DETAILED NOTICE
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 .
The following NON-FINAL Office Action is in response to Applicant’s communication filed 11/07/2024 regarding Application 18/940,224. The following is the first action on the merits.
Priority Acknowledgment
Examiner acknowledges Applicant’s claim to Provisional Application 63/548,142 with priority filing date of 11/10/2023.
Status of Claim(s)
Claim(s) 1-20 is/are currently pending and are rejected as follows.
Statutory Subject Matter with Regard to 35 U.S.C. 101
Claim(s) 1-20 have been analyzed under the Alice/Mayo framework and determined to be statutory with regards to 35 U.S.C. 101 for the following reasons. First, under Step 1 of the Alice/Mayo framework it must be considered whether the claims are directed to one or more of the statutory classes of invention. In the instant case, Claim(s) 1-9 are directed towards a method, Claim(s) 10-19 are directed towards an apparatus, and Claim(s) 20 are directed towards a product. Accordingly, these claims fall under the four statutory category of invention and will be further analyzed under Step 2 of the Alice/Mayo framework. Under Step 2A, Prong One, it was considered whether the claims recite any abstract ideas. The independent claims 1, 9, and 15 were all deemed to recite the abstract ideas of Organizing Human Activity, specifically that of Managing Personal Behavior or Relationships or Interactions Between People. However, under Step 2A, Prong Two, the claims were deemed to recite additional elements, such as the data structure and gated recurrent unit (GRU), such that the abstract idea is integrated in such a way to be significantly more than merely adding the words “apply it” to a computer. Therefore the claims as currently represented are deemed allowable subject matter in view of 101. However, any changes made to Applicant’s claims to overcome any applied rejections below does not prevent a rejection under 101 should it be deemed appropriate under subsequent analysis in view of those changes.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 18 is/are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 18 recites the limitation “wherein the neural network layer…” in its limitation. There is insufficient antecedent basis for this limitation in the claim as the claim from which it is dependent on does not mention the neural network layer. However, for the sake of compact prosecution, the claim will be treated as dependent from Claim 17 as the limitations of both Claim(s) 17 and 18 are similar to those of Claim(s) 7 and 8 and respectively and who’s dependency would remedy Claim(s) 18’s indefiniteness.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
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.
Claim(s) 1-4, 6, 10-14, 16, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Stueve (US 2020/0364843 A1) in view of Johnson (US 2023/0385654 A1).
Claim(s) 1, 10, and 20 –
Stueve discloses the following:
A non-transitory computer readable storage medium including executable instructions (Stueve: Paragraph 15, “In one or more embodiments described herein, systems, computer-implemented methods, apparatuses and/or computer program products provide an automated method for determining when a pest outbreak in particular crop field(s) or portions thereof is probable based upon specific, quantitative measures. The system may include a non-transitory, computer-readable medium containing instructions and a processor that executes the instructions to perform various stages.”)
at least one computing device (Stueve: Paragraph 15, “In one or more embodiments described herein, systems, computer-implemented methods, apparatuses and/or computer program products provide an automated method for determining when a pest outbreak in particular crop field(s) or portions thereof is probable based upon specific, quantitative measures. The system may include a non-transitory, computer-readable medium containing instructions and a processor that executes the instructions to perform various stages.”)
receiving, at a computing device, a request to recommend an application of a treatment for a field, the field including a crop, which is associated with a planting day indicative of the day the crop was planted, the request including a field identifier (ID) for the field; (Stueve: Paragraph 76, “In some embodiments, the process generates a treatment plan (not shown in FIGS. 1A and 1B) based on the pest susceptibility map, as shown in FIG. 2. The treatment plan comprises a recommended agricultural management technique (e.g., application of one or more agricultural chemicals) to prevent the outbreak or control the propagation of one or more crop pests.”; Paragraph 96, “In some embodiments, geospatial image data and machine vision algorithms may be used to determine quantitatively a degree of canopy closure of the crop field. Canopy closure may create in-field conditions needed for the outbreak or propagation of a pest in the particular field at a time that other conditions in a general region of the field are suitable to the pest. If the entire field has not reached the requisite in-field conditions (e.g., reproductive stage and near-full canopy closure) at the relevant time, identifying those areas of the field that have reached the requisite conditions conducive to pest outbreak and propagation may allow for targeted implementation of agricultural management techniques (e.g., applications of specific chemicals such as fungicides) to prevent the outbreak, or control the propagation, of crop pest(s).”; Paragraph 128, “The user computing entity 601 may also comprise a user interface (that can include a display 616 coupled to a processing element 608) and/or a user input interface (coupled to a processing element 608). For example, the user interface may be a user application, browser, user interface, and/or similar words used herein interchangeably executing on and/or accessible via the user computing entity 601 to interact with and/or cause display of information from the management computing entity 501, as described herein. The user input interface can comprise any of a number of devices or interfaces allowing the user computing entity 601 to receive data, such as a keypad 618 (hard or soft), a touch display, voice/speech or motion interfaces, or other input device. In embodiments including a keypad 618, the keypad 618 can include (or cause display of) the conventional numeric (0-9) and related keys (#, *), and other keys used for operating the user computing entity 601 and may include a full set of alphabetic keys or set of keys that may be activated to provide a full set of alphanumeric keys. In addition to providing input, the user input interface can be used, for example, to activate or deactivate certain functions, such as screen savers and/or sleep modes.”; Paragraph 141, “A starting point for any machine learning method such as used by the machine learning component above is a documented dataset containing multiple instances of system inputs and correct outcomes (e.g., the training data). This data set can be used, using methods known in the art, including but not limited to standardized machine learning methods such as parametric classification methods, non-parametric methods, decision tree learning, neural networks, methods combining both inductive and analytic learning, and modeling approaches such as regression models, to train the machine learning system and to evaluate and optimize the performance of the trained system. The quality of the output of the machine learning system depends on (a) the pattern parameterization, (b) the learning machine design, and (c) the quality of the training database. These components can be refined and optimized using various methods. For example, the database can be refined by adding datasets for new documented crop fields. The quality of the database can be improved, for example, by populating the database with cases in which the customization was accomplished by one or more experts in crop pest prediction or treatment (e.g., fungicide) application. Thus, the database will better represent the expert's knowledge. In one embodiment, the database includes data, for example, of poor agricultural management, which can assist in the evaluation of a trained system.”; Paragraph 158, “The geospatial image data (101, 112, 205, 301, 401) and microclimate data (104, 122, 205, 330, 401) used as inputs to the processes described herein may be received from remote sensors located on aircraft. The aircraft may be manned or unmanned with the unmanned aircraft controlled by a ground-based operator or flying autonomously along a programmed flight path. The data may be mosaicked into a single map or image in any suitable manner, where the map provides a pixel value for a plurality of geographically referenced locations in the field. The geographically referenced locations may be referenced relative to any suitable reference frame, including global coordinates, or to a field-specific local reference frame or plant identifier. The term “image” or “map”, as used herein, does not necessarily require or imply a 2-dimensional representation and refers simply to data having a referenced position and a value associated with that position, thereby containing the information of a two-dimensional map without requiring an actual two-dimensional representation.”)
accessing a data structure based on the field ID, the data structure including a planting date of the crop in the field and weather data for the field, the weather data defining time series weather data for an interval; (Stueve: Paragraph 82, “FIG. 2 outlines one embodiment of a process according to the present disclosure, which illustrates a process to predict a pest susceptibility of a crop field. Several inputs and input parameters 210 are automatically determined from source data 205. The source data 205 comprises microclimate data and geospatial image data, such as aerial, satellite, and drone images, as well as sensor and machine data collected remotely or on the crop field. In addition, source data may also include crop stage models. The process generates a set of inputs relative to crop vigor 210 and a set of input parameters 211 from the source data 205. The crop vigor inputs 210 are extracted from the geospatial image data and include a crop vigor index applying to the whole crop field (i.e., field-scale crop vigor index) or a set of geolocated crop vigor indices forming a fine-scale crop vigor map for the crop field. The input parameters 211 comprise microclimate data (e.g., air temperature, relative humidity, wind speed, solar insolation and/or sun exposure) relative to the crop field. The input parameters 211 may also comprise agronomic data (e.g., row spacing, irrigation status, crop stage, and canopy closure) at various times (e.g., planting, treatment application) as well. A risk model 220 is used to predict the susceptibility of an outbreak of one or more crop pests (e.g., white mold in soybeans) based upon the crop vigor 210 and input parameters 211. An output 230 of the process is a measure of pest susceptibility at a fine scale (i.e., pest susceptibility map) or at a field scale (e.g., pest susceptibility index). A treatment plan 231 for the crop field may also be generated from the generated pest susceptibility, where the treatment plan comprises the implementation of agricultural management techniques (e.g., applications of specific chemicals such as fungicides) to prevent the outbreak, or control the propagation, of crop pest(s). In one embodiment, an output treatment plan 231 may depend on whether the field-scale (i.e., macro) and/or the fine-scale (i.e., micro) conditions for a pest outbreak are met, leading to (a) full treatment of the crop field if macro conditions are met and micro conditions are met throughout the field; (b) targeted treatment of certain portions of the crop field if macro conditions are not met and micro conditions are met for those portions, or (c) no treatment if macro conditions are not met or micro conditions are not met throughout the crop field. The process of FIG. 2 therefore converts the crop vigor index map and other input parameters (210, 211) into a prescription for an appropriate agricultural management procedure, such as spraying pesticide (e.g., herbicide, insecticide, fungicide, insect repellent, animal repellent) in parts of the field that are most likely to experience pest outbreaks. Agricultural management procedures also include applying fertilizer and plant nutrients. The output pest susceptibility values 230 can be broken down into zones for targeting different treatments (e.g., spray rates) based on the product being applied, the equipment available for application, and the risk a grower/agronomist is willing to take.”; Paragraph 93, “In one embodiment, a determination may be made whether the crop field is irrigated or non-irrigated from either machine data or geospatial image data. In one embodiment, geospatial image data is utilized to determine field shape or other indicators of irrigation, including either thermal or other imagery which may detect irrigation application. Wavelengths capable of detecting whether a field is irrigated include long-wavelength infrared (8,000-15,000 nanometers (nm), 20-37 THz), short-wavelength infrared (1,400-3,000 nm, 100-214 THz), and C-Band radio frequencies (4-8 GHz, as used in Synthetic Aperture Radar).”; Paragraph 94, “In some embodiments, an estimation may be made of crop stage through the use of physical observation of the field in question or one or more crop stage models. In one embodiment, the crop stage models may estimate crop stage using a combination of data sources including (but not limited to), a measure or estimate of planting or emergence date, a measure or estimate of “thermal time” (i.e., accumulated number hours above a temperature threshold), a measure or estimate of “photoperiod” (i.e., the length of daylight) at critical intervals, etc.”; Paragraph 143, “The CERES server 1050 may provide crop pest susceptibility predictions 1060, real-time analytics 1070, and/or other agricultural management recommendations (e.g., crop field treatment) 1080 to a plurality of end-user devices over the network.”; Paragraph Paragraph 161, “In another aspect, the microclimate parameters may be collected by the same aircraft taking the thermal images. In some embodiments, the aircraft may measure the microclimate parameter(s) during a pass over the field at a lower elevation than when taking the thermal image(s) that may be above 200 meters in altitude, and on the same day as the thermal images were collected. In other embodiments, the microclimate parameters are estimated using models or “synthetic sensors” derived from broader microclimate or weather models.”; Paragraph 162, “In some embodiments, ground-based microclimate measurements may be used without departing from the scope of the present invention. Microclimate parameters may also be obtained from third parties, such as third-party weather stations, whether ground-based or remote.”)
determining, by the computing device, at least one disease risk for the crop in the field, based on at least one disease risk model and the growth stage vector, the at least one disease risk indicative of an occurrence and/or a severity of at least one disease; (Stueve: Paragraph 81, “In one embodiment, the risk model (108, 130) may use a machine learning module, as described below. For example, the machine learning module may use an ensemble of random forest regressors, where the predictor variables are the crop vigor map (102, 116) and other remotely sensed or estimated crop field parameters (120, 128), in conjunction with macroclimate weather data 122. The dependent variable may be the pest of interest (e.g., white mold severity in soybeans). Model training is performed, where ground truth data comprising the coordinates and corresponding disease severity from a field at the end of the season may be used for modeling with in-season crop vigor indices, or other remotely sensed crop field parameters and macroclimate conditions at the time of imagery collection. This process quantifies the relationship between pest severity and in-season variables of crop vigor or other remotely sensed crop parameters and macroclimate conditions. This procedure should be repeated for the pest and crop of interest, as different relationships are expected, resulting in unique crop- and pest-dependent models. It is important to note that training with data from coordinates with all pest outbreak levels (e.g., no disease, light disease, moderate disease, and severe disease) is preferred. Further detailed discussion of the risk model is given below (e.g., see FIGS. 2, 3, 8).”; Paragraph 82, “FIG. 2 outlines one embodiment of a process according to the present disclosure, which illustrates a process to predict a pest susceptibility of a crop field. Several inputs and input parameters 210 are automatically determined from source data 205. The source data 205 comprises microclimate data and geospatial image data, such as aerial, satellite, and drone images, as well as sensor and machine data collected remotely or on the crop field. In addition, source data may also include crop stage models. The process generates a set of inputs relative to crop vigor 210 and a set of input parameters 211 from the source data 205. The crop vigor inputs 210 are extracted from the geospatial image data and include a crop vigor index applying to the whole crop field (i.e., field-scale crop vigor index) or a set of geolocated crop vigor indices forming a fine-scale crop vigor map for the crop field. The input parameters 211 comprise microclimate data (e.g., air temperature, relative humidity, wind speed, solar insolation and/or sun exposure) relative to the crop field. The input parameters 211 may also comprise agronomic data (e.g., row spacing, irrigation status, crop stage, and canopy closure) at various times (e.g., planting, treatment application) as well. A risk model 220 is used to predict the susceptibility of an outbreak of one or more crop pests (e.g., white mold in soybeans) based upon the crop vigor 210 and input parameters 211. An output 230 of the process is a measure of pest susceptibility at a fine scale (i.e., pest susceptibility map) or at a field scale (e.g., pest susceptibility index). A treatment plan 231 for the crop field may also be generated from the generated pest susceptibility, where the treatment plan comprises the implementation of agricultural management techniques (e.g., applications of specific chemicals such as fungicides) to prevent the outbreak, or control the propagation, of crop pest(s). In one embodiment, an output treatment plan 231 may depend on whether the field-scale (i.e., macro) and/or the fine-scale (i.e., micro) conditions for a pest outbreak are met, leading to (a) full treatment of the crop field if macro conditions are met and micro conditions are met throughout the field; (b) targeted treatment of certain portions of the crop field if macro conditions are not met and micro conditions are met for those portions, or (c) no treatment if macro conditions are not met or micro conditions are not met throughout the crop field. The process of FIG. 2 therefore converts the crop vigor index map and other input parameters (210, 211) into a prescription for an appropriate agricultural management procedure, such as spraying pesticide (e.g., herbicide, insecticide, fungicide, insect repellent, animal repellent) in parts of the field that are most likely to experience pest outbreaks. Agricultural management procedures also include applying fertilizer and plant nutrients. The output pest susceptibility values 230 can be broken down into zones for targeting different treatments (e.g., spray rates) based on the product being applied, the equipment available for application, and the risk a grower/agronomist is willing to take.”;
determining a residual protection of the field for at least one prior treatment of the field; (Stueve: Paragraph 81, “In one embodiment, the risk model (108, 130) may use a machine learning module, as described below. For example, the machine learning module may use an ensemble of random forest regressors, where the predictor variables are the crop vigor map (102, 116) and other remotely sensed or estimated crop field parameters (120, 128), in conjunction with macroclimate weather data 122. The dependent variable may be the pest of interest (e.g., white mold severity in soybeans). Model training is performed, where ground truth data comprising the coordinates and corresponding disease severity from a field at the end of the season may be used for modeling with in-season crop vigor indices, or other remotely sensed crop field parameters and macroclimate conditions at the time of imagery collection. This process quantifies the relationship between pest severity and in-season variables of crop vigor or other remotely sensed crop parameters and macroclimate conditions. This procedure should be repeated for the pest and crop of interest, as different relationships are expected, resulting in unique crop- and pest-dependent models. It is important to note that training with data from coordinates with all pest outbreak levels (e.g., no disease, light disease, moderate disease, and severe disease) is preferred. Further detailed discussion of the risk model is given below (e.g., see FIGS. 2, 3, 8).”; Paragraph 82, “FIG. 2 outlines one embodiment of a process according to the present disclosure, which illustrates a process to predict a pest susceptibility of a crop field. Several inputs and input parameters 210 are automatically determined from source data 205. The source data 205 comprises microclimate data and geospatial image data, such as aerial, satellite, and drone images, as well as sensor and machine data collected remotely or on the crop field. In addition, source data may also include crop stage models. The process generates a set of inputs relative to crop vigor 210 and a set of input parameters 211 from the source data 205. The crop vigor inputs 210 are extracted from the geospatial image data and include a crop vigor index applying to the whole crop field (i.e., field-scale crop vigor index) or a set of geolocated crop vigor indices forming a fine-scale crop vigor map for the crop field. The input parameters 211 comprise microclimate data (e.g., air temperature, relative humidity, wind speed, solar insolation and/or sun exposure) relative to the crop field. The input parameters 211 may also comprise agronomic data (e.g., row spacing, irrigation status, crop stage, and canopy closure) at various times (e.g., planting, treatment application) as well. A risk model 220 is used to predict the susceptibility of an outbreak of one or more crop pests (e.g., white mold in soybeans) based upon the crop vigor 210 and input parameters 211. An output 230 of the process is a measure of pest susceptibility at a fine scale (i.e., pest susceptibility map) or at a field scale (e.g., pest susceptibility index). A treatment plan 231 for the crop field may also be generated from the generated pest susceptibility, where the treatment plan comprises the implementation of agricultural management techniques (e.g., applications of specific chemicals such as fungicides) to prevent the outbreak, or control the propagation, of crop pest(s). In one embodiment, an output treatment plan 231 may depend on whether the field-scale (i.e., macro) and/or the fine-scale (i.e., micro) conditions for a pest outbreak are met, leading to (a) full treatment of the crop field if macro conditions are met and micro conditions are met throughout the field; (b) targeted treatment of certain portions of the crop field if macro conditions are not met and micro conditions are met for those portions, or (c) no treatment if macro conditions are not met or micro conditions are not met throughout the crop field. The process of FIG. 2 therefore converts the crop vigor index map and other input parameters (210, 211) into a prescription for an appropriate agricultural management procedure, such as spraying pesticide (e.g., herbicide, insecticide, fungicide, insect repellent, animal repellent) in parts of the field that are most likely to experience pest outbreaks. Agricultural management procedures also include applying fertilizer and plant nutrients. The output pest susceptibility values 230 can be broken down into zones for targeting different treatments (e.g., spray rates) based on the product being applied, the equipment available for application, and the risk a grower/agronomist is willing to take.”)
determining whether application of the treatment is recommended for the field based on the at least on disease risk and the determined residual protection; (Stueve: Paragraph 82, “FIG. 2 outlines one embodiment of a process according to the present disclosure, which illustrates a process to predict a pest susceptibility of a crop field. Several inputs and input parameters 210 are automatically determined from source data 205. The source data 205 comprises microclimate data and geospatial image data, such as aerial, satellite, and drone images, as well as sensor and machine data collected remotely or on the crop field. In addition, source data may also include crop stage models. The process generates a set of inputs relative to crop vigor 210 and a set of input parameters 211 from the source data 205. The crop vigor inputs 210 are extracted from the geospatial image data and include a crop vigor index applying to the whole crop field (i.e., field-scale crop vigor index) or a set of geolocated crop vigor indices forming a fine-scale crop vigor map for the crop field. The input parameters 211 comprise microclimate data (e.g., air temperature, relative humidity, wind speed, solar insolation and/or sun exposure) relative to the crop field. The input parameters 211 may also comprise agronomic data (e.g., row spacing, irrigation status, crop stage, and canopy closure) at various times (e.g., planting, treatment application) as well. A risk model 220 is used to predict the susceptibility of an outbreak of one or more crop pests (e.g., white mold in soybeans) based upon the crop vigor 210 and input parameters 211. An output 230 of the process is a measure of pest susceptibility at a fine scale (i.e., pest susceptibility map) or at a field scale (e.g., pest susceptibility index). A treatment plan 231 for the crop field may also be generated from the generated pest susceptibility, where the treatment plan comprises the implementation of agricultural management techniques (e.g., applications of specific chemicals such as fungicides) to prevent the outbreak, or control the propagation, of crop pest(s). In one embodiment, an output treatment plan 231 may depend on whether the field-scale (i.e., macro) and/or the fine-scale (i.e., micro) conditions for a pest outbreak are met, leading to (a) full treatment of the crop field if macro conditions are met and micro conditions are met throughout the field; (b) targeted treatment of certain portions of the crop field if macro conditions are not met and micro conditions are met for those portions, or (c) no treatment if macro conditions are not met or micro conditions are not met throughout the crop field. The process of FIG. 2 therefore converts the crop vigor index map and other input parameters (210, 211) into a prescription for an appropriate agricultural management procedure, such as spraying pesticide (e.g., herbicide, insecticide, fungicide, insect repellent, animal repellent) in parts of the field that are most likely to experience pest outbreaks. Agricultural management procedures also include applying fertilizer and plant nutrients. The output pest susceptibility values 230 can be broken down into zones for targeting different treatments (e.g., spray rates) based on the product being applied, the equipment available for application, and the risk a grower/agronomist is willing to take.”; Paragraph 89, “In some embodiments, the process generates a treatment plan (not shown in FIGS. 1A and 1B) based on the generated pest susceptibility map, as shown in FIG. 3. The generated treatment plan comprises a recommended agricultural management technique (e.g., application of one or more agricultural chemicals) to prevent the outbreak or control the propagation of one or more crop pests.”; Paragraph 141, “A starting point for any machine learning method such as used by the machine learning component above is a documented dataset containing multiple instances of system inputs and correct outcomes (e.g., the training data). This data set can be used, using methods known in the art, including but not limited to standardized machine learning methods such as parametric classification methods, non-parametric methods, decision tree learning, neural networks, methods combining both inductive and analytic learning, and modeling approaches such as regression models, to train the machine learning system and to evaluate and optimize the performance of the trained system. The quality of the output of the machine learning system depends on (a) the pattern parameterization, (b) the learning machine design, and (c) the quality of the training database. These components can be refined and optimized using various methods. For example, the database can be refined by adding datasets for new documented crop fields. The quality of the database can be improved, for example, by populating the database with cases in which the customization was accomplished by one or more experts in crop pest prediction or treatment (e.g., fungicide) application. Thus, the database will better represent the expert's knowledge. In one embodiment, the database includes data, for example, of poor agricultural management, which can assist in the evaluation of a trained system.”)
reporting a recommendation to apply the treatment to the field and the application intervals, in response to the request to recommend the application of the treatment. (Stueve: Paragraph 35, “In another embodiment, the system further comprises program code to generate a treatment plan based on the pest susceptibility map, wherein the treatment plan comprises an agricultural management technique, comprising application of one or more agricultural chemicals, to prevent outbreak or control propagation of one or more crop pests.”; Paragraph 76, “In some embodiments, the process generates a treatment plan (not shown in FIGS. 1A and 1B) based on the pest susceptibility map, as shown in FIG. 2. The treatment plan comprises a recommended agricultural management technique (e.g., application of one or more agricultural chemicals) to prevent the outbreak or control the propagation of one or more crop pests.”; Paragraph 84, “The present invention addresses some of the limitations of the prior art by providing a pathway to use machine data, remote sensing data, and/or machine learning to determine which fields, or portions thereof, exhibit conditions amenable to pest outbreak or propagation. In another aspect, the present invention provides advantages over prior art methods in that no on-the-ground presence is required. In one embodiment, all input data may be collected via machine data, remote sensing, or crop modeling. In another embodiment, the input data may be analyzed, assessed, and compared to actual outbreaks of disease via machine learning and/or other artificial intelligence techniques to predict which fields, or portions thereof, are most likely to experience a disease outbreak or propagation. In yet another embodiment, particular agricultural management techniques (e.g., specific fungicides) may be analyzed, assessed, and/or compared to other treatment options (e.g., other fungicides) or controls (e.g., non-treatment) to determine the efficacy particular treatment options have in terms of improved crop vigor, yield, or other indicia of effectiveness. In one aspect of this embodiment, treatment efficacy may be determined using machine data or remote sensing.”)
Stueve doesn’t explicitly disclose the following, however, in analogous art of pest control and management, Johnson discloses the following:
determining, by the computing device, a growth stage vector indicative of a growth stage of the crop during each increment of the interval, using a gated recurrent unit (GRU)-based phenology model, based on the planting date and weather data included in the data structure; (Johnson: Paragraph 20, “The study of biological life cycles, such as the developmental cycles of insects is known as phenology, and there are many existing phenological models for various pest insect species. The overall goal of pest modeling is to predict various aspects of insect population dynamics within a season to inform management decisions, such as the timing of pesticide applications or other interventions. Since most insects cannot reliably maintain constant body temperature, insect life cycle and population dynamics are strongly dependent on environmental conditions, such as ambient temperature. A widely used method of quantifying the relationship between temperature and insect biology makes use of a parameter referred to as growing degree days (GDDs). GDDs describe a measure of time and temperature for which the ambient temperature exceeds the lower developmental temperature threshold.”; Paragraph 56, “Control model 220 can incorporate machine learning models that are trained to predict intervention action 240. In an illustrative example, a machine learning model can be trained to input state data 210 and intervention data 170 and to output a predicted set of intervention actions 355 (e.g., a sequence-to-sequence model such as an RNN, LSTM, or GRU model). Training can be based at least in part on a set of labeled training data from prior executed pest management operations and/or using synthesized data produced from model-predictive control simulations using other methods described herein. Advantageously, machine learning techniques can capture latent interactions between different constraints that can be less apparent and therefore excluded from analytical formulations of predictive model(s) 145 and constraint model(s) 150. In some embodiments, machine learning models can be trained to input a set of predicted intervention actions 355 and state data 210 and to output an optimized set of predicted intervention actions 355. As such, it is understood that such machine learning techniques can include training a model to approximate the behavior of the pest-host system in response to intervention actions.”; Paragraph 70, “As DEL(t) 340 is a term in each of the k rate equations, the rate of emergence of the adult stage depends on the rate of growth and on the number of intermediate stages. Timing of emergence and the shape of a population emergence curve are accurately described by an Erlang distribution with shape parameter k and time-dependent mean and variance:”; Paragraph 84, “that can be characteristic of a pest that is a vector of a crop pathogen. In such cases, a relatively low presence of the pest in the host environment can introduce a potentially catastrophic effect on crop yield. The dynamics of crop yield impact can be governed by other models more specific to the pathogen and its spread through the host environment, which can be pest agnostic. An example of a vector-pest is the pea aphid (Acyrthosiphon pisum).”; Paragraph
in response to determining that application of the treatment is recommended, identifying multiple application intervals for the treatment based on the weather data for the multiple application intervals; and (Johnson: Paragraph 58, “Similarly, outputting operations can include generating visualization and/or notification data and communicating the data to a user device or other associated device, such as a smartphone or an internet-connected piece of agricultural equipment. Agricultural equipment can incorporate many of the same types of electronic devices as client computing device 110 or smart phones. As such, operation 209 can include communicating with agricultural equipment, for example, over network 120, such that notifications and/or visualizations can be presented to a user of the agricultural equipment through display devices, acoustic speakers, or the like, that are incorporated into the equipment. In the example of a smartphone, the visualization and/or notification data can be formatted using standardized communication protocols, such that outputting can include sending a digital message including population data 240, intervention timing data, or other types of notifications, without a specialized application.”; Paragraph 59, “Outputting operations can also include communicating intervention action 240 with a pest management system 320 (in reference to FIG. 3). In some embodiments, outputting to pest management system 320 includes autonomous or semiautonomous initiation of an intervention actions 240. For example, intervention action 240 can be initiated through modifying a logistics system managing pest intervention equipment. Where the logistics system manages resource allocation, such as spray trucks, mite dispersal, trap teams, or other automated, pseudo-automated, or manual interventions, outputting intervention action 240 can include engaging an intervention resource 325 within a window of time corresponding to the first time point for effecting intervention action 240.”; Paragraph 60, “Following operations 207 and/or 209, example process 200 can be repeated over one or more iterations with updated state data 210 and/or intervention data 170 for an updated prediction horizon. For example, prediction horizon H can be shifted by one or more timesteps T to permit control model 220 to generate a second intervention action 240 corresponding to a second time temporally after the first time of a first intervention action 240.”; Paragraph 86, “In some embodiments, u.sub.k represents an opportunity cost associated with allocating intervention resources 325 to one region rather than another. Pest management system 320 can include limited intervention resources 325 with relatively little redundancy or excess capacity, as an approach to reduce capital expenditure and maintenance/labor costs. As such, the “cost” of implementing predicted intervention actions 355 can include equipment prioritization and other logistical considerations. In an illustrative example, pest management system 320 can coordinate intervention resources 325 for multiple agricultural environments susceptible to infestation by different pests, each managed by application of respective chemical pesticides. In this way, constraints 315 can include information about existing allocations of intervention resources 325 as a function of time. In some cases, a portion of the environment can be treated, such that u.sub.k can reflect the portion of a constraint 315 representing the resource 325 allocation for the entire environment.”; Paragraph 90, “FIG. 4A is a schematic diagram illustrating example environmental data 130, in accordance with embodiments the disclosure. Environmental data 130 includes spatial data 405 and temporal data 410, allowing environmental data 130 to describe the state of a host environment in one or more spatial dimensions and in time. Environmental data 130, as described in more detail in reference to FIG. 1-3, can include data from multiple different sources, including temperature data 415, wind data 420, humidity data 425, land-use data 430, or the like.”)
Stueve discloses a method for monitoring and predicting pest risk in crops. Johnson discloses a method for predicting pest presence and treatment planning for crops. At the time of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Stueve with the teachings of Johnson in order to improve the accuracy of pest prediction as disclosed by Johnson (Johnson: Paragraph 2, “Accurate prediction of interventions is crucial for pest management, can help reduce pesticide use, and can reduce crop damage by enabling more precise application.”)
Claim(s) 2 and 12 –
Stueve in view of Johnson disclose the limitations of claims 1 and 10
Stueve doesn’t explicitly disclose the following, however, in analogous art of pest control and management, Johnson discloses the following:
mean temperature, high temperature, mean humidity, and precipitation. (Johnson: Paragraph 39, “FIG. 2 is a process flow diagram illustrating an example process 200 for modeling population dynamics of a pest, in accordance with embodiments of the disclosure. Example process 200 may be implemented by one or more constituent elements of example system 100 of FIG. 1, including but not limited to server(s) 105 and/or client computing device(s) 110. Example process 200 includes operations 201-209 for receiving environmental data 130 and generating pest intervention recommendations 240 using control model(s) 220 including predictive models 145 and constraint models 150 as part of an optimization of competing objectives including the presence of a pest in the environment and the resource demand and/or environmental impact of interventions over a prediction horizon 415 (in reference to FIG. 4B), also referred to as “H.” In the context of the present disclosure, prediction horizon “H” describes a period of time over which state data 210 is available from which population data 140 can be predicted for use in iterative optimization of control model(s) 220.”; Paragraph 44, “In some embodiments, environmental data 130 includes data for a plurality of physical locations as part of a spatiotemporal dataset, as described in more detail in reference to FIG. 4A. For example, environmental data 130 can include two-dimensional projection data (e.g., iso-contour maps) for atmospheric pressure, precipitation, wind speed, or the like, that can be developed by meteorological or other models using point-data measured by in situ sensors. As such, environmental data 130 can be received from sources 115 that are in situ (e.g., local sensors) and/or from computer systems that communicate with in situ sensors to generate estimated and/or predicted environmental data 130. Example system 100 can receive environmental data 130 through intermediary systems (e.g., publicly available weather data), rather than communicating directly with a network of sensors specific to the pest/host system. To address limitations in sensor networks and/or prediction systems, in some embodiments, operation 201 includes accessing multiple redundant data sources. Advantageously, accessing redundant environmental data 130 addresses delays in availability of environmental data 130 from any given source and further corrects for error by aggregating environmental data 130.”; Paragraph 75, “In some embodiments, example control system 300 implements ML model(s) as part of predictive models 145 to generate input data for mechanistic model(s) such as PETE model 335. For example, input data can include values for the DEL function generated by inputting environmental data 130 including temperature data and other data, as described in more detail in reference to FIG. 4. Advantageously, ML model(s) can learn the nonlinear dependencies of DEL 340 on temperature and other weather and environmental factors. The system of “k” latent microstate equations can then be solved with the predicted value of DEL 340 to obtain predicted population density over time.”; Paragraph 90, “FIG. 4A is a schematic diagram illustrating example environmental data 130, in accordance with embodiments the disclosure. Environmental data 130 includes spatial data 405 and temporal data 410, allowing environmental data 130 to describe the state of a host environment in one or more spatial dimensions and in time. Environmental data 130, as described in more detail in reference to FIG. 1-3, can include data from multiple different sources, including temperature data 415, wind data 420, humidity data 425, land-use data 430, or the like.”)
Stueve discloses a method for monitoring and predicting pest risk in crops. Johnson discloses a method for predicting pest presence and treatment planning for crops. At the time of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Stueve with the teachings of Johnson in order to improve the accuracy of pest prediction as disclosed by Johnson (Johnson: Paragraph 2, “Accurate prediction of interventions is crucial for pest management, can help reduce pesticide use, and can reduce crop damage by enabling more precise application.”)
Claim(s) 3 and 13 –
Stueve in view of Johnson disclose the limitations of claims 1 and 10
Stueve further discloses the following:
wherein accessing the data structure includes accessing planting data specific to the field based on the field ID. (Stueve: Paragraph 94, “In some embodiments, an estimation may be made of crop stage through the use of physical observation of the field in question or one or more crop stage models. In one embodiment, the crop stage models may estimate crop stage using a combination of data sources including (but not limited to), a measure or estimate of planting or emergence date, a measure or estimate of “thermal time” (i.e., accumulated number hours above a temperature threshold), a measure or estimate of “photoperiod” (i.e., the length of daylight) at critical intervals, etc.”; Paragraph 97, “In some embodiments, the potential for pest outbreak or propagation is estimated in particular fields or portions thereof based upon specific data parameters, including (but not limited to), the crop row spacing, the irrigation status, the degree of canopy closure, and/or the crop stage.”; Paragraph 100, “Using remote geospatial image data and computer vision algorithms allows measurement and quantification of crop field parameters, such as row spacing and canopy closure, across the entire field, and thus provides a more accurate measure across an entire field or specific portions of the field. One benefit of the present invention is measuring quantitatively the crop field parameters across the whole field and providing pest susceptibility or treatment maps, all being performed remotely, automatically, and accurately.”; Paragraph 137, “Components disclosed herein can employ various classification (explicitly trained (e.g., via training data) as well as implicitly trained (e.g., via observing behavior, preferences, historical information, receiving extrinsic information, etc.)) schemes and/or systems (e.g., support vector machines, neural networks, expert systems, Bayesian belief networks, fuzzy logic, data fusion engines, etc.) in connection with performing automatic and/or determined action in connection with the claimed subject matter. Thus, classification schemes and/or systems can be used to automatically learn and perform a number of functions, actions, and/or determinations.”)
Claim(s) 4 and 14 –
Stueve in view of Johnson disclose the limitations of claims 1 and 10
Stueve further discloses the following:
determine a return on investment (ROI) for the treatment; and wherein the at least one computing device is configured, in order to determine whether the treatment is recommended for the field, to determine whether the treatment is recommended for the field further based on the ROI. (Stueve: Paragraph 90, “In some embodiments, the process further receives price information for a crop growing in the crop field, cost information for one or more agricultural management techniques, and an anticipated efficacy for the agricultural management techniques. The process then generates an anticipated return on investment (ROI) based on the price and cost information and the anticipated efficacy, as discussed below.”; Paragraph 107, “In one embodiment, once a given crop field is identified as a likely candidate for a pest outbreak, the system may compare a likely efficacy of various treatment options based upon published data, data from machines, data from manufacturers or retailers of treatment techniques, agricultural consultants, growers, third party vendors, or CERES internal data. In one embodiment, the efficacy determinations are performed through one or more machine learning (ML) algorithms, such as a random forest algorithm, described in relation to FIG. 8. In one embodiment, the ML algorithm predicts which treatment is likely to be most effective given various parameters, including the microclimate data, soil data, the crop stage, crop variety, and so forth. As a result, the likely benefits of various treatment options are then predicted by the ML algorithm in a quantitative manner (e.g., in terms of expected increases in crop yield). The yield benefits are then converted into economic estimates by, in one illustrative aspect, multiplying the yield benefits by the price of the particular crop in question. The economic benefits are then compared to the cost of the treatment option(s) to predict a likely return on investment (ROI) of various treatment options.”; Paragraph 108, “Accordingly, and in accordance to one embodiment, the risk model implementation further comprises program code to receive price information for a crop growing in the crop field, a cost information for one or more agricultural management techniques, and an anticipated efficacy for the agricultural management techniques, and generate an anticipated return on investment (ROI) based on the price and cost information and the anticipated efficacy.”)
Claim(s) 6 and 16 –
Stueve in view of Johnson disclose the limitations of claims 1 and 10
Stueve further discloses the following:
wherein the treatment includes a fungicide. (Stueve: Paragraph 141, “A starting point for any machine learning method such as used by the machine learning component above is a documented dataset containing multiple instances of system inputs and correct outcomes (e.g., the training data). This data set can be used, using methods known in the art, including but not limited to standardized machine learning methods such as parametric classification methods, non-parametric methods, decision tree learning, neural networks, methods combining both inductive and analytic learning, and modeling approaches such as regression models, to train the machine learning system and to evaluate and optimize the performance of the trained system. The quality of the output of the machine learning system depends on (a) the pattern parameterization, (b) the learning machine design, and (c) the quality of the training database. These components can be refined and optimized using various methods. For example, the database can be refined by adding datasets for new documented crop fields. The quality of the database can be improved, for example, by populating the database with cases in which the customization was accomplished by one or more experts in crop pest prediction or treatment (e.g., fungicide) application. Thus, the database will better represent the expert's knowledge. In one embodiment, the database includes data, for example, of poor agricultural management, which can assist in the evaluation of a trained system.”)
Claim(s) 11 –
Stueve in view of Johnson disclose the limitations of claims 1 and 10
Stueve further discloses the following:
comprising an agricultural apparatus in communication with the at least one computing device; and wherein the at least one computing device is further configured to transmit instructions to the agricultural apparatus to apply the treatment to the field consistent with the recommendation. (Stueve: Paragraph 140, “In various embodiments of the present invention, training may apply to the machine vision algorithms described in FIG. 7 or to the machine learning algorithms described in FIG. 8. For the machine vision algorithms described above (e.g., 310, 320), the input data acquired at step 902 may comprise geospatial image data of one or more sample crop fields and one or more crop vigor maps for the one or more sample crop fields. For the machine learning algorithms described above (e.g., the risk model 350), the input data acquired at step 902 may comprise crop vigor map of one or more sample crop fields as well as microclimate data, other crop field parameters (e.g., row spacing), pest outbreak measurements, and/or agricultural treatment plans of the one or more sample crop fields.”; Paragraph 163, “In some embodiments, the sprayers used in precision agriculture may incorporate engineering that allows growers to execute the process at a fine scale (i.e., individual nozzle control for on/off spray applications at a 20 inch spacing). As an example, flow control may be performed at the individual nozzle level, which would allow the application of different fungicide/spray rates at a 20 inch spacing. This process would take into account the spatial variability of canopy vigor in a closed canopy. In one embodiment, the treatment plan generates a control protocol for these spray nozzles. Therefore, heavy rates of fungicide/spray would generate a high ROI where canopy is closed and the most vigorous. And fungicide/spray rates could be decreased substantially (but not eliminated or turned off) in other parts of the field where canopy is closed, but far less vigorous, saving money for growers.”; Paragraph 165, “Embodiments of the subject matter and the operations described herein can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Embodiments of the subject matter described herein can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on computer storage medium for execution by, or to control the operation of, information/data processing apparatus. Alternatively, or in addition, the program instructions can be encoded on an artificially-generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information/data for transmission to suitable receiver apparatus for execution by an information/data processing apparatus. A computer storage medium can be, or be included in, a computer-readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or a combination of one or more of them. Moreover, while a computer storage medium is not a propagated signal, a computer storage medium can be a source or destination of computer program instructions encoded in an artificially-generated propagated signal. The computer storage medium can also be, or be included in, one or more separate physical components or media (e.g., multiple CDs, disks, or other storage devices).”)
Claim(s) 5 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Stueve (US 2020/0364843 A1) in view of Johnson (US 2023/0385654 A1) and Bainbridge (US 2023/0292647 A1)
Claim(s) 5 and 15 –
Stueve in view of Johnson disclose the limitations of claims 1 and 10
Stueve in view of Johnson do not explicitly disclose the following, however, in analogous art of crop health management, Bainbridge discloses the following:
herein the at least one disease model includes multiple of: a septoria model, a leaf rust model, a stripe rust model, and a fusarium model. (Bainbridge: Paragraph 30, “For example, the machine learning model may be trained to detect: various diseases such as septoria, stripe rust, leaf rust and fusarium head blight (FHB); various pests such as aphids, mites, orange wheat blossom midge (OWBM), locusts; and/or various weeds such as black grass. A crop feature may be classed as healthy if no disease, pests or weeds are detected. Crop feature “health” may also be deduced from its size/dimensions compared to the expected size/dimensions for the current crop cycle.”; Paragraph 100, “FIGS. 1(a) and 1(b) show example illustrations of crops 10 and crop features 12, 14, 16 and sub-features 12a which in this example are wheat plants 10, with heads 12, stems 14, leaves 16, and kernels 12a (grains/seeds). The crop features are inspected by farmers to monitor crop health, loss and yield. A crop feature 10 may have several attributes that correlate with crop health, loss and yield, and which a farmer can look for to base various conclusion and decisions on. For example, and pests such as aphids and mites can be detected upon close inspection of crop features. In addition, many diseases manifest as visible deterioration on the crop features that can be detected by experienced farmers at a relatively early stage, such as stripe rust on leaves 16 shown in FIG. 2. Also, the number of kernels 12a can be counted. By way of example, a wheat head 12 may have 25-50 kernels 12a depending on the health and nutrition of the crop. A high yielding crop of wheat may have 45-50 kernels per head, but this is reduced if nitrogen supply is limited. As such, a farmer can visually inspect the number of kernels 12a to base a conclusion that nitrogen supply is limited or yield is high. Based on detection of disease, pest, weeds, and/or poor health/yield the farmer can intervene by applying one or more treatments to the crops. e.g. fungicide, pesticide, weed killer, nitrogen etc. However, this manual process has several drawbacks: it is extremely time consuming; it is not feasible to inspect every crop so in practice only small sample or areas of crops are inspected and results are extrapolated across the whole field; and results can vary depending on the knowledge and experience of the farmer doing the crop monitoring.”; Paragraph 111, “In step 130, one or more crop features 12, 14, 16 of each crop in each HR image I.sub.HR are identified using a using a machine learning model trained on a dataset of crop images to detect and classify the one or more crop features in the respective HR image I.sub.HR. In an embodiment, the machine learning model comprises a convolution neural network (CNN) and leverages Google Vision, Opencv, and Scipy Libraries.”)
Stueve discloses a method for monitoring and predicting pest risk in crops. Johnson discloses a method for predicting pest presence and treatment planning for crops. Bainbridge discloses a method for monitoring and identifying issues in crops. At the time of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Stueve in view of Johnson with the teachings of Bainbridge in order to improve the accuracy crop monitoring as disclosed by Bainbridge (Bainbridge: Paragraph 6, “There is therefore a need for an automated system and method of crop monitoring for more efficient crop monitoring, accurate crop yield predictions, and highly targeted interventions up to a plant-by-plant level.”)
Claim(s) 7-9, and 17-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Stueve (US 2020/0364843 A1) in view of Johnson (US 2023/0385654 A1) and Sohl-Dickstein (US 2022/0108149 A1)
Claim(s) 7 and 17 –
Stueve and Johnson disclose the limitations of claims 1 and 10
Stueve in view of Johnson doesn’t explicitly disclose the following, however, in analogous art of machine learning processing, Sohl-Disckstein discloses the following:
wherein the GRU-based phenology model further includes a neural network layer and a thresholding layer, the thresholding layer including a cross entropy cost function. (Sohl-Dickstein: Paragraph 20, “In some cases, the neural network is a neural network that is configured to perform an image processing task, i.e., receive an input image and to process the input image to generate a network output for the input image. For example, the task may be image classification and the output generated by the neural network for a given image may be scores for each of a set of object categories, with each score representing an estimated likelihood that the image contains an image of an object belonging to the category. As another example, the task can be image embedding generation and the output generated by the neural network can be a numeric embedding of the input image. As yet another example, the task can be object detection and the output generated by the neural network can identify locations in the input image at which particular types of objects are depicted. As yet another example, the task can be image segmentation and the output generated by the neural network can assign each pixel of the input image to a category from a set of categories.”; Paragraph 34, “Additionally, the neural network can have any appropriate architecture for performing the machine learning task. Examples include convolutional neural network architectures, feed-forward network architectures, e.g., multi-layer perceptrons, Transformer architectures that include multiple self-attention layers, and recurrent neural network architectures, e.g., GRUs or LSTMs.”; Paragraph 45, “For example, at each iteration during training, the neural network system 100 can process a batch of training examples and generate a respective neural network output for each training input in the batch. The neural network outputs can then be used to adjust the values of the parameters of the neural network layers, e.g., by computing, through conventional gradient descent and backpropagation neural network training techniques, gradients with respect to the parameters of a loss function for the neural network task, e.g., a cross-entropy loss, a negative log-likelihood loss, a mean squared error loss, and so on, that is based on the neural network outputs and the target outputs in the training example. Thus, the parameters of the pre-normalized layer 108 are learned through gradient descent and backpropagation during the training of the neural network.”; Paragraph 46, “FIG. 2 is a flow diagram of an example process 200 for processing an input using a pre-normalized layer. For convenience, the process 200 will be described as being performed by a system of one or more computers located in one or more locations. For example, a batch normalization layer included in a neural network system, e.g., the batch normalization layer 108 included in the neural network system 100 of FIG. 1, appropriately programmed, can perform the process 200.”)
Stueve discloses a method for monitoring and predicting pest risk in crops. Johnson discloses a method for predicting pest presence and treatment planning for crops. Sohl-Dickstein discloses a method for machine learning architecture. At the time of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Stueve in view of Johnson with the teachings of Sohl-Dickstein to improve the performance of the machine learning models as disclosed by Sohl-Dickstein (Sohl-Dickstein: Paragraph 4, “More specifically, to improve the performance of the neural network, the neural network includes either one or more pre-normalized layers or one or more regularization normalization layers.”)
Claim(s) 8 and 18 –
Stueve and Johnson disclose the limitations of claims 1, 7, 10 and 17
Stueve in view of Johnson doesn’t explicitly disclose the following, however, in analogous art of machine learning processing, Sohl-Disckstein discloses the following:
wherein the neural network layer includes a feedforward neural network. (Sohl-Dickstein: Paragraph 34, “Additionally, the neural network can have any appropriate architecture for performing the machine learning task. Examples include convolutional neural network architectures, feed-forward network architectures, e.g., multi-layer perceptrons, Transformer architectures that include multiple self-attention layers, and recurrent neural network architectures, e.g., GRUs or LSTMs.”; Paragraph 66, “Additionally, the neural network can have any appropriate architecture for performing the machine learning task. Examples include convolutional neural network architectures, feed-forward network architectures, e.g., multi-layer perceptrons, Transformer architectures that include multiple self-attention layers, and recurrent neural network architectures, e.g., GRUs or LSTMs.”)
Stueve discloses a method for monitoring and predicting pest risk in crops. Johnson discloses a method for predicting pest presence and treatment planning for crops. Sohl-Dickstein discloses a method for machine learning architecture. At the time of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Stueve in view of Johnson with the teachings of Sohl-Dickstein to improve the performance of the machine learning models as disclosed by Sohl-Dickstein (Sohl-Dickstein: Paragraph 4, “More specifically, to improve the performance of the neural network, the neural network includes either one or more pre-normalized layers or one or more regularization normalization layers.”)
Claim(s) 9 and 19 –
Stueve and Johnson disclose the limitations of claims 1 and 10
Stueve in view of Johnson doesn’t explicitly disclose the following, however, in analogous art of machine learning processing, Sohl-Disckstein discloses the following:
herein the GRU-based phenology model includes multiple layers of GRUs, which include more than twenty GRUs. (Sohl-Dickstein: Paragraph 34, “Additionally, the neural network can have any appropriate architecture for performing the machine learning task. Examples include convolutional neural network architectures, feed-forward network architectures, e.g., multi-layer perceptrons, Transformer architectures that include multiple self-attention layers, and recurrent neural network architectures, e.g., GRUs or LSTMs.”; Paragraph 38, “Layers 104 and 112 can be any of a variety of types of neural network layers, e.g., conventional layers like fully-connected layers, convolutional layers, recurrent layers, or attention layers, or other pre-normalized layers.”; Paragraph 66, “Additionally, the neural network can have any appropriate architecture for performing the machine learning task. Examples include convolutional neural network architectures, feed-forward network architectures, e.g., multi-layer perceptrons, Transformer architectures that include multiple self-attention layers, and recurrent neural network architectures, e.g., GRUs or LSTMs.”; Paragraph 82, “In some other cases, the layer 308 also applies a scaling parameter to the scaled layer input to generate a second scaled layer input and applies a bias parameter to the second scaled layer input to generate a biased scaled layer input. Then, the layer 308 either uses the biased scaled layer input as the layer output 310 or applies a non-linear activation function to the biased scaled layer input to generate the layer output 310.”; Paragraph 94, “The system determines a gradient with respect to a set of parameters of the neural network of a loss function that includes (i) one or more terms that measure a quality of the training outputs with respect to the neural network task and (ii) a regularizer term that penalizes the neural network for a sum of values of the same scaled transformed elements in different scaled layer inputs having a large magnitude (step 406).”)
Stueve discloses a method for monitoring and predicting pest risk in crops. Johnson discloses a method for predicting pest presence and treatment planning for crops. Sohl-Dickstein discloses a method for machine learning architecture. At the time of Applicant’s filed invention, one of ordinary skill in the art would have deemed it obvious to combine the methods of Stueve in view of Johnson with the teachings of Sohl-Dickstein to improve the performance of the machine learning models as disclosed by Sohl-Dickstein (Sohl-Dickstein: Paragraph 4, “More specifically, to improve the performance of the neural network, the neural network includes either one or more pre-normalized layers or one or more regularization normalization layers.”)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Guan (US 2022/0061236 A1) discloses a method for accessing agriculture productivity
Reese (US 2019/0179982 A1) discloses a method for utilizing a subscribed platform and cloud-computing to model disease risk
Lindores (US 2014/0012732 A1) discloses a method for generating a crop recommendation
Miller (US 2022/0051350 A1) discloses a method for pest and agronomic condition prediction
Du (US 2020/0143191 A1) discloses a method for image recognition with machine learning
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Philip N Warner whose telephone number is (571)270-7407. The examiner can normally be reached Monday-Friday 7am-4:00pm.
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, Jerry O’Connor can be reached at 571-272-6787. 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.
/Philip N Warner/Examiner, Art Unit 3624
/Jerry O'Connor/Supervisory Patent Examiner,Group Art Unit 3624