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 .
Information Disclosure Statement
The information disclosure statement (IDS) was submitted on 07/03/2025. The submissions are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
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 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); 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 nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/process/file/efs/guidance/eTD-info-I.jsp.
1. Claim 1 is rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1 of US Patent No. US 12,377,290. Although the claims at issue are not identical, they are not patentably distinct from each other because of the rationale detailed below.
Application 19/259,945
US Patent No. US 12,377,290
Claim 1
Claim 1
1. A computer-implemented method for detecting and diagnosing a fault in a radiotherapy machine, the method comprising:
receiving machine data indicative of configuration and operation of a target radiotherapy machine component;
applying a trained deep learning model to the received machine data of the target radiotherapy machine component, the trained deep learning model
being trained to establish a relationship between (i) machine data collected from and indicative of configuration and operation of normal components and faulty components with distinct fault severity levels and (ii) fault information of the normal components and the faulty components; and
based on applying the trained deep learning model to the received machine data, detecting a fault of the target radiotherapy machine component and classifying the detected fault into one of a plurality of fault severity levels.
1. (Currently Amended) A computer-implemented method for detecting and diagnosing a fault in a radiotherapy machine, the method comprising:
receiving machine data indicative of configuration and operation of a component of a particular type in a target radiotherapy machine;
applying a trained deep learning model to the received machine data of the component in the target radiotherapy machine, the trained deep learning model being trained to establish a relationship between machine data collected from normal components and faulty components of the particular type in respective radiotherapy machines, and fault information, including fault presence or absence, and fault types, of the normal components and the faulty components;
based on applying the trained deep learning model to the received machine data of the component in the target radiotherapy machine, detecting and diagnosing a fault associated with the component in the target radiotherapy machine, wherein diagnosing the fault includes, in response to a detection of fault presence, classifying the detected fault into one of a plurality of pre- determined distinct fault types associated with the component; and
alerting a user of the detected and diagnosed fault and to initiate predictive maintenance of the target radiotherapy machine in accordance with the detected [[or]]and diagnosed fault.
Claim 2
Claim 2
2. The method of claim 1, further comprising:
constructing a training dataset using the machine data collected from the normal components and the faulty components with distinct fault severity levels; and
generating the trained deep learning model by training a deep learning model using the training dataset.
2. The method of claim 1, further comprising: receiving the machine data collected from the normal components and the faulty components with respectively identified faults, the machine data indicative of configuration and operation of respective components;
constructing a training dataset including a plurality of data sequences generated from the received machine data of the normal components and the faulty components; and training a deep learning model using the constructed training dataset to establish the trained deep learning model.
Claim 10
Claim 3
10. The method of claim 2, wherein the target radiotherapy machine component includes a dynamic leaf guide, DLG,
wherein the training dataset includes machine data collected from and indicative of configuration and operation of normal DLGs and faulty DLGs with
distinct fault severity levels.
3. The method of claim 2, wherein the component in the target radiotherapy machine includes a dynamic leaf guide (DLG), the normal components include normal DLGs, and the faulty components include faulty DLGs with respectively identified DLG faults, and wherein detecting and diagnosing the fault includes detecting and diagnosing a DLG fault in the target radiotherapy machine.
Claim 11
Claim 6
11. The method of claim 10, wherein the training dataset includes a plurality of data segments generated from a series of measurements of a DLG parameter over time from each of the normal DLGs and the faulty DLGs.
6. The method of claim 3, comprising generating the plurality of data sequences including a trend of DLG current measurements over time, the DLG current measured respectively from one or more DLGs at respective axes.
Claim 12
Claim 9
12. The method of claim 11, wherein the DLG parameter includes at least one of a DLG current or a DLG out-of-position event count during a specific time period.
9. The method of claim 8, wherein the DLG position metric includes a count of DLG out-of-position events occurred during a specific time period, and the DLG position trend includes one or more of: a trend of daily count of out-of-position events; or a trend of cumulative count of out-of-position events over a specified number of days.
In view of the foregoing, claim 1 are anticipated by claim 1 of US Patent No. US 12,377,290. In view of the foregoing, claim 2 is anticipated by claim 2 of US Patent No. US 12,377,290. In view of the foregoing, claim 10 is anticipated by claim 3 of US Patent No. US 12,377,290. In view of the foregoing, claim 11 is anticipated by claim 6 of US Patent No. US 12,377,290. In view of the foregoing, claim 12 is anticipated by claims 9 of US Patent No. US 12,377,290.
This is a nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Regarding Claim 15, it is dependent on claim 14 and has similar limitations as of claim 2 above. Therefore, it is rejected under the same rationale as of claim 2 above.
Regarding Claim 16, it is dependent on claim 15 and has similar limitations as of claim 3 above. Therefore, it is rejected under the same rationale as of claim 3 above.
Regarding Claim 19, it is dependent on claim 15 and has similar limitations as of claim 12 above. Therefore, it is rejected under the same rationale as of claim 12 above.
Regarding Claim 20, it is dependent on claim 14 and has similar limitations as of claim 13 above. Therefore, it is rejected under the same rationale as of claim 13 above.
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.
The current 35 USC 101 analysis is based on the current guidance (Federal Register vol. 79, No. 241. pp. 74618-74633). The analysis follows several steps. Step 1 determines whether the claim belongs to a valid statutory class. Step 2A prong 1 identifies whether an abstract idea is claimed. Step 2A prong 2 determines whether any abstract idea is integrated into a practical application. If the abstract idea is integrated into a practical application the claim is patent eligible under 35 USC 101. Last, step 2B determines whether the claims contain something significantly more than the abstract idea. In most cases the existence of a practical application predicates the existence of an additional element that is significantly more.
The 35 USC 101 analysis between each element of claims and its combination is presented in the table below
Claim number and elements
Judicial exception (Step 2A Prong one)
Practical application (Step 2A Prong two)/ Significantly more (Step 2B)
Claim 1
Step2A Prong one: Yes
Step 2A Prong two: No / Step 2B: No
A computer-implemented method for detecting and diagnosing a fault in a radiotherapy machine, the method comprising:
Step 1: Yes, statutory class
receiving machine data indicative of configuration and operation of a target radiotherapy machine component;
“receiving ~” is an insignificant pre-solution activity to collect routine data.
applying a trained deep learning model to the received machine data of the target radiotherapy machine component, the trained deep learning model being trained to establish a relationship between (i) machine data collected from and indicative of configuration and operation of normal components and faulty components with distinct fault severity levels and (ii) fault information of the normal components and the faulty components; and
Abstract idea
“applying ~” is an insignificant pre-solution activity to execute the deep learning model to perform a math process.
“a trained deep learning model” is a software/mathematical algorithm performed in a neural network.
“establish a relationship ~” is a math or mental process.
A radiotherapy machine is a high level of generality.
based on applying the trained deep learning model to the received machine data, detecting a fault of the target radiotherapy machine component and classifying the detected fault into one of a plurality of fault severity levels.
abstract idea
math/mental process
“detecting a fault …” is a math or mental process based on the established relationship.
“classifying the detected fault…” is a math/mental process based on the established relationship.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Claims 1-20 are directed to an abstract idea. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception as addressed below and presented in the above table.
Step 2A: Prong One
Regarding Claim 1, the limitations recited in Claim 1, as drafted, are processes that, under its broadest reasonable interpretation, cover performance of the limitation in the mathematical calculations and/or the mind, as presented in the above table. Nothing in the claim elements precludes the step from practically being performed in the mind and/or the mathematical calculations. For example, the limitations of “applying a trained deep learning model to the received machine data of the target radiotherapy machine component, the trained deep learning model being trained to establish a relationship between (i) machine data collected from and indicative of configuration and operation of normal components and faulty components with distinct fault severity levels and (ii) fault information of the normal components and the faulty components” in the context of this claim may encompass manually calculating or executing deep learning model with respect to the machine data (routine data) because the trained deep learning model is a software algorithm and/or a mathematical concept used for training data to thereby establish a relationship between the machine data and the fault information, where the process related to the established relationship is indicative of a result inferred by a math or metal process. The limitation of “based on applying the trained deep learning model to the received machine data, detecting a fault of the target radiotherapy machine component and classifying the detected fault into one of a plurality of fault severity levels” in the context of this claim is a mental process inferred based on the established relationship inferred by a math or mental process.
Step 2A: Prong Two
This judicial exception is abstract ideal itself and not integrated into a practical application. In particular, the specification details use of a generic computer or processor to perform the processes using a computer system to perform “applying a trained deep learning model to the received machine data of the target radiotherapy machine component, the trained deep learning model being trained to establish a relationship between (i) machine data collected from and indicative of configuration and operation of normal components and faulty components with distinct fault severity levels and (ii) fault information of the normal components and the faulty components”, and “based on applying the trained deep learning model to the received machine data, detecting a fault of the target radiotherapy machine component and classifying the detected fault into one of a plurality of fault severity levels”. The additional elements of a radiotherapy machine and a computer are merely recited as a high level of generality without descriptions of its specific structure/features to perform the claimed features for establishing the relationship, detecting the fault and classifying the detected fault into one of a plurality of fault severity levels. There is no showing of integration into a practical application such as an improvement to the functioning of a computer, or to any other technology or technical field, or use of a particular machine.
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The limitation of “receiving machine data indicative of configuration and operation of a component of a particular type in a target radiotherapy machine” is insignificant extra-solution activity necessary to perform the abstract idea (i.e., gather routine data). See MPEP 2106.05(g). As discussed above, with respect to integration of the abstract idea into a practical application, using a computer system to perform the processes of “receiving machine data indicative of configuration and operation of a component of a particular type in a target radiotherapy machine”, applying a trained deep learning model to the received machine data of the target radiotherapy machine component, the trained deep learning model being trained to establish a relationship between (i) machine data collected from and indicative of configuration and operation of normal components and faulty components with distinct fault severity levels and (ii) fault information of the normal components and the faulty components”, and “based on applying the trained deep learning model to the received machine data, detecting a fault of the target radiotherapy machine component and classifying the detected fault into one of a plurality of fault severity levels” amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept cannot provide statutory eligibility. Claim 1 is not patent eligible.
Regarding Claims 2-13, the limitations are further directed to an abstract idea, because the limitations are directed to performing a mathematical or mental process related to detecting and diagnosing the fault. For the reasons described above with respect to Claim 1, the judicial exceptions are not meaningfully integrated into a practical application, or amount to significantly more than the abstract idea.
Regarding Claim 14, it is a device type claim having similar limitations as of claim 1 above. Therefore, it is rejected under the same rationale as of claim 1 above. The additional elements of “a memory” and “a processor” are recited at a high-level of generality to perform a generic computer function related to a mental or mathematical process. Mere nominal recitation of a device or module related to a generic “computer system” does not take the claim out of the mathematical concepts and the mental process grouping. Thus, the claim recites an abstract idea.
Regarding Claims 15-20, they are depending on claim 15 and having similar limitations as of claim 2-13 above. The limitations of claims 16-19 are further directed to an abstract idea, as described in claims 2-13.
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 1-3, 9-16 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over NOMURA AKIHIRO (JP 5289346 B2, hereinafter referred to as “NOMURA”, cited in IDS filed 12/02/2021) in view of ZHANG et al. (CN 110215581 A, hereinafter referred to as “ZHANG”, cited in IDS filed 12/02/2021).
Regarding Claim 1, NOMURA teaches a computer-implemented method for detecting and diagnosing a fault in a radiotherapy machine (Fig. 1, a particle beam therapy system; a particle beam therapy system and a failure range diagnosis method for the particle beam therapy system), the method comprising:
receiving machine data (a leaf position signal) indicative of configuration and operation of a target radiotherapy machine (Para 0007, “a leaf position signal indicating the position of the driven leaf to the leaf control device”, teaches machine data (i.e., a least position signal) indicative of the driven leaf’s configuration (i.e., the position of the driven leaf of the multi-leaf collimator);
…. the trained deep learning model being trained to establish a relationship between (i) machine data collected from collected from and indicative of configuration and operation of normal components and faulty components with distinct fault severity levels (faulty diagnosis range) (Note that, under the broadest reasonable interpretation, paragraph 0022 of NOMURA teaches a respective fault severity level (faulty diagnosis range such as H or L waveform level shown in Fig. 4) which is classified by a failure range and allowable range to determine whether a leaf position is normal or faulty based on the waveform type (H or L) converted from the simulated signal) and (ii) fault information of the normal components and the faulty components (Para 0007, “a simulation signal output unit that generates a simulation signal indicating that the leaf position is normal”; Note that, under the reasonable interpretation, “the generated simulation signal” is indicative of the established relationship, which is generated by training the data (i.e., leaf position of the multi-leaf collimator; (Para 0007, “a simulation signal output unit that generates a simulation signal indicating that the leaf position is normal … A failure range diagnosis unit for diagnosing the range of a failure site which may cause an abnormality of the leaf position based on the position in the signal input / output in the device”; Note that, under the reasonable interpretation, according to diagnosing the range of abnormality of the leaf position, the leaf (component) of the multi-leaf collimator is diagnosed whether to be normal or faulty. Under this interpretation, “fault information of the normal components and the faulty components” is taught by para 0007 of Nomura.); and
based on applying the trained deep learning model to the received machine data, detecting a fault of the target radiotherapy machine component and classifying the detected fault into one of a plurality of fault severity levels (Para 0007, “detects the presence or absence of an abnormality in a leaf position based on the drive control signal and the leaf position signal …. A failure range diagnosis unit for diagnosing the range of a failure site which may cause an abnormality of the leaf position based on the position in the signal input / output in the device”; Para 0008, “detecting an abnormality in the position of the leaf” in English machine translation; Note that, under the reasonable interpretation, at least paragraphs 0007 and 0008 of NOMURA teaches detecting a fault (i.e., abnormality) associated with the component (i.e., the leaf of the multi-leaf collimator based on the machine data (i.e., a simulated signal related to the leaf position) of the leaf).
NOMURA fails to teaches the limitation related to processing the data using a deep learning model, i.e., “applying a trained deep learning model to the received machine data of the target radiotherapy machine component, the trained deep learning model being trained to establish a relationship between (i) machine data collected from and indicative of configuration and operation of normal components and faulty components with distinct fault severity levels and (ii) fault information of the normal components and the faulty components” and “based on applying the trained deep learning model to the received machine data, … and classifying the detected fault into one of a plurality of fault severity levels” . However, ZHANG teaches applying a trained deep learning model to the received machine data of the target radiotherapy machine component, the trained deep learning model (“the breathing support device hardware fault detection method provided by the invention, by selecting data of multiple respiratory support devices and collecting the multiple respiratory support devices, establishing the linear mapping relation, then establishing a neural network of deep learning by machine learning of the breathing support device, is capable of performing detection when the hardware with a sign has a fault, the detecting of the hardware fault” in page 3 of English machine translation), the trained deep learning model being trained to establish a relationship between (i) machine data collected from and indicative of configuration and operation of normal components and faulty components with distinct fault severity levels and (ii) fault information of the normal components and the faulty components (“data collecting the respiratory support device, comprising an actual pressure value P, the actual flow value F, the flow sensor AD value ADP, pressure sensor AD value ADF, and turbine rotating speed; suggested linear mapping relationship, the mapping of normal device result is 1, mapping the fault device … creating a deep learning of BP neural network, input layer is (P, F, ADP, ADF, R), middle layer with 1 layer, 5 node, the output layer is any one value between 0~1, at each node …. then stopping neural network, outputting the final was the training result of the neural network gradient descent” in pages 3-4 of English machine translation). Note that, under the reasonable interpretation, ZHANG teaches a deep learning model for processing the collected data to thereby establish a mapping relationship between a normal device and fault device by calculating values (i.e., collected machine data) of f(P,F,ADP,ADF R) to tell whether a fault is about to occur (i.e., fault information indicative of being normal and fault, and a plurality of fault severity levels), which teach classifying the detected fault int one of the a plurality of fault severity levels.
NOMURA and ZHANG are both considered to be analogous to the claimed invention because they are in the same field of detecting an abnormal leaf position in the particle beam therapy system and a hardware fault detection method for respiratory support device. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified NOMURA to incorporate the teachings of ZHANG by providing a deep learning model applied to machine data to establish a mapping relationship between a normal device and fault device by calculating values of f(P,F,ADP,ADF R) to tell whether a fault is about to occur, taught by ZHANG.
Regarding Claim 2, NOMURA teaches further comprising: constructing a training dataset using the machine data collected from the normal components and the faulty components with distinct fault severity levels (the range of a failure site) (Para 0007, “a simulation signal output unit that generates a simulation signal indicating that the leaf position is normal … A failure range diagnosis unit for diagnosing the range of a failure site which may cause an abnormality of the leaf position based on the position in the signal input / output in the device”; Note that, under the reasonable interpretation, the “simulating signal” teaches “training data set” generated from the machine data and be indicative of whether the leaf (component) of the multi-leaf collimator is diagnosed to be normal or faulty according to abnormality range of the leaf position.).
NOMURA fails to explicitly disclose generating the trained deep learning model by training a deep learning model using the training dataset. However, the limitation of “generating the trained deep learning model by training a deep learning model using the training dataset” is a similar limitation as of a part of claim 1 and taught by ZHANG at least pages 3-4 of English machine translation as set forth in claim 1. Examiner takes OFFICIAL NOTICE that the feature of “generating the trained deep learning model by training a deep learning model using the training dataset” is merely indicative or well known in the art at the effective filing date, where a deep learning model is trained using the training dataset as taught by ZHANG (US 20070005212 A1) (see at least pages 3-4 of English machine translation as set forth in claim 1), as “generating the trained deep learning model by training a deep learning model using the training dataset” itself is not critical to be distinctly result-effective features but may be selected by routine experimentation and/or a user’s interest/preference. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified NOMURA to incorporate the teachings of ZHANG by providing a deep learning model applied to the constructed training dataset to thereby establish the trained deep learning model, taught by ZHANG.
Regarding Claim 9, NOMURA fails to teaches, but ZHANG teaches wherein the fault indicator has a numerical or categorical value to represent the absence of fault or the fault severity level (ZHANG teaches weight coefficient corresponding a fault indicator, where the weight coefficient represent a sever level of each fault, “suggested linear mapping relationship, the mapping of normal device result is 1, mapping the fault device is 0; linear mapping formula is as follows: f (P, F, ADP, ADF, R) =w1 *P + w2 *F + w3 *ADP + w4 *ADF + w5 + b. weight coefficient, w1, w2, w3, w4, w5 corresponding to each parameter, b is the modified coefficient; creating a deep learning of BP neural network, input layer is (P, F, ADP, ADF, R), middle layer with 1 layer, 5 node, the output layer is any one value between 0~1, at each node, using the Sigmoid excitation function, the expression is: wherein, z=wX + b, w = (w1, w2, w3, w4, w5), X = (P, F, ADP, ADF, R), result of the excitation function is …, the method performing feedback for the neural network, and then correcting the coefficient w, until the overall error of the output result reaches the minimum, then stopping neural network, outputting the final was the training result of the neural network gradient descent.,” in pages 3-4 of English machine translation).
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified NOMURA to incorporate the teachings of ZHANG by providing operations for weight coefficient corresponding a fault indicator, where the weight coefficient represents a sever level of each fault, taught by ZHANG.
Regarding Claim 10, wherein the target radiotherapy machine component includes a dynamic leaf guide, DLG (NOMURA teaches the multi-leaf collimator (i.e., DLG) having multiple leaves (i.e., components), where NOMURA teaches detecting whether a leaf a multi-leaf collimator is normal or faulty according to the leaf position (i.e., received data) as addressed above in claim 1 (Fig. 1; Para 0007-0008; Para 0014, “a leaf device 5 constituting a multi-leaf collimator by a plurality of leaf units 5a, 5b,. A multi-leaf collimator is a parallel arrangement of multiple leaves”),
the limitation of wherein the training dataset includes machine data collected from and indicative of configuration and operation of normal DLGs and faulty DLGs with distinct fault severity levels is similar as of a part of claim 1 above. Therefore, it is rejected under the same rationale as of claim 1 above. The additional limitation of a dynamic leaf guide (DLG) is taught by NOMURA at the multi-leaf collimator (i.e., DLG) having multiple leaves (i.e., components) as addressed above.
Regarding Claim 11, wherein the training dataset includes a plurality of data segments generated from a series of measurements of a DLG parameter over time from each of the normal DLGs and the faulty DLGs (at least paragraphs 0021 and 0022 teach a series of measured leaf positions such as the measured high time or low time of the pulse waveform over time and further teach whether the events of the measured DLG position are within the allowable range to detect or diagnose a fault of each DLG position event (paragraph 0021, “the differential leaf position signal S .sub.P, when the drive control signal commanding the actual driving was for example S .sub.D m, differential leaf position output from the leaf portion 5m It is determined whether or not the High time and Low time are within the allowable range with respect to the pulse waveform converted from the signal S .sub.P m, that is, whether or not the above-described constant portion exists”).
Regarding Claim 12, wherein the DLG parameter includes at least one of a DLG current or a DLG out-of-position event count during a specific time period. Note that, under the broadest reasonable interpretation, claims 12 is indicative of whether the events of the measured DLG position are within the allowable range to detect or diagnose a fault of each DLG position event, which is taught by Para 0022, at least at paragraph 0021, (“the differential leaf position signal S .sub.P, when the drive control signal commanding the actual driving was for example S .sub.D m, differential leaf position output from the leaf portion 5m It is determined whether or not the High time and Low time are within the allowable range with respect to the pulse waveform converted from the signal S .sub.P m, that is, whether or not the above-described constant portion exists”).
Regarding Claim 13, NOMURA fails to teaches, but ZHANG teaches wherein the trained deep learning model is trained further to establish a relationship between (i) the machine data collected from and indicative of configuration and operation of normal components and faulty components with distinct fault severity levels and (ii) remaining useful life, RUL (the plurality of maintenance record), information of the normal components and the faulty components; and
the method further comprising, based on applying the trained deep learning model to the received machine data, predicting a RUL for the target radiotherapy machine component (“the corresponding data and maintenance records stored in the training result database, the plurality of maintenance record, ….” in page 3 of English machine translation; “the data and the corresponding result stored in training database. no matter whether the device determination accurately, then each increased by 20 after maintenance record” in page 5 of English machine translation). Note that, under the broadest reasonable interpretation, fault detection whether to determine a normal device or fault device is indicative of a process for a device maintenance related to a remaining useful life of the device, as taught by ZHANG at least in pages 3-5 of English machine translation.
It would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified NOMURA to incorporate the teachings of ZHANG by providing operations for training the deep learning model using a plurality of maintenance record such as a remaining useful life of a component, taught by ZHANG.
Regarding Claim 14, it is a device type claim having similar limitations as of claim 1 and 2 above. Therefore, it is rejected under the same rationale as of claim 1 above. The additional element of “a memory” is taught by “database” ZHANG, and the additional element of “a processor” is taught by the “leaf control device 1” and “a signal processing unit 4” in Fig. 1 of NOMURA.
Regarding Claim 15, it is dependent on claim 14 and has similar limitations as of claim 2 above. Therefore, it is rejected under the same rationale as of claim 2 above.
Regarding Claim 16, it is dependent on claim 15 and has similar limitations as of claim 3 above. Therefore, it is rejected under the same rationale as of claim 3 above.
Regarding Claim 19, it is dependent on claim 15 and has similar limitations as of claim 12 above. Therefore, it is rejected under the same rationale as of claim 12 above.
Regarding Claim 20, it is dependent on claim 14 and has similar limitations as of claim 13 above. Therefore, it is rejected under the same rationale as of claim 13 above.
Examiner Note
Claims 4-8 and 17-18 are rejected under 35 U.S.C. 101 as set forth in this Office action. No prior art rejection has been made because the prior art of record take alone or in combination fails to teach the following features:
Regarding claim 4, the prior art does not teach or suggest, in combination with the rest of the limitations of Claim 4,
" wherein the plurality of data segments are generated by applying a moving window to a time series of the machine data, wherein each of the plurality of data segments corresponds to a time window, and is assigned with the fault indicator based on a temporal location of the time window relative to one or more reference times".
Claim 17 having similar limitation as of claim 4 is taught or suggested by no prior art under the same rationale as of claim 4 above. Claims 5-8 and 18 are dependent on claim 4 or 17.
Citation of Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Hissoiny (US 20190175952 A1) teaches training a deep convolutional neural network model to provide a beam model for a radiation machine, such as to deliver a radiation treatment dose to a subject. A method can include determining a range of parameter values for at least one parameter of a beam model corresponding to the radiation machine, generating a plurality of sets of beam model parameter values, wherein one or more individual sets of beam model parameter values can include a parameter value selected from the determined range of parameter values.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BYUNG RO LEE whose telephone number is (571)272-3707. The examiner can normally be reached on Monday-Friday 8:30am-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, Lee Rodak can be reached on (571) 270-5628. The fax phone number for the organization where this application or proceeding is assigned is 571-273-2555.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/BYUNG RO LEE/Examiner, Art Unit 2858
/LEE E RODAK/Supervisory Patent Examiner, Art Unit 2858
Prosecution Insights