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 Objections
Claim 9 and 21 are objected to because of the following informalities: the use of maximum number of iterations is exceeded. Appropriate correction is required. It should be maximum number of iterations is met
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 5-7, 10, 12-13, 16-18, 22, are rejected under 102 (a)(1) as being unpatentable over Yin et al (NPL: Predicting Channel Quality Indicators for 5G Downlink Scheduling in a Deep Learning Approach) (“Yin”)
Regarding Claim 1, Yin teaches A method, implemented in a wireless transmit and receive unit (WTRU), the method comprising: receiving, from a base station, a first message comprising a set of reference signals ([Page 3-Column 1: 17-21] teaches learning features about the channel when a user attaches to a base station, and that is being interpreted as reference signals sent from a base station which teaches this limitation)
Training a neural network based on the first message ([Page 3-Column 1: 19-21] teaches training a neural network from the signal)
Determining a quality indicator value based on a neural network loss of demodulation using the set of reference signals ([Page 3-Column 1:17-21] teaches maintaining a channel quality indicator prediction from the base station, and this is later used for the neural network to learn the channel features and provide a reliable prediction. Channel quality indicator would include the process of demodulation with this process restarting to train if the prediction accuracy starts to drop. That is being interpreted as a neural network loss of demodulation using the set of reference signals.
Wherein deploying the trained neural network for use in connection with demodulating at least one symbol comprises predicting a modulation and coding scheme (MCS) ([Page 2 Column 1: 27-29] teaches that the MCS is calculated by the CQI value and CQI would include demodulation. [Page 3 Column 1: 19-22] teaches training a neural network and once it properly learns the features of the channel state it provides a reliable prediction and the training is then stopped. This is being interpreted of deploying a neural network that is used for MCS prediction)
Regarding Claim 5, Yin teaches all the limitations of Claim 1
Yin also teaches in response to or for as long as one or more subsequently computed quality indicator values fail to satisfy the quality indicator threshold, re-training the trained neural network ([Page 3 Column 1: 19-26] discusses a process of training and adjusting a pre-trained model by using the channel quality indicator. And after successfully learning from those CQI it stops training. But when those conditions with the channel changes effecting the quality it will train the model again. That process is being interpreted as retraining neural network model after failing to meet the quality indicator)
Regarding Claim 6, Yin teaches all the limitations of Claim 5
Yin also teaches, receiving, from the base station, a second message comprising another set of reference signals ([Page 3-Column 1: 22-26] teaches determining the predication accuracy drop when channel conditions begin to change due to the environment or user behavior. This is being interpreted as another set of reference signals)
Re-training the trained neural network based on the second message ([Page 3-Column 1: 25-26] teaches when the prediction accuracy begins to drop rapidly restart the model training)
And computing another quality indicator value based on another neural network loss of demodulation using the other set of reference signals ([Page 3: 33-40] teaches receiving another real CQI value which is being interpreted as another quality indicator value)
Regarding Claim 7, Yin teaches all the limitations of Claim 5
Yin also teaches computing error values for one or more nodes of the re-trained neural network ([Page 3 Column 1: 26-32] teaches the reason for retraining the model, which is based off of a weighted mean square error, the use of MSE here is being interpreted as calculated error values of the nodes of the re-trained neural network.
And transmitting, to the base station, a third message comprising information error values for one or more nodes of the re-trained neural network ([Page 3-Column 1: 33-43] teaches using the MSE to determine if the model needs to be retained or not, the results of the MSE here is being interpreted as a message comprising the error values of the retrained neural network)
Regarding Claim 10, Yin teaches all the limitations of Claim 1
Yin also teaches wherein training the neural network comprises updating one or more neural network parameters based on the set of reference signals ([Page 3-Column 1: 22-26] teaches the model is being retrained with the latest date to converge again due to accuracy loss. The updating of the latest date is being interpreted as a parameter with the accuracy drop being the reference signal. Which would teach this limitation)
Regarding Claim 12, Yin teaches the method comprising: receiving, from a base station, a first message comprising a first set of reference signals ([Page 3- Column 1: 17-21] teaches learning features about the channel when a user attaches to a base station, and that is being interpreted as reference signals sent from a base station which teaches this limitation)
Training a neural network, NN, based on the first message ([age 3-Column 1: 19-21] teaches training a neural network from the signal)
Determining a first quality indicator value based on a neural network loss of demodulation using the first set of reference signals; ([Page 3-Column 1:17-21] teaches maintaining a channel quality indicator prediction from the base station, and this is later used for the neural network to learn the channel features and provide a reliable prediction. Channel quality indicator would include the process of demodulation with this process restarting to train if the prediction accuracy starts to drop. That is being interpreted as a neural network loss of demodulation using the set of reference signals.
Based on the first quality indicator value failing to satisfy a quality indicator threshold value: transmitting to the base station, a second message comprising information indicating the first quality indicator value, receiving, from the base station, a third message comprising a second set of reference signals, and re-training the NN based on the second set of reference signals ([Page 3-Column 1: 22-32] teaches that when the accuracy drops due to user behavior or environment changes to retrain the model. That is being interpreted as a failing quality indicator and then the model is retrained until the prediction result is better than the current time series based on the MSE. Knowing that the predication is failing and needs to be re-trained is being interpreted as message containing the first quality indicator value. The signals constantly being used to ensure the predication accuracy is stable is being interpreted as reference signals that can be used to retrain the model which would teach this limitation.)
Determining a second quality indicator based on a NN loss of demodulation using the second set of reference signals; ([Page 3] teaches receiving another real CQI value which is being interpreted as another quality indicator value)
And based on the second quality indicator value satisfying the quality indicator threshold value, deploying the re-trained neural network for use in connection with demodulating at least one symbol ([Page 3-Column 1: 37-43] teaches retraining a neural network and ending training when the prediction result is back to being better than the current series. That new predication result is interpreted as a second quality indicator value and when the predication result is greater than the current time series stop training the model. With the model still being used after training to provide reliable predications that is being interpreted as a deploying the retrained model. The CQI prediction would contain some demodulation which would teach this limitation)
Regarding Claim 13, See the analysis of Claim 1
Regarding Claim 16, See the analysis of Claim 5
Regarding Claim 17, See the analysis of Claim 6
Regarding Claim 18, See the analysis of Claim 7
Regarding Claim 22, See the analysis of Claim 10
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.
Claims 2 and 14 are rejected under 103 as being unpatentable over (NPL: Predicting Channel Quality Indicators for 5G Downlink Scheduling in a Deep Learning Approach) (“Yin”) in view of Futagi et al (US10225042B2) (“Futagi”)
Regarding Claim 2, Yin teaches all the limitations of Claim 1.
Yin does not teach based on the quality indicator value failing to satisfy the quality indicator threshold value utilizing any of conventional modulation and coding scheme and alternative MCS
However, Futagi does teach based on the quality indicator value failing to satisfy the quality indicator threshold value utilizing any of conventional modulation and coding scheme and alternative MCS ([Column 5:50-60] Teaches selecting a lower MCS when the received transmission quality is poorer than expected. The quality being poorer than expected is being interpreted as having a quality threshold and the defaulting to another MCS is interpreted as a utilizing any MCS and an alternative MCS)
Yin and Futagi are analogous art because they both deal with transmissions and CQI
It would have been obvious to ta person skilled in the art before the effective filling date of the claimed invention to combine Yin with the lower MCS defaulting of Futagi. Doing so would allow for an improvement of data channel throughput ([Futagi-Brief Summary] “The radio transmission method of an embodiment includes: a switching step of switching associations between channel quality indicators and modulation and coding schemes according to a parameter of radio communication terminal apparatus; a modulation and coding scheme selection step of determining a modulation and coding scheme of a control channel based on the associations after the switching; and a coding and modulation step of encoding and modulating control data by the determined modulation and coding scheme. An embodiment provides an advantage of improving data channel throughput”)
Regarding Claim 14, See the analysis of Claim 2
Claims 8 and 20 are rejected under 103 as being unpatentable over (NPL: Predicting Channel Quality Indicators for 5G Downlink Scheduling in a Deep Learning Approach) (“Yin”) in view of Kwan et al (JP2003507960) (“Kwan”)
Regarding Claim 8 Yin teaches all the limitations of Claim 5
Yin does not teach receiving, from the base station, a fourth message comprising information indicating a maximum number of iterations for re-training neural network, wherein re-training the trained neural network comprises re-training the trained neural network up to the maximum number of iterations
However, Kwan does teach receiving, from the base station, a fourth message comprising information indicating a maximum number of iterations for re-training neural network, wherein re-training the trained neural network comprises re-training the trained neural network up to the maximum number of iterations ([Page 14 31-34 & Page 15 1-3] teaches after certain number of repetitions has been exceeded for determining the MCS which teaches this limitation and then when those iterations are exceeded the lowest order MCS is selected which teaches this limitation)
Yin and Kwan are analogous art because they both deal with MCS and transmissions
It would have been obvious to ta person skilled in the art before the effective filling date of the claimed invention to combine Yin with the repetitions of Kwan. Doing so would allow for more efficient packet scheduling ([Page 3: 15-21] “Although scheduling for adaptive modulation and coding has already been considered for wireless communications, there has been no concrete proposal yet advanced for a packet scheduling algorithm that optimizes the user throughput based on the selection of the number of Orthogonal Variable Spreading Factor (OVSF) codes in conjunction with the modulation and (error correcting) coding scheme (MCS) in a WCDMA network. Moreover, there has not been any recognition of the need for signaling an appropriate power level based on such an optimization”)
Regarding Claim 20, See the analysis of Claim 8
Claims 9 and 21 are rejected under 103 as being unpatentable over (NPL: Predicting Channel Quality Indicators for 5G Downlink Scheduling in a Deep Learning Approach) (“Yin”) in view of Kwan et al (JP2003507960) (“Kwan”) and Futagi et al (US10225042B2) (“Futagi”)
Regarding Claim 9, Yin and Kwan teaches all the limitations of Claim 8.
Yin does not teach on condition that maximum number of iterations is exceeded and a quality indicator value fails to satisfy the quality indicator threshold value, deploying any of a conventional MCS and an alternative MCS
However, Futagi does teach on condition that maximum number of iterations is exceeded and a quality indicator value fails to satisfy the quality indicator threshold value, deploying any of a conventional MCS and an alternative MCS ([Column 5: 50-60] Teaches selecting a lower MCS when the received transmission quality is poorer than expected. The quality being poorer than expected is being interpreted as having a quality threshold and the defaulting to another MCS is interpreted as a utilizing any MCS and an alternative MCS)
Yin, Kwan, and Futagi are analogous art because they both deal with they both deal with transmissions and MCS
It would have been obvious to ta person skilled in the art before the effective filling date of the claimed invention to combine Yin with the repetitions of Kwan and the Yin with the lower MCS defaulting of Futagi. Doing so would allow for an improvement of data channel throughput ([Futagi-Brief Summary] “The radio transmission method of an embodiment includes: a switching step of switching associations between channel quality indicators and modulation and coding schemes according to a parameter of radio communication terminal apparatus; a modulation and coding scheme selection step of determining a modulation and coding scheme of a control channel based on the associations after the switching; and a coding and modulation step of encoding and modulating control data by the determined modulation and coding scheme. An embodiment provides an advantage of improving data channel throughput”)
Regarding Claim 21, See the analysis of Claim 9
Conclusion
The prior arts are made of record and relied upon is considered to applicant’s disclosure
Kulkarni et al DeepChannel: Wireless Channel Quality Prediction Using Deep Learning (28 October, 2019) ([Abstract] “Accurately modeling and predicting wireless channel quality variations is essential for a number of networking applications such as scheduling and improved video streaming over 4G LTE networks and bit rate adaptation for improved performance in WiFi networks. In this paper, we design DeepChannel, an encoder-decoder based sequence-to-sequence deep learning model that is capable of predicting future wireless signal strength variations based on past signal strength data. We consider two different versions of DeepChannel; the first and second versions use LSTM and GRU as their basic cell structure, respectively. In contrast to prior work that is primarily focused on designing models for particular network settings, DeepChannel is highly adaptable and can predict future channel conditions for different networks, sampling rates, mobility patterns, and communication standards. We compare the performance (i.e., the root mean squared error, mean absolute error and relative error of future predictions) of DeepChannel with respect to two baselines-i) linear regression, and ii) ARIMA for multiple networks and communication standards. In particular, we consider 4G LTE, WiFi, WiMAX, an industrial network operating in the 5.8 GHz range, and Zigbee networks operating under varying levels of user mobility and observe that DeepChannel provides significantly superior performance. Finally, we provide a detailed discussion of the key design decisions including insights into hyper-parameter tuning and the applicability of our model in other networking scenarios”)
Givehchian et al US 20220357419 A1 (2021-05-07) ([Abstract] Methods and systems for generating map information of an environment using channel state information (CSI) of wireless signals received by access points (APs) in the environment are disclosed. In some implementations, a system uses CSI of a wireless signal received by a respective AP to determine a time-of-flight (ToF) and an angle-of-arrival (AoA) of one or more reflected path signal components of the wireless signal, and estimates the locations of points or surfaces in an area of the respective AP based on the ToF and AoA of the reflected path signal components. The estimated locations of the points or surfaces can be used to generate map information for the area. The system aggregates map information generated for different areas of the environment to determine map information for the entire environment. The wireless signals may be received from wireless stations or user equipment, or may be received from the respective AP.”)
Kumar et al US 20210337398 A1 ([Abstract] Various embodiments include methods for autonomous beam switching by a wireless device. A processor of the wireless device may measure signal parameters of signals received from a first synchronization signal block (SSB) beam of a base station monitored by the wireless device and other SSB beams of the base station, determine whether a difference in measured signal parameters of signals received from the first SSB beam and another SSB beam of the base station satisfies a signal quality difference threshold, and autonomously switching to the second SSB beam as the serving beam in response to determining that the difference in the measured signal parameters of signals received from the first SSB beam and a second SSB beam satisfies the signal quality difference threshold. The signal quality difference threshold may be listed in a table in memory or determined via machine learning.”)
Pati et al A Novel Machine Learning Approach for Link Adaptation in 5G Wireless Networks (11 January 2021) ([Abstract] “This study addresses a Machine Learning (ML) based Link Adaptation (LA) scheme for 5G New Radio (NR) wireless networks, which aims to improve the system throughput by selecting the best possible choice of the Modulation Coding Scheme (MCS). This work proposes a Deep Neural Network (DNN) based regression model to maximize the Spectral Efficiency (SE) of the system under the 10% Block Error Rate (BLER) and thus finding the best MCS. We consider a 5G NR Frequency Range-1(FR-1), i.e., the Sub-6GHz operating band for the study. Our simulation results show the mapping of Signal to Interference and Noise Ratio (SINR) to the Channel Quality Indicator (CQI) and thus the best possible selection of modulation and coding scheme in case of perfect channel estimation based system which is found to improve the system throughput.”)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to URIAH V MOORE whose telephone number is (571)384-8341. The examiner can normally be reached Monday-Friday 8am-5pm.
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, Mariela Reyes can be reached at (571)270-1006. 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.
/URIAH VENDELL MOORE/Examiner, Art Unit 2142 /Mariela Reyes/Supervisory Patent Examiner, Art Unit 2142
Prosecution Insights