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 is in response to communications filed on 5/21/26.
Claims 1-20 are pending.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1, 6-11 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lu et al (US Patent Application Publication 2022/0113785).
For claim 1, Lu et al teach the following limitations: A device (Fig 1 – Fig 5) comprising: a plurality of components (Fig 1; 104-1 to 104-N; the nodes include components [0022]-[0023]); and a control circuit (102 in Fig 1 and Fig 2) configured to manage performance states for the plurality of components ([0015][0017]-[0020] – power adjustments to processors of the nodes; [0039] Fig 4 step 406; [0049] Fig 5; [0065] – power management and state transitions, performance message) by: monitoring an activity metric corresponding to at least one of the plurality of components (210 receives service level metrics, OS/hypervisor level metrics and hardware metrics Fig 3; step 502 Fig 5 and [0033]-[0035] [0051]); updating a performance state of each of the plurality of components (Fig 5 step 504; [0015]-[0019] [0039] Fig 3 [0048] [0049] - increasing performance state) by modifying an operating frequency of each of the components ([0049] – increasing frequency of the processor; [0081]; [0015] – to cause computing nodes to individually or collectively adjusts power states or modes of the respective processors to achieve power management of the computer system; [0054] [0086] Fig 3 – the power management advisor 210 sends the power management advisory decisions to the agent 212; [0036]; thus the performance state of the nodes/processors are updated); receiving an event trigger corresponding to a component of the plurality of components that is independent from the activity metric ([0016] -whether an emergent event, power event or thermal event is received; [0063]; these events are independent of the activity metric shown in Fig 3 and described in [0033]-[0035]; performance boost message can also be considered event in Fig 3); and overriding the performance state of the component in response to the event trigger ([0064] -overriding advisory decisions for events; [0068] – attempt to select maximum possible performance state; [0069]; [0071] – the method blocks are repetitive; [0072] – method blocks can be performed in parallel; thus Fig 5 steps 508 and 510 can be parallel; the performance state of the components can be overridden based on the events; [0064][0069] – overriding the power management decision, event resolved, continue operations; [0090] – adjust performance according to the event; thus the performance of the processor is overridden according to the event).
For claim 6, the adjustment is based on step size of performance changes in response to event trigger ([0014] processor operates P0. P1, …Pn and power saving states are C1 to Cm; thus the performance changes follow the step changes; [0068] – attempt to select maximum possible performance state; [0081]-[0083] – the performance state is changed according to the event).
For claim 7, control circuit is configured to suspend performance state changes in response to the event trigger ([0064][0069][0038] – overriding the performance state changes in response to platform event).
For claim 8, plurality of components includes one or more component classes (processors [0015]).
For claim 9, one or more component classes include compute units (processors [0015]).
For claim 10, updating performance states includes updating a subset of the component class (collectively adjusts power states of the processors; [0015]).
For claim 11, control circuit is configured to send high priority message to a related component in response to trigger ([0069] – 102 is sending formal acknowledgement to the node; this is a high priority message in response to the trigger as it is sent immediately after the event).
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) 12, 15, 16, 17, 18 and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Krasadakis (US Patent Application Publication 10310471), in view of Lu et al (US Patent Application Publication 2022/0113785).
For claim 12, Krasadakis teaches the following limitations: A system (system 100 in Fig 1) comprising: a plurality of components comprising: a plurality of compute units (lines 42-45 of col 3 – workstation computers); a plurality of links (lines 42-45 of col 3 – LANs, switches, routers); and a plurality of remote memory (114 in Fig 1 has associated memories; Fig 10; lines 40-55 of col 3 – laptops, workstations have associated memories); and a control circuit (device controller 418 shown in Fig 4) configured to manage performance states for a component class of the plurality of components (line 60, col 18 through line 13 of col 19; controls one or more hardware devices including computers, network equipment; lights can be turned off; air conditioning may be lowered; thus the performance states of one or more component class is managed) by: determining a performance state of the component class based on a weight of an activity metric (Fig 2 222 shows the weight factor of the activity; each activity metric or activity type (lines 5-13 of col 5) has associated weight factor) corresponding to at least one of the plurality of components (lines 10-16 of col 3; lines 40-67 of col 3; lines 1-12 of col 5 mention collecting activities regarding status of the machines including CPU utilization on a workstation, LAN utilization, network traffic, HVAC, lights; Fig 1 and Fig 2 shows the activity modeler to record the activities; activity data samples 104 are modeled and stored 116 117 in Fig 2; thus performance state of a component class is determined and recorded based on the activity metrics corresponds to the components; line 60, col 18 through line 20 col 19 mention that receives trends in the energy metrics and control hardware devices based on the trend; lines 40-46 of col 6 weight factor provides relevance; thus performance is determined based on a weight of the activity metric) receiving an event trigger (Fig 6 – an identified event; Fig 3; lines 50-62 of col 6 mention the meeting event; line 54, col 7 through line 9, col 8 mention special event; thus system can receive the event trigger) corresponding to the component class (line 63, col 6 through line 3, col 7; line 62, col 12 through line 10, col 13; event corresponds to activity identifiers and data samples 104; thus the event trigger corresponds to the component class; activity type identifiers include component class as explained in lines 1-12 of col 5) that is independent from the activity metric (lines 50-62 of col 6 mention that event includes a group of related activities; thus the activity metric may not be included in the event activities; for example, the activity CPU utilization, network traffic mentioned in lines 5-15 of col 5 may not be part of the meeting event explained in lines 50-62 of col 6); and updating the performance state (lines 1-40 of col 19 - turn off light, lower air conditioning) (Fig 3 shows that event weight is assigned; baseline activity score is the activity metric mentioned in lines 35-50 of col 5, lines 4-9 of col 6; weight is adjusted by user lines 30-35 of col 13; the overall energy metric is further calculated in lines 55-60 of col 13 where the weights are adjustable by the user lines 30-33 of col 13 – thus the weight of the event 306 shown in Fig 3 can be increased by the user; Fig 2 222 shows the activity metric weight; the performance is adjusted based on energy metrics; lines 61, col 18 through line 10, col 19).
Krasadakis does not explicitly mention the following limitations:
updating the performance state by modifying an operating frequency of the component class
event trigger to override the weight of the activity metric
Lu et al teach the following limitations:
updating the performance state (Fig 5 step 504; [0015]-[0019] [0039] Fig 3 [0048] [0049] - increasing performance state) by modifying an operating frequency of the component class ([0049] – increasing frequency of the processor; [0081]; [0015] – to cause computing nodes to individually or collectively adjusts power states or modes of the respective processors to achieve power management of the computer system; [0054] [0086] Fig 3 – the power management advisor 210 sends the power management advisory decisions to the agent 212; [0036]; thus the performance state of the nodes/processors are updated)
event trigger to override the activity metric ([0016] -whether an emergent event, power event or thermal event is received; [0063]; these events are independent of the activity metric shown in Fig 3 and described in [0033]-[0035]; performance boost message can also be considered event in Fig 3; [0064] -overriding advisory decisions for events; [0068] – attempt to select maximum possible performance state; [0069]; [0071] – the method blocks are repetitive; [0072] – method blocks can be performed in parallel; thus Fig 5 steps 508 and 510 can be parallel; the performance state of the components can be overridden based on the events; [0064][0069] – overriding the power management decision, event resolved, continue operations; [0090] – adjust performance according to the event; thus the performance of the processor is overridden according to the event)
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 Krasadakis and Lu et al. The system of Krasadakis mentions special events in lines 54-67 of col 7 that have high significance and activity that has low significance (lines 40-46 of col 6). The weight factor represents the significance (lines 22-30 of col 6) and adjustable by the user (lines 1-5 of col 10, line 40, col 6). Therefore, Krasadakis is enabled to increase event weight when the event is highly significant with respect to an activity that is not significant and unrelated to the event.
As the energy metrics of the organization is based on heavier event weight, the activity metric’s weight is less valued (although not completely ignored) to select the performance state. With heavier weight of event, it is likely that the effect of activity metric might be overridden. However, with the teaching of Lu, the activity can be overridden by the event in the system of Krasadakis. Krasadakis further mention controlling devices (lines 61-67 of col 18; lines 1-10 of col 19 including turning off lights, lowering AC, computers and networks equipment). It is understood that lighting control AC control needs the frequency adjustment. With the teachings from Lu, the frequency can be modified to control these devices. Frequency adjustment facilitates power savings in the system.
For claim 15, the adjustment is based on step size of performance changes in response to event trigger ([0014] processor operates P0. P1, …Pn and power saving states are C1 to Cm; thus the performance changes follow the step changes; [0068] – attempt to select maximum possible performance state; [0081]-[0083] – the performance state is changed according to the event; Lu et al).
For claim 16, control circuit is configured to suspend performance state changes in response to the event trigger ([0064][0069][0038] – overriding the performance state changes in response to platform event; Lu et al).
For claim 17, updating performance states includes updating a subset of the component class (lines 60-65 of col 18; one or more hardware devices; Krasadakis; collectively adjusts power states of the processors; [0015] Lu et al).
For claim 18, control circuit is configured to send high priority message to a related component in response to trigger ([0069] – 102 is sending formal acknowledgement to the node; this is a high priority message in response to the trigger as it is sent immediately after the event; Lu et al).
For claim 19, Krasadakis teaches the following limitations: A method comprising: receiving, by a control circuit (device controller 418 shown in Fig 4; processor shown in Fig 10; the combination is the control circuit) configured to manage a performance state of a component (line 60, col 18 through line 13 of col 19; controls one or more hardware devices including computers, network equipment; lights can be turned off; air conditioning may be lowered; thus the performance states of one or more component class is managed) using an weight of an activity metric (Fig 4; the performance is adjusted based on energy metrics; lines 61, col 18 through line 10, col 19; the energy metrics is based on activity metrics lines 45-65 of col 13; (Fig 2 222 shows the weight factor of the activity; each activity metric or activity type (lines 5-13 of col 5) has associated weight factor), an event trigger (Fig 6 – an identified event; Fig 3) corresponding to the component (line 63, col 6 through line 3, col 7; line 62, col 12 through line 10, col 13; event corresponds to activity identifiers and data samples 104; thus the event trigger corresponds to the component class; activity type identifiers include component class as explained in lines 1-12 of col 5) that is independent from the activity metric (lines 50-62 of col 6 mention that event includes a group of related activities;
thus the activity metric may not be included in the event activities; for example, the activity CPU utilization, network traffic mentioned in lines 5-15 of col 5 may not be part of the meeting event explained in lines 50-62 of col 6); adjusting a weight of the event trigger and the weight of the activity metric by increasing the weight of the event trigger with respect to the weight of the activity metric (Fig 3 shows that event weight and metric weight are assigned; baseline activity score is the activity metric mentioned in lines 35-50 of col 5, lines 4-9 of col 6, lines 40-46 of col 6; weight is adjusted by user lines 30-35 of col 13; the overall energy metric is further calculated in lines 55-60 of col 13; adjustment of weights and increasing event weight with respect to metric weight); and updating the performance state based on the adjusted weights (the overall energy metric is further calculated in lines 55-60 of col 13 based on the adjusted weights; the performance is adjusted based on energy metrics; lines 61, col 18 through line 10, col 19).
Krasadakis does not explicitly mention the following limitations:
updating the performance state by modifying an operating frequency of the component
event trigger to override the weight of the activity metric
Lu et al teach the following limitations:
updating the performance state (Fig 5 step 504; [0015]-[0019] [0039] Fig 3 [0048] [0049] - increasing performance state) by modifying an operating frequency of the component ([0049] – increasing frequency of the processor; [0081]; [0015] – to cause computing nodes to individually or collectively adjusts power states or modes of the respective processors to achieve power management of the computer system; [0054] [0086] Fig 3 – the power management advisor 210 sends the power management advisory decisions to the agent 212; [0036]; thus the performance state of the nodes/processors are updated)
event trigger to override the activity metric ([0016] -whether an emergent event, power event or thermal event is received; [0063]; these events are independent of the activity metric shown in Fig 3 and described in [0033]-[0035]; performance boost message can also be considered event in Fig 3; [0064] -overriding advisory decisions for events; [0068] – attempt to select maximum possible performance state; [0069]; [0071] – the method blocks are repetitive; [0072] – method blocks can be performed in parallel; thus Fig 5 steps 508 and 510 can be parallel; the performance state of the components can be overridden based on the events; [0064][0069] – overriding the power management decision, event resolved, continue operations; [0090] – adjust performance according to the event; thus the performance of the processor is overridden according to the event)
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 Krasadakis and Lu et al.
The system of Krasadakis mentions special events in lines 54-67 of col 7 that have high significance and activity that has low significance (lines 40-46 of col 6). The weight factor represents the significance (lines 22-30 of col 6) and adjustable by the user (lines 1-5 of col 10, line 40, col 6). Therefore, Krasadakis is enabled to increase event weight when the event is highly significant with respect to an activity that is not significant and unrelated to the event. As the energy metrics of the organization is based on heavier event weight, the activity metric’s weight is less valued (although not completely ignored). With heavier weight of event, it is likely that the effect of activity metric might be overridden. However, with the teaching of Lu, the activity can be overridden by the event in the system of Krasadakis. Krasadakis further mention controlling devices (lines 61-67 of col 18; lines 1-10 of col 19 including turning off lights, lowering AC, computers and networks equipment). It is understood that lighting control AC control needs the frequency adjustment. With the teachings from Lu, the frequency can be modified to control these devices. Frequency adjustment facilitates power savings in the system.
For claim 20, Krasadakis calculates the energy level in lines 50-60 of col 13, which includes weights. This energy level is used to control the performance (lines 60-67 of col 18). Thus, the performance state based on weights overrides any other performance state in the system. Lu further teaches performance state overriding (the performance state of the components can be overridden based on the events; [0064][0069] – overriding the power management decision, event resolved, continue operations; [0090] – adjust performance according to the event; thus the performance of the processor is overridden).
Response to Arguments
Applicant’s arguments have been considered but are moot because of the new ground of rejection. However, Krasadakis is still relied upon for rejection and Examiner is addressing the arguments related to Krasadakis,
Applicant argues that Krasadakis does not disclose or suggest “receiving an event trigger corresponding to the component class that is independent from the activity metric” and “a weight of the event trigger being increased with respect to the weight of the activity metric to override the weight of the activity metric.” According to the applicant, Krasadakis states that the weight factor of each activity object may be aggregated to adjust energy value of the event object and thus, event and activity metric are not independent to each other.
Examiner disagrees. Krasadakis teaches “receiving an event trigger corresponding to the component class that is independent from the activity metric.” According to Krasadakis, an event includes any group of related activities, not all activities in the system. Therefore, there are other activities in the system which are not part of one particular event. The “meeting” event may not include the activity of CPU utilization of a workstation that is in another location. Thus, the event trigger can be independent of many other unrelated activities that are not part of the event. According to lines 50-62 of col 6 of Krasadakis,
An event may include any group of related activities in an organization. Examples of the events may include a meeting, a presentation, a client demo, an ad-hoc un-registered arrangement of people or any other planned or unplanned collection of related activities. The events may be predefined for each of the activity types and/or groups of activity types. For instance, a meeting may be expected to be accompanied by certain activity type (entering a room, exiting the room, talking, presenting, handshaking etc.) and certain activity contexts associated with the event (i.e. the identifies of certain attendees, content of the conversations discussed, etc).
For the limitations, “a weight of the event trigger being increased with respect to the weight of the activity metric to override the weight of the activity metric”, Krasadakis, although not mentions the overriding/override, teaches the less emphasizing of the activity metric weight because the weight adjustment can be performed by user and the significance of activity/context/event is considered by the system. When the event and associated activities are more important, the weight factor can be increased as the weight factor represents the significance. When weight factor of the event is increased, then the event has more contribution to the combined energy metrics, and the non-related activities will be less emphasized by the event. As Krasadakis teaches:
The activity modeler 116 may determine energy metrics that quantify the significance of activities identified through the activity data samples 102 (lines 35-38 of col 5)
The adjusted activity score 126 may include an energy metric reflecting a significance of the activity type identifier (lines 4-7 of col 6)
The activity context information 124 may be associated with a weight factor 121. The weight factor 121 may include energy metric quantitative of the significance of the activity context information 124 (lines 22-25 of col 6)
For example, a system user may establish the weight factor association. For example, the system user may determine that information collected outside business hours is not as relevant as information collected during business hours. Thus, the system user may established that the weight factor association for context information collected at night and a weight factor association for context information collected during the day (lines 39-46 of col 6)
The event modeler 140 may apply the special event criteria to the energy metrics of the event object 128 to determine if the event qualifies as a special event. A special event includes an event of heightened importance … a special event may be defined by an energy metric exceeding a predefined threshold. For example, the event modeler 140 may determine that an energy metric exceeds the predefined threshold (lines 54-65 of col 7)
The energy metrics, as described herein, means any quantitative value assigned to activity information to contextualize the significance of the activity information. Energy metrics may include baseline scores, adjusted scores, weight factors, or any other type of metric. In addition, the energy metrics may include any additional metrics, such as the energy score of multiple events (lines 48-65 of col 9)
The event weight 306 may be supplied by the user of the system and associated with the event identifier 130 by the event modeler 140 (lines 30-35 of col 13)
As these sections mention, the weight can be adjusted by the user and can be increased for an important event. With that, a non-related activity weight will be devalued by the weight of the important event when computing the energy metrics for the organization. For further clarification, the newly cited reference Lu et al teaches the overriding of the activity by the event. With the combined teachings, the system will be able to override the activity metric and its associated weight by the event weight.
Allowable Subject Matter
Claim 2-5, 13-14 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
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 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 on 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
Prosecution Insights