Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 5/22/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Status of Claims
The present application is being examined under the claims filed on 5/2/2024.
Claims 1-9 are rejected.
Claims 1-9 are pending.
Specification
The specification filed on 5/2/2024 is acceptable for examination purposes.
Drawings
The drawings filed on 5/2/2024 and 5/20/2024 are acceptable for examination purposes.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-9 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding Claim 1,
Step 1: Claim 1 is a method claim. Therefore, Claims 1-9 are directed to a process.
Step 2A Prong 1:
formulating an overall framework (mental process – formulating an overall framework may be performed manually by a user with the aid of pen and paper by observing/analyzing an overall concept and using a judgement to formulate an overall framework. See MPEP 2106.04(a)(2)(III)(C).)
establishing a total dataset (TDS) and a minimum dataset (MIDS), and calculating soil quality indices based on the TDS and the MDS (mental process – establishing a total dataset (TDS) and a minimum dataset (MIDS), and calculating soil quality indices based on the TDS and the MDS may be performed manually by a user with the aid of pen and paper by observing/analyzing a dataset and using a judgement to create a total dataset (TDS) and a minimum dataset (MIDS) and calculating soil quality indices using the TDS and the MIDS. See MPEP 2106.04(a)(2)(III)(C).)
generating a soil quality extended dataset and a soil quality evaluation dataset (mental process – generating a soil quality extended dataset and a soil quality evaluation dataset may be performed manually by a user with the aid of pen and paper by observing/analyzing a dataset and using a judgement to create a soil quality extended dataset and a soil quality evaluation dataset. See MPEP 2106.04(a)(2)(III)(C).)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application.
Additional Elements:
developing a soil quality prediction model based on machine learning (merely using a computer as a tool to perform an abstract idea. See MPEP 2106.05(f).)
analyzing data in the soil quality extended dataset and the soil quality evaluation dataset by using the soil quality prediction model, to evaluate improvement effect of organic materials on soil quality (merely using a computer as a tool to perform an abstract idea. See MPEP 2106.05(f).)
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional elements recite generic computer elements and programs at a high-level of generality to perform the judicial exception as well as recitation of generic computer functionality such as a processor, a first-round artificial intelligence model and a nth-round artificial intelligence model.
Additional Elements:
developing a soil quality prediction model based on machine learning (merely using a computer as a tool to perform an abstract idea. See MPEP 2106.05(f).)
analyzing data in the soil quality extended dataset and the soil quality evaluation dataset by using the soil quality prediction model, to evaluate improvement effect of organic materials on soil quality (merely using a computer as a tool to perform an abstract idea. See MPEP 2106.05(f).)
For the reasons above, Claim 1 is rejected as being directed to an abstract idea without significantly more. This rejection applies equally to dependent claims 2-9. The additional limitations of the dependent claims are addressed below.
Regarding Claim 2,
Step 2A Prong 1:
establishment of the TDS and calculation of a soil quality index based on the TDS, establishment of the MDS and calculation of a soil quality index based on the MDS (mental process – establishment of the TDS and calculation of a soil quality index based on the TDS, establishment of the MDS and calculation of a soil quality index based on the MDS may be performed manually by a user with the aid of pen and paper by observing/analyzing a dataset and using a judgement to create a total dataset (TDS) and a minimum dataset (MDS) and calculating soil quality indices using the TDS and the MDS. See MPEP 2106.04(a)(2)(III)(C).)
generation of the soil quality evaluation dataset (mental process – generation of the soil quality evaluation dataset may be performed manually by a user with the aid of pen and paper by observing/analyzing the dataset and using a judgement to create the soil quality evaluation dataset. See MPEP 2106.04(a)(2)(III)(C).)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application.
Additional Elements:
development of the soil quality prediction model based on the machine learning (merely using a computer as a tool to perform an abstract idea. See MPEP 2106.05(f).)
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional Elements:
development of the soil quality prediction model based on the machine learning (merely using a computer as a tool to perform an abstract idea. See MPEP 2106.05(f).)
Regarding Claim 3,
Step 2A Prong 1:
selecting a standard scoring function for an evaluation indicator of the TDS, selecting an evaluation indicator for the MIDS, and calculating the soil quality indices (mental process – selecting a standard scoring function for an evaluation indicator of the TDS, selecting an evaluation indicator for the MIDS, and calculating the soil quality indices may be performed manually by a user with the aid of pen and paper by observing/analyzing a standard scoring function for an evaluation indicator of the TDS, an evaluation indicator for the MIDS and using the standard scoring function and the evaluation indicator to calculate the soil quality indices. See MPEP 2106.04(a)(2)(III)(C).)
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application.
Additional Elements:
collecting and processing the TDS (Adding insignificant extra-solution activity to the judicial exception. See MPEP 2106.05(g).)
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional Elements:
collecting and processing the TDS (MPEP 2106.05(d)(II) indicates that merely “Receiving or transmitting data over a network” is a well-understood, routine, conventional function when it is claimed in a merely generic manner (as it is in the present claim). Thereby, a conclusion that the claimed limitation is well-understood, routine, conventional activity is supported under Berkheimer)
Regarding Claim 4,
Step 2A Prong 1:
selecting, based on a selection frequency of soil quality indicators and availability of indicator data, a soil physical indicator of bulk density, chemical indicators of organic matter, total nitrogen, rapidly-available phosphorus, rapidly-available potassium, and pH, and biological indicators of microbial biomass carbon, microbial biomass nitrogen, sucrase, phosphatase, and urease as the TDS for soil quality evaluation (mental process – selecting, based on a selection frequency of soil quality indicators and availability of indicator data, a soil physical indicator of bulk density, chemical indicators of organic matter, total nitrogen, rapidly-available phosphorus, rapidly-available potassium, and pH, and biological indicators of microbial biomass carbon, microbial biomass nitrogen, sucrase, phosphatase, and urease as the TDS for soil quality evaluation may be performed manually by a user with the aid of pen and paper by observing/analyzing a selection frequency and availability of indicator data and using a judgement to select a soil physical indicator, chemical indicators and biological indicators as the TDS for soil quality evaluation. See MPEP 2106.04(a)(2)(III)(C).)
Step 2A Prong 2 & Step 2B:
There are no additional elements.
Regarding Claim 5,
Step 2A Prong 1:
establishing the standard scoring function between the evaluation indicator and soil quality based on soil characteristics of different soil types and a correlation between the evaluation indicator and the soil quality (mental process – establishing the standard scoring function between the evaluation indicator and soil quality based on soil characteristics of different soil types and a correlation between the evaluation indicator and the soil quality may be performed manually by a user with the aid of pen and paper by observing/analyzing the soil characteristics of different soil types and a correlation between the evaluation indicator and the soil quality, and using a judgement to create the standard scoring function between the evaluation indicator and soil quality. See MPEP 2106.04(a)(2)(III)(C).)
Step 2A Prong 2 & Step 2B:
There are no additional elements.
Regarding Claim 6,
Step 2A Prong 1:
calculating Norm values of the evaluation indicator as follows:
PNG
media_image1.png
77
135
media_image1.png
Greyscale
wherein Nik represents a comprehensive loading of an i-th indicator on top k principal components (PCs) with eigenvalues greater than 1; Uik is a loading value of the i-th indicator on a k-th PC; and λk is an eigenvalue of the k-th PC (mathematical concept – calculating Norm values of the evaluation indicator may be performed by mathematical process, calculating the given mathematical formula in the claim. See MPEP 2106.04(a)(2)(I)(C).)
Step 2A Prong 2 & Step 2B:
There are no additional elements.
Regarding Claim 7,
Step 2A Prong 1:
calculating a weight value of each indicator by using factor analysis; the soil quality indices are respectively calculated based on the TDS and the MDS by using following formula:
PNG
media_image2.png
63
137
media_image2.png
Greyscale
wherein Wi represents a weight of an i-th evaluation indicator, Si represents a membership degree of the i-th evaluation indicator, and n represents the number of participating evaluation indicators in each dataset (mathematical concept – calculating a weight value of each indicator by using factor analysis may be performed by mathematical process, calculating the given mathematical formula in the claim. See MPEP 2106.04(a)(2)(I)(C).)
Step 2A Prong 2 & Step 2B:
There are no additional elements.
Regarding Claim 8,
Step 2A Prong 1:
See the rejection of Claim 1 above, which Claim 8 depends on.
Step 2A Prong 2: The judicial exceptions are not integrated into a practical application.
Additional Elements:
developing the soil quality prediction model and assessing accuracy of the soil quality prediction model, and developing a random forest regression RFR model (merely using a computer as a tool to perform an abstract idea. See MPEP 2106.05(f).)
Step 2B: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional Elements:
developing the soil quality prediction model and assessing accuracy of the soil quality prediction model, and developing a random forest regression RFR model (merely using a computer as a tool to perform an abstract idea. See MPEP 2106.05(f).)
Regarding Claim 9,
Step 2A Prong 1:
quantifying performance of the prediction model with a coefficient of determination R2, a root mean square error RMSE, and a relative percent deviation RPD as follows:
PNG
media_image3.png
339
246
media_image3.png
Greyscale
wherein N is the number of samples; yi and ŷi represent a measured value and a corresponding predicted value, respectively;
PNG
media_image4.png
32
21
media_image4.png
Greyscale
represents an average value of predicted values; ȳ represents an average value of measured values; when RPD<1.4, predictive performance of the soil quality prediction model is poor; when 1.4<=RPD<1.8, the model has a certain predictive ability and is capable of assessing the samples; when 1.8<=RPD<2.0, the soil quality prediction model has a good predictive ability and is capable of quantitative prediction; when 2.0<=RPD<2.5, the soil quality prediction model is capable of quantitative prediction with higher accuracy; when RPD>=2.5, the model is excellent and exhibits an extremely satisfactory quantitative prediction ability (mathematical concept – quantifying performance of the prediction model with a coefficient of determination R2, a root mean square error RMSE, and a relative percent deviation RPD may be performed by mathematical process, calculating the given mathematical formula in the claim. See MPEP 2106.04(a)(2)(I)(C).)
Step 2A Prong 2 & Step 2B:
There are no additional elements.
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 1-3, 5 and 7-8 are rejected under 35 U.S.C. 103 as being unpatentable over Paul et al. (“Assessing the soil quality of Bansloi river basin, eastern India using soil-quality indices (SQIs) and Random Forest machine learning technique”) (hereinafter Paul) and in view of Chen et al. (“Minimum Data Set for Assessing Soil Quality in Farmland of Northeast China”) (hereinafter Chen).
Regarding Claim 1,
Paul teaches:
“An ensemble learning-based optimized evaluation method for an improvement effect of organic materials on soil quality, comprising following steps:” (Paul, Sections 2.1 and 2.8, “Crop productivity as well as the use of organic fertilizer is relatively low than the state average […] Therefore, through assessment of the soil quality is one of the prime needs for sustaining the agricultural productivity of the region […] In the present study we implemented a Random Forest (RF) model (Conoscenti et al., 2008; Gayen et al., 2019; Tsangaratos et al., 2017) in the prediction of spatial soil quality index using the RF 4.6 package in the R environment.”; Examiner’s note: a Random Forest (RF) teaches an ensemble learning-based optimized evaluation method. The use of organic fertilizer and the assessment of the soil quality teach improvement effect of organic materials on soil quality.)
“formulating an overall framework” (Paul, Section 2.8, “In this spatial soil quality prediction framework, as spatial covariates, eleven land quality and ecological vectors are preliminarily selected as candidates of auxiliary (or predictor) variables.”; Examiner’s note: formulating an overall framework (i.e., formulating a spatial soil quality prediction framework) is taught.)
“developing a soil quality prediction model based on machine learning” (Paul, Section 2.8, “In the present study we implemented a Random Forest (RF) model (Conoscenti et al., 2008; Gayen et al., 2019; Tsangaratos et al., 2017) in the prediction of spatial soil quality index using the RF 4.6 package in the R environment.”; Examiner’s note: developing a soil quality prediction model based on machine learning (i.e., implementing a random forest (RF) model in the prediction of spatial soil quality) is taught.)
“generating a soil quality extended dataset and a soil quality evaluation dataset” (Paul, Section 4, “Addition of more number of sampling points to the training dataset could help to improve the accuracy of predictions. The current work refers to topsoil (0–20 cm depth), but subsoil dataset (i.e. beyond 20 cm of depth) including the soil C horizon in weathering substrate could be incorporated.”; Examiner’s note: generating a soil quality extended dataset (i.e., incorporating subsoil dataset into topsoil dataset) and a soil quality evaluation dataset (i.e., adding more sampling points to the training dataset to improve the accuracy of predictions) is taught.)
analyzing data in the soil quality extended dataset and the soil quality evaluation dataset by using the soil quality prediction model (Paul, Section 2.8, “three error criteria are used for evaluating the ability of the RF models in predicting the SQIs: namely the coefficient of determination (R2), mean error (MAE) and root mean square error (RMSE).”; Examiner’s note: analyzing data in the soil quality extended dataset and the soil quality evaluation dataset (i.e., evaluating the ability of the RF models in predicting the SQIs using the coefficient of determination (R2), mean error (MAE) and root mean square error (RMSE)) by using the soil quality prediction model (i.e., the random forest (RF) model) is taught.)
Paul does not explicitly teach:
“establishing a total dataset (TDS) and a minimum dataset (MIDS), and calculating soil quality indices based on the TDS and the MDS”
to evaluate improvement effect of organic materials on soil quality
Chen teaches:
“establishing a total dataset (TDS) and a minimum dataset (MIDS), and calculating soil quality indices based on the TDS and the MDS” (Chen, Calculation and classification of SQI in Page 567, “Each PC explained a certain amount of the variation in the total data set (TDS). The percentage of the variation divided by the total percentage of variation explained by all PCs with eigenvectors > 1 provided the weight based on variation of PCA. The weight of the TDS was calculated from the communality of the PCA. We then summed the weighted MDS variable scores for each observation. The final PCA-based soil quality equation is as follows:
PNG
media_image5.png
58
473
media_image5.png
Greyscale
where W is the PCA weighting and S is the indicator score.”; Chen, Calculation and classification of SQI in Page 571, “The indicators in the TDS or MDS were weighted based on results of the mathematical statistics (Table IV) […] Silt, clay, SOM, and TN had higher weights, whereas Bd had the lowest weight in the TDS. The indicators had weights from 0.1 to 0.14 in the MDS.”;
PNG
media_image6.png
566
476
media_image6.png
Greyscale
; Examiner’s note: establishing a total dataset (TDS) (i.e., TDS in table IV teaches a total dataset) and a minimum dataset (MIDS) (i.e., MDS in table IV teaches a minimum dataset), and calculating soil quality indices based on the TDS and the MDS (i.e., the final PCA-based soil quality equation in (4)) is taught.)
to evaluate improvement effect of organic materials on soil quality (Chen, Descriptive statistics of soil characteristics and yield in Page 568, “The soils were considered rich in organic matter, with mean SOM values of 48.0 g kg−1. This was considerably higher than for soils in other areas of China, including Hainan, Anhui, and Sichuan Provinces where SOM values averaged 20, 23, and 12 g kg−1, respectively (Cao and Zhou, 2008) […] The high nutrient and SOM levels confirmed that farmland in Hailun County was indeed quite fertile.”; Examiner’s note: to evaluate improvement effect of organic materials on soil quality (i.e., SOM values of 48.0 g kg-1 in Hailun County, the high nutrient and SOM levels confirming that farmland in Hailun County quite fertile) is taught.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the soil quality assessment using soil-quality indices (SQIs) and random forest machine learning technique in Paul, and the minimum data set for assessing soil quality as taught in Chen. Paul teaches formulating an overall framework, developing a soil quality prediction model, generating a soil quality extended dataset and a soil quality evaluation dataset, and analyzing data in the soil quality extended dataset and the soil quality evaluation dataset by using the soil quality prediction model. Chen teaches establishing a total dataset (TDS) and a minimum dataset (MIDS), calculating soil quality indices, and evaluating improvement effect of organic materials on soil quality. One of ordinary skill would have motivation to combine Paul and Chen so that “soil quality indices could be effectively used to evaluate agricultural land and crop response using a variety of different weighting methods” (Chen, Conclusions in Page 574).
Regarding Claim 2,
The combination of Paul and Chen teaches:
“The ensemble learning-based optimized evaluation method according to claim 1,” (preamble)
“wherein in step S1, the overall framework comprises: establishment of the TDS and calculation of a soil quality index based on the TDS, establishment of the MDS and calculation of a soil quality index based on the MDS, development of the soil quality prediction model based on the machine learning, and generation of the soil quality evaluation dataset” (Chen, Calculation and classification of SQI in Page 567, “Each PC explained a certain amount of the variation in the total data set (TDS). The percentage of the variation divided by the total percentage of variation explained by all PCs with eigenvectors > 1 provided the weight based on variation of PCA. The weight of the TDS was calculated from the communality of the PCA. We then summed the weighted MDS variable scores for each observation. The final PCA-based soil quality equation is as follows:
PNG
media_image5.png
58
473
media_image5.png
Greyscale
where W is the PCA weighting and S is the indicator score.”; Chen, Indicator selection in Page 569, “Our approach established an MDS from soil quality indicators that were able to mainly show effects as a result of agriculture management practices. Therefore, as many as 20 physical and chemical indicators were chosen for our TDS. The 20 soil quality properties considered in the PCA were grouped into components. The first seven PCs had eigenvalues > 1, each explaining at least 5% of the data variation and accounting for 74.9% of the total variance (Table II).”; Chen, Calculation and classification of SQI in Page 572, “The SQIs were calculated using Eq. 4 and then ranked with the grades of each method shown in Table V, which showed that classification criteria for SQI based on TDS (SQI-TDS), SQI based on MDS (SQI-MDS) calculated from norm (SQIMDSnorm), SQI-MDS calculated from communality (SQI-MDScommunality), and SQI-MDS calculated from regression (SQI-MDSregression) were almost the same.”;
PNG
media_image7.png
448
985
media_image7.png
Greyscale
; Paul, Sections 2.8 and 4, “In the present study we implemented a Random Forest (RF) model (Conoscenti et al., 2008; Gayen et al., 2019; Tsangaratos et al., 2017) in the prediction of spatial soil quality index using the RF 4.6 package in the R environment […] Addition of more number of sampling points to the training dataset could help to improve the accuracy of predictions.”; Examiner’s note: wherein in step S1, the overall framework comprises: establishment of the TDS (i.e., as many as 20 physical and chemical indicators chosen for our TDS) and calculation of a soil quality index based on the TDS (i.e., calculating SQI based on TDS (SQI-TDS)), establishment of the MDS (i.e., our approach established an MDS from soil quality indicators that were able to mainly show effects as a result of agriculture management practices) and calculation of a soil quality index based on the MDS (i.e., SQI based on MDS (SQI-MDS) calculated from norm, SQI-MDS calculated from communality, and SQI-MDS calculated from regression), development of the soil quality prediction model based on the machine learning (i.e., implementing a Random Forest (RF) model), and generation of the soil quality evaluation dataset (i.e., adding more sampling points to the training dataset to improve the accuracy of predictions) is taught.)
The reasons of obviousness have been noted in the rejection of Claim 1 above and applicable herein.
Regarding Claim 3,
The combination of Paul and Chen teaches:
“The ensemble learning-based optimized evaluation method according to claim 1,” (preamble)
“wherein in step S2, the establishing a TDS and a MIDS and calculating soil quality indices based on the TDS and the MIDS comprises: collecting and processing the TDS, selecting a standard scoring function for an evaluation indicator of the TDS, selecting an evaluation indicator for the MIDS, and calculating the soil quality indices” (Chen, Soil sampling in Pages 565 and 566, “Soil samples were collected from tilled (0 to 20 cm) […] Each subsample was collected in about 1 000 cm2 and weighed about 2 kg […] Each sample was air-dried, placed in a plastic bag and stored until it could be analyzed. The air-dried samples were crushed and passed through a 2-mm (10 meshes) or 0.149-mm (100 meshes) sieve to determine its different attributes […] Each soybean sample was collected within a 2 m2 around the corresponding soil sampling site. The three soybean subsamples were collected, dried and weighed.”; Chen, Indicator selection in Page 566, “[…] the selection of MDS indicators relied primarily on expert opinion (Doran and Parkin, 1994; Larson and Pierce, 1994). However, selection of MDS variables can be simplified using statistical methods, such as PCA (Andrews and Carroll, 2001; Rezaei et al., 2005), factor analysis, and/or regression equations (Masto et al., 2008). We employed PCA as a data reduction tool to select the most appropriate indicators of site potential for the study area.”; Chen, Indicator scoring in Page 567, “In our study, the data of selected indicators were scored through the linear technique according to Diack and Stott (2001).”; Chen, Calculation and classification of SQI in Page 567, “Each PC explained a certain amount of the variation in the total data set (TDS). The percentage of the variation divided by the total percentage of variation explained by all PCs with eigenvectors > 1 provided the weight based on variation of PCA. The weight of the TDS was calculated from the communality of the PCA. We then summed the weighted MDS variable scores for each observation. The final PCA-based soil quality equation is as follows:
PNG
media_image5.png
58
473
media_image5.png
Greyscale
where W is the PCA weighting and S is the indicator score.”; Chen, Indicator selection in Page 569, “Our approach established an MDS from soil quality indicators that were able to mainly show effects as a result of agriculture management practices. Therefore, as many as 20 physical and chemical indicators were chosen for our TDS.”; Chen, Calculation and classification of SQI in Page 572, “The SQIs were calculated using Eq. 4 and then ranked with the grades of each method shown in Table V, which showed that classification criteria for SQI based on TDS (SQI-TDS), SQI based on MDS (SQI-MDS) calculated from norm (SQIMDSnorm), SQI-MDS calculated from communality (SQI-MDScommunality), and SQI-MDS calculated from regression (SQI-MDSregression) were almost the same.”; Examiner’s note: wherein in step S2, the establishing a TDS and a MIDS (i.e., as many as 20 physical and chemical indicators chosen for our TDS and our approach established an MDS from soil quality indicators that were able to mainly show effects as a result of agriculture management practices) and calculating soil quality indices based on the TDS and the MIDS (i.e., calculating SQI based on TDS (SQI-TDS), SQI based on MDS (SQI-MDS) calculated from norm, SQI-MDS calculated from communality, and SQI-MDS calculated from regression) comprises: collecting and processing the TDS (i.e., soil samples and subsamples were collected, dried, weighted and analyzed), selecting a standard scoring function for an evaluation indicator of the TDS (i.e., the data of selected indicators scored through the linear technique according to Diack and Stott (2001)), selecting an evaluation indicator for the MIDS (i.e., PCA employed as a data reduction tool to select the most appropriate indicators for the MDS), and calculating the soil quality indices (i.e., equation (4) teaches calculating the soil quality indices) is taught. Table V is included in claim 2.)
The reasons of obviousness have been noted in the rejection of Claim 1 above and applicable herein.
Regarding Claim 5,
The combination of Paul and Chen teaches:
“The ensemble learning-based optimized evaluation method according to claim 3,” (preamble)
“wherein in step S2, the selecting a standard scoring function for an evaluation indicator of the TDS comprises: establishing the standard scoring function between the evaluation indicator and soil quality based on soil characteristics of different soil types and a correlation between the evaluation indicator and the soil quality” (Chen, Indicator scoring in Page 567, “In our study, the data of selected indicators were scored through the linear technique according to Diack and Stott (2001). Scores ranging from 0 to 1 were assigned to the indicators included in the MDS by applying either “more is better”, or “less is better” or “optimum” function. The equations of the score curves are as follows:
PNG
media_image8.png
227
472
media_image8.png
Greyscale
where f(x) is the linear score; x is the soil property value; and L and U are the lower and upper threshold values, respectively. Eq. 2 was used for the “more is better” scoring function, whereas Eq. 3 was used for the “less is better” function. For the “optimum” function, indicators were scored as “more is better” for the increasing part and then scored as “less is better” for the decreasing part.”; Chen, Calculation and classification of SQI in Page 567, “The final PCA-based soil quality equation is as follows:
PNG
media_image5.png
58
473
media_image5.png
Greyscale
where W is the PCA weighting and S is the indicator score.”; Chen, Table I in Page 568,
PNG
media_image9.png
638
989
media_image9.png
Greyscale
; Chen, Indicator selection in Page 569, “The Pearson correlation test was used to examine the correlation among indicators to reduce redundancy (Table III).”; Examiner’s note: wherein in step S2, the selecting a standard scoring function for an evaluation indicator of the TDS (i.e., the data of selected indicators scored through the linear technique according to Diack and Stott (2001)) comprises: establishing the standard scoring function (i.e., equations 2, 3 and optimum function teach establishing the standard scoring function) between the evaluation indicator and soil quality based on soil characteristics of different soil types (i.e., equation 4 teaches the evaluation indicator and soil quality. Table I discloses soil characteristics of different soil types) and a correlation between the evaluation indicator and the soil quality (i.e., the Pearson correlation test examining the correlation among indicators (Table III) teaches a correlation between the evaluation indicator and the soil quality) is taught.)
The reasons of obviousness have been noted in the rejection of Claim 3 above and applicable herein.
Regarding Claim 7,
The combination of Paul and Chen teaches:
“The ensemble learning-based optimized evaluation method according to claim 3,” (preamble)
“wherein in step S2, the calculating soil quality indices comprises: calculating a weight value of each indicator by using factor analysis; the soil quality indices are respectively calculated based on the TDS and the MDS by using following formula:
PNG
media_image10.png
65
138
media_image10.png
Greyscale
wherein Wi represents a weight of an i-th evaluation indicator, Si represents a membership degree of the i-th evaluation indicator, and n represents the number of participating evaluation indicators in each dataset” (Chen, Calculation and classification of SQI in Page 567, “Each PC explained a certain amount of the variation in the total data set (TDS). The percentage of the variation divided by the total percentage of variation explained by all PCs with eigenvectors > 1 provided the weight based on variation of PCA. The weight of the TDS was calculated from the communality of the PCA. We then summed the weighted MDS variable scores for each observation. The final PCA-based soil quality equation is as follows:
PNG
media_image5.png
58
473
media_image5.png
Greyscale
where W is the PCA weighting and S is the indicator score.”; Chen, Calculation and classification of SQI in Page 571, “The indicators in the TDS or MDS were weighted based on results of the mathematical statistics (Table IV)
PNG
media_image6.png
566
476
media_image6.png
Greyscale
”; Examiner’s note: Table IV teaches calculating a weight value of each indicator by using factor analysis and equation 4 teaches the soil quality indices calculated based on the TDS and the MDS.)
The reasons of obviousness have been noted in the rejection of Claim 3 above and applicable herein.
Regarding Claim 8,
The combination of Paul and Chen teaches:
“The ensemble learning-based optimized evaluation method according to claim 1,” (preamble)
“wherein in step S3, the developing a soil quality prediction model based on machine learning comprises: developing the soil quality prediction model and assessing accuracy of the soil quality prediction model, and developing a random forest regression RFR model“ (Paul, Section 2.8, “In the data sparse environment especially where field sampling followed by laboratory measurements is usually costly and time-consuming, digital soil mapping techniques such as RF (Pahlavan-Rad et al., 2014; Were et al., 2015), Regression Trees (Jafari et al., 2014), Logistic Regression (Vasques et al., 2014) etc. based on ancillary data (land quality and ecological vectors) is found useful for practical purposes (Taghizadeh-Mehrjardi et al., 2015; 2016). In the present study we implemented a Random Forest (RF) model (Conoscenti et al., 2008; Gayen et al., 2019; Tsangaratos et al., 2017) in the prediction of spatial soil quality index using the RF 4.6 package in the R environment.”; Paul, Section 3.4.2, “The mean decrease accuracy presented in the Fig. 10 representing the contribution or importance of individual land quality and ecological variables has been calculated by the RF model.”; Examiner’s note: developing the soil quality prediction model (i.e., implementing a random forest (RF) model in the prediction of spatial soil quality) and assessing accuracy of the soil quality prediction model (i.e., the mean decrease accuracy by RF model assessed and presented in the Fig. 10), and developing a random forest regression RFR model (i.e., regression trees teach developing a random forest regression RFR model since RFR model consists of a collection of many independent regression trees) is taught.)
The reasons of obviousness have been noted in the rejection of Claim 1 above and applicable herein.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Paul in view of Chen as applied in claim 1, in view of Jiang et al. (“Effects of Biochar Application on Enzyme Activities in Tea Garden Soil”) (hereinafter Jiang).
Regarding Claim 4,
The combination of Paul and Chen teaches:
“The ensemble learning-based optimized evaluation method according to claim 3,” (preamble)
wherein in step S2, the collecting and processing the TDS comprises: selecting, based on a selection frequency of soil quality indicators and availability of indicator data, a soil physical indicator of bulk density, chemical indicators of organic matter, total nitrogen, rapidly-available phosphorus, rapidly-available potassium, and pH as the TDS for soil quality evaluation (Chen, Introduction in Page 565, “Indicators used by Qi et al. (2009) not only included common indicators […]”; Chen, Evaluation of index methods in Page 573, “PC5, PC2 and PC3 were significantly correlated with yield, indicating that available nutrients and texture had more effect on yield than other indicators.”; Chen, Descriptive statistics of soil characteristics and yield in Page 568, “The indicators in the TDS or MDS were weighted based on results of the mathematical statistics (Table IV) […] Silt, clay, SOM, and TN had higher weights, whereas Bd had the lowest weight in the TDS. The indicators had weights from 0.1 to 0.14 in the MDS.”; Chen, Table I in Page 568,
PNG
media_image9.png
638
989
media_image9.png
Greyscale
; Examiner’s note: wherein in step S2, the collecting and processing the TDS (i.e., see supra claim 3) comprises: selecting, based on a selection frequency of soil quality indicators (i.e., common indicators used by Qi et al. (2009)) and availability of indicator data (i.e., available nutrients and texture more effect on yield than other indicators), a soil physical indicator of bulk density (i.e., Bd = bulk density), chemical indicators of organic matter (i.e., SOM = soil organic matter), total nitrogen (i.e., TN = total nitrogen), rapidly-available phosphorus (i.e., AvP = available phosphorus), rapidly-available potassium (i.e., AvK = available potassium), and pH as the TDS for soil quality evaluation (i.e., table I teaches the TDS for soil quality evaluation) is taught.)
The combination of Paul and Chen does not explicitly teach:
selecting biological indicators of microbial biomass carbon, microbial biomass nitrogen, sucrase, phosphatase, and urease as the TDS for soil quality evaluation
Jiang teaches:
selecting biological indicators of microbial biomass carbon, microbial biomass nitrogen, sucrase, phosphatase, and urease as the TDS for soil quality evaluation (Jiang, Introduction in Page 2, “Soil microbial biomasses can reflect the environmental changes in the soil and are an important microbiological indicator for reflecting soil quality.”; Jiang, Experimental Methods for Enzyme Activity, Microbial Biomass Carbon, and Nitrogen Measurements in Page 2, “The microbial biomass carbon and nitrogen were extracted by the chloroform fumigation method and 0.5 mol/L K2SO4 extraction method, where the conversion coefficients were 0.45 and 5, respectively (Jien and Wang, 2013; Khan et al., 2020). The urease activity was determined by the indophenol blue colorimetric method […] sucrase activity was measured by reducing sugar titration method (Guan et al., 1986); and soil phosphatase activity was measured by disodium p-nitrophenyl phosphate colorimetry method […]”; Examiner’s note: selecting biological indicators of microbial biomass carbon, microbial biomass nitrogen (i.e., the microbial biomass carbon and nitrogen extracted by the chloroform fumigation method and 0.5 mol/L K2SO4 extraction method), sucrase (i.e., sucrase activity measured by reducing sugar titration method), phosphatase (i.e., soil phosphatase activity measured by disodium p-nitrophenyl phosphate colorimetry method), and urease (i.e., the urease activity determined by the indophenol blue colorimetric method) as the TDS for soil quality evaluation (i.e., soil microbial biomasses are an important microbiological indicator for reflecting soil quality) is taught.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the soil quality assessment using soil-quality indices (SQIs) and random forest machine learning technique in Paul, the minimum data set for assessing soil quality in Chen, and the effects of biochar application on enzyme activities in tea garden soil as taught in Jiang. Paul teaches formulating an overall framework, developing a soil quality prediction model, generating a soil quality extended dataset and a soil quality evaluation dataset, and analyzing data in the soil quality extended dataset and the soil quality evaluation dataset by using the soil quality prediction model. Chen teaches establishing a total dataset (TDS) and a minimum dataset (MIDS), calculating soil quality indices, and evaluating improvement effect of organic materials on soil quality. Jiang teaches selecting biological indicators of microbial biomass carbon, microbial biomass nitrogen, sucrase, phosphatase, and urease as the TDS for soil quality evaluation. One of ordinary skill would have motivation to combine Paul, Chen and Jiang to “be beneficial for the high-efficiency utilization of soil carbon and nitrogen by microorganisms […] beneficial to improve the effectiveness of nutrients in the soil and stimulate the increase of enzyme activities” (Jiang, Conclusion in Page 7).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Paul in view of Chen as applied in claim 1, in view of Li et al. (“Establishing a minimum dataset for soil quality assessment based on soil properties and land-use changes”) (hereinafter Li).
Regarding Claim 6,
The combination of Paul and Chen teaches:
“The ensemble learning-based optimized evaluation method according to claim 3,” (preamble)
The combination of Paul and Chen does not explicitly teach:
“wherein in step S2, the selecting an evaluation indicator for the MDS comprises: calculating Norm values of the evaluation indicator as follows:
PNG
media_image11.png
77
135
media_image11.png
Greyscale
wherein Nik represents a comprehensive loading of an i-th indicator on top k principal components (PCs) with eigenvalues greater than 1; Uik is a loading value of the i-th indicator on a k-th PC; and λk is an eigenvalue of the k-th PC“
Li teaches:
“wherein in step S2, the selecting an evaluation indicator for the MDS comprises: calculating Norm values of the evaluation indicator as follows:
PNG
media_image11.png
77
135
media_image11.png
Greyscale
wherein Nik represents a comprehensive loading of an i-th indicator on top k principal components (PCs) with eigenvalues greater than 1; Uik is a loading value of the i-th indicator on a k-th PC; and λk is an eigenvalue of the k-th PC“ (Li, Section 2, “The Norm value is calculated as:
PNG
media_image12.png
52
132
media_image12.png
Greyscale
where Nik is the total projection of the first k components with eigenvalue >= 1 to the variable i, Uik is the factor loading of soil parameter i on the PC k, and λk is the eigenvalue of the PC k.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the soil quality assessment using soil-quality indices (SQIs) and random forest machine learning technique in Paul, the minimum data set for assessing soil quality in Chen, and the establishing a minimum dataset for soil quality assessment based on soil properties and land-use changes as taught in Li. Paul teaches formulating an overall framework, developing a soil quality prediction model, generating a soil quality extended dataset and a soil quality evaluation dataset, and analyzing data in the soil quality extended dataset and the soil quality evaluation dataset by using the soil quality prediction model. Chen teaches establishing a total dataset (TDS) and a minimum dataset (MIDS), calculating soil quality indices, and evaluating improvement effect of organic materials on soil quality. Li teaches calculating norm values of the evaluation indicator. One of ordinary skill would have motivation to combine Paul, Chen and Li to “identify[] MDS of soil quality assessment, which is able to integrate the influences of land-use changes and land-use duration on soil and can represent maximally all the measured soil parameters with minimal data redundancy” (Li, Introduction in Page 2716).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Paul in view of Chen as applied in claim 1, in view of Chugh (“MAE, MSE, RMSE, Coefficient of Determination, Adjusted R Squared— Which Metric is Better?”).
Regarding Claim 9,
The combination of Paul and Chen teaches:
“The ensemble learning-based optimized evaluation method according to claim 8,” (preamble)
“wherein the developing the soil quality prediction model and assessing accuracy of the soil quality prediction model comprising:“ (see supra claim 8)
“when RPD<1.4, predictive performance of the soil quality prediction model is poor; when 1.4<=RPD<1.8, the model has a certain predictive ability and is capable of assessing the samples; when 1.8<=RPD<2.0, the soil quality prediction model has a good predictive ability and is capable of quantitative prediction; when 2.0<=RPD<2.5, the soil quality prediction model is capable of quantitative prediction with higher accuracy; when RPD>=2.5, the model is excellent and exhibits an extremely satisfactory quantitative prediction ability” (Paul, Table 4,
PNG
media_image13.png
215
1040
media_image13.png
Greyscale
; Paul, Section 3.1.1, “The overall soil quality in the basin area particularly the essential macronutrients N, P, K and S are poor except in the middle and upper catchment area with significantly high standard deviation.”; Examiner’s note: RPD is calculated by using SD and RMSE. Predictive performance of the soil quality prediction model is measured by RPD. Table 4 discloses an example of statistics of the selected soil quality indicators.)
The combination of Paul and Chen does not explicitly teach:
“quantifying performance of the prediction model with a coefficient of determination R2, a root mean square error RMSE, and a relative percent deviation RPD as follows:
PNG
media_image14.png
343
246
media_image14.png
Greyscale
wherein N is the number of samples; yi and ŷi represent a measured value and a corresponding predicted value, respectively;
PNG
media_image4.png
32
21
media_image4.png
Greyscale
represents an average value of predicted values; ȳ represents an average value of measured values“
Chugh teaches:
“quantifying performance of the prediction model with a coefficient of determination R2, a root mean square error RMSE, and a relative percent deviation RPD as follows:
PNG
media_image14.png
343
246
media_image14.png
Greyscale
wherein N is the number of samples; yi and ŷi represent a measured value and a corresponding predicted value, respectively;
PNG
media_image4.png
32
21
media_image4.png
Greyscale
represents an average value of predicted values; ȳ represents an average value of measured values“ (Chugh, R2 in Page 4,
PNG
media_image15.png
72
235
media_image15.png
Greyscale
;
Chugh, Root Mean Squared Error in Page 3, “Root Mean Squared Error is the square root of Mean Squared error. It measures the standard deviation of residuals.”
PNG
media_image16.png
124
405
media_image16.png
Greyscale
; Examiner’s note: RMSE measuring the standard deviation of residuals teaches SD equation. One of ordinary skill in the art can calculate RPD which is SD divided by RMSE.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine the soil quality assessment using soil-quality indices (SQIs) and random forest machine learning technique in Paul, the minimum data set for assessing soil quality in Chen, and the MAE, MSE, RMSE, Coefficient of Determination, Adjusted R Squared as taught in Chugh. Paul teaches formulating an overall framework, developing a soil quality prediction model, generating a soil quality extended dataset and a soil quality evaluation dataset, and analyzing data in the soil quality extended dataset and the soil quality evaluation dataset by using the soil quality prediction model. Chen teaches establishing a total dataset (TDS) and a minimum dataset (MIDS), calculating soil quality indices, and evaluating improvement effect of organic materials on soil quality. Chugh teaches calculating MAE, MSE, RMSE, Coefficient of Determination, SD and Adjusted R squared. One of ordinary skill would have motivation to combine Paul, Chen and Chugh to “evaluate the performance of the model in regression analysis” (Chugh, Page 2, Line 4).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. Huang et al. teaches the long-term intensive management reduced the soil quality of a Carya dabieshanensis forest.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to YONG D RHO whose telephone number is (571)270-0194. The examiner can normally be reached 8am-5pm.
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, Viker Lamardo can be reached at 5712705871. 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.
/YONG DOO RHO/Examiner, Art Unit 2147
/ERIC NILSSON/Primary Examiner, Art Unit 2151
Prosecution Insights