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 .
DETAILED ACTION
The instant application having Application No. 18/680,131 filed on 5/31/2024 is presented for examination.
Examiner Notes
Examiner cites particular columns and line numbers in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner.
Drawings
The applicant’s drawings submitted are acceptable for examination purposes.
Authorization for Internet Communications
The examiner encourages Applicant to submit an authorization to communicate with the examiner via the Internet by making the following statement (from MPEP 502.03):
“Recognizing that Internet communications are not secure, I hereby authorize the USPTO to communicate with the undersigned and practitioners in accordance with 37 CFR 1.33 and 37 CFR 1.34 concerning any subject matter of this application by video conferencing, instant messaging, or electronic mail. I understand that a copy of these communications will be made of record in the application file.”
Please note that the above statement can only be submitted via Central Fax, Regular postal mail, or EFS Web.
Information Disclosure Statement
As required by M.P.E.P. 609, the applicant’s submissions of the Information Disclosure Statement dated 11/25/2025 is acknowledged by the examiner and the cited references have been considered in the examination of the claims now pending.
Claim Rejections - 35 USC § 103
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 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.
Claims 1-6, 8-16, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sun (US 10,109,030) in view of Bernat (US 2022/0269960).
As per claim 1, Sun discloses a method comprising:
receiving, using a worker, an execution request from a queue of a controller (Abstract “The server receives a request from a first client for GPU services. The request includes a first block of GPU code of an application executing on the first client. A first task corresponding to the first block of GPU code is enqueued in a task queue. The task queue includes a second task that corresponds to a second block of GPU code of an application executing on a second client. The server schedules a time for executing the first task using a GPU device that is assigned to the first client, and dispatches the first task to a GPU worker process to execute the first task at the scheduled time using the GPU device. The GPU device is shared, either temporally or spatially, by the first and second clients for executing the first and second tasks.”);
generating an execution result corresponding to the execution request using the first AI model and at least a graphics processing unit (GPU) of a cluster environment hosting the worker; (Column 2, lines 16-29 “The computer server schedules a time for executing the first task using a GPU device that is assigned to the first client system, and dispatches the first task to a server backend GPU worker process to handle execution of the first task at the scheduled time using the GPU device. The utilization of the GPU device is shared by the first and second client systems for executing the first and second tasks. For example, in one embodiment, the utilization of the GPU device is shared temporally, wherein the first and second tasks are executed using the GPU device at different times. In another embodiment, the utilization of the GPU device is shared spatially, wherein both the first and second tasks are concurrently executed using the GPU device.”); and
causing the execution result to be transmitted to the controller (Column 6, lines 8-15 “The system memory 210 comprises volatile memory 212 and non-volatile memory 214. The GPU resources 230 comprise one or more GPU devices 230-1, 230-2, . . . , 230-g. The queue-based GPU virtualization and management system 220 comprises a server frontend module 222, a task queue module 224, a task scheduler and dispatcher module 226, and a server backend GPU worker module 228.”).
Sun does not expressly disclose but Bernat discloses
identifying, based on the execution request, a first artificial intelligence (AI) model of a plurality of AI models of the controller (Paragraph 19 “As discussed herein, the present techniques and configurations provide improvements for these and a variety of other IoT device, Fog network, and data center operation use cases involving AI functions and operations. The present configurations include the deployment of client device (edge), gateway (fog/intermediate), and server (cloud/remote) functions for selecting variations of AI inferencing models. This allows the application of respective inference models in changing scenarios involving mobility, particularly where an IoT device (e.g., an edge device) moves around to a number of edge network locations and generates distinct sensor data in a number of environments.” See also, paragraph 23 “In an example, the AI inference model is operated or otherwise provided by the data center 150 in the form of an AI-as-a-service (AIaaS) deployment. In this fashion, specific AI data operations may be requested and offloaded from the edge device 110 to the cloud, for performance on demand with an inference model operating on platform 142 (e.g., operating on one or more of platforms 142A-142N). However, other examples and uses of an AI inference model may also be provided by the variations of the present architecture and network topology. In particular, the use of the presently described switch and gateway 130 may enable the performance of AI inference operations within a network fog or distributed computing devices. Thus, references to the operation of the AI inference models in a “cloud” and “data center” are used merely for purposes of simplicity.”).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Sun to include the teachings of Bernat because it allows the requesting process to determine the specific model that is appropriate for the task.
As per claim 2, Sun further discloses wherein the worker comprises a code process and a utility process, and wherein access to the code process is limited to the utility process (Column 2, lines 16-21 “The computer server schedules a time for executing the first task using a GPU device that is assigned to the first client system, and dispatches the first task to a server backend GPU worker process to handle execution of the first task at the scheduled time using the GPU device.”).
As per claim 3, Bernat further discloses wherein the worker comprises an initialization process to download the first AI model prior to generating the execution result (Paragraph 31 “As will be apparent, a variety of technical advantages may be provided from the presently disclosed configuration and deployment of AIaaS inferencing services. For instance, such services may be adapted to the capabilities and requirements of edge clients, under the many real-world conditions and scenarios where accelerated models can deliver local customizations. Such services may simplify access to dynamically contextualized solutions, provide end customers with improved knowledge and usefulness, and offer differentiated capabilities in a variety of IoT deployment environments. This is further extended by data-driven continuous customization of services.”).
As per claim 4, Bernat further discloses wherein the utility process transmits periodic heartbeat requests to the controller (Paragraph 144).
As per claim 5, Bernat further discloses wherein causing the execution result to be transmitted to the controller comprises:
causing the execution result to be transmitted to a storage device (Paragraph 62) and
causing a storage identifier associated with the execution result to be transmitted to the controller (Paragraph 62).
As per claim 6, Bernat further discloses wherein the execution request includes an asset identifier, and wherein the initialization process is to download an input asset associated with the asset identifier (Paragraph 28).
As per claim 8, Bernat further discloses wherein the worker is deployed by an agent associated with the cluster environment, and wherein the agent communicates with the controller (Paragraph 106 “Indeed, a component or module of executable code may be a single instruction, or many instructions, and may even be distributed over several different code segments, among different programs, and across several memory devices or processing systems. In particular, some aspects of the described process (such as code rewriting and code analysis) may take place on a different processing system (e.g., in a computer in a data center), than that in which the code is deployed (e.g., in a computer embedded in a sensor or robot). Similarly, operational data may be identified and illustrated herein within components or modules, and may be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set, or may be distributed over different locations including over different storage devices, and may exist, at least partially, merely as electronic signals on a system or network. The components or modules may be passive or active, including agents operable to perform desired functions.”).
As per claim 9, Bernet further discloses wherein the worker is deployed based on a worker deployment request received by the agent from the controller (Paragraph 106).
As per claims 10-15, 17 and 18, they are system claims having similar limitations as cited in claims 1-6, 8 and 9 and are rejected under the same rationale.
As per claims 19 and 20, they are processor claims having similar limitations as cited in claims 1 and 2 and are rejected under the same rationale.
Claims 7 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Sun in view of Bernat in further view of Shilane (US 20210365413).
As per claim 7, Sun does not expressly disclose but Shilane further discloses further comprising:
generating a progress indicator artifact; and causing the progress indicator artifact to be transmitted to the controller (Paragraph 78 “As the workers process the tasks, the workers send progress update messages 648 back to the controller via the message queue. The controller pulls 651 the progress messages from the message queue to track and log 654 a status or progress of the search in search status storage. Search status storage includes persistent storage. The search status storage may include a key-value store. If for any reason the search is interrupted, the search can be restarted without having to reprocess tasks that were already completed. In other words, upon resuming the search, the controller can examine the search status to identify tasks that were already completed, generate new tasks that need to be completed, push the new tasks to the message queue, and not push tasks that were already completed to the message queue.”).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Sun to include the teachings of Shilane because it allows the tracking of execution status which ensures that work is known to be completed and can recover from interruptions.
As per claim 16, it is a system claim having similar limitations as cited in claim 7 and is thus rejected under the same rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Cheng (US 20210224665) discloses receiving a request for system resources (156,156a,156b) for an inference job associated with the machine learning model with one processor. A system resource of multiple system resources is determined for processing the inference job associated with the machine learning model based on multiple performance profiles and a quality of service requirement associated with the inference job with one processor. The system resource is assigned to the inference job for processing the inference job with one processor. The result data associated with processing of the inference job is received with the system resource with one processor. A performance profile of multiple the performance profiles associated with the system resource and the machine learning model is updated with one processor based on the result data.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TIMOTHY A MUDRICK whose telephone number is (571)270-3374. The examiner can normally be reached 9am-5pm Central Time.
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, Pierre Vital can be reached at (571)272-4215. 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.
/TIMOTHY A MUDRICK/Primary Examiner, Art Unit 2198 9/29/2026
