DETAILED ACTION
This action is in response to claims filed 19 January 2024 for application 18290603 filed 19 January 2024. Currently claims 1-20 are pending.
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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
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.
Claim(s) 1-9, 12-13, and 15-20 is/are rejected under 35 U.S.C. 102(A)(1) as being anticipated by Niknam et al. (Federated Learning for Wireless Communications: Motivation, Opportunities and Challenges).
Regarding claims 1 and 16, Niknam discloses: An user equipment (UE) (Fig 2), comprising:
at least one memory (Fig 2); and
at least one processor coupled with the at least one memory and configured to cause the UE to (Fig 2):
receive a first request from a network function, wherein the first request comprises first requirements to provide a trained model (“In general, NWDAF is capable of connecting to any network function (NF) and utilizing any data in the core network (see Fig. 4). In addition, any NF can request network analytic information.” P4 §III.C ¶1);
determine model parameters for aggregation using federated learning based on the first requirements in the first request (“NWDAF can act as the global node that handles the aggregation of the user data. The datasets of the users are vertically fragmented over different entities in the core network, where each entity keeps record of a specific data feature related to all the users. Using vertical federated learning, each entity in the core network transfers its local encrypted model trained by locally collected data features rather than sending the raw data to the NWDAF entity. This can significantly alleviate the massive cybersecurity vulnerability within the network topology introduced by network function virtualization (NFV).” P5 §III.C);
discover at least one local model training logical function that can provide model parameters for aggregation using federated learning based on the first requirements (“NWDAF can act as the global node that handles the aggregation of the user data. The datasets of the users are vertically fragmented over different entities in the core network, where each entity keeps record of a specific data feature related to all the users. Using vertical federated learning, each entity in the core network transfers its local encrypted model trained by locally collected data features rather than sending the raw data to the NWDAF entity. This can significantly alleviate the massive cybersecurity vulnerability within the network topology introduced by network function virtualization (NFV).” P5 §III.C, see also p2 §II ¶1 for federated learning structure of requesting a trained model, training locally, updating the global model with local parameters, and repeating as necessary to train a global model);
transmit a second request to the at least one local model training logical function to receive the model parameters for deriving the aggregated trained model (“NWDAF can act as the global node that handles the aggregation of the user data. The datasets of the users are vertically fragmented over different entities in the core network, where each entity keeps record of a specific data feature related to all the users. Using vertical federated learning, each entity in the core network transfers its local encrypted model trained by locally collected data features rather than sending the raw data to the NWDAF entity. This can significantly alleviate the massive cybersecurity vulnerability within the network topology introduced by network function virtualization (NFV).” P5 §III.C); and
aggregate the model parameters using federated learning, transmit a response to the first request, and the response comprises the aggregated model parameters (“NWDAF can act as the global node that handles the aggregation of the user data. The datasets of the users are vertically fragmented over different entities in the core network, where each entity keeps record of a specific data feature related to all the users. Using vertical federated learning, each entity in the core network transfers its local encrypted model trained by locally collected data features rather than sending the raw data to the NWDAF entity. This can significantly alleviate the massive cybersecurity vulnerability within the network topology introduced by network function virtualization (NFV).” P5 §III.C).
Regarding claims 2 and 17, Niknam discloses: The UE of claim 1, wherein the at least one local model training logical function comprises at least one network function or at least one application function (p4-5 §III.C discloses network and application functions).
Regarding claims 3 and 18, Niknam discloses: The UE of claim 2, wherein the network function comprises an analytics logical function, a model training logical function, or a combination thereof (p4-5 §III.C NWDAF aggregates training data so it is interpreted as a acting as a training logical function).
Regarding claims 4 and 19, Niknam discloses: The UE of claim 3, wherein the first requirements to derive the aggregated training model using federated learning comprises an analytics identifier identifying a model, identifiers corresponding to the data that cannot be collected, a specific area of interest, a public land mobile network identifier, a data network access identifier, a single network slice selection assistant information identifier, an application identifier, a data network name identifier, or a combination thereof (“For instance, the first dataset could contain the registration and authentication information while the second could contain information related to the network slice selection for each user.” P5 §III.C ¶2).
Regarding claims 5 and 20, Niknam discloses: The UE of claim 4, wherein the at least one processor is configured to cause the UE to discover at least one local model training logical function to retrieve model parameters for federated learning from a network repository function (“After training a local model, each individual learner transfers its local model parameters, instead of raw training dataset, to an aggregating unit. The aggregator utilizes the local model parameters to update2 a global model which is eventually fed back to the individual local learners for their use. As a result, each local learner benefits from the datasets of the other learners only through the global model, shared by the aggregator, without explicitly accessing their privacy-sensitive data.” P2 §II ¶1, Fig 2, note: each local user device must have access to local data and local model in storage which would be accessed through a network repository function).
Regarding claim 6, Niknam discloses: The UE of claim 5, wherein the at least one processor is configured to cause the UE to transmit a third request to the network repository function to discover the local model training logical function to retrieve model parameters for federated learning, and the third request comprises a specific area, a public land mobile network, a data network access identifier, a single network slice selection assistant information, an application identifier, a data network name, or a combination thereof (“For instance, the first dataset could contain the registration and authentication information while the second could contain information related to the network slice selection for each user.” P5 §III.C ¶2, note: multiple training/retraining cycles would require multiple requests).
Regarding claim 7, Niknam discloses: The UE of claim 6, wherein the model training logical function provisions local models to the local model training logical functions to initiate local training (“After training a local model, each individual learner transfers its local model parameters, instead of raw training dataset, to an aggregating unit. The aggregator utilizes the local model parameters to update2 a global model which is eventually fed back to the individual local learners for their use. As a result, each local learner benefits from the datasets of the other learners only through the global model, shared by the aggregator, without explicitly accessing their privacy-sensitive data.” P2 §II ¶1, Fig 1).
Regarding claim 8, Niknam discloses: The UE of claim 7, wherein the local model training logical function trains the local model with data collected from local data producer network function and provides model parameters related to the trained local model to the model training logical function (“After training a local model, each individual learner transfers its local model parameters, instead of raw training dataset, to an aggregating unit. The aggregator utilizes the local model parameters to update2 a global model which is eventually fed back to the individual local learners for their use. As a result, each local learner benefits from the datasets of the other learners only through the global model, shared by the aggregator, without explicitly accessing their privacy-sensitive data.” P2 §II ¶1, Fig 1).
Regarding claims 9 and 13, Niknam discloses: A first network function (“In general, NWDAF is capable of connecting to any network function (NF) and utilizing any data in the core network (see Fig. 4). In addition, any NF can request network analytic information.” P4 §III.C ¶1), comprising:
at least one memory (Fig 2); and
at least one processor coupled with the at least one memory and configured to cause the first network function to (Fig 2):
receive a first request from a second network function, wherein the first request comprises first requirements to provide a trained model, the first requirements comprise an analytics identifier identifying a model and requirements to provide the trained model for a specific area of interest, a public land mobile network identifier, a data network access identifier, a single network slice selection assistant information identifier, an application identifier, a data network name identifier, or a combination thereof (“In general, NWDAF is capable of connecting to any network function (NF) and utilizing any data in the core network (see Fig. 4). In addition, any NF can request network analytic information.” P4 §III.C ¶1, “For instance, the first dataset could contain the registration and authentication information while the second could contain information related to the network slice selection for each user.” P5 §III.C ¶2, see also p2 §II ¶1 for federated learning structure of requesting a trained model, training locally, updating the global model with local parameters, and repeating as necessary to train a global model, Fig 2 each UE and aggregator would have associated network functions);
determine that the first request uses federated learning to train the model corresponding to the first requirements (“NWDAF can act as the global node that handles the aggregation of the user data. The datasets of the users are vertically fragmented over different entities in the core network, where each entity keeps record of a specific data feature related to all the users. Using vertical federated learning, each entity in the core network transfers its local encrypted model trained by locally collected data features rather than sending the raw data to the NWDAF entity. This can significantly alleviate the massive cybersecurity vulnerability within the network topology introduced by network function virtualization (NFV).” P5 §III.C);
determine a network function that supports model aggregation using federated learning (“NWDAF can act as the global node that handles the aggregation of the user data. The datasets of the users are vertically fragmented over different entities in the core network, where each entity keeps record of a specific data feature related to all the users. Using vertical federated learning, each entity in the core network transfers its local encrypted model trained by locally collected data features rather than sending the raw data to the NWDAF entity. This can significantly alleviate the massive cybersecurity vulnerability within the network topology introduced by network function virtualization (NFV).” P5 §III.C);
transmit a second request to a third network function supporting model training using federated learning, wherein the second request comprises a request to provide a trained model using federated learning based on the first requirements (“NWDAF can act as the global node that handles the aggregation of the user data. The datasets of the users are vertically fragmented over different entities in the core network, where each entity keeps record of a specific data feature related to all the users. Using vertical federated learning, each entity in the core network transfers its local encrypted model trained by locally collected data features rather than sending the raw data to the NWDAF entity. This can significantly alleviate the massive cybersecurity vulnerability within the network topology introduced by network function virtualization (NFV).” P5 §III.C); and
in response to transmitting the second request, receive aggregated model parameters, train the model using the aggregated model parameters to result in a trained model, transmit a first response to the first request, and the response comprises information indicating that the trained model is available (“NWDAF can act as the global node that handles the aggregation of the user data. The datasets of the users are vertically fragmented over different entities in the core network, where each entity keeps record of a specific data feature related to all the users. Using vertical federated learning, each entity in the core network transfers its local encrypted model trained by locally collected data features rather than sending the raw data to the NWDAF entity. This can significantly alleviate the massive cybersecurity vulnerability within the network topology introduced by network function virtualization (NFV).” P5 §III.C).
Regarding claims 12 and 15, Niknam discloses: The first network function of claim 9, wherein the at least one processor is configured to cause the first network function to determine that the first request uses federated learning to train the model is based on the first requirements (“In general, NWDAF is capable of connecting to any network function (NF) and utilizing any data in the core network (see Fig. 4). In addition, any NF can request network analytic information.” P4 §III.C ¶1, “NWDAF can act as the global node that handles the aggregation of the user data. The datasets of the users are vertically fragmented over different entities in the core network, where each entity keeps record of a specific data feature related to all the users. Using vertical federated learning, each entity in the core network transfers its local encrypted model trained by locally collected data features rather than sending the raw data to the NWDAF entity. This can significantly alleviate the massive cybersecurity vulnerability within the network topology introduced by network function virtualization (NFV).” P5 §III.C).
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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.
Claim(s) 10-11 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Niknam in view of Kumar et al. (US 11424962 B2).
Regarding claim 10, Niknam does not explicitly disclose, however Kumar teaches: The first network function of claim 9, wherein the at least one processor is configured to cause the first network function to determine that the first request uses federated learning to train the model corresponding to the first requirements by receiving a second response from a data producer network function, the second response is received in response to a request for data collection, and the second response indicates that data is unavailable (“The discovery procedure may be based on sub-procedures for a ML training/inference host (e.g., UE 402, base station 404, or OAM core network 406) that transmits data and model requests to the MDAC 408 for coordination. The MDAC 408 may query the data lake/pond 412 and the ML/NN server 414 for a uniform resource identifier (URI) of the data and model. The MDAC 408 may signal the ML/NN database 410 for an update to the ML/NN model. The MDAC 408 may further request the data lake/pond 412 to initiate data collection, if the data for the procedure is not current or is unavailable, for signaling corresponding information to the base station 404 or the UE 402. In aspects, the MDAC 408 may request the ML/NN server 414 to generate a ML/NN model for a different ML/NN procedure, if a model is not available for such procedure.” C14L1-15).
Niknam and Kumar are in the same field of endeavor of distributed ML and are analogous. Niknam discloses federated learning in a wireless system. Kumar teaches determining if data is available and retrieving data for training if necessary. It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the federated learning of Niknam with the data determination and acquisition as taught by Kumar to yield predictable results of keeping the local models up to date.
Regarding claim 11 and 14, Niknam does not explicitly disclose, however Kumar teaches: The first network function of claim 9, wherein the at least one processor is configured to cause the first network function to determine that the first request uses federated learning to train the model corresponding to the first requirements by determining that data is to be collected from at least one data producer network function to train the model is not available (“The discovery procedure may be based on sub-procedures for a ML training/inference host (e.g., UE 402, base station 404, or OAM core network 406) that transmits data and model requests to the MDAC 408 for coordination. The MDAC 408 may query the data lake/pond 412 and the ML/NN server 414 for a uniform resource identifier (URI) of the data and model. The MDAC 408 may signal the ML/NN database 410 for an update to the ML/NN model. The MDAC 408 may further request the data lake/pond 412 to initiate data collection, if the data for the procedure is not current or is unavailable, for signaling corresponding information to the base station 404 or the UE 402. In aspects, the MDAC 408 may request the ML/NN server 414 to generate a ML/NN model for a different ML/NN procedure, if a model is not available for such procedure.” C14L1-15).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Yang et el. (Scheduling Policies for Federated Learning in Wireless Networks) discloses scheduling for federated learning in wireless networks.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIC NILSSON whose telephone number is (571)272-5246. The examiner can normally be reached M-F: 7-3.
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, James Trujillo can be reached at (571)-272-3677. 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.
/ERIC NILSSON/ Primary Examiner, Art Unit 2151
Prosecution Insights