CONTROL METHOD AND SYSTEM BASED ON LAYER-WISE ADAPTIVE CHANNEL PRUNING

DETAILED ACTION This Office Action is in response to the RCE filed on 06/09/2026. Claims 1, 10, and 19 are currently amended. Claims 1-20 are currently pending in this application and have been examined. 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 . Response to Arguments In reference to Applicant’s arguments on page(s) 11-16 regarding rejections made under 35 U.S.C. 101: In the rejection, the Office Action alleges independent claim 1 recites features that can be categorized as a mental process. Even if it is assumed that certain limitations of claim 1 could be characterized as mental processes, which is not conceded, the claim as a whole must be evaluated at Step 2A Prong Two. Applicant respectfully submits that the claim, when considered as a whole, integrates any alleged abstract idea into a practical application by providing an improvement to deep-learning model computation acceleration technology. Paragraph [0014] of the specification describes a related technique that focuses on "minimizing decrease in accuracy, and performs control based on only how many of all of parameters is reduced." Paragraph [0015] of the specification further explains that "in terms of acceleration of computation, even when the decrease in accuracy may occur by a certain amount, removing a channel with a large computation amount reduction effect may be ultimately more advantageous in terms of accuracy than removing a large number of channels with a small acceleration effect in order to minimize the decrease in accuracy." Additionally, paragraph [0016] of the specification notes that "the computation amount and memory occupancy characteristics vary in a layer-wise manner" and that "acceleration of computation may be achieved via reduction of a computation amount through the channel pruning, and an allocable batch size may be increased via reduction of a resource memory occupancy amount of the model." Thus, the specification describes a technical problem and a technical improvement. Page 11 of the Office Action also alleges "employing the channel-pruned model in the deep-learning model computation acceleration" amounts to "mere instructions to apply the exception using a generic computer component (deep learning model)." Applicant respectfully disagrees. First, Applicant respectfully notes the deep learning model is not a "generic computer component." Rather, the employed deep learning model is a channel-pruned model that has undergone specifically recited channel pruning operations. Applicant respectfully submits that the analysis in the Office Action improperly evaluated each additional element in isolation rather than considering the ordered combination. When viewed as a whole, the claims describe a specific technical process for optimizing deep- learning model inference on accelerator hardware that produces a concrete result: increased throughput on the accelerator resource. Paragraph [0110] of the specification confirms this technical improvement: "the method according to the present disclosure may increase the available batch size in the individual resource, for example, the accelerator to increase throughput thereof, and may achieve the effect of accelerating the deep-learning model inference computation, thereby satisfying the processing latency at the service demand level." Accordingly, amended claim 1 integrates any possible judicial exception into a practical application, and accordingly is patent eligible under Prong Two of the revised Step 2A of the Alice test. Examiner’s response: Applicant’s arguments have been fully considered but are found to be not persuasive. Applicant argues that the instant application provides an improvement to the state of the art of deep-learning model computation acceleration technology. Examiner disagrees. By Applicant’s own specification, the relied upon improvement merely stems from the fact that less data is being processed which leads to an increase in computational acceleration and a minimized decrease in model accuracy. Applicant states in [0016] that "the computation amount and memory occupancy characteristics vary in a layer-wise manner" and that "acceleration of computation may be achieved via reduction of a computation amount through the channel pruning, and an allocable batch size may be increased via reduction of a resource memory occupancy amount of the model." It is explicitly stated in the specification that the acceleration of computation results from a reduction of computation amount. This is not a technological improvement simply because it is obvious to one skilled in the art that a reduced amount of data to be processed necessarily results in a faster computation. Applicant argues that the use of the channel pruned deep learning model is not simply a generic computer component. Examiner disagrees. There is no information in the claims that would indicate that the deep learning model is unique in its structure or execution. That the generic model is then pruned in a channel wise manner does not change the fact that the model itself is still a generic model for all intents and purposes. The pruning does not affect the model insofar as to change its purpose or operation it just prunes the model to allow for a certain accuracy level to be maintained. Applicant argues that the alleged judicial exceptions are integrated into a practical application because they provide a technological improvement. Examiner disagrees. The technological improvement, as stated above, relies on the fact that less data is processed and therefore the model becomes more accurate and the computation amount is increased. This is not a practical application nor is it a technological improvement because a technological improvement cannot arise from an abstract idea, in this case removing data to be processed or removing channels for data to be processed on. In light of the amendments made on the claims, the rejections made under 35 U.S.C. 101 are maintained and updated below. Claim Rejections - 35 USC § 101 The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action. Claims 1-20 rejected under 35 U.S.C. 101 because they are directed to an abstract idea without significantly more. Step 1 analysis: Independent claim 1 recites, in part, a control method, therefore falling into the statutory category of process. Independent claim 10 recites, in part, a control system, therefore falling into the statutory category of manufacture. Independent claim 19 recites, in part, a non-transitory computer-readable recording medium storing therein a program for performing a control method, therefore falling into the statutory category of machine. Regarding Claim 1: Step 2A: Prong 1 analysis: Claim 1 recites in part: “profiling an accuracy pattern curve to obtain a layer-wise pruning sensitivity of an original deep-learning model”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses checking the viability of a pruning method for a deep learning model. “comparing an influence of a resource memory occupancy reduction on a throughput of an accelerator resource with an influence of a computation amount reduction on the throughput of the accelerator resource”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses comparing the results of two different methods of increased throughput on a processor. “determining, based on a result of the comparing, whether to perform channel pruning based on a model layer-wise resource memory occupancy characteristic of the original deep- learning model or based on a model layer-wise computation amount characteristic of the original deep-learning model”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses deciding which technique to use based on the results of comparing two different methods of increased throughput on a processor. Accordingly, at Step 2A: Prong 1, the claim is directed to an abstract idea. Step 2A: Prong 2 analysis: The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of: “performing, based on a result of the determining, the channel pruning based on the model layer-wise resource memory occupancy characteristic of the original deep-learning model to obtain a channel-pruned model or based on the model layer-wise computation amount characteristic of the original deep-learning model to obtain the channel-pruned model”. This additional element is directed to a particular field of use (channel pruning). “in response to the channel-pruned model satisfying a certain model analysis accuracy level, determining a batch size for the accelerator resource”. This additional element is directed to a particular field of use (batch processing). “in response to a throughput of the channel-pruned model based on the determined batch size being greater than a throughput of the original deep-learning model, allocating the channel- pruned model to the accelerator resource and employing the channel-pruned model in the deep- learning model computation acceleration, and processing, by the accelerator resource, inference requests from a plurality of service users at the determined batch size using the channel-pruned model”. This additional element is recited at a high level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (deep learning model acceleration resource) (See MPEP 2106.05(f)). Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. The additional element(s) of “performing, based on a result of the determining, the channel pruning based on the model layer-wise resource memory occupancy characteristic of the original deep-learning model to obtain a channel-pruned model or based on the model layer-wise computation amount characteristic of the original deep-learning model to obtain the channel-pruned model” is/are directed to a particular field of use (channel pruning and batch processing) (MPEP 2106.05(h)) and therefore does not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible. As discussed above, the additional element(s) of “in response to a throughput of the channel-pruned model based on the determined batch size being greater than a throughput of the original deep-learning model, allocating the channel- pruned model to the accelerator resource and employing the channel-pruned model in the deep- learning model computation acceleration, and processing, by the accelerator resource, inference requests from a plurality of service users at the determined batch size using the channel-pruned model” is/are recited at a high-level of generality such that it/they amount(s) to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)). Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception. Regarding Claim 2: Step 2A: Prong 2 analysis: The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of: “based on the influence of the resource memory occupancy reduction being greater than the influence of the computation amount reduction, determining to perform the channel pruning based on the model layer-wise resource memory occupancy characteristic”. This additional element is directed to a particular field of use (channel pruning). “or based on the influence of the resource memory occupancy reduction being not greater than the influence of the computation amount reduction, determining to perform the channel pruning based on the model layer-wise computation amount characteristic”. This additional element is directed to a particular field of use (channel pruning). Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. The additional element(s) of “based on the influence of the resource memory occupancy reduction being greater than the influence of the computation amount reduction, determining to perform the channel pruning based on the model layer-wise resource memory occupancy characteristic” and “or based on the influence of the resource memory occupancy reduction being not greater than the influence of the computation amount reduction, determining to perform the channel pruning based on the model layer-wise computation amount characteristic” is/are directed to a particular field of use (channel pruning) (MPEP 2106.05(h)) and therefore does not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible. Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception. Regarding Claim 3: Step 2A: Prong 1 analysis: Claim 3 recites in part: “setting a reference value to an initial value”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses initializing a value. “deriving a layer-wise pruning level satisfying a specific condition”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses creating a pruning condition. “based on the derived layer-wise pruning level satisfying an available batch size increase condition, deriving a final pruning policy, wherein the available batch size increase condition is a condition to increase an available batch size increase level via the resource memory occupancy reduction by a target value”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses creating a pruning policy based on a processing increase condition. Accordingly, at Step 2A: Prong 1, the claim is directed to an abstract idea. Step 2A: Prong 2 analysis: The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of: “performing the channel pruning based on the model layer-wise resource memory occupancy characteristic under the final pruning policy”. This additional element is directed to a particular field of use (channel pruning). Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. The additional element(s) of “performing the channel pruning based on the model layer-wise resource memory occupancy characteristic under the final pruning policy” is/are directed to a particular field of use (channel pruning) (MPEP 2106.05(h)) and therefore does not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible. Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception. Regarding Claim 4: Step 2A: Prong 1 analysis: Claim 4 recites in part: “based on the derived layer-wise pruning level not satisfying the available batch size increase condition, increasing the reference value and performing the deriving based on the increased reference value”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses creating a pruning policy based on a new reference value. Accordingly, at Step 2A: Prong 1, the claim is directed to an abstract idea. Step 2A: Prong 2 analysis: The claim does not recite any additional elements that integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. Regarding Claim 5: Step 2A: Prong 1 analysis: Claim 5 recites in part: “setting a reference value to an initial value”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses initializing a value. “deriving a layer-wise pruning level satisfying a specific condition”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses creating a pruning condition. “based on the derived layer-wise pruning level satisfying a model inference computation acceleration condition, deriving a final pruning policy, wherein the model inference computation acceleration condition is a condition to increase a model inference computation latency acceleration level via the computation amount reduction by a target value”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses creating a pruning policy based on a processing increase condition. Accordingly, at Step 2A: Prong 1, the claim is directed to an abstract idea. Step 2A: Prong 2 analysis: The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of: “performing the channel pruning based on the model layer-wise computation amount characteristic under the final pruning policy”. This additional element is directed to a particular field of use (channel pruning). Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. The additional element(s) of “performing the channel pruning based on the model layer-wise resource memory occupancy characteristic under the final pruning policy” is/are directed to a particular field of use (channel pruning) (MPEP 2106.05(h)) and therefore does not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible. Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception. Regarding Claim 6: Step 2A: Prong 1 analysis: Claim 6 recites in part: “based on the derived layer-wise pruning level not satisfying the model inference computation acceleration condition, increasing the reference value and deriving the layer-wise pruning level based on the increased reference value”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses creating a pruning policy based on a new reference value. Accordingly, at Step 2A: Prong 1, the claim is directed to an abstract idea. Step 2A: Prong 2 analysis: The claim does not recite any additional elements that integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. Regarding Claim 7: Step 2A: Prong 2 analysis: The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of: “performing an additional training on the channel-pruned model”. This additional elements is recited at a high level of generality such that the claim recites only the idea of a solution or outcome (training a model) i.e., the claim fails to recite details of how a solution to a problem is accomplished. Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional element(s) of “performing an additional training on the channel-pruned model” is/are recited at a high-level of generality such that the claim recites only the idea of a solution or outcome (training a model) i.e., the claim fails to recite details of how a solution to a problem is accomplished (See MPEP 2106.05(f)). Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception. Regarding Claim 8: Step 2A: Prong 1 analysis: Claim 8 recites in part: “based on the channel-pruned model not satisfying the certain model analysis accuracy level, decreasing a reduction amount in the resource memory occupancy reduction or in the computation amount reduction”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses creating a pruning policy based on a new reference value. Accordingly, at Step 2A: Prong 1, the claim is directed to an abstract idea. Step 2A: Prong 2 analysis: The claim does not recite any additional elements that integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. Regarding Claim 9: Step 2A: Prong 1 analysis: Claim 9 recites in part: “in response to the throughput of the channel-pruned model based on the determined batch size being not greater than the throughput of the original deep-learning model, increasing a reduction amount in the resource memory occupancy reduction or in the computation amount reduction”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, this limitation encompasses creating a pruning policy based on a new reference value. Accordingly, at Step 2A: Prong 1, the claim is directed to an abstract idea. Step 2A: Prong 2 analysis: The claim does not recite any additional elements that integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. Regarding Claim 10: Due to claim language similar to that of claim 1, claim 10 is rejected for the same reasons as presented above in the rejection of claim 1, with the exception of the limitation(s) covered below. Step 2A: Prong 2 analysis: The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of: “at least one processor”. This additional element is recited at a high level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (a processor) (See MPEP 2106.05(f)). “at least one memory configured to store instructions therein”. This additional element is recited at a high level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (a memory) (See MPEP 2106.05(f)). Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application. Step 2B analysis: In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional element(s) of “at least one processor” and “at least one memory configured to store instructions therein” is/are recited at a high-level of generality such that it/they amount(s) to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)). Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception. Regarding Claim 11: Due to claim language similar to that of claim 2, claim 11 is rejected for the same reasons as presented above in the rejection of claim 2. Regarding Claim 12: Due to claim language similar to that of claim 3, claim 12 is rejected for the same reasons as presented above in the rejection of claim 3. Regarding Claim 13: Due to claim language similar to that of claim 4, claim 13 is rejected for the same reasons as presented above in the rejection of claim 4. Regarding Claim 14: Due to claim language similar to that of claim 5, claim 14 is rejected for the same reasons as presented above in the rejection of claim 5. Regarding Claim 15: Due to claim language similar to that of claim 6, claim 15 is rejected for the same reasons as presented above in the rejection of claim 6. Regarding Claim 16: Due to claim language similar to that of claim 7, claim 16 is rejected for the same reasons as presented above in the rejection of claim 7. Regarding Claim 17: Due to claim language similar to that of claim 8, claim 17 is rejected for the same reasons as presented above in the rejection of claim 8. Regarding Claim 18: Due to claim language similar to that of claim 9, claim 18 is rejected for the same reasons as presented above in the rejection of claim 9. Regarding Claim 19: Due to claim language similar to that of claims 1 and 10, claim 19 is rejected for the same reasons as presented above in the rejection of claims 1 and 10. Regarding Claim 20: Due to claim language similar to that of claims 8, 9, 17, and 18, claim 20 is rejected for the same reasons as presented above in the rejection of claims 8, 9, 17, and 18. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. S. Lym, E. Choukse, S. Zangeneh, W. Wen, S. Sanghavi and M. Erez, "PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration,"SC19: International Conference for High Performance Computing, Networking, Storage and Analysis, Denver, CO, USA, 2019, pp. 1-13. – PruneTrain, a cost-efficient mechanism that gradually reduces the training cost during training S. V. Naik et al., "Survey on Comparative Study of Pruning Mechanism on MobileNetV3 Model," 2021 International Conference on Intelligent Technologies (CONIT), Hubli, India, 2021, pp. 1-8, doi: 10.1 109/CONIT51480.2021.9498400. – we have summarized the recent works done on optimization of DNNs using various pruning techniques and their comparisons Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H.P. (2016). Pruning Filters for Efficient ConvNets. ArXiv, abs/1608.08710. – an acceleration method for CNNs, where we prune filters from CNNs that are identified as having a small effect on the output accuracy Any inquiry concerning this communication or earlier communications from the examiner should be directed to COREY M SACKALOSKY whose telephone number is (703)756-1590. The examiner can normally be reached M-F 7:30am-3:30pm EST. 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, Omar Fernandez Rivas can be reached at (571) 272-2589. 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. /COREY SACKALOSKY/Examiner, Art Unit 2128 /OMAR F FERNANDEZ RIVAS/Supervisory Patent Examiner, Art Unit 2128