Artificial intelligence based signal transformation platform

A signal transformation computing system having at least one processor and at least one memory having computer-executable instructions stored therein that, when executed by the at least one processor, cause the signal transformation computing system to perform operations that reduce false positive lien identification compared with ETL (extract, transform, load) processing, the operations comprising:

• receiving, by the signal transformation computing system, an inbound signal having a payload comprising first alphanumeric data comprising event data including event date, the first alphanumeric data relating to a claim;
• using at least a portion of the payload, retrieving anatomy image data and inputting the anatomy image data to a computer vision model to generate an attribute set An,
• where in the computer vision model applies pattern recognition to identify patterns in the anatomy image data,
• where in the anatomy image data is processed in combination with the event date to determine that the claim is related to a specific event or incident,
• wherein the attribute set An comprises second alphanumeric data generated using the anatomy image data, and
• causing a trained model to process the attribute set An to generate a classifier for a data signal;
• using the classifier, generating routing data to include in the data signal, wherein the routing data comprises an agentic artificial intelligence (AI) instruction, a target computing system identifier, or both;
• linking (i) the attribute set An, (ii) the event data, and (iii) routing data to generate the data signal;
• using the data signal, causing an autonomous agent to generate an electronic command, the electronic command configured at least in part using (i) the attribute set An, (ii) the event data, and (iii) the routing data;
• generating an incremental training data set using the attribute set An and event data;
• and
• causing the trained model to update model configuration information by learning the incremental data set, wherein the model configuration information comprises at least one of node information, weight information, or activation function.

One or more non-transitory computer-readable media having computer-executable instructions stored thereon that, when executed by at least one processor, cause a signal transformation computing system to perform operations that reduce false positive lien identification compared with ETL (extract, transform, load) processing, the operations comprising:

• receiving, by the signal transformation computing system, an inbound signal having a payload comprising first alphanumeric data comprising event data including event date, the first alphanumeric data relating to a claim;
• using at least a portion of the payload, retrieving anatomy image data and inputting the anatomy image data to a computer vision model to generate an attribute set An,
• where in the computer vision model applies pattern recognition to identify patterns in the anatomy image data,
• where in the anatomy image data is processed in combination with the event date to determine that the claim is related to a specific event or incident,
• and
• wherein the attribute set An comprises second alphanumeric data generated using the anatomy image data;
• causing a trained model to process the attribute set An to generate a classifier for a data signal;
• using the classifier, generating routing data to include in the data signal, wherein the routing data comprises an agentic artificial intelligence (AI) instruction, a target computing system identifier, or both;
• linking (i) the attribute set An, (ii) the event data, and (iii) routing data to generate the data signal;
• generating an incremental training data set using the attribute set An and event data;
• and
• causing the trained model to update model configuration information by learning the incremental data set, wherein the model configuration information comprises at least one of node information, weight information, or activation function.