Detailed Action
This action is in response to the application filed on 08/18/2026. Claims 1-20 are
pending and have been fully examined.
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 .
Status of the Claims
Claims 1-20 are rejected under 35 U.S.C. 103
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, 4-6, 8, 11-10, 14, and 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Tse et al. (U.S. Publication No. 2025/0330839 A1), hereinafter referred to as Tse, in view of Suba et al. (U.S. Publication No. 2025/0328567 A1), hereinafter referred to as Suba, in further view of Balachandran et al. (U.S. Publication No. 2025/0379780 A1), hereinafter referred to as Balachandran.
Regarding Claim 1 Tse teaches:
A method for automated root cause analysis via one or more structured data sources and one or more unstructured data sources, comprising:
identifying an error in a process based on executing the process at a first time period; ([0019]; regarding, “The recommendation engine 120 can analyze various metrics related to the predicted user experience classification to identify the root cause of any user experience degradation.”);
searching, via a retrieval-augmented generation (RAG) component, the one or more unstructured data sources in accordance with an error description corresponding to the identified error; ([0079]; regarding, “the LLM may comprise a retrieval-augmented generation (RAG) LLM that can search a vectorized database of knowledge that includes, among other aspects, the above recommendations… the RAG-based LLM may have access to manuals, API documentation, and other documents that engineers would use”);
generating, via the RAG component, a hypothesis for the error in accordance with searching the one or more unstructured data sources; ([0079]; regarding, “the RAG-based LLM may have access to manuals, API documentation, and other documents that engineers would use to improve network operations. Using this knowledge, the LLM can synthesize actions”);
autonomously adjusting one or more parameters of one or more physical devices associated with the process... ([0019]; regarding, “the RAG-based LLM can further be trained on a corpus of network configuration templates, scripts, and API documentation to enable it to generate accurate and actionable commands based on the provided recommendations.”; [0083]; regarding, “The generated commands can then be executed through network orchestration tools or platforms, automating the implementation of the recommended optimizations across the network.”).
The one or more parameters including process parameters that control operation of the one or more physical devices; ([0019]; regarding, “…adjusting radio resource allocation, optimizing network configurations, scaling network resources…”)
And executing the process at a second time period in accordance with autonomously adjusting the one or more parameters ([0084]; regarding, “In step 412, the method can include monitoring the impact of the implemented changes on user experience, using feedback from the machine learning model and other monitoring tools, to assess the effectiveness of the optimization efforts.”).
Tse fails to explicitly disclose but Suba teaches:
searching the one or more structured data sources in accordance with one or more queries generated via a text-to-SQL component in accordance with the hypothesis; ([0050]; regarding, “a retrieval unit 205 configured to retrieve relevant data… in response to a user query.”; [0054]; regarding, “the retrieval unit 205 may use a fine-tuned model specifically trained for the task of converting natural language into SQL queries… the LLM model learns the nuances of the database's schema, common query patterns, and industry-specific terminology, enabling it to generate more accurate and context-aware SQL queries. This customization then ensures that the retrieval unit 205 can handle complex or ambiguous user queries with higher precision, ultimately improving the effectiveness of structured data retrieval.”);
Therefore, it would have been obvious before the effective filing date of the claimed invention to one of ordinary skill in the art to which said subject matter pertains to combine Tse with the teachings of Suba. Doing so could improve search accuracy and relevance (Suba, [0021]).
Tse in view of Suba fails to explicitly disclose but Balachandran teaches:
comparing the retrieved structured data from the one or more structured data source with the hypothesis ([0042]; regarding, “Each one of the historical RCA documents includes description of a network incident or anomaly (e.g., type, geolocation, timeframe, etc.), a root cause analysis for the incident or anomaly, an impact of the incident or anomaly, a resolution to the incident or anomaly, and a recommendation on preventing the incident or anomaly.”);
to determine whether the retrieved structured data supports or contradicts the hypothesis as a probable root cause of the error; ([0056]; regarding, “The root causes may include factors such as hardware failures, software bugs, misconfigurations, or unexpected events. The root causes may be further validated against known patterns and historical RCA data or network data before output.”; [0055]; regarding, “one or more network incidents/anomalies are verified or identified, by the query analytical system using the AI/ML models. For example, a deviation of network usage data from a predetermined normal usage is calculated to exceed a predetermined level, and a predetermined type/class of anomaly correlating/corresponding to the deviation is identified using the AI/ML models.”).
…adjusting one or more parameters of one or more physical devices associated with the process in accordance with the retrieved structured data supporting the hypothesis, ([0036]; regarding, “The RCA report may include the identified anomalies, root cause analysis, and recommendations on the preventive/corrective actions.”; [0057]; regarding, “one or more actions are recommended, by the query analytical system using the AI/ML models, to resolve the incident or cure the anomaly. The actions may include specific configuration changes, software updates, network reconfigurations, security measures, or other operational procedures. At 462, a response indicating the identified network incident or anomaly, the determined root causes, and/or the recommended actions is generated and output to the operator, by the query analytical system.”).
Therefore, it would have been obvious before the effective filing date of the claimed invention to one of ordinary skill in the art to which said subject matter pertains to combine Tse and Suba with the teachings of Balachandran. Doing so could provide advanced analytical techniques (Balachandran, [0025]).
Regarding Claim 4, Tse in view of Suba, in further view of Balachandran teaches the method of claim 1 as referenced above. Tse in view of Suba, in further view of Balachandran further teaches:
wherein the RAG component generates the hypothesis via a large language model. (Tse, [0079]; regarding, “the LLM may comprise a retrieval-augmented generation (RAG) LLM”).
Regarding Claim 5, Tse in view of Suba, in further view of Balachandran teaches the method of claim 1 as referenced above. Tse in view of Suba, in further view of Balachandran further teaches:
the one or more structured data sources include parameters associated with the one or more devices, sensor data, machine logs, and/or production data; (Tse, [0014]; regarding, “a database 110 captures various metrics, KPIs, and other data during operation of the network.”; [0024]; regarding, “the metrics captured by UEs and end user devices can include, but is not limited to, CPU/GPU utilization, battery temperature, memory usage, signal strength, signal-to-noise ratio, modulation and coding scheme, and congestion indicators, application-specific KPIs…”);
and the one or more unstructured data sources include device manuals, notes, troubleshooting guides, and/or online community forums. ([0079]; regarding, “the RAG-based LLM may have access to manuals, API documentation, and other documents that engineers would use to improve network operations.”).
Regarding Claim 6, Tse in view of Suba, in further view of Balachandran teaches the method of claim 1 as referenced above. Tse in view of Suba, in further view of Balachandran further teaches:
retrieving structured data from the one or more structured data sources in accordance with searching the one or more structured data sources; (Suba, [0053]; regarding, “the retrieval unit 205 may interpret the query and generate a corresponding SQL statement. The retrieval unit 205 may then run this query (i.e., the SQL statement) directly on the relational database, extracting only the records that meet the exact criteria.”);
and comparing the retrieved structured data with the hypothesis, wherein the one or more parameters are autonomously adjusted based on the comparison of the retrieved structured data with the hypothesis. ([0057]; regarding, “the retrieval unit 205 may further enhance the verification mechanism by fine-tuning domain-specific models to classify documents as relevant or irrelevant, and potentially even re-rank results based on how confidently they match the user query.”).
Claims 8, 14 and 11-12, 17-18 are rejected under 35 U.S.C. 103 under the same grounds of rejection as claim 1 and 4-5 respectively.
Claims 10 and 19 are rejected under 35 U.S.C. 103 under the same grounds of rejection as claim 6.
Claims 2-3, 7, 9, 13, 15-16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Tse et al. (U.S. Publication No. 2025/0330839 A1), hereinafter referred to as Tse, in view of Suba et al. (U.S. Publication No. 2025/0328567 A1), hereinafter referred to as Suba, in further view of Balachandran et al. (U.S. Publication No. 2025/0379780 A1), hereinafter referred to as Balachandran, in further view of Wolff et al. (U.S. Patent No. 12,443,635 B1), hereinafter referred to as Wolff.
Regarding Claim 2, Tse in view of Suba, in further view of Balachandran teaches the method of claim 1 as referenced above. Tse in view of Suba, in further view of Balachandran fail to explicitly disclose but Wolff teaches:
wherein the error is identified, via a machine learning model, based on one or more images, one or more sensor readings, and/or data associated with the process or the environment. (Col. 39, lines 57-63; regarding, “upon receiving a machine-generated alert or detecting an outlier in one or more sensor readings, the system described herein may apply rule-based, statistical, and machine learning techniques… to determine whether the observed outlier constitutes a true anomaly.”).
Therefore, it would have been obvious before the effective filing date of the claimed invention to one of ordinary skill in the art to which said subject matter pertains to combine Tse, Suba, and Balachandran with the teachings of Wolff. Doing so could improve the relevance of retrieved results (Wolff, Col. 52, lines 2-4).
Claims 9 and 15 are rejected under 35 U.S.C. 103 under the same grounds of rejection as claim 2.
Regarding Claim 3, Tse in view of Suba in view of Balachandran in further view of Wolff teaches the method of claim 2 as referenced above. Tse in view of Suba in view of Balachandran in further view of Wolff teaches:
the error description is a natural language error description; and the machine learning model generates the natural language error description. (Wolff, Col. 39, lines 56-67; Col. 4-, lines 1-4; regarding, “upon receiving a machine-generated alert or detecting an outlier in one or more sensor readings, the system described herein may apply rule-based, statistical, and machine learning techniques…to determine whether the observed outlier constitutes a true anomaly… the system may determine whether the observed data satisfies predefined exception rules, exhibits high correlation among specific sensor groups, or has patterns that contribute significantly to anomaly detection models. The system may then generate an alert that includes a contextual description of the anomaly…”).
Claim 16 is rejected under 35 U.S.C. 103 under the same grounds of rejection as claim 3.
Regarding Claim 7, Tse in view of Suba, in further view of Balachandran teaches the method of claim 1 as referenced above. Tse in view of Suba fail to explicitly disclose but Wolff teaches:
wherein the process is a manufacturing process. (Wolff, Col. 51, lines 1-10; regarding, “Performing predictive maintenance may reduce unplanned downtime and may extend the lifespan of physical assets as compared to other techniques in which equipment issues are resolved at the time of failure (e.g., reactive maintenance). Additionally, it should be noted that the techniques described herein may be applied to environments distinct from manufacturing environments (e.g., other environments in which real-time monitoring of complex systems occurs).”; Col. 41, lines 55-58; regarding, ““physical asset” may refer to a physical system, machine, device, or subcomponent from which measurement data (e.g., telemetry data) may be obtained.”).
Therefore, it would have been obvious before the effective filing date of the claimed invention to one of ordinary skill in the art to which said subject matter pertains to combine Tse, Suba, and Balachandran with the teachings of Wolff. Doing so could improve the relevance of retrieved results (Wolff, Col. 52, lines 2-4).
Claims 13 and 20 are rejected under 35 U.S.C. 103 under the same grounds of rejection as claim 7.
Response to Arguments
Applicant’s arguments filed 08/18/2026 have been fully considered.
Applicant’s arguments with respect to the previous rejection under 35 U.S.C. 103 on independent Claim 1, and similarity Claims 8 and 14, have been considered and a new grounds of rejection has been provided addressing the newly claimed matter. See the above detailed rejection of the newly recited subject matter.
Newly cited reference Balachandran in combination with Tse and Suba discloses the newly claimed subject matter.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATHEW GUSTAFSON whose telephone number is (571)272-5273. The examiner can normally be reached Monday-Friday 8:00-4:00.
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, Bryce Bonzo can be reached at (571) 272-3655. 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.
/M.D.G./Examiner, Art Unit 2113 /BRYCE P BONZO/Supervisory Patent Examiner, Art Unit 2113
Prosecution Insights