# US 2026/0095370 A1 · Systems and methods for determining and locating network component errors in a distributed network > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0095370 A1 - Document ID: US20260095370A1 - Status: Published application - Kind: A1 - Application number: 18/903,766 - Filed: 2024-10-01 - Published: 2026-04-02 - Earliest claimed: 2024-10-01 - Assignees: Bank of America Corporation - Applicants: Bank of America Corporation - Inventors: John Andres Lozes; Amer Ali; Aravind Singtalur; Mohammad Saleem Gaziani; Andrea M. Weisberger; Aaron Gee; Tonya Kyra Miller; Aisha Jenkins; Asha Thekkumpurath; Manonmani Palanichamy; Naresh Kumar Petapalle - Web page: https://patentgrep.com/patent/US20260095370A1 ## CPC - H04L 41/0677: Localisation of faults - H04L 41/16: using machine learning or artificial intelligence - H04L 41/22: comprising specially adapted graphical user interfaces [GUI] - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Systems, computer program products, and methods are described herein for determining and locating network component errors in a distributed network. The present invention is configured to collect, from at least one source component, exception data at a pre-defined interval; group the exception data into a bucket(s) based on the at least one source component, the pre-defined interval, and an exception type; determine, based on the bucket(s) and by an artificial intelligence (AI) pattern module, an average exception count for the bucket(s) over the pre-defined interval; collect historical exception data associated with the bucket(s); compare, by the AI pattern module, the historical exception data associated with the bucket(s) and the average exception count for the bucket(s); and determine, based on the comparison, an outlier exception pattern for the bucket(s) for the pre-defined interval. ## Claims ### Claim 1 A system for determining and locating network component errors in a distributed network, the system comprising: a memory device with computer-readable program code stored thereon; at least one processing device operatively coupled to the at least one memory device and the at least one communication device, wherein executing the computer-readable code is configured to cause the at least one processing device to: collect, from at least one source component, exception data at a pre-defined interval; group the exception data into at least one bucket based on the at least one source component, the pre-defined interval, and an exception type; determine, based on the at least one bucket and by an artificial intelligence (AI) pattern module, an average exception count for the at least one bucket over the pre-defined interval; collect historical exception data associated with the at least one bucket; compare, by the AI pattern module, the historical exception data associated with the at least one bucket and the average exception count for the at least one bucket; and determine, based on the comparison, an outlier exception pattern for the at least one bucket for the pre-defined interval. ### Claim 2 (depends on 1) The system of claim 1, wherein the exception type is based on at least one of a source component flow, a source component sub-flow, a data center identifier, a server identifier, or an exception identifier. ### Claim 3 (depends on 1) The system of claim 1, wherein executing the computer-readable code is further configured to cause the at least one processing device to: collect metric data associated with the at least one source component; extract, from the metric data, the exception data associated with the at least one source component; generate an exception count for the exception data for the at least one source component and based on the exception type; and generate the at least one bucket based on the exception count, the at least one source component, the pre-defined interval, and the exception type. ### Claim 4 (depends on 1) The system of claim 1, wherein the AI pattern module comprises at least one of a z-score algorithm, an interquartile regression pattern, a quartile regression algorithm, or a standard deviation algorithm. ### Claim 5 (depends on 1) The system of claim 1, wherein the exception type comprises at least one of a checked exception, an error exception, a runtime exception, a logical exception, an argument exception, a null reference exception, or a compilation exception. ### Claim 6 (depends on 1) The system of claim 1, wherein executing the computer-readable code is further configured to cause the at least one processing device to: determine, based on the pre-defined interval, a historical exception pattern for the pre-defined interval; compare the outlier exception pattern and the historical exception pattern for the pre-defined interval; and determine, based on the comparison of the outlier exception pattern and the historical exception pattern, an outlier comparison score for the pre-defined interval, wherein the outlier comparison score indicates at least one of a sharp increase pattern or a consistent pattern. ### Claim 7 (depends on 6) The system of claim 6, wherein executing the computer-readable code is further configured to cause the at least one processing device to: compare the outlier comparison score with a comparison score threshold; identify the sharp increase pattern or the consistent pattern for the outlier comparison score based on the comparison of the outlier comparison score and the comparison score threshold; and generate an alert interface component in an instance where the outlier comparison score comprises the sharp increase pattern. ### Claim 8 (depends on 6) The system of claim 6, wherein executing the computer-readable code is further configured to cause the at least one processing device to: generate a report interface component comprising the outlier exception pattern in an instance where the outlier comparison score comprises the consistent pattern for the pre-defined interval; transmit the report interface component to a user device associated with the at least one source component, wherein the user device comprises a graphical user interface (GUI); and trigger a configuration of the GUI of the user device with the report interface component, wherein the GUI indicates the at least one source component and the outlier exception pattern at the pre-defined interval. ### Claim 9 (depends on 1) The system of claim 1, wherein executing the computer-readable code is further configured to cause the at least one processing device to: generate a dashboard interface component comprising the outlier exception pattern for the at least one source component; transmit the dashboard interface component to a user device associated with the at least one source component, wherein the user device comprises a graphical user interface; and trigger a configuration of the GUI of the user device with the dashboard interface component. ### Claim 10 A computer program product for determining and locating network component errors in a distributed network, the computer program product comprising a non-transitory computer-readable medium comprising code causing an apparatus to: collect, from at least one source component, exception data at a pre-defined interval; group the exception data into at least one bucket based on the at least one source component, the pre-defined interval, and an exception type; determine, based on the at least one bucket and by an artificial intelligence (AI) pattern module, an average exception count for the at least one bucket over the pre-defined interval; collect historical exception data associated with the at least one bucket; compare, by the AI pattern module, the historical exception data associated with the at least one bucket and the average exception count for the at least one bucket; and determine, based on the comparison, an outlier exception pattern for the at least one bucket for the pre-defined interval. ### Claim 11 (depends on 10) The computer program product of claim 10, wherein the exception type is based on at least one of a source component flow, a source component sub-flow, a data center identifier, a server identifier, or an exception identifier. ### Claim 12 (depends on 10) The computer program product of claim 10, wherein the computer program product comprising the non-transitory computer-readable medium comprising code further causes the apparatus to: collect metric data associated with the at least one source component; extract, from the metric data, the exception data associated with the at least one source component; generate an exception count for the exception data for the at least one source component and based on the exception type; and generate the at least one bucket based on the exception count, the at least one source component, the pre-defined interval, and the exception type. ### Claim 13 (depends on 10) The computer program product of claim 10, wherein the AI pattern module comprises at least one of a z-score algorithm, an interquartile regression pattern, a quartile regression algorithm, or a standard deviation algorithm. ### Claim 14 (depends on 10) The computer program product of claim 10, wherein the exception type comprises at least one of a checked exception, an error exception, a runtime exception, a logical exception, an argument exception, a null reference exception, or a compilation exception. ### Claim 15 (depends on 10) The computer program product of claim 10, wherein the computer program product comprising the non-transitory computer-readable medium comprising code further causes the apparatus to: determine, based on the pre-defined interval, a historical exception for the pre-defined interval; compare the outlier exception pattern and the historical exception pattern for the pre-defined interval; and determine, based on the comparison of the outlier exception pattern and the historical exception pattern, an outlier comparison score for the pre-defined interval, wherein the outlier comparison score indicates at least one of a sharp increase pattern or a consistent pattern. ### Claim 16 A computer implemented method for determining and locating network component errors in a distributed network, the computer implemented method comprising: collecting, from at least one source component, exception data at a pre-defined interval; grouping the exception data into at least one bucket based on the at least one source component, the pre-defined interval, and an exception type; determining, based on the at least one bucket and by an artificial intelligence (AI) pattern module, an average exception count for the at least one bucket over the pre-defined interval; collecting historical exception data associated with the at least one bucket; comparing, by the AI pattern module, the historical exception data associated with the at least one bucket and the average exception count for the at least one bucket; and determining, based on the comparison, an outlier exception pattern for the at least one bucket for the pre-defined interval. ### Claim 17 (depends on 16) The computer implemented method of claim 16, wherein the exception type is based on at least one of a source component flow, a source component sub-flow, a data center identifier, a server identifier, or an exception identifier. ### Claim 18 (depends on 16) The computer implemented method of claim 16, further comprising: collecting metric data associated with the at least one source component; extracting, from the metric data, the exception data associated with the at least one source component; generating an exception count for the exception data for the at least one source component and based on the exception type; and generating the at least one bucket based on the exception count, the at least one source component, the pre-defined interval, and the exception type. ### Claim 19 (depends on 16) The computer implemented method of claim 16, wherein the AI pattern module comprises at least one of a z-score algorithm, an interquartile regression pattern, a quartile regression algorithm, or a standard deviation algorithm. ### Claim 20 (depends on 16) The computer implemented method of claim 16, wherein the exception type comprises at least one of a checked exception, an error exception, a runtime exception, a logical exception, an argument exception, a null reference exception, or a compilation exception.