US 2021/0174347 A1 · User Routing Application and Recommendation Engine for Distributed Terminal Network

a) providing a client in the distributed terminal network, wherein:

i) the client comprises a terminal, node, point of sale, and/or kiosk:

1) wherein the client at least comprises:

(a) al least one processor;

(h) at least one memory storing an application;

(c) at least one liquid crystal display (LCD) touch screen;

(d) at least one dispenser;

(e) at least one validator;

(f) at least one electronic vault;

(g) at least one barcode reader;

(h) at least one thermal printer;

(i) at least one EMV card reader;

(j) at least one high definition camera;

and

(k) al least one fingerprint reader;

ii) wherein the client is in communication, through a communication interface of network, with at least:

1) one or more specialized servers providing the software service by the software service provider;

iii) wherein the client is configured to:

1) establish a secure session with the software service provider:

(a) wherein the secure session is established using at least a secure socket layer (SSL) or a transport layer security (TLS) protocol;

(b) wherein the secure session is established using a secured connection using a virtual private network (VPN);

2) communicate, to the software service provider, an encrypted first payload;

(a) wherein the encrypted first payload is produced by encrypting a first payload, the first payload produced by the hardware terminal, and wherein the first payload comprises a phone number, the phone number received from the first customer at the hardware terminal;

(b) wherein the encrypted first payload is communicated to the software service provider from the hardware terminal during the secure session using the secured connection;

3) communicate, to the software service provider, an encrypted second payload;

(a) wherein the encrypted second payload is produced by encrypting a second payload, the second payload produced by the hardware terminal;

(b) wherein the encrypted second payload is communicated to the software service provider from the hardware terminal during the secure session using the secured connection;

4) communicate, to the software service provider, an encrypted third payload;

(a) wherein the encrypted third payload is produced by encrypting a third payload, the payload produced by the hardware terminal, and wherein the third payload comprises at least first data;

(b) wherein the encrypted third payload is communicated to the software service provider from the hardware terminal during the secure session using the secured connection;

5) gather customer image or video data using at least:

(a) a camera hardware device;

6) communicate, to the software service provider, an encrypted fourth payload;

(a) wherein the encrypted fourth payload is produced by encrypting a fourth payload, the fourth payload produced by the hardware terminal, and wherein the fourth payload comprises at least one parameter associated with image or video data associated with the first customer's face;

(b) wherein the encrypted fourth payload is communicated to the software service provider from the hardware terminal during the secure session using the secured connection;

downloading or storing, in the at least one computer memory, a machine learning model or machine learning model parameters locally to the client, wherein the client comprises an edge hardware device or edge server;

wherein the edge hardware device may be a dispensary terminal, a client terminal, a node, or a vending machine;

wherein the machine learning model or machine learning model parameters are communicated to the client from the software service provider during the first secure session using the first secured connection;

wherein the machine learning model comprises, at least:

a trained or pre-trained deep neural network or convolutional neural network based model;

wherein the deep neural network or convolutional neural network based model has been trained on, at least:

a dataset including information about known customers and/or restricted users;

wherein the dataset includes data based on images of the known customers and restricted users, the images including facial features of the known customers and restricted users;

receiving an operation from a first visitor at the edge device;

identifying local facial recognition data associated with the first visitor, wherein the identifying the local facial recognition data associated with the first visitor comprises:

gathering, using a camera, image or video data of the first visitor's face;

extracting a plurality of facial features associated with the image or video data;

calculating, at the edge device or edge server, using the machine learning model whether the first visitor matches a known user or restricted user, wherein the calculating comprises, at least:

determining a nearest neighbor probability;

determining whether the nearest neighbor probability exceeds a threshold probability;

based on the calculating, determining whether to authenticate the first visitor;

updating, at the edge device or edge server, the machine learning model using the local facial recognition data to produce a first updated machine learning model;

determining new model parameters reflecting the first updated machine learning model;

performing a first processing of the new model parameters, wherein performing the first processing of the new model parameters comprises:

producing an encrypted first payload;

wherein the encrypted first payload is produced by encrypting a first payload, the first payload produced by the client, and wherein the first payload comprises at least the new model parameters;

establishing a second secure session between the software service provider and the client;

wherein the secure session is established using at least the secure socket layer (SSL) or transport layer security (TLS) protocol;

wherein the second secure session is established using a second secured connection using the virtual private network (VPN);

communicating the encrypted first payload to a server of the software service provider, without transmitting the image to the server;

wherein the encrypted first payload is communicated to the server of the software service provider from the client during the second secure session using the second secured connection;

downloading or storing locally to the client, in the least one computer memory, updated machine learning model parameters reflecting a second updated machine learning model;

wherein the second updated machine learning model is a global model that includes, at least, updates based on the local facial recognition data;

and

referring to the first updated machine learning model or second updated machine learning model for a subsequent visitor authentication request.

User Routing Application and Recommendation Engine for Distributed Terminal Network

Life of this patent

User Routing Application and Recommendation Engine for Distributed Terminal Network

Life of this patent

Abstract

Claims20