DETAILED ACTION
Claim Interpretation
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: a receiver configured to receive data from a plurality of data collection devices; a data converter configured to: determine a plurality of properties for the data, and convert, based on the determined properties, the data into a unified format, thereby generating converted data; an image generator configured to generate an image from the converted data; a data classifier configured to generate a classification for the image, wherein the classification identifies the image as belonging to a label; and an error detector configured to determine, based on the image and the classification, whether an error is likely present in the data. in claim 6. The same interpretation is also applied to claim 1 and 16.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory obviousness-type double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); and In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on a nonstatutory double patenting ground provided the conflicting application or patent either is shown to be commonly owned with this application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement.
Effective January 1, 1994, a registered attorney or agent of record may sign a terminal disclaimer. A terminal disclaimer signed by the assignee must fully comply with 37 CFR 3.73(b).
Claims 1-20 are provisionally rejected on the ground of nonstatutory obviousness-type double patenting as being unpatentable over claims 1-20 of co-pending Application No. 18/902,620, 18/902,606, and 18902588. Although the conflicting claims are not identical, they are not patentably distinct from each other because claim in the pending application is broader than the one in co-pending application, In re Van Ornum and Stang, 214 USPQT61, broad claims in the pending application are rejected as obvious double patenting over previously patented/filed narrow claims. For example, claim 1 of the pending application is the same as claim 1 of the co-pending application map a range of each data stream in the file to range of values in a color back and translate each sequence in the converted data into a corresponding pixel column.
This is a provisional obviousness-type double patenting rejection because the conflicting claims have not in fact been patented.
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 1 is 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. It states “an error detector configured to determine, based on the image and the classification, whether an error is likely present in the data”; the word “likely” renders the limitation indefinite because it’s unclear whether error is present or not.
Claims 9 and 18 are rejected for the same reason as claim 1.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine,
manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. When reviewing independent claim 1, and based upon consideration of all of the relevant factors with respect to the claim as a whole, claims 1-20 are held to claim an abstract idea without reciting elements that amount to significantly more than the abstract idea and is/are therefore rejected as ineligible subject matter under 35 U.S.C. 101.
The Examiner will analyze Claim 1, and similar rationale applies to independent Claim 6 and 16.
The rationale, under MPEP § 2106, for this finding is explained below. The claimed invention (1) must be directed to one of the four statutory categories, and (2) must not be wholly directed to subject matter encompassing a judicially recognized exception, as defined below. The following two step analysis is used to evaluate these criteria.
Step 1: Is the claim directed to one of the four patent-eligible subject matter categories: process, machine, manufacture, or composition of matter?
When examining the claim under 35 U.S.C. 101, the Examiner interprets that the claims is related to a machine since the claim is directed to a data harmonizer device.
Step 2a, Prong 1: Does the claim wholly embrace a judicially recognized exception, which includes laws of nature, physical phenomena, and abstract ideas, or is it a particular practical application of a judicial exception?
The Examiner interprets that the judicial exception applies since Claim 1 limitation of determine a plurality of properties for the data [mental process]; data converter configured to convert the data into a unified format, thereby generating converted data [this is like Parsing, translating or normalizing information at high level, which could be done in human mind]; a data classifier configured to generate a classification for the image, wherein the classification identifies the image as belonging to a label [This could also be done in human mind] are directed to an abstract.
If/when the claim recites a judicial exception (i.e., an abstract idea enumerated in MPEP § 2106.04(a), a law of nature, or a natural phenomenon), the claim requires further analysis in Prong Two.
Step 2a, Prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application? NO,
The additional claim limitations
a receiver configured to receive data from a plurality of data collection devices is nothing more than insignificant extra solution activity.
an image generator configured to generate an image from the converted data This doesn’t recite a specific/new image generation technique, it doesn’t improve error detection technology.
an error detector configured to determine, based on the image and the classification, whether an error is likely present in the data it generates outcome with no restriction on how the result is accomplished, which doesn’t integrate an abstract idea into a practical application.
Data harmonizer devices are used to generally apply the abstract idea without limiting how it functions.
Step 2b: If a judicial exception into a practical application is not recited in the claim, the Examiner must interpret if the claim recites additional elements that amount to significantly more than the judicial exception.
The Examiner interprets that the claims do not amount to significantly more.
Furthermore, the generic computer components or machine learning algorithm of the memory recited as performing generic computer or machine learning functions that are well-understood, routine and conventional activities amount to no more than implementing the abstract idea with a computerized system.
The Examiner finds that Claims 2-8, 10-17, and 19-20 does not state significantly more since the claim only recites additional steps for detecting an error using data harmonizer device.
Thus, claims 1-20 recite the same abstract idea and therefore are not drawn to the eligible subject matter as they are directed to the abstract idea without significantly more.
Therefore, all claims are rejected under 35 U.S.C. 101.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 4-6, 9, and 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over OSHIMA et al. (Pub. No. US 2023/0377313) in view of Thewes et al. (Pub. No. 2023/0325640).
Regarding claim 1 and 9, OSHIMA teaches a data harmonizer device (state detection apparatus), comprising: a receiver (spectral intensity transformation unit 11) configured to receive data from a plurality of data collection devices (plurality of sensors) [Para. 10 “According to the present invention, the following state detection apparatus is provided”; Para. 41 “A time-series signal is output from each of the plurality of sensors for monitoring the state of the facility.”; And Para. 42 “The digitized time-series signals are input to a spectral intensity transformation unit 11.”]; a data converter configured to: determine a plurality of properties (spectral intensity vectors) for the data, and convert, based on the determined properties (spectral intensity vectors), the data into a unified format (quantized spectral intensity vector), thereby generating converted data; [Para. 42 “The spectral intensity transformation unit 11 transforms each of the digitized time-series signals into a vector with respect to the frequency spectral intensity by, for example, a discrete Fourier transform or a fast Fourier transform (FFT)”; Para. 44 “Each of the spectral intensity vectors is input to a quantization unit 12” and “thus, the quantized spectral intensity vector is output by the number of sensors”]; an image generator (pseudo image generation unit 13) configured to generate an image (pseudo image) from the converted data (quantized spectral intensity vector) [Para. 45 “Each of the quantized spectral intensity vectors is input to the pseudo image generation unit 13. The pseudo image generation unit 13 treats a single quantized spectral intensity vector as one row, and generates a two-dimensional image by arranging the quantized spectral intensity vectors corresponding to each sensor in the vertical direction.”]; a data classifier (classification unit 23) configured to generate a classification (classification result) for the image (pseudo image), wherein the classification identifies the image as belonging to a label (class) [Para. 71 “The classification unit 23 is composed of a single layer or a plurality of layers, receives the result of the feature extraction, calculates the probability that the pseudo image input to the convolutional neural network 21 belongs to each class, and outputs the probability as a classification result”); and an error detector (convolutional neural network 21) configured to determine, based on the image and the classification, whether an error (abnormal state) is likely present [Para. 71 “The classification unit 23 is composed of a single layer or a plurality of layers, receives the result of the feature extraction, calculates the probability that the pseudo image input to the convolutional neural network 21 belongs to each class, and outputs the probability as a classification result. For example, in FIG. 2B, the convolutional neural network 21 performs the classification of a first normal state, a second normal state, a first abnormal state, a second abnormal state, a third abnormal state of the five classes and outputs the probability of belonging to each class. Thus, the state of the facility being monitored by the sensor can be classified based on the digitized time-series signal of the sensor.”].
however, OSHIMA doesn’t explicitly teach that the error is in the data.
Thewes teaches detecting anomaly in sensor data [Para 13 “According to one aspect, a system is obtained with which an explanation output can be rendered for users that relates to an anomaly predicted by an anomaly detection module in high frequency sensor data or values derived therefrom in an industrial production process.”].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify OSHIMA’s convolutional-neural-network classification logic by incorporating Thewes’ teaching of treating an anomaly prediction as occurring in data so that OSHIMA’s abnormal state classification from pseudo image analysis is tied to the underlying sensor data being processed. This modification improves OSHIMA by making the abnormal classification result data specific, thereby enabling the system to identify whether the processed sensor data likely contains an error rather than merely reporting a facility state label.
Regarding claims 4 and 15, OSHIMA teaches wherein the error detector is further configured to: send (input) the image (pseudo image) to a convolutional neural network (CNN) (21), wherein the CNN (21) is configured to analyze spatial relationships (same area in the image) in the image [Para. 69 “The pseudo image output from the pseudo image generation unit 13 is input to the convolutional neural network 21” and Para. 123 “generally, in a convolutional neural network, when an image of a plurality of channels (plural number) is input, multiply-accumulation operation on the pixel values of the same area in the image of the plurality of channels is operated to fuse the information of the plurality of channels, and feature extraction and classification are performed based on the fused information”].
Regarding claims 5 and 16, OSHIMA teaches wherein the error detector is further configured to: determine whether the error (abnormal state) is likely present based on the spatial relationships (same area in the image) in the image analyzed by the CNN (21) [Para. 123 and 71].
However, OSHIMA doesn’t explicitly teach about the error being in the data.
Thewes teaches detecting anomaly in sensor data [Para 13 “According to one aspect, a system is obtained with which an explanation output can be rendered for users that relates to an anomaly predicted by an anomaly detection module in high frequency sensor data or values derived therefrom in an industrial production process.”].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify OSHIMA’s convolutional-neural-network classification logic by incorporating Thewes’ teaching of treating an anomaly prediction as occurring in data so that OSHIMA’s abnormal state classification from pseudo image analysis is tied to the underlying sensor data being processed. This modification improves OSHIMA by making the abnormal classification result data specific, thereby enabling the system to identify whether the processed sensor data likely contains an error rather than merely reporting a facility state label.
Regarding claims 6 and 17, OSHIMA teaches wherein the error detector is further configured to: train weights (weight parameters) of the CNN (21) based on the label (label data) and the image [Para. 82 and 84].
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over OSHIMA et al. (Pub. No. US 2023/0377313) in view of Thewes et al. (Pub. No. 2023/0325640) further in view MATHUR et al. (Pub. No. US 2022/0299338).
Regarding claim 2, OSHIMA teaches wherein the image generator (pseudo image generation unit 13) is configured to generate a image based on the converted data (quantized spectral intensity vectors) [Para. 45 “Each of the quantized spectral intensity vectors is input to the pseudo image generation unit 13. The pseudo image generation unit 13 treats a single quantized spectral intensity vector as one row, and generates a two-dimensional image by arranging the quantized spectral intensity vectors corresponding to each sensor in the vertical direction. Since the image is not a normal image such as a camera image, it is a pseudo image”].
However, OSHIMA in vie of Thewes doesn’t explicitly teach generating heat map image.
Mathur teaches having a heat map image [Para. 17].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify OSHIMA in view of Thewes’s Pseudo image generation unit by incorporating Mathur’s teaching of generating a heat map image so that Oshima’s quantized spectral intensity vectors are encoded as heat map values rather than only as a generic two-dimensional pseudo image. This medication improves Oshima by making sensor derived intensity variations visually separable in the generated image, thereby facilitating downstream classification and abnormal state detection.
Claims 3 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over OSHIMA et al. (Pub. No. US 2023/0377313) in view of Thewes et al. (Pub. No. 2023/0325640) further in view Wang (Pub. No. US 2021/0334954).
Regarding claims 3 and 14, OSHIMA in view of Thewes doesn’t explicitly teach the claim limitations.
However, Wang teaches wherein the error detector is further configured to: determine the presence of outlier data (anomalies) in the image [Para. 6]; and determine that the error is likely present in the data in response to a determination of the presence of the outlier data (anomalies) in the image (score image) [para. 13].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify OSHIMA in view of Thewes’s abnormal state decision, by incorporating Wang’s score image anomaly detection so that detected outlier data in the generated image triggers the decision that the underlying data is abnormal. This modification improves OSHIMA by providing a direct image-level trigger for a data level anomaly decision, thereby reducing unexplained abnormal state outputs.
Claims 7 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over OSHIMA et al. (Pub. No. US 2023/0377313) in view of Thewes et al. (Pub. No. 2023/0325640) further in view ARDITTI ILITZKY et al. (Pub. No. US 2020/0278665 hereinafter “ARDI”).
Regarding claim 7, OSHIMA in view of Thewes doesn’t explicitly teach the claim limitations.
However, ARDI teaches wherein the error detector is further configured to: identify a data collection device in the plurality of data collection devices (deficient sensor) corresponding to the error [Para. 36].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify OSHIMA in view of Thewes’s sensor based abnormal state detection by incorporating ARDI’s deficient sensor confidence tracking to enable targeted maintenance or data handling.
Regarding claim 8, OSHIMA in view of Thewes doesn’t explicitly teach the claim limitations.
However, ARDI teaches wherein the error detector is further configured to: send a signal to the identified data collection device to remediate the error [Para. 38].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify OSHIMA in view of Thewes’s sensor based abnormal state detection by incorporating ARDI’s deficient sensor confidence tracking to enable targeted maintenance or data handling.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over OSHIMA et al. (Pub. No. US 2023/0377313) in view of Thewes et al. (Pub. No. 2023/0325640) further in view Platt et al. (Pub. No. US 2025/0157570).
Regarding claim 10, OSHIMA in view of Thewes doesn’t explicitly teach the claim limitations.
However, Platt teaches having a plurality of mass spectrometry devices [Para. 6].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify OSHIMA in view of Thewes’s sensor based abnormal state detection by incorporating Platt’s deficient sensor confidence tracking to enable targeted maintenance or data handling.
Claims 11 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over OSHIMA et al. (Pub. No. US 2023/0377313) in view of Thewes et al. (Pub. No. 2023/0325640) further in view Bondarenko (Pub. No. US 2014/0156612 hereinafter “bond”) further in view of Li et al. (Pub. No. US 2016/0266141).
Regarding claim 11, OSHIMA in view of Thewes doesn’t explicitly teach wherein the properties include retention time, and intensity.
However, Bond teaches determine a plurality of properties (M/Z and RT grids) for the data, wherein the properties include retention time , and intensity [Para. 12, 20 and 21]; and convert the data into the unified format (one unifying format) based on the determined properties (M/Z and RT grids) [Para. 12, 20 and 21].
It would have been obvious to one of ordinary skill in the art before the effective filing data to modify OSHIMA in view of Thewes’s preprocessing/transformation pipeline by incorporating Bond’s teaching of converting data (raw LC/MS data) in different equipment formats into a unified format (one unifying format) to produce converted data (unified LC/MS image files), so that OSCHIMA’s image generation, CNN-classification, and anomaly detection stages operated on harmonized inputs rather than merely transformed time serios inputs. This medication improves OSCHIMA by making data from different equipment formats and operation system files, thereby reducing format driven incompatibility and improving downstream classification error detection.
OSHIMA in view of Thewes further in view of Bond doesn’t explicitly teach Molecular weight.
Li teaches having a molecular weight [Para. 73].
It would have been obvious to one ordinary skill in the art before the effective filing date to modify OSHCIMA in view of Thewes and Bond’s LC/MS data-property handling by incorporating Li’s teaching of determining molecular weight so that molecular weight is determined with retention time and intensity before unifying LC/MS data. This modification improves Bond by adding intact-mass characterization to the LC/MS feature set, thereby improving the analytical content of the unified image data.
Regarding claim 12, OSHIMA in view of Thewes doesn’t explicitly teach the claim limitations.
Bond teaches generating an image (LC/MS images) from the converted data (LC/MS images) based on the retention time (RT), the molecular weight, and the intensity (raw intensity) [Para. 23 “The method receives the specified RT range and M/Z range at block 2020” and “The method, at block 2022, prepares to calculate global M/Z and RT grids and subsequently creates LC/MS images by interpolating raw intensities into an intensity matrix with rows and columns corresponding to the global M/Z and RT grids”].
It would have been obvious to one of ordinary skill in the art before the effective filing data to modify OSHIMA in view of Thewes’s preprocessing/transformation pipeline by incorporating Bond’s teaching of converting data (raw LC/MS data) in different equipment formats into a unified format (one unifying format) to produce converted data (unified LC/MS image files), so that OSCHIMA’s image generation, CNN-classification, and anomaly detection stages operated on harmonized inputs rather than merely transformed time serios inputs. This medication improves OSCHIMA by making data from different equipment formats and operation system files, thereby reducing format driven incompatibility and improving downstream classification error detection.
However, OSHIMA in view of Thewes further in view of Bond doesn’t explicitly teach the molecular weight.
Li teaches having a molecular weight [Para. 73].
It would have been obvious to one ordinary skill in the art before the effective filing date to modify OSHIMA in view of Thewes further in view of Bond’s LC/MS data-property handling by incorporating Li’s teaching of determining molecular weight so that molecular weight is determined with retention time and intensity before unifying LC/MS data. This modification improves Bond by adding intact-mass characterization to the LC/MS feature set, thereby improving the analytical content of the unified image data.
Claim 13 are rejected under 35 U.S.C. 103 as being unpatentable over OSHIMA et al. (Pub. No. US 2023/0377313) in view of Thewes et al. (Pub. No. 2023/0325640) further in view CHANG et al. (Pub. No. US 2018/0137633).
Regarding claim 13, OSHIMA in view of Thewes doesn’t explicitly teach generating a feature map based on the image.
However, CHANG teaches generating a feature map based on the image [Para. 6, and 36].
It would have been obvious to one ordinary skill in the art before the effective filing date to modify OSHIMA in view of Thewes’s LC/MS data-property handling by incorporating CHANGE’s teaching of generating a feature map so that the modification improves Bond by adding intact-mass characterization to the LC/MS feature set, thereby improving the analytical content of the unified image data.
Claims 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Bondarenko (Pub. No. US 2014/0156612 hereinafter “bond”) in view of Platt et al. (Pub. No. US 2025/0157570) further view Li et al. (Pub. No. US 2016/0266141) and further view of Ryan et al. (Pub. No. US 2020/0387797).
Regarding claim 18, Bond teaches a method for harmonizing data from a spectrometry device; receiving the data from the spectrometry device [Para. 14].
However, Bond doesn’t explicitly teach a plurality of mass spectrometry devices.
Platt teaches having a plurality of mass spectrometry devices [Para. 6].
It would have been obvious to one ordinary skill in the art before the effective filing date to modify Bond’s LC/MS format unifying workflow by incorporating Platt’s teaching of receiving measurement from a plurality of mass spectrometry devices so that Bond’s format unifying hardware receives LC/MS data originating from multiple mass spectrometers. This medication improves Bond by extending the unified LC/MS image workflow to cross-instrument datasets, thereby improving throughput and consistency for multi-instrument mass-spectrometry experiments.
Bond teaches determining a plurality of properties for the data, wherein the properties include retention time, and intensity [Para. 12].
However, Bond in view of Platt doesn’t explicitly teach Molecular weight.
Li teaches having a molecular weight [Para. 73].
It would have been obvious to one ordinary skill in the art before the effective filing date to modify Bond in view of Platt’s LC/MS data-property handling by incorporating Li’s teaching of determining molecular weight so that molecular weight is determined with retention time and intensity before unifying LC/MS data. This modification improves Bond by adding intact-mass characterization to the LC/MS feature set, thereby improving the analytical content of the unified image data.
Bond also teaches converting, based on the determined properties, the data into a unified format (one unifying format), thereby generating converted data (LC/MS image) [Para. 20, and 21], and generating an image (LC/MS images) from the converted data (LC/MS images) based on the retention time (RT), the molecular weight, and the intensity (raw intensity) [Para. 23 “The method receives the specified RT range and M/Z range at block 2020” and “The method, at block 2022, prepares to calculate global M/Z and RT grids and subsequently creates LC/MS images by interpolating raw intensities into an intensity matrix with rows and columns corresponding to the global M/Z and RT grids”].
However, Bond in view of Platt doesn’t explicitly teach the molecular weight.
Li teaches having a molecular weight [Para. 73].
It would have been obvious to one ordinary skill in the art before the effective filing date to modify Bond in view of Platt’s LC/MS data-property handling by incorporating Li’s teaching of determining molecular weight so that molecular weight is determined with retention time and intensity before unifying LC/MS data. This modification improves Bond by adding intact-mass characterization to the LC/MS feature set, thereby improving the analytical content of the unified image data.
Bond view of Platt further in view of Li doesn’t explicitly each generating a classification for the image, wherein the classification identifies the image as belonging to a label and determining, based on the image and the classification, whether an error is likely present in the data.
However, Ryan teaches generating a classification for the image, wherein the classification identifies the image as belonging to a label (cluster label) [Para. 100 “The pattern detection online procedure can be summarized as follows: (1) upon receipt of a new time-series, obtain new two-dimensional window and pass it to the trained CNN, which provides the classification at its output.” and Para. 112 “The clustered images are used to train the DNN with images in each cluster being labelled by the cluster label”], and determining, based on the image and the classification, whether an error (anomaly) is likely present in the data (time-series data) [Para. 97 “For each matrix in the sequence, a figure of merit is found (e.g., probability that an anomaly or other pattern is present)”; Para. 172, and Para. 76].
It would have been obvious to one ordinary skill in the art before the effective filing date to modify Bond view of Platt further in view of Li’s LC/MS image processing workflow by incorporating Ryan’s teaching of generating a classification for images labelled by a label (cluster label) so that Bond’s LC/MS images are classified after generation. This medication improves bond by adding automated image-based categorization to the unified LC/MS image files, thereby enabling downstream decision logic to operate on classified LC/MS image data.
Regarding claim 19, Bond view of Platt further in view of Li further in view of Ryan teaches all claim limitations above. Furthermore, Ryan teaches determining stored information corresponding to the label [Para. 93];
comparing the image (matrix) with the stored information (model), thereby generating a comparison (figure of merit) [Para. 93, and 97];
determining, based on the comparison, whether outlier data (anomaly) is present in the image [Para. 97]; and
determining that the error is likely present in the data in response to a determination that the outlier data is present in the image [Para. 97].
Regarding claim 20, Bond view of Platt further in view of Li further in view of Ryan teaches all claim limitations above. Furthermore, Ryan teaches sending the image to a convolutional neural network (CNN) [Para. 100];
analyzing, using the CNN (two-dimensional CNN block 406), spatial relationships (rectangular bounding boxes) in the image [Para. 172]; and
determining whether the error is likely present in the data based on the spatial relationships [Para. 172].
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SOLOMON G BEZUAYEHU whose telephone number is (571)270-7452. The examiner can normally be reached on Monday-Friday 10 AM-7 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, O’Neal Mistry can be reached on 313-446-4912. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-0101 (IN USA OR CANADA) or 571-272-1000.
/SOLOMON G BEZUAYEHU/ Primary Examiner, Art Unit 2666
Prosecution Insights