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 submitted on 01/22/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Amendment
The Amendment filed on 02/10/2026 has been entered. Claims 1-6 remain pending in the application.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 1-6 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention. Claim 1 recites “wherein the second processing circuitry further share results from a previously provided feature extraction layer in the edge device with the server device; and output a feature map from the shared results”, claim 5 recites “wherein by the server device, share results from a previously provided feature extraction layer in the edge device with the server device; and output a feature map from the shared results” and claim 6 recites “share results from a previously provided feature extraction layer in the edge device with the server device; and outputting a feature map from the shared results”. Per the instant specification,
[0021] In the processing system according to the present embodiment, the feature extraction layer Bf2 in the original DNN2′ is arranged as the feature extraction layer Bf2 of the DNN1 on the edge side. Therefore, the detection layer Bd2 of the DNN2 on the cloud side can execute inference processing using the feature map output from the feature extraction layer Bf2 of the DNN1 on the edge side (see an arrow Y2 in FIG. 2-2).
[0060] [Effects of Embodiment] As described above, in the embodiment, by arranging the feature extraction layer Bf2 in the DNN2′ before being arranged in the server device 20 as the feature extraction layer Bf2 of the DNN1 of the edge device 30, the feature map output from the edge device 30 can also be shared with the server device 20.
The specification appears to disclose the edge device outputs and shares the feature map output to the server. The specification does not disclose the server shares results from a previously provided feature extraction layer in the edge device with the server device and outputs a feature map from the shared results. For the purpose of examination, examiner will interpret the limitation of “wherein the second processing circuitry further share results from a previously provided feature extraction layer in the edge device with the server device; and output a feature map from the shared results” as “wherein the first processing circuitry outputs a feature map from the feature amount of processing target data and shares the feature map with server device”.
Therefore, claims 1, 5 and 6 are rejected for containing subject matter which was not described in the specification. Claims 2-4 are rejected for failing to cure the deficiency from their respective parent claims.
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.
Claim 3 is 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 pre-AIA the applicant regards as the invention.
Claim 3 recites the limitation " the quantized feature amount". There is insufficient antecedent basis for this limitation in the claim.
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 2 is rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. All of the limitations of Claim 2 are already recited in parent Claim 1 from which Claim 2 depends. Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-6 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Claims 1-4 are directed to a system, claim 5 is directed to a method and claim 6 is directed to a medium. Therefore, the claims are eligible under Step 1 for being directed to a machine, a process and a manufacture respectively.
Independent claims 1, 5 and 6:
Step 2A Prong 1:
Claims recite:
output an inference result in a case where reliability of the inference result exceeds a threshold, and output the feature amount of the processing target data to the server device in a case where the reliability is equal to or less than the threshold - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and generating an inference result based on judgement, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper, or is a mathematical concept that is achievable through mathematical computation.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
A processing system performed by using an edge device and a server device, wherein the edge device includes: first processing circuitry; a feature extraction layer; the server device includes: second processing circuitry; A non-transitory computer-readable recording medium storing therein a processing program that causes a computer to execute a process - These limitations amount to components of a general purpose computer that applies a judicial exception, by use of conventional computer functions (see MPEP § 2106.05(b)).
extract a feature amount of processing target data by using a first model and
execute inference processing on the processing target data on a basis of the extracted feature amount - steps recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
execute inference processing on the processing target data on the basis of the feature amount of the processing target data output from the edge device by using a second model having higher inference accuracy than the first model - steps recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
deletes the feature extraction layer - the step recited at a high level of generality, and amounts to selecting a particular data source or type of data to be manipulated, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
share results and output a feature map from the shared results - the steps recited at a high level of generality, and amounts to mere data transmission which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
A processing system performed by using an edge device and a server device, wherein the edge device includes: first processing circuitry; a feature extraction layer; the server device includes: second processing circuitry; A non-transitory computer-readable recording medium storing therein a processing program that causes a computer to execute a process - These limitations amount to components of a general purpose computer that applies a judicial exception, by use of conventional computer functions (see MPEP § 2106.05(b)).
extract a feature amount of processing target data by using a first model and
execute inference processing on the processing target data on a basis of the extracted feature amount - steps recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
execute inference processing on the processing target data on the basis of the feature amount of the processing target data output from the edge device by using a second model having higher inference accuracy than the first model - steps recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
deletes the feature extraction layer - the step recited at a high level of generality, and amounts to selecting a particular data source or type of data to be manipulated, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
share results and output a feature map from the shared results - the steps recited at a high level of generality, and amounts to mere data transmission which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 2:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
extract the feature amount of the processing target data, and
execute first inference processing on the basis of the feature amount of the processing target data - steps recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
extract the feature amount of the processing target data, and
execute first inference processing on the basis of the feature amount of the processing target data - steps recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 3:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
output the quantized feature amount of the processing target data to the server device - the steps recited at a high level of generality, and amounts to mere data outputting which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
output the quantized feature amount of the processing target data to the server device - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 4:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the reliability is based on entropy of the inference result - the step recited at a high level of generality, and amounts to selecting a particular data source or type of data to be manipulated, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the reliability is based on entropy of the inference result - the step recited at a high level of generality, and amounts to selecting a particular data source or type of data to be manipulated, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
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 1-6 are rejected under 35 U.S.C. 103 as being unpatentable over Verma et al. (hereinafter Verma), US 20210174163 A1, in view of Clayton et al. (hereinafter Clayton), US 20170206464 A1.
Regarding independent claim 1, Verma teaches a processing system performed by using an edge device and a server device (Fig. 1, 100, 150; [0021]-[0022]), wherein
the edge device includes:
a feature extraction layer ([0041] FIG. 5 illustrates a second example system for inference at an edge device, according to one embodiment disclosed herein … a first model may be based on a CNN, a second model may first use principal component analysis to reduce input images to a set of feature vectors and then use a decision tree); and
first processing circuitry configured to (Fig. 2, 211; [0026] the system node 210 includes a processor 211, memory 215, storage 220, and a network interface 225. In the illustrated embodiment, the processor 210 retrieves and executes programming instructions stored in memory 215, as well as stores and retrieves application data residing in storage 220):
extract a feature amount of processing target data by using a first model and execute inference processing on the processing target data on a basis of the extracted feature amount (Fig. 1; [0023] Continuing with reference to FIG. 1, as noted, cache decision maker 110 includes input analyzer 120. Cache decision maker 110 also includes model selector 125 and training data generator 123. Input analyzer 120 is tasked with receiving the client request from client interface 115, which is its input, and analyzing the input to determine whether a cached local model may be used to respond to the client request, or whether a more complex AI model stored in the cloud is required. Input analyzer 120 performs this task using classifier model 121, which is a third AI model that is trained to determine, for a given client request, whether a simpler local model would provide results compatible with the counterpart complex model stored in the cloud. As described in detail below, classifier model 121 of input analyzer 120 is trained to recognize the types of inputs where the simple model is suitable, and those for which it is not. In embodiments, classifier model 121 is trained using data generated by training data generator 123, described more fully below. Thus, in embodiments, input analyzer 120 checks incoming client requests and decides whether to use a simple local model at the edge, which may be known as a “cache hit”, or whether to use a more complex model in the cloud, which may be known as a “cache miss.”); and
output an inference result in a case where reliability of the inference result exceeds a threshold, and output the feature amount of the processing target data to the server device in a case where the reliability is equal to or less than the threshold ([0024] In embodiments, input analyzer forwards its decision to model selector 125, which both selects, and acts as an interface to, the model designated by input analyzer 120. Model selector, as shown in FIG. 1, is communicably connected to each local model in memory 111, over communications links 113, as well as to counterpart complex AI model(s) stored on cloud server 150, which model selector 125 accesses via cloud interface 130, described above. Model selector selects a model to respond to the client request, and transmits the client request to it. Model selector then receives the response, and forwards it over communication link 114 to client interface 115, which, in turn, provides the response to client 105, thus closing out the client request; [0025] In one or more embodiments, cache decision maker analyzes an input on a per request basis and decides whether it is better to use the simpler model at the edge, or to use the complex model; Fig. 4; [0033] Cache decision maker 215 decides on a per request basis whether it is better to use the simpler model at the edge, or to use the complex model. Thus, cache decision maker 215 acts as a gateway between client 210 and the two available AI models, simple AI model 221 and complex AI model 231. In one example, the simple AI model may be a two-tier neural network, and the complex model may be a five stage convolutional neural network. The cache decision maker 215 itself includes a fast AI model that is trained to determine whether the simple AI model 221 would provide results compatible with the complex AI model 231; Fig. 6; [0045] method 600 begins at block 610, where a client request is received; [0046] From block 610 method 600 proceeds to block 620, where it is determined if a response to the request from a first locally stored AI model is predicted to be the same as a response to the same request from a second AI model, the second AI model either remotely stored in the cloud, or also locally stored, the second AI model more complex than the first AI mode. For example, the complex model may have a significantly higher accuracy rate in detecting defects from images in the subject domain of the client request; [0047] From block 620, method 600 proceeds to query block 630, where it is determined whether the determination made in block 620 is affirmative or negative. If the return to query block 630 is a “Yes”, and thus the answers from each of the simple and complex AI models are predicted to be the same, then method 600 proceeds to block 635, where a response is provided to the client request from the first AI model, and method 600 ends; [0048] If, however, a “No” is returned at query block 630, and the simple model is not predicted to provide the same answer as the complex AI model, then method 600 moves to block 640, where a response to the client request is provided from the second AI model, and method 600 then ends), and
the server device includes:
second processing circuitry configured to ([0022] cloud servers 150 are high performance computing devices, with multiple processor cores and multiple graphic processing units):
execute inference processing on the processing target data on the basis of the feature amount of the processing target data output from the edge device by using a second model having higher inference accuracy than the first model (Fig. 6; [0046] From block 610 method 600 proceeds to block 620, where it is determined if a response to the request from a first locally stored AI model is predicted to be the same as a response to the same request from a second AI model, the second AI model either remotely stored in the cloud, or also locally stored, the second AI model more complex than the first AI model. For example, the complex model may have a significantly higher accuracy rate in detecting defects from images in the subject domain of the client request; [0048] If, however, a “No” is returned at query block 630, and the simple model is not predicted to provide the same answer as the complex AI model, then method 600 moves to block 640, where a response to the client request is provided from the second AI model, and method 600 then ends).
Verma does not expressly teach wherein the second processing circuitry further deletes the feature extraction layer in the server device and share results from a previously provided feature extraction layer in the edge device with the server device; and output a feature map from the shared results.
However, in the same field of endeavor, Clayton teaches wherein the second processing circuitry further deletes the feature extraction layer in the server device ([0057] FIG. 10 is a flow diagram illustrating time series data adaptation including sensor fusion, according to an example embodiment of the present disclosure. In this example embodiment, the sensor fusion machine 908 includes a multi-modal variational inference machine (MMVIM) 910 and a multi-modal recurrent neural network (MMRNN) 912, both of which receive multiple modalities of data as inputs (i.e., data from multiple different domains), to provide a multi-modal sensor fusion output; [0058] The sensor fusion machine 908 may receive the time dependency infused latent distributions z1t, z2t, and z3t, for example, from the VIM-SDFM pairs 902, 904, 906. For example, the time dependency infused latent distributions z1t, z2t, z3t and a first version of the multi-modal hidden state Ht−1 may be input in parallel into the input layer of MMVIM 910; [0071] FIG. 12 illustrates an exemplary structure of feature extractors as provided within a variational inference machine such as MMVIM 910. FIG. 12 is high-level block diagram of a variational inference machine 1200, according to an example embodiment of the present disclosure. The input layer 302 of the variational inference machine 1200 may include sublayers 1202 and 1204. Inputs received at sublayer 1202 are provided to feature extractor 1206, which then provides outputs to hidden layers 1210. Likewise, inputs received at sublayer 1204 are provided to feature extractor 1208, which then provides outputs to hidden layers 1210, which outputs a time dependency infused latent distribution z from output layer 306; [0072] one or both of the feature extractors 1206 and 1208 may be omitted from the hidden layers 304. For example, a feature extractor 1206 may be unnecessary, so hidden state h inputs received at sublayer 1202 may be provided directly to hidden layers 1210. For example, a feature extractor 1208 may be omitted for the input of time dependency infused latent distributions z1, z2, z3, for example, as described in FIG. 10) and share results from a previously provided feature extraction layer in the edge device with the server device; and output a feature map from the shared results ([0072] a common feature extractor 1208 may be used in the different variational inference machines).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of omitting a feature extractor and using shared extracted features among the different variational inference machines as suggested in Clayton into Verma’s system because both of these systems are addressing a system including a variational inference machine. This modification would have been motivated by the desire to improve fault tolerance within the system, decrease the required costs of sensors, decrease the impact from sensor failure or unavailability, decrease the amount of data to be transmitted and stored, increase the speed of processing time and data transfer, and improve the accuracy, precision, and consistency of results (Clayton, [0030]).
Regarding dependent claim 2, the combination of Verma and Clayton teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. Verma further teaches wherein
the first processing circuitry is further configured to:
extract the feature amount of the processing target data (Fig. 1; [0023] Continuing with reference to FIG. 1, as noted, cache decision maker 110 includes input analyzer 120. Cache decision maker 110 also includes model selector 125 and training data generator 123. Input analyzer 120 is tasked with receiving the client request from client interface 115, which is its input, and analyzing the input to determine whether a cached local model may be used to respond to the client request, or whether a more complex AI model stored in the cloud is required. Input analyzer 120 performs this task using classifier model 121, which is a third AI model that is trained to determine, for a given client request, whether a simpler local model would provide results compatible with the counterpart complex model stored in the cloud. As described in detail below, classifier model 121 of input analyzer 120 is trained to recognize the types of inputs where the simple model is suitable, and those for which it is not. In embodiments, classifier model 121 is trained using data generated by training data generator 123, described more fully below. Thus, in embodiments, input analyzer 120 checks incoming client requests and decides whether to use a simple local model at the edge, which may be known as a “cache hit”, or whether to use a more complex model in the cloud, which may be known as a “cache miss.”, and
execute first inference processing on the basis of the feature amount of the processing target data ([0032] The edge device 220 can execute an inference operation using the simpler AI model 221; [0041] FIG. 5 illustrates a second example system for inference at an edge device, according to one embodiment disclosed herein. The embodiment illustrated in FIG. 5 is identical to the example illustrated in FIG. 4, with the additional element that edge device 220 has not only one cached simple AI model, but rather a full set of simple AI models 221. The set 221 thus includes, as shown, models M1 through MN. In this embodiment, cache decision maker 215 is adapted to choose among the multiple cached models, based upon their respective fidelity with the complex cloud based model 231 and relative performance. It is noted that in the example of FIG. 5, all of models 221 may provide the same type of inference, but could be different. For example, a first model may be based on a CNN, a second model may first use principal component analysis to reduce input images to a set of feature vectors and then use a decision tree, a third model may use a recurrent neural network, a fourth model may be trained to process images that are taken in bright sunlight, and a fifth model may be trained for images that are taken under shady conditions. In the case of the latter two examples, cache decision maker 215 may determine whether an input image was taken under either bright or shady conditions by analyzing the values of the image pixels, for example), and
the second processing circuitry is further configured to:
execute second inference processing on the basis of the feature amount of the processing target data (Fig. 6; [0046] From block 610 method 600 proceeds to block 620, where it is determined if a response to the request from a first locally stored AI model is predicted to be the same as a response to the same request from a second AI model, the second AI model either remotely stored in the cloud, or also locally stored, the second AI model more complex than the first AI model. For example, the complex model may have a significantly higher accuracy rate in detecting defects from images in the subject domain of the client request; [0048] If, however, a “No” is returned at query block 630, and the simple model is not predicted to provide the same answer as the complex AI model, then method 600 moves to block 640, where a response to the client request is provided from the second AI model, and method 600 then ends).
Regarding dependent claim 3, the combination of Verma and Clayton teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. Verma further teaches wherein the first processing circuitry is further configured to output the quantized feature amount of the processing target data to the server device ([0022] Edge device 100 includes a cache decision maker 110, a memory 111 and a cloud interface 130. Memory 111 stores, on the edge device, one or more local models, shown as local model 126, and optionally local models 127 and 128 (thus the latter two shown in dashed lines in FIG. 1). These models, as noted above, are faster, but more simple (and thus, in some cases, less accurate) versions of AI models designed or trained for the same functionality. Cache decision maker 110 can access each of the local models via communications links, as shown. In some embodiments, the local AI models 126-128 are generated from the more complex cloud based versions of these AI models via at least one of transfer learning or model compression. The cloud based versions of the AI models may be stored on cloud servers 150, described below. Through cloud interface 130 and network connection 131, for example a data network, edge device 100 communicates and exchanges data with cloud servers 150, over network connection 131; 0024] In embodiments, input analyzer forwards its decision to model selector 125, which both selects, and acts as an interface to, the model designated by input analyzer 120. Model selector, as shown in FIG. 1, is communicably connected to each local model in memory 111, over communications links 113, as well as to counterpart complex AI model(s) stored on cloud server 150, which model selector 125 accesses via cloud interface 130, described above. Model selector selects a model to respond to the client request, and transmits the client request to it. Model selector then receives the response, and forwards it over communication link 114 to client interface 115, which, in turn, provides the response to client 105, thus closing out the client request).
Regarding dependent claim 4, the combination of Verma and Clayton teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. Verma further teaches wherein the reliability is based on entropy of the inference result ([0014] Embodiments and examples described herein relate to selection of an appropriate AI model, out of two or more possible models, to respond to a client request. In some examples, the client request is received at an edge device, the edge device having one or more locally saved first AI models, the edge device further being able to access a remotely stored second AI model, such as, for example, one provided in the cloud. In such examples the first AI models are relatively simple in comparison with the second AI model, but have the advantage of being faster, whereas the second AI model is more complex than the first AI models, and thus more accurate, but has the disadvantage of being slower, due to one or more of longer latency or longer processing times; [0020] in order to improve the accuracy to responses to client requests and still obtain the benefit of the faster response time from the cached model, an intelligent cache decision maker is provided. In embodiments, the cache decision maker decides, on a per request basis, whether it is better to use the simpler model at the edge, or to use the complex model from the cloud).
Regarding independent claim 5, it is a method claim that corresponding to the system of claim 1. Therefore, it is rejected for the same reason as claim 1 above.
Regarding independent claim 6, it is a medium claim that corresponding to the system of claim 1. Therefore, it is rejected for the same reason as claim 1 above.
Response to Arguments
Applicant's arguments filed 02/10/2026 have been fully considered. Each of applicant’s remarks is set forth, followed by examiner’s response.
(1) The minor informalities object to the specification regarding the title of the invention is respectfully withdrawn in response to Applicant’s amendment to the specification.
(2) The 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph rejections to claim 2 is respectfully withdrawn in response to Applicant's amendment to the claim.
(3) Regarding 35 U.S.C. 101 rejections, Applicant alleges amended claim 1 recites the limitations of "the second processing circuitry further deletes the feature extraction layer in the server device and share results from a previously provided feature extraction layer in the edge device with the server device; and output a feature map from the shared results." (Emphasis added). At least the above limitations cannot be practically performed in the human mind. Even assuming, arguendo, amended claim 1 falls into the grouping of a mental process, amended claim 1 is still not directed to an abstract idea because amended claim 1 as a whole integrates the alleged judicial exceptions into a practical application (e.g., "the second processing circuitry further deletes the feature extraction layer in the server device and share results from a previously provided feature extraction layer in the edge device with the server device; and output a feature map from the shared results"). Amended claim 1 recites specific improvements to the technical field of providing a processing methods capable of reducing an amount of data transfer and delay from an edge device to a server device. For example, amended claim 1 recites limitations of "the second processing circuitry further deletes the feature extraction layer in the server device and share results from a previously provided feature extraction layer in the edge device with the server device; and output a feature map from the shared results." (Emphasis added). Such features help to optimizing the allocation and accuracy of processes to an edge and a cloud in accordance with the processing target data, and reducing overall system power consumption, and reducing an amount of data transmitted between the edge and the cloud. Even assuming, arguendo, amended claim 1 is directed to the judicial exception of an abstract idea, amended claim 1 is patent eligible because it recites additional elements that are "unconventional or otherwise more than what is well-understood, routine, conventional activity in the field."
As to point (3), Applicant’s statutory subject matter arguments with respect to the pending claims have been considered but they are moot in view of the new ground(s) of rejections presented above. As discuss in the rejection above, the claim is directed to an abstract idea that encompasses the mental process of evaluating data and generating an inference result based on judgement, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper, or is a mathematical concept that is achievable through mathematical computation. One way to determine integration into a practical application is when the claimed invention improves the functioning of a computer or improves another technology or technical field. To evaluate an improvement to a computer or technical field, the specification must set forth an improvement in technology and the claim itself must reflect the disclosed improvement. See MPEP 2106.04(d)(1) and 2106.05(a). The consideration of whether the claim as a whole includes an improvement to a computer or to a technological field requires an evaluation of the specification and the claim to ensure that a technical explanation of the asserted improvement is present in the specification, and that the claim reflects the asserted improvement. While the claim recites “the second processing circuitry further deletes the feature extraction layer in the server device and share results from a previously provided feature extraction layer in the edge device with the server device; and output a feature map from the shared results”, the claim does not provide any details about how the deleting, the sharing and the outputting reflect an improvement in technology. There is no improvement to the functioning of a computer nor to any other technology. At best, the claimed combination amounts to an improvement to the abstract idea rather than to any technology. See MPEP 2106.05(a). Any purported improvements are provided by the judicial exception alone, i.e. mental process, thus the claim as a whole does not integrate the judicial exception into a practical application nor provide significantly more than the judicial exception. Thus, the claims are patent ineligible and are rejected under 35 U.S.C. 101 as detailed in the rejections set forth above.
(4) Applicant’s prior art arguments with respect to the pending claims have been considered but they are moot in view of the new ground(s) of rejections presented above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Applicant is required under 37 C.F.R. § 1.111(c) to consider these references fully when responding to this action.
Horie et al. (US 20210241105 A1) discloses sharing inference processing between two inference apparatuses so as to shorten the time required for communication between the two inference apparatuses.
It is noted that any citation to specific pages, columns, lines, or figures in the prior art references and any interpretation of the references 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. In re Heck, 699 F.2d 1331, 1332-33, 216 U.S.P.Q. 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1009, 158 U.S.P.Q. 275, 277 (C.C.P.A. 1968)).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 nonprovisional extension fee (37 CFR 1.17(a)) 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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AMY P HOANG whose telephone number is (469)295-9134. The examiner can normally be reached M-TH 8:30-5:00PM.
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, JENNIFER WELCH can be reached at 571-272-7212. 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.
/AMY P HOANG/Examiner, Art Unit 2143
/JENNIFER N WELCH/Supervisory Patent Examiner, Art Unit 2143
Prosecution Insights