DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application is being examined under the pre-AIA first to invent provisions.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/30/2023 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
In reference to claim 1:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a process
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“determining, by the first local controller, a parameter for a pre-trained modem algorithm of the first edge device based on the input;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine a parameter for a pre-trained modem algorithm based on the input.
“determining a result of executing the task;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine/predict a result of executing the task.
“generating a first update to the first machine-learning algorithm based on the training;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could generate a first update based on the training.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“A method comprising: receiving, by a first local controller of a first edge device, an input associated with an environment in which the first edge device operates;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“using a first machine-learning algorithm,” 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 (MPEP 2106.05(f)).
“executing a task on the first edge device based on executing the pre-trained modem algorithm with the parameter;” 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 (MPEP 2106.05(f)).
“training the first machine-learning algorithm, based on the task and the result of executing the task;” 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 (MPEP 2106.05(f)).
“sending the first update to an external server;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“receiving, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“and based on the server update, updating the first machine-learning algorithm.” 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 (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“A method comprising: receiving, by a first local controller of a first edge device, an input associated with an environment in which the first edge device operates;” (well-understood, routine, conventional MPEP 2106.05(d))
“using a first machine-learning algorithm,” 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 (MPEP 2106.05(f)).
“executing a task on the first edge device based on executing the pre-trained modem algorithm with the parameter;” 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 (MPEP 2106.05(f)).
“training the first machine-learning algorithm, based on the task and the result of executing the task;” 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 (MPEP 2106.05(f)).
“sending the first update to an external server;” (well-understood, routine, conventional MPEP 2106.05(d))
“receiving, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device;” (well-understood, routine, conventional MPEP 2106.05(d))
“and based on the server update, updating the first machine-learning algorithm.” 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 (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 2:
Claim 2 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 3:
Claim 3 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 4:
Claim 4 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 5:
Claim 5 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 6:
Claim 6 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 7:
Claim 7 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 8:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a machine
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“to determine a parameter for the pre-trained modem algorithm based on the input;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine a parameter for the pre-trained modem algorithm based on the input.
“determine a result of executing the task;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine/predict a result of executing the task.
“generate a first update to the first machine-learning algorithm based on the training;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could generate a first update based on the training.
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“A first device comprising a processing circuit comprising: a first local controller; and a pre-trained modem algorithm communicatively coupled to the first local controller, wherein the processing circuit is configured to:”
“receive an input associated with an environment in which the first device operates;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“use a first machine-learning algorithm,” 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 (MPEP 2106.05(f)).
“execute a task on the first device based on executing the pre-trained modem algorithm with the parameter;” 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 (MPEP 2106.05(f)).
“train the first machine-learning algorithm, based on the task and the result of executing the task;” 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 (MPEP 2106.05(f)).
“send the first update to an external server;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“receive, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“and based on the server update, update the first machine-learning algorithm.” 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 (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“A first device comprising a processing circuit comprising: a first local controller; and a pre-trained modem algorithm communicatively coupled to the first local controller, wherein the processing circuit is configured to:”
“receive an input associated with an environment in which the first device operates;” (well-understood, routine, conventional MPEP 2106.05(d))
“use a first machine-learning algorithm,” 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 (MPEP 2106.05(f)).
“execute a task on the first device based on executing the pre-trained modem algorithm with the parameter;” 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 (MPEP 2106.05(f)).
“train the first machine-learning algorithm, based on the task and the result of executing the task;” 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 (MPEP 2106.05(f)).
“send the first update to an external server;” (well-understood, routine, conventional MPEP 2106.05(d))
“receive, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device;” (well-understood, routine, conventional MPEP 2106.05(d))
“and based on the server update, update the first machine-learning algorithm.” 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 (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 9:
Claim 9 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 10:
Claim 10 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 11:
Claim 11 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 12:
Claim 12 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 13:
Claim 13 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 14:
Claim 14 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 15:
Step 1 - Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a manufacture
Step 2A Prong 1 - Does the claim recite an abstract idea, law of nature, or natural phenomenon?
“to determine a parameter for the pre-trained modem algorithm based on the input;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine a parameter for the pre-trained modem algorithm based on the input.
“determine a result of executing the task;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could determine/predict a result of executing the task.
“generate a first update to the first machine-learning algorithm based on the training;” which is an abstract idea because it is directed to a mental process, an observation, evaluation, judgement, or opinion. The limitation as drafted, and under a broadest reasonable interpretation, can be performed in the human mind, or by a human using a pen and paper (MPEP 2106.04(a)(2)(Ill)(c)). For example, a person could generate a first update based on the training of .
Step 2A Prong 2 - Does the claim recite additional elements that integrate the judicial exception into a practical application?
“A system comprising a first edge device comprising: a processing circuit; and a memory for storing instructions, which, based on being executed by the processing circuit, cause the processing circuit to:”
“receive an input associated with an environment in which the first edge device operates;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“use a first machine-learning algorithm,” 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 (MPEP 2106.05(f)).
“execute a task on the first edge device based on executing the pre-trained modem algorithm with the parameter;” 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 (MPEP 2106.05(f)).
“train the first machine-learning algorithm, based on the task and the result of executing the task;” 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 (MPEP 2106.05(f)).
“send the first update to an external server;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“receive, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device;” (insignificant extra-solution activity mere data gathering MPEP 2106.05(g))
“and based on the server update, update the first machine-learning algorithm.” 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 (MPEP 2106.05(f)).
The claim does not include additional elements that are integrated into a practical application.
Step 2B - Does the claim recite additional elements that amount to significantly more than the judicial exception?
“A system comprising a first edge device comprising: a processing circuit; and a memory for storing instructions, which, based on being executed by the processing circuit, cause the processing circuit to:”
“receive an input associated with an environment in which the first edge device operates;” (well-understood, routine, conventional MPEP 2106.05(d))
“use a first machine-learning algorithm,” 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 (MPEP 2106.05(f)).
“execute a task on the first edge device based on executing the pre-trained modem algorithm with the parameter;” 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 (MPEP 2106.05(f)).
“train the first machine-learning algorithm, based on the task and the result of executing the task;” 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 (MPEP 2106.05(f)).
“send the first update to an external server;” (well-understood, routine, conventional MPEP 2106.05(d))
“receive, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device;” (well-understood, routine, conventional MPEP 2106.05(d))
“and based on the server update, update the first machine-learning algorithm.” 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 (MPEP 2106.05(f)).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
In reference to claim 15:
Claim 15 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 16:
Claim 16 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 17:
Claim 17 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 18:
Claim 18 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 19:
Claim 19 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
In reference to claim 20:
Claim 20 is directed to a judicial exception from claim(s) depended on and does not recite additional elements that integrate the judicial exception into a practical application and amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 103
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 (i.e., changing from AIA to pre-AIA ) 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.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 6, 8, 13 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Abdulrahman Alabbasi et al; US 20230010095 A1 filed on Dec 18, 2019 (hereinafter “Alabbasi”) in view of Arhum Ahmad et al; “DeepDeMod: BPSK Demodulation Using Deep Learning Over Software-Defined Radio” published Nov 2, 2022 (hereinafter “Ahmad”) in further view of Ziyi Li et al; US 20220038349 A1 filed on Oct 19, 2021 (hereinafter “Li”)
Regarding claim 1, Alabbasi teaches A method comprising: receiving, by a first local controller of a first edge device, an input associated with an environment in which the first edge device operates; (Alabbasi Paragraph 0037; “the target node may be a user equipment (UE). The skilled person will be familiar with UEs, but generally, a UE may comprise any device capable, configured, arranged and/or operable to communicate wirelessly with network nodes and/or other wireless devices… a UE may represent a vehicle or other equipment that is capable of monitoring and/or reporting on its operational status or other functions associated with its operation.” Alabbasi Paragraph 0199; “The first node receives signal S1” Examiner notes that an input (signal s1) associated with an environment in which the first edge device operates (the communication network the UE operates on) by a first local controller (device capable to communicate wirelessly) of a first edge device (target node))
using a first machine-learning algorithm, determining, by the first local controller, a parameter for a pre-trained modem algorithm of the first edge device based on the input; (Alabbasi Paragraph 0199; “The first model, or a second model may also determine the type of channel information that should be obtained by each of the selected subset of other nodes.” Examiner notes that a first machine learning algorithm (model) is used to determine, by the first local controller (controller present in first node), a parameter for a pre-trained modem algorithm (type of channel information) of the first edge device (first node) based on the input (signal s1))
training the first machine-learning algorithm, [based on the task and the result of executing the task]; (Alabbasi Paragraph 0175; “the first or second models may be further trained to determine a manner in which to combine the obtained channel information in order to determine whether the channel is in use.” Examiner notes that the first machine learning algorithm (first model) is trained)
Alabbasi does not teach executing a task on the first edge device based on executing the pre-trained modem algorithm with the parameter;
determining a result of executing the task;
training [the first machine-learning algorithm], based on the task and the result of executing the task;
However, Ahmad does teach executing a task on the first edge device based on executing the pre-trained modem algorithm with the parameter; (Ahmad Page 5 Paragraph 1; “we present a novel DNN based demodulator” Page 5 Paragraph 4; “the DNN is trained with the known signals to get the optimal weights for the DNN. This pre-trained DNN is used to detect the bits transmitted in the received signal.” Examiner notes that executing a task on the first edge device is/based on executing the pre-trained modem algorithm (pre-trained DNN based demodulator) with the parameter (optimal weights))
determining a result of executing the task; (Ahmad Page 8 Last Paragraph; “The signal is provided as input to the DNN for detection. Initially, DNN is loaded with primary weights [Wp]. DNN uses this set of weights [Wp] to check BER of this packet using pilot.” Examiner notes that a result (BER; Bit Error Rate) of executing the task (detection) is determined/checked)
training [the first machine-learning algorithm], based on the task and the result of executing the task; (Ahmad Page 9 Paragraph 1; “If BER>λ, the DNN uses primary weight [Wp] as starting point to re-train itself using pilot data.” Examiner notes that retraining is done based on the task and the result of executing the task (if BER > λ; BER is obtained from executing task of detection))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi and Ahmad. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. One of ordinary skill would have motivation to combine Alabbasi and Ahmad to get better performance in terms of bit error rate “our proposed DeepDeMod provides significantly better performance in term of bit error rate.” (Ahmad Abstract).
Alabbasi in view of Ahmad does not teach generating a first update to the first machine-learning algorithm based on the training;
sending the first update to an external server;
receiving, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device; and
based on the server update, updating the first machine-learning algorithm.
However, Li does teach generating a first update to the first machine-learning algorithm based on the training; (Li Paragraph 0067; “ Local nodes (UEs) who are to use the model for the first time are to download the whole trained model package from the central server, as well as expected updated model parameters… Each local node (e.g., UE) starts local training based on its own data, and no information exchange is expected during this period for AI/ML model training purposes... Each local node reports its training model updated parameters to the central node” Examiner notes that a first update (updated parameters) to the first machine learning algorithm (model downloaded on UE) is generated based on the training (local training))
sending the first update to an external server; (Examiner refers to previous mapping to show that the first update (updated parameters) is sent/reported to an external server (central node))
receiving, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device; and (Li Paragraph 0042; “The communication device 200 may be a UE” Li Paragraph 0045; “The communication device 200 may further include an output controller” Li Fig 3D and Paragraph 0069; “Each local node reports its training model updated parameters to the central node via RRC signaling, and the central node aggregates all collected information and starts updating the general model.” Examiner notes that a server update to the first machine learning algorithm (updating the general model) is received by the external server (central node), wherein the server update is created (central node aggregates all collected information and starts updating the general model), by the external server (central node) using at least one or the first update and second update (each local node reports is updated parameters) from a second local controller (controller in second UE) of a second edge device (Fig 3D shows a plurality of edge devices/local nodes/UE))
based on the server update, updating the first machine-learning algorithm. (Li Paragraph 0067; “as well as expected updated model parameters (for local nodes reporting in operation 4, and for periodic updates from the central node). Local nodes (UEs) who have previously received the model, the central node sends updated model parameters (refreshed in operation 4) in a bitstring to the local nodes.” Examiner notes that the first machine learning algorithm (local model on UE) is updated based on the server update (expected updated model parameters sent from the central server))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Regarding claim 6, Alabbasi does not teach The method of claim 1, wherein server update is created by: receiving, by the external server, the first update and the second update;
generating aggregated data based on the first update and the second update;
and updating a global algorithm associated with a global controller based on the aggregated data.
However, Li does teach The method of claim 1, wherein server update is created by: receiving, by the external server, the first update and the second update; (Li Fig 3D and Paragraph 0069; “Each local node reports its training model updated parameters to the central node via RRC signaling, and the central node aggregates all collected information and starts updating the general model.” Examiner notes that server update (updating the general model) by: receiving, by the external server (central node), the first update and the second update (Fig 3 shows each local node reports its training model updated parameters))
generating aggregated data based on the first update and the second update; (Examiner refers to previous mapping to show that the first update and second update (updated parameters) is aggregated)
and updating a global algorithm associated with a global controller based on the aggregated data. (Li Paragraph 0023; “any of the RAN nodes 111 and 112 can fulfill various logical functions for the RAN 110 including, but not limited to, radio network controller (RNC) functions” Examiner refers to previous mapping to show that a global algorithm (general model) associated with a global controller (radio network controller) is updated based on the aggregated data (the central node aggregates all collected information and starts updating the general model))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Regarding claim 8, Alabbasi teaches wherein the processing circuit is configured to: receive an input associated with an environment in which the first device operates (Alabbasi Paragraph 0037; “the target node may be a user equipment (UE). The skilled person will be familiar with UEs, but generally, a UE may comprise any device capable, configured, arranged and/or operable to communicate wirelessly with network nodes and/or other wireless devices… a UE may represent a vehicle or other equipment that is capable of monitoring and/or reporting on its operational status or other functions associated with its operation.” Alabbasi Paragraph 0199; “The first node receives signal S1” Examiner notes that an input (signal s1) associated with an environment in which the first edge device operates (the communication network the UE operates on) by a first local controller (device capable to communicate wirelessly) of a first edge device (target node))
use a first machine-learning algorithm to determine a parameter for the pre- trained modem algorithm based on the input; (Alabbasi Paragraph 0199; “The first model, or a second model may also determine the type of channel information that should be obtained by each of the selected subset of other nodes.” Examiner notes that a first machine learning algorithm (model) is used to determine, by the first local controller (controller present in first node), a parameter for a pre-trained modem algorithm (type of channel information) of the first edge device (first node) based on the input (signal s1))
train the first machine-learning algorithm, [based on the task and the result of executing the task]; (Alabbasi Paragraph 0175; “the first or second models may be further trained to determine a manner in which to combine the obtained channel information in order to determine whether the channel is in use.” Examiner notes that the first machine learning algorithm (first model) is trained)
Alabbasi does not teach A first device comprising a processing circuit comprising: a first local controller; and
a pre-trained modem algorithm communicatively coupled to the first local controller,
execute a task on the first device based on executing the pre-trained modem algorithm with the parameter;
determine a result of executing the task;
train [the first machine-learning algorithm], based on the task and the result of executing the task;
However, Ahmad does teach A first device comprising a processing circuit comprising: a first local controller; and (Ahmad Page 14 Paragraph 2; “For the hardware implementation of the proposed method, we use software defined radio(SDR), which is a generic radio communication system with most of the physical layer (PHY) functionality written in software [41]. In our prototype, a packet-based radio communication system is implemented. It consists of two USRPs namely B210 (as a transmitter) and B205 mini-i (as a receiver). Each of these are connected to their respective host processing device running a baseband processing algorithm using Matlab/Simulink software.” Examiner notes that host processing device is a first device comprising a processing circuit comprising a first local controller)
a pre-trained modem algorithm communicatively coupled to the first local controller, (Examiner refers to previous mapping to show that pre-trained modem algorithm (proposed method) is communicatively coupled/implemented to the first local controller (controller present in hose processing device))
execute a task on the first device based on executing the pre-trained modem algorithm with the parameter; (Ahmad Page 5 Paragraph 1; “we present a novel DNN based demodulator” Page 5 Paragraph 4; “the DNN is trained with the known signals to get the optimal weights for the DNN. This pre-trained DNN is used to detect the bits transmitted in the received signal.” Examiner notes that executing a task on the first edge device is/based on executing the pre-trained modem algorithm (pre-trained DNN based demodulator) with the parameter (optimal weights))
determine a result of executing the task; (Ahmad Page 8 Last Paragraph; “The signal is provided as input to the DNN for detection. Initially, DNN is loaded with primary weights [Wp]. DNN uses this set of weights [Wp] to check BER of this packet using pilot.” Examiner notes that a result (BER; Bit Error Rate) of executing the task (detection) is determined/checked)
train [the first machine-learning algorithm], based on the task and the result of executing the task; (Ahmad Page 9 Paragraph 1; “If BER>λ, the DNN uses primary weight [Wp] as starting point to re-train itself using pilot data.” Examiner notes that retraining is done based on the task and the result of executing the task (if BER > λ; BER is obtained from executing task of detection))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi and Ahmad. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. One of ordinary skill would have motivation to combine Alabbasi and Ahmad to get better performance in terms of bit error rate “our proposed DeepDeMod provides significantly better performance in term of bit error rate.” (Ahmad Abstract).
Alabbasi in view of Ahmad does not teach generate a first update to the first machine-learning algorithm based on the training;
send the first update to an external server;
receive, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device; and
based on the server update, update the first machine-learning algorithm.
However, Li does teach generate a first update to the first machine-learning algorithm based on the training; (Li Paragraph 0067; “ Local nodes (UEs) who are to use the model for the first time are to download the whole trained model package from the central server, as well as expected updated model parameters… Each local node (e.g., UE) starts local training based on its own data, and no information exchange is expected during this period for AI/ML model training purposes... Each local node reports its training model updated parameters to the central node” Examiner notes that a first update (updated parameters) to the first machine learning algorithm (model downloaded on UE) is generated based on the training (local training))
send the first update to an external server; (Examiner refers to previous mapping to show that the first update (updated parameters) is sent/reported to an external server (central node))
receive, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device; and (Li Paragraph 0042; “The communication device 200 may be a UE” Li Paragraph 0045; “The communication device 200 may further include an output controller” Li Fig 3D and Paragraph 0069; “Each local node reports its training model updated parameters to the central node via RRC signaling, and the central node aggregates all collected information and starts updating the general model.” Examiner notes that a server update to the first machine learning algorithm (updating the general model) is received by the external server (central node), wherein the server update is created (central node aggregates all collected information and starts updating the general model), by the external server (central node) using at least one or the first update and second update (each local node reports is updated parameters) from a second local controller (controller in second UE) of a second edge device (Fig 3D shows a plurality of edge devices/local nodes/UE))
based on the server update, update the first machine-learning algorithm. (Li Paragraph 0067; “as well as expected updated model parameters (for local nodes reporting in operation 4, and for periodic updates from the central node). Local nodes (UEs) who have previously received the model, the central node sends updated model parameters (refreshed in operation 4) in a bitstring to the local nodes.” Examiner notes that the first machine learning algorithm (local model on UE) is updated based on the server update (expected updated model parameters sent from the central server))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Regarding claim 13, Alabbasi does not teach The first device of claim 8, wherein the server update is created by: receiving, by the external server, the first update and the second update;
generating aggregated data based on the first update and the second update;
and updating a global algorithm associated with a global controller based on the aggregated data.
However, Li does teach The first device of claim 8, wherein the server update is created by: receiving, by the external server, the first update and the second update; (Li Fig 3D and Paragraph 0069; “Each local node reports its training model updated parameters to the central node via RRC signaling, and the central node aggregates all collected information and starts updating the general model.” Examiner notes that server update (updating the general model) by: receiving, by the external server (central node), the first update and the second update (Fig 3 shows each local node reports its training model updated parameters))
generating aggregated data based on the first update and the second update; (Examiner refers to previous mapping to show that the first update and second update (updated parameters) is aggregated)
and updating a global algorithm associated with a global controller based on the aggregated data. (Li Paragraph 0023; “any of the RAN nodes 111 and 112 can fulfill various logical functions for the RAN 110 including, but not limited to, radio network controller (RNC) functions” Examiner refers to previous mapping to show that a global algorithm (general model) associated with a global controller (radio network controller) is updated based on the aggregated data (the central node aggregates all collected information and starts updating the general model))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Regarding claim 15, Alabbasi teaches cause the processing circuit to: receive an input associated with an environment in which the first edge device operates; (Alabbasi Paragraph 0037; “the target node may be a user equipment (UE). The skilled person will be familiar with UEs, but generally, a UE may comprise any device capable, configured, arranged and/or operable to communicate wirelessly with network nodes and/or other wireless devices… a UE may represent a vehicle or other equipment that is capable of monitoring and/or reporting on its operational status or other functions associated with its operation.” Alabbasi Paragraph 0199; “The first node receives signal S1” Examiner notes that an input (signal s1) associated with an environment in which the first edge device operates (the communication network the UE operates on) by a first local controller (device capable to communicate wirelessly) of a first edge device (target node))
use a first machine-learning algorithm to determine a parameter for the pre- trained modem algorithm based on the input; (Alabbasi Paragraph 0199; “The first model, or a second model may also determine the type of channel information that should be obtained by each of the selected subset of other nodes.” Examiner notes that a first machine learning algorithm (model) is used to determine, by the first local controller (controller present in first node), a parameter for a pre-trained modem algorithm (type of channel information) of the first edge device (first node) based on the input (signal s1))
train the first machine-learning algorithm, [based on the task and the result of executing the task]; (Alabbasi Paragraph 0175; “the first or second models may be further trained to determine a manner in which to combine the obtained channel information in order to determine whether the channel is in use.” Examiner notes that the first machine learning algorithm (first model) is trained)
Alabbasi does not teach A system comprising a first edge device comprising: a processing circuit; and
a memory for storing instructions, which, based on being executed by the processing circuit,
execute a task on the first device based on executing the pre-trained modem algorithm with the parameter;
determine a result of executing the task;
train [the first machine-learning algorithm], based on the task and the result of executing the task;
However, Ahmad does teach A system comprising a first edge device comprising: a processing circuit; and a memory for storing instructions, which, based on being executed by the processing circuit, (Ahmad Page 14 Paragraph 2; “For the hardware implementation of the proposed method, we use software defined radio(SDR), which is a generic radio communication system with most of the physical layer (PHY) functionality written in software [41]. In our prototype, a packet-based radio communication system is implemented. It consists of two USRPs namely B210 (as a transmitter) and B205 mini-i (as a receiver). Each of these are connected to their respective host processing device running a baseband processing algorithm using Matlab/Simulink software.” Examiner notes that host processing device is a first edge device comprises a processing circuit and a memory for storing instructions, which, based on being executed by the processing circuit)
execute a task on the first device based on executing the pre-trained modem algorithm with the parameter; (Ahmad Page 5 Paragraph 1; “we present a novel DNN based demodulator” Page 5 Paragraph 4; “the DNN is trained with the known signals to get the optimal weights for the DNN. This pre-trained DNN is used to detect the bits transmitted in the received signal.” Examiner notes that executing a task on the first edge device is/based on executing the pre-trained modem algorithm (pre-trained DNN based demodulator) with the parameter (optimal weights))
determine a result of executing the task; (Ahmad Page 8 Last Paragraph; “The signal is provided as input to the DNN for detection. Initially, DNN is loaded with primary weights [Wp]. DNN uses this set of weights [Wp] to check BER of this packet using pilot.” Examiner notes that a result (BER; Bit Error Rate) of executing the task (detection) is determined/checked)
train [the first machine-learning algorithm], based on the task and the result of executing the task; (Ahmad Page 9 Paragraph 1; “If BER>λ, the DNN uses primary weight [Wp] as starting point to re-train itself using pilot data.” Examiner notes that retraining is done based on the task and the result of executing the task (if BER > λ; BER is obtained from executing task of detection))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi and Ahmad. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. One of ordinary skill would have motivation to combine Alabbasi and Ahmad to get better performance in terms of bit error rate “our proposed DeepDeMod provides significantly better performance in term of bit error rate.” (Ahmad Abstract).
Alabbasi in view of Ahmad does not teach generate a first update to the first machine-learning algorithm based on the training;
send the first update to an external server;
receive, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device; and
based on the server update, update the first machine-learning algorithm.
However, Li does teach generate a first update to the first machine-learning algorithm based on the training; (Li Paragraph 0067; “ Local nodes (UEs) who are to use the model for the first time are to download the whole trained model package from the central server, as well as expected updated model parameters… Each local node (e.g., UE) starts local training based on its own data, and no information exchange is expected during this period for AI/ML model training purposes... Each local node reports its training model updated parameters to the central node” Examiner notes that a first update (updated parameters) to the first machine learning algorithm (model downloaded on UE) is generated based on the training (local training))
send the first update to an external server; (Examiner refers to previous mapping to show that the first update (updated parameters) is sent/reported to an external server (central node))
receive, from the external server, a server update to the first machine-learning algorithm, wherein the server update is created, by the external server, using at least one of the first update and a second update from a second local controller of a second edge device; and (Li Paragraph 0042; “The communication device 200 may be a UE” Li Paragraph 0045; “The communication device 200 may further include an output controller” Li Fig 3D and Paragraph 0069; “Each local node reports its training model updated parameters to the central node via RRC signaling, and the central node aggregates all collected information and starts updating the general model.” Examiner notes that a server update to the first machine learning algorithm (updating the general model) is received by the external server (central node), wherein the server update is created (central node aggregates all collected information and starts updating the general model), by the external server (central node) using at least one or the first update and second update (each local node reports is updated parameters) from a second local controller (controller in second UE) of a second edge device (Fig 3D shows a plurality of edge devices/local nodes/UE))
based on the server update, update the first machine-learning algorithm. (Li Paragraph 0067; “as well as expected updated model parameters (for local nodes reporting in operation 4, and for periodic updates from the central node). Local nodes (UEs) who have previously received the model, the central node sends updated model parameters (refreshed in operation 4) in a bitstring to the local nodes.” Examiner notes that the first machine learning algorithm (local model on UE) is updated based on the server update (expected updated model parameters sent from the central server))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Claim(s) 2, 9, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Abdulrahman Alabbasi et al; US 20230010095 A1 filed on Dec 18, 2019 (hereinafter “Alabbasi”) in view of Arhum Ahmad et al; “DeepDeMod: BPSK Demodulation Using Deep Learning Over Software-Defined Radio” published Nov 2, 2022 (hereinafter “Ahmad”) in further view of Ziyi Li et al; US 20220038349 A1 filed on Oct 19, 2021 (hereinafter “Li”) in further view of Seoyoung Back et al; US 20230199875 A1 filed on Apr 28, 2021 (hereinafter “Back”)
Regarding claim 2, Alabbasi does not teach The method of claim 1, wherein the task comprises sending a resource allocation request from the first edge device to a base station.
However, Back does teach The method of claim 1, wherein the task comprises sending a resource allocation request from the first edge device to a base station. (Back Paragraph 0165; “the relay UE may request additional resource allocation from the BS based on failure to satisfy the second QoS-related information of the second remote UE in order to satisfy the first QoS-related information of the first remote UE.” Examiner notes that wherein the task comprises sending a resource allocation requestion (request additional resource allocation) from the first edge device (UE) to a base station (BS; Base Station))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Back. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Back teaches method of a relay UE related to a side link relay in a wireless communication system. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Back to increase the efficiency of resource usage “the optional relay resource pool allocated to the relay UE 1 and the optional relay resource pool allocated to the adjacent relay UE 2 are allocated differently, thereby increasing the efficiency of resource usage.” (Back Paragraph 0183).
Regarding claim 9, Alabbasi does not teach The first device of claim 8, wherein the task comprises sending a resource allocation request from the first device to a base station.
However, Back does teach The first device of claim 8, wherein the task comprises sending a resource allocation request from the first device to a base station. (Back Paragraph 0165; “the relay UE may request additional resource allocation from the BS based on failure to satisfy the second QoS-related information of the second remote UE in order to satisfy the first QoS-related information of the first remote UE.” Examiner notes that wherein the task comprises sending a resource allocation requestion (request additional resource allocation) from the first edge device (UE) to a base station (BS; Base Station))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Back. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Back teaches method of a relay UE related to a side link relay in a wireless communication system. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Back to increase the efficiency of resource usage “the optional relay resource pool allocated to the relay UE 1 and the optional relay resource pool allocated to the adjacent relay UE 2 are allocated differently, thereby increasing the efficiency of resource usage.” (Back Paragraph 0183).
Regarding claim 16, Alabbasi does not teach The system of claim 15, wherein the task comprises sending a resource allocation request from the first edge device to a base station.
However, Back does teach The system of claim 15, wherein the task comprises sending a resource allocation request from the first edge device to a base station. (Back Paragraph 0165; “the relay UE may request additional resource allocation from the BS based on failure to satisfy the second QoS-related information of the second remote UE in order to satisfy the first QoS-related information of the first remote UE.” Examiner notes that wherein the task comprises sending a resource allocation requestion (request additional resource allocation) from the first edge device (UE) to a base station (BS; Base Station))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Back. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Back teaches method of a relay UE related to a side link relay in a wireless communication system. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Back to increase the efficiency of resource usage “the optional relay resource pool allocated to the relay UE 1 and the optional relay resource pool allocated to the adjacent relay UE 2 are allocated differently, thereby increasing the efficiency of resource usage.” (Back Paragraph 0183).
Claim(s) 3, 10, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Abdulrahman Alabbasi et al; US 20230010095 A1 filed on Dec 18, 2019 (hereinafter “Alabbasi”) in view of Arhum Ahmad et al; “DeepDeMod: BPSK Demodulation Using Deep Learning Over Software-Defined Radio” published Nov 2, 2022 (hereinafter “Ahmad”) in further view of Ziyi Li et al; US 20220038349 A1 filed on Oct 19, 2021 (hereinafter “Li”) in further view of Chenxi Hao et al; US 20250088232 A1 filed on Apr 2, 2022 (hereinafter “Hao”)
Regarding claim 3, Alabbasi does not teach The method of claim 1, wherein the input comprises a channel estimate.
However, Hao does teach The method of claim 1, wherein the input comprises a channel estimate. (Hao Paragraph 0094; “the first machine learning module 1104a may be representative of a machine learning module for CSI feedback which takes channel estimation results as input wherein the channel estimation may be performed using AI or non-AI modules.” Examiner notes that the input comprises a channel estimate (channel estimation results))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Hao. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Hao teaches techniques for channel estimation based on transmission spatial information. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Hao to reduce CSI-RS overhead for better resource usage “The transmission spatial information described herein may facilitate CSI-RS overhead reduction with usage of a machine learning module to perform channel estimation and/or determine CSI and reduce the CSI-RS overhead.” (Hao Paragraph 0073).
Regarding claim 10, Alabbasi does not teach The first device of claim 8, wherein the input comprises a channel estimate.
However, Hao does teach The first device of claim 8, wherein the input comprises a channel estimate. (Hao Paragraph 0094; “the first machine learning module 1104a may be representative of a machine learning module for CSI feedback which takes channel estimation results as input wherein the channel estimation may be performed using AI or non-AI modules.” Examiner notes that the input comprises a channel estimate (channel estimation results))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Hao. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Hao teaches techniques for channel estimation based on transmission spatial information. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Hao to reduce CSI-RS overhead for better resource usage “The transmission spatial information described herein may facilitate CSI-RS overhead reduction with usage of a machine learning module to perform channel estimation and/or determine CSI and reduce the CSI-RS overhead.” (Hao Paragraph 0073).
Regarding claim 17, Alabbasi does not teach The system of claim 15, wherein the input comprises a channel estimate.
However, Hao does teach The system of claim 15, wherein the input comprises a channel estimate. (Hao Paragraph 0094; “the first machine learning module 1104a may be representative of a machine learning module for CSI feedback which takes channel estimation results as input wherein the channel estimation may be performed using AI or non-AI modules.” Examiner notes that the input comprises a channel estimate (channel estimation results))
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Hao. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Hao teaches techniques for channel estimation based on transmission spatial information. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Hao to reduce CSI-RS overhead for better resource usage “The transmission spatial information described herein may facilitate CSI-RS overhead reduction with usage of a machine learning module to perform channel estimation and/or determine CSI and reduce the CSI-RS overhead.” (Hao Paragraph 0073).
Claim(s) 4, 7, 11, 14, 18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Abdulrahman Alabbasi et al; US 20230010095 A1 filed on Dec 18, 2019 (hereinafter “Alabbasi”) in view of Arhum Ahmad et al; “DeepDeMod: BPSK Demodulation Using Deep Learning Over Software-Defined Radio” published Nov 2, 2022 (hereinafter “Ahmad”) in further view of Ziyi Li et al; US 20220038349 A1 filed on Oct 19, 2021 (hereinafter “Li”) in further view of Ekdeep Singh Lubana et al; US 20230368025 A1 filed on Apr 25, 2023 (hereinafter “Lubana”)
Regarding claim 4, Alabbasi does not teach The method of claim 1, wherein: the first edge device comprises a processing circuit comprising a central processing unit (CPU);
and sending the first update [comprises sending an update associated with the first feature extractor.]
However, Li does teach The method of claim 1, wherein: the first edge device comprises a processing circuit comprising a central processing unit (CPU); (Li Paragraph 0042; “The communication device 200 may be a UE such as a specialized computer” Li Paragraph 0045; “The communication device 200 may include a hardware processor (or equivalently processing circuitry) 202 (e.g., a central processing unit (CPU), a GPU, a hardware processor core, or any combination thereof), a main memory 204 and a static memory 206, some or all of which may communicate with each other via an interlink (e.g., bus) 208.”)
and sending the first update [comprises sending an update associated with the first feature extractor.] (Li Paragraph 0067; “ Local nodes (UEs) who are to use the model for the first time are to download the whole trained model package from the central server, as well as expected updated model parameters… Each local node (e.g., UE) starts local training based on its own data, and no information exchange is expected during this period for AI/ML model training purposes... Each local node reports its training model updated parameters to the central node” Examiner notes that the first update (updated parameters) is sent/report)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Alabbasi in view of Li does not teach the training comprises updating a first feature extractor associated with the first local controller;
However, Lubana does teach the training comprises updating a first feature extractor associated with the first local controller; (Lubana Paragraph 0055; “the devices 24 to 26 may provide the parameters of the local feature extractors at the respective devices to the server 22” Lubana Paragraph 0076; “the parameters of the local feature extractor are updated based on or replaced with the global feature extractor parameters received in the operation 55.” Examiner notes that the training comprises updating a first feature extractor (local feature extractor) associated with the first local controller (controller on devices 24))
[and sending the first update comprises] sending an update associated with the first feature extractor. (Examiner refers to previous mapping to show that an update associated with the first feature extractor is sent/provided)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Lubana. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Lubana teaches a method for training a feature extractor of a device using machine learning principles. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Lubana to minimize the loss function of the feature extractor for a better performance “The means for further updating parameters of the feature extractor may be configured to minimize a loss function, wherein the loss function includes a clustering parameter.” (Lubana Paragraph 0004).
Regarding claim 7, Alabbasi does not teach The method of claim 1, wherein the updating of the first machine-learning algorithm comprises updating at least one of a first feature extractor or a first controller logic.
However, Lubana does teach The method of claim 1, wherein the updating of the first machine-learning algorithm comprises updating at least one of a first feature extractor or a first controller logic. (Lubana Paragraph 0055; “the devices 24 to 26 may provide the parameters of the local feature extractors at the respective devices to the server 22” Lubana Paragraph 0076; “the parameters of the local feature extractor are updated based on or replaced with the global feature extractor parameters received in the operation 55.” Examiner notes first feature extractor (local feature extractor) is updated)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Lubana. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Lubana teaches a method for training a feature extractor of a device using machine learning principles. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Lubana to minimize the loss function of the feature extractor for a better performance “The means for further updating parameters of the feature extractor may be configured to minimize a loss function, wherein the loss function includes a clustering parameter.” (Lubana Paragraph 0004).
Regarding claim 11, Alabbasi does not teach The first device of claim 8, wherein: the processing circuit comprises a central processing unit (CPU);
and sending of the first update [comprises sending an update associated with the first feature extractor.]
However, Li does teach The first device of claim 8, wherein: the processing circuit comprises a central processing unit (CPU); (Li Paragraph 0042; “The communication device 200 may be a UE such as a specialized computer” Li Paragraph 0045; “The communication device 200 may include a hardware processor (or equivalently processing circuitry) 202 (e.g., a central processing unit (CPU), a GPU, a hardware processor core, or any combination thereof), a main memory 204 and a static memory 206, some or all of which may communicate with each other via an interlink (e.g., bus) 208.”)
and sending of the first update [comprises sending an update associated with the first feature extractor.] (Li Paragraph 0067; “ Local nodes (UEs) who are to use the model for the first time are to download the whole trained model package from the central server, as well as expected updated model parameters… Each local node (e.g., UE) starts local training based on its own data, and no information exchange is expected during this period for AI/ML model training purposes... Each local node reports its training model updated parameters to the central node” Examiner notes that the first update (updated parameters) is sent/report)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Alabbasi in view of Li does not teach the processing circuit is configured to train the first local controller by updating a first feature extractor associated with the processing circuit; and
[and sending of the first update comprises] sending an update associated with the first feature extractor.
However, Lubana does teach the processing circuit is configured to train the first local controller by updating a first feature extractor associated with the processing circuit; and (Lubana Paragraph 0055; “the devices 24 to 26 may provide the parameters of the local feature extractors at the respective devices to the server 22” Lubana Paragraph 0076; “the parameters of the local feature extractor are updated based on or replaced with the global feature extractor parameters received in the operation 55.” Examiner notes that the training comprises updating a first feature extractor (local feature extractor) associated with the first local controller (controller on devices 24))
[and sending of the first update comprises] sending an update associated with the first feature extractor. (Examiner refers to previous mapping to show that an update associated with the first feature extractor is sent/provided)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Lubana. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Lubana teaches a method for training a feature extractor of a device using machine learning principles. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Lubana to minimize the loss function of the feature extractor for a better performance “The means for further updating parameters of the feature extractor may be configured to minimize a loss function, wherein the loss function includes a clustering parameter.” (Lubana Paragraph 0004).
Regarding claim 14, Alabbasi does not teach The first device of claim 8, wherein the updating of the first machine-learning algorithm comprises updating at least one of a first feature extractor or a first controller logic.
However, Lubana does teach The first device of claim 8, wherein the updating of the first machine-learning algorithm comprises updating at least one of a first feature extractor or a first controller logic. (Lubana Paragraph 0055; “the devices 24 to 26 may provide the parameters of the local feature extractors at the respective devices to the server 22” Lubana Paragraph 0076; “the parameters of the local feature extractor are updated based on or replaced with the global feature extractor parameters received in the operation 55.” Examiner notes first feature extractor (local feature extractor) is updated)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Lubana. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Lubana teaches a method for training a feature extractor of a device using machine learning principles. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Lubana to minimize the loss function of the feature extractor for a better performance “The means for further updating parameters of the feature extractor may be configured to minimize a loss function, wherein the loss function includes a clustering parameter.” (Lubana Paragraph 0004).
Regarding claim 18, Alabbasi does not teach The system of claim 15, wherein: the processing circuit comprises a central processing unit (CPU);
and sending of the first update [comprises sending an update associated with the first feature extractor.]
However, Li does teach The system of claim 15, wherein: the processing circuit comprises a central processing unit (CPU); (Li Paragraph 0042; “The communication device 200 may be a UE such as a specialized computer” Li Paragraph 0045; “The communication device 200 may include a hardware processor (or equivalently processing circuitry) 202 (e.g., a central processing unit (CPU), a GPU, a hardware processor core, or any combination thereof), a main memory 204 and a static memory 206, some or all of which may communicate with each other via an interlink (e.g., bus) 208.”)
and sending of the first update [comprises sending an update associated with the first feature extractor.] (Li Paragraph 0067; “ Local nodes (UEs) who are to use the model for the first time are to download the whole trained model package from the central server, as well as expected updated model parameters… Each local node (e.g., UE) starts local training based on its own data, and no information exchange is expected during this period for AI/ML model training purposes... Each local node reports its training model updated parameters to the central node” Examiner notes that the first update (updated parameters) is sent/report)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Alabbasi in view of Li does not teach the processing circuit is configured to train the first local controller by updating a first feature extractor associated with the processing circuit; and
[and sending of the first update comprises] sending an update associated with the first feature extractor.
However, Lubana does teach the processing circuit is configured to train the first local controller by updating a first feature extractor associated with the processing circuit; and (Lubana Paragraph 0055; “the devices 24 to 26 may provide the parameters of the local feature extractors at the respective devices to the server 22” Lubana Paragraph 0076; “the parameters of the local feature extractor are updated based on or replaced with the global feature extractor parameters received in the operation 55.” Examiner notes that the training comprises updating a first feature extractor (local feature extractor) associated with the first local controller (controller on devices 24))
[and sending of the first update comprises] sending an update associated with the first feature extractor. (Examiner refers to previous mapping to show that an update associated with the first feature extractor is sent/provided)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Lubana. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Lubana teaches a method for training a feature extractor of a device using machine learning principles. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Lubana to minimize the loss function of the feature extractor for a better performance “The means for further updating parameters of the feature extractor may be configured to minimize a loss function, wherein the loss function includes a clustering parameter.” (Lubana Paragraph 0004).
Regarding claim 20, Alabbasi does not teach The system of claim 15, wherein updating of the first machine-learning algorithm comprises updating at least one of a first feature extractor or a first controller logic.
However, Lubana does teach The system of claim 15, wherein updating of the first machine-learning algorithm comprises updating at least one of a first feature extractor or a first controller logic. (Lubana Paragraph 0055; “the devices 24 to 26 may provide the parameters of the local feature extractors at the respective devices to the server 22” Lubana Paragraph 0076; “the parameters of the local feature extractor are updated based on or replaced with the global feature extractor parameters received in the operation 55.” Examiner notes first feature extractor (local feature extractor) is updated)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Lubana. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Lubana teaches a method for training a feature extractor of a device using machine learning principles. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Lubana to minimize the loss function of the feature extractor for a better performance “The means for further updating parameters of the feature extractor may be configured to minimize a loss function, wherein the loss function includes a clustering parameter.” (Lubana Paragraph 0004).
Claim(s) 5, 12, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Abdulrahman Alabbasi et al; US 20230010095 A1 filed on Dec 18, 2019 (hereinafter “Alabbasi”) in view of Arhum Ahmad et al; “DeepDeMod: BPSK Demodulation Using Deep Learning Over Software-Defined Radio” published Nov 2, 2022 (hereinafter “Ahmad”) in further view of Ziyi Li et al; US 20220038349 A1 filed on Oct 19, 2021 (hereinafter “Li”) in further view of Aaron Werth et al; US 12238120 B1 filed on Dec 10, 2021 (hereinafter “Werth”)
Regarding claim 5, Alabbasi does not teach The method of claim 1, wherein: the first edge device comprises a processing circuit comprising an artificial intelligence (AI) processor;
and sending the first update [comprises sending an update associated with the first controller logic.]
However, Li does teach The method of claim 1, wherein: the first edge device comprises a processing circuit comprising an artificial intelligence (AI) processor; (Li Paragraph 0042; “The communication device 200 may be a UE such as a specialized computer” Li Paragraph 0045; “The communication device 200 may include a hardware processor (or equivalently processing circuitry) 202 (e.g., a central processing unit (CPU), a GPU, a hardware processor core, or any combination thereof), a main memory 204 and a static memory 206, some or all of which may communicate with each other via an interlink (e.g., bus) 208.” Examiner notes that a GPU is an artificial intelligence processor)
and sending the first update [comprises sending an update associated with the first controller logic.] (Li Fig 4 and Paragraph 0067; “ Local nodes (UEs) who are to use the model for the first time are to download the whole trained model package from the central server, as well as expected updated model parameters… Each local node (e.g., UE) starts local training based on its own data, and no information exchange is expected during this period for AI/ML model training purposes... Each local node reports its training model updated parameters to the central node” Examiner notes that the first update (updated parameters) is sent/report)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Alabbasi in view of Li does not teach the training comprises updating a first controller logic associated with the first local controller;
However, Werth does teach the training comprises updating a first controller logic associated with the first local controller; (Werth Column 13 Line 8; “The monitoring and evaluation of incoming packets step involves using the physical system model 222 (i.e., the selected and validated ARMA model) to evaluate incoming command packets and controller process logic uploads (i.e., changes and/or updates to the controller process logic 174).” Examiner notes that the training comprises updating a first controller logic (updates to the controller process logic) associated with the first local controller (Fig 4 industrial controller))
PNG
media_image1.png
540
667
media_image1.png
Greyscale
[and sending the first update comprises] sending an update associated with the first controller logic. (Examiner refers to previous mapping to show that an update associated with the first controller logic (updates to the controller process logic) is sent/uploaded)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Werth. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Werth teaches an intrusion prevention system that can be embedded into an industrial controller, such as programmable logic controller (PLC), for an industrial control system. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Werth to protect edge controllers from cyberattacks “Thus, it would be beneficial to have an intrusion prevention system in the edge controllers as a last line of defense against cyberattacks on physical systems and processes.” (Werth Column 1 Paragraph 59).
Regarding claim 12, Alabbasi does not teach The first device of claim 8, wherein: the processing circuit comprises an artificial intelligence (Al) processor;
and sending of the first update [comprises sending an update associated with the first controller logic.]
However, Li does teach The first device of claim 8, wherein: the processing circuit comprises an artificial intelligence (Al) processor; (Li Paragraph 0042; “The communication device 200 may be a UE such as a specialized computer” Li Paragraph 0045; “The communication device 200 may include a hardware processor (or equivalently processing circuitry) 202 (e.g., a central processing unit (CPU), a GPU, a hardware processor core, or any combination thereof), a main memory 204 and a static memory 206, some or all of which may communicate with each other via an interlink (e.g., bus) 208.” Examiner notes that a GPU is an artificial intelligence processor)
and sending of the first update [comprises sending an update associated with the first controller logic.] (Li Fig 4 and Paragraph 0067; “ Local nodes (UEs) who are to use the model for the first time are to download the whole trained model package from the central server, as well as expected updated model parameters… Each local node (e.g., UE) starts local training based on its own data, and no information exchange is expected during this period for AI/ML model training purposes... Each local node reports its training model updated parameters to the central node” Examiner notes that the first update (updated parameters) is sent/report)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Alabbasi in view of Li does not teach the processing circuit is configured to train the first local controller by updating a first controller logic associated with the processing circuit; and
[and sending of the first update comprises] sending an update associated with the first controller logic.
However, Werth does teach the processing circuit is configured to train the first local controller by updating a first controller logic associated with the processing circuit; and (Werth Column 13 Line 8; “The monitoring and evaluation of incoming packets step involves using the physical system model 222 (i.e., the selected and validated ARMA model) to evaluate incoming command packets and controller process logic uploads (i.e., changes and/or updates to the controller process logic 174).” Examiner notes that the training comprises updating a first controller logic (updates to the controller process logic) associated with the first local controller (Fig 4 industrial controller))
PNG
media_image1.png
540
667
media_image1.png
Greyscale
[and sending of the first update comprises] sending an update associated with the first controller logic. (Examiner refers to previous mapping to show that an update associated with the first controller logic (updates to the controller process logic) is sent/uploaded)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Werth. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Werth teaches an intrusion prevention system that can be embedded into an industrial controller, such as programmable logic controller (PLC), for an industrial control system. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Werth to protect edge controllers from cyberattacks “Thus, it would be beneficial to have an intrusion prevention system in the edge controllers as a last line of defense against cyberattacks on physical systems and processes.” (Werth Column 1 Paragraph 59).
Regarding claim 19, Alabbasi does not teach The system of claim 15, wherein: the processing circuit comprises an artificial intelligence (AI) processor;
and sending of the first update [comprises sending an update associated with the first controller logic.]
However, Li does teach The system of claim 15, wherein: the processing circuit comprises an artificial intelligence (AI) processor; (Li Paragraph 0042; “The communication device 200 may be a UE such as a specialized computer” Li Paragraph 0045; “The communication device 200 may include a hardware processor (or equivalently processing circuitry) 202 (e.g., a central processing unit (CPU), a GPU, a hardware processor core, or any combination thereof), a main memory 204 and a static memory 206, some or all of which may communicate with each other via an interlink (e.g., bus) 208.” Examiner notes that a GPU is an artificial intelligence processor)
and sending of the first update [comprises sending an update associated with the first controller logic.] (Li Fig 4 and Paragraph 0067; “ Local nodes (UEs) who are to use the model for the first time are to download the whole trained model package from the central server, as well as expected updated model parameters… Each local node (e.g., UE) starts local training based on its own data, and no information exchange is expected during this period for AI/ML model training purposes... Each local node reports its training model updated parameters to the central node” Examiner notes that the first update (updated parameters) is sent/report)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, and Li. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, and Li to obtain a well performed model covering various environments and feedbacks “By taking advantage of various updated parameters from UEs that experience different environments and channel conditions, a general trained model at the local server (RAN) can not only guarantee the privacy and security between UEs, but also train a well-performed model covering various environments and feedbacks.” (Li Paragraph 0071).
Alabbasi in view of Li does not teach the processing circuit is configured to train the first local controller by updating a first controller logic associated with the processing circuit; and
[and sending of the first update comprises] sending an update associated with the first controller logic.
However, Werth does teach the processing circuit is configured to train the first local controller by updating a first controller logic associated with the processing circuit; and (Werth Column 13 Line 8; “The monitoring and evaluation of incoming packets step involves using the physical system model 222 (i.e., the selected and validated ARMA model) to evaluate incoming command packets and controller process logic uploads (i.e., changes and/or updates to the controller process logic 174).” Examiner notes that the training comprises updating a first controller logic (updates to the controller process logic) associated with the first local controller (Fig 4 industrial controller))
PNG
media_image1.png
540
667
media_image1.png
Greyscale
[and sending of the first update comprises] sending an update associated with the first controller logic. (Examiner refers to previous mapping to show that an update associated with the first controller logic (updates to the controller process logic) is sent/uploaded)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Alabbasi, Ahmad, Li, and Werth. Alabbasi teaches methods performed by a first node in a communications network. Ahmad teaches a non-coherent binary phase shift keying demodulator based on deep neural network. Li teaches a system to provide a federated learning scheme between a RAN and connected UEs. Werth teaches an intrusion prevention system that can be embedded into an industrial controller, such as programmable logic controller (PLC), for an industrial control system. One of ordinary skill would have motivation to combine Alabbasi, Ahmad, Li, and Werth to protect edge controllers from cyberattacks “Thus, it would be beneficial to have an intrusion prevention system in the edge controllers as a last line of defense against cyberattacks on physical systems and processes.” (Werth Column 1 Paragraph 59).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL DUC TRAN whose telephone number is (571)272-6870. The examiner can normally be reached Mon-Fri 8:00-5:00 EST.
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, Viker Lamardo can be reached at (571) 270-5871. 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.
/D.D.T./Examiner, Art Unit 2147
/ERIC NILSSON/Primary Examiner, Art Unit 2151
Prosecution Insights