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 .
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.
Claim(s) 1, 11, 13, 15, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bulut et al. (US 2020/0330046) (hereinafter Bulut) in view of Adari et al. (US Pat. 12,664,484) (hereinafter Adari).
Regarding claims 1, 15, and 18, Bulut teaches a computer-implemented method, system having one or more processors and storage media having instructions to perform the method (ph. [0078]), and a computer program product comprising a storage medium having instructions to perform the method for digital twin usage (ph. [0078]), the method comprising:
inputting a first digital twin and performance data of the first digital twin into a first machine learning model that performs neural network-based data clustering to produce a second digital twin, the first and second digital twins digitally representing a first physical entity, the second digital twin comprising one or more changes from the first digital twin (ph.[0053]-[0056], “The personalized parameter model may be generated as a mathematical function that is able to represent data, or as a data model such as a convolutional neural network trained on the data received in operation 103, by using regression analysis of the data received in operation 103 and so on…In case of the personalized parameter model based on a data driven approach, the connections between inputs and outputs are established using a convolutional neutral network or any other suitable supervised or unsupervised machine learning approach.. In a preferred embodiment, the data in the personalized parameter model is clustered into a plurality of distinct clusters or non-overlapping sub-ranges during the generation of the personalized parameter model…Upon generation of the personalized parameter model in operation 105, the method 100 proceeds to operation 107 in which the personalized parameter model is made available for updating the digital twin of the person 10.”);
analyzing performance data of the second digital twin (ph. [0057], “If it is decided in operation 205 that the parameter information contained within the personalized parameter model corresponds to the previously assumed parameter information, e.g. dynamic behaviour and/or transfer functions as previously explained, it may be concluded that the digital model of the person 10 is still up-to-date such that no further action is required and the method 200 may terminate in operation 213. On the other hand, if it is decided in operation 205 that there is a discrepancy between the parameter information contained within the personalized parameter model and the previously assumed parameter information, the method 200 proceeds to operation 207 in which the test protocols for obtaining the range of values for a parameter in a controlled test performed on the person 10 for which such a discrepancy has been determined is updated, such that the updates test or measurement procedure can capture the dynamic behaviour this parameter as indicated or predicted in the personalized parameter model.”).
Bulut does not explicitly teach in response to the analysis indicating a problem with the second digital twin, revoking implementation of the second digital twin and reimplementing the first digital twin. However, Adari teaches in response to the analysis indicating a problem with the second digital twin, revoking implementation of the second digital twin and reimplementing the first digital twin (col. 7 line 67 to col. 8, line 16, “In certain embodiments, when the accuracy rate for the second ML model 130 is higher than the accuracy rate for the first ML model 120, the accuracy rate of the second ML model 130 may be determined to be “above threshold”, as shown in FIG. 3. When the second ML model 130 accuracy is above the threshold, it may be an indication that the second ML model 130 has become more accurate in making predictions with the updates over the first ML model 120. Accordingly, second ML deployment module 340 may then implement deployment of the second ML model 130 to replace the first ML model 120 (similar to the deployment implemented by second ML deployment module 145, shown in FIG. 1). When the accuracy rate for the second ML model 130 is lower than the accuracy rate for the first ML model 120, the accuracy rate of the second ML model 130 may be determined to be “below threshold”, as shown in FIG. 3. When the second ML model 130 accuracy is below the threshold, it may be an indication that the second ML model 130 needs more refinement before it can be deployed and replace the first ML model 120. Accordingly, second ML reassessment module 350 may implement a refinement process for the second ML model 130.). One of ordinary skill in the art before the effective filing date would have been motivated to modify Bulut in the manner taught by Adari in order to have live shadow testing of updated models whereby the new model can be compared to the old model based on live real-time data.
Regarding claim 11, the Bulut/Adari combination teaches the method of claim 1. Bulut further teaches producing the performance data of the first digital twin via inputting of the first digital twin to a simulation program (ph. [0065], “In this embodiment, after updating the digital model, a simulation is run with the updated digital model 1 in operation 206. This simulation simulates the extended time period over which the sensor data captured in the personalized parameter model was acquired and generates simulated sensor data based on which a further personalized parameter model is generated in operation 208.”).
Regarding claim 13, the Bulut/Adari combination teaches the method of claim 1. Bulut further teaches the performance data of the digital twin includes at least one member selected from a group consisting of digital sensor readings, digital component data, and user feedback (ph. [0048], “The sensor data provided by the one or more sensors 12, 14, 16 to the computer system 20 hosting the digital twin through its processor arrangement 22 is used to update the digital twin such that the physiology of the patient 10 as monitored by the sensor data can be accurately simulated with the digital twin..”).
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over the Bulut/Adari combination as applied to claim 1 above, and further in view of Wyper et al. (US 2023/0214837) (hereinafter Wyper).
Regarding claim 9, the Bulut/Adari combination teaches the method of claim 1. The combination does not explicitly teach applying a clustering algorithm to the performance data of the first digital twin to identify clusters and outliers, wherein the clusters and not the outliers are input into the first machine learning model. However, Wyper teaches applying a clustering algorithm to the performance data of the first digital twin to identify clusters and outliers, wherein the clusters and not the outliers are input into the first machine learning model (ph. [0068], “During the outlier removal in historical training data, it is noted that historical training data, in this context, may be the historical customer data utilized to train the machine learning models 208. During the outlier removal in historical training data, the machine learning models 208 may remove outlier data present in such historical training data.”). One of ordinary skill in the art before the effective date would have been motivated to modify the Bulut/Adari combination in the manner taught by Wyper in order to improve the accuracy of the cluster groupings, e.g. prevent centroid distortion.
Allowable Subject Matter
Claims 2-8, 10, 12, 14, 16, 17, 19, and 20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Liu et al. (US 2023/0358640) teaches simulating autonomous vehicle testing environments using digital twins and neural network vehicle control.
Ambhore et al. (US 2024/0319687) teaches process optimization using integrated digital twins.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRIAN W WATHEN whose telephone number is (571)270-5570. The examiner can normally be reached M-F 9-5:30pm.
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, James Trujillo can be reached at 571-272-3677. 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.
BRIAN W. WATHEN
Primary Examiner
Art Unit 2151
/BRIAN W WATHEN/ Primary Examiner, Art Unit 2151
Prosecution Insights