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 .
This office action is in response to applicant’s amendment filed on 04/06/2026.
Claims 1-11 and 13-26 are pending and examined.
Claim 12 is cancelled.
Response to Arguments
Applicant's arguments filed 04/06/2026 with respect to 35 U.S.C. 103 have been fully considered but they are not persuasive. Applicant argued that “neither Pyla nor Akiona discloses autonomous agents comprising onboard processing circuitry that are recruited as compute nodes to a workload cell for performing assigned processing operations distributed among the onboard processing circuitry of the recruited autonomous agents.” Examiner respectfully disagrees, see 35 U.S.C. 103 rejections below for a detailed analysis. While Pyla does not explicitly teach that the compute nodes are one or more autonomous agents and that the assigned processing operations are distributed among the onboard processing circuitry of the recruited autonomous agents, autonomous agents are a popular form of compute node for performing assigned processing operations that are distributed among the onboard processing circuitry of the recruited autonomous agents as evidenced by Akiona. For example, Akiona’s agents such as robot agents including a state machine, task, and model correlates to compute nodes being one or more autonomous agents. The robot agents performing tasks at the physical area would include onboard processing circuitry and therefore correlates to each of the one or more autonomous agents being a physical autonomous agent comprising onboard processing circuitry and being configured to navigate a physical environment. Therefore, it would have been obvious to one of ordinary skill in the art to which said subject matter pertains before the effective filing date of the claimed invention to combine Pyla with Akiona because simulation results can be directly used to adjust the navigation of robots in a physical area for completing tasks. Additionally, the allocation of robots for each task, allowed directionality of travel through segments of the area, and general efficiency adjustments can be done in response to simulations. These adjustments result in more efficient operation of the robots and reduced errors/damage caused by the robots by reducing collisions or overheating due to congestion. Task allocators can assign tasks to agents based on the type of tasks each agent is capable of performing and their location. Agents transitioning from node locations can be configured to request permission in scenarios where the number of agents at a particular node an agent is transitioning out of is below its limit. The data recorded during simulation can be used to generate performance metrics, evaluate task/navigation completion times, evaluate congestion within area nodes, and/or replay the simulation in two dimensions or three dimensions.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that use the word “means” or “step” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph because the claim limitation(s) do not recite(s) sufficient structure, materials, or acts to entirely perform the recited function. Such claim limitation(s) is/are: “a first/second/third network edge computing means” in claims 15 and 19 explicitly include the word “means” and are coupled with functional language including “means for determining/generating/establishing/populating/selectively assigning” without sufficient structure to perform the recited function.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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 1, 4, 6-11, 13-15, 18-20 and 23-26 are rejected under 35 U.S.C. 103 as being unpatentable over Pyla et al. (U.S. Patent No. US 20230065444 A1), hereinafter “Pyla” in view of Akiona et al. (U.S. Patent No. US 20210349473 A1), hereinafter “Akiona.”
With regards to Claim 1, Pyla teaches:
An apparatus comprising:
A first processing circuitry configured to:
determine available compute nodes within an environment (Paragraph 21, “Controller 170 may also configure and manage aspects of how each of workloads 130 are executed. For instance, controller 170 may serve as an orchestration platform for bare metal composition, provisioning, and management within data center 108. In such a role, controller 170 may act as a “composer system,” where controller 170 composes instances of compute nodes 140 out of available resources within data center 108. In particular, and as further described herein, controller 170 may compose, create, instantiate, or otherwise configure one or more of compute nodes 140 to enable efficient execution of workloads 130 within data center 108.” The controller serving as an orchestration platform for provisioning instances of available compute nodes within the data center correlates to a first processing circuitry determining available compute nodes within an environment); and
determine a set of appropriate compute nodes, of the available compute nodes, based on a node manifest (Paragraphs 21 and 32, “Controller 170 may, in response to administrator input and/or its own analysis, compose one or more compute nodes 140 from available hardware and deploy such compute nodes 140 to process or execute one or more workloads 130… In accordance with one or more aspects of the present disclosure, controller 170 may receive information about resources needed to execute workloads 130.” The controller composing one or more compute nodes from available hardware based on information about resources needed to execute workloads correlates to determining a set of appropriate compute nodes based on a node manifest); and
a second processing circuitry configured to:
generate the node manifest based on a target configuration for executing processing operations in accordance with an identified task to be performed by the one or more nodes and provide the node manifest to the first processing circuitry for node determination (Paragraph 32, “In accordance with one or more aspects of the present disclosure, controller 170 may receive information about resources needed to execute workloads 130. For instance, in an example that can be described in the context of FIG. 1A, controller 170 detects a signal from administrator device 171 (e.g., generated in response to input by an administrator operating device 171). Controller 170 determines that the signal corresponds to specifications about the compute or server needs of various workloads 130, including workloads 130A, 130B, and 130C. Controller 170 further determines that the specifications describe the geometry of compute nodes that may be needed to execute workloads 130. In some examples, the specifications may take the form of a composition profile (e.g., one or more composition profiles 182) for each of workloads 130. Such composition profiles 182 may include compute, storage, and network specifications.” The composition profile comprising compute, storage, and network specifications for each workload correlates to generating a node manifest based on a target configuration for executing processing operations in accordance with an identified task to be performed by the one or more nodes. The administrator device sending a signal corresponding to a composition profile and information describing the geometry of compute nodes needed to execute workloads to the controller correlates to providing the node manifest to the first processing circuitry for node determination);
establish a compute cluster comprising a workload cell based on the target configuration (Paragraphs 24 and 33, “Groups or clusters of compute nodes 140 may be deployed or tasked to support operations of various applications or workloads, including, as illustrated in FIG. 1A, workloads 130A, 130B, and 130C (collectively “workloads 130”) … Controller 170 may provision resources for workloads 130. For instance, continuing with the example being described in the context of FIG. 1A, controller 170 provisions, based on composition profile 182, one or more compute nodes 140. Specifically, controller 170 provisions compute node 140A and compute node 140B for workload 130A.” The controller provisioning one or more compute nodes for a workload as a cluster based on the composition profile correlates to establishing a workload cell based on the target configuration);
populate the established workload cell with the appropriate compute nodes received from the first processing circuitry by recruiting the compute nodes for performing assigned processing operations (Paragraphs 34-35, “Each of compute nodes 140 may be configured as illustrated in FIG. 1B, so that, for example, physical compute server 150A of compute node 140 includes a corresponding processor 153A, memory device 155A, and DPU 157A… Controller 170 may configure each of workloads 130 to execute on a specific set of compute nodes 140. For instance, continuing with the example being described in the context of FIG. 1A, controller 170 configures and/or enables workload 130A to execute on compute nodes 140A and 140B.” The controller configuring each workload to execute on a specific set of compute nodes correlates to populating the established workload cell with the appropriate compute nodes received from the first processing circuitry by recruiting the compute nodes for performing assigned processing operations);
and selectively assign, based upon processing constraints of the identified task, the execution of the processing operations in accordance with the identified task to (i) the established compute cluster (Paragraphs 24 and 32-33, “Groups or clusters of compute nodes 140 may be deployed or tasked to support operations of various applications or workloads, including, as illustrated in FIG. 1A, workloads 130A, 130B, and 130C (collectively “workloads 130”) … In accordance with one or more aspects of the present disclosure, controller 170 may receive information about resources needed to execute workloads 130. For instance, in an example that can be described in the context of FIG. 1A, controller 170 detects a signal from administrator device 171 (e.g., generated in response to input by an administrator operating device 171). Controller 170 determines that the signal corresponds to specifications about the compute or server needs of various workloads 130, including workloads 130A, 130B, and 130C. Controller 170 further determines that the specifications describe the geometry of compute nodes that may be needed to execute workloads 130. In some examples, the specifications may take the form of a composition profile (e.g., one or more composition profiles 182) for each of workloads 130. Such composition profiles 182 may include compute, storage, and network specifications… Controller 170 may provision resources for workloads 130. For instance, continuing with the example being described in the context of FIG. 1A, controller 170 provisions, based on composition profile 182, one or more compute nodes 140. Specifically, controller 170 provisions compute node 140A and compute node 140B for workload 130A.” The controller provisioning one or more compute nodes for a workload as a cluster correlate to assigning the execution of the processing operations in accordance with the identified task to the established compute cluster. The controller provisioning the compute nodes based on the composition profile, which includes specifications about compute, storage, network, or server needs for a particular workload correlate to selectively assigning the execution of the processing operating based upon processing constraints of the identified task), or (ii) a network edge component in communication with the first processing circuitry and the second processing circuitry.
Pyla does not explicitly teach that the target configuration for executing processing operations in accordance with the identified task is performed by one or more autonomous agents, that the compute nodes are one or more autonomous agents and that the assigned processing operations are distributed among the onboard processing circuitry of the recruited autonomous agents. However, autonomous agents are a popular component of systems for the target configuration for executing processing operations in accordance with the identified task is performed by one or more autonomous agents as evidenced by Akiona below (paragraphs 35, 37, and 41-42). Additionally, autonomous agents are a popular form of compute node for performing assigned processing operations that are distributed among the onboard processing circuitry of the recruited autonomous agents as evidenced by Akiona below (paragraphs 35-37 and 41-42).
Pyla does not explicitly teach:
the compute nodes being one or more autonomous agents, each of the one or more autonomous agents being a physical autonomous agent comprising onboard processing circuitry and being configured to navigate a physical environment;
wherein the processing operations comprise part of an application workload executed by the one or more autonomous agents while navigating the physical environment to perform the identified task;
However, Akiona teaches:
the compute nodes being one or more autonomous agents, each of the one or more autonomous agents being a physical autonomous agent comprising onboard processing circuitry and being configured to navigate a physical environment (Paragraphs 35, 37, and 41-42, “The area configuration data 305 can include a graph that includes area nodes, terminal nodes, edges between various nodes, and data for the various nodes, e.g., metadata for the nodes. For example, the area configuration data 305 can include a graph similar to the graph 200 of FIG. 2. The area configuration data 305 can also include data identifying agents for the actors for which the simulation will be performed, e.g., agents for the actors that will perform tasks at the physical area represented by the area configuration data 305… During a simulation, the task allocator 310 can assign the tasks to the agents, e.g., based on the type of tasks that each agent is capable of performing and the location of each agent in the graph (e.g., the node in which the agent is located) … The simulation system 301 can simulate various types of agents performing tasks in the area defined by the area configuration data 305. In this example, the simulation system 301 includes robot agents 330 and human agents 332. In other examples, the simulation system 301 can include forklift agents, drone agents, bulldozer agents, crane agents, and/or other types of agents for other types of actors that can perform tasks in an area. Each agent can include a state machine, a task, and a model.” The agents such as robot agents including a state machine, task, and model correlates to compute nodes being one or more autonomous agents. The robot agents performing tasks at the physical area correlates to each of the one or more autonomous agents being a physical autonomous agent comprising onboard processing circuitry and being configured to navigate a physical environment);
wherein the processing operations comprise part of an application workload executed by the one or more autonomous agents while navigating the physical environment to perform the identified task (Paragraphs 35-37, “The area configuration data 305 can also include data identifying agents for the actors for which the simulation will be performed, e.g., agents for the actors that will perform tasks at the physical area represented by the area configuration data 305… The task allocator 310 can include a list of tasks that are to be performed during a simulation. The list of tasks can be in the order in which the agents are to be simulated as performing the tasks during the simulation… During a simulation, the task allocator 310 can assign the tasks to the agents, e.g., based on the type of tasks that each agent is capable of performing and the location of each agent in the graph (e.g., the node in which the agent is located). For example, as described in more detail below, when an agent completes a task, the agent can request another task from the task allocator 310 or indicate to the task allocator 310 that the agent is available for another task.” The list of tasks to be performed during a simulation correlates to an application workload executed by the one or more autonomous agents. The agents being assigned tasks to be performed at the physical area and completing the assigned tasks correlates to the processing operations comprising part of an application workload executed by the one or more autonomous agents while navigating the physical environment to perform the identified task);
Therefore, it would have been obvious to one of ordinary skill in the art to which said subject matter pertains before the effective filing date of the claimed invention to combine Pyla with the compute nodes being one or more autonomous agents, each of the one or more autonomous agents being a physical autonomous agent comprising onboard processing circuitry and being configured to navigate a physical environment wherein the processing operations comprise part of an application workload executed by the one or more autonomous agents while navigating the physical environment to perform the identified task as taught by Akiona because simulation results can be directly used to adjust the navigation of robots in a physical area for completing tasks. Additionally, the allocation of robots for each task, allowed directionality of travel through segments of the area, and general efficiency adjustments can be done in response to simulations. These adjustments result in more efficient operation of the robots and reduced errors/damage caused by the robots by reducing collisions or overheating due to congestion. Task allocators can assign tasks to agents based on the type of tasks each agent is capable of performing and their location. Agents transitioning from node locations can be configured to request permission in scenarios where the number of agents at a particular node an agent is transitioning out of is below its limit. The data recorded during simulation can be used to generate performance metrics, evaluate task/navigation completion times, evaluate congestion within area nodes, and/or replay the simulation in two dimensions or three dimensions (Akiona: paragraphs 11, 37 and 39-40).
With regards to Claims 15 and 20, the machine of Claim 1 performs the same steps as the machine and manufacture of Claims 15 and 20 respectively, and Claims 15 and 20 are therefore rejected using the same rationale set forth above in the rejection of Claim 1.
With regards to Claim 4, Pyla in view of Akiona teaches the system of Claim 1 above. Pyla further teaches:
wherein the second processing circuitry is further configured to monitor the established workload cell (Paragraph 36, “Controller 170 may monitor execution of workloads 130. For instance, still referring to the example being described in the context of FIG. 1A, controller 170 monitors, queries, or otherwise receives information about utilization, performance, and/or other metrics associated with various workloads 130 executing within data center 108.” The controller monitoring the execution of workloads to receive information about various metrics correlates to the second processing circuitry monitoring the established workload cell) and add one or more other compute nodes to the established workload cell or remove one or more of the appropriate compute nodes from the workload cell to provide an adapted workload cell (Paragraphs 37, “Controller 170 may increase the number of compute nodes 140 supporting workload 130B. For instance, again with reference to FIG. 1A, controller 170 determines that workload 130B would benefit from additional processing resources, and that workload 130A could operate effectively with less processing resources. Controller 170 increases the size of the cluster of compute nodes 140 (i.e., compute nodes 140C and 140D) supporting workload 130B by composing compute node 140E.” The controller increasing the number of compute nodes in the cluster supporting a specific workload correlate to adding one or more other compute nodes to the established workload cell to provide an adapted workload cell).
With regards to Claims 18 and 23, the machine of Claim 4 performs the same steps as the machine and manufacture of Claims 18 and 23 respectively, and Claims 18 and 23 are therefore rejected using the same rationale set forth above in the rejection of Claim 4.
With regards to Claim 6, Pyla in view of Akiona teaches the system of Claim 1 above. Pyla further teaches:
further comprising a third processing circuitry configured to generate telemetry information based on telemetry data received from the compute nodes of the established workload cell (Paragraph 59, “Collection module 284 may perform functions relating to collecting data about workloads or other operations executing on one or more compute nodes 140. For instance, collection module 284 may collect data indicating utilization rates of resources of each of compute nodes 140, including CPU utilization, memory utilization, storage utilization, networking statistics, and utilization rates of any GPU (e.g., GPUs 163) that may be included within a given compute node 140. Collection module 284 may cause controller 270 to poll one or more compute nodes 140 for such data. Alternatively, or in addition, collection module 284 may cause controller 270 to configure one or more compute nodes 140 to report data, metrics, summary information, or other information. Such data may be reported periodically, when a threshold is met, when an event occurs, on demand, or in another way or on another schedule. Collection module 284 may store some or all of such data within data store 289, and/or may output such data to analysis module 285 for evaluation.” The collection module collecting and storing data about workloads and compute nodes which are received from compute nodes correlates to a third processing circuitry generating telemetry information based on telemetry data received from the compute nodes), wherein the second processing circuitry is configured to adapt the workload cell based on the telemetry information (Paragraph 60, “Analysis module 285 may perform functions relating to analyzing how one or more workloads 230 are executing within data center 108 and may assess and/or determine ways in which workloads 230 might execute more efficiently. To perform such analyses, analysis module 285 may evaluate data collected by collection module 284 and determine which of workloads 230 might benefit from additional computing resources and which of workloads 230 are relatively idle (and have an over-allocation of computing resources).” The analysis module evaluating data collected by the collection module to determine which workloads might benefit from additional computing resources correlates to the second processing circuitry adapting the workload cell based on the telemetry information).
With regards to Claims 19 and 24, the machine of Claim 6 performs the same steps as the machine and manufacture of Claims 19 and 24 respectively, and Claims 19 and 24 are therefore rejected using the same rationale set forth above in the rejection of Claim 6.
With regards to Claim 7, Pyla in view of Akiona teaches the system of Claim 6 above. Pyla further teaches:
wherein adapting the workload cell comprises adding one or more other compute nodes to the established workload cell or removing one or more of the appropriate compute nodes from the workload cell (Paragraphs 91-92, “Analysis module 285 determines, based on the metrics and related information, that each of compute nodes 140D and 140E are experiencing relatively high CPU utilization while executing workload 230B. Analysis module 285 also determines that compute nodes 140A through 140C are experiencing relatively low CPU utilization while executing workload 230A… Controller 270 may idle one or more of compute nodes 140 that support workload 230A... DPU 157C terminates the portion of workload 230A that is being executed at compute server 150C of compute node 140C, thereby idling compute node 140C. DPU 157 thus “dehydrates” the idle workload executing on compute server 150C. Workload 230A continues to be processed within data center 208, but now only by compute nodes 140A and 140B. Accordingly, the cluster of compute nodes 140 that support workload 230A has been reduced by one.” The analysis module determining that the compute nodes for workload 230A have low CPU utilization and signaling the removal of one of the nodes for that workload correlates to adapting the workload cell by removing one or more appropriate compute nodes from the workload cell).
With regards to Claim 8, Pyla in view of Akiona teaches the system of Claim 6 above. Pyla further teaches:
wherein the telemetry information comprises one or more compute- node metrics and/or one or more network metrics (Paragraph 59, “Collection module 284 may perform functions relating to collecting data about workloads or other operations executing on one or more compute nodes 140. For instance, collection module 284 may collect data indicating utilization rates of resources of each of compute nodes 140, including CPU utilization, memory utilization, storage utilization, networking statistics, and utilization rates of any GPU (e.g., GPUs 163) that may be included within a given compute node 140. Collection module 284 may cause controller 270 to poll one or more compute nodes 140 for such data. Alternatively, or in addition, collection module 284 may cause controller 270 to configure one or more compute nodes 140 to report data, metrics, summary information, or other information.” The collection module collecting data indicating utilization rates of resources for each compute node and networking statistics correlates to the telemetry information comprising one or more compute node metrics or network metrics).
With regards to Claims 11 and 25, the machine of Claim 8 performs the same steps as the machine and manufacture of Claims 11 and 25 respectively, and Claims 11 and 25 are therefore rejected using the same rationale set forth above in the rejection of Claim 8.
With regards to Claim 9, Pyla in view of Akiona teaches the system of Claim 1 above. Pyla further teaches:
wherein the first processing circuitry is configured to determine the appropriate compute nodes further based on received telemetry information and/or Quality-of-Service (QoS) information (Paragraphs 58 and 60, “Provisioning module 282 may perform functions relating to composing and/or provisioning one or more compute nodes 140 to handle or support processing of one or more workloads 230. Provisioning module 282 may cause controller 270 to compose one or more compute nodes 140 based on one or more composition profiles 182, where such composition profiles 182 are derived from administrator input (e.g., from administrator device 171) or generated in response to data produced by analysis module 285… To perform such analyses, analysis module 285 may evaluate data collected by collection module 284.” The controller composing one or more compute nodes based on composition profiles which are derived from the analysis and collection modules correlates to the first processing circuitry determining the appropriate compute nodes based on telemetry information received by the first processing circuitry).
With regards to Claim 10, Pyla in view of Akiona teaches the system of Claim 9 above. Pyla further teaches:
third processing circuitry configured to generate the telemetry information based on telemetry data received from the compute nodes (Paragraph 59, “Collection module 284 may perform functions relating to collecting data about workloads or other operations executing on one or more compute nodes 140. For instance, collection module 284 may collect data indicating utilization rates of resources of each of compute nodes 140, including CPU utilization, memory utilization, storage utilization, networking statistics, and utilization rates of any GPU (e.g., GPUs 163) that may be included within a given compute node 140. Collection module 284 may cause controller 270 to poll one or more compute nodes 140 for such data. Alternatively, or in addition, collection module 284 may cause controller 270 to configure one or more compute nodes 140 to report data, metrics, summary information, or other information. Such data may be reported periodically, when a threshold is met, when an event occurs, on demand, or in another way or on another schedule. Collection module 284 may store some or all of such data within data store 289, and/or may output such data to analysis module 285 for evaluation.” The collection module collecting and storing data about workloads and compute nodes which are received from compute nodes correlates to a third processing circuitry generating telemetry information based on telemetry data received from the compute nodes).
With regards to Claim 13, Pyla in view of Akiona teaches the system of Claim 1 above. Pyla further teaches:
wherein the second processing circuitry and the first processing circuitry are embodied in a same computing device (Paragraphs 52 and 58-60, “One or more processors 274 of controller 270 may implement functionality and/or execute instructions associated with controller 270 or associated with one or more modules illustrated herein and/or described below… Provisioning module 282 may perform functions relating to composing and/or provisioning one or more compute nodes 140 to handle or support processing of one or more workloads 230. Provisioning module 282 may cause controller 270 to compose one or more compute nodes 140 based on one or more composition profiles 182… Collection module 284 may perform functions relating to collecting data about workloads or other operations executing on one or more compute nodes 140… Analysis module 285 may perform functions relating to analyzing how one or more workloads 230 are executing within data center 108 and may assess and/or determine ways in which workloads 230 might execute more efficiently.” The provisioning, collection, and analysis modules correlate to the second processing circuitry, and the controller correlates to the first processing circuitry. The processors of the controller implementing the functionality associated with the one or more modules correlates to the second processing circuitry and first processing circuitry being embodied on the same computing device).
With regards to Claim 14, Pyla in view of Akiona teaches the system of Claim 1 above. Pyla further teaches:
wherein the second processing circuitry and the first processing circuitry are embodied in different computing devices (Paragraphs 58-60 and 83, “Provisioning module 282 may perform functions relating to composing and/or provisioning one or more compute nodes 140 to handle or support processing of one or more workloads 230. Provisioning module 282 may cause controller 270 to compose one or more compute nodes 140 based on one or more composition profiles 182… Collection module 284 may perform functions relating to collecting data about workloads or other operations executing on one or more compute nodes 140… Analysis module 285 may perform functions relating to analyzing how one or more workloads 230 are executing within data center 108 and may assess and/or determine ways in which workloads 230 might execute more efficiently... Modules illustrated in FIG. 2 (e.g., provisioning module 282, collection module 284, and analysis module 285) and/or illustrated or described elsewhere in this disclosure may perform operations described using software, hardware, firmware, or a mixture of hardware, software, and firmware residing in and/or executing at one or more computing devices.” The provisioning, collection, and analysis modules correlate to the second processing circuitry, and the controller correlates to the first processing circuitry. The modules executing at one or more computing devices correlates to the second processing circuitry and first processing circuitry being embodied on different computing devices).
With regards to Claim 26, Pyla in view of Akiona teaches the system of Claim 1 above. Akiona further teaches:
wherein the processing constraints of the identified task comprise motion planning constraints (Paragraph 31, 37, 64, and 66 “An edge between an area node and a terminal node represents the corresponding region at which the task corresponding to the terminal node is performed. For example, the edge between area node 211A and terminal node 214A indicates that an actor would need to travel to the region 111A corresponding to the area node 211A to perform the task represented by terminal node 214A… During a simulation, the task allocator 310 can assign the tasks to the agents, e.g., based on the type of tasks that each agent is capable of performing and the location of each agent in the graph (e.g., the node in which the agent is located) … For example, if a particular node has higher congestion than other nodes, the robot simulation system can reroute agents around that node or determine a different sequence of tasks such that fewer agents are in the node at the same time… In this example, the robot controller 340 can adjust the control of robots to take a different path between the regions of the physical area to avoid the region corresponding to the area node that has congestion. The robot controller 340 can transmit, to a robot, instructions that cause the robot to take the different path or to avoid the region.” The agent being assigned a task based on its location in the graph and needing to take a path to the specific area node represented by the terminal node task correlates to processing constraints of the identified task. A particular node having congestion which causes the robot simulation system to reroute agents around the node by avoiding the region or taking a different path correlate to the processing constraints of the identified task comprising motion planning constraints) or sensor data processing latency constraints.
Therefore, it would have been obvious to one of ordinary skill in the art to which said subject matter pertains before the effective filing date of the claimed invention to combine Pyla with wherein the processing constraints of the identified task comprise motion planning constraints or sensor data processing latency constraints as taught by Akiona because actors often have to travel between various regions to perform tasks. Using different durations or distributions of durations to simulate indirect interactions between agents such as congestion results in more accurate simulations of actors performing tasks in a facility or other area in which robots, people, and/or other actors perform tasks. Additionally, by reducing the delay in navigating robots through various areas, idling times of robots can be reduced resulting in less wasted computational resources and less wasted power consumption for the robots. (Akiona: paragraphs 49 and 64).
Claim(s) 2-3, 5, 16-17 and 21-22 are rejected under 35 U.S.C. 103 as being unpatentable over Pyla in view of Akiona and Zeng et al. (U.S. Patent No. US 20220083375 A1), hereinafter “Zeng.”
With regards to Claim 2, Pyla in view of Akiona teaches the system of Claim 1 above. Pyla in view of Akiona does not explicitly teach:
wherein the node manifest comprises node types and respective quantities of compute nodes for the workload cell based on the target configuration.
However, Zeng teaches:
wherein the node manifest comprises node types and respective quantities of compute nodes for the workload cell based on the target configuration (Paragraphs 41 and 46, “In this way, the first primary node receives a task processing request message, where the task processing request message carries resource requirement information required by a to-be-processed task, and the resource requirement information includes at least a resource type, a quantity of required resources, and the like… The cluster information of the first cluster includes an identifier and a status that are of the first cluster and a quantity of idle resources corresponding to each resource type included in the node in the first cluster.” The task processing request carrying resource requirement information which includes a resource type and quantity of required resources correlates to the target configuration. The cluster information which includes details of the quantity and types of resources correlates to the node manifest comprising node types and respective quantities of compute nodes for the workload cell based on the target configuration).
Therefore, it would have been obvious to one of ordinary skill in the art to which said subject matter pertains before the effective filing date of the claimed invention to combine Pyla with wherein the node manifest comprises node types and respective quantities of compute nodes for the workload cell based on the target configuration as taught by Zeng because resource requirements can be used to determine whether idle resources meeting the resource type requirements are available to be added to a cluster for processing tasks. Additional clusters may also be queried using the resource requirement information (Zeng: paragraphs 41-42).
With regards to Claims 16 and 21, the machine of Claim 2 performs the same steps as the machine and manufacture of Claims 16 and 21 respectively, and Claims 16 and 21 are therefore rejected using the same rationale set forth above in the rejection of Claim 2.
With regards to Claim 3, Pyla in view of Akiona and Zeng teach the system of Claim 2 above. Zeng further teaches:
wherein the node types include respective node attributes for the different node types (Paragraphs 46 and 49, “The cluster information of the first cluster includes an identifier and a status that are of the first cluster and a quantity of idle resources corresponding to each resource type included in the node in the first cluster… The first primary node may obtain resource usage corresponding to each resource type in the target node based on a quantity of idle resources and a total quantity of resources corresponding to each resource type included in the target node.” The cluster information including a status of resources for each resource type, which have corresponding resource usage for each type in a target node, correlates to the node types including respective node attributes for the different node types).
Therefore, it would have been obvious to one of ordinary skill in the art to which said subject matter pertains before the effective filing date of the claimed invention to combine Pyla with wherein the node types include respective node attributes for the different node types as taught by Zeng because resource requirements can be used to determine whether idle resources meeting the resource type requirements are available to be added to a cluster for processing tasks. Additional clusters may also be queried using the resource requirement information. Detailed resource information can be used to gauge whether the resource usage for a resource type exceeds or does not exceed a preset usage threshold and apply a corresponding tag to indicate whether the node is busy or idle (Zeng: paragraphs 41-42 and 49).
With regards to Claims 17 and 22, the machine of Claim 3 performs the same steps as the machine and manufacture of Claims 17 and 22 respectively, and Claims 17 and 22 are therefore rejected using the same rationale set forth above in the rejection of Claim 3.
With regards to Claim 5, Pyla in view of Akiona teaches the system of Claim 4 above. Pyla in view of Akiona does not explicitly teach:
wherein the second processing circuitry is configured to adjust the node manifest based on the adapted workload cell to reflect changes of the compute nodes within the workload cell.
However, Zeng teaches:
wherein the second processing circuitry is configured to adjust the node manifest based on the adapted workload cell to reflect changes of the compute nodes within the workload cell (Paragraphs 40 and 46, “Then, the first primary node may periodically or aperiodically query a quantity of idle resources corresponding to each resource type currently included in the node, and separately update the stored quantity of idle resources corresponding to each resource type in the node to the currently found quantity of idle resources corresponding to each resource type. Alternatively, when an idle resource corresponding to a specific resource type included in the node changes, the node sends the resource type and a quantity of current idle resources to the first primary node, and the first primary node receives the resource type and the quantity of current idle resources, and updates a stored quantity of idle resources corresponding to the resource type in the node to the received quantity of current idle resources… The cluster information of the first cluster includes an identifier and a status that are of the first cluster and a quantity of idle resources corresponding to each resource type included in the node in the first cluster.” The cluster information, which includes the quantity of resources for each resource type, being updated to reflect the current stored quantity when an idle resource changes correlates to adjusting the node manifest based on the adapted workload cell to reflect changes of the compute nodes).
Therefore, it would have been obvious to one of ordinary skill in the art to which said subject matter pertains before the effective filing date of the claimed invention to combine Pyla with wherein the second processing circuitry is configured to adjust the node manifest based on the adapted workload cell to reflect changes of the compute nodes within the workload cell as taught by Zeng because resource requirements can be used to determine whether idle resources meeting the resource type requirements are available to be added to a cluster for processing tasks. Ensuring the quantity of idle resources is updated when changes to resources occur allows the task processing request to be accurate. Additional clusters may also be queried using the resource requirement information (Zeng: paragraphs 40-42).
Prior Art Made of Record
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
Hamann et al. (U.S. Patent No. US 20230367647 A1); teaching a method of adaptive resource allocation for applications in a distributed system of heterogeneous compute nodes. The adaptive steps are carried out in an automated manner and the applications and resources are monitored to determine if a change in resource allocation of the system is required. Changes in resource allocation can also include the entry or exit of compute nodes.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 SELINA HU whose telephone number is (571)272-5428. The examiner can normally be reached Monday-Friday 8:30-5:30.
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, Chat Do can be reached at (571) 272-3721. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
The publicPAIR and privatePAIR systems are no longer available. 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.
/SELINA ELISA HU/Examiner, Art Unit 2193
/Chat C Do/Supervisory Patent Examiner, Art Unit 2193
Prosecution Insights