0405], which discloses convolutional neural networks capable of ingesting data from unstructured construction material documents).
As per claim 5, ‘305 in view of ‘014 further discloses that the analytical data comprises specific surface area as an analytical property (e.g., See ‘305; [0052], which discloses specific surface area as a physicochemical property of a cement component).
As per claim 6, ‘305 in view of ‘014 further discloses that the one or more predictive models comprise one or more deterministic equations (e.g., See ‘305; [0058] – [0059], which disclose a multilinear regression model expressed using equations based on measurable physical properties of a cement component).
As per claim 7, ‘305 in view of ‘014 further discloses that the one or more predictive models comprise one or more machine learning models (e.g., See ‘014; [0252], which discloses one or more artificial neural network algorithms trained to determine concrete performance from mixture characteristics and external conditions).
As per claim 8, ‘305 in view of ‘014 further discloses that the machine learning models are trained to predict performance based on historical cement performance data (e.g., See ‘014; [0195], [0252] and [0255], which disclose storing cement performance data, training one or more artificial neural network algorithms using acquired data to determine concrete performance, and using acquired material performance data from previous deployments).
As per claim 10, ‘305 in view of ‘014 further discloses that at least one of the one or more predictive models is built using a random forest (e.g., See ‘014; [0252], which discloses random forests as a machine learning approach for determining concrete performance).
As per claim 11, ‘305 in view of ‘014 further discloses that the one or more predictive models is trained on a dataset comprising material performance data (e.g., See ‘014; [0252] and [0255], which disclose training a machine learning model using acquired data and acquired material performance data from previous deployments).
As per claim 12, ‘305 in view of ‘014 further discloses that the one or more predicted performance characteristics comprise Young's modulus as at least one cement performance characteristic (e.g., See ‘305; [0047] and [0057], which disclose Young’s modulus as a mechanical property of a cement composition and predicting Young’s modulus using correlations).
Claims 13-18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Singh, U.S. Patent Application Publication No. 2021/0147305 A1 (hereinafter: ‘305), in view of FAHIM, U.S. Patent Application Publication No. 2025/0208014 A1 (hereinafter: ‘014), in further view of Platt, U.S. Patent Application Publication No. 2024/0119202 A1 (hereinafter: ‘202).
As per claim 13, ‘305 in view of ‘014, in further view of ‘202 discloses a method of producing a sustainable pipeline of pozzolanic materials (e.g., See ‘305; [0012], which discloses a method for identifying and categorizing silica sources and other materials for use in cement compositions) comprising:
training a machine learning model to recognize pozzolanic materials within a document to form a trained machine learning model (e.g., See ‘014; [0381] and [0394], and ‘202; [0033], which collectively disclose training a machine learning system using construction material documents and using machine learning text mining to identify a building material, including document content identifying fly ash);
training a predictive model to predict a pozzolan performance characteristic, to form a trained predictive model (e.g., See ‘305; [0038], and ‘014[ [0252], which collectively disclose using material data to predict cement performance and training a predictive model to make the prediction);
gathering unstructured and/or structured data publicly available on a network with a web-crawler and converting the unstructured data to structured data (e.g., See ‘202; [0041], and ‘014; [0380] and [0405], which collectively disclose using a web crawler to obtain a construction material document from a network and organizing unstructured construction material data into structured data for processing and storage);
identifying analytical data of a pozzolanic material using the trained machine learning model, wherein the analytical data is present within at least the structured data (e.g., See ‘305; [0039], which discloses physicochemical properties of a cement component including fly ash, and also See ‘014; [0393] and [0394], which disclose using AI or machine learning to identify content in the construction material document, including fly ash and measured construction material properties);
extracting the analytical data from the structured data (e.g., See ‘202; [0039], which discloses selecting material parameters from structured data stored in the system, including parameters extracted from previously unstructured text);
predicting, using the trained predictive model, one or more performance characteristics of the pozzolanic material based at least in part on the analytical data, to form one or more predicted performance characteristics (e.g., See ‘305; [0038], which discloses using data concerning the physicochemical properties to predict cement slurry properties and blend mechanical properties);
comparing the predicted one or more performance characteristics to one or more minimum acceptable performance characteristics (e.g., See ‘305; [0129] and [0130], which disclose a predictive cement algorithm that uses required engineering parameters, and outputs one or more predicted material properties, and generates a cement slurry that conforms to the engineering parameters);
storing the extracted analytical data and the one or more predicted performance characteristics in a database if the one or more performance characteristics meets or exceeds the minimum acceptable performance characteristic (e.g., See ‘305; [0128] -[0130] and ‘014; [0381], which collectively disclose storing raw physicochemical data and predictive models in a predictive model database, adding the cement slurry that conforms to the engineering parameters to the predictive model database, and storing the extracted content in remote database); and
preparing a cement composition comprising the pozzolanic material if the predicted one or more performance characteristics meets or exceeds the one or more minimum acceptable performance characteristics (e.g., See ‘305; [0063] and [0112], which disclose generating a cement composition to meet a desired compressive strength and preparing the cement slurry based on the cement composition).
Although some of the references disclose websites, Internet or network sources, and database sources for obtaining construction material or building material information, none of the references specifically disclose that the gathered information is publicly available. However, it would have been obvious to one of ordinary skill in the art at the time the invention was made to use publicly available sources because they would provide readily accessible material information for collection and processing without requiring access to a private data source.
Further, although some of the references disclose storing the raw physicochemical data, the cement slurry, and the extracted content, they do not specifically disclose storing the predicted material properties with the extracted content when the engineering requirements are met. However, it would have been obvious to one of ordinary skill in the art at the time the invention was made to store the predicted material properties with the extracted content because retaining the information associated with a conforming cement slurry would preserve the data used for future calculations, as described by ‘305 (e.g., See [0130]).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to incorporate the teachings of ‘014 into ‘305 for the purpose of supplying ‘305’s predictive system with automatically identified and extracted construction material data, thereby reducing manual data preparation and increasing available input data.
Further, it would have been obvious to one of ordinary skill in the art at the time the invention was made to incorporate the teachings of ‘202 into ‘305 as modified by ‘014 for the purpose of automatically locating construction material documents on network sources, identifying material information with the documents, and supplying structured material information from those documents to the predictive system, thereby reducing manual document collection and data preparation and increasing the amount of usable material data available for analysis.
As per claim 14, ‘305 in view of ‘014, in further view of ‘202 discloses that the one or more machine learning models comprise a convolutional neural network (e.g., See ‘014; [0405], which discloses convolutional neural networks capable of ingesting data from unstructured construction material documents).
As per claim 15, ‘305 in view of ‘014, in further view of ‘202 discloses that the one or more predictive models is trained on a dataset comprising material performance data (e.g., See ‘014; [0252] and [0255], which disclose training a machine learning model using acquired data and acquired material performance data from previous deployments).
As per claim 16, ‘305 in view of ‘014, in further view of ‘202 discloses that the one or more predictive models comprise at least one algorithm type that is represented by multilayer perceptron’s (e.g., See ‘014; [0261], which discloses a multilayer perceptron machine learning algorithm training historical strength and construction material composition data).
As per claim 17, ‘305 in view of ‘014, in further view of ‘202 discloses that at least one of the one or more predictive models is built using a random forest (e.g., See ‘014; [0252], which discloses random forests as a machine learning approach for determining concrete performance).
As per claim 18, ‘305 in view of ‘014, in further view of ‘202 discloses that the one or more predictive models comprise one or more deterministic equations (e.g., See ‘305; [0058] – [0059], which disclose a multilinear regression model expressed using equations based on measurable physical properties of a cement component).
As per claim 20, ‘305 in view of ‘014, in further view of ‘202 discloses that the analytical data comprises specific surface area as an analytical property (e.g., See ‘305; [0052], which discloses specific surface area as a physicochemical property of a cement component).
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Singh, U.S. Patent Application Publication No. 2021/0147305 A1 (hereinafter: ‘305), in view of Fahim, U.S. Patent Application Publication No. 2025/0208014 A1 (hereinafter: ‘014), as applied to claim 1, from above, in further view of Chapdelaine, U.S. Patent Application Publication No. 2022/0355509 A1 (hereinafter: ‘509).
As per claim 3, although ‘014, of ‘305 in view of ‘014, discloses converting unstructured construction material data to structured data and storing the extracted data in a database, ‘014 does not specifically disclose that the gathering and storing both occur on at least a semi-continuous basis.
‘509 the missing feature by disclosing truck and in drum sensors sending data through a cloud network to a central database to continuously provide new raw data, and continuously acquiring new truth data (e.g., See ‘509; [0092]).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to incorporate the teachings of ‘509 into ‘305 in view of ‘014 for the purpose of gathering and storing construction material data on an ongoing basis as new data becomes available, thereby maintaining a current and growing data set for predictive analysis.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Singh, U.S. Patent Application Publication No. 2021/0147305 A1 (hereinafter: ‘305), in view of FAHIM, U.S. Patent Application Publication No. 2025/0208014 A1 (hereinafter: ‘014), as applied to claim 1, from above, in further view of Hennessy, U.S. Patent Application Publication No. 2010/0153323 A1 (hereinafter: ‘323).
As per claim 9, ’305 in view of ‘014 does not specifically disclose that the one or more machine learning models comprise an ensemble of machine learning models, each associated at least with identity and/or concentration of at least one of the one or more pozzolanic materials.
‘323 discloses this missing feature by disclosing an ensemble of machine learning models in which individual models independently analyze material spectral data and predict the presence or concentration of a target material (e.g., See ‘323; [0129], [0137] and [0142] – [0144]).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to incorporate the teachings of ‘323 into ‘305 in view of ‘014 for the purpose of using multiple machine learning models to analyze measured material data and determine material identity or concentration, thereby making the material identification and concentration results more reliable.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Singh, U.S. Patent Application Publication No. 2021/0147305 A1 (hereinafter: ‘305), in view of FAHIM, U.S. Patent Application Publication No. 2025/0208014 A1 (hereinafter: ‘014), in view of Platt, U.S. Patent Application Publication No. 2024/0119202 A1 (hereinafter: ‘202), in further view of Hennessy, U.S. Patent Application Publication No. 2010/0153323 A1 (hereinafter: ‘323).
As per claim 19, ’305 as modified by ‘014 and ‘202, does not specifically disclose that the one or more machine learning models comprise an ensemble of machine learning models, each associated at least with identity and/or concentration of at least one of the one or more pozzolanic materials.
‘323 discloses this missing feature by disclosing an ensemble of machine learning models in which a separate model is built for each spectral attribute of the analytical data (e.g., See ‘323; [0112] and [0129] – [0131]).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to incorporate the teachings of ‘323 into ‘305, as modified by ‘014 and ‘202, for the purpose of using multiple machine learning models to analyze different types of material data, thereby making the analytical results more reliable.
References Considered but Not Relied Upon
The following references were considered but were not relied upon with respect to any prior art rejections:
(1) US 2022/0253734 A1, which discloses using machine learning and material data to predict and optimize cement and concrete formulations;
(2) US 2023/0416164 A1, which discloses using material properties and machine learning to predict concrete performance and select mixtures meeting performance targets;
(3) US 2023/0193720 A1, which discloses using cement test data and machine learning to predict properties, validate results, and store acceptable cement data;
(4) US 2021/0033553 A1, which discloses collecting concrete performance data and using machine learning to assess properties and improve concrete mixtures;
(5) US 2024/0296265 A1, which discloses using material inventories, design requirements, test databases, and machine learning to design and prepare cement compositions.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RONALD D HARTMAN JR whose telephone number is (571)272-3684. The examiner can normally be reached M-F 8:30 - 4:30 EST.
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, Mohammad Ali can be reached at (571) 272-4105. 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.
/RONALD D HARTMAN JR/Primary Patent Examiner, Art Unit 2119 October 3, 2026
/RDH/
Prosecution Insights