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 .
This action is responsive to the Amendment filed on 12/11/2025.
Claims 1-20 are pending in the case.
Response to Arguments
Applicant's arguments and amendments with regards to the 35 U.S.C. § 102 and 103 rejection of claim(s) 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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 (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 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 1-6, 10-15, 19, 20, are rejected under 35 U.S.C. 103 as being unpatentable over Asres et al “Supporting Telecommunication Alarrn Management System With Trouble Ticket Prediction”, IEEE Transactions on Industrial Informatics, New York, NY, US, vol 17, no. 2, 25 May 2020, pages 1459-1469, XPO1 1821348, ISSN: 1551-3203, DO 10.1 709/TI 2020 2996942 (retrieved on 2020-11-19), in view of Bhalla (US 20200259700 A1), Saraiya (US 20210406041 A1) and Arzani (US 20210224676 A1).
Regarding claim 1, Asres teaches perform steps of (Asres Abstract, process to classify alarms):
receiving alarms from a network (Asres Pg 1460, Rt Col, lines 8-14, streaming data for network alarms is received);
utilizing a machine learning model to classify the alarms as one of important and non-important for a ...Network Operations Center (NOC) (Asres Pg1460-Left-lines14-16, Pg1460-Left-LastPara and Pg1460-Rt-lines1-7, SectionV-1st two paragraphs, Figs. 1 and 2, machine learning (ML) model(s) are used to classify alarms as true-positive or false-positive and as major (non-important) or critical (important), Asres Pg1459-Rt, Pg1460-Left-LastPara, Sec IV.A.1, Table II, model may be for alarms for NOC operator(s)); and
displaying the important alarms and suppressing display of the non-important alarms (Asres Pg1460-Left-lines14-16, Pg1460-Left-LastPara and Pg1460-Rt-lines1-21, relevant alarms are presented to operators and non-relevant alarms are suppressed (as noted above relevance may be determined as major or ciritcal).
Asres does not specifically teach a non-transitory computer-readable medium software including instructions executable by one or more processors that, in response to such execution, cause the one or more processors to perform steps of: utilizing a machine learning model to classify the alarms as one of important and non-important for a particular role of a ... team or person based on a plurality of insights including (1) roles of different teams or people, (2) predicted service impact, (3) predicted level of priority of resolving the alarm, and (4) predicted time and resource required for resolution, wherein the machine learning model generates the plurality of insights for each alarm and combines the plurality of insights to produce a role-specific importance classification such that an alarm is classified as important for the particular role and non-important for a different role; and displaying, to a user, the important alarms that are classified as important for the role of the user based on the plurality of insights and the role of the user viewing the alarms, and suppressing display of the non-important alarms that are classified as non- important for the role of the user.
However Bhalla teaches a non-transitory computer-readable medium storing instructions executable by one or more processors that, in response to such execution, cause the one or more processors to perform steps of (Bhalla [3, 21, 37, 68, 140, 141] processor executes instructions stored in medium, invention is directed towards classifying network alarms as critical and non-critical so that short-term staff can concentrate on urgent service-affecting issues).
It would have been obvious to one of an ordinary skill in the art before the effective filing date of the claimed invention, to have incorporated the concept taught by Bhalla of a non-transitory computer-readable medium software including instructions executable by one or more processors that, in response to such execution, cause the one or more processors to perform steps of, into the invention suggested by Asres; since both inventions are directed towards classifying network alarms as critical and non-critical, and incorporating the teaching of Bhalla into the invention suggested by Asres would provide the added advantage of using generic or well-known processors and memory to store and execute instructions that allow short-term staff can concentrate on urgent service-affecting issues, and the combination would perform with a reasonable expectation of success (Bhalla [3, 21, 37, 68, 140, 141]).
Asres and Bhalla do not specifically teach utilizing a machine learning model to classify the alarms as one of important and non-important for a particular role of a ... team or person based on a plurality of insights including (1) roles of different teams or people, (2) predicted service impact, (3) predicted level of priority of resolving the alarm, and (4) predicted time and resource required for resolution, wherein the machine learning model generates the plurality of insights for each alarm and combines the plurality of insights to produce a role-specific importance classification such that an alarm is classified as important for the particular role and non-important for a different role; and displaying to a user the important alarms that are classified as important for the role of the user based on the plurality of insights and the role of the user viewing the alarms that are classified as non- important for the role of the user.
However Saraiya teaches utilizing a machine learning model to classify the ...importance of ....alarms ... based on a plurality of insights including (1) roles of different teams or people, (2) predicted service impact, (3) predicted level of priority of resolving the alarm, and (4) predicted time and resource required for resolution, wherein the machine learning model generates the plurality of insights for each alarm and combines the plurality of insights to produce a role-specific importance classification ... (Saraiya [49, 68, 69, 71, 72, 74, 79, 81, 82, 116, 151, 154] insights may be generated to determine importance classification (critical) of alarms, insights may include (1) roles of different teams or people (Saraiya [71, 116, 151, 154], (2) predicted service impact (Saraiya [82], (3) predicted level of priority of resolving the alarm (Saraiya [49, 68, 69, 81]), and (4) predicted time and resource required for resolution (Saraiya [72, 74, 79]); and
displaying the ...classified... alarms based on the plurality of insights (Saraiya [57] alarms may be displayed based on determined classification, which is determined based on insights, Also see Saraiya [69-71, 116, 127, 137, 138, 150-154, 181, 201, 207-214, 237] data regarding alarms (for e.g. network related IT incidents)- including priority, how event was resolved, team and/or personnel involved with the alarms are collected; based on previous data- alarm may be classified by a model in terms of priority and team and/or personnel that the alarm should be assigned to; using all available information answers a number of questions- including “is this critical event launched with right priority and right impact?”, “are all relevant resources notified, and if yes, is it the best team?”, “does the team have the best analytics, historical information, and steps for faster resolution?”).
It would have been obvious to one of an ordinary skill in the art before the effective filing date of the claimed invention, to have incorporated the concept taught by Saraiya of utilizing a machine learning model to classify the ...importance of ....alarms ... based on a plurality of insights including (1) roles of different teams or people, (2) predicted service impact, (3) predicted level of priority of resolving the alarm, and (4) predicted time and resource required for resolution, wherein the machine learning model generates the plurality of insights for each alarm and combines the plurality of insights to produce a role-specific importance classification ...; and
displaying the ...classified... alarms based on the plurality of insights (Saraiya [57] alarms may be displayed based on determined classification, which is determined based on insights, into the invention suggested by Asres and Bhalla, since both inventions are directed towards classifying importance of network alarms, and incorporating the teaching of Saraiya into the invention suggested by Asres and Bhalla would provide the added advantage of determining insights by leveraging received information to answer questions related to the alarms for alarm classification, rather than merely using the received information, and the combination would perform with a reasonable expectation of success (Saraiya [49, 68, 69, 71, 72, 74, 79, 81, 82, 116, 151, 154, 69-71, 116, 127, 137, 138, 150-154, 181, 201, 207-214, 237]).
Asres, Bhalla and Saraiya do not specifically teach utilizing a machine learning model to classify the alarms as one of important and non-important for a particular role of a ... team or person based on a plurality of insights ...wherein the machine learning model generates the plurality of insights for each alarm and combines the plurality of insights to produce a role-specific importance classification such that an alarm is classified as important for the particular role and non-important for a different role; and displaying to a user the important alarms that are classified as important for the role of the user based on the plurality of insights and the role of the user viewing the alarms that are classified as non- important for the role of the user.
However Arzani teaches utilizing a machine learning model to classify the alarms as one of important and non-important for a particular role of a ... team or person based on a plurality of insights ...wherein the machine learning model generates the plurality of insights for each alarm and combines the plurality of insights to produce a role-specific importance classification such that an alarm is classified as important for the particular role and non-important for a different role; and displaying to a user the important alarms that are classified as important for the role of the user based on the plurality of insights and the role of the user viewing the alarms that are classified as non- important for the role of the user (Arzani [3, 25, 66, 67] based on a team’s responsibilities (role) alarm (incident) is classified as associated or not associated (important or not important) with a team , Arzani [24, 34, 53, 54] alarms are routed to team devices for team responsible and are not sent to devices for other teams, Arzani [1, 28, 29, 57] routing only incidents that a team is responsible for avoids time spent by team members attempting to resolve an incident outside of their expertise).
It would have been obvious to one of an ordinary skill in the art before the effective filing date of the claimed invention, to have incorporated the concept taught by Arzani of utilizing a machine learning model to classify the alarms as one of important and non-important for a particular role of a ... team or person based on a plurality of insights ...wherein the machine learning model generates the plurality of insights for each alarm and combines the plurality of insights to produce a role-specific importance classification such that an alarm is classified as important for the particular role and non-important for a different role; and displaying to a user the important alarms that are classified as important for the role of the user based on the plurality of insights and the role of the user viewing the alarms that are classified as non- important for the role of the user, into the invention suggested by Asres, Bhalla and Saraiya; since both inventions are directed towards classifying network alarm severity, and incorporating the teaching of Parmer into the invention suggested by Arzani, Bhalla and Saraiya would provide the added advantage of avoiding time spent by team members attempting to resolve an incident outside of their expertise, and the combination would perform with a reasonable expectation of success (Parmer [Arzani [3, 25, 66, 67], 24, 34, 53, 54, 1, 28, 29, 57).
Regarding claim 2, Asres, Bhalla, Saraiya and Arzani teach the invention as claimed in claim 1 above.
Asres further teaches training the machine learning model with historical alarm data that includes features related to an associated device and comments related to how a Network Operations Center (NOC) handles an associated alarm or group of alarms, wherein the comments are analyzed to distinguish automatically generated comments from human authored comments (Asres Pg1462-Left-lines3-8, Pg1460-Left-LastPara, Pg1460-Rt-2ndPara, Sec IV.A, Table II, model is trained using previous data, data may be features based on alarm attributes/characteristics including particular device and remark for alarm, Asres Sec III.A.1 Asres Sec IV.B,C, Algorithm 1 and V-1st-2Paras features are selected based on relevant features identified by domain experts; based on selected features and identifying source (and other attributes and characteristics) of alarm- groups may be formed (rules), classification may take based on alarm characteristics and attributes, Asres Table II, Secs III and IV.A, Pg 1460-Left-2nd Para, system may have user remarks and system generated text, both are treated as separate features).
Regarding claim 3, Bhalla, Saraiya and Arzani teach the invention as claimed in claim 2 above.
Asres further teaches wherein the training is via supervised machine learning with Network Operations Center (NOC) interactions used as labels ( Asres Pg1459-Rt, Pg1460-Left-LastPara, Sec IV.A.1, Table II, training may be supervised trained using labels from alarm data, labels may be based on information associated with how the alarm is processed by an NOC operator(s)).
Regarding claim 4, Bhalla, Saraiya and Arzani teach the invention as claimed in claim 2 above.
Asres does not specifically teach wherein the training is via reinforcement learning with Network Operations Center (NOC) interactions used as a reward.
However Bhalla teaches wherein the training is via reinforcement learning with Network Operations Center (NOC) interactions used as a reward (Bhalla [5, 6, 21, 22, 34-36] reinforcement learning (RL) using actions in NOC as reward(s), reinforcement learning is used to maximize the probability and thus reinforcing behavior of achieving the target state)
It would have been obvious to one of an ordinary skill in the art before the effective filing date of the claimed invention, to have incorporated the concept taught by Bhalla of wherein the training is via reinforcement learning with Network Operations Center (NOC) interactions used as a reward, into the invention suggested by Asres, Bhalla, Saraiya and Arzani; since both inventions are directed towards classifying network alarms as critical and non-critical, and incorporating the teaching of Bhalla into the invention suggested by Asres, Bhalla, Saraiya and Arzani would provide the added advantage of maximizing the probability and thus reinforcing behavior of achieving the target state by using reinforcement learning, and the combination would perform with a reasonable expectation of success (Bhalla [5, 6, 21, 22, 34-36]).
Regarding claim 5, Bhalla, Saraiya and Arzani teach the invention as claimed in claim 1 above.
Asres further teaches collecting data related to ... importance of...alarms (Asres Table II, severity of alarm may be included in data).
Asres does not specifically teach collecting data related to any of importance of and action on the alarms including roles of different teams or people in the NOC; and
classifying the alarms based on the roles of different teams or people
However Saraiya teaches collecting data related to any of importance of and action on the alarms including roles of different teams or people in the NOC; and classifying the alarms based on the roles of different teams or people (Saraiya [69-71, 116, 127, 137, 138, 150-154, 181, 201, 207-214, 237] data regarding alarms (for e.g. network related IT incidents)- including priority, how event was resolved, team and/or personnel involved with the alarms are collected; based on previous data- alarm may be classified by a model in terms of priority and team and/or personnel that the alarm should be assigned to; using all available information answers a number of questions- including “is this critical event launched with right priority and right impact?”, “are all relevant resources notified, and if yes, is it the best team?”, “does the team have the best analytics, historical information, and steps for faster resolution?”).
Regarding claim 6, Asres, Bhalla, Saraiya and Arzani teach the invention as claimed in claim 1 above.
Asres further teaches utilizing rules to group the alarms together and classifying by the machine learning model is performed on groups of alarms (Asres Sec III.A.1 Asres Sec IV.B,C, Algorithm 1 and V-1st-2Paras features are selected based on relevant features identified by domain experts; based on selected features and identifying source (and other attributes and characteristics) of alarm- groups may be formed (rules), classification may take based on alarm characteristics and attributes).
Claim 10 is directed towards a method performing instructions similar in scope to the instructions stored by the ...medium... of claim 1, and is rejected under the same rationale.
Claim(s) 11-15, is/are dependent on claim 10 above, is/are directed towards a method performing instructions similar in scope to the instructions stored by the ...medium...of claim(s) 2-6, respectively, and is/are rejected under the same rationale.
Claim 19 is directed towards a system executing instructions similar in scope to the instructions performed by the method of claim 1, and is rejected under the same rationale. Bhalla further teaches a system comprising: a data base configured to receive alarms and associated data from a network; one or more processors; and memory storing instructions that, when executed, cause the one or more processors to (Bhalla [3, 21, 37, 68, 140, 141] processor executes instructions stored in medium, invention is directed towards classifying urgency of network alarms and data, Bhalla [49-55] issues are generated from incidents (alarms), issues are stored in database).
Regarding claim 20, Asres, Bhalla, Saraiya and Arzani teach the invention as claimed in claim 19 above.
Asres further teaches train the machine learning model with historical alarm data that includes features related to an associated device and comments related to how a Network Operations Center (NOC) handles an associated alarm or group of alarms (Asres Pg1462-Left-lines3-8, Pg1460-Left-LastPara, Pg1460-Rt-2ndPara, Sec IV.A, Table II, model is trained using previous data, data may be features based on alarm attributes/characteristics including particular device and remark for alarm, Asres Sec III.A.1 Asres Sec IV.B,C, Algorithm 1 and V-1st-2Paras features are selected based on relevant features identified by domain experts; based on selected features and identifying source (and other attributes and characteristics) of alarm- groups may be formed (rules), classification may take based on alarm characteristics and attributes).
Claims 7-9, 16-18, are rejected under 35 U.S.C. 103 as being unpatentable over Asres in view of Bhalla (US 20200259700 A1), Saraiya (US 20210406041 A1) and Arzani (US 20210224676 A1), and further in view of Jilani (US 10438212 B1).
Regarding claim 7, Asres, Bhalla, Saraiya and Arzani teach the invention as claimed in claim 1 above.
Asres further teaches utilizing a Natural Language Processing (NLP) model to extract features from interactions with the received alarms; and utilizing the extracted features to train the machine learning model (Asres Pg1462-Left-lines3-8, Pg1460-Left-LastPara, Pg1460-Rt-2ndPara, Sec IV.A, Table II, model is trained using previous data, data may be features based on alarm attributes/characteristics including remark for alarm, Asres Sec IV.A.3 Table II tokenization (natural language processing) is applied using text mining for alarm attributes).
Asres does not specifically wherein the NLP model performs sentiment or semantic analysis of comments to label alarms as important or non-important.
However Jilani teaches wherein the NLP model performs sentiment ... analysis of comments to label alarms as important or non-important (Jilani Col 6, line 59-67, Col 9, lines 15-54, NLP model may analyze comments, comment sentiment may determine ticket severity).
It would have been obvious to one of an ordinary skill in the art before the effective filing date of the claimed invention, to have incorporated the concept taught by Jilani of wherein the NLP model performs sentiment ... analysis of comments to label alarms as important or non-important, into the invention suggested by Asres, Bhalla, Saraiya and Arzani; since both inventions are directed towards classifying severity of network alarms, and incorporating the teaching of Jilani into the invention suggested by Asres, Bhalla and Arzani would provide the added advantage of levering sentiment analysis of comments to determine the likelihood of urgency or excalation, and the combination would perform with a reasonable expectation of success (Jilani Col 6, line 59-67, Col 9, lines 15-54).
Regarding claim 8, Asres, Bhalla, Saraiya, Arzani and Jilani teach the invention as claimed in claim 7 above.
Asres further teaches utilizing the NLP model to identify alarms that need to be resolved urgently relative to alarms that are less urgent and can be resolved ...later... (Asres Pg1462-Left-lines3-8, model classifies alarms in critical (ticket to be resolved in the first hours of alarms life), or major (ticket will typically be issued later) categories, Asres Pg1462-Left-lines3-8, Pg1460-Left-LastPara, Pg1460-Rt-2ndPara, Sec IV.A, Table II, model is trained using previous data, data may be features based on alarm attributes/characteristics including remark for alarm, Asres Sec IV.A.3 Table II tokenization (natural language processing) is applied using text mining for alarm attributes.
Asres does not specifically teach ...alarms that are less urgent and can be resolved during a maintenance window.
However Bhalla teaches identify alarms that need to be resolved urgently relative to alarms that are less urgent ... can be resolved during a maintenance window (Bhalla [62, 68]
alarms are classified as urgent or non-urgent, non-urgent alarms may be assigned to staff working on improving system, urgent alarms can be assigned to immediate action).
Regarding claim 9, Asres, Bhalla, Saraiya and Arzani teach the invention as claimed in claim 1 above.
Asres does not specifically teach measuring accuracy of the classified alarms; and
responsive to the accuracy being below a threshold, automatically retraining the machine learning model, wherein the retraining includes promoting a newly trained model to production only if performance metrics exceed those of a currently deployed model).
However Jilani teaches measuring accuracy of the classified alarms; and
responsive to the accuracy being below a threshold, automatically retraining the machine learning model, wherein the retraining includes promoting a newly trained model to production only if performance metrics exceed those of a currently deployed model (Jilani Col 5, lines 62-63, Col 6, line 60- Col 7, line 10, machine learning model is used to determine classification regarding the severity of an issue, Jilani Col 6, lines 47-56, Col 9, lines 15-54, accuracy of alarm classifications determined by model is determined, if accuracy is below a threshold- then model may be retrained, retrained model may be monitored (to check whether accuracy is above metrics such as threshold), model is switched to retrained if retrained is acceptable (above threshold)).
It would have been obvious to one of an ordinary skill in the art before the effective filing date of the claimed invention, to have incorporated the concept taught by Jilani of measuring accuracy of the classified alarms; and responsive to the accuracy being below a threshold, automatically retraining the machine learning model, wherein the retraining includes promoting a newly trained model to production only if performance metrics exceed those of a currently deployed model, into the invention suggested by Asres, Bhalla, Saraiya and Arzani; since both inventions are directed towards classifying severity of network alarms, and incorporating the teaching of Jilani into the invention suggested by Asres, Bhalla, Saraiya and Arzani would provide the added advantage of attempting to improve a classification model when accuracy is below a desired threshold- by retraining the model, and using the retrained model only after it is seen to have acceptable performance, and the combination would perform with a reasonable expectation of success (Jilani Col 5, lines 62-63, Col 6, line 60- Col 7, line 10, Col 6, lines 47-56, Col 9, lines 15-54).
Claim(s) 16-18, is/are dependent on claim 10 above, is/are directed towards a method performing instructions similar in scope to the instructions stored by the ...medium...of claim(s) 7-9 respectively, and is/are rejected under the same rationale.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 SANCHITA ROY whose telephone number is (571)272-5310. The examiner can normally be reached Monday-Friday 12-8.
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, Usmaan Saeed can be reached at (571) 272-4046. 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.
SANCHITA . ROY
Primary Examiner
Art Unit 2146
/SANCHITA ROY/Primary Examiner, Art Unit 2146
Prosecution Insights