DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement filed 12/2/2025 fails to comply with 37 CFR 1.98(b)(5) (“Each publication listed in an information disclosure statement must be identified by publisher, author (if any), title, relevant pages of the publication, date, and place of publication.”) because it does not include all the required information including author, relevant pages, and date. It has been placed in the application file, but the information referred to therein has not been considered as indicated by the corresponding strike-through.
Drawings
The drawings are objected to because Figure 3 has a horizontal axis with various numbers that are bunched up together in a manner that makes it incomprehensible and difficult to understand.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The title of the invention is not descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed.
Claim Objections
Claim 19 is objected to because of the following informalities: Claim 19’s preamble indicates it is directed to a client where the body of the claim indicates that this client sends “a first instruction to a client” and also receives “a training result reported by the client”. The usage of ‘A client’ as the subject of the claim as well as having that client interact with another ‘a client’ can cause confusion. Based on claim 1’s limitations being substantially similar to claim 19 and claim 1 illustrating a central device communicating with a client, it is apparent that the various “the client” refers to currently; however, later amendments could compound on this issue and cause greater confusion as to what “the client” would refer to. The Examiner recommends that the preamble be changed to either “A server” or “A central device” or that the body of the claim provide some label for the client, e.g. “sending a first instruction to a first client” (or second client) and subsequently receiving a training result “reported by the first client” (or second client). Appropriate correction is required.
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 2-7 and 10-17 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
With regard to claim 1, no limitation was identified that was directed towards an abstract idea under Step 2A, Prong One. However, as noted below, other claims are directed towards an abstract idea.
With regard to claim 2:
Step 2A, Prong One:
The claim recites the following limitations which are drawn towards an abstract idea:
wherein the sending, by a central device, a first instruction to a client comprises: screening, by the central device, N clients from M candidate clients according to a preset first screening condition (recites mental process steps of evaluation/comparison of a dataset to rules/conditions to form a decision/judgement),
As seen from above, the identified limitations recite concepts associated with an abstract idea and thus the respective claim recites a judicial exception (see 2106.04(a)) and thus requires further analysis as discussed below.
Step 2A, Prong Two:
The following limitations have been identified as being additional elements as discussed below.
A client screening method, comprising: sending,
“by a central device” (which recites a generic computer element at a high-level of generality to implement the abstract idea, similar to apply-it type limitations, see MPEP 2106.05(f)),
receiving, by the central device, a training result reported by the client (recites insignificant extrasolution activity of receiving information, see MPEP 2106.05(g)),
wherein the training result is a result or an intermediate result after the client performs a round of model training (recites field of use limitations describing the intended meaning of the received data, see MPEP 2106.05(h));
and unicasting the first instruction to the N clients, wherein M and N are positive integers, and N is less than or equal to M; or broadcasting, by the central device, the first instruction to M candidate clients, wherein the first instruction carries a second screening condition, the second screening condition is used for screening a client that reports the training result, and the client meets the second screening condition (recites insignificant extrasolution activity of transmitting information, see MPEP 2106.05(g)).
As seen from the above discussion, the identified limitations did not integrate the judicial exception into a practical application (see MPEP 2106.04(d)). This judicial exception is not integrated into a practical application because the additional elements describe at a high-level of generality a central device that under broadest reasonable interpretation is a generic computer performing generic computer functionality including transmitting and receiving data.
Step 2B:
Below is the analysis of the claims:
A client screening method, comprising: sending,
“by a central device” (which recites a generic computer element at a high-level of generality to implement the abstract idea, similar to apply-it type limitations, see MPEP 2106.05(f)),
receiving, by the central device, a training result reported by the client (recites well-understood, routine, and conventional activity of receiving information, see MPEP 2106.05(d)),
wherein the training result is a result or an intermediate result after the client performs a round of model training (recites field of use limitations describing the intended meaning of the received data, see MPEP 2106.05(h));
and unicasting the first instruction to the N clients, wherein M and N are positive integers, and N is less than or equal to M; or broadcasting, by the central device, the first instruction to M candidate clients, wherein the first instruction carries a second screening condition, the second screening condition is used for screening a client that reports the training result, and the client meets the second screening condition (recites well-understood, routine, and conventional activity of transmitting information, see MPEP 2106.05(d)).
As seen from above, the respective claim elements taken individually do not amount to significantly more than the judicial exception. When taken as a whole (in combination), the claim also does not amount to significantly more than the abstract idea because the additional elements describe at a high-level of generality a central device that under broadest reasonable interpretation is a generic computer performing generic computer functionality including transmitting and receiving data.
With regard to claim 3, this claim recites wherein before the sending, by a
central device, a first instruction to a client, the method further comprises: receiving, by the central device, first training data and/or a first parameter reported by each candidate client (recites insignificant extra-solution activity of receiving information which amounts to well-understood, routine, and conventional activity of receiving information over a network, see MPEP 2106.05(d)),
wherein the first parameter is a determining parameter of the first screening condition (recites field of use limitations describing the intended meaning of the received data, see MPEP 2106.05(h)).
With regard to claim 4, this claim recites wherein the central device only receives the first training data reported by each candidate client (recites insignificant extra-solution activity of receiving information which amounts to well-understood, routine, and conventional activity of receiving information over a network, see MPEP 2106.05(d)),
and determines the first parameter based on the first training data (recites mental process steps of evaluation and analysis to form a determination/judgement based on the dataset);
and/or, wherein the first parameter comprises at least one of the following: a data type of the candidate client; a data distribution parameter of the candidate client; a service type of the candidate client; a working scenario of the candidate client; a communication network access manner of the candidate client; channel quality of the candidate client; difficulty in collecting data of the candidate client; a battery level state of the candidate client; a storage state of the candidate client; computing power of the candidate client; a number of times that the candidate client participates in the model training of the specific federated learning or federated meta learning; and willingness of the candidate client for participating in the model training of the specific federated learning or federated meta learning (recites field of use limitations describing the intended meaning of the received data, see MPEP 2106.05(h)).
With regard to claim 5, this claim recites wherein the unicasted first instruction comprises at least one of the following: a model file; a structure of a model; a model initialization parameter; an output physical quantity of the model; an input physical quantity of the model; a reference point corresponding to the model; a hyperparameter of the model; and communication information; or, wherein the broadcasted first instruction comprises at least one of the following: an identifier of each candidate client that participates in training; an identifier of each candidate client that does not participate in training; a first screening condition; a model file; a structure of a model; a model initialization parameter; an output physical quantity of the model; an input physical quantity of the model; a reference point corresponding to the model; a hyperparameter of the model; and communication information (recites field of use limitations describing the intended meaning of the sent information, see MPEP 2106.05(h)).
With regard to claim 6, this claim recites wherein after the receiving, by the central device, a training result reported by the client, the method further comprises: sending, by the central device in a case of determining that a model reaches convergence according to the training result (recites mental process step of comparison/evaluation/analysis to know what a condition is reached), a converged model and a hyperparameter to L inference clients, wherein L is greater than M, equal to M, or less than M (recites insignificant extra-solution activity of transmitting information which amounts to well-understood, routine, and conventional activity of transmitting information over a network, see MPEP 2106.05(d)).
With regard to claim 7, this claim recites wherein the model is a federated meta learning model (recites apply-it limitations describing the computer element that is used at a high-level of generality to implement the abstract idea, see MPEP 2106.05(f)), and the hyperparameter is determined by the first parameter; or, wherein the hyperparameter comprises at least one of the following: a learning rate, an external iteration learning rate, an internal iteration learning rate, a meta learning rate, a number of iterations, a number of internal iterations, a number of external iterations, a data volume required for training, a size of a batch, a size of a mini batch, a regularization parameter, a number of layers of a neural network, a number of neurons in each hidden layer, a number of learning epochs, selection of a cost function, and a neuron activation function (recites field of use limitations describing the intended meaning of some of the data, see MPEP 2106.05(h)).
With regard to claim 8, similar to claim 1, this claim does not recite any limitation that is directed towards a judicial exception.
With regard to claims 9-10, these claims are substantially similar to claims 1-2 and the same rationale described above applies to these claims too.
With regard to claim 11, this claim recites wherein the performing, by the client, the model training of the specific federated learning or federated meta learning, and reporting a training result to the central device comprises: performing, by the client, the model training and reporting the training result if the client receives the first instruction unicasted by the central device; or performing, by the client, the model training and reporting the training result if the client receives the first instruction broadcasted by the central device (recites apply-it limitations of using generic computer to perform judicial exception such as training a model to perform a function, see MPEP 2106.05(f); additionally, the reporting limitation recites insignificant extrasolution activity of transmitting information which amounts to well-understood, routine, and conventional activity of transmitting information, see MPEP 2106.05(d)).
With regard to claim 12, this claim is substantially similar to claims 3 and 4 and is rejected for similar reasons as discussed above.
With regard to claim 13, this claim is substantially similar to claim 5 and is rejected for similar reasons as discussed above.
With regard to claim 14, this claim is substantially similar to claim 6 and is rejected for similar reasons as discussed above.
With regard to claim 15, this claim is substantially similar to claim 7 and is rejected for similar reasons as discussed above.
With regard to claim 16, this claim recites wherein a first part of the hyperparameter is determined by a first parameter corresponding to the inference client, and the first part comprises at least one of the following: an external iteration learning rate, an internal iteration learning rate, a meta learning rate, a number of internal iterations, and a number of external iterations (recites field of use limitations of describing meaning of particular data/parameters that are used by the system, see MPEP 2106.05(h)).
With regard to claim 17, this claim recites wherein after the receiving, by an inference client, a converged model and a hyperparameter sent by the central device, the method further comprises: performing, by the inference client, performance verification on the model (recites apply-it type limitations of testing machine learning models which recites generic computer elements performing generic computer functionality, see MPEP 2106.05(f));
and using, by the inference client, the model for inference if a performance verification result meets a preset first condition (recites apply-it limitations of using the trained model to perform some action at a high-level of generality, see MPEP 2106.05(f));
wherein the model on which performance verification is performed is a model distributed by the central device, or a fine-tuned model of the model distributed by the central device (recites insignificant extrasolution activity of transmitting/receiving information over a network which amounts to well-understood, routine, and conventional activity of transmitting/receiving information over a network, see MPEP 2106.05(d)).
Claims 18-20 are substantially similar to claims 8, 1, and 1 respectively and the same rational as discussed above applies to these claims respectively.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-5, 8-13, and 18-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by AbdulRahman et al, FedMCCS: Multicriteria Client Selection Model for Optimal IoT Federated Learning (reference provided from IDS).
With regard to claim 1, AbdulRahman teaches a client screening method, comprising: sending, by a central device, a first instruction to a client, to indicate the client to participate in model training of specific federated learning or federated meta learning (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request as well as Protocol 3 in the right column steps 2 and 3; the system or central device/server can send an instruction/request that indicates the desire for the client to participate in model training);
and receiving, by the central device, a training result reported by the client, wherein the training result is a result or an intermediate result after the client performs a round of model training (see page 4727, right column steps 6) and 7) as well as Protocol 3 steps 6 and 7; the client can perform the training and be able to provide results of their training back to the server/central device).
With regard to claim 2, AbdulRahman teaches wherein the sending, by a central device, a first instruction to a client comprises: screening, by the central device, N clients from M candidate clients according to a preset first screening condition, and unicasting the first instruction to the N clients, wherein M and N are positive integers, and N is less than or equal to M; or broadcasting, by the central device, the first instruction to M candidate clients, wherein the first instruction carries a second screening condition, the second screening condition is used for screening a client that reports the training result, and the client meets the second screening condition (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request as well as Protocol 3 in the right column steps 2 and 3; the system or central device/server can filter/screen clients and be able to communicate with only the filtered/screened clients).
With regard to claim 3, AbdulRahman teaches wherein before the sending, by a central device, a first instruction to a client, the method further comprises: receiving, by the central device, first training data and/or a first parameter reported by each candidate client, wherein the first parameter is a determining parameter of the first screening condition (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request as well as Protocol 3 in the right column steps 2 and 3; see page 4728, second paragraph in section C.; the clients can send the server information about their resources via a first parameter).
With regard to claim 4, AbdulRahman teaches wherein the central device only receives the first training data reported by each candidate client, and determines the first parameter based on the first training data; and/or, wherein the first parameter comprises at least one of the following: a data type of the candidate client; a data distribution parameter of the candidate client; a service type of the candidate client; a working scenario of the candidate client; a communication network access manner of the candidate client; channel quality of the candidate client; difficulty in collecting data of the candidate client; a battery level state of the candidate client; a storage state of the candidate client; computing power of the candidate client; a number of times that the candidate client participates in the model training of the specific federated learning or federated meta learning; and willingness of the candidate client for participating in the model training of the specific federated learning or federated meta learning (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request as well as Protocol 3 in the right column steps 2 and 3; see page 4728, second paragraph in section C.; the clients can send the server information about their resources via a first parameter such as computing power).
With regard to claim 5, AbdulRahman teaches wherein the unicasted first instruction comprises at least one of the following: a model file; a structure of a model; a model initialization parameter; an output physical quantity of the model; an input physical quantity of the model; a reference point corresponding to the model; a hyperparameter of the model; and communication information; or, wherein the broadcasted first instruction comprises at least one of the following: an identifier of each candidate client that participates in training; an identifier of each candidate client that does not participate in training; a first screening condition; a model file; a structure of a model; a model initialization parameter; an output physical quantity of the model; an input physical quantity of the model; a reference point corresponding to the model; a hyperparameter of the model; and communication information (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request and 5) Distribution; as well as Protocol 3 in the right column steps 2 and 3 and 5; the system or central device/server can filter/screen clients and be able to communicate with only the filtered/screened clients including providing communication information to the clients).
With regard to claim 8, AbdulRahman teaches wherein the central device is a network side device or a terminal; and the client is a network side device or a terminal (see Figure 1; various computing devices can be used including a terminal/server and IoT devices or network side devices).
With regard to claim 9, AbdulRahman teaches a client screening method, comprising: receiving, by a client, a first instruction from a central device, wherein the first instruction is used for indicating the client to participate in model training of specific federated learning or federated meta learning (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request as well as Protocol 3 in the right column steps 2 and 3; the client can receive an instruction from the system or central device/server that indicates the desire for the client to participate in model training);
performing, by the client, the model training of the specific federated learning or federated meta learning, and reporting a training result to the central device, wherein the training result is a result or an intermediate result after the client performs a round of model training (see page 4727, right column steps 6) and 7) as well as Protocol 3 steps 6 and 7; the client can perform the training and be able to provide/report results of their training back to the server/central device).
With regard to claim 10, AbdulRahman teaches wherein the receiving, by a client, a first instruction from a central device comprises: receiving, by the client, the first instruction unicasted by the central device, wherein the client is a client screened by the central device from candidate clients according to a preset first screening condition; or receiving, by the client, the first instruction broadcasted by the central device, wherein the first instruction carries a second screening condition, the second screening condition is used for screening a client that reports the training result, and the client meets the second screening condition (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request as well as Protocol 3 in the right column steps 2 and 3; the system or central device/server can filter/screen clients and be able to communicate with only the filtered/screened clients).
With regard to claim 11, AbdulRahman teaches wherein the performing, by the client, the model training of the specific federated learning or federated meta learning, and reporting a training result to the central device comprises: performing, by the client, the model training and reporting the training result if the client receives the first instruction unicasted by the central device; or performing, by the client, the model training and reporting the training result if the client receives the first instruction broadcasted by the central device (see page 4727, right column steps 6) and 7) as well as Protocol 3 steps 6 and 7; the client can perform the training and be able to provide/report results of their training back to the server/central device).
With regard to claim 12, AbdulRahman teaches wherein before the receiving, by a client, a first instruction from a central device, the method further comprises: reporting, by each candidate client, first training data and/or a first parameter to the central device, wherein the first parameter is a determining parameter of the first screening condition, and the first training data is used for determining the first parameter (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request as well as Protocol 3 in the right column steps 2 and 3; see page 4728, second paragraph in section C.; the clients can send the server information about their resources via a first parameter);
wherein the first parameter comprises at least one of the following: a data type of the candidate client; a data distribution parameter of the candidate client; a service type of the candidate client; a working scenario of the candidate client; a communication network access manner of the candidate client; channel quality of the candidate client; difficulty in collecting data of the candidate client; a battery level state of the candidate client; a storage state of the candidate client; computing power of the candidate client; a number of times that the candidate client participates in the model training of the specific federated learning or federated meta learning; and willingness of the candidate client for participating in the model training of the specific federated learning or federated meta learning (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request as well as Protocol 3 in the right column steps 2 and 3; see page 4728, second paragraph in section C.; the clients can send the server information about their resources via a first parameter such as computing power).
With regard to claim 13, AbdulRahman teaches wherein the unicasted first instruction comprises at least one of the following: a model file; a structure of a model; a model initialization parameter; an output physical quantity of the model; an input physical quantity of the model; a reference point corresponding to the model; a hyperparameter of the model; and communication information; or, wherein the broadcasted first instruction comprises at least one of the following: an identifier of each candidate client that participates in training; an identifier of each candidate client that does not participate in training; a first screening condition; a model file; a structure of a model; a model initialization parameter; an output physical quantity of the model; an input physical quantity of the model; a reference point corresponding to the model; a hyperparameter of the model; and communication information (see page 4727, left column, bullet points 2) Client Filtering and 3) Resource Request and 5) Distribution; as well as Protocol 3 in the right column steps 2 and 3 and 5; the system or central device/server can filter/screen clients and be able to communicate with only the filtered/screened clients including providing communication information to the clients).
With regard to claim 18, AbdulRahman teaches wherein the central device is a network side device or a terminal; and the client is a network side device or a terminal (see Figure 1; various computing devices can be used including a terminal/server and IoT devices or network side devices).
With regard to claims 19 and 20, these claims are substantially similar to claim 1 and are rejected for similar reasons as discussed above.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 6, 7, 14, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over AbdulRahman et al, FedMCCS: Multicriteria Client Selection Model for Optimal IoT Federated Learning (reference provided from IDS) in view of Guo et al [US 2022/0318412 A1].
With regard to claim 6, AbdulRahman teaches all the claim limitations of claims 1-3 as discussed above.
AbdulRahman teaches model convergence (see Protocols 2 and 3 such as repeating the steps until achieving a desired performance of the model, i.e. convergence) but do not appear to explicitly teach:
wherein after the receiving, by the central device, a training result reported by the client, the method further comprises: sending, by the central device in a case of determining that a model reaches convergence according to the training result, a converged model and a hyperparameter to L inference clients, wherein L is greater than M, equal to M, or less than M.
Guo teaches wherein after the receiving, by the central device, a training result reported by the client, the method further comprises: sending, by the central device in a case of determining that a model reaches convergence according to the training result, a converged model and a hyperparameter to L inference clients, wherein L is greater than M, equal to M, or less than M (see paragraphs [0030] and [0072] and [0078]-[0079]; the system can send the final model to all the clients as well as hyperparameters).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify the federated learning system of AbdulRahman by sending the clients the final model as taught by Guo in order to allow the system to actually be used by the clients after spending their resources to help train the respective model thereby not only increasing ability to train models but also allows the system to use the models too.
With regard to claim 7, AbdulRahman in view of Guo teach wherein the model is a federated meta learning model, and the hyperparameter is determined by the first parameter; or, wherein the hyperparameter comprises at least one of the following: a learning rate, an external iteration learning rate, an internal iteration learning rate, a meta learning rate, a number of iterations, a number of internal iterations, a number of external iterations, a data volume required for training, a size of a batch, a size of a mini batch, a regularization parameter, a number of layers of a neural network, a number of neurons in each hidden layer, a number of learning epochs, selection of a cost function, and a neuron activation function (see Guo, paragraph [0055]; the system can provide various parameters to the user including number of layers).
With regard to claim 14, this claim is substantially similar to claim 6 and is rejected for similar reasons as discussed above.
With regard to claim 15, this claim is substantially similar to claim 7 and is rejected for similar reasons as discussed above.
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over AbdulRahman et al, FedMCCS: Multicriteria Client Selection Model for Optimal IoT Federated Learning (reference provided from IDS) in view of Guo et al [US 2022/0318412 A1] in further view of Balakrishnan et al [US 2023/0177349 A1].
With regard to claim 16, AbdulRahman in view of Guo teach all the claim limitations of claims 9, 10, 12, 14, and 15 as discussed above.
AbdulRahman in view of Guo teach various hyperparameters (see Guo, paragraph [0055]; see AbdulRahman, page 4731, right column, section D) but do not appear to explicitly teach:
wherein a first part of the hyperparameter is determined by a first parameter corresponding to the inference client, and the first part comprises at least one of the following: an external iteration learning rate, an internal iteration learning rate, a meta learning rate, a number of internal iterations, and a number of external iterations.
Balakrishnan teaches wherein a first part of the hyperparameter is determined by a first parameter corresponding to the inference client, and the first part comprises at least one of the following: an external iteration learning rate, an internal iteration learning rate, a meta learning rate, a number of internal iterations, and a number of external iterations (see paragraph [0219]; the system can utilize other hyperparameters).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify the federated learning system of AbdulRahman in view of Guo by utilizing other widely used hyperparameters as taught by Balakrishnan in order to allow the system to be customized accordingly with respect to how it is going to be training so that the training can perform and accomplish training in a reasonable amount of time such as by limiting the number of iterations for training thus preventing stalled training (where a local model doesn’t converge for extremely long periods) which wastes the systems time and processing resources.
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over AbdulRahman et al, FedMCCS: Multicriteria Client Selection Model for Optimal IoT Federated Learning (reference provided from IDS) in view of Guo et al [US 2022/0318412 A1] in further view of Zivkovic et al [US 2022/0308975 A1].
With regard to claim 17, AbdulRahman in view of Guo teach all the claim limitations of claims 9, 10, 12, and 14 as discussed above.
AbdulRahman in view of Guo do not appear to explicitly teach:
wherein after the receiving, by an inference client, a converged model and a hyperparameter sent by the central device, the method further comprises: performing, by the inference client, performance verification on the model; and using, by the inference client, the model for inference if a performance verification result meets a preset first condition; wherein the model on which performance verification is performed is a model distributed by the central device, or a fine-tuned model of the model distributed by the central device.
Zivkovic teaches wherein after the receiving, by an inference client, a converged model and a hyperparameter sent by the central device, the method further comprises: performing, by the inference client, performance verification on the model (see paragraphs [0032] and [0006]-[0007]; the client device is able to performing testing on the respective model to determine performance measurements).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify the federated learning system of AbdulRahman in view of Guo by allowing for local performance evaluations of the model by clients as taught by Zivkovic in order to allow the client systems to be able to discern whether the received model performs adequately within required conditions/parameters and be able to have means adjust that device’s respective model accordingly to align with the heterogeneous client device’s hardware capabilities thus helping to optimize the model for lower performance devices while still maintaining the respective model for other devices that meet the performance verification conditions thus allowing higher performing devices to keep and use higher performing models while still allowing lower performing devices to be able to use the model(s).
AbdulRahman in view of Guo in further view of Zivkovic teach using, by the inference client, the model for inference if a performance verification result meets a preset first condition; wherein the model on which performance verification is performed is a model distributed by the central device, or a fine-tuned model of the model distributed by the central device (see Guo, paragraphs [0030], [0072], and [0078]-[0079]; AbdulRahman, page 4727, right column section 8); and Zivkovic, paragraphs [0032], [0037], and [0006]-[0007]; the system can send the final model to all the clients as well as hyperparameters where the client device can perform performance testing/verification and can activate or use the respective model when performance meets some condition/threshold).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Chu et al [US 2021/0374617 A1] teaches at paragraph [0047] that the system can send the final model from federated learning to all the clients.
Ding et al [US 2022/0300618 A1] teaches at paragraph [0055] that the finalized model is deployed to the various clients for usage as well as hyperparameters of at least learning rate and number of local epochs (paragraph 58-59) which help lead to optimization in heterogeneous systems including communication constrained networks.
Wang et al [US 2022/0076169 A1] teaches federated learning with client selection as shown in Figure 2.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARC S SOMERS whose telephone number is (571)270-3567. The examiner can normally be reached M-F 11-8 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, Ann Lo can be reached at 5712729767. 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.
/MARC S SOMERS/Primary Examiner, Art Unit 2159 9/8/2026
Prosecution Insights