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 .
Response to Arguments
The amendment filed 2/26/2026 has been entered. Claims 1-2, 4-10, and 12-20 remain pending in the application. Claims 1, 5, and 16 have been amended.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 4-5, 8, 12-16, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Anderson et al. (US 20210105931 A1) in view of Chandra et al. (US 20200110170 A1).
Regarding claim 1, Anderson discloses an agricultural machine (Fig. 3, system 10) comprising: a frame (Fig. 3, vehicle 20) configured to be coupled to a tool such that the tool performs an agricultural operation on a field as the agricultural machine travels across the field ([0056]); a transceiver-based sensor (Fig. 3, sensor 22/26) configured to emit an output signal directed toward soil within a portion of the field and receive an echo signal indicative of a backscattering of the output signal by the soil ([0046], sensor 22/26 comprises a ground penetrating radar); and a computing system (Fig. 3, computer 28; [0033], onboard laptop computer) communicatively coupled to the transceiver-based sensor ([0043], computer 28 communicatively couples to the at least one sensor 22,26), the computing system including one or more processors (Fig. 3, computer 28) and one or more non- transitory computer-readable media ([0065], memory device 514; [0115], the program code may execute entirely on the user's computer) that collectively store a machine-learned model configured to receive input data ([0033], machine learning protocols; Fig. 10), and instructions that, when executed by the one or more processors, configure the computing system to perform operations ([0066], memory device 514 may store program code and instructions), the operations comprising: receiving data from the transceiver-based sensor as the agricultural machine travels across the field (Fig. 6, Block 604); extracting a set of features (Fig. 9, Block 904) associated with the echo signal from the received data ([0046]); inputting the set of features into the machine-learned model (Fig. 10, input data 1004 provided to the model); receiving an output of the machine-learned model (Fig. 10, model output data 1010); and adjusting an operating parameter of the agricultural machine based on the final moisture value ([0053 & 0055], vary the tilling depth based on the tillage prescription plan). This tilling prescription plan is taught to be based on characteristics of the soil ([0016]), including detected soil moisture ([0044]).
Anderson does not explicitly disclose that the machine-learned model is configured to process the input data to determine a preliminary soil moisture value for the input data. Anderson additionally does not disclose that, in the operation of the method, the output of the machine-learned model is the preliminary soil moisture value for the set of features inputted, and that the operation further comprises determining a final soil moisture value for the portion of the soil within the field based on the preliminary soil moisture value and one or more correction factors based on at least one of a soil type of the field or a weather condition.
In the same field of endeavor, Chandra teaches operations involving a machine-learned model that is configured to process the input data to determine a preliminary soil moisture value for the input data ([0116], machine learning model estimates permittivity as the preliminary soil moisture value). These operations comprise receiving the preliminary soil moisture value for the set of features as an output of the machine-learned model ([0116], machine learning model estimates permittivity as the preliminary soil moisture value); and determining a final soil moisture value for the portion of the soil within the field based on the preliminary soil moisture value and one or more correction factors based on at least one of a soil type of the field, a time of year, a crop growing in the field, or a weather condition ([0038] and [0042], initial permittivity value of the soil, i.e. preliminary soil moisture value, is fit onto a water content-permittivity model “for that soil type to estimate the water content” and soil moisture).
It would have been obvious to one of ordinary skill in the art at the effective date of filing to modify Anderson with the inclusion of the models and analysis based on soil type for the motivation of obtaining a more accurate soil moisture estimate as Chandra teaches that the accuracy of soil moistures is important to various aspects of agriculture ([0001-0002]).
Regarding claim 4, Anderson further discloses that the transceiver-based sensor is configured to emit a microwave output signal directed toward the soil within the portion of the field ([0046], GPR can operate at the frequency range of a microwave signal, which is 300 MHz to 300 GHz).
Regarding claim 5, Anderson discloses a computing system (Fig. 3, computer 28), comprising: one or more processors (Fig. 5, processing circuit 512); and one or more non-transitory computer-readable media ([0065], memory device 514; [0115], the program code may execute entirely on the user's computer) that collectively store: a machine-learned model ([0033], machine learning protocols; Fig. 10) configured to receive and process the input data, and instructions that, when executed by the one or more processors, configure the computing system to perform operations ([0066], memory device 514 may store program code and instructions), the operations comprising: receiving data from a transceiver-based sensor configured to emit an output signal directed toward soil within a portion of a field and receive an echo signal indicative of a backscattering of the output signal by the soil (Fig. 6, Block 604; [0046], sensor 22 and 26 comprises a ground penetrating radar); extracting a set of features (Fig. 9, Block 904) associated with the echo signal from the received data ([0046]); inputting the set of features into the machine-learned model (Fig. 10, input data 1004 provided to the model); receiving an output of the machine-learned model (Fig. 10, model output data 1010); and adjusting an operating parameter of the agricultural machine based on the final moisture value ([0053 & 0055], vary the tilling depth based on the tillage prescription plan). This tilling prescription plan is taught to be based on characteristics of the soil ([0016]), including detected soil moisture ([0044]).
Anderson does not explicitly disclose that the machine-learned model is configured to process the input data to determine a preliminary soil moisture value for the input data. Anderson additionally does not disclose that, in the operation of the method, the output of the machine-learned model is the preliminary soil moisture value for the set of features inputted, and that the operation further comprises determining a final soil moisture value for the portion of the soil within the field based on the preliminary soil moisture value and one or more correction factors based on at least one of a soil type of the field, a time of year, a crop growing in the field, or a weather condition;
In the same field of endeavor, Chandra teaches operations involving a machine-learned model that is configured to process the input data to determine a preliminary soil moisture value for the input data ([0116], machine learning model estimates permittivity as the preliminary soil moisture value). These operations comprise receiving the preliminary soil moisture value for the set of features as an output of the machine-learned model ([0116], machine learning model estimates permittivity as the preliminary soil moisture value); and determining a final soil moisture value for the portion of the soil within the field based on the preliminary soil moisture value and one or more correction factors based on at least one of a soil type of the field, a time of year, a crop growing in the field, or a weather condition ([0038] and [0042], initial permittivity value of the soil, i.e. preliminary soil moisture value, is fit onto a water content-permittivity model “for that soil type to estimate the water content” and soil moisture).
It would have been obvious to one of ordinary skill in the art at the effective date of filing to modify Anderson with the inclusion of the models and analysis based on soil type for the motivation of obtaining a more accurate soil moisture estimate as Chandra teaches that the accuracy of soil moistures is important to various aspects of agriculture ([0001-0002]).
Regarding claim 8, Anderson further teaches that the machine-learned model comprises an unsupervised machine-learned model ([0074], labeling of data with unsupervised classification).
Regarding claim 12, Anderson further discloses that controlling the operation of the agricultural machine comprises initiating an adjustment to a ground speed of the agricultural machine based on the determined final soil moisture value ([0042], software adjusting the tractor speed during the operation based on tillage prescription plan). This tilling prescription plan is taught to be based on characteristics of the soil ([0016]), including detected soil moisture ([0044]).
Regarding claim 13, Anderson further discloses that controlling the operation of the agricultural machine comprises initiating an adjustment to a penetration depth of a ground-engaging tool of the agricultural machine based on the determined final soil moisture value ([0053 & 0055], vary the tilling depth based on the tillage prescription plan). This tilling prescription plan is taught to be based on characteristics of the soil ([0016]), including detected soil moisture ([0044]).
Regarding claim 14, Anderson further discloses that controlling the operation of the agricultural machine comprises initiating at least one of a change in the direction of travel of the agricultural machine or lifting up an implement of the agricultural machine ([0053 & 0055], vary the tilling depth based on the tillage prescription plan).
Regarding claim 15, Anderson further teaches that the operations further comprise generating a field map identifying the determined final soil moisture value at a plurality of locations within the field ([0038-0040], soil compaction map corresponding to location specific soil compaction data, tillage prescription plan includes data identifying which areas should be tilled). The detected soil moisture is taught to be a component of both the soil compaction ([0062], moisture content) and the tilling prescription plan ([0016 & 0044], determined from characteristics including soil moisture).
Regarding claim 16, Anderson discloses a computer-implemented method (Figs. 6-11), comprising: receiving, with a computing system comprising one or more computing devices (Fig. 3, computer 28), data from a transceiver-based sensor configured to emit an output signal directed toward soil within a portion of a field and receive an echo signal indicative of a backscattering of the output signal by the soil ([0046], sensor 22 and 26 comprises a ground penetrating radar); extracting, with the computing system, a set of features (Fig. 9, Block 904) associated with the echo signal from the received data ([0046]); inputting, with the computing system, the set of features into a machine- learned model configured to receive input data and process the input data (Fig. 10, input data 1004 provided to the model); receiving, with the computing system, an output of the machine-learned model (model output data 1010); and adjusting, with the computing system, an operating parameter of the agricultural machine based on the final moisture value ([0053 & 0055], vary the tilling depth based on the tillage prescription plan). This tilling prescription plan is taught to be based on characteristics of the soil ([0016]), including detected soil moisture ([0044]).
Anderson does not disclose that, in the operation of the method, the output of the machine-learned model is the preliminary soil moisture value for the set of features inputted, and that the operation further comprises determining, with the computing system, a final soil moisture value for the portion of the soil within the field based on the preliminary soil moisture value and one or more correction factors based on at least one of a soil type of the field, a time of year, a crop growing in the field, or a weather condition;
In the same field of endeavor, Chandra teaches operations involving a machine-learned model. These operations comprise receiving the preliminary soil moisture value for the set of features as an output of the machine-learned model ([0116], machine learning model estimates permittivity as the preliminary soil moisture value); and determining a final soil moisture value for the portion of the soil within the field based on the preliminary soil moisture value and one or more correction factors based on at least one of a soil type of the field, a time of year, a crop growing in the field, or a weather condition ([0038] and [0042], initial permittivity value of the soil, i.e. preliminary soil moisture value, is fit onto a water content-permittivity model “for that soil type to estimate the water content” and soil moisture).
It would have been obvious to one of ordinary skill in the art at the effective date of filing to modify Anderson with the inclusion of the models and analysis based on soil type for the motivation of obtaining a more accurate soil moisture estimate as Chandra teaches that the accuracy of soil moistures is important to various aspects of agriculture ([0001-0002]).
Regarding claim 19, Anderson further discloses that the machine-learned model comprises an unsupervised machine-learned model ([0074], labeling of data with unsupervised classification).
Claims 2, 6, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Anderson and Chandra as applied to claims 1, 5, and 16 above, and further in view of Abubakar et al. (WO 2022204682 A1).
Regarding claim 2, Anderson teaches training the machine-learned model (Fig. 10, training data 1002 fed into model 1006). Anderson does not that the training data for training the model is based on systematic synthetic trained samples.
However, Abubakar teaches that the training data for training the model is based on systematic synthetic trained samples ([0075]).
Abubakar is analogous to the art of using machine-learning algorithms to analyze and predict subsurface properties. It would have been obvious to one having ordinary skill in the art at the time of the invention to modify Anderson with the model being trained on synthetic trained samples and would be motivated to do because, as outlined in Abubakar, synthetic input data will always result in a sufficiently large training set as opposed to training sets based on real data, and thus being more reliable and accurate for producing models ([0079]).
Regarding claim 6, Anderson teaches training the machine-learned model (Fig. 10, training data 1002 fed into model 1006). Anderson does not that the training data for training the model is based on a plurality of systematic synthetic trained samples.
However, Abubakar teaches that the training data for training the model is based on systematic synthetic trained samples ([0075]).
Abubakar is analogous to the art of using machine-learning algorithms to analyze and predict subsurface properties. It would have been obvious to one having ordinary skill in the art at the time of the invention to modify Anderson with the model being trained on synthetic trained samples and would be motivated to do because, as outlined in Abubakar, synthetic input data will always result in a sufficiently large training set as opposed to training sets based on real data, and thus being more reliable and accurate for producing models ([0079]).
Regarding claim 17, Anderson teaches training the machine-learned model (Fig. 10, training data 1002 fed into model 1006). Anderson does not that the training data for training the model is based on a plurality of systematic synthetic trained samples.
However, Abubakar teaches that the training data for training the model is based on systematic synthetic trained samples ([0075]).
Abubakar is analogous to the art of using machine-learning algorithms to analyze and predict subsurface properties. It would have been obvious to one having ordinary skill in the art at the time of the invention to modify Anderson with the model being trained on synthetic trained samples and would be motivated to do because, as outlined in Abubakar, synthetic input data will always result in a sufficiently large training set as opposed to training sets based on real data, and thus being more reliable and accurate for producing models ([0079]).
Claims 7 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Anderson and Chandra as applied to claims 5 and 16 above, and further in view of Ferrari et al. (US 10963751 B2).
Regarding claim 7, Anderson in view of Chandra teaches the machine-learned model and method step of determining the final soil moisture value for a portion of the soil of claim 5. Anderson does not teach that the machine-learned model is configured to additionally output a confidence score, and that this confidence score is used along with the preliminary soil moisture value to determine the final soil moisture value.
However, Ferrari teaches a machine-learned model that is configured to output a confidence score for each input feature vector (Col. 17-18, lines 63-67 & 1-3), that this confidence score is used along with the preliminary soil moisture value to determine the final soil moisture value (Col. 18, lines 57-67, where a relationship between the average confidence value and the crop residue parameter value, i.e. preliminary value, is used to determine the returned crop residue parameter value, i.e. final value).
Ferrari is analogous to the art of using machine-learning models to analyze agricultural information of a crop field. It would have been obvious to one having ordinary skill in the art at the time of the invention to modify the prior combination with the model outputting a confidence score and using this as a component for decision making because, as outlined in Ferrari, this allows the soil moisture value to be an accurate, discrete prediction, indicating either an adequate or inadequate amount of final soil moisture value. (Col. 13, lines 55-65).
Regarding claim 18, Anderson in view of Chandra teaches the machine-learned model and method step of determining the final soil moisture value for a portion of the soil of claim 16. Anderson does not teach that the machine-learned model is configured to additionally output a confidence score, and that this confidence score is used along with the preliminary soil moisture value to determine the final soil moisture value.
However, Ferrari teaches a machine-learned model that is configured to output a confidence score for each input feature vector (Col. 17-18, lines 63-67 & 1-3), that this confidence score is used along with the preliminary soil moisture value to determine the final soil moisture value (Col. 18, lines 57-67, where a relationship between the average confidence value and the crop residue parameter value, i.e. preliminary value, is used to determine the returned crop residue parameter value, i.e. final value).
Ferrari is analogous to the art of using machine-learning models to analyze agricultural information of a crop field. It would have been obvious to one having ordinary skill in the art at the time of the invention to modify the prior combination with the model outputting a confidence score and using this as a component for decision making because, as outlined in Ferrari, this allows the soil moisture value to be an accurate, discrete prediction, indicating either an adequate or inadequate amount of final soil moisture value. (Col. 13, lines 55-65).
Claims 9 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Anderson and Chandra as applied to claims 5 and 16 above, and further in view of Lehner et al. (WO 2022012760 A1).
Regarding claim 9, Anderson in view of Chandra teaches the limitations of claim 5. Anderson does not teach that extracting the set of features comprises determining one or more components of the echo signal.
However, Lehner teaches an echo signal processor that performs a method, in which one step of that method is to derive one or more components of the echo signal (Page 9, lines 5-12).
Lehner is analogous to the art of using a GPR device to generate signals, and interpreting those signals to obtain information about subsurface characteristics. It would have been obvious to one having ordinary skill in the art at the time of the invention to modify the prior combination so that the features extracted from the received echo signal include spectral components. The motivation for doing so is that the reading of and using spectral components of echo signals speeds up data acquisition, allowing the overall device to operate faster (Page 3, lines 11-20).
Regarding claim 20, Anderson in view of Chandra teaches the limitations of claim 16. Anderson does not teach that extracting the set of features comprises determining one or more components of the echo signal.
However, Lehner teaches an echo signal processor that performs a method, in which one step of that method is to derive one or more components of the echo signal (Page 9, lines 5-12).
Lehner is analogous to the art of using a GPR device to generate signals, and interpreting those signals to obtain information about subsurface characteristics. It would have been obvious to one having ordinary skill in the art at the time of the invention to modify the prior combination so that the features extracted from the received echo signal include spectral components. The motivation for doing so is that the reading of and using spectral components of echo signals speeds up data acquisition, allowing the overall device to operate faster (Page 3, lines 11-20).
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Anderson and Chandra as applied to claim 5 above, and further in view of Wu et al. (CN 112578471 A).
Regarding claim 10, Anderson in view of Chandra teaches the limitations of claim 5. Anderson does not teach that extracting the set of features comprises determining an inverse wavelet transformation coefficient of the echo signal.
However, Wu teaches a method for removing noise in a GPR signal by applying a wavelet transform on the echo signal, denoising the coefficients via a K-SVD algorithm, and determining an inverse wavelet transformation coefficient of the echo signal (Page 2, lines 6-11, where parts of the reconstructed signal, i.e. inverse wavelet transformation coefficient, are used in an inverse wavelet transformation to obtain the final denoised image).
Wu is analogous to the art of using a GPR device and interpreting the signals that it produces. It would have been obvious to one having ordinary skill in the art at the time of the invention to modify Anderson so that the features extracted from the received echo signal include an inverse wavelet transformation coefficient. The motivation for doing so is to remove noise from the signal of a GPR, thereby increasing the accuracy of the readings it produces (Page 2, lines 1-5).
Response to Arguments
Applicant’s arguments with respect to the amended claims 1, 5, and 16 have been fully considered and are persuasive. Therefore, the previous 103 rejection over Anderson in view of Yang has been withdrawn. However, upon further consideration, a new 103 rejection is made over Anderson in view of Chandra. Chandra teaches the correction factors being based on a soil type, and additionally teaches the limitations Yang was previously relied upon to teach. Therefore, Chandra replaces Yang in the 103 rejections of the independent claims as necessitated by the applicant’s amendment.
Conclusion
The following art made of record and not relied upon is considered pertinent to applicant’s disclosure:
Barrick et al. (US 11154002 B2)
Mewes et al. (US 20190230875 A1)
Perry et al. (US 20190050948 A1)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JACK R. BREWER whose telephone number is (571)272-4455. The examiner can normally be reached 10AM-6PM.
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, Angela Ortiz can be reached at 571-272-1206. 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.
/JACK ROBERT BREWER/ Examiner, Art Unit 3663
/ADAM D TISSOT/ Primary Examiner, Art Unit 3663
Prosecution Insights