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 .
This office action is in response to submission of application on 2/29/2024.
Claims 1-20 are presented for examination.
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 1-8 and 15-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Is the claim to a process, machine, manufacture or composition of matter?
Claims 1-8 are directed to an apparatus (i.e., a machine/apparatus); and claims 15-20 are directed to a method (i.e., a process); therefore, all pending claims are directed to one of the four categories of invention.
Independent Claims
Step 2A Prong One: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, independent claim 1 recites an abstract idea in the form of mental processes. A mental process is a process that “can be performed in the human mind, or by a human using a pen and paper” (MPEP§ 2106.04(a)(2)(III), paragraph 1). Examples of mental processes include “observations, evaluations, judgments, and opinions” (MPEP § 2106.04(a)(2)(III), paragraph 2).
The following limitations of claim 1 are mental processes:
generate a compressed positioning report… [This is a mental process that can be performed by observations, evaluations, judgments, and opinions. No specific methodology for generating a report is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
…by running the training-based compression algorithm, the training-based compression algorithm taking as input data derived from the one or more reference signals and generating as output the compressed positioning report; and [This is a mental process that can be performed by observations, evaluations, judgments, and opinions. No specific methodology for the algorithm is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
Therefore, the independent claims recite a judicial exception.
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No. The judicial exception recited in the above discussed claims is not integrated into a
practical application.
a processor configured to: [A processor are components recited at a high level are construed as generic computer components used to implement the abstract idea. See MPEP 2106.05(f)(2). As such, the limitations do not integrate the abstract idea into a practical application. Nor to do they amount to significantly more.]
receive one or more reference signals for positioning a target end device; [receiving a signal is sending data, which is insignificant, extra-solution activity. See MPEP 2106.05(g). Transmitting data is well-understood, routine, and conventional. See MPEP 2106.05(d)(II)(i).]
receive a set of trained parameters defining a training-based compression algorithm from a training device, the set of trained parameters being obtained by a joint training of the training-based compression algorithm and one or more training-based algorithms implemented in a positioning reports consumer; [receiving parameters is sending data, which is insignificant, extra-solution activity. See MPEP 2106.05(g). Transmitting data is well-understood, routine, and conventional. See MPEP 2106.05(d)(II)(i).]
send the compressed positioning report to the positioning reports consumer. [sending a report is sending data, which is insignificant, extra-solution activity. See MPEP 2106.05(g). Transmitting data is well-understood, routine, and conventional. See MPEP 2106.05(d)(II)(i).]
Therefore, under MPEP 2106.04(d), the additional elements of the claims do not integrate
the judicial exception into a practical application.
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No. The claims do not include additional elements that are sufficient for the claims to
amount to significantly more than the judicial exception.
Additional elements that are mere instructions to apply an exception or merely generally
linking or generally linking the use of a judicial exception to a particular technological
environment or field of use do not constitute significantly more than a judicial exception under
MPEP§2106.05(I)(A). Since the additional elements in the independent claims are all are mere
instructions to apply an exception or are merely generally linking or generally linking the use of
a judicial exception to a particular technological environment or field of use, they do not
constitute significantly more than a judicial exception.
Therefore, the additional elements identified in the Step 2A Prong Two analysis do not
constitute significantly more than a judicial exception.
Therefore, the independent claim is not patent eligible.
Claim 2
Step 2A Prong One: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, independent claim 2 recites an abstract idea in the form of mental processes. A mental process is a process that “can be performed in the human mind, or by a human using a pen and paper” (MPEP§ 2106.04(a)(2)(III), paragraph 1). Examples of mental processes include “observations, evaluations, judgments, and opinions” (MPEP § 2106.04(a)(2)(III), paragraph 2).
The following limitations of claim 2 are mental processes:
generate a decompressed positioning report… [This is a mental process that can be performed by observations, evaluations, judgments, and opinions. No specific methodology for generating a report is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
…by running the training-based decompression algorithm, the training-based decompression algorithm taking as input the compressed positioning report and generating as output the decompressed positioning report; and [This is a mental process that can be performed by observations, evaluations, judgments, and opinions. No specific methodology for the algorithm is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
generate an estimated distance for positioning a target end device… [This is a mental process that can be performed by observations, evaluations, judgments, and opinions. No specific methodology for generating a distance is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
…by running the training-based distance correction algorithm, the estimated distance designating a distance separating the target end device and a transmitter or a receiver of one or more reference signals for positioning the target end device, the training-based distance correction algorithm taking as input reconstructed data derived from the decompressed positioning report and generating as output the estimated distance. [This is a mental process that can be performed by observations, evaluations, judgments, and opinions. No specific methodology for the algorithm is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
Therefore, the independent claims recite a judicial exception.
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No. The judicial exception recited in the above discussed claims is not integrated into a
practical application.
a processor configured to: [A processor are components recited at a high level are construed as generic computer components used to implement the abstract idea. See MPEP 2106.05(f)(2). As such, the limitations do not integrate the abstract idea into a practical application. Nor to do they amount to significantly more.]
receive a compressed positioning report from a positioning reports producer (101); [receiving a report is sending data, which is insignificant, extra-solution activity. See MPEP 2106.05(g). Transmitting data is well-understood, routine, and conventional. See MPEP 2106.05(d)(II)(i).]
receive, from a training device, a set of trained parameters defining a training-based decompression algorithm and a set of trained parameters defining a training-based distance correction algorithm, the sets of trained parameters being obtained by a joint training of the training-based decompression algorithm, the training-based distance correction algorithm and a training-based compression algorithm implemented in the positioning reports producer; [receiving parameters is sending data, which is insignificant, extra-solution activity. See MPEP 2106.05(g). Transmitting data is well-understood, routine, and conventional. See MPEP 2106.05(d)(II)(i).]
Therefore, under MPEP 2106.04(d), the additional elements of the claims do not integrate
the judicial exception into a practical application.
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No. The claims do not include additional elements that are sufficient for the claims to
amount to significantly more than the judicial exception.
Additional elements that are mere instructions to apply an exception or merely generally
linking or generally linking the use of a judicial exception to a particular technological
environment or field of use do not constitute significantly more than a judicial exception under
MPEP§2106.05(I)(A). Since the additional elements in the independent claims are all are mere
instructions to apply an exception or are merely generally linking or generally linking the use of
a judicial exception to a particular technological environment or field of use, they do not
constitute significantly more than a judicial exception.
Therefore, the additional elements identified in the Step 2A Prong Two analysis do not
constitute significantly more than a judicial exception.
Therefore, the independent claim is not patent eligible.
Claim 3
Step 2A Prong One: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, independent claim 3 recites an abstract idea in the form of mental processes. A mental process is a process that “can be performed in the human mind, or by a human using a pen and paper” (MPEP§ 2106.04(a)(2)(III), paragraph 1). Examples of mental processes include “observations, evaluations, judgments, and opinions” (MPEP § 2106.04(a)(2)(III), paragraph 2).
The following limitations of claim 3 are mental processes:
[generate] a first set of trained parameters defining a training-based compression algorithm; [This is a mental process that can be performed by a human via observations, evaluations, judgments, and opinions, either mentally or with the aid of pen and paper. No specific methodology for a set of trained parameters is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
[generate] a second set of trained parameters defining a training-based decompression algorithm; [This is a mental process that can be performed by a human via observations, evaluations, judgments, and opinions, either mentally or with the aid of pen and paper. No specific methodology for a set of trained parameters is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
[generate] a third set of trained parameters defining a training-based distance correction algorithm: [This is a mental process that can be performed by a human via observations, evaluations, judgments, and opinions, either mentally or with the aid of pen and paper. No specific methodology for a set of trained parameters is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
Independent claim 3 also recites an abstract idea in the form of mathematical concepts. A mathematical concept is defined as “mathematical relationships, mathematical formulas or equations, and mathematical calculations.” (MPEP§ 2106.04(a)(2)(I), paragraph 1).
The following limitations of claim 3 are mathematical concepts:
wherein the first set of trained parameters, the second set of trained parameters and the third set of trained parameters being generated by performing a joint training of the compression, decompression and the distance correction training-based algorithms using training data and according to a minimization of a loss function. [This is a mathematical concept that describes mathematical relationships, mathematical formulas or equations, or mathematical calculations. The claim recites mathematical concept of minimizing a loss function.]
Therefore, the independent claim recites a judicial exception.
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No. The judicial exception recited in the above discussed claims is not integrated into a
practical application.
A training device comprising: a processor configured to generate: [A training device comprising a processor are components recited at a high level are construed as generic computer components used to implement the abstract idea. See MPEP 2106.05(f)(2). As such, the limitations do not integrate the abstract idea into a practical application. Nor to do they amount to significantly more.]
Therefore, under MPEP 2106.04(d), the additional elements of the claims do not integrate
the judicial exception into a practical application.
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No. The claims do not include additional elements that are sufficient for the claims to
amount to significantly more than the judicial exception.
Additional elements that are mere instructions to apply an exception or merely generally
linking or generally linking the use of a judicial exception to a particular technological
environment or field of use do not constitute significantly more than a judicial exception under
MPEP§2106.05(I)(A). Since the additional elements in the independent claims are all mere instructions to apply an exception, they do not constitute significantly more than a judicial exception.
Therefore, the additional elements identified in the Step 2A Prong Two analysis do not
constitute significantly more than a judicial exception.
Independent claim 15 recites the same relevant limitations and a similar analysis applies.
Claim 15 recites the additional elements of “A method comprising:” [A method are components recited at a high level are construed as generic computer components used to implement the abstract idea. See MPEP 2106.05(f)(2). As such, the limitations do not integrate the abstract idea into a practical application. Nor to do they amount to significantly more.]
Therefore, the independent claims are not patent eligible.
Dependent Claims
The remaining dependent claims being rejected do not recite additional elements, whether considered individually or in combination, that are sufficient to integrate the judicial exception into a practical application or amount to significantly more than the judicial exception.
Claims 4 and 16
training a training-based compression algorithm to generate a training compressed positioning report from data derived from one or more training reference signals for positioning a training target end device, for a given training compression level; [This is a mathematical concept that describes mathematical relationships, mathematical formulas or equations, or mathematical calculations. The claim recites mathematical concept of a compression algorithm.]
training a training-based decompression algorithm to generate a training decompressed positioning report from the training compressed positioning report; [This is a mathematical concept that describes mathematical relationships, mathematical formulas or equations, or mathematical calculations. The claim recites mathematical concept of a decompression algorithm.]
training a training-based distance correction algorithm to generate a training estimated distance for positioning the training target end device from reconstructed data derived from the training decompressed positioning report; and [This is a mathematical concept that describes mathematical relationships, mathematical formulas or equations, or mathematical calculations. The claim recites mathematical concept of a distance correction algorithm.]
computing a training distance estimation error by applying the loss function to the training estimated distance and a training real distance separating the training target end device from a training transmitter or a training receiver of the one or more training reference signals. [This is a mental process that can be performed by observations, evaluations, judgments, and opinions. No specific methodology for computing a training distance estimation is recited in the claim; therefore, it broadly encompasses processing that can be performed as a mental process.]
Claims 5 and 17
the training-based compression algorithm and the training-based decompression algorithm form an autoencoder of a given code size that maps to a given compression level, the autoencoder comprising the training-based compression algorithm as an encoder and the training-based decompression algorithm as a decoder. [This additional element does no more than generally link the use of a judicial exception to a particular technological environment or field of use (MPEP § 2106.05(h)). This element merely indicates a field of use or technological environment in which a judicial exception is applied, namely the autoencoder includes managing automated resources]. training-based compression and decompression algorithms.].
Claims 6 and 18
the given code size is selected from a set of two or more code sizes as a tradeoff between positioning latency and accuracy. [This additional element does no more than generally link the use of a judicial exception to a particular technological environment or field of use (MPEP § 2106.05(h)). This element merely indicates a field of use or technological environment in which a judicial exception is applied, namely the code size is selected from a set of two or more code sizes.].
Claims 7 and 19
the two or more code sizes map to two or more compression levels, the joint training being performed for the two or more compression levels, the first set of trained parameters, the second set of trained parameters, and the third set of trained parameters being generated for the two or more code sizes. [This additional element does no more than generally link the use of a judicial exception to a particular technological environment or field of use (MPEP § 2106.05(h)). This element merely indicates a field of use or technological environment in which a judicial exception is applied, namely the code sizes map to compression levels, the joint training being performed on the compression levels, and the first, second, and third set of trained parameters.].
Claims 8 and 20
the processor is configured to send the first set of trained parameters to a positioning reports producer and send the second set of trained parameters and the third set of trained parameters to a positioning reports consumer. [sending parameters is sending data, which is insignificant, extra-solution activity. See MPEP 2106.05(g). Transmitting data is well-understood, routine, and conventional. See MPEP 2106.05(d)(II)(i).]
The prior art used for rejections are provided below:
US12034461B2 (Filed March 6, 2020) to Rydén et al. (hereinafter Rydén)
Distance Measurements in UWB-Radio Localization Systems Corrected with a Feedforward Neural Network Model (March 25, 2021) to Krapež et al. (hereinafter Krapež)
An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization (March 13, 2020) to Lee et al. (hereinafter Lee)
Claim Rejections - 35 USC § 102
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.
Claim(s) 1 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Rydén.
Per claim 1, Rydén discloses: A positioning reports producer comprising: a processor configured to: [Rydén, column 22, line 15 "the wireless device 2310 may comprise processing circuitry 2320 and a memory 2330" (note: the wireless device that compresses and transmits the delay profile is the entity generating and sending the positioning report, which is a positioning reports producer comprising a processor.)]
receive one or more reference signals for positioning a target end device; [Rydén, column 15, line 53 "receiving 1701 a transmission of a known reference signal iron the network node, and cross-correlating 1702 the received signal transmission with the known reference signal" (note: the known reference signal is a positioning reference signal, and cross-correlation is the means of deriving the channel impulse response used for positioning.)]
receive a set of trained parameters defining a training-based compression algorithm from a training device, the set of trained parameters being obtained by a joint training of the training-based compression algorithm and one or more training-based algorithms implemented in a positioning reports consumer; [Rydén, column 8, line 42 “An autoencoder is a type of neural network … comprising an encoder/decoder”;
column 8, line 53 “In step 1, a network node trains an autoencoder for compression”
column 8, line 64 “the network node receives the UE report, reconstructs the CIR ( or the delay profile of the CIR) and performs localization.”) (note: An autoencoder is one network, training it necessarily trains encoder and decoder together. The decoder is at the network node that reconstructs and localizes, a positioning reports consumer. Therefore, this is joint training of the compression algorithm with a consumer-side algorithm.)]
generate a compressed positioning report by running the training-based compression algorithm, the training-based compression algorithm taking as input data derived from the one or more reference signals and generating as output the compressed positioning report; and [Rydén, column 8 line 60 "the UE encodes (or compresses) the estimated CIR (or a delay profile of the CIR) using the autoencoder" (note: the delay profile is data derived from the received reference signal (the specification indicates this… "signal features related to the one or more reference signals" ))]
send the compressed positioning report to the positioning reports consumer. [Rydén, column 8, line 64 "the network node receives the UE report, reconstructs the CIR (or the delay profile of the CIR) and performs localization" (note: the receiving node decompresses and localizes and is therefore the positioning reports consumer)]
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.
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.
Claims 2-8 and 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Rydén in view of Krapež and Lee.
Per claim 2, Rydén discloses:
A positioning reports consumer comprising: a processor configured to: [Rydén, column 22 line 57 "the network node 2360 may comprise processing circuitry 2370 and a memory 2380" (note: the reference states the localizing node may be a location server.)]
receive a compressed positioning report from a positioning reports producer (101); [Rydén, column 16 line 59 "receiving 1904 a compressed delay profile of a channel impulse response (CIR)" (note: the compressed delay profile transmitted by the wireless device is the compressed positioning report.)]
generate a decompressed positioning report by running the training-based decompression algorithm, the training-based decompression algorithm taking as input the compressed positioning report and generating as output the decompressed positioning report; and [Rydén, column 16 , line 63"decompressing 1905 the compressed delay profile using a decompression function" (note: the decompression function is the decoder half of the trained autoencoder, taking the compressed report as input and producing the reconstructed profile as output.)]
Rydén does not expressly disclose, but Rydén combined with Lee does teach:
receive, from a training device, a set of trained parameters defining a training-based decompression algorithm …. the sets of trained parameters being obtained by a joint training of the training-based decompression algorithm, the training-based distance correction algorithm and a training-based compression algorithm implemented in the positioning reports producer; [Lee, pg. 1 "Our proposed JointIQ-Net combines an image compression sub-network and a quality enhancement sub-network in a cascade, both of which are end-to-end trained in a combined manner within the JointIQ-Net." (note: the autoencoder (compression and decompression) and the quality-enhancement network are trained end-to-end in a combined manner, therefore the decompression and distance-correction parameter sets delivered to the consumer are obtained by joint training with the compression algorithm implemented in the producer.);
pg. 6 “two sub-networks to be jointly optimized towards minimizing the total loss” (note: Lee discloses joint training)]
Rydén and Lee are analogous art because they are from the same field of endeavor of compressing sensor-derived data for transmission over a bandwidth-constrained link to a remote node that performs the actual task on the reconstructed data. They are further reasonably pertinent to the same problem of balancing reconstruction/task accuracy against transmission overhead.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to train the decompression function and a downstream correction network jointly with the producer-side compression function as a single end-to-end optimization, rather than training the compression/decompression pair and the correction network separately.
The suggestion/motivation for doing so would have been to improve overall accuracy of the final output by allowing the compression stage to preserve exactly the information the downstream correction task needs, as Lee states: [pg. 1, "the quality enhancement and rate-minimization are conflictively coupled in the process of image compression. That is, maintaining high image quality entails less compression and vice versa. However, by jointly training separate quality enhancement in conjunction with image compression, the coding efficiency can be improved."]
Rydén combined with Lee does not expressly disclose, but Rydén combined with Krapež does teach:
…and a set of trained parameters defining a training-based distance correction algorithm, … [Krapež, pg. 6 "The neural network (NN) has three input parameters—measured distance, azimuth and elevation angles, and one output parameter—corrected distance." (note: the neural network takes a measured distance as input and outputs a corrected distance separating the tag from the anchor, which is the training-based distance correction algorithm.)]
generate an estimated distance for positioning a target end device by running the training-based distance correction algorithm, the estimated distance designating a distance separating the target end device and a transmitter or a receiver of one or more reference signals for positioning the target end device, the training-based distance correction algorithm taking as input reconstructed data derived from the decompressed positioning report and generating as output the estimated distance. [Rydén, column 16, line 65 "estimating 1906 a position of the wireless device based on at least the decompressed delay profile" (note: the decompressed delay profile provides the reconstructed data from which the distance value fed to the distance-correction network is derived.)]
[Krapež, pg. 6 "The neural network (NN) has three input parameters—measured distance, azimuth and elevation angles, and one output parameter—corrected distance." (note: the neural network takes a measured distance as input and outputs a corrected distance separating the tag from the anchor, which is the training-based distance correction algorithm.)]
Rydén and Krapež are analogous art because they are from the same field of endeavor of radio-based device localization. They are further reasonably pertinent to the same problem of obtaining accurate distance estimates from range measurements corrupted by radio-frequency and propagation effects.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to apply a trained distance-correction network to the distance value that the location server derives from the decompressed channel data, before that distance is used in multilateration.
The suggestion/motivation for doing so would have been to recover ranging accuracy lost to hardware and propagation effects that the decompressed channel data cannot itself remove, as stated by Krapež: [pg. 14 "The NN model improved the mean error over all six tags' poses by 2 cm."]
Per claim 3, Rydén discloses:
A training device comprising: a processor configured to generate: [Rydén, column 8, line 53 “In step 1, a network node trains an autoencoder for compression”;
column 22, line 57 “the network node 2360 may comprise processing circuitry 2370 and a memory 2380” (note: this discloses the training device and processor)]
a first set of trained parameters defining a training-based compression algorithm; [Rydén, column 8, line 53 "a network node trains an autoencoder for compression " (note: the network node generates the compression-function parameter set by evaluating candidate pairs of compression and decompression functions.)]
a second set of trained parameters defining a training-based decompression algorithm; [Rydén, column 18, line 19 "The compression function (at step 1901) and/or the decompression function (at step 1902) may for example be determined based on evaluation of a collection of candidate pairs of compression functions and decompression functions. " (note: the same passage discloses generation of the decompression-function parameter set as the other half of each evaluated candidate pair.)]
Rydén does not expressly disclose, but Rydén combined with Krapež does teach:
a third set of trained parameters defining a training-based distance correction algorithm, [Krapež, pg. 6 "Measured and reference distances, azimuth and elevation angles were then used for the training of a feedforward neural network." (note: the trained weights of this feedforward network are the third set of trained parameters, generated from training data comprising measured distances.)]
Rydén and Krapež are analogous art because they are from the same field of endeavor of radio-based device localization. They are further reasonably pertinent to the same problem of obtaining accurate distance estimates from range measurements corrupted by radio-frequency and propagation effects.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to apply a trained distance-correction network to the distance value that the location server derives from the decompressed channel data, before that distance is used in multilateration.
The suggestion/motivation for doing so would have been to recover ranging accuracy lost to hardware and propagation effects that the decompressed channel data cannot itself remove, as stated by Krapež: [pg. 14 "The NN model improved the mean error over all six tags' poses by 2 cm."]
Rydén combined with Krapež does not expressly disclose, but Rydén combined with Lee does teach:
wherein the first set of trained parameters, the second set of trained parameters and the third set of trained parameters being generated by performing a joint training of the compression, decompression and distance correction training-based algorithms using training data and according to a minimization of a loss function. [Lee, pg. 6 "our architecture allows two sub-networks to be jointly optimized towards minimizing the total loss Eq. (1)." (note: Lee's describes joint optimization of two sub-networks, I and Q; the three-set structure of claim 3 is reached by combining Lee's two-network joint-training teaching with Rydén's independent teaching that compression and decompression are themselves two separately-parameterized functions, (candidate pairs). Therefore, applying Lee's joint-training principle to a compression/decompression pair already treated as separately parameterized, together with Krapež's distance-correction task, produces three coupled parameter sets trained under one combined loss.)]
[Rydén, column 18, line 19 "The compression function (at step 1901) and/or the decompression function (at step 1902) may for example be determined based on evaluation of a collection of candidate pairs of compression functions and decompression functions. " (note: this shows that compression and decompression are two separately-parameterized functions, which combined with Lee's two-network joint-training teaching yields the three-set joint-training structure of the limitation.)]
Rydén and Lee are analogous art because they are from the same field of endeavor of compressing sensor-derived data for transmission over a bandwidth-constrained link to a remote node that performs the actual task on the reconstructed data. They are further reasonably pertinent to the same problem of balancing reconstruction/task accuracy against transmission overhead.
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to train the decompression function and a downstream correction network jointly with the producer-side compression function as a single end-to-end optimization, rather than training the compression/decompression pair and the correction network separately.
The suggestion/motivation for doing so would have been to improve overall accuracy of the final output by allowing the compression stage to preserve exactly the information the downstream correction task needs, as Lee states: [pg. 1, "the quality enhancement and rate-minimization are conflictively coupled in the process of image compression. That is, maintaining high image quality entails less compression and vice versa. However, by jointly training separate quality enhancement in conjunction with image compression, the coding efficiency can be improved."]
Per claim 4, Rydén, Krapež and Lee disclose claim 3.
Rydén does not expressly disclose, but with Krapež and Lee does teach:
wherein performing the joint training of the compression, decompression and distance correction training-based algorithms comprises jointly:
training a training-based compression algorithm to generate a training compressed positioning report from data derived from one or more training reference signals for positioning a training target end device, for a given training compression level; [Lee, pg. 7 "we use four fundamental transform functions: an analysis transform ga(x;φg), a synthesis transform gs(ŷ;θg), an analysis transform ha(ŷ;φh), and a synthesis transform hs(ẑ;θh)" (note: ga is the analysis transform that produces the latent representation, which is then quantized, which is the compression side of the cascade.);
pg. 7 "The JointIQ-Net transforms input x into latent representations y, and y is then quantized into ŷ." (note: the quantized latent ŷ is the training compressed report produced by the compression algorithm.)]
training a training-based decompression algorithm to generate a training decompressed positioning report from the training compressed positioning report; [Lee, pg. 8 "a synthesis transform gs(ŷ;θg)" (note: gs is the synthesis transform operating on the quantized latent ŷ.); "Q is a quality enhancement function with input x̂ = I(x) which is an intermediate reconstruction output of I" (note: this passage identifies I's output as x̂, an intermediate reconstruction, combined with the preceding citation identifying gs as the synthesis/decoder transform within I, this shows that the decompression/synthesis stage produces the intermediate reconstruction fed to the next stage.)]
training a training-based distance correction algorithm to generate a training estimated distance for positioning the training target end device from reconstructed data derived from the training decompressed positioning report; and [Lee, pg. 6 "we regard the outputs of I in Eq. (1) as an intermediate latent representation, x̂, which is fed into the quality enhancement sub-network Q" (note: Q's input is x̂, the fully decoded output of I, not the compressed latent.)]
computing a training distance estimation error by applying the loss function to the training estimated distance and a training real distance separating the training target end device from a training transmitter or a training receiver of the one or more training reference signals. [Krapež, pg. 6 "Measured and reference distances, azimuth and elevation angles were then used for the training of a feedforward neural network " (note: this discloses training against both the measurement and the ground truth, which necessarily requires computing their deviation);
Lee, pg. 6 "our architecture allows two sub-networks to be jointly optimized towards minimizing the total loss Eq. (1)." (note: Lee discloses applying the loss function, loss-minimization)]
The rationale to combine Rydén with Krapež and Lee is the same as per claim 3.
Per claim 5, Rydén, Krapež and Lee disclose claim 4.
Rydén further teaches: wherein the training-based compression algorithm and the training-based decompression algorithm form an autoencoder of a given code size that maps to a given compression level, the autoencoder comprising the training-based compression algorithm as an encoder and the training-based decompression algorithm as a decoder. [Rydén, column 11, line 15 "we define the encoding layer as the final layer in the encoder, (in FIG. 12, this corresponds to 1 node(neuron) for example). The value of the node(s) in the encoding layer is what the UE will signal to the network." (note: the number of nodes in the encoding layer is the code size, and it is the quantity transmitted, and is the encoder/decoder structure of the limitation.)]
Per claim 6, Rydén, Krapež and Lee disclose claim 5.
Rydén further teaches: wherein the given code size is selected from a set of two or more code sizes as a tradeoff between positioning latency and accuracy. [Rydén, column 9, line 64 "In case of multiple encoders (or compression functions) at the UE, the UE could receive an index from the location server of what encoder it should use for each network node." (note: this passage discloses a set of two or more selectable encoders and an index-based selection act.);
column 9, line 59 "More encoding layers enables better reconstruction of the CIR … with the drawback of more reporting overhead." (note: this passage discloses the accuracy/overhead tradeoff)]
Per claim 7, Rydén, Krapež and Lee disclose claim 6.
Rydén combined with Krapež does not expressly disclose, but with Lee does teach: wherein the two or more code sizes map to two or more compression levels, the joint training being performed for the two or more compression levels, the first set of trained parameters, the second set of trained parameters, and the third set of trained parameters being generated for the two or more code sizes. [Rydén, column 9, line 64 "In case of multiple encoders (or compression functions) at the UE, the UE could receive an index from the location server of what encoder it should use for each network node." (note: plural separately trained encoders, each indexed and selectable, are plural code sizes mapping to plural compression levels.)]
[Lee, pg. 11 "The values of N and M for different λ values are tabulated in Table 1" (note: N and M are Lee's channel/code-size parameters, and Table 1 tabulates eight distinct settings of them across different λ values.);
pg. 12 "For each quality metric, eight models were trained with different λ values." (note: eight separately jointly-trained models, each comprising the compression, decompression, and quality-enhancement (distance-correction analog) parameter sets trained together, are shown at eight distinct code-size settings, which therefore shows the "generated for the two or more code sizes" requirement using the same serial three-network structure relied upon for claims 3 and 4.)]
The rationale to combine Rydén with Krapež and Lee is the same as per claim 3.
Per claim 8, Rydén, Krapež and Lee disclose claim 3.
Rydén further teaches: wherein the processor is configured to send the first set of trained parameters to a positioning reports producer [Rydén, column 18, line 7 "transmitting 1903 a first set of one or more parameters indicating the determined compression function" (note: the encoder parameters are transmitted to the wireless device that will perform the compression (the positioning reports producer).)] and send the second set of trained parameters and the third set of trained parameters to a positioning reports consumer.
Rydén does not expressly disclose sending the second and third sets of trained parameters to a positioning reports consumer, though Rydén offers preconfiguration as an alternative, [Rydén, column 10, line 4 "The UE could also in one embodiment receive the decoder(s) from the location server, or the decoder(s) may be preconfigured at the UE"].
It would have been obvious to a person having ordinary skill in the art to send the second set of trained parameters and the third set of trained parameters to a positioning reports consumer, because Rydén already transmits the parameter set defining the compression function to the device that executes it [Rydén, column 18, line 1 “As shown in FIG. 19, the method 1900 may optionally comprise determining 1901 a compression function for compressing delay profiles of CIRs at the wireless device, determining 1902 the decompression function for decompressing delay profiles of CIRs which have been compressed by the wireless device using the compression function, and transmitting 1903 a first set of one or more parameters indicating the determined compression function.”] and expressly contemplates delivering a decompression function over the air to a device that needs it [Rydén, column 10, line 4 “The UE could also in one embodiment receive the decoder(s) from the location server, or the decoder(s) may be preconfigured at the UE.”]. Applying that same distribution step to the parameters the consumer executes is the combination of known elements according to known methods to yield predictable results (MPEP 2143(A)).
Claim 15-20 is substantially similar in scope and spirit to claim 3-8. Therefore, the rejection of claim 3-8 is applied respectively. Rydén further shows the apparatus being implemented by a method [Rydén, column 16, line 52 "FIG. 19 is a flow chart of a method 1900 performed by a network node." (note: this states the parameter-generating operations performed by the network node as method steps.)]
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Sayed M Shah whose telephone number is (571)272-9406. The examiner can normally be reached Monday-Friday 8:00 am - 4:00 pm.
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, Miranda Huang can be reached at (571) 270-7092. 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.
/SAYED MUNEER SHAH/Examiner, Art Unit 2124
/ALAN CHEN/Primary Examiner, Art Unit 2125
Prosecution Insights