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 .
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-12 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites, in the last element, “the one or trained neural networks.” This limitation lacks antecedent basis and should be changed to, “the one or more trained neural networks.”
Claim 7 recites “the neural networks.” This limitation lacks antecedent basis and should be changed to, “the one or more neural networks.” Alternatively, the claim could be amended to recite more than one neural network, as seen in Claim 2.
The dependent claims are rejected based on their dependence from Claim 1.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-8 and 10-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jornod et al. (US 20210297171 A1)[hereinafter “Jornod”] and Pickerd et al. (US 20220311513 A1)[hereinafter “Pickerd”].
Regarding Claims 1 and 13, Jornod discloses a test system [Paragraph [0080]](and corresponding method), comprising:
a repository of component models containing characteristic parameters for each component model [Paragraph [0038] – “FIGS. 1A and 1B show flow charts of exemplary embodiments of a method for predicting a future quality of service of a wireless communication link between a mobile transceiver 100 and a further mobile transceiver 102. The method comprises determining 110 a plurality of environmental models of one or more active transceivers 104 in the environment of the mobile transceiver over a plurality of points in time.”Paragraph [0044] – “In general, the environmental model of the one or more active transceivers may model the environment of the mobile transceivers with regards to a presence and/or a transmission activity of the one or more active transceivers.”];
one or more processors configured to execute code to cause the one or more processors [Paragraph [0080]] to:
receive a list of selected component models [Paragraph [0038] – “The method comprises determining 120 a predicted future environmental model of the one or more active transceivers at a point in time of the future using a time-series projection 125 on the plurality of environmental models.”] through a user interface to be tested as a combination [Paragraph [0032] – “Disclosed embodiments of the present disclosure further provide an apparatus for predicting a future quality of service of a wireless communication link between a mobile transceiver and a further mobile transceiver. The apparatus comprises one or more interfaces for communicating in a mobile communication system. The apparatus comprises a control module configured to carry out the above method.”]; and
access the characteristic parameters for each selected component model in the list [Paragraph [0038] – “The method comprises determining 120 a predicted future environmental model of the one or more active transceivers at a point in time of the future using a time-series projection 125 on the plurality of environmental models.”Paragraph [0038] – “The predicted future environmental model is used 135 as input to the machine-learning model.”].
Jornod fails to disclose that the one or more processors are configured to build a tensor image using the characteristic parameters for each selected component model.
However, Pickerd discloses performing machine learning using such tensor images [See Fig. 8 and Paragraph [0027] – “For recognizing FFE taps of the TX parameter settings, impulse response code sequences, i.e. short patterns, are pulled out and placed into the images input to the neural network 22. The term hyperspectral is used in the sense that the image input to deep learning neural network 22 has three color channels labeled as R, G, and B (red, green and blue). The waveforms making up these hyperspectral images are not actually in these colors, but rather the system uses the three color channels to incorporate the different images created by tensor builder. The system collects three waveforms and each of the images from each of the three waveforms goes into one of the color channels.”]. It would have been obvious to build such tensor images because doing so would have been effective in performing machine learning from the data sets.
Jornod, as modified, would disclose that the one or more processors are configured to send the tensor image to one or more trained neural networks [Paragraph [0038] – “The predicted future environmental model is used 135 as input to the machine-learning model.”Machine learning can be accomplished through use of a neural network, see Paragraph [0070].] to predict interoperability of the combination; and receive a prediction from the one or more trained neural networks about the combination [See Fig. 1B and Paragraph [0061] – “Correspondingly, the method may comprise determining 140 a quality of service of the wireless communication link at the plurality of points in time. In other words, for the plurality of points in time, the quality of service may be determined (in light of the one or more active transceivers in the environment of the mobile transceiver). For example, the quality of service may be determined by determining metrics of the wireless communication link, such as a packet inter-reception time, a packet error rate, a latency and/or a data rate of the wireless communication link.”].
Regarding Claims 2 and 14, Jornod discloses a neural network to provide a prediction of an operational margin [See Fig. 1B and Paragraph [0061] – “Correspondingly, the method may comprise determining 140 a quality of service of the wireless communication link at the plurality of points in time. In other words, for the plurality of points in time, the quality of service may be determined (in light of the one or more active transceivers in the environment of the mobile transceiver). For example, the quality of service may be determined by determining metrics of the wireless communication link, such as a packet inter-reception time, a packet error rate, a latency and/or a data rate of the wireless communication link.”Machine learning can be accomplished through use of a neural network, see Paragraph [0070].], but fails to disclose that the one or more neural networks comprise two neural networks, including a first neural network to provide a pass/fail prediction.
However, Pickerd discloses the use of such a neural network [Paragraph [0012] – “The use of a machine learning process can decrease the amount of time needed to tune, test and determine if a part passes or fails. The embodiments here use one or more neural networks to obtain the tuning parameters for optical transceivers to allow a determination of whether the transceiver operates correctly more quickly than current processes.”]. It would have been obvious to implement such a neural network as a supplement to the neural network of Jornod in order to be able to ascertain whether the transceiver network will work.
Regarding Claims 3 and 15, Jornod discloses that the code that causes the one or more processors to access the characteristic parameters for each selected component comprises code to cause the one or more processors to either access the characteristic parameters from the repository or access physical testing results [Paragraph [0038] – “The method comprises determining 120 a predicted future environmental model of the one or more active transceivers at a point in time of the future using a time-series projection 125 on the plurality of environmental models.”Paragraph [0044] – “In general, the environmental model of the one or more active transceivers may model the environment of the mobile transceivers with regards to a presence and/or a transmission activity of the one or more active transceivers.”].
Regarding Claim 4, Jornod discloses that the combination comprises one of a transmitter, a transmitter with a channel, a receiver with a transmitter, a receiver with a channel and a transmitter together, and a transmitter with a channel and with a receiver [Paragraph [0032] – “Disclosed embodiments of the present disclosure further provide an apparatus for predicting a future quality of service of a wireless communication link between a mobile transceiver and a further mobile transceiver. The apparatus comprises one or more interfaces for communicating in a mobile communication system. The apparatus comprises a control module configured to carry out the above method.”].
Regarding Claims 5 and 16, Jornod discloses that the one or more processors are further configured to provide a report of the predictions received for each combination [See Fig. 1B and Paragraph [0061] – “Correspondingly, the method may comprise determining 140 a quality of service of the wireless communication link at the plurality of points in time. In other words, for the plurality of points in time, the quality of service may be determined (in light of the one or more active transceivers in the environment of the mobile transceiver). For example, the quality of service may be determined by determining metrics of the wireless communication link, such as a packet inter-reception time, a packet error rate, a latency and/or a data rate of the wireless communication link.”].
Regarding Claims 6 and 17, Jornod discloses that the one or more processors are further configured to validate the predictions for those combinations for which the prediction is that the combination failed [See Fig. 1B and Paragraph [0061] – “Correspondingly, the method may comprise determining 140 a quality of service of the wireless communication link at the plurality of points in time. In other words, for the plurality of points in time, the quality of service may be determined (in light of the one or more active transceivers in the environment of the mobile transceiver). For example, the quality of service may be determined by determining metrics of the wireless communication link, such as a packet inter-reception time, a packet error rate, a latency and/or a data rate of the wireless communication link.” The determined metrics corresponding to the QoS serving to validate the QoS.].
Regarding Claims 7 and 18, Jornod discloses that the one or more processors are further configured to train the one or more neural networks [Paragraph [0038] – “The machine-learning model is trained to provide information on a predicted quality of service for a given environmental model.”Machine learning can be accomplished through use of a neural network, see Paragraph [0070].].
Regarding Claims 8 and 19, Pickerd (in combination with Jornod) would disclose that the one or more processors are further configured to train the one or more neural networks by executing code that causes the one or more processors to:
generate combinations from the component models in the repository [Paragraph [0038] of Jornod – “FIGS. 1A and 1B show flow charts of exemplary embodiments of a method for predicting a future quality of service of a wireless communication link between a mobile transceiver 100 and a further mobile transceiver 102. The method comprises determining 110 a plurality of environmental models of one or more active transceivers 104 in the environment of the mobile transceiver over a plurality of points in time.”Paragraph [0044] of Jornod – “In general, the environmental model of the one or more active transceivers may model the environment of the mobile transceivers with regards to a presence and/or a transmission activity of the one or more active transceivers.”];
build tensor images for each combination [See Fig. 8 and Paragraph [0027] of Pickerd – “For recognizing FFE taps of the TX parameter settings, impulse response code sequences, i.e. short patterns, are pulled out and placed into the images input to the neural network 22. The term hyperspectral is used in the sense that the image input to deep learning neural network 22 has three color channels labeled as R, G, and B (red, green and blue). The waveforms making up these hyperspectral images are not actually in these colors, but rather the system uses the three color channels to incorporate the different images created by tensor builder. The system collects three waveforms and each of the images from each of the three waveforms goes into one of the color channels.”];
generate ideal waveforms of each combination; apply filters and any noise to the ideal waveforms to produce simulated waveforms; make one or more measurements on the simulated waveforms to produce measurement results [Paragraph [0025] of Pickerd – “The user algorithm 40 tunes each of the Tx device samples for optimal tuning parameters which are then used to train the network to associate the optimal tuning parameters with a given waveform shape and characteristics such as temperature and scope noise. This association is always done using the same input reference tuning parameters stored in the Tx DUT during waveform acquisition.”]; and
provide the measurement results and tensor images for each combination to the one or more neural networks to train the one or more neural networks to associate each tensor image with a corresponding measurement result [Paragraph [0027] of Pickerd – “For recognizing FFE taps of the TX parameter settings, impulse response code sequences, i.e. short patterns, are pulled out and placed into the images input to the neural network 22. The term hyperspectral is used in the sense that the image input to deep learning neural network 22 has three color channels labeled as R, G, and B (red, green and blue). The waveforms making up these hyperspectral images are not actually in these colors, but rather the system uses the three color channels to incorporate the different images created by tensor builder. The system collects three waveforms and each of the images from each of the three waveforms goes into one of the color channels.”].
It would have been obvious to use such a technique in modelling the component combinations because doing so would have been effective in performing machine learning for their analysis.
Regarding Claim 10, Pickerd (in combination with Jornod) would disclose that the noise results from a transmitter component model [Paragraph [0025] of Pickerd – “The user algorithm 40 tunes each of the Tx device samples for optimal tuning parameters which are then used to train the network to associate the optimal tuning parameters with a given waveform shape and characteristics such as temperature and scope noise. This association is always done using the same input reference tuning parameters stored in the Tx DUT during waveform acquisition.”], such that combinations not including a transmitter will have no added noise [Inherent].
Regarding Claim 11, Jornod fails to disclose that the code that causes the one or more processors to make one or more measurements comprises code that causes the one or more processors to perform a pass/fail determination.
However, Pickerd discloses the use of such a neural network [Paragraph [0012] – “The use of a machine learning process can decrease the amount of time needed to tune, test and determine if a part passes or fails. The embodiments here use one or more neural networks to obtain the tuning parameters for optical transceivers to allow a determination of whether the transceiver operates correctly more quickly than current processes.”]. It would have been obvious to implement such a neural network as a supplement to the neural network of Jornod in order to be able to ascertain whether the transceiver network will work.
Regarding Claim 12, Jornod, as modified, would disclose that the code that causes the one or more processors to make one or more measurements comprises code to cause the one or more processors to perform an operational margin measurement [See Fig. 1B and Paragraph [0061] – “Correspondingly, the method may comprise determining 140 a quality of service of the wireless communication link at the plurality of points in time. In other words, for the plurality of points in time, the quality of service may be determined (in light of the one or more active transceivers in the environment of the mobile transceiver). For example, the quality of service may be determined by determining metrics of the wireless communication link, such as a packet inter-reception time, a packet error rate, a latency and/or a data rate of the wireless communication link.”].
Claim(s) 9 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jornod et al. (US 20210297171 A1)[hereinafter “Jornod”], Pickerd et al. (US 20220311513 A1)[hereinafter “Pickerd”], and Bromberg (US 20200057163 A1).
Regarding Claims 9 and 20, Jornod and Pickerd fail to disclose that the code that causes the one or more processors to apply filters and noise to the ideal waveforms causes the one or more processors, for each combination, to:
build an S-parameter model filter from S-parameters for the combination; and
combine the S-parameter model filter for the combination with the ideal waveforms for the combination, and with any noise for the combination to produce the simulated waveform for the combination.
However, Bromberg discloses performing an analysis regarding electromagnetic scattering (i.e., “S-parameters”)[Paragraph [0009] – “The direct path transmit waveform is isolated from the receivers via RF shielding, and delay filtering if needed (described below). If a change is detected in the environment, a position estimate is formed using Bayesian estimation with a likelihood function formed using a channel model that models the electromagnetic scattering over the presumed target type. The estimation is essentially performed using hypothesis testing on the target position, coupled with prior information about previous targets.”Paragraph [0010] – “Both the target type (shape or dielectric constants etc.) are determined by computing the Bayesian posterior probability of that type category. The Bayesian estimation is described below in Parameter Estaimation and Tracking. The channel model uses data obtained through careful calibration of both the antenna arrays, the antenna noise models, and the scattering type. The channel model is described in below in System Model and the calibration procedure is described in Calibration. A more detailed step by step description of the calibration process is illustrated in FIG. 4. Each target type must go through an independent calibration procedure, since the target type will determine the basis function coefficients.”].
It would have been obvious to build an S-parameter model filter from S-parameters for the combination; and combine the S-parameter model filter for the combination with the ideal waveforms for the combination, and with any noise for the combination to produce the simulated waveform for the combination [per Paragraph [0025] of Pickerd – “The user algorithm 40 tunes each of the Tx device samples for optimal tuning parameters which are then used to train the network to associate the optimal tuning parameters with a given waveform shape and characteristics such as temperature and scope noise. This association is always done using the same input reference tuning parameters stored in the Tx DUT during waveform acquisition.”] in order to better model the combinations.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Oliveira, A Gentle Introduction to Audio Classification With Tensorflow, Medium, 2021
Dymarsky et al., Tensor network to learn the wavefunction of data, arXiv, 2021
Krijestorac et al., Spatial Signal Strength Prediction using 3D Maps and Deep Learning, IEEE, 2021
Nguyen et al., Millimeter-Wave Received Power Prediction from Time-Series Images Using Deep Learning, IEEE, 5.16.2022
PANAGAKIS et al., Tensor Methods in Computer Vision and Deep Learning, IEEE, 2021
Seretis et al., Toward Physics-Based Generalizable Convolutional Neural Network Models for Indoor Propagation, IEEE, 1.5.2022
US 20230188394 A1 – COMMUNICATION SYSTEM
US 20230155704 A1 – GENERATIVE WIRELESS CHANNEL MODELING
US 20180232574 A1 – Systems And Methods For Transmitting And Receiving Data Using Machine Learning Classification
US 20200285983 A1 – DATA COMPRESSION AND COMMUNICATION USING MACHINE LEARNING
US 20190213504 A1 – PREDICTING WIRELESS ACCESS POINT RADIO FAILURES USING MACHINE LEARNING
US 20230144796 A1 – ESTIMATING DIRECTION OF ARRIVAL OF ELECTROMAGNETIC ENERGY USING MACHINE LEARNING
US 20190108445 A1 – NEURAL NETWORK TRANSFER LEARNING FOR QUALITY OF TRANSMISSION PREDICTION
US 20150195216 A1 – USING LEARNING MACHINE-BASED PREDICTION IN MULTI-HOPPING NETWORKS
US 20210389373 A1 – SYSTEM AND METHOD FOR MULTI-LEVEL SIGNAL CYCLIC LOOP IMAGE REPRESENTATIONS FOR MEASUREMENTS AND MACHINE LEARNING
US 20220101118 A1 – BANK-BALANCED-SPARSE ACTIVATION FEATURE MAPS FOR NEURAL NETWORK MODELS
US 20220407595 A1 – DEVICES, SYSTEMS, AND METHODS FOR PROCESSING OPTICAL COMPONENTS
US 20240113795 A1 – WIRELESS CHANNEL RENDERING USING NEURAL NETWORKS
US 5720003 A – Method And Apparatus For Determining The Accuracy Limit Of A Learning Machine For Predicting Path Performance Degradation In A Communications Network
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KYLE ROBERT QUIGLEY whose telephone number is (313)446-4879. The examiner can normally be reached 9AM-5PM EST.
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, Arleen Vazquez can be reached at (571) 272-2619. 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.
/KYLE R QUIGLEY/Primary Examiner, Art Unit 2857