DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 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 1-3, 5-6 and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Patel et al. (US 20200136898 A1) in view of Svennebring et al. (US 20190319868 A1).
Regarding claim 1, Patel teaches a traffic prediction method (method of Fig. 2), comprising:
classifying nodes in a metropolitan optical network into multiple node sets based on locations of the nodes (The first clustering block 204 may involve clustering the nodes into groups based on the data received in the data collection, [0042]; The data may include, for example, topology data, telemetry data, geographical data, [0041]; the network may have any suitable communication range associated therewith and may include, for example, global networks (e.g., the Internet), metropolitan area networks , [0037]).
However, Patel does not clearly teach for nodes in each node set, inputting temporal traffic data of the nodes into a traffic prediction model corresponding to the node set to obtain traffic prediction results of the nodes in the node set; wherein, the traffic prediction model is obtained by a deep learning using historical time-series traffic data of the node set as a training set.
In an analogous art, Svennebring teaches for nodes in each node set, inputting temporal traffic data of the nodes into a traffic prediction model corresponding to the node set to obtain traffic prediction results of the nodes in the node set (the spatial-temporal-history data 722 and the real-time data 744 (or subsets thereof) are supplied to the cell load model 710, which is a machine learning (ML) model used to predict one or more cell characteristics, such as an expected cell performance at a given location and time instance. In embodiments, individual cell load models 710 may be generated for respective cells or NANs 131-133, [0179]);
wherein, the traffic prediction model is obtained by a deep learning using historical time-series traffic data of the node set as a training set (The cell load model 710 is generated from one or more ML algorithms using a sample of the spatial-temporal-history data 722 and the real-time data 744 during a training phase, [0179]; the cell load model 710 may be a Recurrent Neural Network (RNN) with a Long Short Term Memory (LSTM), [0180]).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the traffic prediction of Patel with the load prediction of Svennebring to provide a methods and a system to improve wireless network performance by predicting future network behaviors/metrics e.g., bandwidth (BW), latency, capacity, coverage holes, etc. and making applications, user equipment (UE), and/or network infrastructure more aware of these predicted network behaviors/metrics as suggested, Svennebring [0011].
Regarding claim 2, Patel as modified by Svennebring teaches the traffic prediction method according to claim 1, wherein, classifying nodes in the metropolitan optical network into multiple node sets based on locations of the nodes comprises: obtaining bandwidth demand data of the nodes in the metropolitan optical network; classifying the nodes into at least two types based on the bandwidth demand data of the nodes (Once the data is cleaned, clustering and forecasting may be performed. Clustering may involve grouping network elements (e.g., nodes) into groups based on the data received by each of the network elements. For example, network elements may be clustered based on projected growth rates in terms of particular metrics such as bandwidth usage, Patel [0025]); and grouping adjacent nodes of a same type into a node set to obtain the multiple node sets (For example, network elements may be clustered based on projected growth rates in terms of particular metrics such as bandwidth usage. Network elements may also be clustered based on other factors, such as geographical location. In some instances, multiple iterations of clustering may be performed, Patel [0025]).
Regarding claim 3, Patel as modified by Svennebring teaches the traffic prediction method according to claim 1, wherein, the historical time-series traffic data of the node sets is obtained through the following steps: obtaining the bandwidth demand data of nodes comprised in a node set (The GNIS data 306 may also include data such as weekly upstream and downstream bandwidth utilization, the number of aerial and/or buried miles, and other types of information. Examples of such data may be presented below in FIG. 6B. For example, FIG. 6B displays the name of each individual node (e.g., “F-32”) (in the particular example provided in FIG. 6B, data a single node, “F-32” is tracked over time, Patel [0053]); segmenting the bandwidth demand data according to a preset time interval to obtain bandwidth demand data of multiple time periods (The node event data consolidated by week is shown in the “dt” column. For example, the second row may represent data associated with the week of 5/6/18, and so on, Patel [0053]); processing the bandwidth demand data of the multiple time periods to obtain multiple rate data (After receiving all of this data, the system 108 may process the data (e.g., as is described with reference to FIG. 2 or any of the other process flows and or methods described herein) and provide an output, Patel [0038]); and storing the multiple rate data and corresponding time periods to obtain the historical time-series traffic data (Upon categorization of each node into a particular cluster, the node may store information about the cluster it is grouped into, Patel [0067], Table 6).
Regarding claim 5, Patel as modified by Svennebring teaches the traffic prediction method according to claim 1, wherein, a neural network used for the deep learning comprises: any of a recurrent neural network, a bidirectional recurrent neural network, a long short-term memory network, and a bidirectional long short-term memory recurrent network (the cell load model 710 may be a Recurrent Neural Network (RNN) with a Long Short Term Memory (LSTM), Svennebring [0180]).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the traffic prediction of Patel with the load prediction of Svennebring to provide a methods and a system to improve wireless network performance by predicting future network behaviors/metrics e.g., bandwidth (BW), latency, capacity, coverage holes, etc. and making applications, user equipment (UE), and/or network infrastructure more aware of these predicted network behaviors/metrics as suggested, Svennebring [0011].
Regarding claim 6, Patel as modified by Svennebring teaches the traffic prediction method according to claim 1, wherein, after obtaining the traffic prediction results of the nodes, the method further comprises: determining bandwidths of the nodes based on the traffic prediction results of the nodes (The predicted cell change sequence is fed to the cell BW prediction model 1106. Additionally, the spatio-temporal history data is fed to the cell BW prediction model 1106. The cell BW prediction model 1106 uses the predicted cell change sequence and the spatio-temporal history data to predict a BW and other parameters at different time instances or time intervals, Svennebring [0211]).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the traffic prediction of Patel with the load prediction of Svennebring to provide a methods and a system to improve wireless network performance by predicting future network behaviors/metrics e.g., bandwidth (BW), latency, capacity, coverage holes, etc. and making applications, user equipment (UE), and/or network infrastructure more aware of these predicted network behaviors/metrics as suggested, Svennebring [0011].
Regarding claim 9, Patel as modified by Svennebring teaches an electronic device (computing device 1900, Patel Fig. 19A), comprising a memory (memory 1908), a processor (processor 1904), and a computer program stored in the memory and executable on the processor (OS instruction 1918), wherein the processor executes the computer program to implement the method according to claim 1 (The computing device 1900 represents an example implementation of various aspects of the disclosure in which the processing or execution of operations described in connection with systems and methods for network configuration management, Patel [0095]).
Regarding claim 10, Patel as modified by Svennebring teaches a non-transitory computer-readable storage medium (device 1900 of Patel Fig. 19A), which stores computer instructions (OS instruction 1918) for causing a computer to execute the traffic prediction method according to claim 1 (The computing device 1900 represents an example implementation of various aspects of the disclosure in which the processing or execution of operations described in connection with systems and methods for network configuration management, Patel [0095]).
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Patel et al. (US 20200136898 A1) in view of Svennebring et al. (US 20190319868 A1) and further in view of Jalali et al. (US 12393855 B1).
Regarding claim 4, Patel as modified by Svennebring teaches the traffic prediction method according to claim 3, wherein, the rate data comprises: an average rate, a maximum rate, a minimum rate (TNPM data 304 may include a resource ID, a report start date, a report end date, an interface name, a unique name of a given chassis, interface details, speed information, a max percentage utilization, an average utilization, a maximum RF channel utilization percentage, an average RF channel utilization percentage, a 95.sup.th percentile RF channel utilization, Patel [0051] and Fig. 5B).
However, Patel and Svennebring do not teach a first quartile rate, a second quartile rate, and a third quartile rate.
In an analogous art, Jalali teaches a first quartile rate, a second quartile rate, and a third quartile rate (The distribution may be organized into quartiles, quintiles, or any other suitable type of quantile. For example, averaging the 3.sup.rd and 1.sup.st quartiles corresponding to the 75.sup.th and 25.sup.th percentiles of the distribution may be selected and averaged to determine the output of the model. As discussed below in connection with FIG. 6, the average of the 1.sup.st and 3.sup.rd quartiles may, in at least some cases, be a more accurate prediction of the future demand percentile than the median (2.sup.nd quartile or 50.sup.th percentile) of the distribution, col 4, lines 17-26).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the traffic prediction of Patel and Svennebring with the model of Jalali to provide a method to generate, as an output, a value that corresponds to an amount of computing resources that is predicted, over a second time series, to be sufficient to satisfy a threshold level of availability or quality, Jalali Abstract.
Claims 7-8 are rejected under 35 U.S.C. 103 as being unpatentable over Patel et al. (US 20200136898 A1) in view of Svennebring et al. (US 20190319868 A1) and further in view of Patel et al. (US 20140226985 A1) (Hereinafter Patel985).
Regarding 7, Patel as modified by Svennebring teaches the traffic prediction method according to claim 6.
However, Patel and Svennebring do not teach wherein, after determining the bandwidths of the nodes, the method further comprises: determining a source node and a target node for data transmission according to a service request from the source node to the target node; and determining a modulation format for data transmission based on a distance between the source node and the target node as well as a bandwidth request of the service request.
In an analogous art, Patel985 teaches wherein, after determining the bandwidths of the nodes, the method further comprises: determining a source node and a target node for data transmission according to a service request from the source node to the target node (The method includes (a) selecting unconsidered virtual link (VL) (i,j) with a maximum cost, a cost being requested line rate r.sub.ij on VL(i, j).times.shortest distance between nodes i and j, [0018]); and determining a modulation format for data transmission based on a distance between the source node and the target node as well as a bandwidth request of the service request (finding a modulation format that supports requested line rate r.sub.ij with minimum spectrum, [0018]).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the traffic prediction of Patel and Svennebring with the path determination of Patel985 to provide a method wherein the probability of provisioning future VN arrivals is maximized to embed the maximum number of VNs over the network as suggested, Patel [0028].
Regarding 8, Patel as modified by Svennebring and Patel985 teaches the traffic prediction method according to claim 7. Patel985 further teaches wherein, determining a modulation format for data transmission based on a distance between the source node and the target node as well as a bandwidth request of the service request comprises: determining a shortest path from the source node to the destination node; determining a transmission distance of the shortest path (First, the procedure selects a VL, (i, j), with the maximum cost function, where cost is defined as a product of the requested line rate over the VL and the shortest path distance between end nodes of the VL, [0036]); selecting an optimal modulation format according to the transmission distance of the shortest path based on relationships between transmission distance ranges and modulation levels (Next, the procedure selects one of the K-shortest routes k between end nodes of the VL in each iteration, and finds the bit-map of the route. The bit-map of a route can be found by performing logical-AND operations on the bit-vectors of the fibers along the route. Among the offered set of modulation formats by a variable rate transponder, the procedure selects a modulation format that can support the requested line rate over the VL, r.sub.ij, with minimum spectrum, [0036]); and calculating required number of frequency slots for the service request according to the optimal modulation format and the bandwidth request of the service request (number of consecutive wavelength slots at M lowest wavelengths, and evaluates the fragmentation factor F.sub.k.sup.m of the network after provisioning the VL (i, j) at each potential wavelength 1.ltoreq.m.ltoreq.M on the selected route k. A fragmentation factor (FF) is a measure of the network fragmentation, [0036]).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the traffic prediction of Patel and Svennebring with the path determination of Patel985 to provide a method wherein the probability of provisioning future VN arrivals is maximized to embed the maximum number of VNs over the network as suggested, Patel [0028].
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Soldati et al. (US 20240243984 A1): Monitoring the performance of an Artificial Intelligence (AI)/Machine Learning (ML) model or algorithm is disclosed herein. In one embodiment, a method performed by a first network node in a radio communication network comprises sending at least one first message to a second network node of the radio communication network, the at least one first message comprising a subscription request to obtain from the second network node one or more historical data elements associated with the AI/ML model or algorithm.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NICOLE M LOUIS-FILS whose telephone number is (571)270-0671. The examiner can normally be reached Monday-Friday.
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.
/NICOLE M LOUIS-FILS/Examiner, Art Unit 2641
/JINSONG HU/ Supervisory Patent Examiner, Art Unit 2643
Prosecution Insights