DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
101 Rejection
Bases on applicant’s filed amendments, the previously set forth 101 rejections have been overcome.
102/103 Rejection
Based on applicant’s filed amendments, the previous 102 rejection was overcome. However, a new ground of rejection has been made.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-3, 6, 7, 9, 11, 12, 13, 16, 17 and 21-25 is/are rejected under 35 U.S.C. 103 as being unpatentable over Trenholm (2016/0034809) in view of Soni et al. (Hyperspectral imaging and deep learning for quantification of Clostridium sporogenes spores in food products using 1D- convolutional neural networks and random forest model), further in view of Watson et al. (2015/0036138).
With respect to claims 1 and 11, Trenholm et al. teaches a non-transitory computer-readable medium [0053] comprising executable instructions (i.e. readable/executable instructions; [0053]), the executable instructions being executable by one or more processors [0053] to perform a method for analyzing a food sample to identify a practical of interest (as Trenholm teaches in [0150], a method for sensing food ingredient and sending various contamination before or during manufacturing), the method comprising: measuring, via a sensor (via a CMOS sensor used with spectroscopy; [0150]) and based on a predefined resolution (as the sensor will be set to a predefined low to moderate resolution for routine solid and liquid scans for food inspection; [0150]), a plurality of intensities for a plurality of wavelengths of electromagnetic radiation that has passed through the food sample (as Trenholm et al. teaches using spectroscopy for sampling food with the common bandpasses of 2nm to 10nm for UV-ZVis), to produce a first set of data in a first format (as Trenholm teaches receiving data via an interface module 240; [0072]) and including a set of spectral metrics (as Trenholm discloses a first set of data is collected from sensors 1414 that include features extracted using FFT or wavelet transformation; [0072]); processing the first set of data to obtain a second set of data in a second format different from the first format (as Trenholm teaches converting image data to difference image file format; [0129]), the second set of data including the set of spectral metrics (i.e. a set of spectral metric a model has been trained on); applying one or more trained models (i.e. as Trenholm teaches downloading a trained model according to its application; [0134]) to a set of values based on the set of spectral metrics (i.e. the converted set of spectral metrics) to obtain a result (i.e. a generated prediction; [0134]), based on the result (i.e. predictions sent to computational modules), determining either a positive particle of interest detection or a negative particle of interest detection for the particle of interest for the food sample (i.e. as the computational module, trained and receiving the converted data sets from the x-ray sensor, for example, to indicate the presence or absence of a substance; [0152]); generating a particle of interest detection notification that indicates either the positive particle of interest detection or the negative particle of interest detection for the particle of interest for the food sample (as Trenholm teaches notifying a professional based on the indicated presence or absence of the pathogen substance; 0151]); and providing the particle of interest detection notification (as Trenholm teaches providing the profession the notification).
Trenholm remains silent regarding the one or more trained models trained on a set of training samples that represent a plurality of concentrations of a particle of interest and that is prepared based on a plurality of predefined dilution ratio; and in response to the particle of interest detection notification indicating the positive particle of interest detection, to cause at least one of a food quarantine or a food recall, associated with the food sample.
Soni et al. teaches a similar method that includes trained models trained on a set of training samples that represent a plurality of concentrations of a particle of interest and that is prepared based on a plurality of predefined dilution ratio (as Soni et al. teaches the sample preparation using a plurality of concentrations of C. sporogenes, see sections 2.3-2.3.2, then 50% of those samples were used as a training data set to train a model; see section 2.5.2).
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to modify the training of the model in Trenholm using the methodology taught in Soni et al. because Soni et al. teaches such a modification allows for a CNN to improve the accuracy when trained using the taught samples of Soni et al.; Abstract.
Trenholm as modified remains silent regarding in response to the particle of interest detection notification indicating the positive particle of interest detection, to cause at least one of a food quarantine or a food recall, associated with the food sample.
Watson et al. teaches a similar method were based on information about the food containing a particle of interest detection notification to cause a food recall, associated with the food sample; [0252].
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to modify the method to include the step of causing a food recall associated with the food sample, as taught by Watson et al. because Watson et al. teaches such a modification protects public health and the prevention of illness.
With respect to claims 2, 12 and 23, Trenholm et al. teaches the non-transitory computer-readable medium, wherein the method further comprises: receiving metadata (i.e. an origin of the data; [0072]) associated with the sensor that performs the measuring [0150], the food sample, a date and time [0072] at which the sensor (i.e. sensor of the apparatus) obtains the set of spectral metrics (sensed data); and storing the metadata in association with the result (as the overall process stores the data relative the result in the taught computer modules).
With respect to claims 3 and 13, Trenholm et al. teaches the non-transitory computer-readable medium wherein the food sample is a sample of a food processing byproduct [0150], and the particle of interest is a foodborne pathogen [0152].
With respect to claims 6 and 16, Trenholm et al. teaches the non-transitory computer-readable medium wherein the method further comprises training one or more models on the set of training samples for the particle of interest to obtain the one or more trained models (as Trenholm et al. teaches using a trained dataset; [0157]).
With respect to claims 7 and 17, Trenholm et al. teaches the non-transitory computer-readable medium wherein spectral metrics in the set of spectral metrics reflectance metrics (SPIRIS; [0153]).
With respect to claims 9 and 19, Trenholm et al. teaches the non-transitory computer-readable medium wherein the electromagnetic radiation includes visible light (as Trenholm et al. teaches SPIRIS which uses visible light).
With respect to claim 21, Trenholm et al. teaches a system for analyzing a food sample to identify a particle of interest (as Trenholm teaches in [0150] and Fig. 1 a system for sensing food ingredient and sending various contamination before or during manufacturing), the system comprising: a first computing device configured to:
measuring, via a sensor (via a CMOS sensor used with spectroscopy; [0150]) and based on a predefined resolution (as the sensor will be set to a predefined low to moderate resolution for routine solid and liquid scans for food inspection; [0150]), a plurality of intensities for a plurality of wavelengths of electromagnetic radiation that has passed through the food sample (as Trenholm et al. teaches using spectroscopy for sampling food with the common bandpasses of 2nm to 10nm for UV-ZVis), to produce a first set of data in a first format (as Trenholm teaches receiving data via an interface module 240; [0072]) and including a set of spectral metrics (as Trenholm discloses a first set of data is collected from sensors 1414 that include features extracted using FFT or wavelet transformation; [0072]); processing the first set of data to obtain a second set of data in a second format different from the first format (as Trenholm teaches converting image data to difference image file format; [0129]), the second set of data including the set of spectral metrics (i.e. a set of spectral metric a model has been trained on); and transmit the second set of data (para [0152]-[0153]); and a second computing device configured to: receive the second set of data (para [0152]-[0153]); apply one or more trained models to at least one of the set of spectral metrics and a set of values based on the set of spectral metrics to obtain a result; based on the result, determine either a positive particle of interest detection or a negative particle of interest detection for the particle of interest for the sample (para [0152]); and transmit to the first computing device either the positive particle of interest detection or the negative particle of interest detection for the particle of interest for the sample, wherein the first computing device is further configured to: generate a particle of interest detection notification that indicates either the positive particle of interest detection or the negative particle of interest detection for the particle of interest for the food sample (para [0156]); and provide the particle of interest detection notification (para [0156]).
Trenholm remains silent regarding the one or more trained models trained on a set of training samples that represent a plurality of concentrations of a particle of interest and that is prepared based on a plurality of predefined dilution ratio; and in response to the particle of interest detection notification indicating the positive particle of interest detection, to cause at least one of a food quarantine or a food recall, associated with the food sample.
Soni et al. teaches a similar method that includes trained models trained on a set of training samples that represent a plurality of concentrations of a particle of interest and that is prepared based on a plurality of predefined dilution ratio (as Soni et al. teaches the sample preparation using a plurality of concentrations of C. sporogenes, see sections 2.3-2.3.2, then 50% of those samples were used as a training data set to train a model; see section 2.5.2).
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to modify the training of the model in Trenholm using the methodology taught in Soni et al. because Soni et al. teaches such a modification allows for a CNN to improve the accuracy when trained using the taught samples of Soni et al.; Abstract.
Trenholm as modified remains silent regarding in response to the particle of interest detection notification indicating the positive particle of interest detection, to cause at least one of a food quarantine or a food recall, associated with the food sample.
Watson et al. teaches a similar method were based on information about the food containing a particle of interest detection notification to cause a food recall, associated with the food sample; [0252].
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to modify the method to include the step of causing a food recall associated with the food sample, as taught by Watson et al. because Watson et al. teaches such a modification protects public health and the prevention of illness.
With respect to claim 22, Trenholm et al. teaches the system of claim 21, further comprising the apparatus, wherein the apparatus is configured to: obtain the set of spectral metrics based on interactions of electromagnetic radiation with the food sample (para [0152]-[0153], [0156]); and provide the first set of data including the set of spectral metrics to the first computing device (para [0152]-[0153], [0156]).
With respect to claim 24, Trenholm et al. teaches the system of claim 21 wherein spectral metrics in the set of spectral metrics are one of absorbance metrics, transmittance metrics, reflectance metrics, and scattering metrics (para [0153]).
With respect to claim 25 Trenholm et al. teaches the system of claim 21 wherein the electromagnetic radiation includes at least one of ultraviolet light, visible light, and infrared light (para [0153]).
Claim(s) 4, 10, 14 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Trenholm (2016/0034809) in view of Soni et al. (Hyperspectral imaging and deep learning for quantification of Clostridium sporogenes spores in food products using 1D- convolutional neural networks and random forest model) and Watson et al. (2015/0036138), as applied to claim 1, 11 and 14, further in view of Lefkofsky (2021/0118559).
With respect to claims 4 and 14, Trenholm et al. teaches all that is claimed in the above rejection of claims 1 and 11, including the non-transitory computer-readable medium wherein the set of spectral metrics is a first set of spectral metrics (as Trenholm teaches the sensors providing spectral imaging data; [0150], the sensor is a first sensor from a first manufacturer sited (as Trenholm teaches a first apparatus in food manufacturing including the taught sensors; [0150]) at a first location (i.e. at a specialized locations; [0134]), the food sample is a first sample (i.e. a first sample under testing), the set of values is a first set of values (as converted), the result is a first result (related to the first sample), the positive particle of interest detection is a first positive particle of interest detection, the negative particle of interest detection is a first negative particle of interest detection (as the trained model and predication is feed data from the first sample to determine a positive or negative particle of interest), the particle of interest detection notification is a first particle of interest detection notification (as the professional will be notified if there is a positive or negative presence of the pathogen based on the results (para [0129]; "a neural network is applied to drive evolution of the choice of reaction substances provided for pathogen detection with a sample. Particularly, selection of a reaction substance may compensate for mutation, pleomorphism and polymorphism of pathogens to ensure that appropriate reaction substances are selected to maximize likelihood of detecting a pathogen. Accordingly, inputs including a combination of time series genomic data of the pathogen and/or human host cells, and data relating to a plurality of desired substances (e.g. disease biomarkers) may be provided to a neural network trained to provide an output indicating which reaction substance(s) should be selected," para [0158]); applying the one or more modified trained models to at least one of the second set of spectral metrics and a second set of values based on the second set of spectral metrics to obtain a second result (para [0129], [0150]); based on the second result, determining either a second positive particle of interest detection or a second negative particle of interest detection for the particle of interest in the second sample (para [0152]); generating a second particle of interest detection notification that indicates either the second positive particle of interest detection or the second negative particle of interest detection for the particle of interest in the second sample (para [0156]); and providing the second particle of interest detection notification (para [0156]) but remains silent regarding, and the method further comprises: receiving a third set of data in a third format, the third set of data including a second set of spectral metrics, the second set of spectral metrics provided by a second sensor that obtains the second set of spectral metrics based on interactions of electromagnetic radiation with a second sample, and that is sited at a second location different from the first location; processing the third set of data to obtain a fourth set of data in the second format, the fourth set of data including the second set of spectral metrics.
Lefkofsky teaches a similar method receiving a third set of data in a third format, the third set of data including a second set of spectral metrics, the second set of spectral metrics provided by a second apparatus that obtains the second set of spectral metrics based on interactions of electromagnetic radiation with a second sample, and the second apparatus is sited at a second location different from the first location; processing the third set of data to obtain a fourth set of data in the second format, the fourth set of data including the second set of spectral metrics ("[e]ach device may be in operative communication with one or more aspects of the system 101 in order to transmit information from the device into the system for processing and storage into the device dataset 270. Device dataset 270 may further include communication processes, application interfaces, and/or conversion parameters for receipt of the subject information from the devices included within the dataset autonomously. Such communication processes may include communication over the World Wide Web, Wi-Fi, Bluetooth, internet of things, or other communication mediums. Application interfaces may include the APIs and libraries needed to access the communication processes. Conversion parameters may include data formats of which the devices provide subject information and processes for converting the device subject information to the structured format of structured databases 210 and 220," para [0096]; "[o]ften, there are a large number of clinical trials being conducted at any given time, and typically the clinical trials relate to a wide range of diseases and conditions. In some instances, clinical trials are performed at multiple sites, such as hospitals, laboratories, and universities," para [0148]; "A clinical module (not shown) may comprise a feature collection associated with information derived from clinical records of a subject, which can include records from family members of the subject. These may be abstracted from unstructured clinical documents, EMR, EHR, or other sources of subject history. Information may include subject symptoms, diagnosis, treatments, medications, therapies, hospice, responses to treatments, laboratory testing results, medical history, geographic locations of each, demographics, or other features of the subject which may be found in the subject's medical record," para [0195]).
It would have been obvious to one of ordinary skill in the art to modify the spectroscopy system of Trenholm with the support for capturing and processing data at a pluralist of sites of Lefkofsky, because such systems and methods allow for conducting spectroscopic practices across multiple facilities (Lefkofsky: para [0096], [0145], [0195]), thereby improving the versatility of Trenholm, such that a third set of data comes from another site.
With respect to claims 10 and 20, Trenholm teaches the non-transitory computer-readable medium of claims 1 and 11 but fails to explicitly teach such a non-transitory computer-readable medium wherein the one or more trained models include a set of trained decision trees.
However, Lefkofsky teaches such a non-transitory computer-readable medium wherein the one or more trained models include a set of trained decision trees ("decision trees," para [0094]).
It would have been obvious to one of ordinary skill in the art to combine the spectroscopy system of Trenholm with the support for decision trees of Lefkofsky, because such systems and methods allow for the use of decision trees in making determinations using models for processing spectral data (Lefkofshy: para [0094]).
Claim(s) 5, 8, 15, and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Trenholm (2016/0034809) in view of Soni et al. (Hyperspectral imaging and deep learning for quantification of Clostridium sporogenes spores in food products using 1D- convolutional neural networks and random forest model) and Watson et al. (2015/0036138), as applied to claim 1, 11 and 14, further in view of Mahadevan et al. (2019/0250105).
With respect to claim 5, Trenholm et al. teaches the non-transitory computer-readable medium of claim 1, but fails to teach such a non-transitory computer-readable medium wherein the method further comprises normalizing each spectral metric in the set of spectral metrics to be between zero, inclusive, and one, inclusive, to obtain the set of values, and wherein applying the one or more trained models to at least one of the set of spectral metrics and the set of values based on the set of spectral metrics to obtain the result includes applying the one or more trained models to the set of values.
However, Mahadevan et al. teaches such a non-transitory computer-readable medium wherein the method further comprises normalizing each spectral metric in the set of spectral metrics to be between zero, inclusive, and one, inclusive, to obtain the set of values, and wherein applying the one or more trained models to at least one of the set of spectral metrics and the set of values based on the set of spectral metrics to obtain the result includes applying the one or more trained models to the set of values ("This statistical method uses a logistic regression to produce specific weights and frequencies for biochemical features that are important in classification of each bacteria based on a training data set," para [0176]; "To evaluate the importance of spectral features used for classification, a scaled version (from 0 to 1) of both the weight and how often spectral features were found from the SMLR was utilized. The product of these values is used to calculate the SMLR feature importance, which is a quantitative metric that considers both the biochemical differences across the three bacteria characterized in this study and spectral heterogeneity among the same bacteria," para [0260]).
It would have been obvious to one of ordinary skill in the art to combine the spectroscopy system of Trenholm et al. with the support for normalizing metrics to a 0-1 range of Mahadevan et al., because such systems and methods allow for scaling data to analyze data features (Mahadevan et al. para [0176], [0260]). Furthermore, both Trenholm et al. and Mahadevan et al. are directed to systems and methods for spectroscopy.
With respect to claim 8, Trenholm et al. teaches the non-transitory computer-readable medium of claim 1 but fails to explicitly teach such a non-transitory computer-readable medium wherein the result indicates the positive particle of interest detection if the result meets or exceeds a threshold.
However, Mahadevan et al. teaches such a non-transitory computer-readable medium wherein the result indicates the positive particle of interest detection if the result meets or exceeds a threshold ("After Raman spectra are collected from MEE samples, a preliminary statistical analysis approach such as a Student's t-test is calculated at each wavenumber and the significance threshold is calculated using a multiple comparison correction to identify Raman peaks that may be important in identifying the presence of bacteria," para [0206]).
It would have been obvious to one of ordinary skill in the art to combine the spectroscopy system of Trenholm et al. with the support for thresholding of Mahadevan et al., because such systems and methods allow for using thresholded data to determine the presence of a pathogen (Mahadevan et al.: para [0206]). Furthermore, both Trenholm et al. and Mahadevan et al. are directed to systems and methods for spectroscopy.
With respect to claim 15, Trenholm et al. teaches the method of claim 11, but fails to explicitly teach such a method further comprising normalizing each spectral metric in the set of spectral metrics to be between zero, inclusive, and one, inclusive, to obtain the set of values, and wherein applying the one or more trained models to at least one of the set of spectral metrics and the set of values based on the set of spectral metrics to obtain the result includes applying the one or more trained models to the set of values.
However, Mahadevan et al. teaches such a method further comprising normalizing each spectral metric in the set of spectral metrics to be between zero, inclusive, and one, inclusive, to obtain the set of values, and wherein applying the one or more trained models to at least one of the set of spectral metrics and the set of values based on the set of spectral metrics to obtain the result includes applying the one or more trained models to the set of values (para [0176], [0260]).
It would have been obvious to one of ordinary skill in the art to combine the spectroscopy system of Trenholm et al. with the support for normalizing metrics to a 0-1 range of Mahadevan et al., because such systems and methods allow for scaling data to analyze data features (Mahadevan et al.: para [0176], [0260]). Furthermore, both Trenholm et al. and Mahadevan et al. are directed to systems and methods for spectroscopy.
With respect to claim 18, Trenholm et al. teaches the method of claim 11 but fails to explicitly teach such a method wherein the result indicates the positive particle of interest detection if the result meets or exceeds a threshold.
However, Mahadevan et al. teaches such a method wherein the result indicates the positive particle of interest detection if the result meets or exceeds a threshold (para [0206]).
It would have been obvious to one of ordinary skill in the art to combine the spectroscopy system of Trenholm et al. with the support for thresholding of Mahadevan et al., because such systems and methods allow for using thresholded data to determine the presence of a pathogen (Mahadevan et al.: para [0206]). Furthermore, both Trenholm et al. and Mahadevan et al. are directed to systems and methods for spectroscopy.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Lee (2020/0306757) which teaches collects data from a sample to detect pathogens.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW G MARINI whose telephone number is (571)272-2676. The examiner can normally be reached Monday-Friday 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Stephen Meier can be reached at 571-272-2149. 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.
/MATTHEW G MARINI/ Primary Examiner, Art Unit 2853
Prosecution Insights