Intelligent Routing Method for Routing Items Through A Network

• US 20160234098A1
• Filed: 01/26/2016
• Published: 08/11/2016
• Est. Priority Date: 02/08/2015
• Status: Active Grant

• Current Assignee: Bobsweep, Inc.
• Original Assignee: Ai Incorprated
• Inventors: Ebrahimi Afrouzi, Ali
• Granted Patent: US 10,237,167 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 43/0858 One way delays
• CPC Class Codes: H04L 45/121 by minimising delays

Abstract

A method for selecting routes for items being sent from a given beginning node to a given destination node within a network. Each segment of a trip is evaluated and assigned a negative reward based on the deviation from the ideal length of time to complete that segment. Upon arrival of the item at the destination node, the route is assigned a large positive reward. The system is configured to attempt to maximize rewards at all times by selecting the routes with the lowest likelihood of delay. As more and more trips are completed, the control system may define a policy that selects routes based on their probability of yielding the highest reward.

Claims

1. A method for determining the most efficient route from a beginning node to a destination node in a network comprised of a plurality of nodes connected by links, the method comprising:

selecting a route for sending an item from a beginning node to a destination node;

sending the item along the selected route;

calculating a negative reward based on the difference between the estimated time to complete each segment of the route with no delays and the actual time to complete each segment of the route; and

assigning the calculated negative reward to the route after each completed segment;

assigning a fixed positive reward to the route upon arrival at the destination node.

2. The method of claim 1, further comprising:

iteratively creating a plurality of policies for sending items from beginning nodes to destination nodes to maximize the net reward thereby minimizing the difference between the estimated time to complete each segment of a route with no delays and the actual time to complete each segment of a route.

3. A system for minimizing routing delays in a network comprising:

a network including a plurality of nodes connected by links;

a control system configured to;

select a route for sending an item from a given beginning node to a given destination node;

send the item along the selected route;

calculate a negative reward based on the difference between the estimated time to complete each segment of the route with no delays and the actual time to complete each segment of the route;

assign the calculated rewards to the route after each segment is completed;

assign a fixed positive reward to the route upon the item'"'"'s arrival at the destination node.

4. The system of claim 3, wherein the control system is further configured to iteratively select a plurality of routes for sending items from given beginning nodes to given destination nodes to maximize the reward, thereby minimizing delays in routes.

5. A computing device program product for minimizing delays in routing items through networks, the computing device program product comprising:

a network comprised of a plurality of nodes connected by links;

first programmatic instructions for identifying a route for sending items from a given beginning node to a given destination node;

second programmatic instructions for sending the item through the identified route;

third programmatic instructions for calculating a negative reward based on the difference between the estimated time to complete each segment of the identified route with no delays and the actual time to complete each segment of the identified route;

fourth programmatic instructions for assigning the calculated reward to the route upon completion of each segment of the route; and

fifth programmatic instructions for assigning a positive reward to the route upon the item'"'"'s arrival at the given destination node.

6. The program product of claim 5, further comprising:

sixth programmatic instructions for iteratively identifying a plurality of routes for sending items from given beginning nodes to given destination nodes to maximize the reward, thereby minimizing delays in routes.