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 .
Status of Claims
Claims 1-4 are pending in the application, with claims 1-4 having each been amended.
Response to Remarks
Rejections under 35 U.S.C. 101, 112
Examiner acknowledges the amendments to claims 1-4 overcoming all 101 and 112 rejections set forth in the previous office action.
Rejections under 35 U.S.C. 103
Applicant has amended claim 1 to include the limitation “wherein the trained model is configured to, in inferring the pulse origin, discriminate between a neutron, a non-neutron radiation and a pile-up phenomenon”. Applicant submits that Anshuman fails to disclose or suggest this limitation (Remarks, second page, last paragraph).
Examiner notes that Anshuman explicitly discloses at least a trained model configured to, in inferring the pulse origin, discriminate between a neutron and a non-neutron radiation phenomenon. See Anshuman, paragraph [0281], as cited by Applicant. Gamma radiation is a type of non-neutron radiation; the claim that the training model discriminates between a neutron and a non-neutron radiation does not by itself require that all possible types of non-neutron radiation be identifiable. Regardless, Anshuman discloses that the device is capable of identifying a wide variety of non-neutron radiation including alpha and beta particles, neutrinos, muons, etc. (Paragraphs [0101] and [0282]), even if only neutrons and gammas are counted.
Applicant submits that Anshuman does not disclose or suggest determining pile-up phenomena (Remarks, third page, second paragraph; fifth page, last paragraph). Examiner respectfully disagrees. While Anshuman does not explicitly disclose this, it is considered obvious over Anshuman, as detailed in the new 103 rejections below.
Applicant submits that Anshuman does not teach or suggest using an ionization chamber or proportional counter as a detector rather than a PIN diode, as the device of Anshuman is only configured to operate with a PIN diode, and the neural network of Anshuman is therefore trained on an entirely different type of data (Remarks, pages 4-5). Moreover, applicant argues that the problem of determining erroneous neutron counts from pileup phenomena is associated with the claimed ionization chamber or proportional counter detectors; therefore, the PIN diode setup of Anshuman is not conducive to the motivation of identifying these phenomena (Remarks, page 5, last paragraph).
Examiner respectfully disagrees. Similar to the present application, the detector of Anshuman (PIN diode) outputs voltage vs. time data which is input into the machine learning models of Anshuman for processing and identification. See Anshuman Fig. 24A and paragraphs [0282-4]. Therefore, the detector of Anshuman is susceptible to the same problem of erroneous neutron detection due to pileup, and the data interchangeably subjectable to the machine learning model of Anshuman or the model of the present application. Therefore, the corresponding argument set forth in the 103 rejections of the previous office action are maintained in the present 103 rejections.
Moreover, Anshuman applies machine learning to an entirely different type of detector outputting a different type of data (a CMOS detector outputting images in two spatial dimensions. See Fig. 24B and paragraph [0284] onwards). The issue of pileup is present for this type of detector as well (paragraph [0286]). Therefore, the claimed idea of using machine learning to identify different radiation pulse origins, and the motivation to account for pileup, are not exclusive to detectors outputting voltage vs. time data.
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 and 2 are rejected under 35 U.S.C. 103 as being unpatentable over Anshuman (US 20190244056 A1).
Regarding claim 1, Anshuman teaches a learning device configured to obtain a trained model for inferring a pulse origin which is an origin of a pulse signal in a neutron measurement device configured to perform a pulse measurement method, the learning device comprising:
a training data acquisition circuitry configured to acquire training data (Paragraph [0280]) including the pulse signal outputted from a detector (Paragraphs [0280-1]);
a model generation circuitry configured to generate, based on the training data, the trained model for inferring the pulse origin from the pulse signal outputted from the detector (Paragraph [0280]),
wherein the trained model is configured to, in inferring the pulse origin, discriminate between a neutron and a non-neutron radiation (Paragraph [0281]).
Anshuman does not teach the detector being an ionization chamber or a proportional counter.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply a known technique (using an ionization chamber or a proportional counter for detecting radiation and outputting a pulse signal) to a known method ready for improvement (the method of Anshuman for training and generating a neutron detection model) to yield predictable results (acquiring pulse signal training data from an ionization chamber or proportional counter and generating an inference model based on the training data for determining whether a pulse signal is from a neutron source or a gamma ray; with the benefit of using an ionization chamber or proportional counter being that they provide more information about the shape of the pulse useful for discrimination between pulse origins). See KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398, 415-421, 82 USPQ2d 1385, 1395-97 (2007).
Anshuman does not explicitly teach the trained model being configured to, in inferring the pulse origin, discriminate pile-up phenomena among the neutron and non-neutron radiation. However, the issue of pileup is well-known, as for example in paragraph [0286] of Anshuman. One of ordinary skill would therefore be motivated to reduce or identify and account for pileup phenomena. As machine learning has been applied in Anshuman to classifying the origins of various types of pulses, one of ordinary skill in the art could add a classification category for pile-up phenomena.
Regarding claim 2, Anshuman teaches
the training data acquisition circuitry being further configured to acquire the training data including time information which is a time at which the training data acquisition circuitry has acquired the pulse signal outputted from the detector (Paragraph [0283]: signal dependent on amplitude and time), and
the model generation circuitry is further configured to generate, based on the training data, the trained model for inferring the pulse origin from the pulse signal and the time information (Paragraph [0283]).
Claims 3 and 4 are rejected under 35 U.S.C. 103 as being unpatentable over Anshuman.
Regarding claim 3, Anshuman teaches a neutron measurement device configured to perform a pulse measurement method, the neutron measurement device comprising:
a detector (Paragraph [0280]);
a detection data acquisition circuitry configured to acquire a pulse signal outputted from the detector (Paragraph [0278] implies a data acquisition circuitry);
an inference circuitry configured to:
infer with a trained model, from the pulse signal, a pulse origin which is an origin of the pulse signal, wherein the trained model is configured to, in inferring the pulse origin, discriminate between a neutron and a non-neutron radiation (Paragraph [0279]), and
output the pulse origin on the basis of a pulse signal acquired by the detection data acquisition circuitry (Paragraph [0279]); and
a counting device which outputs a count of pulse signals of which the pulse origins are the neutron (Paragraph [0281]).
Anshuman does not teach the detector being an ionization chamber or proportional counter. Anshuman does not teach the trained model being configured to, in inferring the pulse origin, discriminate between a neutron, a non-neutron radiation, and a pile-up phenomenon. These limitations are both considered obvious according to the same rationale as set forth in the above rejection of claim 1.
Regarding claim 4, Anshuman teaches
the detection data acquisition circuitry being further configured to acquire an acquisition time which is a time at which the detection data acquisition circuitry has acquired the pulse signal outputted from the detector (Paragraph [0283]),
the inference circuitry is further configured to output, with a trained model for inferring the pulse origin from the pulse signal and the acquisition time, the pulse origin on the basis of the pulse signal and an acquisition time acquired by the detection data acquisition circuitry (Paragraph [0279]), and
the counting device is further configured to output a count of pulse signals of which the origins are the neutron (Paragraph [0281]).
Anshuman does not teach the counting device being configured to output a count of pulse signals of which the origins are the pile-up phenomenon including a neutron. This limitation is considered obvious according to the same rationale as set forth in the above rejection of claim 1. As identifying the pile-up phenomena is considered obvious, configuring the counting device to count them is obvious and within the ability of one of ordinary skill in the art.
Conclusion
Applicant’s amendment necessitated the new grounds of rejection presented in this office action. Accordingly, THIS ACTION IS MADE FINAL. 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 WILLIAM L TAYLOR whose telephone number is (571)272-8389. The examiner can normally be reached Mon-Fri, 8am-4pm.
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, David Makiya can be reached at (571) 272-2273. 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.
/WILLIAM LAURENCE TAYLOR/Examiner, Art Unit 2884
/DAVID J MAKIYA/Supervisory Patent Examiner, Art Unit 2884
Prosecution Insights