DETAILED ACTION
This is a non-final, first office action on the merits. Claims 1-20 are pending. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. Specifically, claims 1-20 are directed to an abstract idea without additional elements amounting to significantly more than the abstract idea.
With respect to Step 2A Prong One of the framework, claims 1, 16, and 18 recite an abstract idea. Claims 1, 16, and 18 include “receiving a request for a crop disease prediction related to treatment of a target plot for one or more crop disease, the request including crop disease type data and location data relating to the target plot, the crop disease type data including multiple identifiers each associated with a different one of multiple crop disease types; accessing, a multiple disease joint model consistent with the location data; determining, the multiple disease joint model, a first disease likelihood output and a second disease likelihood output based on at least the location data, the first disease likelihood output and the second disease likelihood output each associated with a different one of the multiple disease types; generating, a treatment recommendation based on the first disease likelihood output and the second disease likelihood output of the multiple disease joint model; directing, application of at least one treatment to the target plot, based on the treatment recommendation output; and generating a treatment recommendation based on the first disease likelihood output and the second disease likelihood output of the multiple disease joint model”.
The limitations above recite an abstract idea under Step 2A Prong One. More particularly, the elements above recite mental processes-concepts performed in the human mind (including an observation, evaluation, judgment, opinion) because the elements describe a process for directing crop disease treatments to plots. As a result, claims 1, 16, and 18 recite an abstract idea under Step 2A Prong One.
Claims 2-15, 17, and 19-20 further describe the process for directing crop disease treatments to plots. As a result, claims 2-15, 17, and 19-20 recite an abstract idea under Step 2A Prong One for the same reasons as stated above with respect to claims 1, 16, and 18.
With respect to Step 2A Prong Two of the framework, claims 1, 16, and 18 do not include additional elements that integrate the abstract idea into a practical application. Claims 1, 16, and 18 include additional elements that do not recite an abstract idea under Step 2A Prong One. The additional elements of claims 1, 16, and 18 include a computing device, a non-transitory computer-readable storage medium, computer executable instructions, and one processor. When considered in view of the claim as a whole, the additional elements do not integrate the abstract idea into a practical application because the additional computing elements are generic computing elements that are merely used as a tool to perform the recited abstract idea. As a result, claims 1, 16, and 18 do not include additional elements that integrate the abstract idea into a practical application under Step 2A Prong Two.
Claims 3, 6-11, 17, and 19 do not include any additional elements beyond those recited with respect to claims 1, 16, and 18. As a result, claims 3, 6-11, 17, and 19 do not include additional elements that integrate the abstract idea into a practical application under Step 2A Prong Two for the same reasons as stated above with respect to claims 1, 16, and 18.
Claims 2, 4-5, 12-15, and 20 include additional elements that do not recite an abstract idea under Step 2A Prong One. The additional elements of claims 2, 4-5, 12-15, and 20 include a neural network regression model, a neural network regression model, a neural network covariance function, a communication device, an application, and a website. When considered in view of the claims as a whole, the additional elements do not integrate the abstract idea into a practical application because the additional computing elements do no more than generally link the use of the recited abstract idea to a particular technological environment. As a result, claims 2, 4-5, 12-15, and 20 do not include additional elements that integrate the abstract idea into a practical application under Step 2A Prong Two.
With respect to Step 2B of the framework, claims 1, 16, and 18 do not include additional elements amounting to significantly more than the abstract idea. As noted above, claims 1, 16, and 18 include additional elements that do not recite an abstract idea under Step 2A Prong One. The additional elements of claims 1, 16, and 18 include a computing device, a non-transitory computer-readable storage medium, computer executable instructions, and one processor. The additional elements do not amount to significantly more than the abstract idea because the additional computing elements are generic computing elements that are merely used as a tool to perform the recited abstract idea. Further, looking at the additional elements as an ordered combination adds nothing that is not already present when considering the additional elements individually. As a result, independent claims 1, 16, and 18 do not include additional elements that amount to significantly more than the abstract idea under Step 2B.
Claims 3, 6-11, 17, and 19 do not include any additional elements beyond those recited with respect to claims 1, 16, and 18. As a result, claims 3, 6-11, 17, and 19 do not include additional elements that amount to significantly more than the abstract idea under Step 2B for the same reasons as stated above with respect to claims 1, 16, and 18.
Claims 2, 4-5, 12-15, and 20 include additional elements that do not recite an abstract idea under Step 2A Prong One. The additional elements of claims 2, 4-5, 12-15, and 20 include a neural network regression model, a neural network regression model, a neural network covariance function, a communication device, an application, and a website. The additional elements do not amount to significantly more than the abstract idea because the additional computing elements do no more than generally link the use of the recited abstract idea to a particular technological environment. Further, looking at the additional elements as an ordered combination adds nothing that is not already present when considering the additional elements individually. As a result, claims 2, 4-5, 12-15, and 20 do not include additional elements that amount to significantly more than the abstract idea under Step 2B.
Therefore, the claims are directed to an abstract idea without additional elements amounting to significantly more than the abstract idea. Accordingly, claims 1-20 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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 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 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-4 and 6-19 are rejected under 35 U.S.C. 103 as being unpatentable over Ruff et al. (US Pub No. 2020/0272971) (hereinafter Ruff et al.) in view of Carroll et al. (US Pub No. 2019/0156255) (hereinafter Carroll et al.).
Regarding claim 1, Ruff discloses a computer-implemented method for directing crop disease treatments to plots, the computer-implemented method comprising:
receiving, by a computing device, a request for a crop disease prediction related to treatment of a target plot for one or more crop disease, the request including crop disease type data and location data relating to the target plot, the crop disease type data including multiple identifiers each associated with a different one of multiple crop disease types (see Ruff, paras [0075], [0115], & [0166], wherein one or more user-controlled computer operations are requested or triggered to obtain data for use by the system 130; para [0092], wherein the model may include a model of past events on the one or more fields, a model of the current status of the one or more fields, and/or a model of predicted events on the one or more fields; para [0154], wherein receives one or more different treatments from surrounding areas……the trial may require one or more testing locations to be placed in an area of the field with conditions differing from the rest of the field and/or areas of the field spanning different types of conditions; para [0175], wherein pest and disease data may include subfield pathogen presence in plant tissue, residue, and soil, damage type and extent from biotic stress caused by insects; para [0238], wherein two locations on a field may comprise different soil types, but have a similar yield and a similar pest problem; and para [0340], wherein risk coverage data 1816 may comprise a grower identifier, product information, data identifying return due to overperformance);
accessing, by the computing device, a multiple disease joint model consistent with the location data (see Ruff, para [0091], wherein model and field data is stored in model and field data repository 160. Model data comprises data models created for one or more fields. For example, a crop model may include a digitally constructed model of the development of a crop on the one or more fields. "Model," in this context, refers to an electronic digitally stored set of executable instructions and data values, associated with one another, which are capable of receiving and responding to a programmatic or other digital call, invocation, or request for resolution based upon specified input values, to yield one or more stored or calculated output values that can serve as the basis of computer-Implemented recommendations, output data displays, or machine control, among other things. The models disclosed herein to abstract concepts; instead, each model herein has a practical application in a computer in the form of stored executable instructions and data that implement the model using the computer. The model may include a model of past events on the one or more fields, a model of the current status of the one or more fields, and/or a model of-predicted events on the one or more fields);
determining, by the computing device, via the multiple disease joint model, a first disease likelihood output and a second disease likelihood output based on at least the location data (see Ruff, paras [0182]-[0188] & [0349], wherein the agricultural intelligence computing system may use the environmental factors to determine which fields are at risk and select fields based on the risk percentage or a computed severity of risked damage…..The agricultural intelligence computing system may identify one or more fields which have been damaged by fungus in the past and/or are likely to be damaged by fungus in the future. The agricultural intelligence computing system may additionally determine that a yield of the field and/or total profit for the field would result or be benefited by application of a particular fungicide…..the probabilistic distributions generated using the models described herein allow the agricultural intelligence computer system to select a guaranteed yield value based on a likelihood of yield being below or above the selected value, thereby ensuring that yield guarantees sent to field manager computing devices are high enough to depict an increase in yield for agronomic fields while being low enough that few fields will perform under the guarantees. By providing said guarantee values to field manager computing devices, the agricultural intelligence computer system uses input data to generate improved interfaces that allow field managers lo make better decisions for planting agronomic fields);
generating, by the computing device, a treatment recommendation based on the first disease likelihood output and the second disease likelihood output of the multiple disease joint model (see Ruff, paras [0152], [0182], [0349], & [0356], wherein the portion of the agricultural field comprises a whole field such that the trial comprises a recommendation for one or more different practices being performed on the agricultural field. Implementations which utilize part or all of the agricultural field are described further herein….the trial comprises a fungicide trial, the agricultural intelligence computer system may identify a location for evaluating the trial which includes a control location and a treatment location); and
directing, by the computing device, application of at least one treatment to the target plot, based on the treatment recommendation output (see Ruff, paras [0154] and [0160], wherein an area of an agronomic field that receives one or more different treatments from surrounding areas. Thus, a testing location may refer to any shape of land on an agronomic field…..The agricultural intelligence computing system may generate one or more scripts for a field implement on the one or more fields that causes the field implement to apply the product and/or management practices in the one or more locations).
Ruff et al. fails to explicitly disclose the first disease likelihood output and the second disease likelihood output each associated with a different one of the multiple disease types.
Analogous art Carroll discloses the first disease likelihood output and the second disease likelihood output each associated with a different one of the multiple disease types (see Carroll, paras [0002]-[0007] & [0145], wherein modeling a likelihood of particular diseases presenting on a field based on field data and then using the resulting data models to improve plant pathology, plant pest control, agriculture, or agricultural management……the model of disease probability uses a plurality of randomly generated decision trees to determine a likelihood of onset of a particular disease. For example, the model of disease probability may comprise a random forest classifier which accepts inputs of the one or more factors described herein and outputs a likelihood of onset of a disease for a crop on a given day. Code for implementing a random forest classifier is readily available on public open source program code repository systems).
Ruff directed to a system for implementing trials of the particular practices and tracking the performance of the particular practices. Carroll directed to identifying a probability of a particular disease for the one or more crops on the field based, at least in part, on the one or more crop risk factors. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Ruff, regarding the System for Modeling and Tracking of Agricultural Fields for Implementing Agricultural Field Trials, to have included the first disease likelihood output and the second disease likelihood output each associated with a different one of the multiple disease types because both inventions teach improving plant pathology use efficiency. Further, the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Regarding claim 2, Ruff discloses the computer-implemented method of claim 1, wherein the multiple disease joint model includes at least one of a coregionalization architecture with a separable covariance function, a linear regression model, a neural network regression model, a neural network covariance function, a vector autoregression architecture, a multi-task learning architecture, a shared smoothing penalties architecture, and a Gaussian process model (see Ruff, para [0225], wherein other machine-learning methods known to someone skilled in the art for capturing various relationships between the seeding rate (in conjunction with other attributes) and the crop yield lift, such as neural networks or regression techniques, can also be used; and para [0334], wherein the yield probabilities may comprise a probability value for each of a plurality of yield values. For example, the agricultural intelligence computer' system may compute an expected yield and yield variance for a particular agricultural treatment. Based on the expected yield and yield variance, the agricultural intelligence computer system may determine probabilities for each of a plurality of yield values, such as a probability for each integer yield value between 1 and 500 bushels per acre).
Regarding claims 3 and 19, Ruff discloses the computer-implemented method of claim 2, wherein the multiple disease joint model includes a coregionalization architecture to jointly model occurrence probabilities and/or disease severity probabilities of multiple crop disease types, where model data is shared across the multiple crop disease types, locations of multiple plots, and multiple observation dates, using a separable covariance function (see Ruff, paras [0111] & [0185], wherein the agricultural intelligence computing system may use the environmental factors to determine which fields are at risk and select fields based on the risk percentage or a computed severity of risked damage….The scouting-cab instructions 232 may be programmed to display location-based alerts and information received from the system 130 based on the location of the field manager computing device 104, agricultural apparatus 111, or sensors 112 in the field and ingest, manage, and provide transfer of location-based scouting observations to the system 130 based on the location of the agricultural apparatus 111 or sensors 112 in the field; para [0334], wherein the yield probabilities may comprise a probability value for each of a plurality of yield values. For example, the agricultural intelligence computer' system may compute an expected yield and yield variance for a particular agricultural treatment. Based on the expected yield and yield variance, the agricultural intelligence computer system may determine probabilities for each of a plurality of yield values, such as a probability for each integer yield value between 1 and 500 bushels per acre; and para [0339], wherein the agricultural intelligence computer system also may be programmed to generate aggregated risk data 1810. Risk data generally relates to risk of loss due to failure of a field to meet the predicted yield. Aggregated risk data 1810 may comprise grower identifiers, operation identifiers, location data for various fields, expected yields, actual yields, and yield probabilities).
Regarding claim 4, Ruff discloses the computer-implemented method of claim 3, wherein the multiple disease joint model includes at least one of a linear regression mean function and a neural network regression mean function for relating input parameters characterizing the target plot to likelihood probabilities of multiple crop disease types (see Ruff, paras [0225], [0133], [0135], & [0168], wherein the crop yield lift, such as neural networks or regression techniques, can also be used….The agricultural intelligence computer system 130 may implement data subset selection techniques including, but not limited to, a genetic algorithm method, an all subset models method, a sequential search method, a stepwise regression method, a particle swarm optimization method, and an ant colony optimization method. In an embodiment, agronomic model creation may implement multivariate regression techniques to create preconfigured agronomic data models. The data may Include field descriptions, soil data, planting data, fertility data, harvest and yield data, crop protection data, pest and disease data, irrigation data, tiling data, imagery, weather data, and additional management data).
Regarding claim 6, Ruff discloses the computer-implemented method of claim 1, further comprising training the multiple disease joint model, based on historical data associated with multiple plots and multiple crop disease types (see Ruff, paras [0128]-[0129], [0169], & [0175], wherein Process Overview Agronomic Model Training…ln an embodiment, the agricultural intelligence computer system 130 is programmed or configured to create an agronomic model. In this context, an agronomic model is a data structure in memory of the agricultural intelligence computer system 130 that comprises field data 106, such as identification data and harvest data for one or more fields. The agronomic model may also comprise calculated agronomic properties which describe either conditions which may affect the growth of one or more crops on a field, or properties of the one or more crops, or both. Field descriptions may refer to a field location, a total acreage of the field, a shape and boundaries of the field, elevation and topographic variability of the field, tillage history of the field, crop rotation history of the field, disease history of the field, crop protection of the field, farm equipment use history of the field. and data regarding a field operator. Pest and disease data may include subfield pathogen presence in plant tissue, residue, and soil, damage type and extent from biotic stress caused by insects, and/or damage type and extent from biotic stress caused by pathogens. Extent of damage may be identified as low, medium, or high or as one more numeric ratings. Biotic stress and pathogen .presence may be measured and/or modeled).
Regarding claim 7, Ruff discloses the computer-implemented method of claim 6, wherein inputs for training the multiple disease joint model include, for each of the multiple plots:
a location of the plot; a presence or severity of multiple crop diseases at the plot; and a date of observation of crops of the plot to determine the presence or severity of the multiple crop discases (see Ruff, paras [0087], [0169], & [0185], wherein using the display depicted in FIG. 5, a user computer can input a selection of a particular field and a particular date for the addition of event. Field descriptions may refer to a field location, a total acreage of the field, a shape and boundaries of the field, elevation and topographic variability of the field, tillage history of the field, crop rotation history of the field, disease history of the field, crop protection of the field, farm equipment use history of the field, and data regarding a field operator. The field location may be identified using GPS coordinates or any other data that identifies a location of the field. Additionally, the agricultural intelligence computing system may identify management practices that increase or decrease the risk of the one or more events. Examples for disease control include use of irrigation, crop rotation, tillage methods, plant genetics, arid planting rate. Additionally, the agricultural intelligence computing system may identify environmental factors that increase or decrease the risk of the one or more events. Examples for disease control Include soil organic matter percentage, soil pH, and other soil nutrient concentrations. The agricultural intelligence computing system may use the environmental factors to determine which fields are at risk and select fields based on the risk percentage or a computed severity of risked damage).
Regarding claim 8, Ruff discloses the computer-implemented method of claim 7, wherein the inputs for training the multiple disease joint model include, for each of the multiple plots, at least one of soil information of the plot, field topology information of the plot, weather information associated with the plot, field management practice information associated with the plot, and hybrid/genetic seed information associated with crops on the plot (see Ruff, paras [0087], [0169], & [0185], wherein the agricultural intelligence computer system 130 may include a data server focused exclusively on a type of data that might otherwise be obtained from third party sources, such as weather data. Additionally, the agricultural intelligence computing system may identify management practices that increase or decrease the risk of the one or more events. Examples for disease control include use of irrigation, crop rotation, tillage methods, plant genetics, and planting rate. Additionally, the agricultural intelligence computing system may identify environmental factors that increase or decrease the risk of the one or more events. Examples for disease control include soil organic matter percentage, soil pH, and other soil nutrient concentrations. The agricultural intelligence computing system may use the environmental factors to determine which fields are at risk and select fields based on the risk percentage or a computed severity of risked damage).
Regarding claim 9, Ruff discloses the computer-implemented method of claim 6, wherein training the model includes:
accessing data specific to a region of the target plot; manipulating, by the computing device, the accessed data; and training, by the computing device, the multiple disease joint model based on at least a portion of the manipulated data (see Ruff, paras [0297], [0128]-[0129], & [0400], wherein once a region has been selected, the agricultural intelligence computing system may track and cause display of information pertaining to the selected region. FIG. 11 depicts an example graphical user interface for displaying information pertaining to a selected region. In Fig. 11 shows once a region has been selected, the agricultural intelligence computing system may track and cause display of information pertaining to the selected region……..In an embodiment, the agricultural intelligence computer system communicates with the field manager computing device through a dynamic graphical user interface which updates based on selections from the field manager computing device as well as tracked actions taken by one or more agricultural implements).
Regarding claim 10, Ruff discloses the computer-implemented method of claim 1, further comprising treating the target plot with the treatment in response to the treatment recommendation (see Ruff, para [0166], wherein in step 712, the data identifying the locations for implementing the trial may be sent to a field manager computing device which acts as a controller for a field implement, such as a planter or sprayer, thereby causing the field implement to execute the trial in the identified locations, such as by planting seeds or spraying a treatment according to a trial prescription).
Regarding claims 11 and 17, Ruff discloses the computer-implemented method of claim 10, wherein treating the target plot with the treatment includes applying the treatment to crops in the target plot (see Ruff, para [0156], wherein at step 704, one or more target agricultural fields are identified based, at least in part, on the field data for the plurality of agricultural fields. The agricultural intelligence computing system may be programmed or configured to directly identify fields and/or to identify field manager accounts as target accounts for sending a trial request message. Generally, the agricultural intelligence computing system may select target agricultural fields based on likelihood of acceptance of the trial, likely benefits to the field of performing the trial, likelihood of detecting the benefits to the field of performing the trial, and general applicability of the trial; and para [0006], wherein improvements may be made to the management practices of a field by using different hybrid seeds, applying different products to the field, or performing different management activities on the field).
Regarding claim 12, Ruff discloses the computer-implemented method of claim 10, further comprising:
receiving, at a communication device of a user associated with the target plot, the treatment recommendation (see Ruff, paras [0085]-[0086] & [0166], wherein the user may be prompted via one or more user interfaces on the user device (served by the agricultural intelligence computer system) to input such information…one or more graphical user interface widgets which when selected can identify changes to the field, soil, crops, tillage, or nutrient practices. The direct communication with the field implement may be used to bypass communication with the field manager. For example, in step 712, the data identifying the locations for implementing the trial may be sent to a field manager computing device which acts as a controller for a field implement, thereby causing the field implement to execute the trial in the identified locations, such as by planting seeds or spraying a treatment according to a trial prescription); and
causing operation of one or more agricultural apparatuses at the target plot to apply the treatment to the crops in the target plot (see Ruff, para [0166], wherein in step 712, the data identifying the locations for implementing the trial may be sent to a field manager computing device which acts as a controller for a field implement, such as a planter or sprayer, thereby causing the field implement to execute the trial in the Identified locations, such as by planting seeds or spraying a treatment according to a trial prescription).
Regarding claim 13, Ruff discloses the computer-implemented method of claim 1, further comprising providing a forecasted disease risk map and/or a time series view, via an application and/or website, the map and/or view indicative of the first disease likelihood output and the second disease likelihood output (see Ruff, paras [0107] & [0396], wherein generate and cause displaying a nitrogen map, which indicates projections of plant use of the specified nitrogen and whether a surplus or shortfall is predicted…Trial information 2702 comprises implementation data for the trial. In FIG. 27, trial information 2702 includes a plurality of different management zones corresponding to mapped field 2704. For each management zone, a population rate, average yield, and management zone area is depicted based on the current parameters of the trial recommendation. Additionally, trial information 2702 includes overall statistics, such as estimated yield, seed cost per acre, and an estimated gross revenue based on the estimated yield and an estimated price of the crop).
Regarding claim 14, Ruff discloses the computer-implemented method of claim 1, wherein the request for the crop disease prediction is specific to a first crop type, the method further comprising:
receiving, by the computing device, a second request for a second crop disease prediction related to treatment of a second crop type at the target plot (see Ruff, paras [0159] & [0396], wherein at step 710, one or more locations on the one or more target agricultural fields are determined for implementing the trial. The agricultural intelligence computing system may identify locations on the field for implementing a test location based on areas In the field capable of performing the trial, efficiency of performing the trial in each location, applicability of the trial to other locations, and/or benefit to the field of performing the trial); and
generating, by the computing device, a second treatment recommendation based on the third disease likelihood output and the fourth disease likelihood output (see Ruff, para [0355], wherein the agricultural intelligence computer system may identify one or more trial recommendations for an agricultural field and send the one or more trial recommendations to a field manager computing device. If-the agricultural intelligence computer system receives an acceptance of the trial, the agricultural intelligence computer system may perform the method of FIG. 23 to determine trial locations and analyze trial results).
Ruff et al. fails to explicitly disclose determining, by the computing device, via the multiple disease joint model, a third disease likelihood output and a fourth disease likelihood output, based on at least the location data and the second crop type, the third disease likelihood output and the fourth disease likelihood output each associated with the second crop type and a different one of the multiple disease types.
Analogous art Carroll discloses determining, by the computing device, via the multiple disease joint model, a third disease likelihood output and a fourth disease likelihood output, based on at least the location data and the second crop type, the third disease likelihood output and the fourth disease likelihood output each associated with the second crop type and a different one of the multiple disease types (see Carroll, paras [0002]-[0007] & [0149]-[0156], wherein modeling a likelihood of particular diseases presenting on a field based on field data and then using the resulting data models to improve plant pathology, plant pest control, agriculture, or agricultural management……Agricultural intelligence computer system 130 may use the disease probability to model the likelihood of disease occurring each day since planting. For example, agricultural intelligence computer system 130 may use the random forest model using different datasets…..likelihood of presence of a disease to generate fungicide recommendations. For example, agricultural intelligence computer system 130 may determine a likelihood of onset of the disease on the crop in the next fourteen days using the methods described herein. Agricultural intelligence computer system 130 may additionally determine a benefit of applying the fungicide. The benefit may comprise reducing the likelihood of disease onset and/or increasing the likely yield for the crop. If agricultural intelligence computer system 130 determines that the disease is likely to present on the crop within the next fourteen days, agricultural intelligence computer system 130 may generate a recommendation to apply fungicide to the crop, thereby reducing the probability of disease. By modeling the likelihood of disease occurring in the future, agricultural intelligence computer system 130 is able to generate recommendations that, if implemented, prevent the occurrence or spread of the disease).
One of ordinary skill in the art would have recognized that applying the known technique of Carroll would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 14.
Regarding claim 15, Ruff discloses the computer-implemented method of claim 1, further comprising:
receiving, by the computing device, a second request for a second crop disease prediction related to treatment of a second target plot (see Ruff, paras [0159], [0161], & [0396], wherein at step 710, one or more locations on the one or more target agricultural fields are determined for implementing the trial. The agricultural intelligence computing system may identify locations on the field for implementing a test location based on areas In the field capable of performing the trial, efficiency of performing the trial in each location, applicability of the trial to other locations, and/or benefit to the field of performing the trial); and
generating, by the computing device, a second treatment recommendation based on the third disease likelihood output and the fourth disease likelihood output (see Ruff, para [0355], wherein the agricultural intelligence computer system may identify one or more trial recommendations for an agricultural field and send the one or more trial recommendations to a field manager computing device. If-the agricultural intelligence computer system receives an acceptance of the trial, the agricultural intelligence computer system may perform the method of FIG. 23 to determine trial locations and analyze trial results).
Ruff et al. fails to explicitly disclose determining, by the computing device, via the multiple disease joint model, a third disease likelihood output and a fourth disease likelihood output, based on at least location data of the second target plot, the third disease likelihood output and the fourth disease likelihood output each associated with the second target plot and a different one of the multiple disease types.
Analogous art Carroll discloses determining, by the computing device, via the multiple disease joint model, a third disease likelihood output and a fourth disease likelihood output, based on at least location data of the second target plot, the third disease likelihood output and the fourth disease likelihood output each associated with the second target plot and a different one of the multiple disease types (see Carroll, paras [0002]-[0007] & [0149]-[0156], wherein modeling a likelihood of particular diseases presenting on a field based on field data and then using the resulting data models to improve plant pathology, plant pest control, agriculture, or agricultural management……Agricultural intelligence computer system 130 may use the disease probability to model the likelihood of disease occurring each day since planting. For example, agricultural intelligence computer system 130 may use the random forest model using different datasets…..likelihood of presence of a disease to generate fungicide recommendations. For example, agricultural intelligence computer system 130 may determine a likelihood of onset of the disease on the crop in the next fourteen days using the methods described herein. Agricultural intelligence computer system 130 may additionally determine a benefit of applying the fungicide. The benefit may comprise reducing the likelihood of disease onset and/or increasing the likely yield for the crop. If agricultural intelligence computer system 130 determines that the disease is likely to present on the crop within the next fourteen days, agricultural intelligence computer system 130 may generate a recommendation to apply fungicide to the crop, thereby reducing the probability of disease. By modeling the likelihood of disease occurring in the future, agricultural intelligence computer system 130 is able to generate recommendations that, if implemented, prevent the occurrence or spread of the disease).
One of ordinary skill in the art would have recognized that applying the known technique of Carroll would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 15.
Regarding claims 16 and 18, Ruff discloses a system for directing crop disease treatments to plots, the system comprising at least one computing device configured to:
A non-transitory computer-readable storage medium including computer executable instructions for use in directing crop disease treatments to plots, which when executed by at least one processor (see Ruff, paras [0092]-[0093]), cause the at least one processor to:
receive a request for a crop discase prediction related to treatment of a target plot for one or more crop disease, the request including crop disease type data and location data relating to the target plot, the crop disease type data including multiple identifiers each associated with a different one of multiple crop disease types, as set forth above with claim 1;
access a multiple disease joint model consistent with the location data, as set forth above with claim 1;
determine, via the multiple disease joint model, a first disease likelihood output and a second disease likelihood output based on at least the location data, the first discase likelihood output and the second disease likelihood output each associated with a different one of the multiple disease types, as set forth above with claim 1;
generate a treatment recommendation based on the first disease likelihood output and the second disease likelihood output of the multiple disease joint model (see Ruff, paras [0160], [0182], [0349], & [0356], wherein the portion of the agricultural field comprises a whole field such that the trial comprises a recommendation for one or more different practices being performed on the agricultural field. Implementations which utilize part or all of the agricultural field are described further herein….the trial comprises a fungicide trial, the agricultural intelligence computer system may identify a location for evaluating the trial which includes a control location and a treatment location…..the agricultural intelligence computing system may generate one or more scripts for a field implement on the one or more fields that causes the field implement to apply the product and/or management practices in the one or more locations).
Claims 5 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Ruff et al. (US Pub No. 2020/0272971) (hereinafter Ruff et al.), in view of Carroll et al. (US Pub No. 2019/0156255) (hereinafter Carroll et al.), and further in view of Perry et al. (US Pub No. 2019/0050948) (hereinafter Perry et al.).
Regarding claims 5 & 20, Ruff discloses the computer-implemented method of claim 1, wherein:
the multiple disease joint model process model that interpolates data across plot locations and crop disease observation dates; and an output of the multiple disease joint model includes an output of a neural network (see Ruff, paras [0091] & [0132]).
Ruff et al. fails to explicitly disclose the multiple disease joint model includes a Gaussian process model that interpolates data acro
ss plot locations and crop disease observation dates; and with a smooth Gaussian process.
Analogous art Perry discloses the multiple disease joint model includes a Gaussian process model that interpolates data across plot locations and crop disease observation dates; and an output of the multiple disease joint model includes an output of a neural network combined with a smooth Gaussian process (see Perry, paras [0007], [0049], & [0145], wherein the one or more machine learning operations can include one or more of: a generalized linear model, a generalized additive model, a non-parametric regression operation (i.e., smooth Gaussian process (GP))…..a Bayesian model that includes Gaussian processes or splines, trained on historic soil samples, information describing trends in soil nutrient contents and composition, and information describing soil variation over geographic regions…a Bayesian model that includes Gaussian processes or splines, trained on historic soil samples, information describing trends in soil nutrient contents and composition, and information describing soil variation over geographic regions…..The resulting Bayesian model can interpolate soil sample information over a portion of land, such as a grower's field, for instance using Markov Chain Monte Carlo sampling or variational inference estimations. After samples and corresponding locations are accessed for a particular portion of land, the Bayesian model can be queried for a soil characteristic or measurement (such as pH) at a particular location within the portion of land, and the Bayesian model can provide an inferred soil characteristic or measurement (or a probable range) in response; para [0158], wherein models that map fungicide, herbicide, and nematicide application (including which product to apply, when to apply, where to apply, quantity to apply, and method of application) determined based on one or more of: 1) information about incidence of pests and weeds and disease in nearby geographic regions, 2) historical crop health, 3) reports of pest and weed stress by human "scouts" who visit the field ).
Ruff directed to a system for implementing trials of the particular practices and tracking the performance of the particular practices. Perry directed to identifying an optimized set of farming operations for the grower to perform. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Ruff, regarding the System for Modeling and Tracking of Agricultural Fields for Implementing Agricultural Field Trials, to have included the multiple disease joint model includes a Gaussian process model that interpolates data across plot locations and crop disease observation dates; and an output of the multiple disease joint model includes an output of a neural network combined with a smooth Gaussian process because both inventions teach improving plant pathology use. Further, the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Conclusion
The prior arts made of record and not relied upon is considered pertinent to applicant's disclosure. (US Pub No. 2023/0154623; US Pub No. 2023/0110849; US Pub No. 2020/0019884; US Pub No. 2016/0078570; US Pub No. 2021/0350295; US Pub No. 2014/0012732; US Pub No. 2017/0261645; CA Gilligan (Sustainable agriculture and plant diseases: an epidemiological perspective) - Philosophical Transactions of the Royal Society …, 2007 - pmc.ncbi.nlm.nih.gov; and DH Gent, WF Mahaffee, N McRoberts (The use and role of predictive systems in disease management) - Annual review of …, 2013 - annualreviews.org.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HAFIZ A KASSIM whose telephone number is (571)272-8534. The examiner can normally be reached 9:00 - 5:00 PM.
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 at 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 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.
/HAFIZ A KASSIM/Primary Examiner, Art Unit 3623 07/06/2026
Prosecution Insights