Translation of user requests into itinerary solutions

• US 10,210,270 B2
• Filed: 05/15/2017
• Issued: 02/19/2019
• Est. Priority Date: 03/14/2011
• Status: Active Grant

• Current Assignee: Amgine Technologies (US), Inc.
• Original Assignee: Amgine Technologies (US), Inc.
• Inventors: Miller, Naomi Liora, Miller, Harold Roy, Stableford, Warren
• Primary Examiner(s): Arjomandi, Noosha
• Application Number:
  US15/595,795
• Publication Number:
  US 20170316103A1
• Time in Patent Office: 645 Days
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events

Abstract

A method for translating user requests into itinerary solutions is disclosed. The method may commence with receiving an itinerary request associated with one or more passengers. The method may continue with parsing the itinerary request to create an itinerary network associated with the itinerary request. The itinerary network may include at least two or more nodes and dependencies between two or more nodes. Upon the parsing, a topology of the itinerary network may be created. The method may include processing the itinerary network using the topology to create a plurality of tuples. The plurality of tuples may be analyzed. The method may continue with determining feasible itinerary solutions based on the analysis. The feasible itinerary solutions may be ranked. The method may further include presenting, to the one or more passengers, at least one itinerary solution selected from the feasible itinerary solutions based on the ranking.

Claims

1. A system for translating user requests into itinerary solutions, the system comprising:

a processor configured to;

receive an itinerary request associated with one or more passengers; and

present, to the one or more passengers, at least one itinerary solution selected from feasible itinerary solutions based on a ranking;

a parser configured to;

parse the itinerary request to determine two or more nodes associated with the itinerary request, and dependencies between the two or more nodes; and

combine the two or more nodes associated with the itinerary request into an itinerary network; and

a scheduler configured to;

create a level matrix for the itinerary network by selecting main nodes and child nodes that depend on the main nodes, from the two or more nodes in the itinerary network;

create a topology of the itinerary network based on the level matrix, the topology including at least an ordered list of the two or more nodes;

process the itinerary network using the topology to create a plurality of tuples, wherein;

the plurality of tuples includes at least flight tuples and hotel tuples; and

each tuple of the plurality of tuples is a set of objects associated with a node;

analyze the plurality of tuples based on the itinerary request and the dependencies between the two or more nodes;

based on the analysis, determine the feasible itinerary solutions for each of the one or more passengers; and

rank the feasible itinerary solutions for each of the one or more passengers, based on at least passenger preferences.

2. The system of claim 1, wherein the flight tuples include at least a departure date, a departure time, an arrival date, and an arrival time;

and

wherein the hotel tuples include at least a check-in date, a check-in time, a check-out date, and a check-out time.

3. The system of claim 1, wherein the scheduler is further configured to:

create an adjacency matrix of the itinerary network based on a classification of the main nodes and the child nodes from the two or more nodes of the itinerary network.

4. The system of claim 1, wherein the analyzing of the plurality of tuples includes:

separating the plurality of tuples into groups, each group corresponding to one of the one or more passengers;

selecting a partition of the flight tuples for each of the one or more passengers; and

based on the hotel tuples and the partition of the flight tuples, performing a content search to determine the feasible itinerary solutions for each of the one or more passengers.

5. The system of claim 1, wherein the scheduler is further configured to identify identical dependencies associated with each of the one or more passengers based on the dependencies between two or more nodes, wherein the ranking is further based on the identical dependencies.

6. The system of claim 1, wherein the passenger preferences are determined based on one or more of the following:

the itinerary request and a preexisting selection for the one or more passengers from a previous itinerary request.

7. The system of claim 1, wherein the parser is further configured to:

identify a preexisting itinerary network associated with the one or more passengers, the preexisting itinerary network being associated with one or more previous itinerary requests associated with the one or more passengers; and

update the preexisting itinerary network based on the feasible itinerary solutions.

8. The system of claim 1, wherein the dependencies between two or more nodes include at least level dependencies.

9. The system of claim 1, wherein the two or more nodes are selected from a group comprising:

an origin city, a destination city, a hotel, a date, a time, an airline, and a connection between flights.

10. A method for translating user requests into itinerary solutions, the method comprising:

receiving, by a processor, an itinerary request associated with one or more passengers;

parsing, by a parser, the itinerary request to determine at least two nodes associated with the itinerary request, and dependencies between the at least two nodes;

combining, by the parser, the at least two nodes associated with the itinerary request into an itinerary network;

creating, by a scheduler, a level matrix for the itinerary network by selecting main nodes and child nodes that depend on the main nodes, from the at least two nodes in the itinerary network;

creating, by the scheduler, a topology of the itinerary network based on the level matrix, the topology including at least an ordered list of the at least two nodes;

processing, by the scheduler, the itinerary network using the topology to create a plurality of tuples, wherein;

each tuple of the plurality of tuples is a set of objects associated with a node; and

the plurality of tuples includes at least one flight tuple and at least one hotel tuple;

for each of the one or more passengers, partitioning the flight tuples into one or more disjoint partition subsets by the scheduler, the disjoint partition subsets determined based on a relation or property of interest;

performing, by the scheduler, a content search for each passenger for;

each partition subset of the flight tuples;

each of the hotel tuples;

performing, by the scheduler, a content search across all partition subsets for all passengers;

generating feasible itinerary solutions based on results of the content searches;

ranking, by the scheduler, the feasible itinerary solutions based on at least passenger preferences; and

presenting, by the processor, at least one itinerary solution selected from the feasible itinerary solutions based on the ranking to the one or more passengers.

11. The method of claim 10, wherein the flight tuples include at least a departure date, a departure time, an arrival date, and an arrival time;

and

wherein the hotel tuples include at least a check-in date, a check-in time, a check-out date, and a check-out time.

12. The method of claim 10, further comprising:

creating, by the scheduler, an adjacency matrix of the itinerary network based on a classification of the at least two nodes into the main nodes and the child nodes.

13. The method of claim 10, further comprising identifying, by the scheduler, based on the dependencies between the at least two nodes, identical dependencies associated with each of the one or more passengers, wherein the ranking is further based on the identical dependencies.

14. The method of claim 10, wherein the passenger preferences are determined based on one or more of the following:

the itinerary request and a preexisting selection for the one or more passengers from a previous itinerary request.

15. The method of claim 10, further comprising:

identifying, by the parser, a preexisting itinerary network associated with the one or more passengers, the preexisting itinerary network being associated with one or more previous itinerary requests associated with the one or more passengers; and

updating, by the parser, the preexisting itinerary network based on the feasible itinerary solutions.

16. The method of claim 10, wherein the dependencies between the at least two nodes include at least level dependencies.

17. The method of claim 10, further comprising:

creating an itinerary object associated with the itinerary request, the itinerary object being a set of data that contains at least one of;

an itinerary request;

an itinerary network created by the parser;

at least one structure created by the scheduler, including at least one of an adjacency matrix, a level matrix, and a topology;

a list of partitions;

itinerary solutions;

a list of passengers; and

function calls.

18. The method of claim 10, wherein the generating feasible itinerary solutions are generated for each passenger from a Cartesian product algorithm that combines solutions from the partition subsets and individual hotel tuples correctly into one set.

19. A system for translating user requests into itinerary solutions, the system comprising:

a processor configured to;

receive an itinerary request associated with one or more passengers; and

present at least one itinerary solution selected from feasible itinerary solutions based on ranking to the one or more passengers;

a parser configured to;

parse the itinerary request to create an itinerary network associated with the itinerary request, the itinerary network including two or more nodes and dependencies between the two or more nodes; and

a scheduler configured to;

create a topology of the itinerary network, the topology including at least an ordered list of the two or more nodes;

process the itinerary network using the topology to create a plurality of tuples, the plurality of tuples including at least flight tuples and hotel tuples;

based on the itinerary request and the dependencies between the two or more nodes, analyze the plurality of tuples, wherein the analyzing of the plurality of tuples includes;

separating the plurality of tuples into groups, each group corresponding to one of the one or more passengers;

selecting a partition of the flight tuples for each of the one or more passengers; and

based on the hotel tuples and the partition of the flight tuples, performing a content search to determine the feasible itinerary solutions for each of the one or more passengers;

based on the analysis, determine the feasible itinerary solutions;

rank the feasible itinerary solutions based on at least passenger preferences;

based on the dependencies between the two or more nodes, organize the two or more nodes into levels to create a level matrix of the itinerary network, wherein the topology of the itinerary network is created based on the level matrix;

based on the dependencies between the two or more nodes, classify each of the at least two or more nodes into a main node and a child node, the child node being dependent on the main node;

based on the classifying, create an adjacency matrix of the itinerary network; and

based on the dependencies between the two or more nodes, identify identical dependencies associated with each of the one or more passengers, wherein the ranking is further based on the identical dependencies.