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 .
Claims 1, 3-7, 9-20 are pending.
This is in response to communications filed on 10/15/25.
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(s) 1, 4-5, 7, 9-10, 12, 14-15, 17-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over CN110851529 (Cited in IDS and the machine translation is provided) and further in view of Campbell et al (US Patent 11,265,369).
For claim 1, CN110851529 teaches the following limitations: A computing power request method (page 4; Fig 3 and associated description - S301: receive a computing power request that is sent by a terminal device), performed by a terminal (Fig 1; terminal device 1 – N; page 1 summary of the disclosure – computing power request sent by the terminal device; thus terminal device performs the power request method) and comprising: sending a computing power request to a network side device (page 3; “DETAILED DESCRIPTION OF THE EMBODIMENTS” – the terminal may send a computing power request for requesting computing power to the computing power scheduling platform; Page 9 Fig 6 description – the computing power scheduling apparatus 60 includes a first receiving unit 601 configured to receive a computing power request that is sent by a terminal device), wherein the computing power request is used to request computing power for a computing power task in the terminal (Page 4; Fig 3 and associated description - S301: receive a computing power request that is sent by a terminal device ad that is used to request a computing power where the computing power request includes computing power requirement information of the terminal device – computing power requirement refers to computing power for computing task); (Page 4: Fig 3 and associated description - S302: determine, based on the computing power requirement information, a target edge computing device that provides computing power for the terminal device… determining at least two edge computing devices may provide computing power that meets the computing power requirement information for the terminal device – thus the edge devices include device with a computing power capability); (Page 4; Fig 3 and associated description - S301: receive a computing power request that is sent by a terminal device ad that is used to request a computing power where the computing power request includes computing power requirement information of the terminal device – computing power requirement refers to computing power for computing task), wherein the computing power requirement information is used for determining a target computing power device that matches a computing power requirement (Page 2 – a determining unit configured to determine according to the computing power requirement information a target computing device that provides computing power; Page 4: Fig 3 and associated description - S302: determine, based on the computing power requirement information, a target edge computing device that provides computing power for the terminal device… determining at least two edge computing devices may provide computing power that meets the computing power requirement information for the terminal device) and the computing power requirement information comprises at least one of the following: a total amount of computing power required for the computing power task,
CN110851529 does not explicitly teach the following limitations:
receiving device information of a target computing power device responded by the network side device,
and sending the computing power task to the target computing power device based on the device information, so that the target computing power device executes the computing power task
the total amount of computing power required for the computing power task is a total quantity of CPUs, GPUs or servers required for the computing power task
Campbell et al teach the following limitations:
receiving device information of a target computing power device (node 204 in Fig 3 is the target computing power device; lines 1-28 of col 17 mentions how 204 is selected) responded by the network side device (100 is the network side device; lines 43-60 of col 5 mention that processing facility 104 (part of device 100 as shown in Fig 1) selects an edge compute node in response task assignment request in an optimal manner; lines 1-20 of col 20 mention that operation 5 in Fig 3 shows UE 206 (terminal device) receives the 204’s device information (i.e. target computing device) from 100 (i.e., network side device))
and sending the computing power task to the target computing power device based on the device information, so that the target computing power device executes the computing power task (Fig 3; operation 6; UE sends task to node 204; lines 1-20 of col 20 – task is carried out by node 204)
sending computing power requirement information of the computing power task (Fig 5 shows the task parameters which includes computing power requirement information because latency and processing performance have associated power requirements; these task parameters are sent to 100 of Fig 3; lines 13-16 of col 16) to the network side device (lines 5-15 of col 17 mention that task performance parameters may be represented by task assignment request; lines 13-16 of col 16 further mentions that parameters are provided to system 100 as part of data making up the task assignment request received in operation 1; thus 100 receives the task performance parameters which include the computing power requirement information) wherein the computing power requirement information is used for determining a target computing power device that matches a computing power requirement (lines 5-32 of col 17; final node selection is performed that the node is capable of performing the task in accordance with the identified set of performance parameters) and the computing power requirement information comprises at least one of the following: an expected completing time period of the computing power task (lines 40-60 of col 15 amount of latency that the application can bear for a task), a total quantity of processors/servers required for the computing power task (lines 40-60 of col 15 – number of virtual processors; virtual processors represents virtual CPUs).
It would have been obvious for one ordinary skill in the art before the effective filing date of the invention to combine the teachings of CN110851529 and Campbell et al so that the task is offloaded to the node that has the computing power to execute the task. That way, the terminal device can have less stress on the battery. As Campbell mentions in lines 60-67 of col 10 that application 320 can offload tasks so as to use less battery power of the UE device 206 and in lines 1-8 of col 3 that UE devices cannot have unlimited power, it is more efficient to offload the tasks when terminal device does not have enough power. Campbell selects nodes (lines 20-50 of col 17) that can meet the task performance requirements. Latency requirements are important because that is the indication of a system performance. Therefore, as shown in Campbell, when the power request is made to the network side device, the power requirement information including expected completion period (i.e., latency requirement) can be sent so that the node selection can be appropriately performed.
For claim 4, Campbell teaches the following limitations: wherein the device information comprises at least one of the following: device address information or a device identifier (lines 1-20 of col 20 – which node has been designated to perform the task – which node refers to “device identifier”) ; and the sending the computing power task to the target computing power device based on the device information comprises: establishing a connection with the target computing power device based on at least one of the device address information or the device identifier (operation 6 in Fig 3 shows that the connection is established between 206 and 204; lines 1-20 of col 20 mention so that UE device 206 may provide the task to the node 204 as shown by operation 6); and sending the computing power task to the target computing power device in a case that the connection is successfully established (lines 1-20 of col 20; task is carried out by node 204).
For claim 5, Campbell teaches wherein a quantity of target computing power devices is one, wherein in a case that the quantity of target computing power devices is one, the target computing power device is configured to independently execute the computing power task (lines 25-40 of col 3; one node is selected to perform the task; the claim has multiple alternative embodiments and one embodiment is examined).
For claim 7, CN110851529 teaches the following limitations: A computing power allocation method (Page 1; target edge computing device provides power for the terminal device), performed by a network side device (Page 9 Fig 6 description – the computing power scheduling apparatus 60 (i.e., the network side device) includes a first receiving unit 601 configured to receive a computing power request that is sent by a terminal device) and comprising: receiving a computing power request from a terminal (page 3; “DETAILED DESCRIPTION OF THE EMBODIMENTS” – the terminal may send a computing power request for requesting computing power to the computing power scheduling platform; Page 9 Fig 6 description – the computing power scheduling apparatus 60 includes a first receiving unit 601 configured to receive a computing power request that is sent by a terminal device), wherein the computing power request is used to request computing power for a computing power task in the terminal (Page 4; Fig 3 and associated description - S301: receive a computing power request that is sent by a terminal device ad that is used to request a computing power where the computing power request includes computing power requirement information of the terminal device – computing power requirement refers to computing power for computing task); determining a target computing power device based on the computing power request, wherein the target computing power device comprises a device or device cluster with a computing power capability (Page 4: Fig 3 and associated description - S302: determine, based on the computing power requirement information, a target edge computing device that provides computing power for the terminal device… determining at least two edge computing devices may provide computing power that meets the computing power requirement information for the terminal device – thus the edge devices include device with a computing power capability); (Page 4; Fig 3 and associated description - S301: receive a computing power request that is sent by a terminal device and that is used to request a computing power where the computing power request includes computing power requirement information of the terminal device – computing power requirement refers to computing power for computing task), wherein the computing power requirement information is used for determining a target computing power device that matches a computing power requirement (Page 2 – a determining unit configured to determine according to the computing power requirement information a target computing device that provides computing power; Page 4: Fig 3 and associated description - S302: determine, based on the computing power requirement information, a target edge computing device that provides computing power for the terminal device… determining at least two edge computing devices may provide computing power that meets the computing power requirement information for the terminal device) and the computing power requirement information comprises at least one of the following: a total amount of computing power required for the computing power task,
CN110851529 does not explicitly teach the following limitations:
sending device information of the target computing power device to the terminal, so that the terminal sends the computing power task to the target computing power device based on the device information, and the target computing power device executes the computing power task.
the total amount of computing power required for the computing power task is a total quantity of CPUs, GPUs or servers required for the computing power task
Campbell et al teach the following limitations:
sending device information of a target computing power device (node 204 in Fig 3 is the target computing power device; lines 1-28 of col 17 mentions how 204 is selected) to the terminal (operation 5 shown in Fig 3; lines 1-20 of col 20 – which node has been designated; UE 206 is the terminal)
so that the terminal sends the computing power task to the target computing power device based on the device information, so that the target computing power device executes the computing power task (Fig 3; operation 6; UE sends task to node 204; lines 1-20 of col 20 – task is carried out by node 204).
receiving computing power requirement information of the computing power task (Fig 5 shows the task parameters which includes computing power requirement information because latency and processing performance have associated power requirements; these task parameters are sent to 100 of Fig 3; lines 13-16 of col 16) from the terminal (lines 5-15 of col 17 mention that task performance parameters may be represented by task assignment request; lines 13-16 of col 16 further mentions that parameters are provided to system 100 as part of data making up the task assignment request received in operation 1; thus 100 receives the task performance parameters which include the computing power requirement information from the UE device) wherein the computing power requirement information is used for determining a target computing power device that matches a computing power requirement (lines 5-32 of col 17; final node selection is performed that the node is capable of performing the task in accordance with the identified set of performance parameters) and the computing power requirement information comprises at least one of the following: an expected completing time period of the computing power task (lines 40-60 of col 15 amount of latency that the application can bear for a task), a total quantity of CPUs/servers required for the computing power task (lines 40-60 of col 15 – number of virtual processors; virtual processors represents virtual CPUs).
It would have been obvious for one ordinary skill in the art before the effective filing date of the invention to combine the teachings of CN110851529 and Campbell et al so that the task is offloaded to the node that has the computing power to execute the task. That way, the terminal device can have less stress on the battery. As Campbell mentions in lines 60-67 of col 10 that application 320 can offload tasks so as to use less battery power of the UE device 206 and in lines 1-8 of col 3 that UE devices cannot have unlimited power, it is more efficient to offload the tasks when terminal device does not have enough power. Campbell selects nodes (lines 20-50 of col 17) that can meet the task performance requirements. Latency requirements are important because that is the indication of a system performance. Therefore, as shown in Campbell, when the power request is made to the network side device, the power requirement information including expected completion period (i.e., latency requirement) can be sent so that the node selection can be appropriately performed.
For claim 9, CN110851529 teaches the following limitations: the determining a target computing power device based on the computing power request comprises at least one of the following: determining the target computing power device based on the computing power requirement information in a case that the computing power request comprises the computing power requirement information (Page 4; Fig 3 and associated description - S301: receive a computing power request that is sent by a terminal device and that is used to request a computing power where the computing power request includes computing power requirement information of the terminal device – computing power requirement refers to computing power for computing task; Page 4: Fig 3 and associated description - S302: determine, based on the computing power requirement information, a target edge computing device that provides computing power for the terminal device… determining at least two edge computing devices may provide computing power that meets the computing power requirement information for the terminal device).
For claim 10, CN110851529 teaches the following limitations: wherein the determining the target computing power device based on the computing power requirement information comprises: obtaining computing power state information of a plurality of computing power devices in advance, wherein the computing power state information comprises at least one of the following: a total amount of computing power, a usage amount of computing power, a type of computing power, or available computing power (Page 1 determining at least two edge computing devices, the remaining computing power sizes – which is available computing power; thus the power state information (i.e., available power) is obtained for at least two edge devices); matching the computing power requirement information with the computing power state information of the plurality of computing power devices (Page 1 determining at least two edge computing devices, the remaining computing power sizes being greater than or equal to the computing power size requested by the terminal device), and determining at least one matched candidate computing power device; and determining the target computing power device based on the at least one candidate computing power device (Page 2, first two lines – selecting the target from the at least two edge computing devices).
For claim 12, Campbell teaches wherein a quantity of target computing power devices is one, wherein in a case that the quantity of target computing power devices is one, the target computing power device is configured to independently execute the computing power task (lines 25-40 of col 3; one node is selected to perform the task; the claim has multiple alternative embodiments and one embodiment is examined).
For claim 14, CN110851529 teaches the following limitations: A computing power execution method, performed by a target computing power device (Page 1; target edge computing device provides power for the terminal device) and comprising: Page 4: Fig 3 and associated description - S302: determine, based on the computing power requirement information, a target edge computing device that provides computing power for the terminal device) after receiving a computing power request from the terminal (Page 9 Fig 6 description – the computing power scheduling apparatus 60 (i.e., the network side device) includes a first receiving unit 601 configured to receive a computing power request that is sent by a terminal device) and determining the target computing power device (Page 4: Fig 3 and associated description - S302: determine, based on the computing power requirement information, a target edge computing device that provides computing power for the terminal device… determining at least two edge computing devices may provide computing power that meets the computing power requirement information for the terminal device), the computing power request is used to request computing power for the computing power task in the terminal (Page 4; Fig 3 and associated description - S301: receive a computing power request that is sent by a terminal device ad that is used to request a computing power where the computing power request includes computing power requirement information of the terminal device – computing power requirement refers to computing power for computing task), and the target computing power device comprises a device or device cluster with a computing power capability (Page 4: Fig 3 and associated description - S302: determine, based on the computing power requirement information, a target edge computing device that provides computing power for the terminal device… determining at least two edge computing devices may provide computing power that meets the computing power requirement information for the terminal device – thus the edge devices include device with a computing power capability)(Page 4; Fig 3 and associated description - S301: receive a computing power request that is sent by a terminal device ad that is used to request a computing power where the computing power request includes computing power requirement information of the terminal device – computing power requirement refers to computing power for computing task), wherein the computing power requirement information is used for determining a target computing power device that matches a computing power requirement (Page 2 – a determining unit configured to determine according to the computing power requirement information a target computing device that provides computing power; Page 4: Fig 3 and associated description - S302: determine, based on the computing power requirement information, a target edge computing device that provides computing power for the terminal device… determining at least two edge computing devices may provide computing power that meets the computing power requirement information for the terminal device) and the computing power requirement information comprises at least one of the following: a total amount of computing power required for the computing power task,
CN110851529 does not explicitly teach the following limitations:
the target computing power device receiving a computing power task from a terminal, wherein the computing power task is sent by the terminal based on device information of the target computing power device, the device information is responded to the terminal by a network side device
and executing the computing power task by the target computing power device
the total amount of computing power required for the computing power task is a total quantity of CPUs, GPUs or servers required for the computing power task
Campbell et al teach the following limitations:
the target computing power device receiving a computing power task from a terminal, wherein the computing power task is sent by the terminal based on device information of the target computing power device, the device information is responded to the terminal by a network side device (node 204 in Fig 3 is the target computing power device; lines 1-28 of col 17 mentions how 204 is selected and operation 5 shown in Fig 3; lines 1-20 of col 20 – which node has been designated; UE 206 is the terminal; operation 6 in Fig 3 shows task offloading from 206 to 204 based on the device information sent from 100 to terminal 206 in operation 5)
the target computing power device executing the computing power task (Fig 3; operation 6; UE sends task to node 204; lines 1-20 of col 20 – task is carried out by node 204)
computing power requirement information of the computing power task (Fig 5 shows the task parameters which includes computing power requirement information because latency and processing performance have associated power requirements; these task parameters are sent to 100 of Fig 3; lines 13-16 of col 16; lines 5-15 of col 17 mention that task performance parameters may be represented by task assignment request; lines 13-16 of col 16 further mentions that parameters are provided to system 100 as part of data making up the task assignment request received in operation 1; thus 100 receives the task performance parameters which include the computing power requirement information) wherein the computing power requirement information is used for determining a target computing power device that matches a computing power requirement (lines 5-32 of col 17; final node selection is performed that the node is capable of performing the task in accordance with the identified set of performance parameters) and the computing power requirement information comprises at least one of the following: an expected completing time period of the computing power task (lines 40-60 of col 15 amount of latency that the application can bear for a task), a total quantity of CPUs/GPUs/servers required for the computing power task (lines 40-60 of col 15 – number of virtual processors; virtual processors represents virtual CPUs).
It would have been obvious for one ordinary skill in the art before the effective filing date of the invention to combine the teachings of CN110851529 and Campbell et al so that the task is offloaded to the node that has the computing power to execute the task. That way, the terminal device can have less stress on the battery. As Campbell mentions in lines 60-67 of col 10 that application 320 can offload tasks so as to use less battery power of the UE device 206 and in lines 1-8 of col 3 that UE devices cannot have unlimited power, it is more efficient to offload the tasks when terminal device does not have enough power. Campbell selects nodes (lines 20-50 of col 17) that can meet the task performance requirements. Latency requirements are important because that is the indication of a system performance. Therefore, as shown in Campbell, when the power request is made to the network side device, the power requirement information including expected completion period (i.e., latency requirement) can be sent so that the node selection can be appropriately performed.
For claim 15, Campbell teaches wherein a quantity of target computing power devices is one, wherein in a case that the quantity of target computing power devices is one, the target computing power device is configured to independently execute the computing power task (lines 25-40 of col 3; one node is selected to perform the task; the claim has multiple alternative embodiments and one embodiment is examined).
For claim 17, CN110851529 page 10-11 and Campbell Fig 8 shows the hardware to implement the method of claim 1. The terminal is terminal device 1 – N in CN110851529 and UE devices shown in Fig 2 – Fig 3 in Campbell.
For claim 18, CN110851529 page 10-11 and Campbell Fig 8 shows the hardware to implement the method of claim 7. The network side device is the computing power scheduling apparatus 60 in CN110851529 (page 9 Fig 6) and 100 shown in Fig 1 – Fig 2 in Campbell.
For claim 19, CN110851529 page 10-11 and Campbell Fig 8 shows the hardware to implement the method of claim 14. The target computing power device is the target edge computing device in CN110851529 (page 1) and node 204 in Campbell.
For claim 20, CN110851529 page 11 and Campbell col 21-22 mention the CRM to implement the method.
Claim(s) 3, 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over CN110851529 (Cited in IDS and the machine translation is provided) and further in view of Campbell et al (US Patent 11,265,369), further in view of Ljubuncic et al (US Patent Application Publication 2016/0162004).
For claim 3, cited art does not explicitly mention whether the target application sends power request to the terminal. Ljubuncic et al teach wherein before the sending a computing power request to a network side device, the method further comprises: sending, by a target application in the terminal, the computing power request to the terminal (Fig 3; [0025][0029]-[0030]; receive and execute tasks; thus the tasks provide the request to the OS of the device to be executed; [0025] mentions the determination of the power requirement of the task to be offloaded); and in a case that the computing power request sent by the target application comprises the computing power task description information (conditional limitation and BRI does not include the steps corresponding to conditional limitations; however, [0025] mentions power requirement calculation using OS metrics associated with the task), and the computing power request sent by the terminal comprises the computing power requirement information ([0025] task request broadcast includes requirement), the method further comprises: determining the computing power requirement information based on the computing power task description information ([0025] mentions power requirement calculation using OS metrics associated with the task); and sending the computing power requirement information to the network side device ([0025]; also taught by CN110851529 - Page 4; Fig 3 and associated description - S301: receive a computing power request that is sent by a terminal device ad that is used to request a computing power where the computing power request includes computing power requirement information of the terminal device – computing power requirement refers to computing power for computing task).
It would have been obvious for one ordinary skill in the art before the effective filing date of the invention to send the power request by an application to the terminal and determine the power requirement based on the power task description, since that way operating system can accurately determine the needed power for the task. When the accurate power information can be determined, the offloading will be more optimal and effective.
For claim 11, cited art does not explicitly mention reservation request to the candidate computing device and the success information responded by the candidate computing power device. Ljubuncic et al teach sending a reservation request and reservation success information responded by candidate device (step 502, step 514 and step 516 in Fig 5). It would have been obvious for one ordinary skill in the art before the effective filing date of the invention to send the reservation request to the candidate device and receive a success message from the device, since that way the guaranteed operation has been achieved. (BRI does not include alternative limitations – “sending a computing power reservation request … based on a descending order of a priority of a computing power device”).
Claim(s) 6, 13, 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over CN110851529 (Cited in IDS and the machine translation is provided) and further in view of Campbell et al (US Patent 11,265,369), further in view of Subramaniam (US Patent Application Publication 2020/0133531).
For claim 6, cited art does not explicitly mention about receiving results from the target computing power device (Campbell mentions transmitting data back to UE device 206 in line 62, col 17). Subramaniam teaches the following limitations: after the sending the computing power task to the target computing power device (Fig 3; 110 offloads the computational task to 231 (step 330), the method further comprises: receiving a computing power task execution result responded by the target computing power device (step 345 of Fig 3; transmits results of computational operation); and sending notification information to the network side device in a case of determining that the computing power task execution result meets a preset condition or determining, based on the computing power task execution result, that execution of the computing power task succeeds, wherein the notification information is used by the network side device to release computing power reserved for the computing power task (two distinct embodiments alternatively with “or” and the first embodiment is examined; [0071] mentions offloading additional operations via controller 230 in response to results of the operations; thus when the results meet a condition (i.e., flag/address set as mentioned in [0071]) the sending device 110 sends notification for additional processing to controller 230).
It would have been obvious for one ordinary skill in the art before the effective filing date of the invention to send the notification and result to the network side device and terminal, since the offloaded work should be back to the originating device. Campbell teaches that the offloaded works are part of the application (lines 55-67 of col 10) and therefore, it is necessary to provide the results back to the originating device and the notification to the network side device so that the network device is aware of the condition of offloading.
For claim 13, cited art does not explicitly mention about receiving results from the target computing power device (Campbell mentions transmitting data back to UE device 206 in line 62, col 17). Subramaniam teaches the following limitations: after the sending the computing power task to the target computing power device (Fig 3; 110 offloads the computational task to 231 (step 330), the method further comprises: receiving a computing power task execution result responded by the target computing power device (step 345 of Fig 3; transmits results of computational operation); and sending notification information to the network side device in a case of determining that the computing power task execution result meets a preset condition or determining, based on the computing power task execution result, that execution of the computing power task succeeds, wherein the notification information is used by the network side device to release computing power reserved for the computing power task (two distinct embodiments alternatively with “or” and the first embodiment is examined; [0071] mentions offloading additional operations via controller 230 in response to results of the operations; thus when the results meet a condition (i.e., flag/address set as mentioned in [0071]) the sending device 110 sends notification for additional processing to controller 230).
It would have been obvious for one ordinary skill in the art before the effective filing date of the invention to send the notification and result to the network side device and terminal, since the offloaded work should be back to the originating device. Campbell teaches that the offloaded works are part of the application (lines 55-67 of col 10) and therefore, it is necessary to provide the results back to the originating device and the notification to the network side device so that the network device is aware of the condition of offloading.
For claim 16, cited art does not explicitly mention about receiving results from the target computing power device (Campbell mentions transmitting data back to UE device 206 in line 62, col 17). Subramaniam teaches the following limitations: after the sending the computing power task to the target computing power device (Fig 3; 110 offloads the computational task to 231 (step 330), the method further comprises: receiving a computing power task execution result responded by the target computing power device (step 345 of Fig 3; transmits results of computational operation); and sending notification information to the network side device in a case of determining that the computing power task execution result meets a preset condition or determining, based on the computing power task execution result, that execution of the computing power task succeeds, wherein the notification information is used by the network side device to release computing power reserved for the computing power task (two distinct embodiments alternatively with “or” and the first embodiment is examined; [0071] mentions offloading additional operations via controller 230 in response to results of the operations; thus when the results meet a condition (i.e., flag/address set as mentioned in [0071]) the sending device 110 sends notification for additional processing to controller 230).
It would have been obvious for one ordinary skill in the art before the effective filing date of the invention to send the notification and result to the network side device and terminal, since the offloaded work should be back to the originating device. Campbell teaches that the offloaded works are part of the application (lines 55-67 of col 10) and therefore, it is necessary to provide the results back to the originating device and the notification to the network side device so that the network device is aware of the condition of offloading.
Response to Arguments
Applicant's arguments have been fully considered but they are not persuasive. Applicant argues that both CN110851529 and Campbell fail to teach the limitations because CN110851529 does not disclose specific meaning of computing power size, computing power requirement information including a total amount of computing power required for the computing power task and the total amount of computing power required for the computing power task is a total quantities of CPUs/GPUs/servers required for the computing power task, a type of computing power required for the computing power task, an expected completing time period of the computing power task, or algorithm model information required for the computing power task
Examiner disagrees. Although CN110851529 is silent about specific meaning of computing power size, the secondary reference Campbell teaches sending of computing power requirement information from the terminal to the network side device, the power requirement information comprises an expected completing time of the computing power task and a total quantity of the virtual CPUs required for the computing power task. Applicant did not explain why Campbell fails to the limitations.
Campbell teaches sending of computing power requirement information from the terminal to the network side device, the power requirement information comprises an expected completing time of the computing power task and a total quantity of the virtual CPUs required for the computing power task in the following paragraphs:
The edge compute orchestration system may receive a task assignment request generated by a UE device communicatively coupled to the communication network. For instance, the task assignment request may be associated with an edge compute task that is to be performed in furtherance of an application executing on the UE device… First, it is desirable for any network-edge-deployed resources at edge compute nodes in the set of edge compute nodes to be able to meet minimum processing requirements and maximum latency requirements for specific edge compute tasks that are assigned to the edge compute nodes. (lines 45-65 of col 2)
FIG. 5 illustrates exemplary policy data 306 that may be used by system 100 to selectively assign an edge compute task to an appropriate node 204 in accordance with principles described herein. Edge compute tasks for each application (e.g., including application 320 executing on UE device 206) may each be associated with certain performance requirements, such as an amount of latency that the application can bear for the task (e.g., a total latency that includes transport or travel-time latency, radio latency, processing time latency, etc.), the processing resources (e.g., number of virtual processors, amount of memory and storage, networking bandwidth, etc.) required to perform the task, and so forth. Accordingly, as shown in FIG. 5, policy data 306 includes data representative of various recommendations, requirements, and so forth (“Task Parameters”) associated with each of various tasks of various applications. Specifically, for example, policy data 306 designates parameters corresponding to “Task 1” through “Task N3” of “Application 1”; “Task 1” through “Task N4” of “Application 2”; and so on for each application up to “Application N5.” As will be described in more detail below, these recommended and/or required parameters for each edge compute task may be accounted for by system 100 when selecting an appropriate edge compute node in Operation 4. (lines 39-63 of col 15; Fig 5 explained where task parameters include virtual CPU numbers and latency time (i.e., task completion time))
In the same or other examples, the parameters shown in policy data 306 may additionally or alternatively be provided to system 100 as part of the data making up the task assignment request received in Operation 1 (lines 13-16 of col 16; the request includes the performance parameters)
The selecting of an appropriate node 204 (e.g., the most ideal or optimal node 204 according to the node selection policy) in Operation 4 may be accomplished in any manner as may serve a particular implementation. For example, in certain implementations, scheduler 302 may be configured to identify (e.g., in response to the task assignment request received in Operation 1) a set of performance parameters associated with the edge compute task. These performance parameters may be stored in policy data 306 or may be represented by the task assignment request, as was described above. Scheduler 302 may then analyze several or all of nodes 204 in the set of nodes in communication network 202 in order to identify a subset of these nodes that may be possible candidates for the final selection. More particularly, scheduler 302 may determine, based on node characterization data 310, that each node 204 of a subset of nodes 204 is capable of performing the edge compute task in accordance with the identified set of performance parameters. For example, scheduler 302 may account for what the required and/or recommended latency is for the edge compute task, how many computing resources are required and/or recommended for the edge compute task, and identify possible candidate nodes 204 that have sufficient available resources and are near enough to a current location of UE device 206 to be able to satisfy these parameters. (lines 4-28 of col 17)
Therefore, Campbell teaches that the computing power requirement information of the computing power task including an expected completing time period of the computing task and a quantity of CPUs required for the computing power task. The teachings of Campbell can be incorporated into CN110851529 so that the node selection can account the latency requirement and processing requirements of the task.
Conclusion
THIS ACTION IS MADE FINAL. 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 FAHMIDA RAHMAN whose telephone number is (571)272-8159. The examiner can normally be reached Monday - Friday 10 AM - 7 PM. 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, Andrew Jung can be reached at 571-270-3779. 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.
/FAHMIDA RAHMAN/Primary Examiner, Art Unit 2175