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 .
Claims 26-46 are pending.
Amendments dated 10/29/2025 are entered.
Response to Arguments
Arguments presented 10/29/2025 are fully considered, however they are not persuasive.
Specifically:
Applicant argues that “although Tan teaches that semi-supervised learning can be used to improve clustering, the basis for this clustering is not "a training set of configurations for the radio environments" as claimed. Rather, Tan identifies good cells by training on examples where no configuration modification action is required as indicated by a favorable NormBAM. 0239. In other words, Tan teaches using a training set of devices having favorable network performance metrics (NormBAMs), but not "a training set of configurations for the radio environments" as claimed. “
The examiner respectfully disagrees.
Applicant merely provides general statement their interpretation of Tan’s disclosure and charges the disclosure is not the same as "a training set of configurations for the radio environments" without any detailed analysis as to why so.
The language "a training set of configurations for the radio environments" as claimed is overly vague. The argument relies on the terminology distinction without a functional difference, meaning applicant merely pointed out different label for the data (i.e. “training set of configuration for the radio environment”) but the claim itself is silent on the actual details of the said data. Under BRI, a training set of configurations encompasses any data set used to train a model where the inputs include parameters or data associated with the radio environment. Tan identifies good cells, devices, and best configuration(s), therefore Tan’s training set consists of configurations of the radio environment that are labelled as ‘good’.
Tan in ¶0239, discloses: “semi-supervised learning (EM) to augment clustering for improved thresholding of the NormBAM metric, e.g., NormBAMs of good performing cells (low interferer, high quality, good coverage) taken from optimized configurations can provide labeled training examples in the “no action” range of points.”. ¶0245, “algorithm may learn which cells j under which configurations under which current NormBM(j) and NormBAM(j) (action) values produce the largest reduction (Gain) in NormBM(j) on average”.
That is to say Tan trains the model/algorithm using a plurality of configurations as training material (i.e. a set of training configuration), which are used for optimization of operation with the wireless environment (thus “for the radio environment). If Tan trains the model on the configurations to find one that produced the optimized performance, it meets the claim language.
As such the arguments are not persuasive.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 26-46 is/are rejected under 35 U.S.C. 102(a)(1) as being unpatentable over
Tan et al. (US 2016/0162783).
As to claims 26, 36, and 46 :
Tan discloses a method, implemented by a computing device, as well as a computing device comprising: processing circuitry and a memory, the memory containing instructions executable by the processing circuitry, (¶0251, 0174, processor, memory/CRM) whereby the computing device is configured to perform the method comprising:
generating, from a network graph representing a plurality of network elements in a wireless communication network, a model of the wireless communication network that groups the network elements having similar radio environments together, wherein generating the model is based on a plurality of network performance (¶0164, 0242, 0123, 0218, 0081 using a constructed graph of cell nodes to identify clusters of cells. Components of evaluation includes KPI/KQI of each coverage area.
generating a network configuration recommendation for at least one of the network elements based on the model; Models of clusters determined include cells that have similar cell features points, metrics, geographic areas (neighbors)) and a training set of configurations for the radio environment; (¶0239, “semi-supervised learning (EM) to augment clustering for improved thresholding of the NormBAM metric, e.g., NormBAMs of good performing cells (low interferer, high quality, good coverage) taken from optimized configurations can provide labeled training examples in the “no action” range of points.”. ¶0245, “algorithm may learn which cells j under which configurations under which current NormBM(j) and NormBAM(j) (action) values produce the largest reduction (Gain) in NormBM(j) on average”. See also ¶0103, 0171. Different set of configurations are provided to the algorithm for training, through the algorithm learn which set(s) produce the most optimal result, i.e. largest gains)
generating a network configuration recommendation for at least one of the network elements based on the model. (See at least, Fig. 3, step 320, 340, Fig. 23, step 2304, based on processing parameters above, generate global/local solutions, i.e. network configurations for each nodes in the group/cluster, ¶0010, “Each of the global solutions includes multiple local solutions that specify wireless configuration parameters for local coverage areas in the wireless network”. See also ¶0121, 0189, 190)
and modifying a configuration of the at least one of the network elements in accordance with the network configuration recommendation. (Fig. 23 -2308, Fig. 4, 490, ¶0121, 0171, 0096, 0011, modifying configuration of at least an AP/nodes based on the solution).
Claim 46 is directed to a non-transitory computer readable medium storing a computer program product for controlling a computing device in a wireless communication network, the computer program product comprising software instructions that, when run on the computing device, cause the computing device to perform similar steps as in claim 26, and is rejected by the same reasoning as above.
As to claims 27, 37:
Tan discloses all limitations of claim 26/36, wherein generating the model is further based on configurations of the network elements. (¶0239, “semi-supervised learning (EM) to augment clustering for improved thresholding of the NormBAM metric, e.g., NormBAMs of good performing cells (low interferer, high quality, good coverage) taken from optimized configurations can provide labeled training examples in the “no action” range of points.”. ¶0245, “algorithm may learn which cells j under which configurations under which current NormBM(j) and NormBAM(j) (action) values produce the largest reduction (Gain) in NormBM(j) on average”. See also ¶0103, 0171)
As to claims 28, 38:
Tan discloses all limitations of claim 26/36, further comprising:
receiving configuration and performance metric data describing the wireless communication network; and generating the network graph from the configuration and performance metric data and at least one signal quality threshold for each of a plurality of handover events for each of the network elements. (¶0103, gathering KPI and cell configurations, ¶0171, performing iterations of evaluation of current configuration, ¶02422, 0141, constructing neighbor graph from config, builds interaction graph GU based on KPI interactions of neighbor nodes. Table 2 includes handover hysteresis and CIO, 0093, mobility are inputs to decision rules, use T2/T3 as handover criteria)
As to claims 29, 39:
Tan discloses all limitations of claim 26/36, further comprising: identifying, as behavioral outliers, one or more network elements that are represented in the network graph and omitted from the groups of network elements having similar radio environments; wherein generating the network configuration recommendation based on the model comprises generating the network configuration recommendation based on a portion of the model that excludes the one or more network elements identified as behavioral outliers. (¶0134-0135, identifying over shooter cells based on performance parameters. ¶0245, “Cells that produce extreme/sustained negative gain may be removed from Whitebox list first for no action and then passed on to Blackbox for Oppositional, Exploitative and Explorative Action”. ¶0242-0245, cell with problematic behaviors are dropped from the clique GU, thus only considered those with better cells)
As to claims 30, 40:
Tan discloses all limitations of claim 26/36, further comprising applying rule-based criteria to determine whether configuring the wireless communication network in accordance of the network configuration recommendation would produce a mobility ping-pong effect. (¶0063, ¶0241, “Several cells in the same area (neighbors of each other or have common neighbors) being up-tilted/powered-up at the same time may lend a multiplier effect to such increase in interfered UEs and worsen quality. This can create instability in system performance when successive similar actions run away (due to competition between neighbors) or successive opposite actions on a cell engender oscillations ”. See also ¶0238, 0190, 0189, making adjustments to power level, antenna tilts, to reduce interreferences, i.e. the causes for ping-pong effect)
As to claims 31, 41:
Tan discloses all limitations of claim 26/36, further comprising: aggregating the network performance metrics into fewer network performance metrics; wherein generating the model based on the plurality of network performance metrics is responsive to determining the radio environments that are similar based on the fewer network performance metrics. (¶0118, data are extracted, filtered/aggregated, i.e. condensing the data pool. ¶0105, cell metrics are converted to more generalized parameter, such as “blame” score. ¶0098, “system objective functions and cell level metrics may be aggregations of UE state information (e.g., MRs, etc.)”
As to claims 32, 42:
Tan discloses all limitations of claim 26/36, wherein the network graph representing the plurality of network elements in the wireless communication network further represents a plurality of operator networks, each of which comprises at least one of the network elements. (¶0242, “interaction graph GU of up-tilt/power-up candidate cell nodes with edges between them if they are neighbors or have significantly interacting common neighbors. Use the B(i,j) matrix (e.g., blame metric) as a guideline for figuring out “significant” interacting neighbors”, note that cell node (access point) is the network element)
As to claims 33, 43:
Tan discloses all limitations of claim 26/36, wherein generating the model that groups the network elements having similar radio environments together comprises :determining a preliminary group of network elements; and identifying at least two of the groups of network elements from within the preliminary group of network elements, the at least two of the groups having radio environments are different from each other. (¶0123, cells with similar signature maybe clustered together, . ¶0216, groups similar points together based on cluster membership, i.e. over-shooter vs. non-over shooter, ¶0147, 0094 showing generating a group of cell with common characteristic, then narrowing it down to sub groups of such cell. ¶0178-0179, categorizing cells in the general pool into various “blames” category groups)
As to claims 34, 44:
Tan discloses all limitations of claim 26/36, wherein generating the network configuration recommendation for the at least one of the network elements comprises generating the network configuration recommendation for one of the groups of network elements having a similar radio environment. (¶0121, 0220, 0168, recommended adjustment applied to entire a cluster of the plurality of clusters)
As to claims 35, 45:
Tan discloses all limitations of claim 26/36, wherein the network configuration recommendation comprises: an indication of whether the network configuration recommendation is predicted to accelerate or delay mobility within the wireless communication network; and/or a recommended threshold for triggering a mobility event; and/or an indication of a predicted performance impact that will be caused by adopting the network configuration recommendation; and/or a probability that the radio environment of the at least one of the network elements for which the network configuration recommendation was generated is a behavioral outlier relative to the groups of network elements having similar radio environments.
(See Table 2, handover hysteresis/offset (i.e. threshold for triggering a mobility event), ¶0123, “KPI predictive models for groups of similar cells can predict network performance given predictors such as traffic and resource consumption variables. KPI predictive models may also predict gains/losses due to the application of a new feature on a given type or group of cells”, evaluate a future impact of an application of a new configuration)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 9538401 - A device may receive an initial set of network parameter values, associated with cells of a cellular network, that are measured or calculated based on communications associated with the cells of the cellular network. The device may determine a set of feature values, associated with the cells of the cellular network, using the initial set of network parameter values. The device may cluster the cells of the cellular network into a first group of clusters using a first clustering technique, and may cluster the cells of the cellular network into a second group of clusters using a second clustering technique. The device may cluster the cells of the cellular network into a final group of clusters based on the first group of clusters and the second group of clusters, and may output information associated with the final group of clusters of the cells of the cellular network..
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to QUAN M HUA whose telephone number is (571)270-7232. The examiner can normally be reached 10:30-6:30.
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, Anthony Addy can be reached at 571-272-7795. 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.
/QUAN M HUA/Primary Examiner, Art Unit 2645