General Electric Company

Patent Trials and Appeals Board

Jan 12, 2022

2020006508 (P.T.A.B. Jan. 12, 2022)

UNITED STATES PATENT AND TRADEMARK OFFICE UNITED STATES DEPARTMENT OF COMMERCE United States Patent and Trademark Office Address: COMMISSIONER FOR PATENTS P.O. Box 1450 Alexandria, Virginia 22313-1450 www.uspto.gov APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO. 15/594,779 05/15/2017 Masoud ABBASZADEH 318184_1 (G30.140) 8025 161135 7590 01/12/2022 GRC c/o BUCKLEY, MASCHOFF & TALWALKAR LLC 50 LOCUST AVENUE NEW CANAAN, CT 06840 EXAMINER SARKER, SANCHIT K ART UNIT PAPER NUMBER 2495 NOTIFICATION DATE DELIVERY MODE 01/12/2022 ELECTRONIC Please find below and/or attached an Office communication concerning this application or proceeding. The time period for reply, if any, is set in the attached communication. Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the following e-mail address(es): GRCLegal.mail@ge.com GRCdocketing@bmtpatent.com szpara@bmtpatent.com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE ____________ BEFORE THE PATENT TRIAL AND APPEAL BOARD ____________ Ex parte MASOUD ABBASZADEH and LALIT KESHAV MESTHA _____________ Appeal 2020-006508 Application 15/594,779 Technology Center 2400 ____________ Before JOHNNY A. KUMAR, JASON J. CHUNG, and JOHN A. EVANS, Administrative Patent Judges. KUMAR, Administrative Patent Judge. DECISION ON APPEAL Appellant1 appeals under 35 U.S.C. § 134(a) from a final rejection of claims 1-4, 6-8, 10-13, 15-17, and 19-21. The Examiner has indicated claims 5, 9, 14, and 18 contain allowable subject matter. Final Act. 11. We have jurisdiction over the pending claims under 35 U.S.C. § 6(b). We AFFIRM. 1 We use the word “Appellant” to refer to “applicant” as defined in 37 C.F.R. § 1.42(a) (2018). According to Appellant, the real party in interest is General Electric Company. See Appeal Br. 2. Appeal 2020-006508 Application 15/594,779 2 STATEMENT OF THE CASE 2 Introduction Appellant’s claimed invention relates generally to a system and method for forecasting anomalies in feature detection. See Spec., Abstr. Representative Independent Claims 1 and dependent claim 21 1. A method comprising: storing feature behavior information associated with data received from at least one monitoring node of an asset, the feature behavior information comprising a normalcy boundary identifying normal feature behavior and abnormal feature behavior for the at least one monitoring node in feature space; receiving input signals from the at least one monitoring node of the asset and transforming the input signals into feature values in the feature space; forecasting that a future value of a feature that is currently within the normalcy boundary is going to move outside the normalcy boundary based on the current values of the feature within the normalcy boundary; and outputting information concerning the forecasted future feature value moving outside the normalcy boundary for display. 21. The method of claim 1 wherein the outputting comprises outputting an early warning signal indicating that the future feature value is going to become an abnormal feature prior to a value of the feature crossing over the normalcy boundary. 2 We herein refer to the Final Office Action, mailed Oct. 30, 2019 (“Final Act.”); Appeal Brief, filed Apr. 2, 2020 (“Appeal Br.”); and the Examiner’s Answer, mailed July 13, 2020. (“Ans.”). Appeal 2020-006508 Application 15/594,779 3 Appeal Br. 19, 23 (Claims App.). Rejections and References Claims 1, 3, 4, 6-8, 10, 12, 13, 15-17, and 19-21 are rejected under 35 U.S.C. § 103 as being unpatentable over Baradaran (US 2017/0124478 A1, published May 4, 2017) and Tarassenko (US 2004/0148140 A1, published July 29, 2004). Claims 2 and 11 are rejected under 35 U.S.C. § 103 as being unpatentable over Baradaran, Tarassenko, and Segev (US 10,148,680 B1, published Dec. 4, 2018). ANALYSIS Based on Appellant’s arguments in the Brief, the principal and dispositive issue of whether the Examiner erred in rejecting exemplary claim 1 (and dependent claim 21) turns on whether the combination of Baradaran and Tarassenko teaches the claim limitations “forecasting that a future value of a feature that is currently within the normalcy boundary is going to move outside the normalcy boundary based on the current values of the feature within the normalcy boundary” (hereinafter “the disputed forecasting limitation”). Appeal Br. 11-15. Independent claims 10 and 19 recite similar subject matter. We adopt the findings of facts made by the Examiner in the Final Office Action and Examiner’s Answer as our own. We concur with the decision reached by the Examiner in the Examiner’s Answer for the specific reasons discussed below. We highlight the following for emphasis. Appeal 2020-006508 Application 15/594,779 4 Appellant contends Tarassenko does not teach the disputed forecasting limitation. Appeal Br. 11-15. In particular, Appellant contends that instead of forecasting, “the system of Tarassenko responds to readings of data values that have already travelled outside the range of normalcy.” Appeal Br. 14. The Examiner has identified the relevant portions of Tarassenko and has provided sufficient explanation with corresponding citations to various parts of the reference for disclosing the disputed automatically positioning limitation (Ans. 4, 5). In particular, the Examiner finds: Tarassenko teaches that it is possible to modify the apparatus to include an alarm which responds to data points being plotted outside a pre-defined region of “normality” in the visualisation space or off a predefined normal trajectory (prediction) corresponding to an expected change in patient condition. Further Tarassenko teaches a set of data points from a patient is used (after pre-clustering) to train the artificial neural network (the artificial neural network completely relies on predictions). Ans. 3. The alarm condition for the patient is preferably not triggered only by crossing the threshold, but by a combination of the time and extent to which the threshold is crossed. Therefore, Tarassenko teaches wherein the outputting comprises outputting an early warning signal indicating that the future feature value is going to become an abnormal feature prior to a value of the feature crossing over the normalcy boundary. Ans. 6. (emphasis added). In other words, the Examiner maps “forecasting” on trajectory in paragraph 51 of Tarassenko to suggest prediction along with the “combination of time and extent to which the threshold is crossed” disclosed in paragraph 65 of Tarassenko. Id. (citing Tarassenko ¶¶ 51, 65). Appeal 2020-006508 Application 15/594,779 5 As an initial matter of claim construction, we turn to the Specification for context, and find no explicit definition for the claim term “forecasting.” Claim 1 (emphasis added). Given the absence of a limiting definition in the claim or Specification regarding the disputed forecasting limitation, on this record, we are not persuaded the Examiner’s reading is overly broad, unreasonable, or inconsistent with the Specification.5 Based on our review of Tarassenko and consistent with the Examiner’s stated position (Ans. 3, 4, 6), we interpret the disputed forecasting limitation using the broadest reasonable interpretation consistent with Appellant’s disclosure - to be met by Tarassenko’s trajectory feature of the artificial neural network. See In re Morris, 127 F.3d 1048, 1054 (Fed. Cir. 1997). Regarding dependent claims 4, 6, 13, and 15 while Appellant raises additional arguments for patentability of the cited claims (Appeal Br. 15- 17), we find that the Examiner has responded in the Answer with sufficient evidence. Ans. 4-6. Therefore, we adopt the Examiner’s findings and underlying reasoning, which are incorporated herein by reference. We note that no Reply Brief is of record to rebut the Examiner’s responses to Appellant’s arguments. Therefore, in the absence of persuasive rebuttal evidence or argument to persuade us otherwise, we adopt the Examiner’s findings and underlying reasoning, which are incorporated herein by reference. 5 We emphasize that, because “applicants may amend claims to narrow their scope, a broad construction during prosecution creates no unfairness to the applicant or patentee.” In re ICON Health and Fitness, Inc., 496 F.3d 1374, 1379 (Fed. Cir. 2007). Appeal 2020-006508 Application 15/594,779 6 On this record, and based upon a preponderance of the evidence, we are not persuaded of error regarding the Examiner’s finding of obviousness regarding the rejection of independent representative claim 1. Therefore, we sustain the Examiner’s obviousness rejection of representative independent claim 1 and the rejection of grouped independent claims 10 and 19, which recite similar limitations of commensurate scope. The remaining grouped dependent claims fall with their respective independent claim. See 37 C.F.R. § 41.37(c)(1)(iv). CONCLUSION Appellant has not shown the Examiner erred with respect to the obviousness rejections of 1-4, 6-8, 10-13, 15-17, and 19-21, over the cited prior art of record, and we sustain the rejections. DECISION SUMMARY In summary: Claims Rejected 35 U.S.C. § Reference(s)/Basis Affirmed Reversed 1, 3, 4, 6- 8, 10, 12, 13, 15- 17, 19-21 103 Baradaran, Tarassenko 1, 3, 4, 6-8, 10, 12, 13, 15-17, 19- 21 2, 11 103 Baradaran, Tarassenko, Segev 2, 11 Overall Outcome 1-4, 6-8, 10-13, 15- 17, 19-21 Appeal 2020-006508 Application 15/594,779 7 FINALITY AND RESPONSE No time period for taking any subsequent action in connection with this appeal may be extended under 37 C.F.R. § 1.136(a)(1)(iv). See 37 C.F.R. § 41.50(f). AFFIRMED