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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 08/12/2024 and 01/28/2025 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 § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 7 and 8 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 7 recites the limitation "the media" in line 2. There is insufficient antecedent basis for this limitation in the claim.
Claim 8 recites the limitations “the first portion” in line 2 and “the second portion” in line 3. There is insufficient antecedent basis for these limitations in the claim.
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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-5, 7 and 10-12 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Yue et al. (US 2025/0317365).
Regarding Claim 1, Yue teaches a method performed by a network, the method comprising:
identifying an artificial intelligence (AI) model corresponding to a service ([0037] at least a part of the ML model is run at UE 102 and the rest of the ML model is run at cloud system);
negotiating a split inference configuration with a user equipment (UE) ([0048] Process 400 may begin with step s402. Step s402 comprises UE 102 transmitting towards AF 108 a request for splitting ML inference process 300. The request may be transmitted over the application layer. The request for splitting the ML inference process may include information about UE 102 and/or information about ML inference process; [0051] The information about UE 102 and/or the information about ML inference process 300 may be used for determining how to split ML inference process 300. In one very simplified example, ML inference process 300 may be split depending on resource(s) available at UE 102 and resource requirements for performing ML inference process 300; [0052] ML inference process 300 may be split depending on whether the currently available network bandwidth for UE 102 can handle the transmission of certain intermediate ML processed data. More specifically, in case the size of intermediate ML processed data 312 is substantially greater than the size of intermediate ML processed data 314, and in case the currently available network bandwidth for UE 102 can only handle the size of intermediate ML processed data 314, ML inference process 300 may be split such that the parts of ML inference process 300 corresponding to ML layers 370 and 372 are performed at UE 102 while the part of ML inference process 300 corresponding to ML layer 374 is performed at NE 106; [0054] UE 102 may use this information (i.e., the information about the network to which UE 102 is connected) for selecting one of the multiple ways to use for splitting ML inference process 300; [0055] Referring back to FIG. 4, after AF 108 receives the request for splitting ML inference process 300, AF 108 may optionally transmit to UE 102 an acknowledgement message acknowledging the receipt of the request; FIG. 4, s402);
performing a split inference with the UE, based on the AI model and the split inference configuration ([0081] After receiving the analytics data, in step s422, AF 108 may generate ML assistance information based on the received analytics data and may make a decision regarding how to split ML inference process 300 based on the ML assistance information and/or the information about UE 102 obtained in step s402; [0085] After making the decision as to how to split ML inference process 300, in step s424, AF 106 transmits towards UE 102 split decision information indicating how to split the ML operation and/or which ML sub-operations included in the ML operation UE 102 should perform); and
providing the service based on a result of the split inference ([0088] Upon receiving the split decision information, in step s426, UE 102 performs a part of ML inference process 300, thereby generating intermediate ML processed output data (e.g., 312 or 314). After performing the part of ML inference process 300, UE 102 may transmit towards NE 106 the generated intermediate ML processed output data (e.g., 312 or 314). After receiving the intermediate ML processed output data, NE 106 may perform the remaining part of ML inference process 300, thereby generating the final ML processed output data; [0089] the whole ML model for performing ML inference process 300 may be stored in NE 106 prior to step s426. In such embodiments, in step s426, UE 102 only need to transmit to NE 106 an indication indicating which part of ML inference process 300 NE 106 needs to perform. However, in other embodiments, the ML model may not be stored in NE 106. In such embodiments, in step s426, UE 102 may transmit to NE 106 not only the indication indicating which part of ML inference process 300 NE 106 needs to perform but also the part of the ML model for performing the indicated part of ML inference process 300).
Regarding Claim 2, Yue teaches negotiating the split inference configuration includes exchanging control messages with the UE ([0048] Process 400 may begin with step s402. Step s402 comprises UE 102 transmitting towards AF 108 a request for splitting ML inference process 300. The request may be transmitted over the application layer. The request for splitting the ML inference process may include information about UE 102 and/or information about ML inference process; [0055] Referring back to FIG. 4, after AF 108 receives the request for splitting ML inference process 300, AF 108 may optionally transmit to UE 102 an acknowledgement message acknowledging the receipt of the request).
Regarding Claim 3, Yue teaches negotiating the split inference configuration is based on at least one of AI model specific information, a capability of the UE, or a resource availability ([0051] The information about UE 102 and/or the information about ML inference process 300 may be used for determining how to split ML inference process 300. In one very simplified example, ML inference process 300 may be split depending on resource(s) available at UE 102 and resource requirements for performing ML inference process 300; [0052] ML inference process 300 may be split depending on whether the currently available network bandwidth for UE 102 can handle the transmission of certain intermediate ML processed data. More specifically, in case the size of intermediate ML processed data 312 is substantially greater than the size of intermediate ML processed data 314, and in case the currently available network bandwidth for UE 102 can only handle the size of intermediate ML processed data 314, ML inference process 300 may be split such that the parts of ML inference process 300 corresponding to ML layers 370 and 372 are performed at UE 102 while the part of ML inference process 300 corresponding to ML layer 374 is performed at NE 106).
Regarding Claim 4, Yue teaches the AI model specific information includes at least one of a size of the AI model, a number of layers of the AI model, a number of nodes and links of each of the layers, complexity of each of the layers of the AI model, possible split points for the split inference, or a target inference delay ([0061] The requested NE information may include any one or more of: an amount of computational resources available at NE 106 or end-to-end network performance (e.g., latency, throughput, packet loss rate, etc.) between one or more pairs of NEs in two adjacent layers; [0062] NWDAF 114 may select one or more NEs that satisfy any one or more of: (1) the amount of available resource of a NE is higher than threshold amount(s) or (2) (if more than two layers), the end-to-end latency between a pair of NEs in two adjacent layers is lower than threshold value(s); [0063] The threshold(s) for computation resource and latency may be decided by AF 108 or based on a negotiation between UE 102 and AF 108; [0083] The decision made by AF 108 may indicate any one or more of: (1) a number of ML layers for performing a part of the ML inference process at UE 102; [0106] determining how to split the ML inference process comprises determining any one or more of: a number of ML layers for performing a part of the ML inference process at the UE).
Regarding Claim 5, Yue teaches the split inference configuration includes a split point for the split inference and an order of the split inference ([0040] FIG. 3B shows an exemplary way of splitting ML inference process 300. In FIG. 3B, ML inference process 300 is split into three parts-UE portion of ML inference process 300, first NE portion of ML inference process 300, and second NE portion of ML inference process 300; [0086] as shown in FIG. 3, in case the ML operation is performed by three ML sub-operations performed by three layers 370, 372, and 374, the split decision information may indicate that UE 102 should perform the ML sub-operations of the first two layers 370 and 372. The transmission of the split decision from AF 106 to UE 102 may occur over application layer).
Regarding Claim 7, Yue teaches the media for inference is obtained from the UE ([0035] More specifically, once image 150 is captured, UE 102 may convert the captured image 150 (shown in FIG. 1B) into a portrait image 160 (shown in FIG. 1C) of human object 154 using a trained machine learning (ML) model; [0041] The UE portion of ML inference process 300 that is performed by UE 102 includes receiving ML input data 302 (e.g., the captured image 150) and generating first intermediate ML processed data 312 using a first portion 370 of the ML model 350 based on the received ML input data 302).
Regarding Claim 10, Yue teaches a method performed by a user equipment (UE), the method comprising:
negotiating a split inference configuration with a network ([0048] Process 400 may begin with step s402. Step s402 comprises UE 102 transmitting towards AF 108 a request for splitting ML inference process 300. The request may be transmitted over the application layer. The request for splitting the ML inference process may include information about UE 102 and/or information about ML inference process; [0051] The information about UE 102 and/or the information about ML inference process 300 may be used for determining how to split ML inference process 300. In one very simplified example, ML inference process 300 may be split depending on resource(s) available at UE 102 and resource requirements for performing ML inference process 300; [0052] ML inference process 300 may be split depending on whether the currently available network bandwidth for UE 102 can handle the transmission of certain intermediate ML processed data. More specifically, in case the size of intermediate ML processed data 312 is substantially greater than the size of intermediate ML processed data 314, and in case the currently available network bandwidth for UE 102 can only handle the size of intermediate ML processed data 314, ML inference process 300 may be split such that the parts of ML inference process 300 corresponding to ML layers 370 and 372 are performed at UE 102 while the part of ML inference process 300 corresponding to ML layer 374 is performed at NE 106; [0054] UE 102 may use this information (i.e., the information about the network to which UE 102 is connected) for selecting one of the multiple ways to use for splitting ML inference process 300; [0055] Referring back to FIG. 4, after AF 108 receives the request for splitting ML inference process 300, AF 108 may optionally transmit to UE 102 an acknowledgement message acknowledging the receipt of the request; FIG. 4, s402);
performing a split inference with the network, based on an artificial intelligence (AI) model corresponding to a service and the split inference configuration ([0081] After receiving the analytics data, in step s422, AF 108 may generate ML assistance information based on the received analytics data and may make a decision regarding how to split ML inference process 300 based on the ML assistance information and/or the information about UE 102 obtained in step s402; [0085] After making the decision as to how to split ML inference process 300, in step s424, AF 106 transmits towards UE 102 split decision information indicating how to split the ML operation and/or which ML sub-operations included in the ML operation UE 102 should perform); and
providing the service based on a result of the split inference ([0088] Upon receiving the split decision information, in step s426, UE 102 performs a part of ML inference process 300, thereby generating intermediate ML processed output data (e.g., 312 or 314). After performing the part of ML inference process 300, UE 102 may transmit towards NE 106 the generated intermediate ML processed output data (e.g., 312 or 314). After receiving the intermediate ML processed output data, NE 106 may perform the remaining part of ML inference process 300, thereby generating the final ML processed output data; [0089] the whole ML model for performing ML inference process 300 may be stored in NE 106 prior to step s426. In such embodiments, in step s426, UE 102 only need to transmit to NE 106 an indication indicating which part of ML inference process 300 NE 106 needs to perform. However, in other embodiments, the ML model may not be stored in NE 106. In such embodiments, in step s426, UE 102 may transmit to NE 106 not only the indication indicating which part of ML inference process 300 NE 106 needs to perform but also the part of the ML model for performing the indicated part of ML inference process 300).
Regarding Claim 11, the claim is interpreted and rejected for the same reason as set forth in Claim 3.
Regarding Claim 12, the claim is interpreted and rejected for the same reason as set forth in Claim 5.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 6, 9, 13 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Yue et al. in view of Onno et al. (US 2026/0111794).
Regarding Claim 6, Yue teaches performing the split inference with the UE comprises: transmitting, to the UE, a first portion of the AI model to be inferenced on the UE ([0040] FIG. 3B shows an exemplary way of splitting ML inference process 300. In FIG. 3B, ML inference process 300 is split into three parts-UE portion of ML inference process 300, first NE portion of ML inference process 300, and second NE portion of ML inference process 300).
However, Yue does not teach obtaining a media for inference; generating intermediate data by performing an inference on the media based on a second portion of the AI model; and transmitting, to the UE, the intermediate data.
In an analogous art, Onno teaches obtaining a media for inference; generating intermediate data by performing an inference on the media based on a second portion of the AI model; and transmitting, to the UE, the intermediate data ([0141] for example illustrated in FIG. 3, use-case e), where the UE receives intermediate data from the network (edge/cloud), inference units on the network side send the self-contained segment including the intermediate data. To that end, they may send the segment to the delivery function in the network for encapsulation and transmission of an updated self-contained content package to the UE).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Onno’s method with Yue’s method so that a UE can provide (input) content segmentation adapted for model inference, content aware decision to select and distribute the model execution, and scalable and self-contained segment delivery adapted for content data or intermediate data (Onno [0091]).
Regarding Claim 9, Yue teaches performing the split inference with the UE comprises: transmitting, to the UE, a first portion of the AI model to be inferenced on the UE; receiving, from the UE, intermediate data, the intermediate data being a result of an inference of media based on the first portion of the AI model; performing an inference on the intermediate data based on a second portion of the AI model ([0041] The UE portion of ML inference process 300 that is performed by UE 102 includes receiving ML input data 302 (e.g., the captured image 150) and generating first intermediate ML processed data 312 using a first portion 370 of the ML model 350 based on the received ML input data 302; [0042] The first NE portion of ML inference process 300 that is performed by first NE 106a includes receiving the first intermediate ML processed data 312 and generating second intermediate ML processed data 314 using a second portion 372 of the ML model 350 based on the received first intermediate ML processed data 312; [0043] The second NE portion of ML inference process 300 that is performed by second NE 106b includes receiving the second intermediate ML processed data 314 and generating ML output data 304 using a second portion 374 of the ML model 350 based on the received second intermediate ML processed data 314).
However, Yue does not teach transmitting, to the UE, a result of the inference of the intermediate data.
In an analogous art, Onno teaches transmitting, to the UE, a result of the inference of the intermediate data ([0077] M1 can process (i.e. infer) the AI data to obtain a result or forward different AI data to M2, which in turn processes the different intermediate data to obtain a result. The result is returned to the UE, possibly via the subset with an immediately lower number (e.g. M1 may provide the result via M0). The result can be provided to the application or be used directly by the UE).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Onno’s method with Yue’s method so that a UE can provide (input) content segmentation adapted for model inference, content aware decision to select and distribute the model execution, and scalable and self-contained segment delivery adapted for content data or intermediate data (Onno [0091]).
Regarding Claim 13, Yue teaches performing the split inference with the network comprises: receiving, from the network, a first portion of the AI model to be inferenced on the UE ([0040] FIG. 3B shows an exemplary way of splitting ML inference process 300. In FIG. 3B, ML inference process 300 is split into three parts-UE portion of ML inference process 300, first NE portion of ML inference process 300, and second NE portion of ML inference process 300).
However, Yue does not teach receiving, from the network, intermediate data, the intermediate data being a result of an inference of target media based on a second portion of the AI model; and performing an inference on the intermediate data based on the first portion of the AI model.
In an analogous art, Onno teaches receiving, from the network, intermediate data, the intermediate data being a result of an inference of target media based on a second portion of the AI model; and performing an inference on the intermediate data based on the first portion of the AI model ([0141] for example illustrated in FIG. 3, use-case e), where the UE receives intermediate data from the network (edge/cloud), inference units on the network side send the self-contained segment including the intermediate data. To that end, they may send the segment to the delivery function in the network for encapsulation and transmission of an updated self-contained content package to the UE).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Onno’s method with Yue’s method so that a UE can provide (input) content segmentation adapted for model inference, content aware decision to select and distribute the model execution, and scalable and self-contained segment delivery adapted for content data or intermediate data (Onno [0091]).
Regarding Claim 15, Yue teaches performing the split inference with the network comprises: receiving, from the network, a first portion of the AI model to be inferenced on the UE; obtaining media for an inference; generating intermediate data by performing the inference on the media based on the first portion of the AI model; transmitting, to the network, the intermediate data ([0041] The UE portion of ML inference process 300 that is performed by UE 102 includes receiving ML input data 302 (e.g., the captured image 150) and generating first intermediate ML processed data 312 using a first portion 370 of the ML model 350 based on the received ML input data 302; [0042] The first NE portion of ML inference process 300 that is performed by first NE 106a includes receiving the first intermediate ML processed data 312 and generating second intermediate ML processed data 314 using a second portion 372 of the ML model 350 based on the received first intermediate ML processed data 312; [0043] The second NE portion of ML inference process 300 that is performed by second NE 106b includes receiving the second intermediate ML processed data 314 and generating ML output data 304 using a second portion 374 of the ML model 350 based on the received second intermediate ML processed data 314).
However, Yue does not teach receiving, from the network, a result of the inference of the intermediate data based on a second portion of the AI model.
In an analogous art, Onno teaches receiving, from the network, a result of the inference of the intermediate data based on a second portion of the AI model ([0077] M1 can process (i.e. infer) the AI data to obtain a result or forward different AI data to M2, which in turn processes the different intermediate data to obtain a result. The result is returned to the UE, possibly via the subset with an immediately lower number (e.g. M1 may provide the result via M0). The result can be provided to the application or be used directly by the UE).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Onno’s method with Yue’s method so that a UE can provide (input) content segmentation adapted for model inference, content aware decision to select and distribute the model execution, and scalable and self-contained segment delivery adapted for content data or intermediate data (Onno [0091]).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Yue et al. in view of Ly et al. (US 2025/0310214).
Regarding Claim 8, Yue does not teach the first portion of the AI model corresponds to a task specific portion, and wherein the second portion of the AI model corresponds to a common portion over multiple tasks.
In an analogous art, Ly teaches the first portion of the AI model corresponds to a task specific portion, and wherein the second portion of the AI model corresponds to a common portion over multiple tasks ([0057] In addition to AI/ML inference, model splitting can also be applied to AI/ML training using Federated Learning. In Federated Learning, a cloud server trains a global model by aggregating local models partially trained by end devices in an iterative fashion. Each training iteration consists of device selection, model distribution and training configuration, and the reporting of training results. The cloud server aggregates the training results and updates the global model, which may trigger an update of local models to perform the next training iteration; [0059] The FL models may include a global model and local models. Global model running on an edge server provides the overall analysis. Multiple distributed FL local models are available on the edge servers for download to UEs and other mobile devices; [0070] UEs may download split AI/ML models from a repository of an application server, collect data for application to model training, or upload the intermediate training results to a global model in the AS for aggregation).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Ly’s method with Yue’s method so that it may assist in AI/ML communications in 5GS, AI/ML traffic differentiation, AI/ML slice type, AI/ML triggering rules, AI/ML policy, AI/ML operations, or UE communication interface exposure (Ly [0014]).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Yue et al. in view of Onno et al. and Ly et al. (US 2025/0310214).
Regarding Claim 14, the combination of Yue and Onno does not teach the first portion of the AI model corresponds to a task specific portion, and wherein the second portion of the AI model corresponds to a common portion over multiple tasks.
In an analogous art, Ly teaches the first portion of the AI model corresponds to a task specific portion, and wherein the second portion of the AI model corresponds to a common portion over multiple tasks ([0057] In addition to AI/ML inference, model splitting can also be applied to AI/ML training using Federated Learning. In Federated Learning, a cloud server trains a global model by aggregating local models partially trained by end devices in an iterative fashion. Each training iteration consists of device selection, model distribution and training configuration, and the reporting of training results. The cloud server aggregates the training results and updates the global model, which may trigger an update of local models to perform the next training iteration; [0059] The FL models may include a global model and local models. Global model running on an edge server provides the overall analysis. Multiple distributed FL local models are available on the edge servers for download to UEs and other mobile devices; [0070] UEs may download split AI/ML models from a repository of an application server, collect data for application to model training, or upload the intermediate training results to a global model in the AS for aggregation).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Ly’s method with Yue’s method so that it may assist in AI/ML communications in 5GS, AI/ML traffic differentiation, AI/ML slice type, AI/ML triggering rules, AI/ML policy, AI/ML operations, or UE communication interface exposure (Ly [0014]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Qiao et al. (US 2025/0168688) teaches method of model processing based on UE capability.
Luo et al. (US 2025/0142398) teaches 5GS assisted adaptive AI or ML operation.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to YU-WEN CHANG whose telephone number is (408)918-7645. The examiner can normally be reached M-F 8:00am-5:00pm PT.
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, Un Cho can be reached at 571-272-7919. 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.
/YU-WEN CHANG/Primary Examiner, Art Unit 2413
Prosecution Insights