| CPC H04L 63/20 (2013.01) [G06Q 40/08 (2013.01); H04L 41/0894 (2022.05); G06Q 2220/00 (2013.01)] | 16 Claims |
|
1. An apparatus for determining and recommending transaction protocols, wherein the apparatus comprises:
at least a processor; and
a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to:
receive entity data from an entity;
determine at least a protocol metric for each protocol object of a plurality of protocol objects as a function of the entity data by assigning a rating score to each protocol object, wherein a protocol metric threshold is determined by the entity, wherein the protocol metric threshold is a predetermined value in which the at least a protocol metric for each protocol object of a plurality of protocol objects cannot exceed, wherein the at least a protocol metric for each protocol object of a plurality of protocol objects is compared to the protocol metric threshold, wherein each protocol object of the plurality of protocol objects comprises a policy sub-element wherein determining the at least a protocol metric for each protocol object of the plurality of protocol objects comprises:
creating a policy training data, wherein the policy training data comprises a plurality of entity data as input correlated to a plurality of protocol metrics as output;
training, by the processor, a policy machine-learning model comprising a network of at least an input layer of nodes, one or more intermediate layers, and an output layer of nodes using the policy training data, wherein each node of the at least an input layer of nodes corresponds to each of the plurality of entity data;
generating, by each node of the at least an input layer of nodes, a weighted sum of the plurality of entity data as inputs using weights that are multiplied by the corresponding entity data, wherein the weighted sum is determined by the trained policy machine-learning model, wherein the weights applied to the input indicates whether the input is excitatory or inhibitory, wherein the correlation between the input and the output is determined as a function of the protocol metric threshold, and wherein training the policy machine-learning model comprises:
updating the policy training data iteratively with previous outputs as a function of the input and the outputs of the policy training data;
retraining the policy training data using the updated policy training data;
generating connections between the nodes of the input layer, the one or more intermediate layers, and the output layer, wherein the connections are created by applying the training data to the input layer of nodes; and
adjusting the connections and weights between nodes in adjacent layers to update the protocol metric threshold value at the output layer of nodes;
determining at least a protocol metric for each protocol object of the plurality of protocol objects as a function of the trained policy machine-learning model;
select at least two protocol objects from the plurality of protocol objects as a function of the protocol metric threshold value, wherein the selected at least two protocol objects meet the protocol metric threshold;
modify the policy sub-element of the at least two protocol objects by adjusting the policy sub-element to match the policy sub-element to the entity data; and
generate a policy agreement as a function of the at least two protocol objects, wherein the policy agreement comprises a self-executing transaction protocol.
|