# US 12,216,644 B1 · Adaptive artificial intelligence (AI) engine for secure orchestration of nodes in a distributed ledger hierarchy > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,216,644 B1 - Document ID: US12216644B1 - Status: Granted - Kind: B1 - Application number: 18/410,305 - Filed: 2024-01-11 - Granted: 2025-02-04 - Earliest claimed: 2024-01-11 - Assignees: Bank of America Corporation - Applicants: Bank of America Corporation - Inventors: Saurabh Arora; Sandeep Chauhan; Anil Gajula; Jhalak Khurana - Web page: https://patentgrep.com/patent/US12216644B1 ## CPC - G06F 16/2379: {Updates performed during online database operations; commit processing} - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A computing platform may train, using historical ledger information and historical node confidence information, an adaptive AI engine to output, for a given input node, a particular distributed ledger to which the given input node should be added. The computing platform may receive a request to add a first node to a ledger. The computing platform may input first node information into the adaptive AI engine, which may cause the adaptive AI engine to output a node addition score indicating a first distributed ledger corresponding to an information type of the request. Based on identifying that the node addition score meets or exceeds a node addition threshold, the computing platform may cause the first node to be added to the first distributed ledger. The computing platform may update, using a dynamic feedback loop and based on the node addition score, the adaptive AI engine. ## Claims ### Claim 1 A computing platform comprising: at least one processor; a communication interface communicatively coupled to the at least one processor; and memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to: train, using historical ledger information and historical node confidence information, an adaptive artificial intelligence (AI) engine, wherein training the adaptive AI engine configures the adaptive AI engine to output, for a given input node, a particular distributed ledger of a plurality of distributed ledgers, to which the given input node should be added; receive a request to add a first node to one of the plurality of distributed ledgers; input first node information, of the first node, into the adaptive AI engine, wherein inputting the first node information causes the adaptive AI engine to output a node addition score indicating a first distributed ledger, of the plurality of distributed ledgers, corresponding to an information type of the request; compare the node addition score to a node addition threshold, wherein the node addition threshold is specific to the first distributed ledger; based on identifying that the node addition score meets or exceeds the node addition threshold, cause the first node to be added to the first distributed ledger; and update, using a dynamic feedback loop and based on the node addition score, the adaptive AI engine. ### Claim 2 (depends on 1) The computing platform of claim 1, wherein the historical ledger information comprises information indicating ledgers on which historical requests from various nodes are processed. ### Claim 3 (depends on 1) The computing platform of claim 1, wherein the historical node confidence information indicates, for various nodes, one or more of: results of previous interactions of the various nodes, formats of information sent by the various nodes, indications of malware sent by the various nodes, indications of unrequested files being sent, validity of requests from the various nodes, encryption associated with the requests from the various nodes, or node behavior information. ### Claim 4 (depends on 1) The computing platform of claim 1, wherein the plurality of distributed ledgers includes: at least one category specific ledger, wherein entries to the at least one category specific ledger are specific to a particular information type, and a miscellaneous ledger, wherein entries to the miscellaneous ledger correspond to a plurality of different information types. ### Claim 5 (depends on 1) The computing platform of claim 1, wherein the first node information comprises an IP address of the first node. ### Claim 6 (depends on 1) The computing platform of claim 1, wherein generating the node addition score comprises: generating a confidence score for the first node, wherein the confidence score indicates a representation of confidence that the first node comprises a secure node, identifying a likelihood that the first node should be added to a particular distributed ledger, and generating a combined score based on the confidence score and the likelihood. ### Claim 7 (depends on 1) The computing platform of claim 1, wherein the memory stores additional computer readable instructions that, when executed by the at least one processor, cause the computing platform to: after adding the first node to the first distributed ledger, continue monitoring of the first node, wherein the continued monitoring comprises: generating an updated addition score for the first node, comparing the updated addition score to the node addition threshold, based on identifying that the updated addition score meets or exceeds the node addition threshold, reinforcing a location of the first node in the first distributed ledger, and based on identifying that the updated addition score fails to meet or exceed the node addition threshold, demoting the first node from the first distributed ledger to a miscellaneous distributed ledger. ### Claim 8 (depends on 7) The computing platform of claim 7, wherein generating the updated addition score comprises one or more of: reclassifying the first node to a different information type, wherein the different information type corresponds to a different distributed ledger, or identifying that a trustworthiness of the first node has changed. ### Claim 9 (depends on 1) The computing platform of claim 1, wherein the memory stores additional computer readable instructions that, when executed by the at least one processor, cause the computing platform to: monitor a second node of a miscellaneous distributed ledger; generate an updated node addition score for the second node; compare the updated addition score for the second node to the node addition threshold; based on identifying that the updated addition score meets or exceeds the node addition threshold, promote the second node from the miscellaneous distributed ledger to the first distributed ledger; and based on identifying that the updated addition score of the second node fails to meet or exceed the node addition threshold, reinforce a location of the second node in the miscellaneous ledger. ### Claim 10 (depends on 1) The computing platform of claim 1, wherein the memory stores additional computer readable instructions that, when executed by the at least one processor, cause the computing platform to: dynamically adjust nodes of the first distributed ledger based on current processing load corresponding to the first distributed ledger, wherein dynamically adjusting the nodes comprises one or more of: moving the first node from the first distributed ledger to a miscellaneous distributed ledger, or moving a second node, from the miscellaneous distributed ledger, to the first distributed ledger. ### Claim 11 A method comprising: at a computing platform comprising at least one processor, a communication interface, and memory: training, using historical ledger information and historical node confidence information, an adaptive artificial intelligence (AI) engine, wherein training the adaptive AI engine configures the adaptive AI engine to output, for a given input node, a particular distributed ledger of a plurality of distributed ledgers, to which the given input node should be added; receiving a request to add a first node to one of the plurality of distributed ledgers; inputting first node information, of the first node, into the adaptive AI engine, wherein inputting the first node information causes the adaptive AI engine to output a node addition score indicating a first distributed ledger, of the plurality of distributed ledgers, corresponding to an information type of the request; comparing the node addition score to a node addition threshold, wherein the node addition threshold is specific to the first distributed ledger; based on identifying that the node addition score meets or exceeds the node addition threshold, causing the first node to be added to the first distributed ledger; and updating, using a dynamic feedback loop and based on the node addition score, the adaptive AI engine. ### Claim 12 (depends on 11) The method of claim 11, wherein the historical ledger information comprises information indicating ledgers on which historical requests from various nodes are processed. ### Claim 13 (depends on 11) The method of claim 11, wherein the historical node confidence information indicates, for various nodes, one or more of: results of previous interactions of the various nodes, formats of information sent by the various nodes, indications of malware sent by the various nodes, indications of unrequested files being sent, validity of requests from the various nodes, encryption associated with the requests from the various nodes, or node behavior information. ### Claim 14 (depends on 11) The method of claim 11, wherein the plurality of distributed ledgers includes: at least one category specific ledger, wherein entries to the at least one category specific ledger are specific to a particular information type, and a miscellaneous ledger, wherein entries to the miscellaneous ledger correspond to a plurality of different information types. ### Claim 15 (depends on 11) The method of claim 11, wherein the first node information comprises an IP address of the first node. ### Claim 16 (depends on 11) The method of claim 11, wherein generating the node addition score comprises: generating a confidence score for the first node, wherein the confidence score indicates a representation of confidence that the first node comprises a secure node, identifying a likelihood that the first node should be added to a particular distributed ledger, and generating a combined score based on the confidence score and the likelihood. ### Claim 17 (depends on 11) The method of claim 11, further comprising: after adding the first node to the first distributed ledger, continuing to monitor the first node, wherein the continued monitoring comprises: generating an updated addition score for the first node, comparing the updated addition score to the node addition threshold, based on identifying that the updated addition score meets or exceeds the node addition threshold, reinforcing a location of the first node in the first distributed ledger, and based on identifying that the updated addition score fails to meet or exceed the node addition threshold, demoting the first node from the first distributed ledger to a miscellaneous distributed ledger. ### Claim 18 (depends on 17) The method of claim 17, wherein generating the updated addition score comprises one or more of: reclassifying the first node to a different information type, wherein the different information type corresponds to a different distributed ledger, or identifying that a trustworthiness of the first node has changed. ### Claim 19 (depends on 11) The method of claim 11, further comprising: monitoring a second node of a miscellaneous distributed ledger; generating an updated node addition score for the second node; comparing the updated addition score for the second node to the node addition threshold; based on identifying that the updated addition score meets or exceeds the node addition threshold, promoting the second node from the miscellaneous distributed ledger to the first distributed ledger; and based on identifying that the updated addition score of the second node fails to meet or exceed the node addition threshold, reinforcing a location of the second node in the miscellaneous ledger. ### Claim 20 One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, cause the computing platform to: train, using historical ledger information and historical node confidence information, an adaptive artificial intelligence (AI) engine, wherein training the adaptive AI engine configures the adaptive AI engine to output, for a given input node, a particular distributed ledger of a plurality of distributed ledgers, to which the given input node should be added; receive a request to add a first node to one of the plurality of distributed ledgers; input first node information, of the first node, into the adaptive AI engine, wherein inputting the first node information causes the adaptive AI engine to output a node addition score indicating a first distributed ledger, of the plurality of distributed ledgers, corresponding to an information type of the request; compare the node addition score to a node addition threshold, wherein the node addition threshold is specific to the first distributed ledger; based on identifying that the node addition score meets or exceeds the node addition threshold, cause the first node to be added to the first distributed ledger; and update, using a dynamic feedback loop and based on the node addition score, the adaptive AI engine.