DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-20 are pending in this application.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant’s submission filed on 04/07/2026 has been entered.
Claims 1-20 are presented for examination. Claims 1, 10, and 17 have been amended.
Response to Arguments
The objections to the drawings and specification have been withdrawn.
Applicant’s arguments regarding the rejections of claims 1-20 under 35 U.S.C. 112a have been fully considered and are persuasive. The rejections have been withdrawn.
Applicant’s arguments regarding the rejections of claims 1-20 under 35 U.S.C. 112b have been fully considered and are persuasive. The rejections have been withdrawn. However, new 35 U.S.C. 112b rejections are applied to claims 1-20 based on the amendments.
Applicant's arguments regarding the 35 U.S.C. 101 rejections of claims 1-20 have been fully considered but they are not persuasive.
Regarding the 35 U.S.C. 101 rejection, the applicant argues the following in the remarks:
The newly added limitations are not mental processes.
The limitations integrate the abstract idea into a practical application since an improvement is specified.
Examiner has thoroughly considered Applicant’s arguments, but respectfully finds them unpersuasive for at least the following reasons:
As to point (a), the examiner argues that some of the newly added limitations are mental processes, some are generic computing components, and some are insignificant extra solution activities. See the rejection below.
As to point (b), the examiner respectfully disagrees. The claims do not recite the limitations necessary to realize the improvement disclosed in the specification (MPEP 2106.04(d)(1) if the specification sets forth an improvement in technology, the claim must be evaluated to ensure that the claim itself reflects the disclosed improvement. That is, the claim includes the components or steps of the invention that provide the improvement described in the specification.).
Applicant's arguments regarding the 35 U.S.C. 102/103 rejections of claims 1-20 have been fully considered but they are moot in light of the references being applied in the current rejection.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
As per claims 1, 10, and 17 (line numbers refer to claim 1):
Line 18 recites “a schedule planner service” and it is unclear if this refers to “a schedule planner service” in line 16.
Line 19 recites “workloads” and it is unclear if this refers to the unassigned workloads.
Line 19 recites “nodes” and it is unclear if this refers to “nodes” in line 4.
Claims 2-9, 11-16, and 18-20 are dependent claims of claims 1, 10, and 17, and fail to resolve the deficiencies of claims 1, 10, and 17, so they are rejected for the same reasons.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (abstract idea) without significantly more.
As per claim 1, in step 1 of the 101 analysis, the examiner has determined that the claim
is directed to a non-transitory computer-readable medium. Therefore, the claim is directed to one of the four statutory categories of invention.
In step 2A prong 1 of the 101 analysis, the examiner has determined that the claim recites
a judicial exception. Specifically, the limitations “responsive to a scheduling trigger, scheduling the unassigned workloads together as a pod set based on a scheduling plan, the scheduling plan considering one or more available resources on the nodes and a constraint policy for each of the unassigned workloads, wherein the scheduling plan corresponds to the pod set of the unassigned workloads, is generated prior to execution of the unassigned workloads on the nodes, and is generated using connectivity telemetry between the nodes to determine an optimized placement of the pod set across the nodes in a distributed computing environment comprising the nodes”, “to build the scheduling plan as a mapping of workloads to nodes”, and “wherein, responsive to the scheduling trigger, the workload orchestration system assigns each unassigned workload to a node specified by the SchedulePlan custom resource definition (CRD) object” is a mental process. Humans are capable of mentally determining which nodes to schedule the unassigned workloads to based on resources on the nodes and a constraint policy for each of the unassigned workloads. Humans can mentally associate the scheduling plan to a pod set. Humans can mentally generate the scheduling plan since humans can mentally determine which nodes to assign the unassigned workloads to. Humans can mentally analyze the connectivity telemetry to determine where to schedule the unassigned workloads. Building a scheduling plan is a mental process since humans can mentally map workloads to nodes. Assigning each unassigned workload to a specified node can be performed in the mind.
In step 2A prong 2 of the 101 analysis, the examiner has determined that the additional
elements, alone or in combination do not integrate the judicial exceptions into a practical
application for the following rationale:
The limitations "receiving unassigned workloads for assignment on nodes for execution", “wherein, prior to the scheduling trigger, returns an indication that no node is selected for each of the unassigned workloads, such that each of the unassigned workloads remains in a Pending, non-assigned state”, and “stores the scheduling plan in a SchedulePlan custom resource definition (CRD) object associated with the pod set” represent insignificant, extra-solution activities. The term "extra-solution activity" can be understood as "activities incidental to the primary process or product that are merely a nominal or tangential addition to the claim" (MPEP 2106.05(g)). The examiner has determined that the limitations "receiving unassigned workloads for assignment on nodes for execution", “wherein, prior to the scheduling trigger, returns an indication that no node is selected for each of the unassigned workloads, such that each of the unassigned workloads remains in a Pending, non-assigned state”, and “stores the scheduling plan in a SchedulePlan custom resource definition (CRD) object associated with the pod set” are directed to mere data gathering activities which is a category of insignificant extra-solution activities (MPEP 2106.05(g)).
The limitations "a non-transitory computer-readable medium comprising instructions that, when executed, cause a workload orchestration system including at least one processor to perform steps of ", “automatically”, “by the workload orchestration system”, “the workload orchestration system (i) invokes a schedule planner service”, and “invokes a schedule planner service” apply judicial exceptions on a generic computer. "Alappat 's rationale that an otherwise ineligible algorithm or software could be made patent-eligible by merely adding a generic computer to the claim was superseded by the Supreme Court's Bilski and Alice Corp. decisions" so therefore applying judicial exceptions on a non-transitory computer-readable medium, on a workload orchestration system, on a processor, automatically, by the workload orchestration system, and schedule planner service which are generic computers does not integrate the judicial exceptions into a practical application (MPEP 2106.05(b)).
In step 2B of the 101 analysis, the examiner has determined that the additional elements, alone or in combination do not recite significantly more than the abstract ideas identified above for the following rationale:
The limitations "receiving unassigned workloads for assignment on nodes for execution", “wherein, prior to the scheduling trigger, returns an indication that no node is selected for each of the unassigned workloads, such that each of the unassigned workloads remains in a Pending, non-assigned state”, and “stores the scheduling plan in a SchedulePlan custom resource definition (CRD) object associated with the pod set” represent insignificant, extra-solution activities. The limitations "receiving unassigned workloads for assignment on nodes for execution", “wherein, prior to the scheduling trigger, returns an indication that no node is selected for each of the unassigned workloads, such that each of the unassigned workloads remains in a Pending, non-assigned state”, and “stores the scheduling plan in a SchedulePlan custom resource definition (CRD) object associated with the pod set” are well-understood, routine, or conventional because they are directed to "receiving or transmitting data" or “storing and retrieving information in memory” (MPEP 2106.05(d)). This is an additional element that the courts have recognized as well understood, routine, or conventional (MPEP 2106.05(d)). The citation of court cases in the MPEP meets the Berkheimer evidentiary burden since citation of a court case in the MPEP is one of the 4 types of evidentiary support that can be used to prove that the additional elements are well-understood, routine, or conventional (see 125 USPQ2d 1649 Berkheimer v. HP, Inc.). Thus, the limitations do not amount to significantly more than the abstract idea.
The limitations "a non-transitory computer-readable medium comprising instructions that, when executed, cause a workload orchestration system including at least one processor to perform steps of ", “automatically”, “by the workload orchestration system”, “the workload orchestration system (i) invokes a schedule planner service”, and “invokes a schedule planner service” apply judicial exceptions on a generic computer and therefore do not provide significantly more.
As per claims 10 and 17, they are method and workload orchestration system claims of claim 1, so they are rejected for similar reasons.
As per claim 2 (and similarly for claims 11 and 18), it recites attributes of the technological environment that neither integrate the judicial exceptions into a practical application nor recite significantly more.
As per claim 3 (and similarly for claims 12 and 19), it recites attributes of the technological environment that neither integrate the judicial exceptions into a practical application nor recite significantly more.
As per claim 4 (and similarly for claims 13 and 20), it recites attributes of the technological environment that neither integrate the judicial exceptions into a practical application nor recite significantly more.
As per claim 5 (and similarly for claim 14), it recites attributes of the technological environment that neither integrate the judicial exceptions into a practical application nor recite significantly more.
As per claim 6 (and similarly for claim 15), it recites mental processes.
As per claim 7 (and similarly for claim 16), it recites attributes of the technological environment that neither integrate the judicial exceptions into a practical application nor recite significantly more.
As per claim 8, it recites attributes of the technological environment that neither integrate the judicial exceptions into a practical application nor recite significantly more.
As per claim 9, it recites attributes of the technological environment that neither integrate the judicial exceptions into a practical application nor recite significantly more.
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.
Claims 1-3, 6, 7, 9-12, and 15-19 are rejected under 35 U.S.C. 103 as being unpatentable over Zhou (CN109117265A), in view of Dageville et al. (US 20040187131 A1 hereinafter Dageville), in view of Zhao (CN113760549A), and further in view of Denneman et al. (US 20230035310 A1 hereinafter Denneman).
The portions from Zhou are from a translation of CN109117265A.
The portions from Zhao are from a translation of CN113760549A.
Zhou was cited in a prior office action.
As per claim 1, Zhou teaches a non-transitory computer-readable medium comprising instructions that, when executed, cause a workload orchestration system including at least one processor to perform steps of ([0093] A computer-readable storage medium stores a computer program, which implements the above method when executed by a processor; More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM); [0166-0168] the device 200 for scheduling jobs in a cluster includes…The scheduling unit 220 is used to select one or more target nodes from the cluster according to the node scheduling conditions in the Pod data and the node status of each node in the cluster.): receiving unassigned workloads for assignment on nodes for execution; and responsive to a scheduling trigger, scheduling the unassigned workloads together as a pod set based on a scheduling plan, the scheduling plan considering one or more available resources on the nodes and a constraint policy for each of the unassigned workloads, wherein the scheduling plan corresponds to the pod set of the unassigned workloads, is generated prior to execution of the unassigned workloads on the nodes, and is automatically generated by the workload orchestration system using connectivity telemetry between the nodes to determine an optimized placement of the pod set across the nodes in a distributed computing environment comprising the nodes ([0088] the scheduling unit is further used to monitor whether there are any Pods in the cluster that have not been successfully scheduled, and if so, further determine whether there are scalable nodes; if so, start at least some of the scalable nodes and schedule the Pods that have not been successfully scheduled to the newly started nodes; [0143] For example, the Pod requires a memory lower limit of 1024MB, which means that if 1024MB of memory is not provided, the job cannot be performed. However, if the node can provide 2048MB of memory as the lower limit of schedulable resources, the job can obviously be scheduled to the node; [0142] This embodiment provides a resource-based scheduling method, that is, the Pod can set request conditions for the CPU and memory, specifically including a resource request upper limit and a resource request lower limit; [0034-0035] Calculate the upper and lower limits of schedulable resources for each computing resource based on the Pods deployed in each node; When the resource request lower limits of the computing resources in the node scheduling conditions are all less than or equal to the schedulable resource lower limits of the corresponding computing resources, one or more target nodes are selected from the cluster; [0009-0012] A method for scheduling jobs in a cluster, comprising: Get the container pod data corresponding to the job; Select one or more target nodes from the cluster according to the node scheduling conditions in the Pod data and the node status of each node in the cluster; Pods are deployed on each target node according to the Pod data, and the job process of the job is run in the deployed Pods; [0146] CPU can dynamically adjust its usage and is a compressible resource; [0169] The Pod deployment unit 230 is used to deploy Pods on each target node according to the Pod data, and run the job process of the job in the deployed Pods; [0117] In this embodiment, a job scheduling idea is provided, that is, multiple instances (i.e., Pods) of a job (a job here means an application or a service, such as a log collector) are deployed in an AZ (Availability Zone), that is, each instance of a single application is affinity at the AZ level. An availability zone refers to one or more data centers; [0081] The scheduling unit is used to calculate the schedulable resource upper limit and the schedulable resource lower limit of each computing resource according to the Pods deployed in each node; when the resource request lower limit of each computing resource in the node scheduling condition is less than or equal to the schedulable resource lower limit of the corresponding computing resource, select one or more target nodes from the cluster; [0087] the scheduling unit is used to obtain the CPU utilization of each Pod deployed; [0125] For example, the business has a high affinity with the jobs corresponding to monitoring log processing and local data. If the Pods where they are located are far away, the network overhead of access will cause inefficiency. Therefore, in this embodiment, the proximity deployment of affinity applications is actually provided, for example, deployment in the same node, which naturally reduces network overhead. The scheduling trigger is determining that there are scalable nodes and starting the scalable nodes.).
Zhou fails to teach wherein, prior to the scheduling trigger, the workload orchestration system (i) invokes a schedule planner service that returns an indication that no node is selected for each of the unassigned workloads, such that each of the unassigned workloads remains in a Pending, non-assigned state, (ii) invokes a schedule planner service to build the scheduling plan as a mapping of workloads to nodes, and (iii) stores the scheduling plan in a SchedulePlan custom resource definition (CRD) object associated with the pod set, and wherein, responsive to the scheduling trigger, the workload orchestration system assigns each unassigned workload to a node specified by the SchedulePlan custom resource definition (CRD) object.
However, Dageville teaches wherein, prior to the scheduling trigger, the workload orchestration system (i) invokes a schedule planner service that returns an indication that no node is selected for each of the unassigned workloads, such that each of the unassigned workloads remains in a Pending, non-assigned state ([0067] At step 824, it is determined whether there are any unassigned work granules that have no particular affinity for the node of the slave process. If there are unassigned work granules that have no particular affinity, then control passes to step 828. At step 828, an unassigned work granule is assigned from a list for work granules with no affinity for a particular node; [0029] Database system 100 includes three interconnected nodes 102, 110 and 112. node 102 is connected to disks 106 and is executing a coordinator process 104; [0030] Coordinator process 104 participates in the management of tasks executed in parallel for database system 100. In particular, coordinator process 104 divides each task into work granules, and distributes the work granules to slave processes that may be executing on either of nodes 102, 110, and 112).
It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to have combined Zhou with the teachings of Dageville to improve performance (see Dageville [0069] Overall system performance is improved, and workload skew is reduced.).
Zhou and Dageville fail to teach wherein, prior to the scheduling trigger, the workload orchestration system (ii) invokes a schedule planner service to build the scheduling plan as a mapping of workloads to nodes, and (iii) stores the scheduling plan in a SchedulePlan custom resource definition (CRD) object associated with the pod set, and wherein, responsive to the scheduling trigger, the workload orchestration system assigns each unassigned workload to a node specified by the SchedulePlan custom resource definition (CRD) object.
However, Zhao teaches wherein, prior to the scheduling trigger, the workload orchestration system (ii) invokes a schedule planner service to build the scheduling plan as a mapping of workloads to nodes ([0083] In another example, when the management node selects a business node for the first pod based on the load of each business node, it can select a business node for the first pod based on the load of each business node monitored multiple times within a set period before the first pod is determined to be created (or before the first pod is scheduled from the pod list).).
It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to have combined Zhou and Dageville with the teachings of Zhao to promote efficiency (see Zhao [0015] improving the scheduling efficiency of pod creation tasks.).
Zhou, Dageville, and Zhao fail to teach wherein, prior to the scheduling trigger, the workload orchestration system (iii) stores the scheduling plan in a SchedulePlan custom resource definition (CRD) object associated with the pod set, and wherein, responsive to the scheduling trigger, the workload orchestration system assigns each unassigned workload to a node specified by the SchedulePlan custom resource definition (CRD) object.
However, Denneman teaches wherein, prior to the scheduling trigger, the workload orchestration system (iii) stores the scheduling plan in a SchedulePlan custom resource definition (CRD) object associated with the pod set, and wherein, responsive to the scheduling trigger, the workload orchestration system assigns each unassigned workload to a node specified by the SchedulePlan custom resource definition (CRD) object (Fig. 33; [0116] The ML_CRD allows workload specifications to include a requirement for access to a GPU and/or other hardware accelerator and to specify the desM metric; [0115] Comparison of the available metric to the desired metric can be used to determine whether or not a particular machine-learning-based application instance that requires hardware accelerators can be confidently deployed on a particular computational node to avoid premature termination during a training phase for these more complex cases. For simplicity, in the following discussion, the metrics are generalized as availM and desM; [0117] In a first step 3302, a user prepares a workload specification for an ML workload that includes ML_CRD fields describing requirements for one or more hardware accelerators and one or more desM metric values. The workload specification may specify one or more application instances for which deployment is requested by the user. The workload specification is part of a manifest 3303 that is submitted to the API Server 3304; [0117] The response directs the Kubernetes API server to alter the originally submitted manifest in accordance with the node-affinity specification. In essence, the altered manifest now contains information that will allow the Kubernetes scheduler to select appropriate computational nodes for executing the specified workload in accordance with the information provided in the ML_CRD fields.).
It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to have combined Zhou, Dageville, and Zhao with the teachings of Denneman to promote efficiency (see Denneman [0005] facilitate efficient deployment of machine-learning-based applications with hardware dependencies.).
As per claim 2, Zhou, Dageville, Zhao, and Denneman teach the non-transitory computer-readable medium of claim 1. Zhou teaches wherein the workload orchestration system utilizes Kubernetes and the one or more workloads are pods in Kubernetes ([0168] The scheduling unit 220 is used to select one or more target nodes from the cluster according to the node scheduling conditions in the Pod data and the node status of each node in the cluster; A pod is the smallest deployable unit in Kubernetes, so Zhou does teach that the workload orchestration system utilizes Kubernetes and the one or more workloads are pods in Kubernetes.).
As per claim 3, Zhou, Dageville, Zhao, and Denneman teach the non-transitory computer-readable medium of claim 1. Zhou teaches wherein the unassigned workloads include any of new workloads and evicted workloads based on their constraint policy ([0107] The Pod data of new jobs and the Pod data of killed Pods can be saved in etcd and obtained when scheduling the corresponding jobs; [0083] The scheduling unit is used to kill or block the deployed Pod according to the job priority, or terminate the current job scheduling when the resource request lower limit in the node scheduling condition is greater than the schedulable resource lower limit; [0179] kill or block the deployed Pod according to the job priority when the resource request lower limit in the node scheduling condition is greater than the schedulable resource lower limit, or terminate the current job scheduling.).
As per claim 6, Zhou, Dageville, Zhao, and Denneman teach the non-transitory computer-readable medium of claim 1. Zhou teaches wherein the steps further include associating the constraint policy to a workload of the unassigned workload being managed by the workload orchestration system ([0142] the Pod can set request conditions for the CPU and memory, specifically including a resource request upper limit and a resource request lower limit; [0049] Monitor whether there are any Pods in the cluster that have not been successfully scheduled); subsequent to the scheduling and implementation of the workload, tracking compliance of the workload to the constraint policy; and responsive to a violation of the compliance, performing one or more of ignoring the violation, mediating the violation to meet the compliance, and evicting the workload to restart the workload ([0086] the scheduling unit is further used to calculate the memory usage score of each job process, and kill the job process when the calculated memory usage score reaches a preset value corresponding to the job process; [0149] A container can get the requested amount of memory resources. If the memory resource request is exceeded, the container will be killed (when other containers need memory), but if the resources consumed by the container are less than the resource request lower limit, it will not be killed; [0083] The scheduling unit is used to kill or block the deployed Pod according to the job priority, or terminate the current job scheduling when the resource request lower limit in the node scheduling condition is greater than the schedulable resource lower limit; [0162] This embodiment provides a solution for Pods that are not successfully scheduled, that is, to meet the demand by expanding the capacity of the nodes in the cluster, because not all nodes in the cluster are necessarily in the started state. For example, the capacity expansion component is used to implement it. The capacity expansion component creates a monitor for all pods. It checks every 10 seconds whether there are any pods that cannot be scheduled. Generally, the pod will fall into an unschedulable state because there are no nodes that can be scheduled. Pods that cannot be scheduled will have their PodCondition (status) monitored as unscheduled. If this happens, the expansion component will find a new node to schedule.).
As per claim 7, Zhou, Dageville, Zhao, and Denneman teach the non-transitory computer-readable medium of claim 6. Zhou teaches wherein the constraint policy includes one or more constraint rules ([0143] For example, the Pod requires a memory lower limit of 1024MB, which means that if 1024MB of memory is not provided, the job cannot be performed. However, if the node can provide 2048MB of memory as the lower limit of schedulable resources, the job can obviously be scheduled to the node; [0142] the Pod can set request conditions for the CPU and memory, specifically including a resource request upper limit and a resource request lower limit.).
As per claim 9, Zhou, Dageville, Zhao, and Denneman teach the non-transitory computer-readable medium of claim 7. Zhou teaches wherein the one or more constraint rules include a name, a requested value, and a limit value ([0143] For example, the Pod requires a memory lower limit of 1024MB; [0142] the Pod can set request conditions for the CPU and memory, specifically including a resource request upper limit and a resource request lower limit).
As per claims 10, 11, 12, 15, and 16, they are method claims of claims 1, 2, 3, 6, and 7, so they are rejected for similar reasons.
As per claims 17, 18, and 19, they are workload orchestration system claims of claims 1, 2, and 3, so they are rejected for similar reasons.
Claims 4, 13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zhou, Dageville, Zhao, and Denneman, as applied to claims 1, 10, and 17 above, in view of Vasamsetti et al. (US 11843545 B1 hereinafter Vasamsetti).
Vasamsetti was cited in a prior office action.
As per claim 4, Zhou, Dageville, Zhao, and Denneman teach the non-transitory computer-readable medium of claim 1.
Zhou, Dageville, Zhao, and Denneman fail to teach wherein the scheduling trigger includes expiration of an amount of time where no additional unassigned workloads are received.
However, Vasamsetti teaches wherein the scheduling trigger includes expiration of an amount of time where no additional unassigned workloads are received (Col. 13 line 67-Col. 14 line 3 continuously add resources (e.g., pods) until either a timer associated with the flag expires and/or the maximum number of resources have been allocated to the application service.).
It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to have combined Zhou, Dageville, Zhao, and Denneman with the teachings of Vasamsetti to prevent instability (see Vasamsetti Col. 11 lines 2-5 a threshold (e.g., utilization, availability, etc.) for a compute resource such as CPU, memory, or storage may help identify and avoid current or prospective application instability).
As per claims 13 and 20, they are method and workload orchestration system claims of clam 4, so they are rejected for similar reasons.
Claims 5 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Zhou, Dageville, Zhao, and Denneman, as applied to claims 1 and 10 above, in view of Wang et al. (US2024086225A1 hereinafter Wang).
Wang was cited in a prior office action.
As per claim 5, Zhou, Dageville, Zhao, and Denneman teach the non-transitory computer-readable medium of claim 1.
Zhou, Dageville, Zhao, and Denneman fail to teach wherein the constraint policy of at least two of the unassigned workloads includes a shared constraint.
However, Wang teaches wherein the constraint policy of at least two of the unassigned workloads includes a shared constraint ([0046] It should be noted that, an equivalence class can be used to describe a type of pods that have the same scheduling rule constraint and resource specifications requirement…In other words, for one equivalence class, schedulable nodes of all pods belonging to the equivalence class are basically the same.).
It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to have combined Zhou, Dageville, Zhao, and Denneman with the teachings of Wang to improve efficiency (see Wang [0028] In related technologies, for each to-be-scheduled pod, an equivalence class of the pod is first determined, and then it is determined whether a correspondence between the equivalence class and a schedulable node is stored to improve pod scheduling efficiency and shorten a pod scheduling delay.).
As per claim 14, it is a method claim of claim 5, so it is rejected for similar reasons.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Zhou, Dageville, Zhao, and Denneman, as applied to claim 1 above, in view of Bai et al. (US 20230004436 A1 hereinafter Bai).
Bai was cited in a prior office action.
As per claim 8, Zhou, Dageville, Zhao, and Denneman teach the non-transitory computer-readable medium of claim 7.
Zhou, Dageville, Zhao, and Denneman fail to teach wherein the one or more constraint rules include at least one network connectivity constraints including any of bandwidth, latency, and jitter.
However, Bai teaches wherein the one or more constraint rules include at least one network connectivity constraints including any of bandwidth, latency, and jitter ([0054] . For example, the Pod mode can comprise at least one of a mirror image of a container comprised in the Pod, a corresponding specification of the mirror image, a corresponding service name, or the number of replicas. The specification can comprise hardware resource configuration information required for the mirror image, such as the number of CPU (Central Processing Unit) cores, memory capacity, network bandwidth; [0111] the Pod replicas are all allocated onto physical hosts with high bandwidth networks to ensure high concurrent access to the networks.).
It would have been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to have combined Zhou, Dageville, Zhao, and Denneman with the teachings of Bai to ensure high concurrent access to networks (see Bai [0111] the Pod replicas are all allocated onto physical hosts with high bandwidth networks to ensure high concurrent access to the networks).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HSING CHUN LIN whose telephone number is (571)272-8522. The examiner can normally be reached Mon - Fri 9AM-5PM.
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, Aimee Li can be reached at (571) 272-4169. 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.
/H.L./Examiner, Art Unit 2195
/APRIL Y BLAIR/Supervisory Patent Examiner, Art Unit 2196
Prosecution Insights