DETAILED ACTION
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This action is responsive to the amendment filed 07/13/2026.
Claims 1-20 are currently pending. Claims 1, 14, and 20 have been amended. Claims 1, 14, and 20 are independent Claims.
Information Disclosure Statement
2. The Applicant’s Information Disclosure Statement filed 06/24/2026 has been received, entered into the record, and considered.
Claim Rejections - 35 USC § 102
3. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 1-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Chang et al. (US 20220066760).
It is noted that any citations to specific, pages, columns, paragraphs, lines, or figures in the prior art references and any interpretation of the reference should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. See MPEP 2123.
As to Claim 1:
Chang teaches a method for optimizing neural networks for on-device deployment in an electronic device (Abstract and [0009-0011]), the method comprising:
receiving a plurality of neural network (NN) models ([0070] and [0122-0123]);
fusing at least two NN models from among the plurality of NN models based on at least one layer of each of the at least two NN models, to generate a fused NN model (Abstract, [0009], [0029], [0038], [0043], [0134], and [0147]) wherein each of the at least two NN models is an individual NN model comprising a plurality of layers ([0005], [0174-0175], and [0178]);
identifying at least one redundant layer from the fused NN model; and removing the at least one redundant layer to generate an optimized NN model ([0156-0158]).
As to Claim 2:
Chang teaches the fusing the at least two NN models comprises: determining that the at least one layer of each of the at least two NN models is directly connectable ([0029] and [0043]); and connecting the at least one layer of each of the at least two NN models in a predefined order of execution ([0134-0136]).
As to Claim 3:
Chang teaches the fusing the at least two of the plurality of NN models comprises: determining that the at least one layer of each of the at least two of the plurality of NN models is not directly connectable; converting the at least one layer into a converted at least one layer that is a connectable format; and connecting the converted at least one layer of each of the at least two NN models according to a predefined order of execution ([0029], [0038], [0043], and [0133]).
As to claim 4:
Chang teaches the converting the at least one layer into the converted at least one layer that is a connectable format comprises: adding at least one additional layer in between the at least one layer of each of the at least two NN models, the at least one additional layer comprising at least one of a pre-defined NN operation layer and a user-defined operation layer ([0009] and [0134]).
As to Claim 5:
Chang teaches the determining that the at least one layer of each of the at least two NN models is directly connectable comprises: determining that an output generated from a preceding NN layer is compatible with an input of a succeeding NN layer ([0152] and [0155]).
As to Claim 6:
Chang teaches the converting at least one layer into the converted at least one layer that is a connectable format comprises: transforming an output generated from a preceding NN layer to an input compatible with a succeeding NN layer ([0070] and [0133]).
As to Claim 7:
Chang teaches the identifying the at least one redundant layer from the fused NN model comprises: identifying at least one layer in each of the at least two NN models being executed in a manner that an output of the at least one layer in each of the at least two NN models is redundant with respect to each other ([0156-0158]).
As to Claim 8:
Chang teaches each of the at least two NN models are developed in different frameworks ([0069-0070]).
As to Claim 9:
Chang teaches the at least one layer of each of the at least two NN models comprises at least one of a pre-defined NN operation layer and a user-defined operation layer ([0134-0136]).
As to Claim 10:
Chang teaches validating the fused NN model based on whether a network datatype and layout of the fused NN model is supported by an inference library, and whether a computational value of the fused NN model is above a predefined threshold value ([0134] and [0147]).As to Claim 11:
Chang teaches compressing the optimized NN model to generate a compressed NN model; encrypting the compressed NN model to generate an encrypted NN model; and storing the encrypted NN model in a memory ([0126] and [0133]).
As to claim 12:
Chang teaches the plurality of NN models are configured to execute sequentially ([0038], [0043], and [0134-0135]).
As to Claim 13:
Chang teaches implementing the optimized NN model at runtime of an application in the electronic device ([0178]).As to Claims 14-19:
Refer to the discussion of Claims 1-4, 6, and 10 above, respectively, for rejections. Claims 14-19 are the same as Claims 1-4, 6, and 10, except Claims 14-19 are system Claims and Claims 1-4, 6, and 10 are method Claims.
As to Claim 20:
Refer to the discussion of claim1 above for rejection. Claim 20 is the same as Claim 1, except Claim 20 is a non-transitory computer readable medium Claim and Claim 1 is a method Claim.
Response to Arguments
4. Applicants' arguments filed 07/13/2026 have been fully considered but they are not persuasive.
Claim Rejection under 35 USC § 101:
The 101 rejection has been withdrawn in view of Applicant's arguments.
Claim Rejection under 35 USC § 102:
Applicant argues that Chang does not teach “fusing at least two NN models from among the plurality of NN models based on at least one layer of each of the at least two NN models, to generate a fused NN model, wherein each of the at least two NN models is an individual NN model comprising a plurality of layers”.
In response, under broadest reasonable interpretation, Chang’s teachings “using the one or more processors, fusing available functions and layers in the list of neural network layer model objects” [0029] and “… In step 515, operations or functions of the network layers are fused with the layer (or model) objects and, additionally, various network layers may also be fused into layer (or model) objects. For example, the vector add operation present in ResNet models is fused with a convolution layer. Non-linear operations, such as MFM and ReLU, are also merged with convolution layers. An example is shown in FIG. 13, parts (A) and (B), in which ReLUs 603A, 603B, and 603C are merged or fused into convolution layers to form convolution layer (or model) objects (CONV 605, 607), and separate convolution layers 609 (with a ReLU 603B) are merged or fused into a single convolution layer (or model) object (CONV 607)” [0134] read-on the claimed “fusing at least two NN models from among the plurality of NN models based on at least one layer of each of the at least two NN models, to generate a fused NN model”. Also, under broadest reasonable interpretation, Chang’s teachings “a model is composed of several layers” [0005]; “…The fixed point location can be different for each layer in the model or different sections of the model to reduce degradation of accuracy due to floating to fixed point quantization)” [0174]; and “The compiler system 400 uses one or more inputs of the model to choose the fixed point for input and output of each layer. Each layer output's fixed point location should match the following layer input's fixed point location. For each input, the compiler system 400 executes the model in floating point using the CPU, and keeps track of the best fixed point location for each layer. After reaching a stable point, the compiler system 400 saves the fixed point configuration of each layer to be used in the future executions of that model”[0175] meet the claimed “each of the at least two NN models is an individual NN model comprising a plurality of layers”.
During patent examination, the pending claims must be “given their broadest reasonable interpretation consistent with the specification.” In re Hyatt 21 1 F.3d 1367, 1372, 54 USPQ2d 1664, 1667 (Fed. Cir. 2000).
Conclusion
5. THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Contact information
6. Any inquiry concerning this communication or earlier communications from the
examiner should be directed to MAIKHANH NGUYEN whose telephone number is (571) 272-4093. The examiner can normally be reached on Monday-Friday (8:00 am – 5:30 pm). If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, TAMARA KYLE can be reached at (571)272-4241.
The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center or Private PAIR to authorized users only. Should you have questions about access to Patent Center or the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/MAIKHANH NGUYEN/Primary Examiner, Art Unit 2144
Prosecution Insights