DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
This action is in reply to the amendments and remarks filed on 26 February 2026.
Claims 1, 2, 5, and 12 have been amended.
Claims 1-15 are currently pending and have been examined.
Response to Amendment
Applicant’s amendments are insufficient to overcome the 101 rejections previously raised. Those rejections are respectfully maintained and updated below as necessitated by the amendments to the claims.
Applicant’s amendments have significantly changed the scope of the previously examined claims and have necessitated new grounds of rejection, see below.
Response to Arguments
Applicant’s arguments filed on 26 February 2026 have been fully considered but are not persuasive.
Regarding the 101 applicant argues that the amended claims do not recite a mental process. Examiner respectfully disagrees. The amended claim language is interpreted as reciting a series of observation and evaluation type functions that could be done the same way mentally or manually as well as mathematical concepts that are also considered abstract and are merely applied “by a computer”. See updated grounds of rejection set forth below.
Applicant argues that the claims as a whole are integrated into a practical application and amount to significantly more. Examiner respectfully disagrees. The claims are merely linked to a computerized environment and the steps claimed are instructions that are simply applied by a computer. The use of a computer in a generalized fashion to increase efficiency does not meaningfully limit the otherwise abstract claims. In order for the addition of a machine to impose a meaningful limit on the scope of a claim, it must play a significant part in permitting the claimed method to be performed, rather than function solely as an obvious mechanism for permitting a solution to be achieved more quickly, i.e. through the utilization of a computer in performing calculations. The 101 rejection is respectfully maintained and updated below as necessitated by the amendments to the claims.
Regarding the 103 applicant argues that the previously cited references fail to teach cleaning the data, producing a predicted disease time curve, applying change point detecting to computer a start point index. These arguments have been fully considered but are moot in view of the new grounds of rejection necessitated by the amendments to the claims. See new grounds of rejection set forth below.
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 1-15 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Independent Claim 1 and dependent claims 14 and 15 recite limitations for receiving data, determining disease progression time series data comprising a predicted disease time curve, cleaning the predicted disease time curve and running a change point detection algorithm to determine a start point index and based on the index determining a disease onset date. These limitations, as drafted, illustrate a process that, under its broadest reasonable interpretation, covers performance of the limitations in the mind. Receiving data, making determinations and executing an algorithm to determine a start point index illustrate high level observation and evaluation type functions that could be done the same way mentally or manually with a pen and paper. An algorithm that determines a start point index can also be interpreted as a mathematical concept in that is recites utilizing a mathematical algorithm to determine an index value. But for the computer implemented, apparatus and computer program element language, the claims encompass a user simply observing data and making determinations in their mind and generically linking the functions to a computerized environment. The mere nominal recitation of a generic computer implemented environment, apparatus or program that applies the steps or executes/runs the functions does not take the claim limitations out of the abstract groupings. Thus, the claims recite an abstract idea.
This judicial exception is not integrated into a practical application. The claims recite additional elements including applying a machine learning model that has been trained with conditions and data to determine the disease progression as well as the computer, apparatus and program generically applying the receiving, cleaning, running and determining steps. The receiving is not tied to any specific element. However, even if it was recited as being performed “by the computer”, that would be considered a high level of generality and amount to mere data gathering, which is a form of insignificant extra solution activity. Applying a machine learning model to make a determination, cleaning, and running an algorithm to make a determination are also recited at a high level of generality and merely automates the functions through the application of instructions to implement the abstract idea. Each of the additional elements is no more than mere instructions to apply the exception using a generic computer component or linking the execution to a generic computerized environment. The combination of these additional elements is no more than mere instructions to apply the exception in a generic computer environment with generic computer components. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application. The claims are directed to an abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed with respect to step 2A Prong 2, the additional elements in the claims amount to no more than mere instructions to apply the exception using a generic computer component or linking the steps to a generic computer environment. The same analysis applies here in 2B and does not provide an inventive concept.
For the receiving step that was considered as potentially extra solution activity in step 2A above, this has been re-evaluated in step 2B and determined to be well-understood, routine and conventional activity in the field. The specification does not provide any indication that the computer implementation is anything other than generic, off the shelf computer components, and the Symantec, TLI and OIP Techs. court decisions in MPEP 2106.05 indicate that the mere collection, receipt or transmission of data over a network is a well-understood, routine and conventional function when it is claimed in a merely generic manner, as it is here.
Dependent claims 2-15 include all of the limitations of claim 1 and therefore recite the same abstract idea. The claims merely narrow the recited abstract idea by describing cleaning the data by converting any prediction below .3 to 0, data used to make determinations, algorithms used, describing the type of model, determining an infection rate, conditions included in the determinations, types of models used, data including crop variety, environmental data, location data, and determining a schedule. The specific detection algorithm, type of trained model, Xtreme Gradient Boosting regression model, process based model comprising a susceptible exposed infections removed model can also be considered mathematical concepts applied by a computer or in a generic environment where the computer acts as a tool to implement the instructions.
The additional elements recited fail to transform the claims into a patent eligible invention but instead clarify that the machine learning model and process model applied are merely mathematical models used to analyze data and describe the ability to generate or output a file which is insignificant extra solution activity.
For the generating a file step that was considered outputting and therefore extra solution activity in step 2A above, this has been re-evaluated in step 2B and determined to be well-understood, routine and conventional activity in the field. The specification does not provide any indication that the computer implementation is anything other than generic, off the shelf computer components, and the Symantec, TLI and OIP Techs. court decisions in MPEP 2106.05 indicate that the mere collection, receipt or transmission/outputting of data over a network is a well-understood, routine and conventional function when it is claimed in a merely generic manner, as it is here. These limitations are not sufficient to integrate the abstract idea into a practical application, nor do they amount to significantly more. The apparatus comprising processing units and program element comprising instructions merely establish a generic link between the use of the judicial exception and a particular technological field and therefore are not indicative of integration into a practical application, nor do they amount to significantly more.
Accordingly, claims 1-15 are not drawn to eligible subject matter as they are directed to an abstract idea without significantly more.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-15 are rejected under 35 U.S.C. 103 as being unpatentable over Wiles et al. (US 9563852) in view of Fores et al. (US 2022/0414795) further in view of Perry (US 20210224927).
As per Claim 1 Wiles teaches:
A computer-implemented method for determining a disease progression usable for fungicide spray schedule on an agricultural field, the method comprising:
a) receiving data including: crop variety data relating to a crop grown or to be grown on an agricultural field (Wiles :Fig. 1 and at least Col. 6:15-Col. 9:18, "Input data 110 may further include crop and planting data 116, such as crop type, seed type, planting data, growing season data and projections, projected harvest date, crop canopy and soil conditions over time, relative maturity, planting or emergence date, crop temperature, crop moisture, seed moisture, plant depth, row width, and any other crop and plant information that may be used to profile the risk assessment 145, and the pest occurrence predictions 122 forming the output data 120. Crop and planting data 116 may further comprise crop management information that incorporates all of the above types of data. Regardless, crop and planting data 116 may be provided as output data from one or more of phenology models of crop and plant growth, and other methods of predicting crop and plant growth over the course of a growing season, such as continual crop development profiling of the like disclosed in U.S. Patent No. 9, 131 ,644. Similarly, harvest data may be provided as output data from one or more models of harvestability, such as those disclosed in U.S. Patent No. 9,076, 1 18.",)); environmental data indicative of an environmental condition for the agricultural field (Wiles in at least see also Fig. 1 and 6:15-Col. 9:18 describe environmental constraints and biological characteristics and data, "The positional coordinates of reporting fields 104 and targeted fields 106 may identify a specific agro-ecological zone for a localized modeling of infestation suitability. While it is to be expected that weather patterns and crop management are similar within a common agro- ecological zone, it should be noted that an agro- ecological zone may be defined by either or both environment and management practices, rather than merely using distance alone." and D1 : "Regardless of the method or approach employed to arrive at selected predictors 160, the model 100 analyzes the set of descriptors defining a similarity comparison between the reporting field 104 and the targeted fields 106 from the expected pest- environment relationship to create the risk assessment profile 145 for the targeted field 106 from selected environmental and crop management predictors 160."); location data of the agricultural field (Wiles in at least Col. 9:19-29 describes positional coordinates and Fig. 1 illustrates "Input data 110 may also include GPS data 1 13 that enables the crowd-sourced pest and disease model 100 to correlate reporting fields 104 and targeted fields 106. Such GPS data 113 enables GPS receivers to determine positional coordinates and/ or boundaries of both reporting fields 104 and targeted fields 106 and their proximity to each other. This allows the crowd-sourced pest and disease model 100 to determine a geographical correlation for profiling the risk assessment 145 and prediction of pest occurrence 122 in targeted fields 106, based on the reported pest presence data 11 1 in reporting fields 104, as discussed further herein. Other methods of correlating fields 104 and 106 may also be utilized and are within the scope of the present invention." and D1 : "This method may employ many different statistical processes 146 that apply to analysis of a binary classification (i.e. presence or absence). Samples of locations having a reported pest presence provide the most suitable data for developing an infestation suitability model 148. Nonetheless, the present invention contemplates that fields without reports of a pest presence may be used in a reasonable sampling of other locations, particularly where an agriculture retailer or crop consultant working on a large number of fields in an area needs information on all interested fields.");
b) applying a machine-learning model to the received data to determine disease progression time-series data of a fungal disease (Wiles in at least Col. 11:7-Col. 12:44, Col. 13: 28-Col.14:3, Col. 14:16-54, Col. 17:47-Col. 18:2, describes "The present invention applies unsupervised machine learning in implementing each of these steps, and in many of these approaches, these steps are not distinct. Regardless, some form of unsupervised machine learning is applied to the descriptors 161 representing variables of the infested fields 104" and Wiles "Regardless of the specific method, the unsupervised learning engine 144 may apply one or more of statistical analyses 146 and other mathematical processes 147 to create an infestation suitability model 148 from the pest presence data 1 11.The infestation suitability model 148 may be considered as application of artificial intelligence, for example in one or more models 165 that automatically and continually identify additional descriptors 161 and select additional environmental and crop management predictors 160, as well as any coefficients for those predictors 160 related to the multivariate similarity analysis 149, for the pest-environment relationship 143 as additional crowd- sourced information is received. One such method involves assigning weighted vectors of the field variables, where weights denote the importance of each variable identified in the pest- environment relationship. The unsupervised learning engine 144 models these weighted vectors of field variables by performing statistical analyses 146 and other mathematical processes 147 to estimate a probability that targeted fields 106 will be infested. The unsupervised learning engine 144 generates a risk assessment profile 145 based on this estimate. The profile 145 is applied to generate the pest occurrence prediction 122 as output data 120." The incorporates methods of calculating and analyzing time series data, e.g. a time curve) , wherein the machine-learning model has been trained to learn the disease progression under a condition defined by crop variety data, environmental data, crop management data, and location data based on historic data collected from one or more agricultural fields (Wiles "pest and disease model 100", wherein the disease progression time series data comprises a predicted disease time curve (Wiles Col. 8:46-57 describe crop and planting data including defining time periods for predictions and the ability to identify a specific time period for an infestation in addition to a prediction that an infestation will occur);
Wiles in at least Col. 6:15-48 describes receiving input data including crop and seed history and any prior pest or disease infestations, cropping history and pest presence. Col. 15:7-14 describes analyzing the data to identify suitable windows of opportunity for performing certain cultivation tasks or applying treatments to avoid or mitigate damage from infestation. Wiles does not explicitly recite historical data relating to fungicide spray or treatments performed nor does Wiles explicitly describe determining an onset date based on disease progression time series data.
However, Fores teaches crop disease prediction and treatment based on AI and machine learning models. Fores further teaches:
- crop management data indicative of fungicide spray history for the agricultural field (Fores in at least [0017-0019, 0036, 0043, 0085-0088, 0101, 0136-0137] describe previous plant disease and treat of previous plant disease as being part of the historical records and data used by the system); and
wherein the disease progression time series data comprises a predicted disease time curve (Fores in at least [0046, 0164, 0189])
c) cleaning the predicted disease time curve (Fores in at least [0193 and Fig. 6 illustrate cleaning data); and
d) running a change point detection algorithm on the cleaned predicted disease time curve (Fores in at least [0046, 0129, 0149, 0154, 0176, 0189] describes determining, using trained machine learning models and other predictive methods including change and lag time analyses, state and parameter changes, diseases in plants, disease occurrence, disease development as a function of time, disease growth, spread and prediction, and upcoming disease hotspots see also [0164, 0178, 0180, 0189, 0194, 0195, 0200] ); and
e) determining a disease onset date of the fungal disease (Fores in at least [0129, 0149, 0154] describes determining, using trained machine learning models and other predictive methods, diseases in plants, disease occurrence, disease development as a function of time, disease growth, spread and prediction, and upcoming disease hotspots see also [0164, 0178, 0180, 0189, 0194, 0195, 0200]).
Therefore, it would be obvious to one of ordinary skill in the art to modify the ability to apply machine learning models to determine disease progression and identify suitable windows of opportunity to include techniques for gathering data indicative of historical treatment and using that in combination with other data to determine a specific disease onset date or predicted occurrence because each of the elements were known but not necessarily combined as claimed. The technical ability exists to combine the elements as claimed and the result of the combination is predictable because each of the elements perform the same function as they did individually. By incorporating historical treatment data into an analysis technique that also determines a disease onset date or predicted occurrence using different change analytics and algorithms that can further be utilized to schedule and apply treatments, the combination reduces the likelihood of a disease occurring in a second plant or field by determining the likelihood of a disease being present at multiple locations at specific times and applying targeted treatments where needed.
Neither Wiles nor Fores explicitly recite that the change point detection is to determine a start point index that is the basis for determining the onset date. However, Perry teaches data comprises vegetation indices associated with plants in at least (Perry [0010, 0102]). Perry further teaches:
d) running a change point detection algorithm on the cleaned predicted disease time curve to determine a start point index of the cleaned predicted disease time curve (Perry in at least [0010, 0102 teaches NVDI data determined from change analysis and used to predict onset)
Therefore, it would be obvious to one of ordinary skill in the art to modify the ability to determine onset dates for disease to include techniques utilizes particular indices relating to a starting point because each of the elements were known but not necessarily combined as claimed. The technical ability exists to combine the elements as claimed and the result of the combination is predictable because each of the elements perform the same function as they did individually. By incorporating indices into an analysis technique that also determines a disease onset date or predicted occurrence using different change analytics and algorithms that can further be utilized to schedule and apply treatments, the combination reduces the likelihood of a disease occurring in a second plant or field by determining the likelihood of a disease being present at multiple locations at specific times and applying targeted treatments where needed.
As per Claim 2 Wiles does not explicitly recite but Fores further teaches:
wherein cleaning the predicted disease time curve comprises converting any prediction below .3 as 0 (Fores in at least [0193 and Fig. 6 illustrate cleaning data, [0153] describes the ability to calibrate data into any scaled/normalized or converted method as specified by the user so that it is meaningful for inclusion in the analysis).
Fores is combined based on the same reasons and rationale set forth in the rejection of Claim 1 above.
As per Claim 3 Wiles further teaches:
wherein a plurality of machine-learning models are provided for two or more fungal diseases, and each machine-learning model has been trained for a single disease (Wiles in at least Col. 11:7-Col. 12:44, Col. 13: 28-Col.14:3, Col. 14:33-54, Col. 17:47-Col. 18:2, describes training and retraining as well as "The present invention applies unsupervised machine learning in implementing each of these steps, and in many of these approaches, these steps are not distinct. Regardless, some form of unsupervised machine learning is applied to the descriptors 161 representing variables of the infested fields 104" and Wiles "Regardless of the specific method, the unsupervised learning engine 144 may apply one or more of statistical analyses 146 and other mathematical processes 147 to create an infestation suitability model 148 from the pest presence data 1 11.The infestation suitability model 148 may be considered as application of artificial intelligence, for example in one or more models 165 that automatically and continually identify additional descriptors 161 and select additional environmental and crop management predictors 160, as well as any coefficients for those predictors 160 related to the multivariate similarity analysis 149, for the pest-environment relationship 143 as additional crowd- sourced information is received. One such method involves assigning weighted vectors of the field variables, where weights denote the importance of each variable identified in the pest- environment relationship. The unsupervised learning engine 144 models these weighted vectors of field variables by performing statistical analyses 146 and other mathematical processes 147 to estimate a probability that targeted fields 106 will be infested. The unsupervised learning engine 144 generates a risk assessment profile 145 based on this estimate. The profile 145 is applied to generate the pest occurrence prediction 122 as output data 120." Other models may also be utilized, particularly where additional information such as absence data is incorporated, for example regression-type models may also be applied, such as multivariate adaptive regression splines (MARS), regression trees, generalized additive models (GAMs), generalized dissimilarity models, and generalized linear models. Other machine learning models may also be suitable, such as maximum entropy models (MAXENT and MAXENT-T) and boosted decision / regression trees or stochastic gradient boosting.).
As per Claim 4 Wiles further teaches:
wherein the machine-learning model comprises an Xtreme Gradient Boosting, XGB, regression model (Wiles in at least Col. 11:7-Col. 12:44, Col. 13: 28-Col.14:3, Col. 14:33-54, Col. 17:47-Col. 18:2, "The present invention applies unsupervised machine learning in implementing each of these steps, and in many of these approaches, these steps are not distinct. Regardless, some form of unsupervised machine learning is applied to the descriptors 161 representing variables of the infested fields 104" and Wiles "Regardless of the specific method, the unsupervised learning engine 144 may apply one or more of statistical analyses 146 and other mathematical processes 147 to create an infestation suitability model 148 from the pest presence data 1 11.The infestation suitability model 148 may be considered as application of artificial intelligence, for example in one or more models 165 that automatically and continually identify additional descriptors 161 and select additional environmental and crop management predictors 160, as well as any coefficients for those predictors 160 related to the multivariate similarity analysis 149, for the pest-environment relationship 143 as additional crowd- sourced information is received. One such method involves assigning weighted vectors of the field variables, where weights denote the importance of each variable identified in the pest- environment relationship. The unsupervised learning engine 144 models these weighted vectors of field variables by performing statistical analyses 146 and other mathematical processes 147 to estimate a probability that targeted fields 106 will be infested. The unsupervised learning engine 144 generates a risk assessment profile 145 based on this estimate. The profile 145 is applied to generate the pest occurrence prediction 122 as output data 120." Other models may also be utilized, particularly where additional information such as absence data is incorporated, for example regression-type models may also be applied, such as multivariate adaptive regression splines (MARS), regression trees, generalized additive models (GAMs), generalized dissimilarity models, and generalized linear models. Other machine learning models may also be suitable, such as maximum entropy models (MAXENT and MAXENT-T) and boosted decision / regression trees or stochastic gradient boosting.).
As per Claim 5 Wiles further teaches:
f) applying a process-based model to determine an infection rate of the fungal disease after the disease onset date under a condition defined by the crop variety data, the environmental data, the crop management data, and the location data (Wiles in at least Col. 11:7-Col. 12:44, Col. 13: 28-Col.14:3, Col. 14:33-54, Col. 17:47-Col. 18:2, "One exemplary application of a time-series look-back in the present invention is as follows. Stewart's disease is a bacterial disease affecting corn crops that is spread by corn ilea beetle. Warm winter air temperatures in December, January, and February may increase the survival of corn flea beetle and result in greater transmission of the bacterium in the following growing season. The present invention would not need a model of winter survival of corn flea beetle; instead the model looks for fields that had similar winter weather, along with recent conditions conducive for disease infection, to develop a prediction of pest occurrence in the coming growing season. In addition to the approaches described above, the present invention may further incorporate one or more existing modeling approaches (or, an ensemble of such approaches) that may be suitable for identifying the set of descriptors 161 , and selecting environmental and crop management predictors 160, that are used to construct the localized and adaptive infestation suitability model 148 for determining a risk of pest occurrence in the one or more targeted fields 106. Such approaches include an envelope method, such as BIOCLIM, and distance-based methods such as DOMAIN and LIVES that assess possible infestation sites in terms of environmental similarity to areas with a known pest presence. Other models may also be utilized, particularly where additional information such as absence data is incorporated, for example regression-type models may also be applied, such as multivariate adaptive regression splines (MARS), regression trees, generalized additive models (GAMs), generalized dissimilarity models, and generalized linear models. Other machine learning models may also be suitable, such as maximum entropy models (MAXENT and MAXENT-T) and boosted decision / regression trees or stochastic gradient boosting.").
As per Claim 6 Wiles further teaches:
wherein the infection rate of the fungal disease is determined by further including a condition defined by a variety disease resistance level of the crop(Wiles in at least Col. Col. 7:44-Col:8:6, 11:7-Col. 12:44, Col. 13: 28-Col.14:3, Col. 14:33-54, Col. 17:47-Col. 18:2, describes resistance tolerance data, "One exemplary application of a time-series look-back in the present invention is as follows. Stewart's disease is a bacterial disease affecting corn crops that is spread by corn ilea beetle. Warm winter air temperatures in December, January, and February may increase the survival of corn flea beetle and result in greater transmission of the bacterium in the following growing season. The present invention would not need a model of winter survival of corn flea beetle; instead the model looks for fields that had similar winter weather, along with recent conditions conducive for disease infection, to develop a prediction of pest occurrence in the coming growing season. In addition to the approaches described above, the present invention may further incorporate one or more existing modeling approaches (or, an ensemble of such approaches) that may be suitable for identifying the set of descriptors 161 , and selecting environmental and crop management predictors 160, that are used to construct the localized and adaptive infestation suitability model 148 for determining a risk of pest occurrence in the one or more targeted fields 106. Such approaches include an envelope method, such as BIOCLIM, and distance-based methods such as DOMAIN and LIVES that assess possible infestation sites in terms of environmental similarity to areas with a known pest presence. Other models may also be utilized, particularly where additional information such as absence data is incorporated, for example regression-type models may also be applied, such as multivariate adaptive regression splines (MARS), regression trees, generalized additive models (GAMs), generalized dissimilarity models, and generalized linear models. Other machine learning models may also be suitable, such as maximum entropy models (MAXENT and MAXENT-T) and boosted decision / regression trees or stochastic gradient boosting.").
As per Claim 7 Wiles further teaches:
wherein the infection rate of the fungal disease is determined by further including a condition defined by fungicide application data including fungicide data of a fungicide product to be used and at least one planned application timing (Wiles in at least Col. 11:7-Col. 12:44, Col. 13: 28-Col.14:3, Col. 14:33-54, Col. 17:47-Col. 18:2,"One exemplary application of a time-series look-back in the present invention is as follows. Stewart's disease is a bacterial disease affecting corn crops that is spread by corn ilea beetle. Warm winter air temperatures in December, January, and February may increase the survival of corn flea beetle and result in greater transmission of the bacterium in the following growing season. The present invention would not need a model of winter survival of corn flea beetle; instead the model looks for fields that had similar winter weather, along with recent conditions conducive for disease infection, to develop a prediction of pest occurrence in the coming growing season. In addition to the approaches described above, the present invention may further incorporate one or more existing modeling approaches (or, an ensemble of such approaches) that may be suitable for identifying the set of descriptors 161 , and selecting environmental and crop management predictors 160, that are used to construct the localized and adaptive infestation suitability model 148 for determining a risk of pest occurrence in the one or more targeted fields 106. Such approaches include an envelope method, such as BIOCLIM, and distance-based methods such as DOMAIN and LIVES that assess possible infestation sites in terms of environmental similarity to areas with a known pest presence. Other models may also be utilized, particularly where additional information such as absence data is incorporated, for example regression-type models may also be applied, such as multivariate adaptive regression splines (MARS), regression trees, generalized additive models (GAMs), generalized dissimilarity models, and generalized linear models. Other machine learning models may also be suitable, such as maximum entropy models (MAXENT and MAXENT-T) and boosted decision / regression trees or stochastic gradient boosting.").
As per Claim 8 Wiles further teaches:
wherein the process-based model comprises a susceptible-exposed-infections-removed, SEIR, model (Wiles in at least Col. 6:15-34, Col. 11:7-Col. 12:44, Col. 13: 28-Col.14:3, Col. 14:33-54, Col. 17:47-Col. 18:2, describe susceptibility data, "One exemplary application of a time-series look-back in the present invention is as follows. Stewart's disease is a bacterial disease affecting corn crops that is spread by corn ilea beetle. Warm winter air temperatures in December, January, and February may increase the survival of corn flea beetle and result in greater transmission of the bacterium in the following growing season. The present invention would not need a model of winter survival of corn flea beetle; instead the model looks for fields that had similar winter weather, along with recent conditions conducive for disease infection, to develop a prediction of pest occurrence in the coming growing season. In addition to the approaches described above, the present invention may further incorporate one or more existing modeling approaches (or, an ensemble of such approaches) that may be suitable for identifying the set of descriptors 161 , and selecting environmental and crop management predictors 160, that are used to construct the localized and adaptive infestation suitability model 148 for determining a risk of pest occurrence in the one or more targeted fields 106. Such approaches include an envelope method, such as BIOCLIM, and distance-based methods such as DOMAIN and LIVES that assess possible infestation sites in terms of environmental similarity to areas with a known pest presence. Other models may also be utilized, particularly where additional information such as absence data is incorporated, for example regression-type models may also be applied, such as multivariate adaptive regression splines (MARS), regression trees, generalized additive models (GAMs), generalized dissimilarity models, and generalized linear models. Other machine learning models may also be suitable, such as maximum entropy models (MAXENT and MAXENT-T) and boosted decision / regression trees or stochastic gradient boosting.").
As per Claim 9 Wiles further teaches:
wherein the crop variety data comprises one or more of growth stage of the crop, days after plantation, and/or a variety disease resistance level of the crop (Wiles Fig. 1 and at least Col. 6:15-Col. 9:18 "The present invention also contemplates that the unsupervised learning engine 144 may include applying one or more methods to measure the similarity of time series of one or more weather variables for developing the infestation suitability model 148. Such methods involve calculating the similarity of time series of weather data, which may be constructed for each field based on calendar date or crop date (for example, a number of days since planting, or days since a certain crop growth stage). Such a calculation of the similarity of time series of weather day may also serve as one or more of the environmental and crop management predictors 160, in addition to a separate step in the overall unsupervised learning engine 144.").
As per Claim 10 Wiles further teaches:
wherein the environmental data comprises one or more of air temperature, cloud cover, short ware radiation, long wave radiation, ice accumulation period, liquid accumulation period, relative humidity, precipitation accumulation period adjusted, snow accumulation period, and/or wind speed (Wiles in at least see also Fig. 1 and 6:15-Col. 9:18 "The positional coordinates of reporting fields 104 and targeted fields 106 may identify a specific agro-ecological zone for a localized modeling of infestation suitability. While it is to be expected that weather patterns and crop management are similar within a common agro- ecological zone, it should be noted that an agro- ecological zone may be defined by either or both environment and management practices, rather than merely using distance alone." and D1 : "Regardless of the method or approach employed to arrive at selected predictors 160, the model 100 analyzes the set of descriptors defining a similarity comparison between the reporting field 104 and the targeted fields 106 from the expected pest- environment relationship to create the risk assessment profile 145 for the targeted field 106 from selected environmental and crop management predictors 160.").
As per Claim 11 Wiles further teaches:
wherein the location data comprises latitude and longitude data (Wiles in at least Col. 9:19-29 describes positional coordinates and Fig. 1 illustrates "Input data 110 may also include GPS data 1 13 that enables the crowd-sourced pest and disease model 100 to correlate reporting fields 104 and targeted fields 106. Such GPS data 113 enables GPS receivers to determine positional coordinates and/ or boundaries of both reporting fields 104 and targeted fields 106 and their proximity to each other. This allows the crowd-sourced pest and disease model 100 to determine a geographical correlation for profiling the risk assessment 145 and prediction of pest occurrence 122 in targeted fields 106, based on the reported pest presence data 11 1 in reporting fields 104, as discussed further herein. Other methods of correlating fields 104 and 106 may also be utilized and are within the scope of the present invention." and D1 : "This method may employ many different statistical processes 146 that apply to analysis of a binary classification (i.e. presence or absence). Samples of locations having a reported pest presence provide the most suitable data for developing an infestation suitability model 148. Nonetheless, the present invention contemplates that fields without reports of a pest presence may be used in a reasonable sampling of other locations, particularly where an agriculture retailer or crop consultant working on a large number of fields in an area needs information on all interested fields.").
As per Claim 12 Wiles further teaches:
g) determining based on the disease progression time series data and the disease onset date, a fungicide spray schedule (Wiles in at least Col. 14: 55-Col. 15:22 describes applying a risk profile to identify suitable windows of opportunity for performing certain cultivation tasks, or applying treatments, e.g. a schedule, to avoid to mitigate damage from infestation, examples of management actions include application of preventative treatments, setting traps, applying pesticides, etc. as is described in at least Col. 16:11-Col. 17:26).
As per Claim 13 Wiles in at least Col. 14: 55-Col. 15:22 describes applying a risk profile to identify suitable windows of opportunity for performing certain cultivation tasks, or applying treatments, to avoid to mitigate damage from infestation, examples of management and control actions include application of preventative treatments, setting traps, applying pesticides, etc. as is described in at least Col. 16:1-Col. 17:26 where outputs including data are also described.
Wiles does not explicitly recite outputting a file configuring a sprayer for application. However, Fores further teaches:
f) generating, based on the fungicide spray schedule, a configuration file usable for configuring a sprayer for fungicide spray application (Fores in at least [0117-0129] describes a suitable application running on a mobile device directing a worker to perform targeting spraying of specific plants, [0141] describes a treatment unit that could also be a drone fitted with a treatment substance).
Therefore, it would be obvious to one of ordinary skill in the art to modify the ability to apply machine learning models to determine disease progression and identify suitable windows of opportunity to include techniques for gathering data indicative of historical treatment and using that in combination with other data to determine a specific disease onset date or predicted occurrence and treat the disease accordingly because each of the elements were known but not necessarily combined as claimed. The technical ability exists to combine the elements as claimed and the result of the combination is predictable because each of the elements perform the same function as they did individually. By incorporating historical treatment data into an analysis technique that also determines a disease onset date or predicted occurrence using different change analytics and algorithms that can further be utilized to schedule and apply treatments, the combination reduces the likelihood of a disease occurring in a second plant or field by determining the likelihood of a disease being present at multiple locations at specific times and applying targeted treatments where needed.
As per Claims 14 and 15 the limitations are substantially similar to those set forth in Claim 1 and are therefore rejected based on the same reasons and rationale set forth in the rejection of Claim 1 above. Regarding the apparatus comprising processing units to generate an application scheme including instructions and a program element comprising instructions to cause the apparatus to execute the steps of the method Wiles further teaches in at least Col: 9:57- Col. 10:26 describe components configured to execute program instructions or routines to perform the functions claimed as well as processing components configured to perform the claimed methodology. See also Col. 19:34-67.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to STEPHANIE Z DELICH whose telephone number is (571)270-1288. The examiner can normally be reached on Monday - Friday 7-3:30.
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, Rutao Wu can be reached on 571-272-6045. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/STEPHANIE Z DELICH/Primary Examiner, Art Unit 3623
Prosecution Insights