Prosecution Insights
Last updated: April 19, 2026
Application No. 18/408,555

Generation of Hardware Description Language (HDL) Code Using Machine Learning

Non-Final OA §103§112
Filed
Jan 09, 2024
Examiner
WANG, RONGFA PHILIP
Art Unit
2199
Tech Center
2100 — Computer Architecture & Software
Assignee
Primis Inc.
OA Round
1 (Non-Final)
85%
Grant Probability
Favorable
1-2
OA Rounds
2y 10m
To Grant
91%
With Interview

Examiner Intelligence

Grants 85% — above average
85%
Career Allow Rate
452 granted / 534 resolved
+29.6% vs TC avg
Moderate +7% lift
Without
With
+6.8%
Interview Lift
resolved cases with interview
Typical timeline
2y 10m
Avg Prosecution
19 currently pending
Career history
553
Total Applications
across all art units

Statute-Specific Performance

§101
13.7%
-26.3% vs TC avg
§103
34.5%
-5.5% vs TC avg
§102
19.4%
-20.6% vs TC avg
§112
25.8%
-14.2% vs TC avg
Black line = Tech Center average estimate • Based on career data from 534 resolved cases

Office Action

§103 §112
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 . Detail Action This office action is in response to the application filed on 1/9/2024. Claims 1-20 are pending. Claim Objections Claim 10 is objected to because of the following informalities: Claim 10 recites the limitation of “deep neural network neural work”. It appears “neural network” is duplicated. Appropriate correction is required. Claim Rejections - 35 USC § 112 The following is a quotation of 35 U.S.C. 112(b): (b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as failing to set forth the subject matter which the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the applicant regards as the invention. Independent claims 1, 11 and 16 recite the limitation of “HDL” which appears to be an acronym without particularly definition and therefore “HDL” can be interpreted as “High-Definition Language” and render the above claims indefinite. Dependent claims of the above independent claims inherit the limitation and deficiency of respective parent claims and are rejected for similar reason. Additionally, claim 5 recites acronym “VHSIC” and is rejected for similar reason. Claims 1-10 are rejected because claim 1 recites the limitation "the module generation request" in “the module generation request are input into the deep neural network;”. There is insufficient antecedent basis for this limitation in the claim. Dependent claims of claim 1 inherit the limitation and deficiency of claim 1 and are rejected for similar reason. Claim 5 are rejected because claim 5 recites the limitation "the HDL codes” There is insufficient antecedent basis for this limitation in the claim. 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) 1-5, 7-8, 11-14, and 16-17, 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ogilvie (US 2008/0066046 A1) in view of Wang et al. (CN 202111142407 A) and further in view of Turek et al. (US 2019/0325108 A1) Per claim 1, Ogilvie discloses receiving a request which includes a natural-language description for a high-level representation of computer hardware behavior;( [0065], discloses generating HDL code based on user input including parameters to define optimization goal [0014], discloses user input of desired processing latency corresponding to functions desired corresponding to natural language description as disclosed in Specification [0028]. Also see [0014]) generating code which includes HDL code for a module,(see above) generating a testbench for the code, wherein features of the code and the module generation request are input into the deep neural network; ([0129]-[0130] discloses generating testbench to verify functionality corresponding to features of the code using code simulation) executing a functional simulation of the code using the testbench; (see above, [0129-0130]) and sending the code to be presented when the function simulation passes tests of the testbench.([0130], discloses testbench verify if the outputs are correct. [0131], discloses generated HDL code as options and presented to user) Ogilvie does not, however Wang discloses Discloses using trained deep neural network to generation function codes from natural language. (see. abstract & pp. 3 discloses using deep neural network to generate code) Therefore, it would have been obvious to a person of ordinary skill before the effective filing date of the invention to incorporate the teachings of Wang into the teachings of Ogilvie to include the limitation disclosed by Wang. The modification would be obvious to one of ordinary skill in the art to want to improve code correctness using deep neural network as suggested by Wang(see Abstract) Ogilvie/Wang does not, however, Turek discloses Using deep neural network to a testbench ([0059][0060], using machine learning (neural network) for HDL generator, simulation and performance evaluation/test and Fig. 2,see 214 performance indicator improved, no, then reject, re-apply machine learning model) Therefore, it would have been obvious to a person of ordinary skill before the effective filing date of the invention to incorporate the teachings of Turek into the teachings of Ogilvie/Wang to include the limitation disclosed by Turek. The modification would be obvious to one of ordinary skill in the art to want to converge to a best configuration via repeated reconfiguration ([0105]) Per claim 2, the rejection of 1 is incorporated. Ogilvie/Wang /Turek discloses further comprising re-generating the module when the functional simulation fails, wherein the re-generation uses the deep neural network and the request as input to the deep neural network. (Turek, [0060], Fig. 2, machine learning and simulator to determine if performance indicator improved for rejection (fail) and going back to 208 for re-gen.) Per claim 3, the rejection of 1 is incorporated. Ogilvie/Wang /Turek discloses wherein sending the code and related HDL code further comprises sending the module to a user interface of a development environment using an API (application programming interface) call. (Ogilvie, [0130], discloses MATLAB corresponding to development environment and functions call corresponding to API call. ) Per claim 4, the rejection of 1 is incorporated. Ogilvie/Wang /Turek discloses wherein the features of the code include at least one of: a number of inputs, a number of outputs, functional keywords, hardware keywords, or memory keywords. (Ogilvie [0065], discloses define optimization goals, [0073-74] discloses latency corresponding to functional keywords) Per claim 5, the rejection of 1 is incorporated. Ogilvie/Wang /Turek discloses wherein in the HDL codes are in Verilog or VHSIC Hardware Description Language (VHDL). (Ogilvie [0065], discloses Verilog) Per claim 7, the rejection of 1 is incorporated. Ogilvie/Wang /Turek discloses further comprising writing diagnostic information to temporary files that are processed at the end of the simulation to create a list of issues identified within the code. (Turek, Fig. 2, 216, perform simulation, 218, performance indicators in database, 214/222, at the end of simulation determine if issues arise.) Per claim 8, the rejection of 1 is incorporated. Ogilvie/Wang /Turek discloses wherein the deep neural network is trained on a data set of synthesizable HDL code blocks. (Turek, [0073], discloses training data in database including configuration of parameters as part of HDL code.) Per claims 11-13, see rejections of claims 1-3. Per claim 14, 19, see rejection of claim 8. Per claims 16-17, see rejections of claims 1-2. Claim(s) 6 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ogilvie (US 2008/0066046 A1) in view of Wang et al. (CN 202111142407 A) and further in view of Turek et al. (US 2019/0325108 A1) and Nelson et al. (US 20080288234 A1) Per claim 6, the rejection of 1 is incorporated. Ogilvie/Wang /Turek does not, however, Nelson discloses wherein executing a functional simulation further comprises executing a syntactically correct testbench against the code. ([0075], discloses checking HDL code syntactic correctness.) Therefore, it would have been obvious to a person of ordinary skill before the effective filing date of the invention to incorporate the teachings of Nelson into the teachings of Ogilvie/Wang /Turek to include the limitation disclosed by Nelson. The modification would be obvious to one of ordinary skill in the art to want to ensure syntax corrected for further processing. Per claim 18, see rejection of claim 18. Claim(s) 9-10, 15 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ogilvie (US 2008/0066046 A1) in view of Wang et al. (CN 202111142407 A) and further in view of Turek et al. (US 2019/0325108 A1) and Willson et al. (US 20180143965 A1) Per claim 9, the rejection of 1 is incorporated. Ogilvie/Wang /Turek does not, however, Wilson discloses wherein the deep neural network is a language model. ([0021] discloses deep neural network as a language model) Therefore, it would have been obvious to a person of ordinary skill before the effective filing date of the invention to incorporate the teachings of Wilson into the teachings of Ogilvie/Wang /Turek to include the limitation disclosed by Wilson. The modification would be obvious to one of ordinary skill in the art to want to incorporate language model to process user input. Per claim 10, the rejection of claim 9 is incorporated. Ogilvie/Wang /Turek does not, however, Willson discloses wherein the deep neural network neural network that is a transformer, encoder-decoder transformer, a text-to-text transformer or a generative adversarial network (GAN) (Turek, [0051], disclose machine learning model perform transformation corresponding to function of a transformer.). Per claims 15 and 20, see rejection of claim 9. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. It is noted that any citation [[s]] to specific, pages, columns, lines, or figures in the prior art references and any interpretation of the references should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. [[See, MPEP 2123]] Any inquiry concerning this communication or earlier communications from the examiner should be directed to Philip Wang whose telephone number is 571-272-5934. The examiner can normally be reached on Monday – Friday 8:00AM -4:00PM. Any inquiry of general nature or relating to the status of this application should be directed to the TC2100 Group receptionist: 571-272-2100. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Lewis Bullock, can be reached at 571-272-3759. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. 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 http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). /PHILIP WANG/Primary Examiner, Art Unit 2199
Read full office action

Prosecution Timeline

Jan 09, 2024
Application Filed
Feb 26, 2026
Non-Final Rejection — §103, §112 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12596341
OPERATION LOOP FORMATION FOR ADAPTIVE POWER GRID MANAGEMENT
2y 5m to grant Granted Apr 07, 2026
Patent 12596622
VENDOR ONBOARDING AND PRE-DEPLOYMENT SERVICE TESTING
2y 5m to grant Granted Apr 07, 2026
Patent 12591503
DEBUGGING INSTRUCTION EXECUTION ERRORS IN A SIMULATED COMPUTER SYSTEM
2y 5m to grant Granted Mar 31, 2026
Patent 12579054
APPLICATION PROGRAMMING INTERFACE TEST METHOD AND APPARATUS
2y 5m to grant Granted Mar 17, 2026
Patent 12566689
METHOD AND SYSTEM FOR CALCULATION OF TEST AUTOMATION FEASIBILITY INDICES
2y 5m to grant Granted Mar 03, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
85%
Grant Probability
91%
With Interview (+6.8%)
2y 10m
Median Time to Grant
Low
PTA Risk
Based on 534 resolved cases by this examiner. Grant probability derived from career allow 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