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 .
Priority
The present application does not claim for foreign priority.
This application is a 371 of PCT/EP2022/055178 filed on 3/1/2022.
Information Disclosure Statement
The information disclosure statement (IDS) was submitted on 8/29/2024. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement has been considered by the examiner.
Specification
The abstract of the disclosure is objected to because of following informalities:
The abstract contains reference numbers of elements or steps such as (11) in lines 3 and 4. For clarity, it is suggested to remove the reference numbers from the Abstract. See, MPEP §608.01(b).
Appropriate correction is required.
Claim Objections
Claims 1-18 are objected because of the following informalities:
In claims 1-5, 8-14, 17, and 18, it is suggested to remove the reference numbers such as (11), (201), (202), and (203) for clarity.
In claims 1-3, 8-10, 13, and 17, it is suggested to use parenthesis instead of comma for definition of acronyms such as “radio access network (RAN)”, “key performance indicator (KPI)”, and “root cause analysis (RCA)”.
In claims 3, 5, 10, 12, 13, 14, 17, and 18, it is suggested to use replace “analysing” with “analyzing” to conform to accepted American English spelling convention used in U.S. patent practice.
In claims 6, 7, 15, and 16, it is suggested to amend the preamble to read “A non-transitory computer readable storage medium storing a computer program comprising instructions that, when executed by one or more processors, cause the one or more processors to carry out …” for clarity.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 3-5, 8-14, 17, and 18 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Regarding claims 3, 10, 13, and 17:
Claims 3, 10, 13, and 17 recite multiple limitations or elements without a connection conjunction such as “and” or “or” between the recited limitations. As drafted, it is unclear whether the recited limitations are all required elements of the claimed invention, whether they represent alternative limitations, or whether some other relationship is intended. Therefore, the metes and bounds of the claim cannot be determined with reasonable certainty. Accordingly, the scope of the claim in indefinite.
Applicant is required to amend the claim to clarify the relationship between the recited limitations, for example by introducing an appropriate conjunction (“and” or “or”), or by otherwise clarifying the intended claim scope.
Regarding claim 8:
Claim 8 recites “A network node” which is a machine related apparatus claim. However, the claim only recites actions and steps with no sufficient corresponding structural elements in the claim. As such, the claim is indefinite.
Regarding claims 4, 5, 9, 11, 12, 14, and 18:
Claims 4, 5, 9, 11, 12, 14, and 18 are also rejected because they are directly or indirectly dependent upon the rejected claim, as set forth above.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 6, 7, 15, and 16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
Regarding claims 6 and 15:
The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because claims 6 and 15 are directed toward a computer program product (i.e., software per se) which does not qualify as a statutory category. The claim remains unpatentable. The preamble should be amended to disclose “A non-transitory computer readable storage medium storing a computer program comprising …”.
Regarding claims 7 and 16:
Claims 7 and 16 are directed to “A computer-readable storage medium”, which is non-statutory (such as transitory forms of signal) unless claimed as “A non-transitory computer readable storage medium storing a computer program comprising …”. See In re Nuijten, 500 F.3d 1346,1356-57 (Fed. Cir. 2007) and Interim Examination Instructions Subject Matter Eligibility Under 35 U.S.C. 101, Aug. 24, 2009; p.2.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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 1, 2, 6-9, 15, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Sharma et al. (US 2020/0084087 A1, hereinafter Sharma) in view of Sukkhawatchani et al. (“Performance Evaluation of Anomaly Detection in Cellular Core Networks using Self-Organizing Map”, Proceedings of ECTI-CON 2008, hereinafter Sukkhawatchani).
Regarding claim 1:
Sharma teaches a method (see, Sharma: Fig. 2 and Fig. 6) performed by a network node (see, Sharma: Fig. 1, System 100) for anomaly detection in a radio access network, RAN, (see, Sharma: Fig. 1, Mobile Network 110) in a communication network, the method comprising:
obtaining key performance indicators, KPI, for predicting one or more characteristics of the RAN (see, Sharma: Fig. 2, Collecting Network Usage Data S210; para. [0061], “S210 includes collecting network usage data of a mobile network at a network analysis platform, as described above with respect to the network model engine 130, mobile network 110, and network analysis platform 105. The method can optionally include determining user sessions from the network usage data (e.g., as described above with respect to the user session compiler, etc.).”; Fig. 6 and para. [0072], “Receiving RAN data S610 functions to receive RAN data generated by a set of base stations for anomaly detection. The received RAN data may be later analyzed for anomalies. RAN data can be continuous, discrete (periodic or aperiodic), timeseries, or in any other appropriate format.”; Also, see para. [0020] [0022] [0028] [0039] [0041] [0042] [0061] [0069].));
classifying data related to the obtained KPIs in a multiclass classification incorporated into a machine-learning neural network model (see, Sharma: Fig. 2, Training Machine Learning Models S230 & Classifying Root Cause(s) S250; para. [0068], “S230 includes training one or more machine learning models using the generated network model, as described above with respect to the machine learning engine 1400.”; para. [0063], “S250 includes classifying, with the machine learning models or additional machine learning models, the anomaly as resulting from one or more root causes, as described above with respect to classification engine 160.”; Fig. 6 and para. [0077], “S640 is preferably performed by a set of root cause classifiers which are included in the network analysis platform.”). Also, see para. [0019] [0027] [0028] [0031] [0036] [0040-0042] [0045] [0056] [0063] [0068] [0069].).
Sharma does not explicitly teach wherein classifying multivariate data related to the obtained KPIs using an unsupervised self-learning neural network model.
In the same field of endeavor, Sukkhawatchani teaches wherein classifying multivariate data related to the obtained KPIs using an unsupervised self-learning neural network model (see, Sukkhawatchani: Section I, “an application of the competitive learning algorithms as Self-Organizing Map (SOM) in analyzing and monitoring traffic anomalies in a cellular mobile network operated by cellular network service operator in Thailand is presented. The SOM is an unsupervised neural network and widely applied to pattern recognition and data mining tasks.”; Section II, “The second step involves identifying the method used to classify a newly measured state vector xnew as normal or abnormal. Single threshold methods, such as the univariate and the multivariate anomaly detection tests [7] are currently deployed by local cellular network operators. … B. Multivariate Anomaly Detection Test”; Section III., “Figs. 3 shows that the anomaly detection improves as the number of neurons is increased. This suggests that the more the neurons used, the “finer” the classification SOM becomes resulting in enhanced detection performance.”).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Sharma in combination of the teachings of Sukkhawatchani in order to apply an unsupervised neural network method, such as the Self-Organizing Map (SOM), to detect anomaly states in an actual cellular mobile network (see, Sukkhawatchani: Section I. Introduction; Section V. Conclusions.).
Sharma in view of Sukkhawatchani further teaches wherein providing anomaly classification with a root cause of the classified multivariate data from the unsupervised self-learning neural network model (see, Sharma: Fig. 2, Training Machine Learning Models S230 & Generating Alerts S260; para. [0068], “S230 includes training one or more machine learning models using the generated network model, as described above with respect to the machine learning engine 1400.”; para. [0064], “S260 optionally includes generating one or more alerts for the anomaly, as described above with respect to alert engine 170.”; Fig. 6 and para. [0076], “The anomalous cell detector is preferably a neural network, but can additionally or alternately be any other appropriate detector. S634 can additionally or alternately output cell id, duration, KPI symptoms, or have any other appropriate output. S634 preferably occurs before determining a root cause for each anomaly, but additionally or alternately may happen at any other appropriate time in the method, or appropriately in relation to any other step in the method.”; para. [0077], “S640 is preferably performed by a set of root cause classifiers which are included in the network analysis platform. Preferably there is a single root cause classifier for each of type of root cause, but additionally or alternately there may be multiple root cause classifiers for each root cause, multiple root causes classified by each root cause classifier, and/or any appropriate number of root cause classifiers configured in any appropriate manner. S640 takes in anomalies (anomalous user sessions or anomalous cells) as an input and outputs a root cause.”; Also, see para. [0020] [0027] [0040] [0042] [0045] [0046] [0063] [0064] [0068-0070].).
Regarding claim 2:
As discussed above, Sharma in view of Sukkhawatchani teaches all limitations in claim 1.
Sharma further teaches wherein classifying the multivariate data comprises classifying labelled results indicating multivariate anomalies to be identified as the root causes by indicating root cause analysis, RCA, counters that are contributing factors (see, Sharma: para. [0077], “S640 can determine one or more root causes for each anomaly (e.g., concurrently, serially, etc.). S640 is preferably performed by a set of root cause classifiers which are included in the network analysis platform.”; para. [0078], “Determining a number of anomalous user sessions for each root cause S650 functions to determine the impact (e.g., severity, severity score) of a particular root cause in terms of a number of affected user sessions. S650 is preferably performed by the network analysis platform, but may additionally or alternately be performed wholly or in part by any other appropriate component. S650 may additionally or alternately operate for a group of related root causes or user/cell anomalies. S650 takes in anomalous user sessions as an input, and outputs a number. S650 may additionally or alternately output a cell id or a duration (duration which spans user session anomalies and/or network anomalies). S650 may group anomalous user sessions based on a group time (e.g., group for a period of 1 hr).”; para. [0079], “The alert may include: a severity score for the root cause. A severity score may be, or be determined based on: a number of users or user sessions impacted by the root cause, a percentage of users or user sessions (for a cell, region, network, etc.) impacted by the root cause, a duration of anomalous user sessions, a weight associated with the severity degree to which each session was impacted, and/or otherwise determined.”); and/or training sequential data and classifying the sequential data into root cause classes using multiclass anomaly classifier (see, Sharma: para. [0028], “In variants, the machine learning engine 140 leverages the mobile network model in training the machine learning models. In some embodiments, the machine learning engine 140 trains the machine learning models by feeding training set data into the models. The training set data can include: the received and/or collected network usage data (e.g., historic, subsequent data collected after new configuration deployment), profile information or customized preferences for the mobile operator (such as through an account the operator has within the network analysis platform), operator-labeled training data, historical data used for past training of models, heuristics, rules, statistical techniques, and any other data that would be useful in training the machine learning models for anomaly detection and/or analysis purposes. In preferred embodiments, the network model, machine learning models, network usage data, heuristics, rules, thresholds, and/or other data or models used as training set data are all different per mobile network and/or per operator of a mobile network, as a result of the mobile network's unique usage data, behavioral traits, and generated network model.”; para. [0029], “In some embodiments, the training set data ingested by the models includes labeled datasets of “normal” behavior of the mobile network, which are received or generated by one or more components of the network analysis platform 105. In some embodiments, the labeled datasets of bad emails include human-labeled “normal” behavioral traits and/or usage data. Through human labeling from, e.g., mobile network operators and/or administrators, employees, security service representatives, and/or network analysis representatives, a set of human-labeled training set data can be used to train the machine learning models based on that mobile network.”.).
Regarding claim 6:
Claim 6 is directed towards a computer program product (see, Sharma: para. [0087]) comprising instructions, which, when executed on at least one processor, cause the at least one processor (see, Sharma: para. [0087]) to carry out a method according to claim 1, as performed by the network node. Therefore, claim 6 is rejected by applying the similar rationale used to reject claim 1 above.
Regarding claim 7:
Claim 7 is directed towards a computer-readable storage medium (see, Sharma: para. [0087]), having stored thereon a computer program product (see, Sharma: para. [0087]) comprising instructions which, when executed on at least one processor, cause the at least one processor (see, Sharma: para. [0087]) to carry out a method according to claim 1 as performed by the network node. Therefore, claim 7 is rejected by applying the similar rationale used to reject claim 1 above.
Regarding claim 8:
Claim 8 is directed towards a network node configured to perform the method of claim 1. Therefore, claim 8 is rejected by applying the similar rationale used to reject claim 1 above.
Regarding claim 9:
Claim 9 is directed towards the network node according to claim 8 that is further limited to similar features to claim 2. Therefore, claim 9 is rejected by applying the similar rationale used to reject claim 2 above.
Regarding claim 15:
Claim 15 is directed towards a computer program product (see, Sharma: para. [0087]) comprising instructions, which, when executed on at least one processor, cause the at least one processor (see, Sharma: para. [0087]) to carry out a method according to claim 2, as performed by the network node. Therefore, claim 15 is rejected by applying the similar rationale used to reject claim 2 above.
Regarding claim 16:
Claim 16 is directed towards a computer-readable storage medium (see, Sharma: para. [0087]), having stored thereon a computer program product (see, Sharma: para. [0087]) comprising instructions which, when executed on at least one processor, cause the at least one processor (see, Sharma: para. [0087]) to carry out a method according to claim 2, as performed by the network node. Therefore, claim 16 is rejected by applying the similar rationale used to reject claim 2 above.
Claims 3, 10, 13, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Sharma in view of Sukkhawatchani further in view of Li et al. (“Anomaly detection for cellular networks using big data analytics”, IET Communications, 2019, Vol. 13, Issue 20, pp. 3351-3359, hereinafter Li).
Regarding claim 3:
As discussed above, Sharma in view of Sukkhawatchani teaches all limitations in claim 1.
Sharma in view of Sukkhawatchani does not explicitly teach wherein obtaining the KPIs comprises detecting anomalous KPIs over one or more time periods; statistically analysing one or more clusters of detected anomalous KPIs, by analysing anomalous behavior pattern of the detected anomalous KPIs; filtering the one or more clusters with root cause analysis, RCA, counter values and KPIs above thresholds to identify RCA counters of the KPIs.
In the same field of endeavor, Li teaches wherein obtaining the KPIs comprises detecting anomalous KPIs over one or more time periods (see, Li: Section 4.1.3, Counter filter, “Those aforementioned KQIs/KPIs are averaged over a given time period, e.g., one hour.”); statistically analysing one or more clusters of detected anomalous KPIs, by analysing anomalous behavior pattern of the detected anomalous KPIs (see, Li: Section 2.1.1 Statistical signal processing & Section 2.2.3 Clustering-based methods”); filtering the one or more clusters with root cause analysis, RCA, counter values and KPIs above thresholds to identify RCA counters of the KPIs (see, Li: Secion 4.1.3, Postprocessing: … Count filter).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Sharma in view of Sukkhawatchani in combination of the teachings of Li in order to filter the hours which do not have enough sessions (see, Li: Secion 4.1.3, Postprocessing: … Count filter).
Regarding claim 10:
Claim 10 is directed towards the network node according to claim 8 that is further limited to similar features to claim 3. Therefore, claim 10 is rejected by applying the similar rationale used to reject claim 3 above.
Regarding claim 13:
As discussed above, Sharma in view of Sukkhawatchani teaches all limitations in claim 2.
Sharma in view of Sukkhawatchani does not explicitly teach wherein obtaining the KPIs comprises detecting anomalous KPIs over one or more time periods; statistically analysing one or more clusters of detected anomalous KPIs, by analysing anomalous behavior pattern of the detected anomalous KPIs; filtering the one or more clusters with root cause analysis, RCA, counter values and KPIs above thresholds to identify RCA counters of the KPIs.
In the same field of endeavor, Li teaches wherein obtaining the KPIs comprises detecting anomalous KPIs over one or more time periods (see, Li: Section 4.1.3, Counter filter, “Those aforementioned KQIs/KPIs are averaged over a given time period, e.g., one hour.”); statistically analysing one or more clusters of detected anomalous KPIs, by analysing anomalous behavior pattern of the detected anomalous KPIs (see, Li: Section 2.1.1 Statistical signal processing & Section 2.2.3 Clustering-based methods”); filtering the one or more clusters with root cause analysis, RCA, counter values and KPIs above thresholds to identify RCA counters of the KPIs (see, Li: Secion 4.1.3, Postprocessing: … Count filter).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Sharma in view of Sukkhawatchani in combination of the teachings of Li in order to filter the hours which do not have enough sessions (see, Li: Secion 4.1.3, Postprocessing: … Count filter).
Regarding claim 17:
Claim 17 is directed towards the network node according to claim 9 that is further limited to similar features to claim 13. Therefore, claim 17 is rejected by applying the similar rationale used to reject claim 13 above.
Claims 5 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Sharma in view of Sukkhawatchani further in view of Li further in view of Thampy et al. (US 2021/0176115 A1, hereinafter Thampy).
Regarding claim 5:
As discussed above, Sharma in view of Sukkhawatchani and Li teaches all limitations in claim 3.
Sharma in view of Sukkhawatchani and Li does not explicitly teach wherein classifying the multivariate data comprises providing feedback to the statistical analysing until a detection rate crosses or reaches a threshold set by an operator.
In the same field of endeavor, Thampy teaches wherein classifying the multivariate data comprises providing feedback to the statistical analysing until a detection rate crosses or reaches a threshold set by an operator (see, Thampy: para. [0010], “The service uses an optimization function to identify a set of thresholds for the KPIs. The optimization function is based on: a comparison between the target alarm rate and a fraction of network issues flagged by the service as outliers, KPI thresholds selected based on the lists of unique values from the time series, and a number of thresholds that the KPIs must cross for the service to raise an alarm. The service raises an anomaly detection alarm for the monitored network based on the identified set of thresholds for the KPIs.”; para. [0056], “The techniques herein allow for the selection of optimal thresholds within a network assurance service for key performance indicators (KPIs) of a monitored network that can be used for providing alarms/alerts to a network administrator.”; para. [0080], “threshold optimizer 410 may select a Tr value that specifies the target rate at which service 302 is expected to report anomaly detection alarms. In some embodiments, FCM 412 can collect feedback regarding Tr from the user via the UI. For example, FCM 412 may allow the user to rate a reported anomaly with a thumbs up or a thumbs down, to indicate whether the user considers the reported anomaly to be of relevance. In turn, threshold optimizer 410 may use this feedback to dynamically adjust the Tr value over time (e.g., by lowering the reporting rate if the user deems too many alerts as irrelevant or increasing the reporting rate if the user consistently deems the reported alerts as relevant). In another embodiment, threshold optimizer 410 may adjust Tr based on feedback from a third party application that determines whether a given issue meets specific criteria to be considered as valid. As would be appreciated, Tr can be represented as a percentage, number of anomalies in a predefined time period (e.g., reported anomalies per day, week, etc.).”).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Sharma in view of Sukkhawatchani and Li in combination of the teachings of Thampy in order to allow for the selection of optimal thresholds within a network assurance service for key performance indicators (KPIs) of a monitored network that can be used for providing alarms/alerts to a network administrator (see, Thampy: para. [0056]).
Regarding claim 12:
Claim 12 is directed towards the network node according to claim 10 that is further limited to similar features to claim 5. Therefore, claim 12 is rejected by applying the similar rationale used to reject claim 5 above.
Allowable Subject Matter
Claims 4, 11, 14, and 18 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112(pre-AIA ), 2nd paragraph, set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JI-HAE YEA whose telephone number is (571) 270-3310. The examiner can normally be reached on MON-FRI, 7am-3pm, 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, SUJOY K KUNDU can be reached on (571) 272-8586. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JI-HAE YEA/Primary Examiner, Art Unit 2471
Prosecution Insights