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 .
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 2-28 rejected on the ground of nonstatutory double patenting as being unpatentable over claim1-20 of US 12061982. Although the claims at issue are not identical, they are not patentably distinct from each other because all the claims in the pending Application are transparently found in US 12061982 with obvious wording variations. See the table below for comparison:
Pending Application 18799049
US 12061982
2. A system comprising: one or more processors; and memory storing instructions that are operable, when executed by the one or more processors, to cause the one or more processors to perform operations comprising: providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors; controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals; providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer; obtaining, as an output of the signal transformer, a transformed version of the radio signals; providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors.
3. The system of claim 2, wherein the operations comprise: converting one or more radio signals detected by a radio sensor to digital data, wherein the representation of the radio signals includes digital data.
4. The system of claim 2, wherein providing the representation of the radio signals to the first machine learning network comprises: providing the representation of the radio signals to a neural network that is trained to estimate parameters of the radio signals.
5. The system of claim 2, wherein controlling the first machine learning network to generate the output that comprises estimated parameters of the radio signals comprises: controlling the first machine learning network to generate parameters indicating one or more of the following: timing information, frequency, center frequency, bandwidth, phase, rate of arrival, direction of arrival, offset, or channel state information associated with the radio signals.
6. The system of claim 5, wherein controlling the first machine learning network to generate parameters indicating channel state information associated with the radio signals comprises: controlling the first machine learning network to generate parameters indicating a channel delay response of at least one of the radio signals.
11. The system of claim 2, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using a canonicalized input obtained in the output of the signal transformer, or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal.
12. The system of claim 11, wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector.
13. The system of claim 2, wherein the operations comprise: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset.
14. The system of claim 2, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region.
1. A system to process one or more radio signals, the system comprising: one or more processors; and one or more computer readable media storing computer code that, when executed by the one or more processors, is configured to perform a plurality of operations, the operations comprising: providing, to a signal transformer, first data that includes channel state information describing a characteristic of a channel used for communicating a radio signal; generating, by the signal transformer and based on the first data including the channel state information describing the characteristic of the channel used for communicating the radio signal, second data representing a transformed radio signal, wherein generating the second data representing the transformed radio signal includes applying one or more transforms to the first data representing the radio signal; providing the second data representing the transformed radio signal to a machine learning model that is configured to generate output data describing the radio signal based on processing the second data representing the transformed radio signal; and obtaining output data generated by the machine learning model based on processing the second data representing the transformed radio signal, wherein the output data is configured to enable a radio signal receiver to infer additional information corresponding to one or more emitters of the radio signal based on processing the output data.
3. The system of claim 1, wherein the output data generated by the machine learning model based on processing the second data representing the transformed radio signal comprises one or more of signal labels, modulation type, protocol, symbol values, data bits, or data code-words.
7. The system of claim 1, wherein the operations comprise: obtaining a portion of the first data, that includes channel state information associated with the radio signal, generated by a second machine learning model different than the machine learning model that generates the output data.
7. The system of claim 2, wherein the operations comprise: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms include at least one of the following: an affine transform, an oscillator, a mixer, a multiplier, or a convolution with a parametric set of filter taps.
8. The system of claim 2, wherein the operations comprise: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms are configured to invert effects of the radio signals.
10. The system of claim 2, wherein providing the transformed version of the radio signals as input to the second machine learning network comprises one of: providing the transformed version of the radio signals to a model for regression using a neural network, or providing the transformed version of the radio signals to a model for classification using a neural network.
5. The system of claim 1, wherein generating the second data representing the transformed radio signal comprises: generating the second data representing the transformed radio signal using one or more parametric transforms.
6. The system of claim 1, wherein generating the second data representing the transformed radio signal comprises: generating the second data representing the transformed radio signal using one or more parametric transforms prior to using one or more non-parametric transforms.
9. The system of claim 8, wherein inverting the effects of the radio signals comprises inverting effects of physics acting on the radio signals during transmission or detection.
2. The system of claim 1, wherein the channel state information comprises one or more values representing a channel delay response.
15. A method comprising: providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors; controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals; providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer; obtaining, as an output of the signal transformer, a transformed version of the radio signals; providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors.
16. The method of claim 15, comprising: converting one or more radio signals detected by a radio sensor to digital data, wherein the representation of the radio signals includes digital data.
17. The method of claim 15, wherein providing the representation of the radio signals to the first machine learning network comprises: providing the representation of the radio signals to a neural network that is trained to estimate parameters of the radio signals.
18. The method of claim 15, wherein controlling the first machine learning network to generate the output that comprises estimated parameters of the radio signals comprises: controlling the first machine learning network to generate parameters indicating one or more of the following: timing information, frequency, center frequency, bandwidth, phase, rate of arrival, direction of arrival, offset, or channel state information associated with the radio signals.
19. The method of claim 18, wherein controlling the first machine learning network to generate parameters indicating channel state information associated with the radio signals comprises: controlling the first machine learning network to generate parameters indicating a channel delay response of at least one of the radio signals.
24. The method of claim 15, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using a canonicalized input obtained in the output of the signal transformer, or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal.
26. The method of claim 15, comprising: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset.
27. The method of claim 15, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region.
8. A method for processing one or more radio signals, the method comprising: providing, to a signal transformer, first data that includes channel state information associated with describing a characteristic of a channel used for communicating a radio signal; generating, by the signal transformer and based on the first data including the channel state information describing the characteristic of the channel used for communicating the radio signal, second data representing a transformed radio signal, wherein generating the second data representing the transformed radio signal includes applying one or more transforms to the first data representing the radio signal; providing the second data representing the transformed radio signal to a machine learning model that is configured to generate output data describing the radio signal based on processing the second data representing the transformed radio signal; and obtaining output data generated by the machine learning model based on processing the second data representing the transformed radio signal, wherein the output data is configured to enable a radio signal receiver to infer additional information corresponding to one or more emitters of the radio signal based on processing the output data.
10. The method of claim 8, wherein the output data generated by the machine learning model based on processing the second data representing the transformed radio signal comprises one or more of signal labels, modulation type, protocol, symbol values, data bits, or data code-words.
14. The method of claim 8, comprising: obtaining a portion of the first data, that includes channel state information associated with the radio signal, generated by a second machine learning model different than the machine learning model that generates the output data.
20. The method of claim 15, comprising: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms include at least one of the following: an affine transform, an oscillator, a mixer, a multiplier, or a convolution with a parametric set of filter taps.
21. The method of claim 15, comprising: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms are configured to invert effects of the radio signals.
12. The method of claim 8, wherein generating the second data representing the transformed radio signal comprises: generating the second data representing the transformed radio signal using one or more parametric transforms.
13. The method of claim 8, wherein generating the second data representing the transformed radio signal comprises: generating the second data representing the transformed radio signal using one or more parametric transforms prior to using one or more non-parametric transforms.
22. The method of claim 21, wherein inverting the effects of the radio signals comprises inverting effects of physics acting on the radio signals during transmission or detection.
9. The method of claim 8, wherein the channel state information comprises one or more values representing a channel delay response.
23. The method of claim 15, wherein providing the transformed version of the radio signals as input to the second machine learning network comprises one of: providing the transformed version of the radio signals to a model for regression using a neural network, or providing the transformed version of the radio signals to a model for classification using a neural network.
10. The method of claim 8, wherein the output data generated by the machine learning model based on processing the second data representing the transformed radio signal comprises one or more of signal labels, modulation type, protocol, symbol values, data bits, or data code-words.
25. The method of claim 24, wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector.
10. The method of claim 8, wherein the output data generated by the machine learning model based on processing the second data representing the transformed radio signal comprises one or more of signal labels, modulation type, protocol, symbol values, data bits, or data code-words.
28. One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising: providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors; controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals; providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer; obtaining, as an output of the signal transformer, a transformed version of the radio signals; providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors.
15. A non-transitory computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising: providing, to a signal transformer, first data that includes channel state information describing a characteristic of a channel used for communicating a radio signal; generating, by the signal transformer and based on the first data including the channel state information describing the characteristic of the channel used for communicating the radio signal, second data representing a transformed radio signal, wherein generating the second data representing the transformed radio signal includes applying one or more transforms to the first data representing the radio signal; providing the second data representing the transformed radio signal to a machine learning model that is configured to generate output data describing the radio signal based on processing the second data representing the transformed radio signal; and obtaining output data generated by the machine learning model based on processing the second data representing the transformed radio signal, wherein the output data is configured to enable a radio signal receiver to infer additional information corresponding to one or more emitters of the radio signal based on processing the output data.
Claims 2-28 rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-32 of US 11468317. Although the claims at issue are not identical, they are not patentably distinct from each other because all the claims in the pending Application are transparently found in US 11468317 with obvious wording variations. See the table below for comparison:
Pending Application 18799049
US 11468317
2. A system comprising: one or more processors; and memory storing instructions that are operable, when executed by the one or more processors, to cause the one or more processors to perform operations comprising: providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors; controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals; providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer; obtaining, as an output of the signal transformer, a transformed version of the radio signals; providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors.
4. The system of claim 2, wherein providing the representation of the radio signals to the first machine learning network comprises: providing the representation of the radio signals to a neural network that is trained to estimate parameters of the radio signals.
8. The system of claim 2, wherein the operations comprise: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms are configured to invert effects of the radio signals.
9. The system of claim 8, wherein inverting the effects of the radio signals comprises inverting effects of physics acting on the radio signals during transmission or detection.
27. The method of claim 15, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region.
12. A system to process one or more radio signals, the system comprising: one or more processors; and one or more computer readable media storing computer code that, when executed by the one or more processors, is configured to perform a plurality of operations, the operations comprising: providing a first set of input data representing one or more radio signals to a first machine learning model, wherein the first machine learning model is configured to generate output data based on processing, by the first machine learning model, input data representing one or more radio signals, the generated output data including data representing an estimation of one or more characteristics of a radio signal; obtaining first output data generated by the first machine learning model based on processing, by the first machine learning model, the first set of input data representing the one or more radio signals; providing, to a signal transformer, a second set of input data that includes (i) the first set of input data and (ii) the obtained first output data generated by the first machine learning model; generating, by the signal transformer and based on the second set of input data, data representing a transformed radio signal, wherein generating the data representing the transformed radio signal includes applying one or more transforms to the first set of input data representing the one or more radio signals; providing the data representing the transformed radio signal to a second machine learning model that is configured to generate output data describing the one or more radio signals based on processing the data representing the transformed radio signal; and obtaining second output data generated by the second machine learning model based on the second machine learning model processing the data representing the transformed radio signal, wherein the second output data is configured for interpretation by an application at a receiver, wherein the application is configured to infer additional information related to one or more emitters of the one or more radio signals based on the second output data.
3. The system of claim 2, wherein the operations comprise: converting one or more radio signals detected by a radio sensor to digital data, wherein the representation of the radio signals includes digital data.
13. The system of claim 12, the operations further comprising: detecting, using one or more sensors, the one or more radio signals; and generating, using an analog-to-digital converter, the first set of input data representing the one or more radio signals, wherein the first set of input data includes a digital representation of the one or more radio signals.
5. The system of claim 2, wherein controlling the first machine learning network to generate the output that comprises estimated parameters of the radio signals comprises: controlling the first machine learning network to generate parameters indicating one or more of the following: timing information, frequency, center frequency, bandwidth, phase, rate of arrival, direction of arrival, offset, or channel state information associated with the radio signals.
6. The system of claim 5, wherein controlling the first machine learning network to generate parameters indicating channel state information associated with the radio signals comprises: controlling the first machine learning network to generate parameters indicating a channel delay response of at least one of the radio signals.
14. The system of claim 12, wherein the obtained first output data generated by the first machine learning model represents one or more characteristics of the one or more radio signals or its corresponding channel state information, wherein the one or more characteristics of the one or more radio signals or its corresponding channel state information include (i) estimates of timing information, (ii) center frequency, (iii) bandwidth, (iv) phase, (v) frequency and rate of arrival, (vi) direction of arrival, (vii) channel delay response, or (viii) offset of a particular radio signal.
7. The system of claim 2, wherein the operations comprise: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms include at least one of the following: an affine transform, an oscillator, a mixer, a multiplier, or a convolution with a parametric set of filter taps.
15. The system of claim 12, wherein the one or more transforms include one or more of (i) an affine transform, (ii) an oscillator and mixer, (iii) a filter application, (iv) resampling, (v) sub-band tuning, or (vi) a convolution with a set of filter taps.
10. The system of claim 2, wherein providing the transformed version of the radio signals as input to the second machine learning network comprises one of: providing the transformed version of the radio signals to a model for regression using a neural network, or providing the transformed version of the radio signals to a model for classification using a neural network.
17. The system of claim 12, wherein the second output data generated by the second machine learning model includes one or more of (i) data describing signal labels, (ii) modulation type, (iii) protocol, (iv) wireless standards, (v) equipment type, (vi) symbol values, (vii) data bits, (viii) data code-words, or (ix) estimated radio signal values representing the one or more radio signals.
11. The system of claim 2, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using a canonicalized input obtained in the output of the signal transformer, or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal.
17. The system of claim 12, wherein the second output data generated by the second machine learning model includes one or more of (i) data describing signal labels, (ii) modulation type, (iii) protocol, (iv) wireless standards, (v) equipment type, (vi) symbol values, (vii) data bits, (viii) data code-words, or (ix) estimated radio signal values representing the one or more radio signals.
20. The system of claim 12, wherein the one or more radio signals are synchronized using the combination of the first machine learning model and the one or more transforms to produce a set of canonicalized encoded information representing the one or more radio signals.
12. The system of claim 11, wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector.
17. The system of claim 12, wherein the second output data generated by the second machine learning model includes one or more of (i) data describing signal labels, (ii) modulation type, (iii) protocol, (iv) wireless standards, (v) equipment type, (vi) symbol values, (vii) data bits, (viii) data code-words, or (ix) estimated radio signal values representing the one or more radio signals.
13. The system of claim 2, wherein the operations comprise: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset.
14. The system of claim 12, wherein the obtained first output data generated by the first machine learning model represents one or more characteristics of the one or more radio signals or its corresponding channel state information, wherein the one or more characteristics of the one or more radio signals or its corresponding channel state information include (i) estimates of timing information, (ii) center frequency, (iii) bandwidth, (iv) phase, (v) frequency and rate of arrival, (vi) direction of arrival, (vii) channel delay response, or (viii) offset of a particular radio signal.
18. The system of claim 12, the operations further comprising: providing the second output data to another device that is configured to use the second output data to adjust one or more communications systems.
14. The system of claim 2, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region.
19. The system of claim 18, wherein the inferred additional information can include information related to (i) a location of one or more emitters, (ii) a movement of one or more emitters, (iii) a behavior of one or more emitters, or (iv) a pattern of life of one or more emitters.
15. A method comprising: providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors; controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals; providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer; obtaining, as an output of the signal transformer, a transformed version of the radio signals; providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors.
17. The method of claim 15, wherein providing the representation of the radio signals to the first machine learning network comprises: providing the representation of the radio signals to a neural network that is trained to estimate parameters of the radio signals.
21. The method of claim 15, comprising: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms are configured to invert effects of the radio signals.
22. The method of claim 21, wherein inverting the effects of the radio signals comprises inverting effects of physics acting on the radio signals during transmission or detection.
1. A method for processing one or more radio signals, the method comprising: providing a first set of input data representing one or more radio signals to a first machine learning model, wherein the first machine learning model is configured to generate output data based on processing, by the first machine learning model, input data representing one or more radio signals, the generated output data including data representing an estimation of one or more characteristics of a radio signal; obtaining first output data generated by the first machine learning model based on processing, by the first machine learning model, the first set of input data representing the one or more radio signals; providing, to a signal transformer, a second set of input data that includes (i) the first set of input data and (ii) the obtained first output data generated by the first machine learning model; generating, by the signal transformer and based on the second set of input data, data representing a transformed radio signal, wherein generating the data representing the transformed radio signal includes applying one or more transforms to the first set of input data representing the one or more radio signals; providing the data representing the transformed radio signal to a second machine learning model that is configured to generate output data describing the one or more radio signals based on processing the data representing the transformed radio signal; and obtaining second output data generated by the second machine learning model based on the second machine learning model processing the data representing the transformed radio signal, wherein the second output data is configured for interpretation by an application at a receiver, wherein the application is configured to infer additional information related to one or more emitters of the one or more radio signals based on the second output data.
16. The method of claim 15, comprising: converting one or more radio signals detected by a radio sensor to digital data, wherein the representation of the radio signals includes digital data.
2. The method of claim 1, the method further comprising: detecting, using one or more sensors, the one or more radio signals; and generating, using an analog-to-digital converter, the first set of input data representing the one or more radio signals, wherein the first set of input data includes a digital representation of the one or more radio signals.
18. The method of claim 15, wherein controlling the first machine learning network to generate the output that comprises estimated parameters of the radio signals comprises: controlling the first machine learning network to generate parameters indicating one or more of the following: timing information, frequency, center frequency, bandwidth, phase, rate of arrival, direction of arrival, offset, or channel state information associated with the radio signals.
19. The method of claim 18, wherein controlling the first machine learning network to generate parameters indicating channel state information associated with the radio signals comprises: controlling the first machine learning network to generate parameters indicating a channel delay response of at least one of the radio signals.
3. The method of claim 1, wherein the obtained first output data generated by the first machine learning model represents one or more characteristics of the one or more radio signals or its corresponding channel state information, wherein the one or more characteristics of the one or more radio signals or its corresponding channel state information include (i) estimates of timing information, (ii) center frequency, (iii) bandwidth, (iv) phase, (v) frequency and rate of arrival, (vi) direction of arrival, (vii) channel delay response, or (viii) offset of a particular radio signal.
20. The method of claim 15, comprising: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms include at least one of the following: an affine transform, an oscillator, a mixer, a multiplier, or a convolution with a parametric set of filter taps.
4. The method of claim 1, wherein the one or more transforms include one or more of (i) an affine transform, (ii) an oscillator and mixer, (iii) a filter application, (iv) resampling, (v) sub-band tuning, or (vi) a convolution with a set of filter taps.
23. The method of claim 15, wherein providing the transformed version of the radio signals as input to the second machine learning network comprises one of: providing the transformed version of the radio signals to a model for regression using a neural network, or providing the transformed version of the radio signals to a model for classification using a neural network.
6. The method of claim 1, wherein the second output data generated by the second machine learning model includes one or more of (i) data describing signal labels, (ii) modulation type, (iii) protocol, (iv) wireless standards, (v) equipment type, (vi) symbol values, (vii) data bits, (viii) data code-words, or (ix) estimated radio signal values representing the one or more radio signals.
24. The method of claim 15, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using a canonicalized input obtained in the output of the signal transformer, or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal.
6. The method of claim 1, wherein the second output data generated by the second machine learning model includes one or more of (i) data describing signal labels, (ii) modulation type, (iii) protocol, (iv) wireless standards, (v) equipment type, (vi) symbol values, (vii) data bits, (viii) data code-words, or (ix) estimated radio signal values representing the one or more radio signals.
9. The method of claim 1, wherein the one or more radio signals are synchronized using the combination of the first machine learning model and the one or more transforms to produce a set of canonicalized encoded information representing the one or more radio signals.
25. The method of claim 24, wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector.
6. The method of claim 1, wherein the second output data generated by the second machine learning model includes one or more of (i) data describing signal labels, (ii) modulation type, (iii) protocol, (iv) wireless standards, (v) equipment type, (vi) symbol values, (vii) data bits, (viii) data code-words, or (ix) estimated radio signal values representing the one or more radio signals.
26. The method of claim 15, comprising: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset.
3. The method of claim 1, wherein the obtained first output data generated by the first machine learning model represents one or more characteristics of the one or more radio signals or its corresponding channel state information, wherein the one or more characteristics of the one or more radio signals or its corresponding channel state information include (i) estimates of timing information, (ii) center frequency, (iii) bandwidth, (iv) phase, (v) frequency and rate of arrival, (vi) direction of arrival, (vii) channel delay response, or (viii) offset of a particular radio signal.
7. The method of claim 1, the method further comprising: providing the second output data to another device that is configured to use the second output data to adjust one or more communications systems.
28. One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising: providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors; controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals; providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer; obtaining, as an output of the signal transformer, a transformed version of the radio signals; providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors.
23. A computer-readable storage device having stored thereon instructions, which, when executed by a data processing apparatus, cause the data processing apparatus to perform operations comprising: providing a first set of input data representing one or more radio signals to a first machine learning model, wherein the first machine learning model is configured to generate output data based on processing, by the first machine learning model, input data representing one or more radio signals, the generated output data including data representing an estimation of one or more characteristics of a radio signal; obtaining first output data generated by the first machine learning model based on processing, by the first machine learning model, the first set of input data representing the one or more radio signals; providing, to a signal transformer, a second set of input data that includes (i) the first set of input data and (ii) the obtained first output data generated by the first machine learning model; generating, by the signal transformer and based on the second set of input data, data representing a transformed radio signal, wherein generating the data representing the transformed radio signal includes applying one or more transforms to the first set of input data representing the one or more radio signals; providing the data representing the transformed radio signal to a second machine learning model that is configured to generate output data describing the one or more radio signals based on processing the data representing the transformed radio signal; and obtaining second output data generated by the second machine learning model based on the second machine learning model processing the data representing the transformed radio signal, wherein the second output data is configured for interpretation by an application at a receiver, wherein the application is configured to infer additional information related to one or more emitters of the one or more radio signals based on the second output data.
Claims 2-28 rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-30 of US 10296831. Although the claims at issue are not identical, they are not patentably distinct from each other because all the claims in the pending Application are transparently found in US 10296831 with obvious wording variations. See the table below for comparison:
Pending Application 18799049
US 10296831
2. A system comprising: one or more processors; and memory storing instructions that are operable, when executed by the one or more processors, to cause the one or more processors to perform operations comprising: providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors; controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals; providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer; obtaining, as an output of the signal transformer, a transformed version of the radio signals; providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors.
4. The system of claim 2, wherein providing the representation of the radio signals to the first machine learning network comprises: providing the representation of the radio signals to a neural network that is trained to estimate parameters of the radio signals.
10. The system of claim 2, wherein providing the transformed version of the radio signals as input to the second machine learning network comprises one of: providing the transformed version of the radio signals to a model for regression using a neural network, or providing the transformed version of the radio signals to a model for classification using a neural network.
13. A system to process one or more radio signals, the system comprising: one or more processors; and one or more computer readable media storing computer code that, when executed by the one or more processors, is configured to perform a plurality of operations, the operations comprising: providing a first set of input data representing one or more radio signals to a first neural network that has been trained to generate output data representing an estimation of one or more characteristics of a radio signal; obtaining first output data generated by the first neural network based on the first neural network processing the first set of input data; receiving, by a signal transformer, a second set of input data that includes (i) the first set of input data and (ii) the first output data generated by the first neural network; generating, by the signal transformer and based on the second set of input data, data representing a transformed radio signal by applying one or more transforms of a set of predetermined transforms to the first set of input data representing the one or more radio signals; providing the data representing the transformed radio signal to a second neural network that has been trained to generate output data describing the one or more radio signals based on processing the data representing the transformed radio signal; obtaining second output data generated by the second neural network based on the second neural network processing the data representing the transformed radio signal; and determining based on the second output data a set of information describing one or more radio signals in the first set of input data.
3. The system of claim 2, wherein the operations comprise: converting one or more radio signals detected by a radio sensor to digital data, wherein the representation of the radio signals includes digital data.
14. The system of claim 13, wherein the first set of input data is a digital output of an analog-to-digital converter that has sampled the one or more radio signals into a basis function.
5. The system of claim 2, wherein controlling the first machine learning network to generate the output that comprises estimated parameters of the radio signals comprises: controlling the first machine learning network to generate parameters indicating one or more of the following: timing information, frequency, center frequency, bandwidth, phase, rate of arrival, direction of arrival, offset, or channel state information associated with the radio signals.
15. The system of claim 13, wherein the first output data represents one or more characteristics of the one or more radio signals or its corresponding channel state information include estimates of timing information, center frequency, bandwidth, phase, frequency and rate of arrival, direction of arrival, channel delay response, offset, or bandwidth of the particular radio signal.
6. The system of claim 5, wherein controlling the first machine learning network to generate parameters indicating channel state information associated with the radio signals comprises: controlling the first machine learning network to generate parameters indicating a channel delay response of at least one of the radio signals.
15. The system of claim 13, wherein the first output data represents one or more characteristics of the one or more radio signals or its corresponding channel state information include estimates of timing information, center frequency, bandwidth, phase, frequency and rate of arrival, direction of arrival, channel delay response, offset, or bandwidth of the particular radio signal.
7. The system of claim 2, wherein the operations comprise: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms include at least one of the following: an affine transform, an oscillator, a mixer, a multiplier, or a convolution with a parametric set of filter taps.
17. The system of claim 13, wherein the set of predetermined transforms includes one or more of an affine transform, oscillator and mixer, filter application, resampling, sub-band tuning, or a convolution with a set of filter taps.
8. The system of claim 2, wherein the operations comprise: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms are configured to invert effects of the radio signals.
9. The system of claim 8, wherein inverting the effects of the radio signals comprises inverting effects of physics acting on the radio signals during transmission or detection.
23. The system of claim 22, wherein the one or more radio signals are synchronized or recovered using the combination of the first neural network and the set of transforms to produce a set of canonicalized encoded information representing the one or more received radio signals.
24. The system of claim 22, wherein a threshold amount of uncertainty surrounding one or more of a frequency offset, a time offset, or other the channel effects has been eliminated from the second set of input data.
11. The system of claim 2, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using a canonicalized input obtained in the output of the signal transformer, or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal.
19. The system of claim 13, wherein the second output generated by the second neural network includes one or more of data describing signal labels, modulation type, protocol, wireless standards, equipment type, symbol values, data bits, or data code-words.
23. The system of claim 22, wherein the one or more radio signals are synchronized or recovered using the combination of the first neural network and the set of transforms to produce a set of canonicalized encoded information representing the one or more received radio signals.
12. The system of claim 11, wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector.
19. The system of claim 13, wherein the second output generated by the second neural network includes one or more of data describing signal labels, modulation type, protocol, wireless standards, equipment type, symbol values, data bits, or data code-words.
13. The system of claim 2, wherein the operations comprise: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset.
15. The system of claim 13, wherein the first output data represents one or more characteristics of the one or more radio signals or its corresponding channel state information include estimates of timing information, center frequency, bandwidth, phase, frequency and rate of arrival, direction of arrival, channel delay response, offset, or bandwidth of the particular radio signal.
20. The system of claim 13, wherein the operations further comprise: providing the second output data to another device to another device that is configured to use the second output data to adjust one or more communications systems.
14. The system of claim 2, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region.
21. The system of claim 20, wherein the second output data is interpreted by an application at a receiver in order to infer additional information about one or more emitters, wherein the additional information about the emitters may include location of an emitter, movement of an emitter, behavior of an emitter, or pattern of life of an emitter.
15. A method comprising: providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors; controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals; providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer; obtaining, as an output of the signal transformer, a transformed version of the radio signals; providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors.
17. The method of claim 15, wherein providing the representation of the radio signals to the first machine learning network comprises: providing the representation of the radio signals to a neural network that is trained to estimate parameters of the radio signals.
23. The method of claim 15, wherein providing the transformed version of the radio signals as input to the second machine learning network comprises one of: providing the transformed version of the radio signals to a model for regression using a neural network, or providing the transformed version of the radio signals to a model for classification using a neural network.
13. A system to process one or more radio signals, the system comprising: one or more processors; and one or more computer readable media storing computer code that, when executed by the one or more processors, is configured to perform a plurality of operations, the operations comprising: providing a first set of input data representing one or more radio signals to a first neural network that has been trained to generate output data representing an estimation of one or more characteristics of a radio signal; obtaining first output data generated by the first neural network based on the first neural network processing the first set of input data; receiving, by a signal transformer, a second set of input data that includes (i) the first set of input data and (ii) the first output data generated by the first neural network; generating, by the signal transformer and based on the second set of input data, data representing a transformed radio signal by applying one or more transforms of a set of predetermined transforms to the first set of input data representing the one or more radio signals; providing the data representing the transformed radio signal to a second neural network that has been trained to generate output data describing the one or more radio signals based on processing the data representing the transformed radio signal; obtaining second output data generated by the second neural network based on the second neural network processing the data representing the transformed radio signal; and determining based on the second output data a set of information describing one or more radio signals in the first set of input data.
16. The method of claim 15, comprising: converting one or more radio signals detected by a radio sensor to digital data, wherein the representation of the radio signals includes digital data.
14. The system of claim 13, wherein the first set of input data is a digital output of an analog-to-digital converter that has sampled the one or more radio signals into a basis function.
18. The method of claim 15, wherein controlling the first machine learning network to generate the output that comprises estimated parameters of the radio signals comprises: controlling the first machine learning network to generate parameters indicating one or more of the following: timing information, frequency, center frequency, bandwidth, phase, rate of arrival, direction of arrival, offset, or channel state information associated with the radio signals.
15. The system of claim 13, wherein the first output data represents one or more characteristics of the one or more radio signals or its corresponding channel state information include estimates of timing information, center frequency, bandwidth, phase, frequency and rate of arrival, direction of arrival, channel delay response, offset, or bandwidth of the particular radio signal.
19. The method of claim 18, wherein controlling the first machine learning network to generate parameters indicating channel state information associated with the radio signals comprises: controlling the first machine learning network to generate parameters indicating a channel delay response of at least one of the radio signals.
15. The system of claim 13, wherein the first output data represents one or more characteristics of the one or more radio signals or its corresponding channel state information include estimates of timing information, center frequency, bandwidth, phase, frequency and rate of arrival, direction of arrival, channel delay response, offset, or bandwidth of the particular radio signal.
20. The method of claim 15, comprising: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms include at least one of the following: an affine transform, an oscillator, a mixer, a multiplier, or a convolution with a parametric set of filter taps.
17. The system of claim 13, wherein the set of predetermined transforms includes one or more of an affine transform, oscillator and mixer, filter application, resampling, sub-band tuning, or a convolution with a set of filter taps.
21. The method of claim 15, comprising: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms are configured to invert effects of the radio signals.
23. The system of claim 22, wherein the one or more radio signals are synchronized or recovered using the combination of the first neural network and the set of transforms to produce a set of canonicalized encoded information representing the one or more received radio signals.
24. The system of claim 22, wherein a threshold amount of uncertainty surrounding one or more of a frequency offset, a time offset, or other the channel effects has been eliminated from the second set of input data.
22. The method of claim 21, wherein inverting the effects of the radio signals comprises inverting effects of physics acting on the radio signals during transmission or detection.
24. The system of claim 22, wherein a threshold amount of uncertainty surrounding one or more of a frequency offset, a time offset, or other the channel effects has been eliminated from the second set of input data.
24. The method of claim 15, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using a canonicalized input obtained in the output of the signal transformer, or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal.
19. The system of claim 13, wherein the second output generated by the second neural network includes one or more of data describing signal labels, modulation type, protocol, wireless standards, equipment type, symbol values, data bits, or data code-words.
23. The system of claim 22, wherein the one or more radio signals are synchronized or recovered using the combination of the first neural network and the set of transforms to produce a set of canonicalized encoded information representing the one or more received radio signals.
25. The method of claim 24, wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector.
19. The system of claim 13, wherein the second output generated by the second neural network includes one or more of data describing signal labels, modulation type, protocol, wireless standards, equipment type, symbol values, data bits, or data code-words.
26. The method of claim 15, comprising: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset.
15. The system of claim 13, wherein the first output data represents one or more characteristics of the one or more radio signals or its corresponding channel state information include estimates of timing information, center frequency, bandwidth, phase, frequency and rate of arrival, direction of arrival, channel delay response, offset, or bandwidth of the particular radio signal.
20. The system of claim 13, wherein the operations further comprise: providing the second output data to another device to another device that is configured to use the second output data to adjust one or more communications systems.
27. The method of claim 15, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region.
21. The system of claim 20, wherein the second output data is interpreted by an application at a receiver in order to infer additional information about one or more emitters, wherein the additional information about the emitters may include location of an emitter, movement of an emitter, behavior of an emitter, or pattern of life of an emitter.
28. One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising: providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors; controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals; providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer; obtaining, as an output of the signal transformer, a transformed version of the radio signals; providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors.
25. A device, the device comprising: one or more processors; and one or more computer readable media storing computer code that, when executed by the one or more processors, is configured to perform a plurality of operations, the operations comprising: providing a first set of input data representing one or more radio signals to a first neural network that has been trained to generate output data representing an estimation of one or more characteristics of a radio signal; obtaining first output data generated by the first neural network based on the first neural network processing the first set of input data; receiving, by a signal transformer, a second set of input data that includes (i) the first set of input data and (ii) the first output data generated by the first neural network; generating, by the signal transformer and based on the second set of input data, data representing a transformed radio signal by applying one or more transforms of a set of predetermined transforms to the first set of input data representing the one or more radio signals; providing the data representing the transformed radio signal to a second neural network that has been trained to generate output data describing the one or more radio signals based on processing the data representing the transformed radio signal; obtaining second output data generated by the second neural network based on the second neural network processing the data representing the transformed radio signal; and determining based on the second output data a set of information describing one or more radio signals in the first set of input data.
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.
Claims 2-11, 15-24 and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Tu et al. (US 20160072590, hereinafter “Tu”) and further in view of Holt et al. (US 20180174050, hereinafter “Holt”).
Regarding claim 2, Tu discloses,
A system comprising:
one or more processors; an memory storing instructions that are operable, when executed by the one or more processors (The general purpose processor 206 may also be coupled to at least one memory 214. The memory 214 may be a non-transitory tangible computer readable storage medium that stores processor-executable instructions. For example, the instructions may include routing communication data relating to the first or second subscription though a corresponding baseband-RF resource chain, [0049]-[0050]), to cause the one or more processors to perform operations comprising:
providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors ( With reference to FIGS. 1-4A, the multilayer perceptron neural network 400 may be implemented in a multi-technology wireless communications device (e.g., 110, 120, 200 in FIGS. 1 and 2) in software, general processing hardware, dedicated hardware, or a combination of any of the preceding. The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”, [0067]; the victim signal and the aggressor signal or aggressor kernel may be used by the multi-technology communication device as input signals for the multilayer perceptron neural network with Hammerstein structure. The victim signal and the aggressor signal or aggressor kernel may be received by the input layer of the multilayer perceptron neural network. The aggressor signal or aggressor kernel may be divided into one or more real and imaginary components, [0106]-[0107]);
controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals (The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”. The multilayer perceptron neural network 400 may be configured to produce an estimated nonlinear interference signal 410 for the time “i”, [0067]-[0068]; Augmenting the combined hidden layer output signals with the bias factor may produce a jammer signal estimate. Blocks 816 and 818 may be executed for multiple groups of hidden layer output signals and multiple bias factors such that the linear combinations produce real and imaginary components of the jammer signal estimate, [0111]-[0112]);
providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer (The estimated nonlinear interference signal 410 for the time “i” may be used by a linear combination function 438 to cancel the estimated nonlinear interference signal 410 from the victim signal 408. For example, the linear combination function 438 may subtract, add, or otherwise mathematically manipulate portions of the estimated nonlinear interference signal 410 affecting the victim signal 408, [0069]; Canceling or removing the estimated nonlinear interference from the victim signal may be implemented in a variety of known ways, such as filtration, transformation, extraction, reconstruction, and suppression. In block 712, the multi-technology communication device may decode the victim signal without presence of the interference by the aggressor signal(s), [0105]);
obtaining, as an output of the signal transformer, a transformed version of the radio signals (The result of the linear combination function 438 may be the victim signal with the nonlinear interference cancelled 412. A demodulator 440 may receive the victim signal with the nonlinear interference cancelled 412 and demodulate it to produce the desired signal 414, [0069]; the multi-technology communication device may decode the victim signal without presence of the interference by the aggressor signal(s). In block 714, the multi-technology communication device may advance to the next time interval “i” (e.g., move to the current time interval) and begin the process again with regard to aggressor and victim signals for the current time “i”, [0105]).
However, Tu does not disclose, providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors. In the same field of endeavor, Holt discloses,
providing the transformed version of the radio signals as input to a second machine learning network (the encoder model can be implemented by a transmitter device or component to encode communication data prior to transmission of the communication data via the communication channel, while the decoder model can be implemented by a receiver device or component to decode the communication data received via the communication channel [0023]; At 906, one or more computing devices can input the first set of communication data obtained at 904 into the machine-learned decoder model trained at 902. At 908, one or more computing devices can receive as an output of the machine-learned decoder model a decoded version of the communication data. At 910, one or more computing devices can provide the decoded version of the communication data as output. In some examples, the decoded version of the communication data received at 908 can be provided to one or more other computing devices or components [0098]-[0100]); and
controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors (the encoder model can be implemented by a transmitter device or component to encode communication data prior to transmission of the communication data via the communication channel, while the decoder model can be implemented by a receiver device or component to decode the communication data received via the communication channel [0023]; At 906, one or more computing devices can input the first set of communication data obtained at 904 into the machine-learned decoder model trained at 902. At 908, one or more computing devices can receive as an output of the machine-learned decoder model a decoded version of the communication data. At 910, one or more computing devices can provide the decoded version of the communication data as output. In some examples, the decoded version of the communication data received at 908 can be provided to one or more other computing devices or components [0098]-[0100]).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify Tu by specifically providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors, as taught by Holt for the purpose of providing systems and methods for implementing adaptive channel coding using machine-learned models [0001].
Regarding claim 3, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 2), further Tu discloses,
wherein the operations comprise: converting one or more radio signals detected by a radio sensor to digital data, wherein the representation of the radio signals includes digital data (The various embodiments include methods for removing nonlinear interference from a victim signal in digital communications by using a neural network analysis method to estimate the coefficients of the signal to be removed before a received signal is decoded, [0041]; the multilayer perceptron neural network with Hammerstein structure 400 may be a neural network technique (e.g., multilayer perceptron) and linear filtering technique (e.g., Hammerstein structure) implemented in a multi-technology wireless communications device (shown in FIGS. 4B-4C). For any time “i”, the multilayer perceptron neural network 400 may be implemented to help identify an intended receive signal x(i), [0067]-[0068]).
Regarding claim 4, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 2), further Tu discloses,
wherein providing the representation of the radio signals to the first machine learning network comprises: providing the representation of the radio signals to a neural network that is trained to estimate parameters of the radio signals (The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”. The multilayer perceptron neural network 400 may be configured to produce an estimated nonlinear interference signal 410 for the time “i”, [0067]-[0068]).
Regarding claim 5, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 2), further Tu discloses,
wherein controlling the first machine learning network to generate the output that comprises estimated parameters of the radio signals comprises: controlling the first machine learning network to generate parameters indicating one or more of the following: timing information, frequency, center frequency, bandwidth, phase, rate of arrival, direction of arrival, offset, or channel state information associated with the radio signals (The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”. The multilayer perceptron neural network 400 may be configured to produce an estimated nonlinear interference signal 410 for the time “i”, [0067]-[0068]; Augmenting the combined hidden layer output signals with the bias factor may produce a jammer signal estimate. Blocks 816 and 818 may be executed for multiple groups of hidden layer output signals and multiple bias factors such that the linear combinations produce real and imaginary components of the jammer signal estimate, [0111]-[0112]).
Regarding claim 6, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 2), further Tu discloses,
wherein controlling the first machine learning network to generate parameters indicating channel state information associated with the radio signals comprises: controlling the first machine learning network to generate parameters indicating a channel delay response of at least one of the radio signals (the linear filter 418 may be a finite impulse response filter having multiple delay lines and associated delay line linear combinations. In some embodiments, the linear filter may include a delay line 632a(1)-(n) for the real jammer signal estimate component 424, and a delay line 632b(1)-(n) for the imaginary jammer signal estimate component 426. Sets of weighting components 633a-d, 635a-d may augment the real and imaginary jammer signal estimate components 424, 426 respectively at each operation of the delay lines 632a(1)-(n), 632b(1)-(n), [0094]-[0095]).
Regarding claim 7, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 2), further Tu discloses,
wherein the operations comprise: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms include at least one of the following: an affine transform, an oscillator, a mixer, a multiplier, or a convolution with a parametric set of filter taps (The estimated nonlinear interference signal 410 for the time “i” may be used by a linear combination function 438 to cancel the estimated nonlinear interference signal 410 from the victim signal 408. For example, the linear combination function 438 may subtract, add, or otherwise mathematically manipulate portions of the estimated nonlinear interference signal 410 affecting the victim signal 408, [0068]-[0070]).
Regarding claim 8, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 2), further Tu discloses,
wherein the operations comprise: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms are configured to invert effects of the radio signals (The estimated nonlinear interference signal 410 for the time “i” may be used by a linear combination function 438 to cancel the estimated nonlinear interference signal 410 from the victim signal 408. For example, the linear combination function 438 may subtract, add, or otherwise mathematically manipulate portions of the estimated nonlinear interference signal 410 affecting the victim signal 408, [0068]-[0070]).
Regarding claim 9, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 8), further Tu discloses,
wherein inverting the effects of the radio signals comprises inverting effects of physics acting on the radio signals during transmission or detection (an aggressor's transmissions may cause severe impairment to the victim's ability to receive transmission. This interference may be in the form of blocking interference, harmonics, intermodulation, or other noises and distortion. Such interference may significantly degrade the victim's receiver sensitivity, link to a network, voice call quality and data throughput. These effects may result in a reduced network capacity for the affected communication service or subscription [0038]; removing or subtracting nonlinear interference from a victim signal is particularly problematic for devices having multiple RF chain, such as multi-SIM multi-active (“MSMA”) devices and for Long-Term Evolution (“LTE”) carrier aggregation, because interference experienced on one RF chain may come from multiple RF sources and thus may have unpredictable signal form [0040]-[0041]).
Regarding claim 10, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 2), in addition Holt discloses,
wherein providing the transformed version of the radio signals as input to the second machine learning network comprises one of: providing the transformed version of the radio signals to a model for regression using a neural network, or providing the transformed version of the radio signals to a model for classification using a neural network (a decoder model can be configured to receive a set of inputs (e.g., the second set of outputs generated by the channel model) and, in response to receipt of the second set of outputs, generate a third set of outputs. The decoder model can be, for example, a neural network such as a deep neural network or other multi-layer non-linear model [0027]; The third loss function can be backpropagated through the decoder model while modifying the decoder model to train the decoder model (e.g., by modifying one or more weights associated with the decoder model) to generate outputs that attempt to reconstruct the data provided to the communication channel [0032]; provided as input to the trained machine-learned decoder model. A decoded version of the transmit data can be received as an output of the machine-learned trained decoder model in response to receipt of the transmitted encoded version of the transmit data received from the communication channel, [0035]).
Regarding claim 11, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 2), further Tu discloses, a canonicalized input obtained in the output of the signal transformer ( the linear combination function 438 may subtract, add, or otherwise mathematically manipulate portions of the estimated nonlinear interference signal 410 affecting the victim signal 408. Thus, unnecessary elements of the victim signal 408 caused by aggressor signal 402 interference may be removed from the victim signal 402 and elements obscured by aggressor signal 402 interference may be recaptured [0069]; In block 712, the multi-technology communication device may decode the victim signal without presence of the interference by the aggressor signal(s). In block 714, the multi-technology communication device may advance to the next time interval “i” (e.g., move to the current time interval) and begin the process again with regard to aggressor and victim signals for the current time “i”, [0104]-[0105]).
However, Tu does not discloses, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal.
In the same field of endeavor, Holt discloses, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal (The decoder model can be, for example, a neural network such as a deep neural network or other multi-layer non-linear model. In some implementations, the third set of outputs can be expressed according to the first set of dimensions. Thus, in some implementations, while the encoder model transforms data from the first set of dimensions to the second set of dimensions, the decoder model transforms data from the second set of dimensions back into the first set of dimensions. As such, the decoder model can be said to have performed an inverse transformation relative to the encoder model [0027]; The decoded version of the transmit data then can be provided to one or more computing devices or components thereof for further processing or provision as output data (e.g., via a display device and/or audio device) [0035]).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify Tu by specifically providing wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal, as taught by Holt for the purpose of providing systems and methods for implementing adaptive channel coding using machine-learned models [0001].
Regarding claim 15, Tu discloses,
A method comprising:
providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors ( With reference to FIGS. 1-4A, the multilayer perceptron neural network 400 may be implemented in a multi-technology wireless communications device (e.g., 110, 120, 200 in FIGS. 1 and 2) in software, general processing hardware, dedicated hardware, or a combination of any of the preceding. The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”, [0067]; the victim signal and the aggressor signal or aggressor kernel may be used by the multi-technology communication device as input signals for the multilayer perceptron neural network with Hammerstein structure. The victim signal and the aggressor signal or aggressor kernel may be received by the input layer of the multilayer perceptron neural network. The aggressor signal or aggressor kernel may be divided into one or more real and imaginary components, [0106]-[0107]);
controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals (The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”. The multilayer perceptron neural network 400 may be configured to produce an estimated nonlinear interference signal 410 for the time “i”, [0067]-[0068]; Augmenting the combined hidden layer output signals with the bias factor may produce a jammer signal estimate. Blocks 816 and 818 may be executed for multiple groups of hidden layer output signals and multiple bias factors such that the linear combinations produce real and imaginary components of the jammer signal estimate, [0111]-[0112]);
providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer (The estimated nonlinear interference signal 410 for the time “i” may be used by a linear combination function 438 to cancel the estimated nonlinear interference signal 410 from the victim signal 408. For example, the linear combination function 438 may subtract, add, or otherwise mathematically manipulate portions of the estimated nonlinear interference signal 410 affecting the victim signal 408, [0069]; Canceling or removing the estimated nonlinear interference from the victim signal may be implemented in a variety of known ways, such as filtration, transformation, extraction, reconstruction, and suppression. In block 712, the multi-technology communication device may decode the victim signal without presence of the interference by the aggressor signal(s), [0105]);
obtaining, as an output of the signal transformer, a transformed version of the radio signals (The result of the linear combination function 438 may be the victim signal with the nonlinear interference cancelled 412. A demodulator 440 may receive the victim signal with the nonlinear interference cancelled 412 and demodulate it to produce the desired signal 414, [0069]; the multi-technology communication device may decode the victim signal without presence of the interference by the aggressor signal(s). In block 714, the multi-technology communication device may advance to the next time interval “i” (e.g., move to the current time interval) and begin the process again with regard to aggressor and victim signals for the current time “i”, [0105]).
However, Tu does not disclose, providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors. In the same field of endeavor, Holt discloses,
providing the transformed version of the radio signals as input to a second machine learning network (the encoder model can be implemented by a transmitter device or component to encode communication data prior to transmission of the communication data via the communication channel, while the decoder model can be implemented by a receiver device or component to decode the communication data received via the communication channel [0023]; At 906, one or more computing devices can input the first set of communication data obtained at 904 into the machine-learned decoder model trained at 902. At 908, one or more computing devices can receive as an output of the machine-learned decoder model a decoded version of the communication data. At 910, one or more computing devices can provide the decoded version of the communication data as output. In some examples, the decoded version of the communication data received at 908 can be provided to one or more other computing devices or components [0098]-[0100]); and
controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors (the encoder model can be implemented by a transmitter device or component to encode communication data prior to transmission of the communication data via the communication channel, while the decoder model can be implemented by a receiver device or component to decode the communication data received via the communication channel [0023]; At 906, one or more computing devices can input the first set of communication data obtained at 904 into the machine-learned decoder model trained at 902. At 908, one or more computing devices can receive as an output of the machine-learned decoder model a decoded version of the communication data. At 910, one or more computing devices can provide the decoded version of the communication data as output. In some examples, the decoded version of the communication data received at 908 can be provided to one or more other computing devices or components [0098]-[0100]).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify Tu by specifically providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors, as taught by Holt for the purpose of providing systems and methods for implementing adaptive channel coding using machine-learned models [0001].
Regarding claim 16, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 15), further Tu discloses,
converting one or more radio signals detected by a radio sensor to digital data, wherein the representation of the radio signals includes digital data (The various embodiments include methods for removing nonlinear interference from a victim signal in digital communications by using a neural network analysis method to estimate the coefficients of the signal to be removed before a received signal is decoded, [0041]; the multilayer perceptron neural network with Hammerstein structure 400 may be a neural network technique (e.g., multilayer perceptron) and linear filtering technique (e.g., Hammerstein structure) implemented in a multi-technology wireless communications device (shown in FIGS. 4B-4C). For any time “i”, the multilayer perceptron neural network 400 may be implemented to help identify an intended receive signal x(i), [0067]-[0068]).
Regarding claim 17, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 15), further Tu discloses,
wherein providing the representation of the radio signals to the first machine learning network comprises: providing the representation of the radio signals to a neural network that is trained to estimate parameters of the radio signals (The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”. The multilayer perceptron neural network 400 may be configured to produce an estimated nonlinear interference signal 410 for the time “i”, [0067]-[0068]).
Regarding claim 18, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 15), further Tu discloses,
wherein controlling the first machine learning network to generate the output that comprises estimated parameters of the radio signals comprises: controlling the first machine learning network to generate parameters indicating one or more of the following: timing information, frequency, center frequency, bandwidth, phase, rate of arrival, direction of arrival, offset, or channel state information associated with the radio signals (The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”. The multilayer perceptron neural network 400 may be configured to produce an estimated nonlinear interference signal 410 for the time “i”, [0067]-[0068]; Augmenting the combined hidden layer output signals with the bias factor may produce a jammer signal estimate. Blocks 816 and 818 may be executed for multiple groups of hidden layer output signals and multiple bias factors such that the linear combinations produce real and imaginary components of the jammer signal estimate, [0111]-[0112]).
Regarding claim 19, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 18), further Tu discloses,
wherein controlling the first machine learning network to generate parameters indicating channel state information associated with the radio signals comprises: controlling the first machine learning network to generate parameters indicating a channel delay response of at least one of the radio signals (the linear filter 418 may be a finite impulse response filter having multiple delay lines and associated delay line linear combinations. In some embodiments, the linear filter may include a delay line 632a(1)-(n) for the real jammer signal estimate component 424, and a delay line 632b(1)-(n) for the imaginary jammer signal estimate component 426. Sets of weighting components 633a-d, 635a-d may augment the real and imaginary jammer signal estimate components 424, 426 respectively at each operation of the delay lines 632a(1)-(n), 632b(1)-(n), [0094]-[0095]).
Regarding claim 20, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 15), further Tu discloses,
wherein the operations comprise: controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms include at least one of the following: an affine transform, an oscillator, a mixer, a multiplier, or a convolution with a parametric set of filter taps (The estimated nonlinear interference signal 410 for the time “i” may be used by a linear combination function 438 to cancel the estimated nonlinear interference signal 410 from the victim signal 408. For example, the linear combination function 438 may subtract, add, or otherwise mathematically manipulate portions of the estimated nonlinear interference signal 410 affecting the victim signal 408, [0068]-[0070]).
Regarding claim 21, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 15), further Tu discloses,
controlling the signal transformer to perform one or more transforms on the representation of the radio signals, wherein the one or more transforms are configured to invert effects of the radio signals (The estimated nonlinear interference signal 410 for the time “i” may be used by a linear combination function 438 to cancel the estimated nonlinear interference signal 410 from the victim signal 408. For example, the linear combination function 438 may subtract, add, or otherwise mathematically manipulate portions of the estimated nonlinear interference signal 410 affecting the victim signal 408, [0068]-[0070]).
Regarding claim 22, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 21), further Tu discloses,
wherein inverting the effects of the radio signals comprises inverting effects of physics acting on the radio signals during transmission or detection (an aggressor's transmissions may cause severe impairment to the victim's ability to receive transmission. This interference may be in the form of blocking interference, harmonics, intermodulation, or other noises and distortion. Such interference may significantly degrade the victim's receiver sensitivity, link to a network, voice call quality and data throughput. These effects may result in a reduced network capacity for the affected communication service or subscription [0038]; removing or subtracting nonlinear interference from a victim signal is particularly problematic for devices having multiple RF chain, such as multi-SIM multi-active (“MSMA”) devices and for Long-Term Evolution (“LTE”) carrier aggregation, because interference experienced on one RF chain may come from multiple RF sources and thus may have unpredictable signal form [0040]-[0041]).
Regarding claim 23, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 15), in addition Holt discloses,
wherein providing the transformed version of the radio signals as input to the second machine learning network comprises one of: providing the transformed version of the radio signals to a model for regression using a neural network, or providing the transformed version of the radio signals to a model for classification using a neural network (a decoder model can be configured to receive a set of inputs (e.g., the second set of outputs generated by the channel model) and, in response to receipt of the second set of outputs, generate a third set of outputs. The decoder model can be, for example, a neural network such as a deep neural network or other multi-layer non-linear model [0027]; The third loss function can be backpropagated through the decoder model while modifying the decoder model to train the decoder model (e.g., by modifying one or more weights associated with the decoder model) to generate outputs that attempt to reconstruct the data provided to the communication channel [0032]; provided as input to the trained machine-learned decoder model. A decoded version of the transmit data can be received as an output of the machine-learned trained decoder model in response to receipt of the transmitted encoded version of the transmit data received from the communication channel, [0035]).
Regarding claim 24, the combination of Tu and Holt does not disclose everything claimed as applied above (see claim 15), further Tu discloses, a canonicalized input obtained in the output of the signal transformer ( the linear combination function 438 may subtract, add, or otherwise mathematically manipulate portions of the estimated nonlinear interference signal 410 affecting the victim signal 408. Thus, unnecessary elements of the victim signal 408 caused by aggressor signal 402 interference may be removed from the victim signal 402 and elements obscured by aggressor signal 402 interference may be recaptured [0069]; In block 712, the multi-technology communication device may decode the victim signal without presence of the interference by the aggressor signal(s). In block 714, the multi-technology communication device may advance to the next time interval “i” (e.g., move to the current time interval) and begin the process again with regard to aggressor and victim signals for the current time “i”, [0104]-[0105]).
However, Tu does not discloses, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal.
In the same field of endeavor, Holt discloses, wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal (The decoder model can be, for example, a neural network such as a deep neural network or other multi-layer non-linear model. In some implementations, the third set of outputs can be expressed according to the first set of dimensions. Thus, in some implementations, while the encoder model transforms data from the first set of dimensions to the second set of dimensions, the decoder model transforms data from the second set of dimensions back into the first set of dimensions. As such, the decoder model can be said to have performed an inverse transformation relative to the encoder model [0027]; The decoded version of the transmit data then can be provided to one or more computing devices or components thereof for further processing or provision as output data (e.g., via a display device and/or audio device) [0035]).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify Tu by specifically providing wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises one of: controlling the second machine learning network to generate the one or more information bits or codewords using or controlling the second machine learning network to generate a classification label target that indicates whether or not the radio signals include a particular type of radio signal, as taught by Holt for the purpose of providing systems and methods for implementing adaptive channel coding using machine-learned models [0001].
Regarding claim 28, Tu discloses,
. One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations (The general purpose processor 206 may also be coupled to at least one memory 214. The memory 214 may be a non-transitory tangible computer readable storage medium that stores processor-executable instructions. For example, the instructions may include routing communication data relating to the first or second subscription though a corresponding baseband-RF resource chain, [0049]-[0050]) comprising:
providing, as input to a first machine learning network, a representation of radio signals detected by one or more sensors ( With reference to FIGS. 1-4A, the multilayer perceptron neural network 400 may be implemented in a multi-technology wireless communications device (e.g., 110, 120, 200 in FIGS. 1 and 2) in software, general processing hardware, dedicated hardware, or a combination of any of the preceding. The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”, [0067]; the victim signal and the aggressor signal or aggressor kernel may be used by the multi-technology communication device as input signals for the multilayer perceptron neural network with Hammerstein structure. The victim signal and the aggressor signal or aggressor kernel may be received by the input layer of the multilayer perceptron neural network. The aggressor signal or aggressor kernel may be divided into one or more real and imaginary components, [0106]-[0107]);
controlling the first machine learning network to generate an output that comprises estimated parameters of the radio signals (The multilayer perceptron neural network 400 may be configured to receive an aggressor signal 402 and a victim signal 408 at a time “i”. The multilayer perceptron neural network 400 may be configured to produce an estimated nonlinear interference signal 410 for the time “i”, [0067]-[0068]; Augmenting the combined hidden layer output signals with the bias factor may produce a jammer signal estimate. Blocks 816 and 818 may be executed for multiple groups of hidden layer output signals and multiple bias factors such that the linear combinations produce real and imaginary components of the jammer signal estimate, [0111]-[0112]);
providing the output from the first machine learning network and the representation of the radio signals as an input to a signal transformer (The estimated nonlinear interference signal 410 for the time “i” may be used by a linear combination function 438 to cancel the estimated nonlinear interference signal 410 from the victim signal 408. For example, the linear combination function 438 may subtract, add, or otherwise mathematically manipulate portions of the estimated nonlinear interference signal 410 affecting the victim signal 408, [0069]; Canceling or removing the estimated nonlinear interference from the victim signal may be implemented in a variety of known ways, such as filtration, transformation, extraction, reconstruction, and suppression. In block 712, the multi-technology communication device may decode the victim signal without presence of the interference by the aggressor signal(s), [0105]);
obtaining, as an output of the signal transformer, a transformed version of the radio signals (The result of the linear combination function 438 may be the victim signal with the nonlinear interference cancelled 412. A demodulator 440 may receive the victim signal with the nonlinear interference cancelled 412 and demodulate it to produce the desired signal 414, [0069]; the multi-technology communication device may decode the victim signal without presence of the interference by the aggressor signal(s). In block 714, the multi-technology communication device may advance to the next time interval “i” (e.g., move to the current time interval) and begin the process again with regard to aggressor and victim signals for the current time “i”, [0105]).
However, Tu does not disclose, providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors. In the same field of endeavor, Holt discloses,
providing the transformed version of the radio signals as input to a second machine learning network (the encoder model can be implemented by a transmitter device or component to encode communication data prior to transmission of the communication data via the communication channel, while the decoder model can be implemented by a receiver device or component to decode the communication data received via the communication channel [0023]; At 906, one or more computing devices can input the first set of communication data obtained at 904 into the machine-learned decoder model trained at 902. At 908, one or more computing devices can receive as an output of the machine-learned decoder model a decoded version of the communication data. At 910, one or more computing devices can provide the decoded version of the communication data as output. In some examples, the decoded version of the communication data received at 908 can be provided to one or more other computing devices or components [0098]-[0100]); and
controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors (the encoder model can be implemented by a transmitter device or component to encode communication data prior to transmission of the communication data via the communication channel, while the decoder model can be implemented by a receiver device or component to decode the communication data received via the communication channel [0023]; At 906, one or more computing devices can input the first set of communication data obtained at 904 into the machine-learned decoder model trained at 902. At 908, one or more computing devices can receive as an output of the machine-learned decoder model a decoded version of the communication data. At 910, one or more computing devices can provide the decoded version of the communication data as output. In some examples, the decoded version of the communication data received at 908 can be provided to one or more other computing devices or components [0098]-[0100]).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify Tu by specifically providing the transformed version of the radio signals as input to a second machine learning network; and controlling the second machine learning network to generate, using the transformed version of the radio signals, one or more information bits or codewords that represent the radio signals detected by the one or more radio signal sensors, as taught by Holt for the purpose of providing systems and methods for implementing adaptive channel coding using machine-learned models [0001].
Claims 12 and 25 are rejected under 35 U.S.C. 103 as being unpatentable over Tu, in view of Holt and further in view of Chen et al. (US 20200044899, hereinafter “Chen”).
Regarding claim 12, the combination of Tu and Holt discloses everything claimed as applied above (see claim 11), however the combination of Tu and Holt does not explicitly disclose, wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector.
In the same field of endeavor, Chen discloses wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector (Training a strong classifier, and training five weak classifiers based on a BP neural network through Bagging concurrent integrated learning, then combining the weak classifiers into the strong classifier, and a specific step comprises as follows, [0048]-0055]).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify the combination of Tu and Holt by specifically providing wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector, as taught by Chen for the purpose of providing a method for automatically identifying a modulation mode for a digital communication signal (abstract).
Regarding claim 25, the combination of Tu and Holt discloses everything claimed as applied above (see claim 24), however the combination of Tu and Holt does not explicitly disclose, wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector.
In the same field of endeavor, Chen discloses wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector (Training a strong classifier, and training five weak classifiers based on a BP neural network through Bagging concurrent integrated learning, then combining the weak classifiers into the strong classifier, and a specific step comprises as follows, [0048]-0055]).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify the combination of Tu and Holt by specifically providing wherein controlling the second machine learning network to generate the classification label target comprises: controlling the second machine learning network to generate a one-hot vector, as taught by Chen for the purpose of providing a method for automatically identifying a modulation mode for a digital communication signal (abstract).
Claims 13 and 26 are rejected under 35 U.S.C. 103 as being unpatentable over Tu, in view of Holt and further in view of Mody et al. (US 20130288734, hereinafter “Mody”).
Regarding claim 13, the combination of Tu and Holt discloses everything claimed as applied above (see claim 2), however the combination of Tu and Holt does not explicitly disclose, wherein the operations comprise: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset.
In the same field of endeavor, Mody discloses, wherein the operations comprise: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset (the minimum capability that the cognitive radio should have is that it should be able to sense the environment, for example, the spectrum, and go into a particular spectrum to try to figure out whether the spectrum is occupied or not occupied. While such capabilities have existed in the past, in the subject invention, one is not just ascertaining whether the spectrum is occupied or not occupied, but rather the system ascertains what exactly the spectrum contains and what kind of signals exist. This is because sometimes one can have certain signals that would indicate that the entire spectrum is occupied and cannot be used, [0031]-[0034]).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify the combination of Tu and Holt by specifically providing wherein the operations comprise: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset, as taught by Mody for the purpose of providing technique of signal processing, communications, pattern classification and machine learning, which are employed to make a dynamic use of the spectrum such that the emanated signals do not interfere with the existing ones [0003].
Regarding claim 26, the combination of Tu and Holt discloses everything claimed as applied above (see claim 15), however the combination of Tu and Holt does not explicitly disclose, wherein the operations comprise: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset.
In the same field of endeavor, Mody discloses, wherein the operations comprise: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset (the minimum capability that the cognitive radio should have is that it should be able to sense the environment, for example, the spectrum, and go into a particular spectrum to try to figure out whether the spectrum is occupied or not occupied. While such capabilities have existed in the past, in the subject invention, one is not just ascertaining whether the spectrum is occupied or not occupied, but rather the system ascertains what exactly the spectrum contains and what kind of signals exist. This is because sometimes one can have certain signals that would indicate that the entire spectrum is occupied and cannot be used, [0031]-[0034]).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify the combination of Tu and Holt by specifically providing wherein the operations comprise: providing the one or more information bits or codewords to a device configured to adjust one or more communications systems associated with the device, or to improve a respective network, wherein providing the one or more information bits or codewords to the device configured to improve the respective network comprises: providing data indicating characteristics of the radio signals, wherein the characteristics of the radio signals include at least one of the following: timing information, center frequency, bandwidth, phase, frequency, rate of arrival, direction of arrival, channel delay response, or offset, as taught by Mody for the purpose of providing technique of signal processing, communications, pattern classification and machine learning, which are employed to make a dynamic use of the spectrum such that the emanated signals do not interfere with the existing ones [0003].
Claims 14 and 27 are rejected under 35 U.S.C. 103 as being unpatentable over Tu, in view of Holt and further in view of Wicker et al. (US 6404750, hereinafter “Wicker”).
Regarding claim 14, the combination of Tu and Holt discloses everything claimed as applied above (see claim 2), however the combination of Tu and Holt does not explicitly disclose, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region.
In the same field of endeavor, Wicker discloses, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region (A cell is a section of the geographic region covered by the wireless network. The purpose of the division into cells is to make the most use out of a limited number of available channels. The sensors in a cluster are tuned to the reverse random access and scheduled channels. The sensors in a cell are connected to a low-bandwidth network that allows for the transmission of sensor data to a single processing site at or near the BSC where the signals are processed by the neural network. Depending on the multiple access scheme employed and the reverse channel structure, the random access and traffic channels may vary in frequency, time slots, spreading code, or all of the above. A single sensor can cover the entire reverse channel spectrum. On the other extreme, a cluster can contain a single sensor for every sub-channel of interest, Col. 3; lines 1-51).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify the combination of Tu and Holt by specifically providing wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region, as taught by Wicker for the purpose of stabilizing a network to minimize delays experienced by users when trying to access the network (Col. 1; lines 5-8).
Regarding claim 27, the combination of Tu and Holt discloses everything claimed as applied above (see claim 2), however the combination of Tu and Holt does not explicitly disclose, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region.
In the same field of endeavor, Wicker discloses, wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region (A cell is a section of the geographic region covered by the wireless network. The purpose of the division into cells is to make the most use out of a limited number of available channels. The sensors in a cluster are tuned to the reverse random access and scheduled channels. The sensors in a cell are connected to a low-bandwidth network that allows for the transmission of sensor data to a single processing site at or near the BSC where the signals are processed by the neural network. Depending on the multiple access scheme employed and the reverse channel structure, the random access and traffic channels may vary in frequency, time slots, spreading code, or all of the above. A single sensor can cover the entire reverse channel spectrum. On the other extreme, a cluster can contain a single sensor for every sub-channel of interest, Col. 3; lines 1-51).
Therefore, it would have been obvious to one of ordinary skill in art before the effective filing date of the claimed invention to modify the combination of Tu and Holt by specifically providing wherein the second machine learning network is trained to generate output that indicates a number of wireless devices that are producing radio signals within a predetermined geographical region, and wherein controlling the second machine learning network to generate the one or more information bits or codewords that represent the radio signals comprises: controlling the second machine learning network to generate an indication of a number of devices that produced the radio signals within a region, as taught by Wicker for the purpose of stabilizing a network to minimize delays experienced by users when trying to access the network (Col. 1; lines 5-8).
Prior Art of the Record:
The prior art made of record not relied upon and considered pertinent to
Applicant’s disclosure:
US 20180367192: he subject matter described in this disclosure can be embodied in methods, apparatuses, and systems for training and deploying machine-learning networks to communicate over RF channels, and specifically to encode and decode information for communication over RF channels using multi-antenna transceivers.
US 10108903: Motion detection systems have been used to detect movement, for example, of objects in a room or an outdoor area. In some example motion detection systems, infrared or optical sensors are used to detect movement of objects in the sensor's field of view. Motion detection systems have been used in security systems, automated control systems and other types of systems.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GOLAM SOROWAR whose telephone number is (571)270-3761. The examiner can normally be reached Mon-Fri: 8:30AM-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, Charles Appiah can be reached at (571) 272-7904. 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.
/GOLAM SOROWAR/ Primary Examiner, Art Unit 2641
Prosecution Insights