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 . in the amendments of 5/14/2026 claims 8 and 19-20 were cancelled. Therefore, Claims 1-7, 9-18 are still pending in this Application.
Response to Amendments/Remarks
Applicant’s argument/remarks, on page 7, with respect to objections to the claims have been fully considered and are persuasive. Therefore, objections to the claims have been withdrawn due to amendments to it. Applicant amendments to the claims overcame the objections.
Applicant’s argument/remarks, on page 7, with respect to rejections to claims 1-20 under 35 USC § 112(b) have been fully considered and are persuasive. Therefore, rejections to the claims under 35 USC § 112 have been withdrawn.
Applicant’s argument/remarks, on page 7-9, with respect to rejections to claims 1-20 under 35 USC § 102(a)(1)/(2) and/or 103(a) have been fully considered and are persuasive. Therefore, rejections to claims have been withdrawn due to the amendments. However, upon further consideration, a new ground(s) of rejection is made in view of Sinha and Liu, see the new rejections below.
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, 3, 11-13, 15, and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Amores et al (US 20210191378) view of Sinha et al (US 10788798) and Liu et al (US 20220237521).
As per claim 1, Amores teaches a system for maintaining equipment (see 0065), comprising:
an interface configured to receive information about a state of the equipment from a plurality of sources (see Fig. 3 and Fig. 4 and see [0047] “For example, AHU controller 330 may provide BMS controller 366 with temperature measurements from temperature sensors 362-364, equipment on/off states, equipment operating capacities, and/or any other information that can be used by BMS controller 366 to monitor or control a variable state or condition within building zone 306.”; also, see [0053], "Still referring to FIG. 4, BMS controller 366 is shown to include a processing circuit 404 including a processor 406 and memory 408. Processing circuit 404 can be communicably connected to BMS interface 409 and/or communications interface 407 such that processing circuit 404 and the various components thereof can send and receive data via interfaces 407, 409.", para [0058], "Building subsystem integration layer 420 can be configured to manage communications between BMS controller 366 and building subsystems 428. For example, building subsystem integration layer 420 may receive sensor data and input signals from building subsystems 428 and provide output data and control signals to building subsystems 428. Building subsystem integration layer 420 may also be configured to manage communications between building subsystems 428. Building subsystem integration layer 420 translate communications (e.g., sensor data, input signals, output signals, etc.) across a plurality of multi-vendor/multi-protocol systems.");
a data pool including the information from the interface (see (para [0069], "FDD layer 416 can be configured to store or access a variety of different system data stores (or data points for live data). FDD layer 416 may use some content of the data stores to identify faults at the equipment level ( e.g., specific chiller,
specific AHU, specific terminal unit, etc.) and other content to identify faults at component or subsystem levels. For example, building subsystems 428 may generate temporal (i.e., time-series) data indicating the performance of BMS 400 and the various components thereof. The data generated by building subsystems 428 can include measured or calculated values that exhibit statistical characteristics and provide information about how the corresponding system or process (e.g., a temperature control process, a flow control process, etc.) is performing in terms of error from its setpoint.", para [0087], "Still referring
to FIG. 6, memory 612 is shown to include database 616 and FDD circuit 620. Database 616 is configured to store data collected from a component/system under observation. For example, FDD circuit 620 may be applied to building management system 602 and database 616 may store data collected from buildings and building management system devices. As a further example, FDD circuit 620 may be applied to a CCTV network and database 616 may store data collected from CCTV devices (e.g., cameras, controllers, etc.).In some embodiments, the data is timeseries data. In various embodiments, the data relates to operation of building 10 and/or BMS 400. For example, database 616 may include sensor data describing a state of building 10.", para [0089], "As a concrete example, FDD circuit 620 may be trained with a training dataset to determine the weight associated with each of FDD models 622. Additionally or alternatively, the weights may be determined dynamically. For example, the weights may be determined based on a rules engine. As a further example, the weights may be determined based on user input (e.g., a rule-based expert
system, etc.).");
a plurality of agents, including a first agent and a second agent (see Fig. 7 agents are interpreted as models; also, see [0081] “For example, a first FDD model may analyze sensor data while a second FDD model may analyze aggregate data. In various embodiments, the FDD system may determine fault confidences.", para [0089], "Weighting circuit 624 may receive the fault determinations from FDD models 622 and apply various weights to the fault determinations. For example, a first fault determination received from a first FDD model may be assigned a weight of 0.2 while a second fault determination received from a second FDD model may be assigned a weight of 0.8. The weights assigned to each FDD model 622 output (e.g., fault determination, etc.) may be predetermined. For example, the weights may be determined based on machine learning. As a concrete example, FDD circuit 620 may be trained with a training dataset to determine the weight associated with each of FDD models 622. Additionally or alternatively, the weights may be determined dynamically. For example, the weights may be determined based on a rules engine. As a further example, the weights may be determined based on user input (e.g., a rule-based expert system, etc.”), configured to access data in the data pool, wherein the plurality of agents are trained to assess a condition of the equipment based on the data (see [0020], "Disclosed herein is an improved fault detection and diagnosis (FDD) system including an ensemble of FDD models. The FDD system of the present disclosure may greatly increase the accuracy of fault determinations and provide improved robustness to individual parameter selection. In various embodiments, the FDD system of the present disclosure includes a superposition of FDD models and/or parameters. As a non-limiting example, the FDD system may include ten FDD models, each having a number of different parameters, and may develop a consensus from the fault determinations of the ten FDD models. In some embodiments, the FDD system of the present disclosure facilitates generation of fault confidences. The FDD system of the present disclosure may improve the functioning of computing systems and the field of fault detection generally by greatly improving the accuracy of fault determinations, reducing false fault determinations, improving fault integrity, reducing fault noise (e.g., alarm fatigue), and thereby conserving operator and system resources devoted to investigating fallacious faults.", see [0047], "For example, AHU controller 330 may provide BMS controller 366 with temperature measurements from temperature sensors 362-364, equipment on/off states, equipment operating capacities, and/or any other information that can be used by BMS controller 366 to monitor or control a variable state or condition within building zone 306.", para [0075], "System manager 502 can provide a user interface for any device containing an equipment model. Devices such as zone coordinators 506-510 and 518 and thermostat controller 516 can provide their equipment models to system manager 502 via system bus 554. In some embodiments, system manager 502 automatically creates equipment models for connected devices that do not contain an equipment model (e.g., IOM 514, third party controller 520, etc.). For example, system manager 502 can create an equipment model for any device that responds to a device tree request. The equipment models created by system manager 502 can be stored within system manager 502."; also, see Fig. 7 and see [0088] “…FDD circuit 620 may be implemented in a computer network to determine faults related to computer hardware functioning. FDD models 622 may be configured to receive input data and produce a fault determination. In some embodiments, FDD models 622 may be configured to produce a fault confidence. Each of FDD models 622 may include parameters. For example, a first FDD model 622 may include a first parameter associated with a temperature threshold and a second FDD model 622 may include a second parameter associated with a humidity threshold….”; also, see [0091], [0093]. In the broadest reasonable interpretation in light of disclosure, agents are ML model, models in general, subprogram/thread program performing an analysis of function on collected data); and
an orchestrator configured to:
evaluate an assessment of the first agent (see para [0093], "At step 704, FDD models 622 may generate individual fault determinations based on the received input data. Process 700 may include any number of FDD models 622. In various embodiments, the individual fault determinations are binary (e.g., fault/no-fault, etc.). In some embodiments, FDD models 622 are chosen from a candidate set of FDD models. For example, FDD circuit 620 may evaluate m candidate FDD models and select n models as the FDD models 622 based on which of the m candidate FDD models performed the best ( e.g., had the highest fault determination accuracy, lowest number of false fault determinations, etc.);
determine a next action to take based at least in part on the evaluation of the assessment of the first agent (the next action could accessing a second agent/model or collecting additional data or any action performed/outputted based on the evaluation of the first agent; also, see [0081], [0089]; also, see [0056], "Still referring to FIG. 4, memory 408 is shown to include an enterprise integration layer 410, an automated measurement and validation (AM AND V) layer 412, a demand response (DR) layer 414, a fault detection and diagnostics (FDD) layer 416, an integrated control layer 418, and a building subsystem integration later 420. Layers 410-420 can be configured to receive inputs from building subsystems 428 and other data sources, determine optimal control actions for building subsystems 428 based on the inputs, generate control signals based on the optimal control actions, and provide the generated control signals to building subsystems 428. The following paragraphs describe some of the general functions performed by each of layers 410-420 in BMS 400”; the next action is also determining a fault and sending an message or notification based on the output of the first agent/model, see [0093] “…For example, FDD circuit 620 may evaluate m candidate FDD models and select n models as the FDD models 622 based on which of the m candidate FDD models performed the best (e.g., had the highest fault determination accuracy, lowest number of false fault determinations, etc.)…”, thus, based on evaluating at least one first model, a next action is determined including accessing a second agent/model that has higher highest accuracy and [0103]) including by:
determining whether the next action includes accessing the second agent (see para [0081], "For example, a first FDD model may analyze sensor data while a second FDD model may analyze aggregate data. In various embodiments, the FDD system may determine fault confidences.", para [0094], "At step 706, weighting circuit 624 may apply a weight to each of the individual fault determinations generated by FDD models 622. In various embodiments, there are no fault determinations, each corresponding to one of FDD models 622. Weighting circuit 624 may apply weights wl, w2, ... , wn to then fault determinations. In some embodiments, the weights wl, w2, ... , wn are predetermined. For example, FDD circuit 620 may generate weights wl, w2, ... , wn using a machine learning algorithm. Additionally or alternatively, the weights wl, w2, ... , wn may be determined dynamically. For example, FDD circuit 620 may receive weights wl, w2, ... , wn from an external distributed processing system based on the specific FDD models 622 being used. As a concrete example, weights wl, w2, ... , wn may be determined by testing a number of candidate weights and selecting the weights that perform the best (e.g., have the highest fault determination accuracy, the lowest number of false fault determinations, etc.) over a training data set."; see [0093] “…For example, FDD circuit 620 may evaluate m candidate FDD models and select n models as the FDD models 622 based on which of the m candidate FDD models performed the best (e.g., had the highest fault determination accuracy, lowest number of false fault determinations, etc.)….”, based on evaluating a first model a second model can be selected which will be used and accessed to perform a further determination);
perform the next action, including by:
;
in the event the next action includes accessing the second agent accessing the second agent for further assessment (see [0081], [0089], [0093] “…For example, FDD circuit 620 may evaluate m candidate FDD models and select n models as the FDD models 622 based on which of the m candidate FDD models performed the best (e.g., had the highest fault determination accuracy, lowest number of false fault determinations, etc.)….”, based on evaluating a first model a second model can be selected which will be used and accessed to perform a further determination or assessment of a fault);
cause a modification to be made to the equipment (see para [0051], "Interface 407 may facilitate communications between BMS controller 366 and external applications (e.g., monitoring and reporting applications 422, enterprise control applications 426, remote systems and applications 444, applications residing on client devices 448, etc.) for allowing user control, monitoring, and adjustment to BMS controller 366 and/or subsystems 428.", para [0060], "According to some embodiments, demand response layer 414 includes control logic for responding to the data and signals it receives. These responses can include communicating with the control processes in integrated control layer 418, changing control strategies, changing setpoints, or activating/deactivating building equipment or subsystems in a controlled manner. Demand response layer 414 may also include control logic configured to determine when to utilize stored energy.", para [0061], "In some embodiments, demand response layer 414 includes a control module configured to actively initiate control actions (e.g., automatically changing setpoints) which minimize energy costs based on one or more inputs representative of or based on demand (e.g., price, a curtailment signal, a demand level, etc.). In some embodiments, demand response layer 414 uses equipment models to determine an optimal set of control actions.", para [0068], "FDD layer 416 can be configured to output a specific identification of the faulty component or cause of the fault ( e.g., loose damper linkage) using detailed subsystem inputs available at building subsystem integration layer 420. In other exemplary embodiments, FDD layer 416 is configured to provide "fault" events to integrated control layer 418 which executes control strategies and policies in response to the received fault events. According to some embodiments, FDD layer 416 ( or a policy executed by an integrated control engine or business rules engine) may shut-down systems or direct control activities around faulty devices or systems to reduce energy waste, extend equipment life, or assure proper control response.", Thus, based on the output of a second model, the system executes control strategies and policies in response to the received fault events based on the second model; para [0112], "Although only a few embodiments have been described in detail in this disclosure, many modifications are possible ( e.g., variations in sizes, dimensions, structures, shapes and proportions of the various elements, values of parameters, mounting arrangements, use of materials, colors, orientations, etc.).").
Amores does not explicitly teach determining whether the next action includes obtaining additional information;
in the event the next action includes obtaining the additional information, obtaining the additional information;
determine whether to repeat the evaluation of the assessment of the first agent and in the event it is determined to not repeat the evaluation of the assessment of the first agent, cause a modification to be made to the equipment (these limitations have been interpreted in light of the disclosure, wherein in Fig. 6 if after performing step 214 accessing a second agent and reaching a task plan or stopping condition (which is not explicitly defined in the disclosure but exemplified as “orchestrator's task plan being sufficiently complete”), the system does not reevaluates the first agent but instead goes to step 208).
However, Sinha teaches a system comprising an orchestrator determining whether a next action (see Fig. 8 orchestrator 602 and first agent/edge controller 700/7022), determined based on an evaluation of a first agent (see Col 6 lines 1-65 “…the edge controller is a first edge controller and the edge device is a first edge device. In some embodiments, a second edge controller is a second software agent implemented within the at least one server… In some embodiments, the local control scheme of the edge controller includes a first neural network. In some embodiments, the edge control adaptation command is configured to modify the first neural network… In some embodiments, the local control scheme of the edge controller includes a first neural network. In some embodiments, the edge control adaptation command is configured to modify the first neural network… In some embodiments, the request to analyze the data is generated by the edge controller in response to a determination that the data does not match a recognized pattern. (52) In some embodiments, the request to analyze the data is generated by the edge controller in response to determining that that a level of processing resources required to process the data is greater than a threshold level. (53) In some embodiments, the request to analyze the data is generated by the edge controller in response to determining that a response of the edge controller to the data would violate a policy of the edge controller…”; also, see Col 27 line 56 to Col 28 line 5 and see Col 28 lines 18-22 “…one or more of edge controllers 702 are software-defined controllers, shown as agents for edge devices 800…”, thus, based on the request from the first agent, the orchestrator determines whether the next action includes obtaining additional data or performing other actions), includes obtaining additional information (see Fig. 8 orchestrator 602 also, see Col 7 lines 60-63 “… the edge control adaptation command is configured to cause the edge controller modify the local control scheme to utilize additional data provided by a second edge controller of a second edge device”; also, see Col 25 lines 29-40 determining whether to generate the command or not which includes the obtaining of additional data ) and in the event the next action includes obtaining the additional information, obtaining the additional information (see Col 5 lines 29-56 “the adaptation command is configured to cause the first edge controller to retrieve the additional data directly from the second edge controller without the additional data passing through the cloud controller... In some embodiments, analyzing, by the cloud controller, the data based on information obtained by the cloud controller regarding at least one of the second space or the second building equipment domain includes determining whether the data satisfies a condition. In some embodiments, the edge control adaptation command is generated in response to determining that the data satisfies the condition. In some embodiments, the edge control adaptation command is configured to cause the edge controller to modify the local control scheme such that the edge controller (a) determines locally whether subsequent data satisfies the condition and (b) in response to determining that the subsequent data satisfies the condition, controls the edge device without requesting for the cloud controller to analyze the subsequent data…”; see Fig. 10 the first agent/edge controller performs an evaluation of data collected, if the input data fails processing conditions in step 1006, the first agent requests the orchestrator to perform a further evaluation, then the orchestrator performs an evaluation, the orchestrator determines whether to perform a next action wherein the next action includes obtaining additional data for the first agent/edge controller, and said additional data is obtained… In some embodiments, the edge control adaptation command is generated in response to determining that the data satisfies the condition. In some embodiments, the edge control adaptation command is configured to cause the edge controller to modify the local control scheme such that the edge controller (a) determines locally whether subsequent data satisfies the condition and (b) in response to determining that the subsequent data satisfies the condition, controls the edge device without requesting for the cloud controller to analyze the subsequent data”; also, see Col 45 claim 7 “analyzing, by the first edge controller, the data and the additional data using the modified first neural network; and controlling the first edge device based on the analysis of the data and the additional data by the first edge controller.).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ invention to include an orchestrator determining whether a next action, determined based on an evaluation of a first agent, includes obtaining additional information, and in the event the next action includes obtaining the additional information, obtaining the additional information as taught by Sinha in order to allow the first agent to determine locally whether subsequent data satisfies the condition and (b) in response to determining that the subsequent data satisfies the condition, controls the edge device without requesting for the cloud controller to analyze the subsequent data (see Co 5 lines 43-56) and/or to obtain additional data to obtain better analysis and control the equipment with the first agent based on the additional data (see Col 44 claim 1 “er, a response to the request including an edge control adaptation command; modifying, by the first edge controller based on the edge control adaptation command, a local control scheme of the first edge controller to utilize additional data provided by a second edge controller of a second edge device, wherein the edge control adaptation command is configured to cause the first edge controller to retrieve the additional data directly from the second edge controller without the additional data passing through the cloud controller; and controlling, by the first edge controller, operation of the first edge device according to the modified local control scheme.) .
While Amores and Sinha teaches a second agent as characterized above, they do not explicitly teach determine whether to repeat the evaluation of the assessment of the first agent and in the event it is determined to not repeat the evaluation of the assessment of the first agent, cause a modification to be made to the equipment (these limitations have been interpreted in light of the disclosure, wherein in Fig. 6 if after performing step 214 accessing a second agent and reaching a task plan or stopping condition (which is not explicitly defined in the disclosure but exemplified as “orchestrator's task plan being sufficiently complete”), the system does not reevaluates the first agent but instead goes to step 208).
Liu teaches a system comprising a first agent and a second agent, determine whether to repeat the evaluation of the assessment of the first agent (see Fig. 4 first agent is evaluated, and second agent is evaluated; Fig. 5 teaches if a condition is met at step 504 which is equivalent to determine to “to not repeat the evaluation of the assessment of the first agent”, because in step 505 only second agent will be the target model and will be used for evaluating the system ) and in the event it is determined to not repeat the evaluation of the assessment of the first agent (see Fig. 4 first agent is evaluated, and second agent is evaluated; Fig. 5 teaches if a condition is met at step 504 which is equivalent to determine to “to not repeat the evaluation of the assessment of the first agent”, because in step 505 only second agent will be the target model and will be used for evaluating the system; also, see [0045] “If this difference is less than or equal to the threshold difference, it indicates that the second machine learning model can be used to update the first machine learning model, so at 505, the second machine learning model can be determined as the target machine learning model. Otherwise, at 506, the first machine learning model can be determined as the target machine learning model, i.e., no updates are made to the first machine learning model. As an example, this threshold difference can be determined by computing device 320 when training the second machine learning model. As an example, two parameters can be set in advance, i.e., the number of validation successes and the number of validation failures. If it is determined that the first analysis result is the same as the second analysis result, the number of validation successes is incremented by one. In addition, in the case where the first analysis result is different from the second analysis result, if the difference between the first analysis result and the second analysis result is determined to comply with a predetermined rule generated when training the second machine learning model, the number of validation successes is incremented by one, while if the difference between the first analysis result and the second analysis result is determined not to comply with the predetermined rule generated when training the second machine learning model, the number of validation failures is incremented by one. Thus, the ratio of the number of validation failures to the number of validation successes or the total number of validations can be determined. If this ratio is lower than a threshold ratio, it indicates that second machine learning model passes the validation and the machine learning model can be updated. In this manner, it is possible to quickly determine whether the second machine learning model is suitable for model updating, thus ensuring that the updated model does not degrade the system performance”), cause a modification to be made to the system (see 0045 Thus, the ratio of the number of validation failures to the number of validation successes or the total number of validations can be determined. If this ratio is lower than a threshold ratio, it indicates that second machine learning model passes the validation and the machine learning model can be updated. In this manner, it is possible to quickly determine whether the second machine learning model is suitable for model updating, thus ensuring that the updated model does not degrade the system performance”; also, see [0044] “…Specifically, if the second analysis result, individually or as a whole, is worse than the first analysis result, the first machine learning model is determined as the target machine learning model, i.e., no updates are made to the first machine learning model. FIG. 5 illustrates a flow chart of detailed process 500 for updating a machine learning model according to embodiments of the present disclosure…”, it is determined whether to access the second model/agent or not based on the results also, see [0046] “when the second machine learning model is determined to be suitable for model updating, the first machine learning model can also be updated with the second machine learning model that is determined as the target machine learning model. In this manner, after the first machine learning model has completed the processing of the current to-be-analyzed data 110, the validated second machine learning model can be used to continue processing the subsequent to-be-analyzed data, so that the updating of the machine learning model can be completed with virtually no delay in processing the to-be-analyzed data.”).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ invention to include determine whether to repeat the evaluation of the assessment of the first agent, and in the event it is determined to not repeat the evaluation of the assessment of the first agent, cause a modification to be made to the system as taught by Liu in order to allow the system to decide when to update the agents/models that will be used to analyze data of a system or equipment and acquire more accurate analysis results when the first agent/model is updated (see [0004] and [0044-0046]) or avoid updating a first agent model to avoid degrading the system (see [0004]]).
As per claim 3, Amores-Sinha-Liu teaches the system of claim 1, wherein the information from the interface includes at least one of: historical information and a maintenance history (see [0109], "FDD circuit 620 may generate a model to determine a fault confidence associated with a fault determination. For example, FDD circuit 620 may analyze historical data x'l, x'2, ... , x'h to generate an FDD model 622 where h is the number of historical data elements.", para [0110], "Accordingly, each FDD model 622 may generate a fault confidence and confidence circuit 626 may analyze the individual fault confidences to generate a fault confidence as described above with reference to FIG. 8. As a concrete example, a first prediction based FDD model 622 may generate a model based on the input vector x and/or historical input data. The first prediction based FDD model 622 may generate predictions of expected next normal observations ).
As per claim 11, Amores-Sinha-Liu teaches the system of claim 1, Amores further teaches wherein the orchestrator is further configured to output a maintenance recommendation (see (para [0067], "FDD layer 416 may receive data inputs from
integrated control layer 418, directly from one or more building subsystems or devices, or from another data source. FDD layer 416 may automatically diagnose and respond to detected faults. The responses to detected or diagnosed faults can include providing an alert message to a user, a maintenance scheduling
system, or a control algorithm configured to attempt to repair the fault or to work-around the fault.", para [0068], "In other exemplary embodiments, FDD layer 416 is configured to provide "fault" events to integrated control layer 418 which executes control strategies and policies in response to the received fault
events. According to some embodiments, FDD layer 416 (or a policy executed by an integrated control engine or business rules engine) may shut-down systems or direct control activities around faulty devices or systems to reduce energy waste, extend equipment life, or assure proper control response.").).
As per claim 12, Amores-Sinha-Liu teaches the system of claim 1, Amores further teaches wherein the orchestrator is further configured to output at least one of: a prediction or request for more information (see para [0110], "Accordingly, each FDD model 622 may generate a fault confidence and confidence circuit 626 may analyze the individual fault confidences to generate a fault confidence as described above with reference to FIG. 8. As a concrete example, a first prediction based FDD model 622 may generate a model based on the input vector x and/ or historical input data. The first prediction based FDD model 622 may generate predictions of expected next normal observations. For example, for a room temperature at a steady state 70° F., the first prediction based FDD model 622 may generate predictions of next temperature measurements around 70° F. The first prediction based FDD model 622 may compare the predictions to the actual observed value to determine a result (e.g., a difference, etc.). Based on the result, the first prediction based FDD model 622 may generate a binary fault output. For example, the first prediction based FDD model 622 may generate a fault indication if the result exceeds a threshold.").
As per claim 13, Amores-Sinha-Liu teaches the system of claim 1, Amores further teaches wherein the orchestrator is further configured to determine a generalization across at least one of: assets within a threshold similarity of each other and a plurality of instances of assets (see [0066] “…(e.g., using data aggregated by AM&V layer 412, integrated control layer 418, building subsystem integration layer 420, FDD layer 416, or otherwise)….”; also, see [0081] “…For example, a first FDD model may analyze sensor data while a second FDD model may analyze aggregate data…”; also, see [0090], "Confidence circuit 626 may receive the outputs from FDD models 622 and determine a fault confidence. In some embodiments, confidence circuit 626 receives a fault confidence from each of FDD models 622 and determines an aggregate fault confidence. Additionally or alternatively, confidence circuit 626 may receive fault determinations from FDD models 622 and determine a fault confidence based on the received fault determinations." ... "Additionally or alternatively, the fault confidence may be associated with the accuracy of the fault determination. For example, a fault confidence of 80% may indicate that 80% of previous faults having similar characteristics were determined to be accurate faults. Determining a fault confidence is described in greater detail below with reference to FIG. 8.", para [0091], "Threshold circuit 628 may receive the fault determinations from FDD models 622 and analyze the received fault determinations to generate an aggregate fault determination. In some embodiments, the aggregate fault determination is a composite of the individual fault determinations. In various embodiments, threshold circuit 628 receives a fault score from weighting circuit 624. Threshold circuit 628 may compare the fault score to a threshold to generate a fault determination.").).
As per claim 15, Amores-Sinha-Liu teaches the system of claim 1, Amores further teaches wherein: at least one parameter is extracted from the received information about the state of the equipment (see [0020], "In various embodiments, the FDD system of the present disclosure includes a superposition of FDD models and/or parameters. As a non-limiting example, the FDD system may include ten FDD models, each having a number of different parameters, and may develop a consensus from the fault determinations of the ten FDD models.", para [0088], "Each of FDD models 622 may include parameters. For example, a first FDD model 622 may include a first parameter associated with a temperature threshold and a second FDD model 622 may include a second parameter associated with a humidity threshold. In various embodiments, the parameters are unique to each FDD model 622. Additionally or alternatively, FDD models 622 may share one or more parameters. FDD models 622 may be generated based on training data”); and
the at least one parameter includes at least one of: electrical current, temperature, vibration frequency, and vibration amplitude (see para [0047], "For example, AHU controller 330 may provide BMS controller 366 with temperature measurements from temperature sensors 362-364, equipment on/off states, equipment operating capacities, and/or any other information that can be used by BMS controller 366 to monitor or control a variable state or condition within building zone 306.", para [0059], "The inputs received from other layers can include environmental or sensor inputs such as temperature, carbon dioxide levels, relative humidity levels, air quality sensor outputs, occupancy sensor outputs, room schedules, and the like. The inputs may also include inputs such as electrical use (e.g., expressed in kWh), thermal load measurements, pricing information, projected pricing, smoothed pricing, curtailment signals from utilities, and the like.", para [0092], "As a concrete example, a two-dimensional vector such that may include room temperature measurements and energy consumption measurements”).
As to claim 17, this claim is the method claim corresponding to the system claim 1 and is rejected for the same reasons mutatis mutandis.
As to claim 18, this claim is the computer program product embodied in a non-transitory computer readable medium and comprising computer instructions claim corresponding to the system claim 1 and is rejected for the same reasons mutatis mutandis (Amores teaches see [0053-0054] “…. Memory 408 can be or include volatile memory or non-volatile memory. Memory 408 can include database components, object code components, script components, or any other type of information structure for supporting the various activities and information structures described in the present application. According to some embodiments, memory 408 is communicably connected to processor 406 via processing circuit 404 and includes computer code for executing (e.g., by processing circuit 404 and/or processor 406) one or more processes described herein.”; also, see page 16 claim 21):
Claim(s) 2, 4 and 6 are rejected under 35 U.S.C. 103 as being unpatentable over Amores et al (US 20210191378) in view of Sinha et al (US 10788798) and Liu et al (US 20220237521) as applied to claim 1 above, and further in view of Madam et al (US 20140200686).
As per claim 2, Amores-Sinha-Liu teaches the system of claim 1, While Amores teaches control logic (see [0060], and [0063]), Amores does not explicitly teach wherein the plurality of sources includes a programmable logic controller (PLC).
However, Madam teaches a monitoring equipment system (see Abstract and see [0036]) comprising a plurality of sources providing state data of equipment, wherein the plurality of sources includes a programmable logic controller (PLC) (see Fig. 1 sources 104(1-n) and see [0036] “…at least a portion of the monitoring system 108 (e.g., one or more of the monitoring computers 108, the user interface 120, and/or the data archive 122, etc.) may form at least part of a type of supervisory control and data acquisition (SCADA). In such embodiments, the SCADA system may gather, acquire, and/or receive the operational data from and/or transmit commands to the one or more data acquisition systems 106. Although not depicted in FIG. 1A, remote terminal units (RTUs) and/or programmable logic controllers (PLCs) may be connected to sensors (e.g., temperature sensors) provided as part of the equipment installation 104 that serve to receive sensor signals and convert the sensor signals to digital data, which may then be transmitted to the SCADA system.)
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ combination as taught above to include the plurality of sources includes a programmable logic controller (PLC) as taught by Madam in order to receive sensor signals and convert the sensor signals to digital data, which may then be transmitted to a monitoring system or device (see [0036] “(PLCs) may be connected to sensors (e.g., temperature sensors) provided as part of the equipment installation 104 that serve to receive sensor signals and convert the sensor signals to digital data, which may then be transmitted to the SCADA system).
As per claim 4, Amores-Sinha-Liu teaches the system of claim 1, While Amores teaches the equipment or system comprises configurations settings (see 0039) and data received at the monitoring device from the equipment (see 0047 “…AHU controller 330 may provide BMS controller 366 with temperature measurements from temperature sensors 362-364, equipment on/off states, equipment operating capacities, and/or any other information that can be used by BMS controller 366 to monitor or control a variable state or condition within building zone 306.), Amores does not explicitly teach wherein the information from the interface includes a configuration.
However, Madam teaches a monitoring equipment system (see Abstract and see [0036]) comprising acquiring information via an interface, wherein the information from the interface includes a configuration (see [0048] “…As noted previously, the configuration information associated with a particular equipment installation may include information relating to various design, installation, and/or operating parameters associated with the equipment installation... In certain embodiments, the configuration module 116 may retrieve or receive configuration information relating to design and/or installation parameters from the datastore(s), while configuration information relating to certain installation and/or operating parameters may be received from systems or operators obtaining the information on-site…”; also, see [0057]).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ combination as taught above to include comprising acquiring information via an interface, wherein the information from the interface includes a configuration as taught by Madam in order generate configurable rules based on the configuration data associated with an equipment to analyze operational data and detect conditions of the equipment ( see [0050] “…As described above, computer-executable instructions provided as part of the configuration module 116 may have been executed to configure a set of configurable rules with the configuration information 134 associated with a particular equipment installation to generate the set of configured rules. The rules engine 124 may then analyze the operating data 130 associated with the particular equipment installation based at least in part on the generated set of configured rules. The rules engine 124 may include a standard interface that is capable of receiving various sets of configurable base rules…”; also, see [0053]).
As per claim 6, Amores-Sinha-Liu teaches the system of claim 1, but it does not explicitly teach wherein the information from the interface includes data collected by a technician.
However, Madam teaches a monitoring equipment system (see Abstract and see [0036]) comprising acquiring information via an interface, wherein the information from the interface includes data collected by a technician (see [0048] “... In certain embodiments, the configuration module 116 may retrieve or receive configuration information relating to design and/or installation parameters from the datastore(s), while configuration information relating to certain installation and/or operating parameters may be received from systems or operators obtaining the information on-site…”; also, see [0049] “…The input data 142 may have been gathered by, for example, an operator at the installation site 102 where the equipment 104 is installed. For example, in certain embodiments, certain configuration information relating to installation and/or operating parameters may be acquired on-site and provided to the monitoring computer 108, or more specifically, the configuration module 116 as the input data 142…”).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ combination as taught above to include comprising acquiring information via an interface, wherein the information from the interface includes data collected by a technician as taught by Madam in order generate configurable rules based on the configuration data associated with an equipment to analyze operational data and detect conditions of the equipment ( see [0050] “…As described above, computer-executable instructions provided as part of the configuration module 116 may have been executed to configure a set of configurable rules with the configuration information 134 associated with a particular equipment installation to generate the set of configured rules. The rules engine 124 may then analyze the operating data 130 associated with the particular equipment installation based at least in part on the generated set of configured rules. The rules engine 124 may include a standard interface that is capable of receiving various sets of configurable base rules…”; also, see [0053]).
Claim(s) 5 is rejected under 35 U.S.C. 103 as being unpatentable over Amores et al (US 20210191378) in view of Sinha et al (US 10788798) and Liu et al (US 20220237521) as applied to claim 1 above, and further in view of Mani et (US 11599815).
As per claim 5, Amores teaches the system of claim 1, While Amores teaches collecting data from a plurality of devices (see Fig. 4 and see [0023] and [0032]) but it does not explicitly teach wherein the information from the interface includes information associated with another equipment within a threshold similarity of the equipment (this has been interpreted in the BRI in light of the disclosure as equipment of same model different series, or same type but different manufacturer or same type different model or version, same machine but different location, etc. as suggested in the disclosure, 0078).
However, Mani teaches a monitoring and prediction system comprising collecting information of assets (see Col 1 lines 52-65 and Col 4 lines 23-39), wherein the information from the interface includes information associated with another equipment within a threshold similarity of the equipment (see Col 3 line 63 to Col 4 line 4 “Therefore, it should be notes that, while two assets, Asset A 142A and Asset N 142N, are illustrated in the example embodiment, the system may include any number of assets, which may, depending on the embodiment, be of a same type (e.g. different instances of the same machine), similar type (e.g. different brands or models of machine that perform similar or the same functions),…”).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ combination as taught above to include collecting information of assets, wherein the information from the interface includes information associated with another equipment within a threshold similarity of the equipment as taught by Mani in order to train models with the collected data of similar assets (see Col 14 lines 11-45) and perform anomaly detection of the assets (see Col 8 lines 20-45 and see Col 12 lines 29-38).
Claim(s) 7 and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Amores et al (US 20210191378) in view of Sinha et al (US 10788798) and Liu et al (US 20220237521) as applied to claim 1 above, and further in view of Schwarzkopf et al (US 9986313).
As per claim 7, Amores-Sinha-Liu teaches the system of claim 1, Amores further teaches further comprising a sensor (see [0027] “…AHU 106 can include various sensors (e.g., temperature sensors, pressure sensors, etc.) configured to measure attributes of the supply airflow…), but it does not explicitly teach wherein the modification made to the equipment includes turning on the sensor.
However, Schwarzkopf teaches a monitoring and response system comprising a sensor, wherein a modification made to the equipment includes turning on the sensor (see Fig. 9 step 920 and see Col 10 lines 62 to Col 11 line 10 “When readings from the one or more less energy or resource intensive sensors indicate a possible event or preliminary event, the system or controller 18 may permanently, temporarily, or intermittently activate or change the operating mode of one or more of the sensors in an off state or low power mode to gather additional data regarding the event or preliminary event. For example, the system may keep one or more infrared sensors in an OFF state and one or more additional sensors in an ON state, for example, a temperature sensor and/or a smoke sensor. If and when the one or more additional sensor readings indicate a spike in a temperature or presence of smoke, the system can activate the infrared sensor to read a temperature gradient and more accurately confirm a suspected event such as a fire”, also, see Fig. 8 normal and abnormal modes are detected; Thus, when the system is normal only a subset of sensors are active but when an event/or mode of operation is detected such as an abnormality, then a second subset of sensors is selected).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ combination as taught above to include further sensor, wherein a modification made to the equipment includes turning on the further sensor as taught by Schwarzkopf in order to select a second algorithm including selecting a subset of sensors to gather additional data regarding an event or mode of operation of a component and more accurately confirm a suspected event or prefigure event (see Col 11 lines 1-10).
As per claim 9, Amores-Sinha-Liu teaches the system of claim 1, but it does not explicitly teach further teaches wherein the assessment of the first agent includes adding a sensor (see the BRI interpretation of an agent).
However, Schwarzkopf teaches a monitoring and response system comprising wherein an assessment of a first agent includes adding a sensor (see Fig. 9 step 920; also, see Col 10 lines 62 to Col 11 line 10 “…change the operating mode of one or more of the sensors in an off state or low power mode to gather additional data regarding the event or preliminary event. For example, the system may keep one or more infrared sensors in an OFF state and one or more additional sensors in an ON state, for example, a temperature sensor and/or a smoke sensor. If and when the one or more additional sensor readings indicate a spike in a temperature or presence of smoke, the system can activate the infrared sensor to read a temperature gradient and more accurately confirm a suspected event such as a fire”, also, see Fig. 8 normal and abnormal modes are detected; Thus, when the system is normal only a subset of sensors are active but when an event/or mode of operation is detected such as an abnormality, then a second subset of sensors is selected); also, see Col 35 lines 36-60 “…While performing act 900, a number of temperature sensors in a particular zone plus data from an external weather sensor array 424 indicate sub-freezing outdoor temperatures for the next several hours. Based on these readings, it is determined that a preliminary event corresponding to a potential frozen and/or bursting water pipe is in progress. Action 918 is performed, notifying necessary personnel of the potential for a pipe freezing over the next several hours, and sending a communication to one of the nearby base units 01 connected via external peripheral 30 to control a temporary heat source to raise the heat setting of the temporary heat source. Base unit 01 is further instructed to perform action 920, changing the mode of operation of several sensors including the temperature and humidity sensor to take measurements more often and transmit at a higher frequency, and turns ON PIR sensor to begin looking for detectable temperature profiles…”).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ combination as taught above to include wherein an assessment of a first agent includes adding a sensor as taught by Schwarzkopf in order to gather additional data regarding an event or mode of operation of a component and more accurately confirm a suspected event or prefigure event (see Col 11 lines 1-10).
Claim(s) 10 is rejected under 35 U.S.C. 103 as being unpatentable over Amores et al (US 20210191378) in view of Sinha et al (US 10788798) and Liu et al (US 20220237521) as applied to claim 1 above, and further in view of ZHAO et al (CN 205175690 U, as supported by the machine translation provided).
As per claim 10, Amores-Sinha-Liu teaches the system of claim 1, But it does not explicitly teach wherein the orchestrator is configured to detect an anomaly associated with the equipment based at least in part on digital signal processing (DSP).
However, Zhao teaches a system for detecting faults comprising a device, wherein the device/orchestrator is configured to detect an anomaly associated with an equipment based at least in part on digital signal processing (DSP) (see Abstract “then “…DSP to the message after preprocessing by A/D sampling, through program of DSP for analysis, processing, to obtain peak value factor value and
Kurtosis value of rolling bearing, then up through Ethernet of DSP through the light send to upper position machine, wherein upper place machine the group state software, displaying peak value factor value and kurtosis value…”).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ combination as taught above to include a device/orchestrator, wherein the device/orchestrator is configured to detect an anomaly associated with an equipment based at least in part on digital signal processing (DSP) as taught by Zhao in order to detect failures in equipment in a simple manner (see page 3 par. 6 “…sampling module on the DSP signal processing after A/D sampling and analyzing and processing the signal to obtain the peak factor and kurtosis, light cross-machine to the upper computer configuration software of the upper computer capable of on-line remote monitoring. when the numerical value of the peak factor and kurtosis with big change will send out alarm, convenient maintenance, convenient use and simple operation”).
Claim(s) 14 is rejected under 35 U.S.C. 103 as being unpatentable over Amores et al (US 20210191378) in view of Sinha et al (US 10788798) and Liu et al (US 20220237521) as applied to claim 1 above, and further in view of Pujana (EP 4311934 A1).
As per claim 14, Amores-Sinha-Liu teaches the system of claim 1, Amores further teaches wherein: at least one of the first agent and the second agent is trained using a training data set (see [0088] “…Additionally or alternatively, FDD models 622 may share one or more parameters. FDD models 622 may be generated based on training data…”; also, see [0091] “…As a concrete example, threshold circuit 628 may be trained with a training dataset to determine a threshold that produces accurate fault determinations. Additionally or alternatively, thresholds may be determined dynamically…”); and;
But Amores does not explicitly teach the training data set includes synthetic data associated with a fault in the equipment.
However, Pujana teaches a system of training a model/agent with a dataset, wherein the training data set includes synthetic data associated with a fault in an equipment (see the abstract “…applying a set of failure data (150") and a set of synthetic input data (710) associated to the at least one anomaly situation of the drivetrain to the fault hybrid model (500), thus generating a set of synthetic failure data (750) for the at least one anomaly situation…”; also, see [0013] “…In fact, the
synthetic data generated by the digital twin (in particular, by the fault hybrid model) can be used to augment the training dataset and improve the generalization capacity of the existing data driven models (e.g. a classifier)…”; also, see [0015]).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ combination as taught above to include training a model/agent with a dataset, wherein the training data set includes synthetic data associated with a fault in the equipment as taught by Pujana in order to augment the data in dataset used for training and thus increase and improve the generalization capacity of the model/agent (see [0013], [0015]-[0016]).
Claim(s) 16 is rejected under 35 U.S.C. 103 as being unpatentable over Amores et al (US 20210191378) in view of Sinha et al (US 10788798) and Liu et al (US 20220237521) as applied to claim 1 above, and further in view of Wilson et al (US 20240104473).
As per claim 16, Amores-Sinha-Liu teaches the system of claim 1, Amores further teaches wherein the data pool is assembled according to a unified data acquisition framework including by:
collecting data from at least one sensor based at least in part on defined data standards (see [0046] “…BMS controller 366 may communicate with multiple downstream building systems or subsystems (e.g., HVAC system 100, a security system, a lighting system, waterside system 200, etc.) via a communications link 370 according to like or disparate protocols (e.g., LON, BACnet, etc.)…”, the communication is via a standard; also, see [0047]);
While Amores teaches data normalization, and integration (see 0088), it does not explicitly teach normalizing the collected data and integrating the normalized data.
However, Wilson teaches a system for sensor data normalization comprising collecting data from at least one sensor based at least in part on defined data standards (see the abstract “…The first sensor may be associated with a first vendor and may output data in a first format unique to the first vendor. Second sensor data may be received from a second sensor. The second sensor may be a second sensor type. The second sensor may be associated with a second vendor and may output data in a second format unique to the second vendor. The first and second sensor data may be normalized from the first format and second format to a uniform format unique to an enterprise organization…”), normalizing a collected data (seethe abstract and see [0039] “…For instance, as data from each sensor in the sensor farm is received in its vender-specific format, an adapter configured to modify the vendor-specific formatted data to the enterprise-specific format may be identified and executed to normalize the data and integrate the data into the computing platform 110. Accordingly, an adapter for each vendor, each type of sensor, each model sensor, or the like, may be used to normalize data from a particular sensor…” ) and integrating the normalized data (see [0039] “…integrate…”; also, see [0040]).
Therefore, it would have been obvious to one of ordinary skilled in the art before effective filing date of the claimed invention to which said subject matter pertains to have modified Amores’ Combination to include a system for collecting data from at least one sensor based at least in part on defined data standards, normalizing the collected data and integrating the normalized data as taught by Wilson in order to normalize and integrate data from sensors that have different data format or manufacturers (see the Abstract [0005-0006] “…the first sensor data and second sensor data may be normalized or formatted from the first format and second format to a uniform format. The uniform format may be unique to an enterprise organization. The formatted data may be aggregated and compared to one or more enterprise-specific thresholds. If one or more thresholds have been met or exceeded, a notification may be generated and transmitted to a computing device”).
Conclusion
The prior art made of record and not relied upon, as cited in PTO form 892, is considered pertinent to applicant's disclosure.
Kou et al (US 20230229890) teaches a step of determining if additional data is needed for a first agent/model and obtaining the data (see 0006).
Turkelson et al (US 20210004589) teaches a system for training a model comprising determining an action of whether additional data is needed, and obtaining the data to train a model to increase its performance of prediction (0240).
Leen et al (US 11580379) teaches “If the new model is not as accurate as the previous model, then additional training data can be obtained to continue training the model until the accuracy improves..” (see Col 4 lines 44-66)
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 OLVIN LOPEZ ALVAREZ whose telephone number is (571) 270-7686 and fax (571) 270-8686. The examiner can normally be reached Monday thru Friday from 9:00 A.M. to 6:00 P.M.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Robert Fennema, can be reached at (571) 272-2748. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/O. L./
Examiner, Art Unit 2117
/ROBERT E FENNEMA/Supervisory Patent Examiner, Art Unit 2117
Prosecution Insights