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 .
Applicant’s Reply, filed on 05/08/2026 is hereby acknowledged.
Claims 1-5, 8, 10, 12 and 55 are pending and examined herein on the merits.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 2, 4-5, 8, 12 and 55 remain rejected under 35 U.S.C. 102(a)(1) as being anticipated by Parmley et al (2019 Nature Research Scientific Reports 9:17132).
The claims are drawn to a computer-implemented method for use in allocating test protocols associated with a plant breeding pipeline to a plurality of test locations comprising executing by a computing device a first stage machine learning prediction model based on protocol data for a plurality of test protocols for a current test experiment to generate a first stage output wherein the first stage is trained based on historical allocation data and, based on the first stage output, executing by the computing device a second stage optimization model to generate second stage output wherein the second stage output includes an allocation plan that comprises one or more of the plurality of test locations and storing the output in a memory that is accessible, wherein the MLPM is further based on test location data and wherein the test location data identifies one or more characteristics of each test location, harvesting the plants (claim 4), wherein the historical data includes one or more requirements for one or more historical test protocols wherein the plurality of allocation prediction scores represent probabilities that the test locations satisfy the test protocol, further comprising updating the historical allocation data, and further reserving one or more resources at the test locations identified.
Parmley et al teach a machine learning approach for prescriptive plant breeding wherein Random Forest (which is a machine learning prediction tool) was used to train models for seed yield prediction using a plurality of test protocols including row spacing, seeding density and training historical data such as canopy temperature, leaf area index and light interception, wherein the combination of variables was combined to maximize resource allocation (see data, particularly Figures 1 and 2 and Table 1), each of the locations is disclosed (see materials and methods) and harvesting was inherent in measuring seed yield.
Response to Arguments
Applicant's arguments filed 05/08/2026 have been fully considered but they are not persuasive.
Applicant’s urge that Parmley does disclose or teach, expressly or inherently the claimed method for use in allocating test protocols associated with a plant breeding pipeline, or anything that “dictates requirements and characteristics for test sets of seeds being advanced through a breeding pipeline” (see pages 5-6 of response).
This is not persuasive because the specification does not define what is considered to be a plant breeding pipeline. There does seem to be a currently art accepted meaning for the term, however, the open claim language uses the term “associated” with a plant breeding pipeline, which would mean any plant that is bred or could be bred which is an inherent property of plants. Furthermore, even if this were to be imparted into the claim it is noted that this method is generally applicable to all plant species even though plant species may differ considerably depending on how variable these factors are from plant species to plant species. Finally, There are no method steps or limitations that directly correlate the claimed method to such a breeding pipeline or any breeding steps whatsoever. The only requirement is the prediction and plant of seeds.
Applicants urge that Parmley does not teach or disclose historical allocation data from prior breeding experiments to predict allocation suitability (see page 7).
This is not persuasive because the claims do not require the data to come from prior breeding experiments. This phrase is not mentioned in the claims.
Applicants urge that Parmley does not teach 2nd stage optimization or output, nor does it teach automated allocation planning (see page 7 of response).
This is not persuasive because as a first matter, Applicant is arguing limitations not present in the claims as currently written (ie automated allocation planning) and further, relies on a second stage that is inherent in the method taught by Parmley, for example, included in the methods is a recursive feature elimination wherein a second stage of prediction based on genotype is mentioned (see pages 4-5).
Applicants urge that Parmley never addresses nor solves the technical problem of the significantly large number of possible allocation plans and urges that the instant method solves this technical problem (see pages 7-8 of response).
This is not persuasive because the instant claims are broad and do not limit the method nor mention automation or indicate how their method differs from methods present in the prior art. Terms such as “plurality” do not impart a magnitude to the numbers tested, but simply indicate multiple numbers which Parmley also teach.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-5, 8, 12 and 55 remain rejected under 35 U.S.C. 102(a)(1) as being Anticipated by Adebiyi et al (2020 Hindawi Scientifica 2020 pages 1-12 Machine Learning-Based Predictive Farmland Optimization and Crop Monitoring System published May 11, 2020).
The claims are drawn to a computer-implemented method for use in allocating test protocols associated with a plant breeding pipeline to a plurality of test locations comprising executing by a computing device a first stage machine learning prediction model based on protocol data for a plurality of test protocols for a current test experiment to generate a first stage output wherein the first stage is trained based on historical allocation data and, based on the first stage output, executing by the computing device a second stage optimization model to generate second stage output wherein the second stage output includes an allocation plan that comprises one or more of the plurality of test locations and storing the output in a memory that is accessible, wherein the MLPM is further based on test location data and wherein the test location data identifies one or more characteristics of each test location, harvesting the plants (claim 4), wherein the historical data includes one or more requirements for one or more historical test protocols wherein the plurality of allocation prediction scores represent probabilities that the test locations satisfy the test protocol, further comprising updating the historical allocation data, and further reserving one or more resources at the test locations identified and further comprising generating at least one interactive user interface representative of the allocation plan and displaying by the computing device the at least one interactive interface.
Adebiyi et al teach a computer-implemented method using machine learning applied to historical data including irrigation, spacing, nutrient requirements, location, temperature using Random Forest to generate output (see materials and methods 3.1) wherein the output is generated in a dataset on a mobile application (which is a user interface displayed, wherein this output is optimized using an optimization model (see figures 15 and 16, for example), wherein the allocation data was used to generate outputs and predictions to determine locations specifically (see bottom of page 8).
Response to Arguments
Applicant's arguments filed 05/08/2026 have been fully considered but they are not persuasive.
Applicant’s urge similar to Parmley that Adebiyi does not disclose or teach their method with association with plant breeding pipeline (see page 9).
This is not persuasive because the specification does not define what is considered to be a plant breeding pipeline. There does seem to be a currently art accepted meaning for the term, however, the open claim language uses the term “associated” with a plant breeding pipeline, which would mean any plant that is bred or could be bred which is an inherent property of plants. Furthermore, even if this were to be imparted into the claim it is noted that this method is generally applicable to all plant species even though plant species may differ considerably depending on how variable these factors are from plant species to plant species. Finally, There are no method steps or limitations that directly correlate the claimed method to such a breeding pipeline or any breeding steps whatsoever. The only requirement is the prediction and plant of seeds.
Applicants urge that Adebiyi does not disclose a two stage process (see page 9).
This is not persuasive as the two stages are illustrated with the machine learning creating prediction and output combined with the interface which is the second stage wherein selections and predictions are made.
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.
Claim 10 remains rejected under 35 U.S.C. 103 as being unpatentable over Adebiyi et al 2020 (Hindawi Scientifica 2020 pages 1-12 Machine Learning-Based Predictive Farmland Optimization and Crop Monitoring System published May 11, 2020).
The claim is drawn to the above method wherein the first stage MLPM includes a recurrent neural network trained based on historical allocation data
Adebiyi et al teach a computer-implemented method using machine learning applied to historical data including irrigation, spacing, nutrient requirements, location, temperature using Random Forest to generate output (see materials and methods 3.1) wherein the output is generated in a dataset on a mobile application (which is a user interface displayed, wherein this output is optimized using an optimization model (see figures 15 and 16, for example), wherein the allocation data was used to generate outputs and predictions to determine locations specifically (see bottom of page 8). Adebiyi et al also teach in a review of existing technologies that a number of studies have used neural networks including with Random forest and with crop yield prediction (See Table 1).
Although Adebiyi et al do not specifically incorporate neural network training explicitly, it is clear that this was a well-known approach at the time of filing and available for plant breeding pipelines. It appears this is a design choice that would have readily been available to one of ordinary skill in the art.
Response to Arguments
Applicant's arguments filed 05/08/2026 have been fully considered but they are not persuasive.
Applicant’s urge the arguments above in reference to Adebiyi regarding claim 1.
This is not persuasive because the specification does not define what is considered to be a plant breeding pipeline. There does seem to be a currently art accepted meaning for the term, however, the open claim language uses the term “associated” with a plant breeding pipeline, which would mean any plant that is bred or could be bred which is an inherent property of plants. Furthermore, even if this were to be imparted into the claim it is noted that this method is generally applicable to all plant species even though plant species may differ considerably depending on how variable these factors are from plant species to plant species. Finally, There are no method steps or limitations that directly correlate the claimed method to such a breeding pipeline or any breeding steps whatsoever. The only requirement is the prediction and plant of seeds.
Applicants urge that Adebiyi does not disclose a two stage process (see page 9).
This is not persuasive as the two stages are illustrated with the machine learning creating prediction and output combined with the interface which is the second stage wherein selections and predictions are made.
No claims are allowed.
THIS ACTION IS MADE FINAL. 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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRENT T PAGE whose telephone number is (571)272-5914. The examiner can normally be reached M-F 7-4 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, Amjad Abraham can be reached at 5712707058. 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.
/BRENT T PAGE/Primary Examiner, Art Unit 1663
Prosecution Insights