Prosecution Insights
Last updated: November 04, 2026
Application No. 18/947,105

ALGORITHM EXECUTION OPTIMISATION

Final Rejection §102
Filed
Nov 14, 2024
Priority
Nov 14, 2023 — EU 23209785.7
Examiner
PATEL, HETUL B
Art Unit
3992
Tech Center
3900
Assignee
Klepsydra Technologies GmbH
OA Round
2 (Final)
63%
Grant Probability
Moderate
3-4
OA Rounds
1y 4m
Est. Remaining
66%
With Interview

Examiner Intelligence

Grants 63% of resolved cases
63%
Career Allowance Rate
133 granted / 211 resolved
+3.0% vs TC avg
Minimal +3% lift
Without
With
+3.0%
Interview Lift
resolved cases with interview
Typical timeline
3y 4m
Avg Prosecution
5 currently pending
Career history
218
Total Applications
across all art units

Statute-Specific Performance

§101
5.1%
-34.9% vs TC avg
§103
39.4%
-0.6% vs TC avg
§102
25.5%
-14.5% vs TC avg
§112
19.8%
-20.2% vs TC avg
Black line = Tech Center average estimate • Based on career data from 211 resolved cases

Office Action

§102
DETAILED ACTION This office action is in response to the claim amendment and remarks filed on August 7, 2026. Claims 1, 4, 7, 10, 12 and 14 are amended; and claims 3, 5-6 and 15 are cancelled. Claims 1-2, 4 and 7-14 are currently pending in this application. The examiner respectfully requests that support be shown for all the claim amendment(s) by specifically pointing to page(s) and line numbers in the specification and/or drawing figure(s). This will assist the examiner in prosecuting this application. All previously outstanding objections and/or rejections to the Applicant's disclosure and/or claims not contained in this office action have been respectfully withdrawn by the examiner hereto. Claim interpretation Claim 1 as currently presented is shown below. PNG media_image1.png 417 620 media_image1.png Greyscale PNG media_image2.png 206 612 media_image2.png Greyscale Based on the reasonings below, the patentable weight is given only to the highlighted limitations above. The claim language shown in the solid line boxes above is simply intended use/purpose and do not limit the scope of the claim. (“An intended use or purpose usually will not limit the scope of the claim because such statements usually do no more than define a context in which the invention operates.” Boehringer Ingelheim Vetmedica, Inc. v. Schering-Plough Corp., 320 F.3d 1339, 1345 (Fed. Cir. 2003)). The claim language shown in dotted line box above describes structural limitations of a computer system where the claimed method can be applied/ran. (“To be entitled to such [patentable] weight in method claims, the recited structural limitations therein must affect the method in a manipulative sense and not to amount to the mere claiming of a use of a particular structure . . . .” Ex Parte Pfeiffer, 135 USPQ 31, 33 (B.P.A.I. 1961)). The remaining limitations (i.e. which are not highlighted, not shown in dotted/solid line boxes) describe what the algorithm, the configuration file and the one or more ring buffers includes. Additionally, dependent claims 2, 4, 7, 11 and 13 are also considered non-limiting as they further limit the structure of the computer system recited in the non-limiting preamble of claim 1. Claim Rejections - 35 USC § 102 The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action: A person shall be entitled to a patent unless – (a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention. Claims 1-2, 4 and 7-14 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by IEEE publication “AI/ML Inference Engine Software for High-Reliability applications on Space Qualifiable Hardware”, hereinafter referred as “the IEEE publication” dated 10/2/2023 submitted by the applicant. As per claim 1, the IEEE publication teaches a method comprising: implementing an optimizer, wherein the optimizer: receives optimization criteria relating to the operation of the algorithm, wherein the optimization includes execution of at least two streams in parallel ("Adapting the Klepsydra Streaming Distribution (SDO) framework to efficiently distribute Al operations among the HPDP nodes. This adaptation will optimize the distribution of AI tasks across the co-processor, enabling parallel processing and maximizing performance"; See page 5, right-hand column); receives data relating to the running of the algorithm in the computing system according to a naïve configuration file ("Incorporate off-line inference optimization using Genetic Algorithms to cater to different optimization criteria, such as minimal CPU usage, minimal latency, and maximal data rate"; See page 4, left-hand column); and adjusts the naïve configuration file to output an optimized configuration file according to the optimization criteria ("The final result is a configuration file that, along with the ONNX model, enables the optimal execution of the Al model on the HPDP nodes"; See page 6, left-hand column). As per claim 8, the IEEE publication further teaches the optimizer adjusts the native configuration file using a genetic algorithm ("Using genetic algorithms, the SDO framework further optimizes the distribution and execution of the ONNX model within the Klepsydra Al + HPDP system. This optimization process aims to achieve the best possible performance based on the defined criteria"; See page 6, left-hand column). As per claim 9, the IEEE publication further teaches the algorithm of which the execution is to be accelerated is an AI algorithm ("developing an extension to accelerate Al algorithms via the HPDP co-processor"; See Abstract). As per claim 10, the IEEE publication further teaches the criteria comprise minimizing or maximizing any one or more of parameters selected from the configuration file, and the configuration file comprises any one or more of latency, power consumption, throughput, array processor memory usage and CPU usage ("The findings demonstrated substantial performance improvements, including increased data processing rates and power savings", "Algorithm pipelining has experienced a resurgence in high-performance computing due to its low power consumption and high throughput capabilities. The approach proposed in this paper introduces a sophisticated threading model that combines pipeline and parallelization techniques applied to deep neural networks (DNNs)"; See Abstract; page 2, left-hand column, section II.A Overview). As per claim 12, the IEEE publication further teaches the optimizer creates an optimal number of streams that will be executed in parallel, associates memory with the streams and determines an optimal number of ring buffers that will orchestrate the streams ("The Klepsydra Streaming Distribution (SDO) framework performs a series of dry runs to evaluate and optimize the execution of the Al model on the HPDP'; See page 6, left-hand column). As per claim 14, the IEEE publication further teaches the optimizer distributes operators of the algorithm to different HPDP nodes ("This involves adapting Klepsydra Alto utilize the HPDP as a co-processor and hardware backend accelerator. The support will include integration with the HPDP's unique capabilities, ensuring optimal utilization and performance. Adapting the Klepsydra Streaming Distribution (SDO) framework to efficiently distribute Al operations among the HPDP nodes"; See page 5, left-hand column). Dependent claims 2, 4, 7, 11 and 13 are considered non-limiting as they further limit the structure of the computer system recited in the non-limiting preamble of claim 1. Therefore, these claims are rejected for the same reasons as claim 1 above. Response to Arguments Applicant alleges that: There is no specific disclosure in the IEEE publication that the lock-free ring buffers are assigned to CPU cores and that the ring buffers are configured to retrieve memory and streams from the respective pools and output these to processing elements. While the IEEE publication may mention optimising the configuration file, it is silent on the specific method in which the configuration file is optimised. The IEEE publication fails to teach the skilled person how the configuration file is optimised. The IEEE publication merely states that "The final result is a configuration file that, along with the ONNX model, enables the optimal execution of the Al model on the HPDP nodes. This configuration file provides the necessary instructions and parameters to leverage the capabilities of the co-processor effectively". There is no teaching of how the lock-free ring buffers should be assigned to the CPU cores or that the lock-free ring buffers orchestrates the processing elements. Applicant's arguments filed 8/7/2026 have been fully considered but they are not persuasive. With respect to both a) and b), as indicated in the “Claim Interpretation” section above, the argued limitations of claim 1 are a part of the non-limiting preamble of claim 1. So these arguments are moot. Conclusion Claims 1-2, 4 and 7-14 are rejected. 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 Hetul Patel whose telephone number is (571)272-4184. The examiner can normally be reached M-F 9am-5pm. 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. 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. /Hetul Patel/ Supervisory Patent Examiner Art Unit 3992
Read full office action

Prosecution Timeline

Nov 14, 2024
Application Filed
Apr 07, 2026
Non-Final Rejection mailed — §102
Aug 07, 2026
Response Filed
Oct 23, 2026
Final Rejection mailed — §102 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12625970
PROVIDING BIOS FEATURES IN A PRE-BOOT ENVIRONMENT FOR A CLIENT COMPUTER SYSTEM
1y 8m to grant Granted May 12, 2026
Patent 8255618
PERFORMANCE ISOLATION IN A SHARED MEMORY DEVICE
10m to grant Granted Aug 28, 2012
Patent 8234473
METHOD AND APPARATUS FOR BACKUP AND RECOVERY USING STORAGE BASED JOURNALING
2y 0m to grant Granted Jul 31, 2012
Patent 8219754
NOVEL CONTEXT INSTRUCTION CACHE ARCHITECTURE FOR A DIGITAL SIGNAL PROCESSOR
1y 12m to grant Granted Jul 10, 2012
Patent 8214622
FACILITATING MANAGEMENT OF STORAGE OF A PAGEABLE MODE VIRTUAL ENVIRONMENT ABSENT INTERVENTION OF A HOST OF THE ENVIRONMENT
8y 1m to grant Granted Jul 03, 2012
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
63%
Grant Probability
66%
With Interview (+3.0%)
3y 4m (~1y 4m remaining)
Median Time to Grant
Moderate
PTA Risk
Based on 211 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month