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 .
Status of Claims
This action is responsive to the application filed on March 7, 2025. Claims 1-24 were presented, and are pending examination.
Drawings
The drawings filed on November 27, 2025 are accepted.
Examiner’s Note about the Format of 35 U.S.C. 102/103 Rejections
Generally, limitations of a claim are reproduced identically and followed by examiner’s explanation with citation from prior art in Italic enclosed by a parenthesis, (), for each limitation. In examiner’s explanation, the mapping of the key elements of a limitation to the disclosed elements of prior art is shown by stating the disclosed element immediately followed by the claimed element inside a parenthesis. Specific quotation from prior art is delineated with quotation mark, ““. If primary art fails to teach a limitation or part of the limitation, the limitation or the part of the limitation is placed inside double square brackets, [[ ]], for better understandability, and appropriate secondary art(s) is/are applied later addressing the deficiency of the primary art.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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, 9-13, and 21-24 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Phanishayee et al. (US PGUB No. US 20250060998 A1), hereinafter, Phanishayee.
Regarding claim 1:
Phanishayee teaches:
A system for distributing tasks, comprising: a computing resource pool including computer hardware configured to execute tasks (see Fig. 4);
a deep neural network (DNN) repository comprising a plurality of DNN models (Fig. 4 shows a model manager 424 storing plurality of DNN models as stated in paragraph 0044 “Model manager component 424 manages the storage of models and loads/picks the models which have been requested to be served”);
a controller configured to (Fig. 4 shows a thread optimization system 400 (controller) as stated in paragraph 0036 “An example implementation of a thread optimization system 400 is shown in FIG. 4.”) :
receive a request to process a task from a device across a network (paragraph 0062 discloses inference request as stated “The method begins with estimating a batch size of a batch of inference requests for the model serving system (block 902”). Fig. 4 shows receiving inference request 416. Paragraph 0035 discloses client device request DNN service),
determine a DNN configuration to process the task based on an identification of computing resources required to process the task (paragraph 0062 discloses determining DNN configuration as stated “An optimizer component of a thread optimizer system for the model serving system then determines an optimal configuration that defines a number of inference instances, a number of threads per inference instance, and a sub-batch size per inference instance for processing the batch of inference requests using intra-operator parallelism with the plurality of threads that minimizes average per-patch latency (block 904)”),
allocate a subset of the computing resource pool to execute the task based on the DNN configuration (paragraph 0062 discloses allocating resource based on the configuration as stated “Once the optimal configuration is determined, compute resources are allocated based on the number of inference instances, the number of threads per inference instance, and the sub-batch size per inference instance indicated by the optimal configuration (block 906).”),
activate a selected set of DNN blocks from the DNN repository based on the DNN configuration (Fig. 4 shows worker instances (DNN blocks). Paragraph 0045 discloses selecting appropriate worker instance ), and
enable the device to transmit input data to the subset of the computing resource pool to execute the task via the selected set of DNN blocks (paragraph 0062 discloses inference request is dispatched to the inference instances as stated “The batch of inference requests is then dispatched to the inference instances in accordance with the optimal configuration (block 908).” ).
As to claim 9, the rejection of claim 1 is incorporated. Phanishayee teaches all the limitations of claim 1 as shown above.
Phanishayee further teaches wherein the controller is further configured to construct a dynamic DNN to execute the task, the dynamic DNN comprising the selected set of DNN blocks (paragraph 0052 discloses dynamic DNN with worker instance).
As to claim 10, the rejection of claim 9 is incorporated. Phanishayee teaches all the limitations of claim 9 as shown above.
Phanishayee further teaches wherein the dynamic DNN comprises layers extracted from a plurality of different DNN models of the DNN repository (paragraph 0062 disclose worker instance are selected from plurality of model profiles as stated “. The predetermined model profiles are used as input to a dynamic programming algorithm that identifies optimal configurations that minimize the average per-batch latency.”).
As to claim 11, the rejection of claim 1 is incorporated. Phanishayee teaches all the limitations of claim 1 as shown above.
Phanishayee further teaches wherein each of the subset of DNN blocks are one or more layers of the plurality of DNN models (paragraph 0046 discloses the worker instance are layer of DNN model).
As to claim 12, the rejection of claim 1 is incorporated. Phanishayee teaches all the limitations of claim 1 as shown above.
Phanishayee further teaches wherein the controller is further configured to allocate a transmission slot based on the DNN configuration, the transmission slot defining the transmission of the input data from the device to the selected set of DNN blocks (Fig. 4 shows queue for transmission of the data to the selected worker instance 412).
Regarding claim 13:
Claim 13 is directed towards method performed by the system of claim 1. Accordingly, it is rejected under similar rationale.
Claim 21 is directed towards method performed by the system of claim 9. Accordingly, it is rejected under similar rationale.
Claim 22 is directed towards method performed by the system of claim 10. Accordingly, it is rejected under similar rationale.
Claim 23 is directed towards method performed by the system of claim 11. Accordingly, it is rejected under similar rationale.
Claim 24 is directed towards method performed by the system of claim 12. Accordingly, it is rejected under similar rationale.
Allowable Subject Matter
Claims 2-8 and 14-20 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
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KAMAL M HOSSAIN whose telephone number is (571)270-3070. The examiner can normally be reached 9:30-5:30 M-F.
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, John Follansbee can be reached at (571)272-3964. 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.
July 30, 2026
/KAMAL M HOSSAIN/ Primary Examiner, Art Unit 2444
Prosecution Insights