DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claim 1 is objected to because of the following informalities:
In claim 1 line 10 the limitation “the branching unit” lacks antecedent basis. Appropriate correction is required.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-8 are rejected under 35 U.S.C. 103 as being unpatentable over Schmogrow et al (US Patent No. 12,387,108 B2) in view of Sato (US Patent No. 9,020,340 B2).
Regarding claim 1, Schmogrow et al teaches a communication system (col. 3, lines 52-54; “…the technology relates to optical communication links, or more generally, optical communication systems.”) comprising:
a processor (col. 13, lines 55-58; “…the computing system 810 includes at least one processor 850 for performing actions in accordance with instructions and one or more memory devices 870 or 875 for storing instructions and data.”); and
a storage medium having computer program instructions stored thereon, when executed by the processor (col. 14, lines 22-25; “The memory 870 may be any device suitable for storing computer readable data. The memory 870 may be a device with fixed storage or a device for reading removable storage media.”), perform to:
update an estimation model, which is a mathematical model for estimating a state of a host system on the basis of information indicating an object characteristic that is a predetermined characteristic of the optical signal (GSNR of the optical link is considered as object characteristic; col. 6, lines 5-17; “…a machine learning model can be tested on a different optical link than the optical link upon which the model was trained. A simulated GSNR of the optical link and link features can be provided to a trained machine learning model, which can output a GSNR. The trained machine learning model can apply GSNR corrections to the simulated GSNR data. The model can provide a GSNR with variability data or confidence intervals for the GSNR data. The same optical link can also be empirically measured for performance metrics, which can be converted into a GSNR. A comparison output from the machine learning model and the empirically measured GSNR data can be performed to assess prediction accuracy.”; col. 17, lines 8-24; “…predicting link design margins, the method comprising: obtaining a plurality of link features associated with an optical link; simulating the optical link with a first model based on the plurality of link features to produce a first value; obtaining empirically one or more performance metrics associated with the optical link; calculating a second value based on the one or more performance metrics; determining one or more prediction error values based on the first value and the second value; training or updating a machine learning model using the plurality of link features and at least one of the one or more prediction error values or the one or more performance metrics.”).
Schmogrow et al teaches obtaining one or more performance metrics associated with the optical link (col. 17, lines 8-24) and network interface driver controller to manage data exchange (col. 14, lines 46-47; “The network interface driver controller 820 manages data exchanges via the network interface driver 822 (also referred to as network interface driver ports).”) and differs from the claimed invention in that Schmogrow et al does not specifically teach branching an optical signal and update the estimation model on the basis of one of the branched optical signals. Sato teaches optical communication system wherein optical signal is branched (col. 3, lines 46-51; “The optical packet signal inputted to the network element 101 is bifurcated by the optical coupler 16. One of the branched-off optical packet signals is inputted to the optical switch unit 12 of the optical packet switching apparatus 10, whereas the other thereof is inputted to the OSNR processing unit 31.”). Since Schmogrow et al teaches obtaining a plurality of link features associated with an optical link, therefore, it would have been obvious to an artisan of ordinary skill in the art before the effective filling date of the claimed invention to modify the optical communication system of Schmogrow et al by providing coupler to branch the optical signal, as taught by Sato, in order to obtain portion of the optical signal to be analyzed and simulated by the model.
Regarding claim 2, the combination of Schmogrow et al as modified by Sato teaches wherein the computer program instructions further perform a series of processes of updating the estimation model from start of learning until a predetermined termination condition related to learning is satisfied at each predetermined timing (col. 6, lines 30-40; “…the technology allows for a more accurate margin by adjusting a physics simulation of an optical network with the results of a trained machine learning model to more accurately match the adjusted simulation results to a “truer” performance of the optical network. The trained machine learning model can provide prediction errors from the physics simulation of the optical network which, when applied to the results of the physics simulation, correct the results of the simulation and more closely tailor them to a “truer” or empirical performance driven model of the optical network.”).
Regarding claim 3, the combination of Schmogrow et al as modified by Sato teaches the wherein the computer program instructions further perform to estimate the state of the host system using the estimation model on the basis of another object characteristic of the optical signal (col. 7, lines 31-42; “Non-limiting examples of link features include the above described characteristics, including type of optical node, amplifier, or fiber, channel frequencies, power spectral densities, and order of optical nodes, and fiber spans. Other link features can be derived from empirically measured link features or known parameters related to the optical link. Additional non-limiting examples of link features can include cumulated chromatic dispersion, cumulated gain profiles, gain responses of a single span, gain responses of multiple spans, frequency response (such as for example, gain, attenuation, noise figures) of individual spans or of the system as a whole.”).
Regarding claim 4, the combination of Schmogrow et al as modified by Sato teaches wherein the estimation model is updated to the estimation model at a point in time when the termination condition is satisfied each time the termination condition is satisfied (col. 6, lines 30-40; “…the technology allows for a more accurate margin by adjusting a physics simulation of an optical network with the results of a trained machine learning model to more accurately match the adjusted simulation results to a “truer” performance of the optical network. The trained machine learning model can provide prediction errors from the physics simulation of the optical network which, when applied to the results of the physics simulation, correct the results of the simulation and more closely tailor them to a “truer” or empirical performance driven model of the optical network.”).
Regarding claim 5, the combination of Schmogrow et al as modified by Sato teaches wherein the object characteristic used for learning of the estimation model is an object characteristic of an optical signal obtained by changing the optical signal (col. 6, lines 30-40; “…the technology allows for a more accurate margin by adjusting a physics simulation of an optical network with the results of a trained machine learning model to more accurately match the adjusted simulation results to a “truer” performance of the optical network. The trained machine learning model can provide prediction errors from the physics simulation of the optical network which, when applied to the results of the physics simulation, correct the results of the simulation and more closely tailor them to a “truer” or empirical performance driven model of the optical network.”; adjusting a physics simulation of an optical network is considered as changing the optical signal).
Regarding claim 6, the combination of Schmogrow et al as modified by Sato teaches wherein the object characteristic is an optical signal-to-noise ratio (OSNR) and polarization mode dispersion (col. 6, lines 5-17; “…a machine learning model can be tested on a different optical link than the optical link upon which the model was trained. A simulated GSNR of the optical link and link features can be provided to a trained machine learning model, which can output a GSNR. The trained machine learning model can apply GSNR corrections to the simulated GSNR data. The model can provide a GSNR with variability data or confidence intervals for the GSNR data. The same optical link can also be empirically measured for performance metrics, which can be converted into a GSNR. A comparison output from the machine learning model and the empirically measured GSNR data can be performed to assess prediction accuracy.”).
Regarding claim 7, Schmogrow et al teaches a communication method executed by a communication system (col. 3, lines 52-54; “…the technology relates to optical communication links, or more generally, optical communication systems.”), a transmitter that transmits an optical signal (col. 6, lines 50-56; “FIG. 1 is a schematic view of network 100. Network 100 can be an optical communication link or an optical network. Network 100 can be made up of one or more network components. Illustrated in FIG. 1 are various exemplary network components, such as optical node 105, optical transponder 110, optical amplifier 115, optical fiber span 120.”), and a learning unit configured to update an estimation model, which is a mathematical model for estimating a state of a host system on the basis of an object characteristic that is a predetermined characteristic of the optical signal on the basis of one of optical signals (GSNR of the optical link is considered as object characteristic; col. 6, lines 5-17; “…a machine learning model can be tested on a different optical link than the optical link upon which the model was trained. A simulated GSNR of the optical link and link features can be provided to a trained machine learning model, which can output a GSNR. The trained machine learning model can apply GSNR corrections to the simulated GSNR data. The model can provide a GSNR with variability data or confidence intervals for the GSNR data. The same optical link can also be empirically measured for performance metrics, which can be converted into a GSNR. A comparison output from the machine learning model and the empirically measured GSNR data can be performed to assess prediction accuracy.”; col. 17, lines 8-24; “…predicting link design margins, the method comprising: obtaining a plurality of link features associated with an optical link; simulating the optical link with a first model based on the plurality of link features to produce a first value; obtaining empirically one or more performance metrics associated with the optical link; calculating a second value based on the one or more performance metrics; determining one or more prediction error values based on the first value and the second value; training or updating a machine learning model using the plurality of link features and at least one of the one or more prediction error values or the one or more performance metrics.”).
Schmogrow et al teaches obtaining one or more performance metrics associated with the optical link (col. 17, lines 8-24) and network interface driver controller to manage data exchange (col. 14, lines 46-47; “The network interface driver controller 820 manages data exchanges via the network interface driver 822 (also referred to as network interface driver ports).”) and differs from the claimed invention in that Schmogrow et al does not specifically teach branching an optical signal and update the estimation model on the basis of one of the branched optical signals. Sato teaches optical communication system wherein optical signal is branched (col. 3, lines 46-51; “The optical packet signal inputted to the network element 101 is bifurcated by the optical coupler 16. One of the branched-off optical packet signals is inputted to the optical switch unit 12 of the optical packet switching apparatus 10, whereas the other thereof is inputted to the OSNR processing unit 31.”). Since Schmogrow et al teaches obtaining a plurality of link features associated with an optical link, therefore, it would have been obvious to an artisan of ordinary skill in the art before the effective filling date of the claimed invention to modify the optical communication system of Schmogrow et al by providing coupler to branch the optical signal, as taught by Sato, in order to obtain portion of the optical signal to be analyzed and simulated by the model.).
Regarding claim 8, the combination of Schmogrow et al as modified by Sato teaches a non-transitory computer-readable medium having computer-executable instructions that, upon execution of the instructions by a processor of a computer, cause the computer to function as the communication system according to claim 1 (col. 17, lines 62-67; “A non-transient computer readable medium containing program instructions, the instructions when executed perform the steps of: simulating the optical link with a first model based on a plurality of link features to produce a first simulated value;…”).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Varughese et al (US Patent No. 12,483,328 B2) is cited to show supplying the optical output data to a trained neural network.
Neog et al (US Patent No. 11,979,186 B2) is cited to show neural network computation of optimum fiber input power.
Sasai et al (US Pub. No. 2023/0106338 A1) is cited to show optical transmission system and characteristic estimation method.
Frankel et al (US Pub. No. 2022/0261686 A1) is cited to show network system modeling using nested models combining machine learning and behavioral approaches.
Kuwabara et al (US Patent No. 11,342,990B2) is cited to show state estimating device and communication system.
Huang et al (US Patent No. 11,133,865 B2) is cited to show optical network performance evaluation using a hybrid neural network.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DALZID E SINGH whose telephone number is (571)272-3029. The examiner can normally be reached Monday-Friday 9-5 ET.
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, DAVID PAYNE can be reached at 571-272-3024. 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.
DALZID E. SINGH
Primary Examiner
Art Unit 2635
/DALZID E SINGH/Primary Examiner, Art Unit 2635