Prosecution Insights
Last updated: April 19, 2026
Application No. 18/544,201

GRAPH BASED ANOMALY DETECTION IN CELLULAR NETWORKS

Final Rejection §103
Filed
Dec 18, 2023
Examiner
LEE, PHILIP C
Art Unit
2454
Tech Center
2400 — Computer Networks
Assignee
Samsung Electronics Co., Ltd.
OA Round
4 (Final)
78%
Grant Probability
Favorable
5-6
OA Rounds
2y 9m
To Grant
96%
With Interview

Examiner Intelligence

Grants 78% — above average
78%
Career Allow Rate
237 granted / 306 resolved
+19.5% vs TC avg
Strong +19% interview lift
Without
With
+18.7%
Interview Lift
resolved cases with interview
Typical timeline
2y 9m
Avg Prosecution
18 currently pending
Career history
324
Total Applications
across all art units

Statute-Specific Performance

§101
6.7%
-33.3% vs TC avg
§103
46.1%
+6.1% vs TC avg
§102
24.1%
-15.9% vs TC avg
§112
16.8%
-23.2% vs TC avg
Black line = Tech Center average estimate • Based on career data from 306 resolved cases

Office Action

§103
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 1-20 have been examined. Response to Argument Applicant’s arguments in the Remarks, filed on 1/28/26 have been fully considered but they are moot in view of new grounds of rejections. Allowable Subject Matter Claims 3-5, 10-12 and 17-19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. 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. Claims 1, 7, 8, 14 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Yen et al, Graph Neural Network based Root Cause Analysis Using Multivariate Time-series KPIs for Wireless Networks, (hereinafter Yen) in view of Liebman, U.S. Patent Application Publication 2023/0085991 (hereinafter Liebman). As per claim 1, Yen teaches the invention substantially as claimed comprising: generating multiple embedded features representing operational data of network elements in a wireless communication network (See III, Problem Formulation, first paragraph; IV, A: Input data, first paragraph, e.g., generating features representing KPI of nodes in 5G wireless network); generating a relationship graph based on the multiple embedded features, the relationship graph representing a behavior of the network elements in the wireless communication network (e.g., building an input graph based on the nodes’ features (see IV, B: Graph Structure Construction, first paragraph), the nodes’ features representing the KPI of the nodes (see IV, A: Input data, first paragraph)); detecting one or more anomalies in the wireless communication network using the relationship graph (e.g., detecting if parts of the networks go wrong using the Input graph (see IV, A: Input data, first paragraph)), the one or more anomalies identifying one or more deviations of one or more network elements from an expected behavior of the one or more network elements (e.g., identifying nodes that are performing normally and nodes that are failing (i.e., nodes that are deviating from expected/normal behavior) (see IV, B: Graph Structure Construction, first paragraph)) that is identified based on a fusing operation (e.g., combing operation Z1=Ɵ1·Xr Z2=Ɵ2·Xr Zˊ1=tanh(α · Z1) Zˊ2=tanh(α · Z2) A=ReLU(tanh(α · (Zˊ1 Zˊ2 – Zˊ2 Zˊ1)))) between the behavior of the network elements and a behavior of neighbor network elements(i.e., combine/fuse nodes’ features/KPIs (including neighboring nodes) to determine nodes that are performing normally and nodes that are failing)) (see IV, B: Graph Structure Construction, first paragraph); and generating network analytics based on the one or more detected anomalies (e.g., CNN generating analysis of possible root causes (e.g., potential root causes (sources) and the other victim nodes (symptoms) based on the detected root cause identification problem (e.g., detected nodes classification) (see IV, C, “Classification”, 2nd paragraph). Yen is silent in regards to the operational data comprises non-numerical data, the non-numerical data being encoded based on a variable encoding operation to identify numerical values of the non-numerical data. Liebman teaches wherein the operational data comprises non-numerical data, the non-numerical data being encoded based on a variable encoding operation to identify numerical values of the non-numerical data ([13], e.g., categorical data being encoded based on on-hot encoding to identify numerical values of the categorical data) It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Liebman’s teaching with Yen’s system in order to allow different types of data including categorial data to be transformed for machine learning training, thus improving the machine learning training in Yen’s system. As per claim 7, Yen and Liebman teach the invention substantially as claimed in claim 1 above. Yen further teach wherein the operational data of the network elements comprises at least one of performance management data, fault management data, and configuration management data (See III, Problem Formulation, first paragraph; IV, A: Input data, first paragraph). As per claims 8 and 15, they are rejected for the same reason as set forth in claim 1 above. See I, “Introduction”, third paragraph; III. “Problem Formulation” (e.g., must comprised a transceiver for collecting and propagating KPI data of nodes from the 5G networks and must comprised a processor to utilizing the KPI data as inputs to train a RCA model…) for a transceiver; and a processor operably connected to the transceiver, the processor configured to perform the method of claim 1. As per claim 14, it is rejected for the same reason as set forth in claim 7 above. Claims 2, 9 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Yen and Liebman in view of Chawathe et al, U.S. Patent Application Publication 2022/0376970 (hereinafter Chawathe). As per claim 2, Yen and Liebman teach the invention substantially as claimed in claim 1 above. Yen and Liebman are silent in regards to scoring the one or more anomalies for prioritization of troubleshooting. Chawathe teaches scoring the one or more detected anomalies for prioritization of troubleshooting ([154], e.g., scoring the anomalies and displaying the highest ranked score anomaly for troubleshooting by a user). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Chawathe’s teaching with Yen’s and Liebman’s system in order to identify highest scored potential cause as the root cause, thus enhancing the root cause analysis in Yen’s and Liebman ’s system. As per claims 9 and 16, they are rejected for the same reason as set forth in claim 2 above. Claims 6, 13 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Yen and Liebman in view of Li et al, U.S. Patent 11,636,090 (hereinafter Li). As per claim 6, Yen and Liebman teach the invention substantially as claimed in claim 1 above. Although Yen teaches network analytics, however, Yen and Liebman are silent in regards to at least one of an anomaly causal graph and a root cause ranking. Li teaches wherein the network analytics comprise at least one of an anomaly causal graph and a root cause ranking (col. 6, lines 56-64; col. 7, lines 36-39). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Li’s teaching with Yen’s and Liebman’s system in order to identify the first ranked potential cause as the root cause, thus enhancing the root cause analysis in Yen’s and Liebman’s system. As per claims 13 and 20, they are rejected for the same reason as set forth in claim 6 above. Conclusion 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 extension fee 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 Philip Lee whose telephone number is (571)272-3967. The examiner can normally be reached on 6a-3p M-F. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Glenton Burgess can be reached on 571-272-3949. 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 http://pair- direct.uspto.gov. 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. /PHILIP C LEE/Primary Examiner, Art Unit 2454
Read full office action

Prosecution Timeline

Dec 18, 2023
Application Filed
Jan 21, 2025
Non-Final Rejection — §103
Apr 24, 2025
Response Filed
Jun 23, 2025
Final Rejection — §103
Aug 22, 2025
Response after Non-Final Action
Sep 26, 2025
Request for Continued Examination
Oct 07, 2025
Response after Non-Final Action
Oct 26, 2025
Non-Final Rejection — §103
Jan 21, 2026
Examiner Interview Summary
Jan 21, 2026
Applicant Interview (Telephonic)
Jan 28, 2026
Response Filed
Feb 19, 2026
Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12603820
SYSTEM AND METHOD FOR CELLULAR NETWORK PREDICTION MODEL ANALYSIS
2y 5m to grant Granted Apr 14, 2026
Patent 12596794
SYSTEMS AND METHODS FOR ADAPTIVE ACTION WITH DISTRIBUTED ENFORCEMENT POINTS
2y 5m to grant Granted Apr 07, 2026
Patent 12598243
Service Request and Response Handling
2y 5m to grant Granted Apr 07, 2026
Patent 12580971
ASSIGNING AGENTS TO COMMUNICATION SESSIONS BASED ON LANGUAGE PREFERENCES IN MOBILE APPLICATIONS
2y 5m to grant Granted Mar 17, 2026
Patent 12580825
APPARATUS, METHOD, AND COMPUTER PROGRAM
2y 5m to grant Granted Mar 17, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

5-6
Expected OA Rounds
78%
Grant Probability
96%
With Interview (+18.7%)
2y 9m
Median Time to Grant
High
PTA Risk
Based on 306 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month