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 43, 45-53 and 67-76 are rejected.
Response to Amendment
The amendment filed on 05/07/2026 has been entered and considered by the examiner. By the
amendment, claims 43, 45-53 are amended, claims 1-42, 44, and 54-66 are cancelled and claims 67-76 are newly added. Following Applicants arguments and amendments made, Examiner modify the prior art rejections. And, the 101 rejection is still maintained. The double patent rejection for claims 54-66 was withdrawn and the previous 112 rejection for claims 55 and 57 are withdrawn. See office action
Response to 101 Arguments
Applicant’s arguments, with respect to the rejection(s) of claim(s) 43 under 35 U.S.C. 101, have been considered but they are not persuasive. The applicant argues that the amended claims of cannot practically be generated in the human mind, or even with the aid of pen and paper”, and therefore overcome the 101 rejections. The examiner respectfully disagrees. The steps of receiving data values, adjusting parameters, and predicting future values can be performed entirely in the human mind or with pen and paper as a mathematical exercise. The claim recites generic hardware like a "first device," a "second device," and a "physical component” in an industrial environment which are generic computer components and thus merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f). Transmitting model parameters and using predicted values to cause a generic "physical control action" are mere data-gathering and post-solution steps and thus falls under the insignificant extra solution activity as recited in MPEP 2106.05(g) The Applicant argues based on specification to reduce network bandwidth and computational power, but the instant claim itself does not recite how the model is structurally improved or how a specific technological process is transformed; it merely states the result of sending parameters instead of data. Simply adding a generic step like "causing a physical control action to be performed" does not automatically make the claim eligible since the action merely uses the result of a mathematical calculation and mental process in a conventional way without improving the operational steps of the physical component itself. The additional elements and use in the claim do not operate to overcome the previous 101 abstract idea rejection. The amended operations are determined to be equivalent to generally linking the use of the judicial exception to a particular technological environment or field of use; and adding the words “apply it” (or an equivalent, i.e., “[re]training”) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f). See 35 U.S.C 101 section for full, updated analysis of claim limitations necessitated by applicant amendments.
Applicant argues these plurality of model parameters are neural weights/biases, however after looking Claim 45, the predictive model parameters are data driven parameters (see claim 45-motion vectors) predicted by the predictive model, thus they are not the internal parameter of the model as the Applicant argues. Applicant is encouraged to add clarifying amendments of the “predictive model parameters” steps/training performed by the invention so that the recitations of predictive learning are not at a high level.
Response to Applicant 102 arguments
Following Applicants arguments and amendments, the 102 rejection of the claims is Withdrawn. See updated 103 below that is necessitated by applicant’s amendment. New reference is added.
Claim Rejections - 35 USC §101
9. 35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
4. Claims 43, 45-63, 67-76 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. These claims are directed to an abstract idea without significantly more.
(Step 1) Is the claims to a process, machine, manufacture, or composition of matter?
Claims: 43, 45-63 and 67-68 are directed to method or process, which falls into the one of the statutory category.
Claims: 69-76 and are directed to system or machine, which falls into the one of the statutory category.
(Step 2A) (Prong 1) Is the claim directed to a law of nature, a natural phenomenon, or an abstract idea? (Judicially recognized exceptions)?
Claim 43 recites
generating, and refining ….a first predictive model for predicting future data values of the first device based on the received plurality of data values, wherein the generating and the refining of the first predictive model comprises determining and adjusting a plurality of predictive model parameters based on newly received data values of the plurality of data values of the first device; (a modeler must form an abstract understanding (a mental model) of the system under study and decide how different variables might interact. This initial diagram or framework of key players and interactions is conceptual and guides the selection of the appropriate mathematical approach. The choice of which variables to include, the underlying assumptions about the data, and the interpretation of the model's results (e.g., what a specific parameter value reflects about a cognitive process) are all abstract, mental processes. Thus, it falls under the combination of mental process and mathematical concepts of abstract idea)
parameterizing, a second predictive model using the plurality of the predictive model parameters; (mentally/with the aid of pen and paper parameterizing…a predictive model using the set of model parameters included in the selected at least one predictive model data stream (e.g. by thinking of/writing out tuning the calculation setting values to match the chosen observed thought values. Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract ideas), and
predicting, future values of the first device using the parameterized second predictive model. (mentally/with the aid of pen and paper predicting…the future data values of the data source using the parameterized predictive model (e.g. by thinking of/writing out the tuned calculation to output values based on the input of remembered values. Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract ideas).
Step 2A, Prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application?
In accordance with Step 2A, Prong 2, the judicial exception is not integrated into a practical application In particular the claim 43 recites the additional elements of receiving, by the first device, a plurality of data values of a data stream, wherein the plurality of data values comprise sensor data collected from one or more sensor devices in an industrial environment; transmitting, by the first device, the plurality of predictive model parameters to the second device; receiving, by the second device, the plurality of predictive model parameters which are mere data gathering or transmission steps and thus it falls under insignificant extra-solution activity to the judicial exception, as discussed in MPEP § 2106.05(g) The additional elements of causing, by the second device, a physical control action to be performed with respect to a physical component in the industrial environment, wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device is merely reciting the words “apply it” (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f); The additional elements of “by the first device and “by the second device” in claim 43 are merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f). Thus, a computer-implemented method for transmitting a predictive model of a first device from the first device to a second device more than generally linking the use of the judicial exception to a particular technological environment or field of use, and do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea (Step 2A, Prong 2; see MPEP 2106.05(h)). These additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
In accordance with Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. In accordance with Step 2A, Prong 2, the judicial exception is not integrated into a practical application. In particular the claim 43 recites the additional elements of receiving, by the first device, a plurality of data values of a data stream, wherein the plurality of data values comprise sensor data collected from one or more sensor devices in an industrial environment; transmitting, by the first device, the plurality of predictive model parameters to the second device; receiving, by the second device, the plurality of predictive model parameters which are mere data gathering or transmission steps and thus it falls under insignificant extra-solution activity to the judicial exception, as discussed in MPEP § 2106.05(g) and is well-understood, routine or conventional. ((See MPEP 2106.05 (d)(II)(i))) Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v.Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014). The additional elements of causing, by the second device, a physical control action to be performed with respect to a physical component in the industrial environment, wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device is merely reciting the words “apply it” (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f); The additional elements of “by the first device and “by the second device” in claim 43 are merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f). Thus, a computer-implemented method for transmitting a predictive model of a first device from the first device to a second device more than generally linking the use of the judicial exception to a particular technological environment or field of use, and do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea (Step 2A, Prong 2; see MPEP 2106.05(h)). Thus, claim 43 is not patent eligible.
Claim 45 further recites wherein the plurality of predictive model parameters comprises a motion vector associated with a robot. A person mentally/with the aid of pen and paper write the plurality of predictive model parameters is a motion vector associated with a robot (e.g. by mentally/writing out the vectorized data includes a movement vector of a remembered robot)Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract idea. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 46 further recites wherein the future values predicted using the parameterized second predictive model comprise one or more future predicted locations of the robot. A person mentally/with the aid of pen and paper predict the future values that comprise one or more future predicted locations of the robot (e.g. by mentally/writing out the calculation output includes a predicted placement of the remembered robot). Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract idea. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 47 further recites wherein the parameterized second predictive model is a behavior analysis model, wherein the future values indicate a predicted behavior of an entity. A person mentally/with the aid of pen and paper wherein the predictive model is a behavior analysis model (e.g. by mentally/writing out the calculation in a behavior model architecture). Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract idea. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 48 further recites wherein the parameterized second predictive model is an augmentation model, wherein the future values correspond to an inoperative sensor. A person mentally/with the aid of pen and paper wherein the predictive model is an augmentation model (e.g. by mentally/writing out the calculation in a future data values of an inoperative sensor). Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract idea. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 49 further recites wherein the parameterized second predictive model is a classification model, wherein the future values indicate a predicted future state of a system comprising the one or more sensor devices. A person •mentally/with the aid of pen and paper wherein the predictive model is a classification model (e.g. by mentally/writing out the calculation in a classification model architecture). Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract idea. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 50 further recites wherein the one or more sensor devices are security cameras, wherein the data stream comprises motion vectors extracted from video data captured by the security cameras. It is recited at a high level generally link the use of the judicial exception to a particular technological environment or field of use, and do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea (Step 2A, Prong 2; see MPEP 2106.05(h)). The additional elements in the claims do not amount to significantly more than an abstract idea. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements to perform the steps of in the dependent claims and perform the steps of the claims amount to no more than mere instructions to apply the exception using generic computer components and generally link the use of the judicial exception to a particular technological environment or field of use. Generally linking the use of the judicial exception to a particular technological environment or field of use cannot provide an inventive concept. (STEP 2B). As such, dependent claims 50 and 65 additional elements or combination of elements do not amount to significantly more than an abstract idea nor provide any inventive concept, nor impose a meaningful limit to integrate the elements into a practical application or significantly more than the judicial exceptions; therefore, the dependent claims are not deemed patent eligible.
Claim 51 further recites wherein the one or more sensor devices are vibration sensors measuring vibrations generated by machines, wherein the future data values indicate a potential need for maintenance of the machines. It is recited at a high level generally link the use of the judicial exception to a particular technological environment or field of use, and do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea (Step 2A, Prong 2; see MPEP 2106.05(h)). The additional elements in the claims do not amount to significantly more than an abstract idea. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements to perform the steps of in the dependent claims and perform the steps of the claims amount to no more than mere instructions to apply the exception using generic computer components and generally link the use of the judicial exception to a particular technological environment or field of use. Generally linking the use of the judicial exception to a particular technological environment or field of use cannot provide an inventive concept. (STEP 2B). As such, dependent claims 51 additional elements or combination of elements do not amount to significantly more than an abstract idea nor provide any inventive concept, nor impose a meaningful limit to integrate the elements into a practical application or significantly more than the judicial exceptions; therefore, the dependent claims are not deemed patent eligible.
Claim 52 further recites wherein refining the first predictive model of the first device adjusts the plurality of predictive model parameters. Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract idea. The additional elements of receiving, by the first device, additional data values of the data stream and transmitting the adjusted plurality of predictive model parameters to the second device which are mere data gathering or transmission steps and thus it falls under insignificant extra-solution activity to the judicial exception, as discussed in MPEP § 2106.05(g) and is well-understood, routine or conventional. ((See MPEP 2106.05 (d)(II)(i))) Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v.Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014). The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 53 further recites re-parameterizing the parameterized second predictive model of the second device using the adjusted plurality of predictive model parameters; and generating additional future data values using the re-parameterized second predictive model of the second device. Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract idea. The additional elements of receiving, by the second device, the adjusted plurality of predictive model parameters which are mere data gathering steps and thus it falls under insignificant extra-solution activity to the judicial exception, as discussed in MPEP § 2106.05(g) and is well-understood, routine or conventional. ((See MPEP 2106.05 (d)(II)(i))) Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v.Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014). The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 67 further recites predicting, by the second device, a fault condition in the industrial environment based on the future data values predicted by the parameterized second predictive model of the second device; and generating a response to the predicted fault condition in the industrial environment, wherein the response comprises the physical control action caused based at least in part on the predicted fault condition. A human engineer can look at historical data columns on a notepad, calculate future trends using basic math/statistics (a "predictive model"), decide a fault will happen, and write down an instruction telling a technician to pull a physical lever (the "physical control action"). Because the pure cognitive/calculation part can be done mentally or on paper, it falls under the mental process exception. The recitation of "the second device" or a "parameterized second predictive model" are mere using generic computer components to perform an abstract idea and does not integrate the abstract idea into a practical technological improvement. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 68 further recites wherein the physical control action comprises at least one of: adjusting an operating parameter of the physical component in the industrial environment, issuing a control instruction to a physical actuator associated with the physical component, or modifying a data collection configuration of the one or more sensor devices, wherein the physical control action is selected based on a type of future state predicted by the parameterized second predictive model of the second device. This is merely reciting the words “apply it” (or an equivalent) with the judicial exception as discussed in MPEP § 2106.05(f); The recitation of claim limitations that attempt to cover any solution to an identified problem with no restriction on how the result is accomplished and no description of the mechanism for accomplishing the result, does not integrate a judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words “apply it”. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Regarding claim 69
(Step 2A) (Prong 1) Is the claim directed to a law of nature, a natural phenomenon, or an abstract idea? (Judicially recognized exceptions)?
Claim 69 recites
generate, and refine ….using the received plurality of data values, a first predictive model for predicting future values of the first device, wherein the generating and the refining of the first predictive model includes determining and adjusting a plurality of predictive model parameters based on newly received data values of the plurality of data values; (a modeler must form an abstract understanding (a mental model) of the system under study and decide how different variables might interact. This initial diagram or framework of key players and interactions is conceptual and guides the selection of the appropriate mathematical approach. The choice of which variables to include, the underlying assumptions about the data, and the interpretation of the model's results (e.g., what a specific parameter value reflects about a cognitive process) are all abstract, mental processes. Thus, it falls under the combination of mental process and mathematical concepts of abstract idea)
parameterize, a second predictive model using the plurality of the predictive model parameters; (mentally/with the aid of pen and paper parameterizing…a predictive model using the set of model parameters included in the selected at least one predictive model data stream (e.g. by thinking of/writing out tuning the calculation setting values to match the chosen observed thought values. Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract ideas), and
predict, future values of the first device using the parameterized second predictive model. (mentally/with the aid of pen and paper predicting…the future data values of the data source using the parameterized predictive model (e.g. by thinking of/writing out the tuned calculation to output values based on the input of remembered values. Under the broadest reasonable interpretation, this limitation covers mental process including an evaluation or judgement that could be performed in the human mind or with the aid of pencil and paper therefore it falls within the “Mental Process” grouping of abstract ideas).
Step 2A, Prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application?
In accordance with Step 2A, Prong 2, the judicial exception is not integrated into a practical application In particular the claim 69 recites the additional elements of one or more sensor devices disposed in an industrial environment and configured to generate sensor data, receive a plurality of data values of a data stream, wherein the plurality of data values comprise sensor data collected from one or more sensor devices in an industrial environment; transmit, the plurality of predictive model parameters to the second device; receive, , the plurality of predictive model parameters from the first device which are mere data gathering or transmission steps and thus it falls under insignificant extra-solution activity to the judicial exception, as discussed in MPEP § 2106.05(g) The additional elements of cause a physical control action to be performed with respect to a physical component in the industrial environment, wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device is merely reciting the words “apply it” (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f); The additional elements of a system for transmitting a predictive model of a future values from a first device to a second device, the system comprising: the first device including: a first processor including a first modelling system, a first memory, and a first transceiver module and the second device including: a second processor including a second modelling system, a second memory, and a second transceiver module, the second device communicatively coupled to the first device in claim 69 are merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f). These additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
In accordance with Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. In accordance with Step 2A, Prong 2, the judicial exception is not integrated into a practical application. In particular the claim 69 recites the additional elements of one or more sensor devices disposed in an industrial environment and configured to generate sensor data , receive a plurality of data values of a data stream, wherein the plurality of data values comprise sensor data collected from one or more sensor devices in an industrial environment; transmit, the plurality of predictive model parameters to the second device; receive, , the plurality of predictive model parameters from the first device which are mere data gathering or transmission steps and thus it falls under insignificant extra-solution activity to the judicial exception, as discussed in MPEP § 2106.05(g) and is well-understood, routine or conventional. ((See MPEP 2106.05 (d)(II)(i))) Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v.Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014). The additional elements of cause a physical control action to be performed with respect to a physical component in the industrial environment, wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device is merely reciting the words “apply it” (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f); The additional elements of a system for transmitting a predictive model of a future values from a first device to a second device, the system comprising: the first device including: a first processor including a first modelling system, a first memory, and a first transceiver module and the second device including: a second processor including a second modelling system, a second memory, and a second transceiver module, the second device communicatively coupled to the first device in claim 69 are merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f). Thus, claim 69 is not patent eligible.
Claim 70 further recites train and execute a classification model using the data values received from the one or more sensor devices, wherein the classification model outputs predicted states or conditions of the industrial environment based on the data values; and generate the first predictive model, including the predictive model parameters, based on the predicted states or conditions of the industrial environment, such that the first predictive model will generate the predicted states or conditions of the industrial environment without accessing the data values from the one or more sensor devices. Training a model, predicting states, and generating parameters are cognitive tasks. A human can do these steps in their head or on paper. A person can read sensor numbers on a clipboard, write down a guess of the plant state, and make a simple rule to guess future states without looking at the sensors again. Reciting "one or more sensor devices" or a generic processor to "train and execute" does not save the claim. Under MPEP § 2106.05(f), mere instructions to apply an abstract idea on generic hardware fail to provide an inventive concept or practical application integration under Step 2A Prong Two / Step 2B. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 71 further recites wherein the second device further comprises a controller configured to cause the physical control action by issuing a command to a physical actuator in the industrial environment, wherein the command causes the physical actuator to perform at least one of: stopping an assembly line, shutting a valve, or activating or deactivating a machine in the industrial environment in response to the future values indicating a predicted failure or off- nominal condition of the physical component, and wherein the command is issued before the predicted failure or off-nominal condition occur. It is causing a generic physical action (stopping a line, shutting a valve) in response to a predicted abstract which is mere post-solution activity. It applies an abstract prediction to a generic industrial environment rather than improving how the machinery or actuator operates. Reciting that a "controller" causes a "physical control action" is viewed as mere "extra-solution activity" or "instructions to apply an exception on a generic computer. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 72 further recites wherein the physical component in the industrial environment is a bearing, and wherein the parameterized second predictive model of the second device predicts at least one of. a vibration amplitude, a vibration frequency, or a vibration phase location corresponding to the bearing, and wherein the second device causes the physical control action to be performed based on the predicted at least one of: the vibration amplitude, the vibration frequency, or the vibration phase location indicating a predicted bearing failure. A human engineer can theoretically look at raw vibration numbers on a sheet of paper, calculate frequencies or phase shifts using math formulas, and write down "bearing failure predicted." Thus, the claim recites a mental process (evaluating parameters to judge bearing health via a predictive model). Reciting that a "second device" causes a "physical control action" is viewed as mere "extra-solution activity" or "instructions to apply an exception on a generic computer. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 73 further recites wherein the one or more sensor devices are security cameras disposed in the industrial environment, wherein the first predictive model comprises motion vectors extracted from video data captured by the security cameras, wherein the parameterized second predictive model predicts future locations of entities in the industrial environment based on the motion vectors, and wherein the second device causes the physical control action in response to a predicted future location indicating an anomalous security condition. Extracting motion vectors, running predictive models, and evaluating conditions are mental processes or abstract mathematical calculations that can conceptually be done via pen and paper. A human security analyst can watch camera feeds, manually draw or calculate motion vectors on paper, predict where a person will walk, and decide if it looks anomalous. Reciting "security cameras," a "first predictive model," and a “second device” amount to generic implementation instructions without improving computer or camera functionality itself. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 74 further recites wherein the one or more sensor devices are vibration sensors communicatively coupled to a rotating or oscillating machine in the industrial environment, wherein the data values comprise vibration data generated by the rotating or oscillating machine, wherein the parameterized second predictive model of the second device predicts a future vibration state of the rotating or oscillating machine indicating a potential need for maintenance, and wherein the second device causes the physical control action comprising initiating a maintenance procedure for the rotating or oscillating machine based on the predicted future vibration state. The steps of receiving data values, applying a predictive model based on motion/vibration vectors, and determining a future state or anomaly are mental processes. A human analyst can watch video footage, sketch motion vectors on a notepad, calculate future locations, and decide an anomaly occurred. Similarly, a technician can look at a log of vibration numbers, plot them on graph paper, extrapolate a trend line, and write down "schedule maintenance”. Reciting generic hardware—such as "security cameras," "vibration sensors," and a "second device"—does not integrate the mental process into a practical application since it is only the hardware that performs generic data gathering. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 75 further recites wherein the first device is configured to continue generating and refining the predictive model and adjusting the plurality of predictive model parameters based on newly received data values from the one or more sensor devices during periods when the first device is disconnected from a network connecting the first device to the second device, and wherein the first device is further configured to transmit the adjusted plurality of predictive model parameters to the second device upon reconnection to the network. The recited functions—continuously refining a model, adjusting parameters based on data values during a network disconnect, and transmitting parameters upon reconnection—fall under the mental process grouping of abstract ideas. Merely assigning these steps to generic components like "a first device," "sensor devices," and a "network" does not provide the practical application. The claim recites generic functional terms ("first device," "one or more sensor devices," "network"). Under MPEP § 2106.05(f), reciting generic hardware to perform an abstract calculation is "instructions to apply an exception" and does not integrate the idea into a practical application. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim 76 further recites wherein the one or more sensor devices comprise security sensors disposed in the industrial environment and configured to generate security sensor data, wherein the data values comprise the security sensor data, wherein the first modelling system of the first device generates and refines the predictive model for predicting future security states of the industrial environment based on the security sensor data, wherein the second device detects an anomalous security condition in the industrial environment based on future data values predicted by the parameterized second predictive model of the second device and causes the physical control action in response to the detected anomalous security condition, wherein the physical control action comprising restricting physical access to a portion of the industrial environment based on the future data values predicted by the parameterized second predictive model of the second device indicating a predicted security event in the industrial environment, and wherein the physical control action is caused to occur prior to the predicted security event occurring. Generating a predictive model, processing sensor values, and predicting a future state are categorized under mental processes (evaluating/analyzing information). If a person can look at past log entries on a sheet of paper, calculate a trend, and write down a prediction, the core analysis is considered practical to conceptualize mentally. A human security analyst can read security logs (sensor data), write down calculations on a notepad to update a predictive risk formula (refine the model), notice a trend indicating trouble (detect condition), and lock a door (restrict access) before an incident occurs. Reciting "security cameras," "the first modeling system," and “the second device” amount to generic implementation instructions without improving computer or camera functionality itself. The claim does not include any additional element; thus, it does not integrate the judicial exception into a practical application nor amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 103
5. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
6. 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.
7. The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
8. This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
9. Claims 43, 47, 49, 51, 52, 53, 67, 68 and 69 are rejected under 35 U.S.C. 103 as being unpatentable over Kaira et al. (PUB NO: US20220004174A1) in view of Kirshenbaum et al (PUB NO: US 20060173559 A1)
Regarding claim 43
Kaira teaches a computer implemented method of ingested and analyzed—at the edge or in the cloud—to train predictive analytics models using machine learning algorithms. See para 77- The resulting training datasets are then used to train and create machine learning models 210 a-n (e.g., predictive models), each of which applies to a specific machine group. Each model 210 a-n is trained to predict a target variable based on the training dataset 202 for a particular group. see para 93-FIG. 4 illustrates an example of a computing device 400 for predictive analytics model management in accordance with certain embodiments. In some embodiments, for example, computing device 400 may be used to implement the predictive analytics model management functionality described throughout this disclosure.) the system comprising:
receiving, by the first device, a plurality of data values, wherein the plurality of data values includes sensor data collected from the one or more sensor devices in an industrial environment;(see para 39- The underlying data values in the data stream—which tend to be heavily represented using time-series data—can include any representation of data from any type or combination of modalities, including configuration data for tasks and equipment (e.g., robots, tools), performance data captured by sensors and other devices. see para 107-108- The flowchart begins at block 502, where a data stream captured at least partially by one or more sensors is received)
generating and refining, by the first device, a first predictive model for predicting future values of the first device based on the received plurality of data values by the first device, (see para 51- Moreover, the data streams generated by the controllers 110 a-d can be ingested and analyzed—at the edge or in the cloud—to train predictive analytics models using machine learning algorithms. see para 77 and fig 2-At the model development phase, the grouping function 208 is applied to the existing training dataset 202. For example, the grouping function is used to split the existing training dataset 202 into smaller training datasets or groups based on machine characteristics. The resulting training datasets are then used to train and create machine learning models 210 a-n (e.g., predictive models), each of which applies to a specific machine group. For example, each model 210 a-n is trained to predict a target variable based on the training dataset 202 for a particular group. The target variable can include any type of predicted information depending on the particular use case that the models 210 a-n are developed and trained for (e.g., a predicted quality level for a quality control use case). see para 60-61- reconfigurations to feed forward learnings for future model development and predictive maintenance of the autonomous agents. The described solution also provides the ability to dynamically reconfigure group(s) based on changes in data stream characteristics with appropriate model tuning.)
wherein the generating and the refining of the first predictive model includes determining and adjusting a plurality of predictive model parameters based on newly received data values of the plurality of data values of the first device; (see para 64-(i) A machine learning model is used to determine parameters from the training dataset 202 (e.g., a set of labeled data points or data streams) that characterize machine groupings. The machine learning model may be implemented using any suitable data grouping model or clustering model, such as k-means clustering. See para 83- If it is determined that the data points of the new machines are not close to any of the data points in the grouping dataset 204, then a new machine group needs to be created. For example, the grouping dataset 204 can be updated by updating the clustering model used to create the grouping dataset 204 to add the new machine group. See para 114-115- Thus, the set of data stream groups may be dynamically updated to reassign the data stream to another data stream group in the set of data stream groups (e.g., an existing group or a newly created group). The flowchart then proceeds to block 506 to determine which data stream group the data stream was assigned to (e.g., group 1, 2, . . . , k), and then to one of blocks 508 a-k to select the predictive analytics model corresponding to that data stream group.)
parameterizing, ; (see para 55-64-(i) A machine learning model is used to determine parameters from the training dataset 202 (e.g., a set of labeled data points or data streams) that characterize machine groupings. The machine learning model may be implemented using any suitable data grouping model or clustering model, such as k-means clustering. In some embodiments, for example, the described solution may include the following features and functionality:(i) analyzing the data streams to characterize similarities of their underlying data;(ii) creating groups of streams based on the similarities; (iii) creating models per group and validating convergence of machine learning models; (iv) dynamically reconfiguring group(s) based on change in data stream characteristics with appropriate model tuning; and/or (v) tracking telemetry of adaptive reconfigurations to feed forward learnings for future model development and predictive maintenance of the autonomous agents.)
the second device; (see para 148- The communication circuitry 912 may be embodied as any communication circuit, device, or collection thereof, capable of enabling communications over a network between the compute circuitry 902 and another compute device (e.g., an edge gateway of an implementing edge computing system). see para 166-A battery monitor/charger 978 may be included in the edge computing node 950 to track the state of charge (SoCh) of the battery 976, if included. The battery monitor/charger 978 may be used to monitor other parameters of the battery 976 to provide failure predictions, such as the state of health (SoH) and the state of function (SoF) of the battery 976. The battery monitor/charger 978 may communicate the information on the battery 976 to the processor 952 over the interconnect 956. The battery monitor/charger 978 may also include an analog-to-digital (ADC) converter that enables the processor 952 to directly monitor the voltage of the battery 976 or the current flow from the battery 976. The battery parameters may be used to determine actions that the edge computing node 950 may perform, such as transmission frequency, mesh network operation, sensing frequency, and the like.)
predicting ; (see para 77 and fig 2-At the model development phase, the grouping function 208 is applied to the existing training dataset 202. For example, the grouping function is used to split the existing training dataset 202 into smaller training datasets or groups based on machine characteristics. The resulting training datasets are then used to train and create machine learning models 210 a-n (e.g., predictive models), each of which applies to a specific machine group. For example, each model 210 a-n is trained to predict a target variable based on the training dataset 202 for a particular group. The target variable can include any type of predicted information depending on the particular use case that the models 210 a-n are developed and trained for (e.g., a predicted quality level for a quality control use case).
causing a physical control action to be performed with respect to a physical component in the industrial environment, (See para 21- In many cases, predictive analytics for various types of events are implemented by software modules that feed into a larger application, and the larger application takes certain actions based on the predictions, such as actions designed to minimize or maximize the likelihood of the predicted events actually occurring (e.g., depending on whether the events are desirable or undesirable). These various use cases are often referred to generally as predictive analytics. see para 37- In the illustrated embodiment, for example, predictive analytics is leveraged to perform quality control on the production line, such as detecting faulty production tasks (e.g., faulty welds), detecting faulty components used or produced during production, proactively detecting and/or performing preventive measures that are likely to prevent or minimize faults during production (e.g., configuration changes and/or maintenance tasks), and so forth.)
Kaira does not teach a computer-implemented method of for transmitting a predictive model of a first device from the first device to a second device; transmitting, by the first device, the plurality of predictive model parameters to the second device; receiving, by the second device, the plurality of predictive model parameters from the first device; parameterizing, by the second device, a second predictive model using the plurality of predictive model parameters; predicting by the second device, future values of the first device using the parameterized second predictive model; and wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device.
In the related field of invention, Kirshenbaum teaches a computer-implemented method of for transmitting a predictive model of a first device from the first device to a second device. (See fig 4 and para 52- FIG. 4 illustrates one embodiment of another system 400. As shown in FIG. 4, the system 400 comprises a first component 402 that provides data sequences 406 and a second component 410)
transmitting, by the first device, the plurality of predictive model parameters to the second device; receiving, by the second device, the plurality of predictive model parameters from the first device; (see para 52-53- The parameterizable data providers 404A-404N generate data or data sequences 406A-406N. These data sequences 406A-406N are provided to the second component 410 via the input/output port 408. FIG. 4, the system 400 comprises a first component 402 that provides data sequences 406 and a second component 410 that monitors the data sequences 406 to detect abnormalities (or data changes of interest) in the data sequences 406. The second component 410 comprises a processor 414 coupled to an input/output port 412 and to a memory 416. See para 62-In such embodiments, the I/O port 408 and the I/O port 412 comprise network ports that allow the transfer of data from the first component 402 to the second component 410 across large distances. Also, the data sequences 418, the training instructions 420, the optimizing instructions, 422 and the monitoring logic 424 may be implemented in separate computing devices and are not necessarily stored and executed by a single computing device. Thus, one computing device may generate a behavior prediction model and another computing device may use the behavior prediction model)
parameterizing, by the second device, a second predictive model using the plurality of predictive model parameters; (see para 0016- in at least some embodiments, a set of parameters according to the parametric model 106 are considered a state description for the system. See para 56- The behavior prediction models are used by the optimizing instructions 422 to predict operant characteristics of the monitoring logic 424. In at least some embodiments, a behavior prediction model predicts operant characteristics based on a state description and a parameterization associated with the monitoring logic 424. See para 42-The optimizer 220 also receives input from a behavior prediction model 122 that predicts operant characteristics of the performance of the detector 224 when the detector 224 is parameterized by a set of parameters. . See para 62-64-Thus, one computing device may generate a behavior prediction model and another computing device may use the behavior prediction model to determine a substantially optimal parameterization of monitoring logic that monitors data to detect changes of interest in the data or abnormal data. The method 600 comprises obtaining a behavior prediction model configured to predict an operant characteristic of a component based on a combination of a state description and a parameterization for the component (block 602).
predicting by the second device, future values of the first device using the parameterized second predictive model; (see para 13- As described below, embodiments of the invention derive and use behavior prediction models capable of predicting of an operant characteristic of a parameterizable system component based on a state description of a system and a parameterization for the system component. See para 42-The optimizer 220 also receives input from a behavior prediction model 122 that predicts operant characteristics of the performance of the detector 224 when the detector 224 is parameterized by a set of parameters. See para 60- the monitoring logic 424 receives and implements the substantially optimal parameterization with a detection or monitoring algorithm (e.g., the detection algorithm 154) to detect abnormalities (or changes of interest) in data sequences 406 being monitored. If a change of interest is detected, the monitoring logic 424 causes the processor 414 (or a separate processing device) to assert a signal 426 (e.g., the change detect signal 226).)
wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device.(see para 32- In a preferred embodiment, the optimization algorithm 146 holds the state description 144 constant while determining optimal values for the detection algorithm's parameters based on predictions, computed according to the behavior prediction model 122, of operant characteristics of the detection algorithm 154 when it is run on a system whose state is described by the state description 144 and when it is parameterized by various sets of detection algorithm parameters. See also para 38-39- The substantially optimal parameterization 150 is provided to the detection algorithm 154, which monitors data 152 from a system having a parameterizable component. In response to detecting a notable change or notable event in the data 152, the detection algorithm 154 outputs a signal 156. The signal 156 also causes other actions in a system to occur (e.g., turning on a fire sprinkler or locking a door).)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include a computer-implemented method of for transmitting a predictive model of a first device from the first device to a second device; transmitting, by the first device, the plurality of predictive model parameters to the second device; receiving, by the second device, the plurality of predictive model parameters from the first device; parameterizing, by the second device, a second predictive model using the plurality of predictive model parameters; predicting by the second device, future values of the first device using the parameterized second predictive model; and wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device as taught by Kirshenbaum in the system of Kaira for determining a substantially optimal parameterization of the system component by predicting operant characteristics of the system component using combinations of state descriptions and possible parameterizations. The substantially optimal parameterization is then applied to the system component. In some embodiments, the system component comprises monitoring logic that detects “notable” changes or events in a system based on the substantially optimal parameterization and data received from the system. (See Kirshenbaum, [0013]).
Regarding claim 47
The combination of Kaira and Kirshenbaum teaches the system of method of claim 43. Kaira further teaches wherein the parameterized second predictive model is a behavior analysis model, wherein the future values indicate a predicted behavior of an entity. (see para 37- In the illustrated embodiment, for example, predictive analytics is leveraged to perform quality control on the production line, such as detecting faulty production tasks (e.g., faulty welds), detecting faulty components used or produced during production, proactively detecting and/or performing preventive measures that are likely to prevent or minimize faults during production (e.g., configuration changes and/or maintenance tasks), and so forth.)
Regarding claim 49
The combination of Kaira and Kirshenbaum teaches the system of method of claim 43. Kaira teaches wherein the parameterized second predictive model is a classification model, (see para 78- In various embodiments, for example, the predictive models may be trained using a variety of different types and combinations of artificial intelligence and/or machine learning, such as logistic regression, random forest, decision trees, classification and regression trees (CART), gradient boosting (e.g., extreme gradient boosted trees), k-nearest neighbors (kNN), Naïve-Bayes, support vector machines (SVM), deep learning (e.g., convolutional neural networks), and/or ensembles thereof (e.g., models that combine the predictions of multiple machine learning models to improve prediction accuracy), among other examples.)
wherein the future values indicate a predicted future state of a system comprising the one or more sensor devices. (see para 163-164- The interconnect 956 may couple the processor 952 to a sensor hub or external interface 970 that is used to connect additional devices or subsystems. The devices may include sensors 972, such as accelerometers, level sensors, flow sensors, optical light sensors, camera sensors, temperature sensors, global navigation system (e.g., GPS) sensors, pressure sensors, barometric pressure sensors, and the like. The hub or interface 970 further may be used to connect the edge computing node 950 to actuators 974, such as power switches, valve actuators, an audible sound generator, a visual warning device, and the like. A display or console hardware, in the context of the present system, may be used to provide output and receive input of an edge computing system; to manage components or services of an edge computing system; identify a state of an edge computing component or service; or to conduct any other number of management or administration functions or service use cases.)
Regarding claim 51
The combination of Kaira and Kirshenbaum teaches the system of method of claim 43. Kaira further teaches wherein the one or more sensor devices are vibration sensors measuring vibrations generated by machines, wherein the future data values indicate a potential need for maintenance of the machines. (See para 137-Example housings and/or surfaces thereof may support one or more sensors (e.g., temperature sensors, vibration sensors, light sensors, acoustic sensors, capacitive sensors, proximity sensors, etc.). see para 19- In industrial settings, for example, one of the leading use cases of predictive analytics is predictive maintenance, where data generated by machines and sensors is used to predict when a particular machine or production line needs maintenance. The algorithms and models developed for predictive maintenance use cases typically aim to minimize downtime and optimize maintenance frequency.)
Regarding claim 52
The combination of Kaira and Kirshenbaum teaches the method of claim 43. Kaira teaches receiving, by the first device, additional data values of the data stream; refining, by the first device, the first predictive model using the additional data values, (see para 83-86- If it is determined that the data points of the new machines are not close to any of the data points in the grouping dataset 204, then a new machine group needs to be created. For example, the grouping dataset 204 can be updated by updating the clustering model used to create the grouping dataset 204 to add the new machine group. This requires the grouping model/function 208 to be redeployed since it depends on the grouping dataset 204. The new group ID and corresponding data points are added to the grouping dataset 204, and a new predictive analytics model 210 is created for that group (e.g., developed/trained) and then deployed with the existing predictive analytics models 210. See para 120 and fig 5- At this point, the flowchart may be complete. In some embodiments, however, the flowchart may restart and/or certain blocks may be repeated. For example, in some embodiments, the flowchart may restart at block 502 to continue receiving data streams and performing predictive analytics on the data streams.)
wherein refining the first predictive model of the first device adjusts the plurality of predictive model parameters; (see para 55-60- In some embodiments, for example, the described solution may include the following features and functionality:(i) analyzing the data streams to characterize similarities of their underlying data;(ii) creating groups of streams based on the similarities; (iii) creating models per group and validating convergence of machine learning models; (iv) dynamically reconfiguring group(s) based on change in data stream characteristics with appropriate model tuning; and/or (v) tracking telemetry of adaptive reconfigurations to feed forward learnings for future model development and predictive maintenance of the autonomous agents.)
Kaira does not teach transmitting the plurality of adjusted predictive model parameters to the second device.
However, Kirshenbaum teaches transmitting the plurality of adjusted predictive model parameters to the second device. ( (see para 52-53- The parameterizable data providers 404A-404N generate data or data sequences 406A-406N. These data sequences 406A-406N are provided to the second component 410 via the input/output port 408. FIG. 4, the system 400 comprises a first component 402 that provides data sequences 406 and a second component 410 that monitors the data sequences 406 to detect abnormalities (or data changes of interest) in the data sequences 406. The second component 410 comprises a processor 414 coupled to an input/output port 412 and to a memory 416. See para 62-In such embodiments, the I/O port 408 and the I/O port 412 comprise network ports that allow the transfer of data from the first component 402 to the second component 410 across large distances. Also, the data sequences 418, the training instructions 420, the optimizing instructions, 422 and the monitoring logic 424 may be implemented in separate computing devices and are not necessarily stored and executed by a single computing device. Thus, one computing device may generate a behavior prediction model and another computing device may use the behavior prediction model)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include transmitting the plurality of adjusted predictive model parameters to the second device as taught by Kirshenbaum in the system of Kaira for determining a substantially optimal parameterization of the system component by predicting operant characteristics of the system component using combinations of state descriptions and possible parameterizations. The substantially optimal parameterization is then applied to the system component. In some embodiments, the system component comprises monitoring logic that detects “notable” changes or events in a system based on the substantially optimal parameterization and data received from the system. (See Kirshenbaum, [0013]).
Regarding claim 53
The combination of Kaira and Kirshenbaum teaches the method of claim 43. Kaira does not teach receiving, by the second device, the adjusted plurality of predictive model parameters; re-parameterizing the parameterized second predictive model of the second device using the adjusted plurality of predictive model parameters; and generating additional future data values using the re-parameterized second predictive model of the second device.
However, Kirshenbaum further teaches receiving, by the second device, the adjusted plurality of predictive model parameters; re-parameterizing the parameterized second predictive model of the second device using the adjusted plurality of predictive model parameters; and generating additional future data values using the re-parameterized second predictive model of the second device. (see para 0016- in at least some embodiments, a set of parameters according to the parametric model 106 are considered a state description for the system. see para 52-53- The parameterizable data providers 404A-404N generate data or data sequences 406A-406N. These data sequences 406A-406N are provided to the second component 410 via the input/output port 408. FIG. 4, the system 400 comprises a first component 402 that provides data sequences 406 and a second component 410 that monitors the data sequences 406 to detect abnormalities (or data changes of interest) in the data sequences 406. See para 56- The behavior prediction models are used by the optimizing instructions 422 to predict operant characteristics of the monitoring logic 424. In at least some embodiments, a behavior prediction model predicts operant characteristics based on a state description and a parameterization associated with the monitoring logic 424. See para 42-The optimizer 220 also receives input from a behavior prediction model 122 that predicts operant characteristics of the performance of the detector 224 when the detector 224 is parameterized by a set of parameters. See para 62-64-Thus, one computing device may generate a behavior prediction model and another computing device may use the behavior prediction model to determine a substantially optimal parameterization of monitoring logic that monitors data to detect changes of interest in the data or abnormal data. The method 600 comprises obtaining a behavior prediction model configured to predict an operant characteristic of a component based on a combination of a state description and a parameterization for the component (block 602). See para 37- The process is repeated for a specified amount of time, a specified number of iterations, or until a specified number of iterations have been performed without discovering a set that is associated with a lower combined cost.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include receiving, by the second device, the adjusted plurality of predictive model parameters; re-parameterizing the parameterized second predictive model of the second device using the adjusted plurality of predictive model parameters; and generating additional future data values using the re-parameterized second predictive model of the second device as taught by Kirshenbaum in the system of Kaira for determining a substantially optimal parameterization of the system component by predicting operant characteristics of the system component using combinations of state descriptions and possible parameterizations. The substantially optimal parameterization is then applied to the system component. In some embodiments, the system component comprises monitoring logic that detects “notable” changes or events in a system based on the substantially optimal parameterization and data received from the system. (See Kirshenbaum, [0013]).
Regarding claim 67
The combination of Kaira and Kirshenbaum teaches the method of claim 43. Kaira does not teach predicting, by the second device, a fault condition in the industrial environment based on the future data values predicted by the parameterized second predictive model of the second device; and generating a response to the predicted fault condition in the industrial environment, wherein the response comprises the physical control action caused based at least in part on the predicted fault condition.
However, Kirshenbaum further teaches predicting, by the second device, a fault condition in the industrial environment based on the future data values predicted by the parameterized second predictive model of the second device; (see para 60-Alternatively, the monitoring logic 424 may comprise instructions or hardware implemented separately from the second component 410. In either case, the monitoring logic 424 receives and implements the substantially optimal parameterization with a detection or monitoring algorithm (e.g., the detection algorithm 154) to detect abnormalities (or changes of interest) in data sequences 406 being monitored. If a change of interest is detected, the monitoring logic 424 causes the processor 414 (or a separate processing device) to assert a signal 426 (e.g., the change detect signal 226). )
and generating a response to the predicted fault condition in the industrial environment, wherein the response comprises the physical control action caused based at least in part on the predicted fault condition. (See para 60-. If a change of interest is detected, the monitoring logic 424 causes the processor 414 (or a separate processing device) to assert a signal 426 (e.g., the change detect signal 226). see para 51-In some embodiments, the signal 156 is used in a variety of ways such as to alert a user of the event or the changes, to activate a logging mechanism, to change behavior of a system being monitored or to cause the system being monitored to perform an action.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include predicting, by the second device, a fault condition in the industrial environment based on the future data values predicted by the parameterized second predictive model of the second device; and generating a response to the predicted fault condition in the industrial environment, wherein the response comprises the physical control action caused based at least in part on the predicted fault condition as taught by Kirshenbaum in the system of Kaira for determining a substantially optimal parameterization of the system component by predicting operant characteristics of the system component using combinations of state descriptions and possible parameterizations. The substantially optimal parameterization is then applied to the system component. In some embodiments, the system component comprises monitoring logic that detects “notable” changes or events in a system based on the substantially optimal parameterization and data received from the system. (See Kirshenbaum, [0013]).
Regarding claim 68
The combination of Kaira and Kirshenbaum teaches the method of claim 43. Kaira further teaches wherein the physical control action comprises at least one of: adjusting an operating parameter of the physical component in the industrial environment, issuing a control instruction to a physical actuator associated with the physical component, or modifying a data collection configuration of the one or more sensor devices. (See para 20-21- The underlying input data—which tends to be heavily represented using time-series data—can include any representation of data from any type or combination of modalities, including configuration and performance data captured by machines and sensors, visual data (e.g., video) captured by cameras and other visual sensors, and so forth. In many cases, predictive analytics for various types of events are implemented by software modules that feed into a larger application, and the larger application takes certain actions based on the predictions, such as actions designed to minimize or maximize the likelihood of the predicted events actually occurring (e.g., depending on whether the events are desirable or undesirable). These various use cases are often referred to generally as predictive analytics. see para 37- In the illustrated embodiment, for example, predictive analytics is leveraged to perform quality control on the production line, such as detecting faulty production tasks (e.g., faulty welds), detecting faulty components used or produced during production, proactively detecting and/or performing preventive measures that are likely to prevent or minimize faults during production (e.g., configuration changes and/or maintenance tasks), and so forth.)
Kaira does not teach wherein the physical control action is selected based on a type of future state predicted by the parameterized second predictive model of the second device.
However, Kirshenbaum further teaches wherein the physical control action is selected based on a type of future state predicted by the parameterized second predictive model of the second device. (see para 13-As described below, embodiments of the invention derive and use behavior prediction models capable of predicting of an operant characteristic of a parameterizable system component based on a state description of a system and a parameterization for the system component. See para 20 see para 20- For example, in some embodiments, the changes to detect signal 110 comprises a statistical distribution of modifications to be made to the parameters of the parametric model 106 contained in a state description drawn from the state description distribution 108)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include wherein the physical control action is selected based on a type of future state predicted by the parameterized second predictive model of the second device as taught by Kirshenbaum in the system of Kaira for determining a substantially optimal parameterization of the system component by predicting operant characteristics of the system component using combinations of state descriptions and possible parameterizations. The substantially optimal parameterization is then applied to the system component. In some embodiments, the system component comprises monitoring logic that detects “notable” changes or events in a system based on the substantially optimal parameterization and data received from the system. (See Kirshenbaum, [0013]).
Regarding claim 69
Kaira teaches a system of at the edge or in the cloud—to train predictive analytics models using machine learning algorithms. See para 77- The resulting training datasets are then used to train and create machine learning models 210 a-n (e.g., predictive models), each of which applies to a specific machine group. Each model 210 a-n is trained to predict a target variable based on the training dataset 202 for a particular group. see para 93-FIG. 4 illustrates an example of a computing device 400 for predictive analytics model management in accordance with certain embodiments. In some embodiments, for example, computing device 400 may be used to implement the predictive analytics model management functionality described throughout this disclosure.) the system comprising:
one or more sensor devices disposed in an industrial environment and configured to generate sensor data;(see fig 4 and para 94-95- The computing device 400 is also coupled to various other devices (e.g., via I/O subsystem 410 and/or NIC 408), such as I/O device(s) 412 (e.g., display/touchscreen, keyboard, mouse, etc.), sensor(s) 414 (e.g., voltage/current sensors, temperature/thermal sensors, humidity sensors, pressure sensors, camera sensors, audio sensors, infrared (IR) sensors, accelerometers, etc.), tool(s) 416 (e.g., welding gun, glue gun, riveting machine, screwdriver, pump, etc.), and/or robot(s) 418. See also para 107-108- The flowchart begins at block 502, where a data stream captured at least partially by one or more sensors is received)
the first device including: a first processor including a first modelling system, a first memory, and a first transceiver module, (see fig 4 and para 94- In the illustrated embodiment, computing device 400 includes processing circuitry 402, memory 404, data storage device 406, network interface controller (NIC) 408, and input/output (I/O) subsystem 410. The processing circuitry 402 includes a collection of processing components 403, such as a processor 403 a (e.g., central processing unit (CPU), microcontroller, etc.) and an artificial intelligence (Al) accelerator 403 b (e.g., co-processor, ASIC, FPGA, etc.).
the first device configured to: receive a plurality of data values, wherein the plurality of data values includes sensor data collected from the one or more sensor devices in the industrial environment;(see para 39- The underlying data values in the data stream—which tend to be heavily represented using time-series data—can include any representation of data from any type or combination of modalities, including configuration data for tasks and equipment (e.g., robots, tools), performance data captured by sensors and other devices. see para 107-108- The flowchart begins at block 502, where a data stream captured at least partially by one or more sensors is received)
generate and refine, by the first modelling system using the received plurality of data values, a first predictive model for predicting future values of the first device, (see para 51- Moreover, the data streams generated by the controllers 110 a-d can be ingested and analyzed—at the edge or in the cloud—to train predictive analytics models using machine learning algorithms. see para 77 and fig 2-At the model development phase, the grouping function 208 is applied to the existing training dataset 202. For example, the grouping function is used to split the existing training dataset 202 into smaller training datasets or groups based on machine characteristics. The resulting training datasets are then used to train and create machine learning models 210 a-n (e.g., predictive models), each of which applies to a specific machine group. For example, each model 210 a-n is trained to predict a target variable based on the training dataset 202 for a particular group. The target variable can include any type of predicted information depending on the particular use case that the models 210 a-n are developed and trained for (e.g., a predicted quality level for a quality control use case). see para 60-61- reconfigurations to feed forward learnings for future model development and predictive maintenance of the autonomous agents. The described solution also provides the ability to dynamically reconfigure group(s) based on changes in data stream characteristics with appropriate model tuning.)
wherein the generating and the refining of the first predictive model includes determining and adjusting a plurality of predictive model parameters based on newly received data values of the plurality of data values; (see para 64-(i) A machine learning model is used to determine parameters from the training dataset 202 (e.g., a set of labeled data points or data streams) that characterize machine groupings. The machine learning model may be implemented using any suitable data grouping model or clustering model, such as k-means clustering. See para 83- If it is determined that the data points of the new machines are not close to any of the data points in the grouping dataset 204, then a new machine group needs to be created. For example, the grouping dataset 204 can be updated by updating the clustering model used to create the grouping dataset 204 to add the new machine group. See para 114-115- Thus, the set of data stream groups may be dynamically updated to reassign the data stream to another data stream group in the set of data stream groups (e.g., an existing group or a newly created group). The flowchart then proceeds to block 506 to determine which data stream group the data stream was assigned to (e.g., group 1, 2, . . . , k), and then to one of blocks 508 a-k to select the predictive analytics model corresponding to that data stream group.)
the second device; (see para 148- The communication circuitry 912 may be embodied as any communication circuit, device, or collection thereof, capable of enabling communications over a network between the compute circuitry 902 and another compute device (e.g., an edge gateway of an implementing edge computing system). see para 166-A battery monitor/charger 978 may be included in the edge computing node 950 to track the state of charge (SoCh) of the battery 976, if included. The battery monitor/charger 978 may be used to monitor other parameters of the battery 976 to provide failure predictions, such as the state of health (SoH) and the state of function (SoF) of the battery 976. The battery monitor/charger 978 may communicate the information on the battery 976 to the processor 952 over the interconnect 956. The battery monitor/charger 978 may also include an analog-to-digital (ADC) converter that enables the processor 952 to directly monitor the voltage of the battery 976 or the current flow from the battery 976. The battery parameters may be used to determine actions that the edge computing node 950 may perform, such as transmission frequency, mesh network operation, sensing frequency, and the like.)
cause a physical control action to be performed with respect to a physical component in the industrial environment, (See para 21- In many cases, predictive analytics for various types of events are implemented by software modules that feed into a larger application, and the larger application takes certain actions based on the predictions, such as actions designed to minimize or maximize the likelihood of the predicted events actually occurring (e.g., depending on whether the events are desirable or undesirable). These various use cases are often referred to generally as predictive analytics. see para 37- In the illustrated embodiment, for example, predictive analytics is leveraged to perform quality control on the production line, such as detecting faulty production tasks (e.g., faulty welds), detecting faulty components used or produced during production, proactively detecting and/or performing preventive measures that are likely to prevent or minimize faults during production (e.g., configuration changes and/or maintenance tasks), and so forth.)
Kaira does no teach a system for transmitting a predictive model of a future values from a first device to a second device; transmit, by the first transceiver module, the plurality of predictive model parameters to the second device; and the second device including: a second processor including a second modelling system, a second memory, a-and a second transceiver module, the second device communicatively coupled to the first device and configured to: receive, by the second transceiver module, the plurality of predictive model parameters from the first device; parameterize, by the second modelling module, a second predictive model using the received plurality of predictive model parameters; predict future values of the first device using the parameterized second predictive model of the second device; and wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device.
In the related field of invention, Kirshenbaum teaches a system for transmitting . (See fig 4 and para 52- FIG. 4 illustrates one embodiment of another system 400. As shown in FIG. 4, the system 400 comprises a first component 402 that provides data sequences 406 and a second component 410)
transmit, by the first transceiver module, the plurality of predictive model parameters to the second device, the second device including: a second processor including a second modelling system, a second memory, and a second transceiver module, the second device communicatively coupled to the first device and configured to: receive, by the second transceiver module, the plurality of predictive model parameters from the first device; (see para 52-53- The parameterizable data providers 404A-404N generate data or data sequences 406A-406N. These data sequences 406A-406N are provided to the second component 410 via the input/output port 408. FIG. 4, the system 400 comprises a first component 402 that provides data sequences 406 and a second component 410 that monitors the data sequences 406 to detect abnormalities (or data changes of interest) in the data sequences 406. The second component 410 comprises a processor 414 coupled to an input/output port 412 and to a memory 416. See para 62-In such embodiments, the I/O port 408 and the I/O port 412 comprise network ports that allow the transfer of data from the first component 402 to the second component 410 across large distances. Also, the data sequences 418, the training instructions 420, the optimizing instructions, 422 and the monitoring logic 424 may be implemented in separate computing devices and are not necessarily stored and executed by a single computing device. Thus, one computing device may generate a behavior prediction model and another computing device may use the behavior prediction model)
parameterize, by the second modelling module, a second predictive model using the received plurality of predictive model parameters; (see para 0016- in at least some embodiments, a set of parameters according to the parametric model 106 are considered a state description for the system. See para 56- The behavior prediction models are used by the optimizing instructions 422 to predict operant characteristics of the monitoring logic 424. In at least some embodiments, a behavior prediction model predicts operant characteristics based on a state description and a parameterization associated with the monitoring logic 424. See para 42-The optimizer 220 also receives input from a behavior prediction model 122 that predicts operant characteristics of the performance of the detector 224 when the detector 224 is parameterized by a set of parameters. . See para 62-64-Thus, one computing device may generate a behavior prediction model and another computing device may use the behavior prediction model to determine a substantially optimal parameterization of monitoring logic that monitors data to detect changes of interest in the data or abnormal data. The method 600 comprises obtaining a behavior prediction model configured to predict an operant characteristic of a component based on a combination of a state description and a parameterization for the component (block 602).
predict future values of the first device using the parameterized second predictive model of the second device; (see para 13- As described below, embodiments of the invention derive and use behavior prediction models capable of predicting of an operant characteristic of a parameterizable system component based on a state description of a system and a parameterization for the system component. See para 42-The optimizer 220 also receives input from a behavior prediction model 122 that predicts operant characteristics of the performance of the detector 224 when the detector 224 is parameterized by a set of parameters. See para 60- the monitoring logic 424 receives and implements the substantially optimal parameterization with a detection or monitoring algorithm (e.g., the detection algorithm 154) to detect abnormalities (or changes of interest) in data sequences 406 being monitored. If a change of interest is detected, the monitoring logic 424 causes the processor 414 (or a separate processing device) to assert a signal 426 (e.g., the change detect signal 226).)
wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device.(see para 32- In a preferred embodiment, the optimization algorithm 146 holds the state description 144 constant while determining optimal values for the detection algorithm's parameters based on predictions, computed according to the behavior prediction model 122, of operant characteristics of the detection algorithm 154 when it is run on a system whose state is described by the state description 144 and when it is parameterized by various sets of detection algorithm parameters. See also para 38-39- The substantially optimal parameterization 150 is provided to the detection algorithm 154, which monitors data 152 from a system having a parameterizable component. In response to detecting a notable change or notable event in the data 152, the detection algorithm 154 outputs a signal 156. The signal 156 also causes other actions in a system to occur (e.g., turning on a fire sprinkler or locking a door).)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include a system for transmitting a predictive model of a future values from a first device to a second device; transmit, by the first transceiver module, the plurality of predictive model parameters to the second device; and the second device including: a second processor including a second modelling system, a second memory, a-and a second transceiver module, the second device communicatively coupled to the first device and configured to: receive, by the second transceiver module, the plurality of predictive model parameters from the first device; parameterize, by the second modelling module, a second predictive model using the received plurality of predictive model parameters; predict future values of the first device using the parameterized second predictive model of the second device and wherein the physical control action is at least partially based on the future values predicted using the parameterized second predictive model of the second device as taught by Kirshenbaum in the system of Kaira for determining a substantially optimal parameterization of the system component by predicting operant characteristics of the system component using combinations of state descriptions and possible parameterizations. The substantially optimal parameterization is then applied to the system component. In some embodiments, the system component comprises monitoring logic that detects “notable” changes or events in a system based on the substantially optimal parameterization and data received from the system. (See Kirshenbaum, [0013]).
10. Claims 45-46, 48, 50 and 70-76 are rejected under 35 U.S.C. 103 as being unpatentable over Kaira et al. (PUB NO: US20220004174A1) in view of Kirshenbaum et al (PUB NO: US 20060173559 A1) and further in view of Cella et al. (PUB NO: US20200225655A1)
Regarding claim 45
The combination of Kaira and Kirshenbaum teaches the method of claim 43. Kaira does not teach wherein the plurality of predictive model parameters is a motion vector associated with a robot.
In the related field of invention, Cella teaches wherein the plurality of predictive model parameters is a motion vector associated with a robot. (See para 361- For example, a model of fuel consumption by an industrial machine may include physical model parameters that characterize weights, motion. See para 984- A convolutional neural network may be used for recognition within images and video streams, such as for recognizing a type of machine in a large environment using a camera system disposed on a mobile data collector, such as on a drone or mobile robot. See para 1091- Ambient noise may be measured by a microphone, ultrasound sensors, acoustic wave sensors, optical vibration sensors (e.g., using a camera to see oscillations that produce noise), or “deep learning” neural networks involving various sensor arrays that learn, using large data sets, to identify patterns, sounds types, noise types, etc. In an embodiment, the ambient sensed condition may relate to motion detection. For example, the motion may be a platform motion (e.g., vehicle, oil platform, suspended platform on land, etc.) or an object motion (e.g., moving equipment, people, robots, parts (e.g., fan blades or turbine blades), etc.). see para 2377- At 29612, the edge device 28704 may generate one or more feature vectors based on the sensor data)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include wherein the plurality of predictive model parameters is a motion vector associated with a robot as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 46
The combination of Kaira and Kirshenbaum teaches the method of claim 43. Kaira does not teach wherein the future values predicted using the parameterized second predictive model of the data stream comprise one or more future predicted locations of the robot.
In the related field of invention, Cella teaches wherein the future values predicted using the parameterized second predictive model of the data stream comprise one or more future predicted locations of the robot. (see para 243- For example, data streams from vibration, pressure, temperature, accelerometer, magnetic, electrical field, and other analog sensors may be multiplexed or otherwise fused, relayed over a network, and fed into a cloud-based machine learning facility, which may employ one or more models relating to an operating characteristic of an industrial machine, an industrial process, or a component or element thereof. The learning machine may then operate on other data, initially using a set of rules or elements of a model, such as to provide a variety of outputs, such as classification of data into types, recognition of certain patterns. The machine learning facility may take feedback, such as one or more inputs or measures of success, such that it may train, or improve, its initial model (such as improvements by adjusting weights, rules, parameters, or the like, based on the feedback). see para 1091- Ambient noise may be measured by a microphone, ultrasound sensors, acoustic wave sensors, optical vibration sensors (e.g., using a camera to see oscillations that produce noise), or “deep learning” neural networks involving various sensor arrays that learn, using large data sets, to identify patterns, sounds types, noise types, etc. In an embodiment, the ambient sensed condition may relate to motion detection. For example, the motion may be a platform motion (e.g., vehicle, oil platform, suspended platform on land, etc.) or an object motion (e.g., moving equipment, people, robots, parts (e.g., fan blades or turbine blades), etc.). In an embodiment, the ambient sensed condition may be sensed by imaging, such as to detect a location and nature of various machines, equipment, and other objects, such as ones that might impact local vibration. See para 1068-1071- The machine learning data analysis circuit 10712 may be disposed in part on a machine, on one or more data collectors, in network infrastructure, in the cloud, or any combination thereof.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include wherein the future values predicted using the parameterized second predictive model of the data stream comprise one or more future predicted locations of the robot as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 48
The combination of Kaira and Kirshenbaum teaches the method of claim 43. Kaira further teaches wherein the parameterized second predictive model is an augmentation model, (See para 114-Thus, in some embodiments, the groupings may be dynamically updated to adapt to changes in data stream characteristics. See also para [0083-0086]- a new predictive analytics model 210 is created for that group (e.g., developed/trained) and then deployed with the existing predictive analytics models 210.)
Kaira does not teach wherein the future values correspond to an inoperative sensor.
In the related field of invention, Cella teaches wherein the future values correspond to an inoperative sensor. (See para 1068-The data collection band circuit may alter the subset of the plurality of sensors when the learned received output data pattern does not reliably predict the state, which may include discontinuing collection of data from the at least one sub set. see para 1071-wherein the data collection band circuit 10708 alters the at least one of the plurality of sensors 10702 when the learned received output data pattern 10718 does not reliably predict the state.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include wherein the future values correspond to an inoperative sensor as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 50
The combination of Kaira and Kirshenbaum teaches the method of claim 43. Kaira further teaches wherein the sensors are security cameras, wherein the data stream comprises (see para 39- The underlying data values in the data stream—which tend to be heavily represented using time-series data—can include any representation of data from any type or combination of modalities, including configuration data for tasks and equipment (e.g., robots, tools), performance data captured by sensors and other devices, visual data—such as images and video—captured by cameras and other visual sensors, audio captured by microphones, and so forth. )
The combination of Kaira and Kirshenbaum does not teach motion vectors extracted from video data.
However, Cella further teaches motion vectors extracted from video data. (see para 361- For example, a model of fuel consumption by an industrial machine may include physical model parameters that characterize weights, motion. See para 984- A convolutional neural network may be used for recognition within images and video streams, such as for recognizing a type of machine in a large environment using a camera system disposed on a mobile data collector, such as on a drone or mobile robot. See para 1091- Ambient noise may be measured by a microphone, ultrasound sensors, acoustic wave sensors, optical vibration sensors (e.g., using a camera to see oscillations that produce noise), or “deep learning” neural networks involving various sensor arrays that learn, using large data sets, to identify patterns, sounds types, noise types, etc. In an embodiment, the ambient sensed condition may relate to motion detection. For example, the motion may be a platform motion (e.g., vehicle, oil platform, suspended platform on land, etc.) or an object motion (e.g., moving equipment, people, robots, parts (e.g., fan blades or turbine blades), etc.). see para 2377- At 29612, the edge device 28704 may generate one or more feature vectors based on the sensor data)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include motion vectors extracted from video data as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 70
The combination of Kaira and Kirshenbaum teaches the system of claim 69. Kaira further teaches wherein the first modelling system of the first device is further configured to: train and execute a classification model using the data values received from the one or more sensor devices, wherein the classification model outputs predicted states or conditions of the industrial environment based on the data values; (see para 54- The predictive analytics model management system 100 leverages the concept of collaborative filtering to group data streams based on data characteristics of the different machines or streams, train a predictive analytics model for each group, and classify live data streams using the prediction model corresponding to the group of each stream. See also para 78-79-- At the deployment phase, the resulting models 210 a-n are then deployed and used to perform inference or classification on live data streams to generate predictions 212 associated with those data streams (e.g., based on whatever type of prediction or use case the models were trained for). See also para 91-As an example, predictive analytics models for the respective groups could be trained based on certain features represented in the respective training datasets for an industrial use case, such as predicting or determining the quality of spot welds (e.g., good vs. defective/errored) based on certain features or characteristics represented in the data streams generated for the spot welds.)
Kaira does not teach generate the first predictive model, including the predictive model parameters, based on the predicted states or conditions of the industrial environment, such that the first predictive model will generate the predicted states or conditions of the industrial environment without accessing the data values from the one or more sensor devices.
In the related field of invention, Cella teaches generate the first predictive model, including the predictive model parameters, based on the predicted states or conditions of the industrial environment, (see para 1068-1069-and fi g140-The machine learning data analysis circuit may be structured to learn received output data patterns 10718 by being seeded with a model 10720, which may be a physical model, an operational model, or a system model. The controller 10706 may adjust the weights/biases of the machine learning data analysis circuit 10712, such as in response to the learned received output data patterns 10718, in response to the accuracy of the prediction of an anticipated state by the machine learning data analysis circuit, in response to the accuracy of a classification of a state by the machine learning data analysis circuit, and the like)
such that the first predictive model will generate the predicted states or conditions of the industrial environment without accessing the data values from the one or more sensor devices. (see para 1068-The data collection band circuit may alter the subset of the plurality of sensors when the learned received output data pattern does not reliably predict the state, which may include discontinuing collection of data from the at least one sub set. see para 1071-wherein the data collection band circuit 10708 alters the at least one of the plurality of sensors 10702 when the learned received output data pattern 10718 does not reliably predict the state.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include generate the first predictive model, including the predictive model parameters, based on the predicted states or conditions of the industrial environment, such that the first predictive model will generate the predicted states or conditions of the industrial environment without accessing the data values from the one or more sensor devices as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 71
The combination of Kaira and Kirshenbaum teaches the system of claim 69. Kaira does not teach wherein the second device further comprises a controller configured to cause the physical control action by issuing a command to a physical actuator in the industrial environment, wherein the command causes the physical actuator to perform at least one of: stopping an assembly line, shutting a valve, or activating or deactivating a machine in the industrial environment in response to the future values indicating a predicted failure or off- nominal condition of the physical component, and wherein the command is issued before the predicted failure or off-nominal condition occurs.
However, Cella further teaches wherein the second device further comprises a controller configured to cause the physical control action by issuing a command to a physical actuator in the industrial environment, wherein the command causes the physical actuator to perform at least one of: stopping an assembly line, shutting a valve, or activating or deactivating a machine in the industrial environment in response to the future values indicating a predicted failure or off- nominal condition of the physical component, and wherein the command is issued before the predicted failure or off-nominal condition occurs.(see para 2345- For example, the control module 29130 may issue a command to a manufacturing facility to stop an assembly line in response to a determination that a critical component on the assembly line is likely failing or likely failed. In another example, the control module 29130 may issue a command to an agricultural facility to activate a dehumidifier in response to a determination that the humidity levels are too high in the facility. In another example, the control module 29130 may issue a command to shut a valve in an oil pipeline in response to a determination that a component in the oil pipeline downstream to the valve is likely failing or likely failed. See para 2451-n embodiments, the present disclosure may include situations, wherein the current status of the at least one of the plurality of components or the production process includes at least one value selected from the values consisting of a process failure value, an off-nominal process value)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include wherein the second device further comprises a controller configured to cause the physical control action by issuing a command to a physical actuator in the industrial environment, wherein the command causes the physical actuator to perform at least one of: stopping an assembly line, shutting a valve, or activating or deactivating a machine in the industrial environment in response to the future values indicating a predicted failure or off- nominal condition of the physical component, and wherein the command is issued before the predicted failure or off-nominal condition occurs as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 72
The combination of Kaira and Kirshenbaum teaches the system of claim 69. Kaira does not teach wherein the physical component in the industrial environment is a bearing, and wherein the parameterized second predictive model of the second device predicts at least one of. a vibration amplitude, a vibration frequency, or a vibration phase location corresponding to the bearing, and wherein the second device causes the physical control action to be performed based on the predicted at least one of: the vibration amplitude, the vibration frequency, or the vibration phase location indicating a predicted bearing failure.
However, Cella further teaches, wherein the physical component in the industrial environment is a bearing, and wherein the parameterized second predictive model of the second device predicts at least one of. a vibration amplitude, a vibration frequency, or a vibration phase location corresponding to the bearing, (see para 1081-Elements of these machines operating in an industrial environment (e.g., rotating elements, reciprocating elements, swinging elements, flexing elements, flowing elements, suspending elements, floating elements, bouncing elements, bearing elements, etc.) may generate vibrations that may be of a specific frequency and/or amplitude typical of the element when the element is in a given operating condition or state (e.g., a normal mode of operation of a machine at a given speed, in a given gear, or the like))
and wherein the second device causes the physical control action to be performed based on the predicted at least one of: the vibration amplitude, the vibration frequency, or the vibration phase location indicating a predicted bearing failure. (see para 1081-Typical faults that can be identified using vibration analysis include: machine out of balance, machine out of alignment, resonance, bent shafts, gear mesh disturbances, blade pass disturbances, vane pass disturbances, recirculation & cavitation, motor faults (rotor & stator), bearing failures, mechanical looseness, critical machine speeds, and the. See para 1085-. For example, when the vibration fingerprint from a turbine agitator in a pharmaceutical processing plant matches a vibration fingerprint for a turbine agitator when it required a replacement bearing, the expert system may cause an action to occur, such as immediately shutting down the agitator or scheduling its shutdown and maintenance.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include wherein the second device further comprises a controller configured to cause the physical control action by issuing a command to a physical actuator in the industrial environment, wherein the command causes the physical actuator to perform at least one of: stopping an assembly line, shutting a valve, or activating or deactivating a machine in the industrial environment in response to the future values indicating a predicted failure or off- nominal condition of the physical component, and wherein the command is issued before the predicted failure or off-nominal condition occurs as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 73
The combination of Kaira and Kirshenbaum teaches the system of claim 69. Kaira further teaches wherein the one or more sensor devices are security cameras disposed in the industrial environment, wherein the first predictive model comprises , (see para 39- The underlying data values in the data stream—which tend to be heavily represented using time-series data—can include any representation of data from any type or combination of modalities, including configuration data for tasks and equipment (e.g., robots, tools), performance data captured by sensors and other devices, visual data—such as images and video—captured by cameras and other visual sensors, audio captured by microphones, and so forth. )
Kaira does not teach motion vectors extracted from video data captured by the security cameras, wherein the parameterized second predictive model predicts future locations of entities in the industrial environment based on the motion vectors.
However, Cella teaches motion vectors extracted from video data captured by the security cameras. (See para 361- For example, a model of fuel consumption by an industrial machine may include physical model parameters that characterize weights, motion. See para 984- A convolutional neural network may be used for recognition within images and video streams, such as for recognizing a type of machine in a large environment using a camera system disposed on a mobile data collector, such as on a drone or mobile robot. See para 1091- Ambient noise may be measured by a microphone, ultrasound sensors, acoustic wave sensors, optical vibration sensors (e.g., using a camera to see oscillations that produce noise), or “deep learning” neural networks involving various sensor arrays that learn, using large data sets, to identify patterns, sounds types, noise types, etc. In an embodiment, the ambient sensed condition may relate to motion detection. For example, the motion may be a platform motion (e.g., vehicle, oil platform, suspended platform on land, etc.) or an object motion (e.g., moving equipment, people, robots, parts (e.g., fan blades or turbine blades), etc.). see para 2377- At 29612, the edge device 28704 may generate one or more feature vectors based on the sensor data)
wherein the parameterized second predictive model predicts future locations of entities in the industrial environment based on the motion vectors, (see para 1091- Ambient noise may be measured by a microphone, ultrasound sensors, acoustic wave sensors, optical vibration sensors (e.g., using a camera to see oscillations that produce noise), or “deep learning” neural networks involving various sensor arrays that learn, using large data sets, to identify patterns, sounds types, noise types, etc. In an embodiment, the ambient sensed condition may relate to motion detection. For example, the motion may be a platform motion (e.g., vehicle, oil platform, suspended platform on land, etc.) or an object motion (e.g., moving equipment, people, robots, parts (e.g., fan blades or turbine blades), etc.). In an embodiment, the ambient sensed condition may be sensed by imaging, such as to detect a location and nature of various machines, equipment, and other objects, such as ones that might impact local vibration. )
and wherein the second device causes the physical control action in response to a predicted future location indicating an anomalous security condition.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include motion vectors extracted from video data captured by the security cameras, wherein the parameterized second predictive model predicts future locations of entities in the industrial environment based on the motion vectors as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 74
The combination of Kaira and Kirshenbaum teaches the system of claim 69. Kaira further teaches wherein the one or more sensor devices are vibration sensors (see para 137- Example housings and/or surfaces thereof may support one or more sensors (e.g., temperature sensors, vibration sensors, light sensors, acoustic sensors, capacitive sensors, proximity sensors, etc.).)’
Kaira does not teach vibration sensors communicatively coupled to a rotating or oscillating machine in the industrial environment, wherein the data values comprise vibration data generated by the rotating or oscillating machine, wherein the parameterized second predictive model of the second device predicts a future vibration state of the rotating or oscillating machine indicating a potential need for maintenance wherein the second device causes the physical control action comprising initiating a maintenance procedure for the rotating or oscillating machine based on the predicted future vibration state.
However, Cella further teaches vibration sensors communicatively coupled to a rotating or oscillating machine in the industrial environment, wherein the data values comprise vibration data generated by the rotating or oscillating machine, (see para 297-299 and fig 8- n embodiments, due to a system's multiplexer and crosspoint switch, an ODS, a transfer function, or other special tests on all the vibration sensors attached to a machine/structure can be performed and show exactly how the machine's points are moving in relationship to each other. In embodiments, the machine 2020 can further include a housing 2100 that can contain a drive motor 2110 that can drive a shaft 2120. The shaft 2120 can be supported for rotation or oscillation by a set of bearings 2130, such as including a first bearing 2140 and a second bearing 2150. A data collection module 2160 can connect to (or be resident on) the machine 2020. In one example, the data collection module 2160 can be located and accessible through a cloud network facility 2170 )
wherein the parameterized second predictive model of the second device predicts a future vibration state of the rotating or oscillating machine indicating a potential need for maintenance, (see para 321- The various embodiments include methods of sequentially monitoring vibration or similar process parameters and signals of a rotating or oscillating machine or analogous process machinery from a number of channels simultaneously, which can be known as an ensemble. See para 1068-1071- The controller 10706 may adjust the weights/biases of the machine learning data analysis circuit 10712, such as in response to the learned received output data patterns 10718, in response to the accuracy of the prediction of an anticipated state by the machine learning data analysis circuit, in response to the accuracy of a classification of a state by the machine learning data analysis circuit, and the like. The machine learning data analysis circuit 10712 may be disposed in part on a machine, on one or more data collectors, in network infrastructure, in the cloud, or any combination thereof. See para 1080- hat are processed by a “deep learning” machine/expert system that learns to predict one or more states (e.g., maintenance, failure, or operational) or overall outcomes, such as by learning from human supervision or from other feedback) and
wherein the second device causes the physical control action comprising initiating a maintenance procedure for the rotating or oscillating machine based on the predicted future vibration state. (see para 1709- providing vibration feedback for a bearing, motor, or other rotating or vibrating component that is operating off-nominally; and/or providing requested feedback to the user based upon sensed data (e.g., transmitting a vibration profile to the haptic feedback device that is analogous to the detected vibration in a requested component for example allowing an expert user to diagnose the component without physical contact)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include vibration sensors communicatively coupled to a rotating or oscillating machine in the industrial environment, wherein the data values comprise vibration data generated by the rotating or oscillating machine, wherein the parameterized second predictive model of the second device predicts a future vibration state of the rotating or oscillating machine indicating a potential need for maintenance wherein the second device causes the physical control action comprising initiating a maintenance procedure for the rotating or oscillating machine based on the predicted future vibration state as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 75
The combination of Kaira and Kirshenbaum teaches the system of claim 69. Kaira does not teach wherein the first device is configured to continue generating and refining the predictive model and adjusting the plurality of predictive model parameters based on newly received data values from the one or more sensor devices during periods when the first device is disconnected from a network connecting the first device to the second device, and wherein the first device is further configured to transmit the adjusted plurality of predictive model parameters to the second device upon reconnection to the network.
However, Cella further teaches wherein the first device is configured to continue generating and refining the predictive model and adjusting the plurality of predictive model parameters based on newly received data values from the one or more sensor devices during periods when the first device is disconnected from a network connecting the first device to the second device, (see para 943- A sudden absence of signal from a sensor may be indicative of sensor disconnection which may due to vibration, impact and the like. See para 1060- The expert system may determine that the system should discontinue collection of data from a smart band, one or more sensors, or the like. In another embodiment, the expert system may determine that the system should initiate data collection from a new smart band, such as a new smart band identified by the neural net itself. see para 1356- In embodiments, the system accumulates data received from other similarly configured systems while an upstream network connection is unavailable, and then sends all accumulated data once the upstream network connection is restored.)
and wherein the first device is further configured to transmit the adjusted plurality of predictive model parameters to the second device upon reconnection to the network. (see para 247- FIG. 2 depicts a mobile ad hoc network (“MANET”) 20, which may form a secure, temporal network connection 22 (sometimes connected and sometimes isolated), with a cloud 30 or other remote networking system. see para 1356- In embodiments, the system accumulates data received from other similarly configured systems while an upstream network connection is unavailable, and then sends all accumulated data once the upstream network connection is restored.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include wherein the first device is configured to continue generating and refining the predictive model and adjusting the plurality of predictive model parameters based on newly received data values from the one or more sensor devices during periods when the first device is disconnected from a network connecting the first device to the second device, and wherein the first device is further configured to transmit the adjusted plurality of predictive model parameters to the second device upon reconnection to the network as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Regarding claim 76
The combination of Kaira and Kirshenbaum teaches the system of claim 69. Kaira further teaches wherein the one or more sensor devices comprise security sensors disposed in the industrial environment and configured to generate security sensor data, wherein the data values comprise the security sensor data; (see para 39- The underlying data values in the data stream—which tend to be heavily represented using time-series data—can include any representation of data from any type or combination of modalities, including configuration data for tasks and equipment (e.g., robots, tools), performance data captured by sensors and other devices, visual data—such as images and video—captured by cameras and other visual sensors, audio captured by microphones, and so forth. See para 181- As used herein, the term “data center” refers to a purpose-designed structure that is intended to house multiple high-performance compute and data storage nodes such that a large amount of compute, data storage and network resources are present at a single location. This often entails specialized rack and enclosure systems, suitable heating, cooling, ventilation, security, fire suppression, and power delivery systems.)
Kaira does not teach wherein the first modelling system of the first device generates and refines the predictive model for predicting future security states of the industrial environment based on the security sensor data, wherein the second device detects an anomalous security condition in the industrial environment based on future data values predicted by the parameterized second predictive model of the second device and causes the physical control action in response to the detected anomalous security condition, wherein the physical control action comprising restricting physical access to a portion of the industrial environment based on the future data values predicted by the parameterized second predictive model of the second device indicating a predicted security event in the industrial environment, and wherein the physical control action is caused to occur prior to the predicted security event occurring.
However, Cella further teaches wherein the first modelling system of the first device generates and refines the predictive model for predicting future security states of the industrial environment based on the security sensor data,(see para 243- For example, data streams from vibration, pressure, temperature, accelerometer, magnetic, electrical field, and other analog sensors may be multiplexed or otherwise fused, relayed over a network, and fed into a cloud-based machine learning facility, which may employ one or more models relating to an operating characteristic of an industrial machine, an industrial process, or a component or element thereof. The learning machine may then operate on other data, initially using a set of rules or elements of a model, such as to provide a variety of outputs, such as classification of data into types, recognition of certain patterns. The machine learning facility may take feedback, such as one or more inputs or measures of success, such that it may train, or improve, its initial model (such as improvements by adjusting weights, rules, parameters, or the like, based on the feedback). See also para 261-262- Methods and systems are disclosed herein for cloud-based, machine pattern analysis of state information from multiple industrial sensors to provide anticipated state information for an industrial system. See para 1826- Data security policies may determine how data at rest, for example stored data, as well transmitted data is required to be secured.)
wherein the second device detects an anomalous security condition in the industrial environment based on future data values predicted by the parameterized second predictive model of the second device and causes the physical control action in response to the detected anomalous security condition,(see para 1757- In some examples, approaches respond to instantaneous network behavior and learn the network's data handling policy and state by probing for changes. In an industrial environment, this may include learning policies relating to authorization to use aspects of a network; for example, a SCADA system may allow a data path to be used only by a limited set of authorized users, services, or applications, because of the sensitivity of underlying machines or processes that are under control (including remote control) via the SCADA system and concern over potential for cyberattacks. See para 2439- Other features that may be provided and/or be integrated with the hydrogen-based systems described herein may include data collection, analysis, and modeling for improvement, data security, cyber security, network security to avoid external attacks on control systems and the like, monitoring and analysis to facilitate preventive maintenance and repair.)
wherein the physical control action comprising restricting physical access to a portion of the industrial environment based on the future data values predicted by the parameterized second predictive model of the second device indicating a predicted security event in the industrial environment, wherein the physical control action is caused to occur prior to the predicted security event occurring. (see para 366- Polices, which may include access policies, network usage policies, storage usage policies, bandwidth usage policies, device connection policies, security policies, rule-based policies, role-based polices, and others, may be required to govern the use of IoT devices. see para 1757- In some examples, approaches respond to instantaneous network behavior and learn the network's data handling policy and state by probing for changes. In an industrial environment, this may include learning policies relating to authorization to use aspects of a network; for example, a SCADA system may allow a data path to be used only by a limited set of authorized users, services, or applications, because of the sensitivity of underlying machines or processes that are under control (including remote control) via the SCADA system and concern over potential for cyberattacks. See para 1816- A policy automation engine 13002 may be used to create, deploy, and/or manage an interconnected set of policies 13030, rules 13028 and protocols 13004, such as policies relating to security, authorization, permissions, and the like) and
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the method of developing, deploying, and maintaining predictive analytics models as disclosed by Kaira to include wherein the first modelling system of the first device generates and refines the predictive model for predicting future security states of the industrial environment based on the security sensor data, wherein the second device detects an anomalous security condition in the industrial environment based on future data values predicted by the parameterized second predictive model of the second device and causes the physical control action in response to the detected anomalous security condition, wherein the physical control action comprising restricting physical access to a portion of the industrial environment based on the future data values predicted by the parameterized second predictive model of the second device indicating a predicted security event in the industrial environment, and wherein the physical control action is caused to occur prior to the predicted security event occurring as taught by Cella in the system of Kaira and Kirshenbaum in order to provide improved monitoring, control, intelligent diagnosis of problems and intelligent optimization of operations in various heavy industrial environments. (Cella, [0009])
Conclusion
19. Claims 43, 45-53 and 67-76 is/are rejected.
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 PURSOTTAM GIRI whose telephone number is (469)295-9101. The examiner can normally be reached 7:30-5:30 PM, Monday to Friday.
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, RENEE CHAVEZ can be reached at 5712701104. 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.
/PURSOTTAM GIRI/Examiner, Art Unit 2186
/SAIF A ALHIJA/Primary Examiner, Art Unit 2186
Prosecution Insights