MANAGING AN EXCHANGE THAT FULFILLS NATURAL LANGUAGE TRAVEL REQUESTS

• US 20120239440A1
• Filed: 03/14/2012
• Published: 09/20/2012
• Est. Priority Date: 03/14/2011
• Status: Active Grant

• Current Assignee: Amgine Technologies (US), Inc.
• Original Assignee: Amgine Technologies (US), Inc.
• Inventors: Miller, Jonathan David, Miller, Harold Roy, Seider, Steven Mark
• Granted Patent: US 10,078,855 B2
• Time in Patent Office: Days
• US Class Current: 705/5
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions

Abstract

An exchange that fulfills natural language travel requests is described herein. According to some embodiments, systems for managing an exchange that fulfills natural language travel requests may include a publishing module that receives a plurality of inventory records from a plurality of suppliers, each of the plurality of inventory records pertaining to an available offering, the offering being defined by a set of metadata attributes, and a pattern recognition artificial intelligence engine that generates equivalent phrases for the set of metadata attributes from each inventory record by applying pattern recognition artificial intelligence to the set of metadata attributes, the equivalent phrases representing possible natural language queries to which an inventory record may correspond.

Claims

1. A method for managing an exchange that fulfills natural language travel requests, the method comprising:

receiving a plurality of inventory records from a plurality of suppliers, each of the plurality of inventory records pertaining to an available offering, the offering being defined by a set of metadata attributes; and

generating equivalent phrases for the set of metadata attributes from each inventory record by applying pattern recognition artificial intelligence to the set of metadata attributes, the equivalent phrases representing possible natural language queries to which an inventory record may correspond.

2. The method according to claim 1, further comprising parsing the plurality of inventory records to:

evaluate the set of metadata attributes for each inventory record; and

determine at least one category to associate with an inventory record based upon the set of metadata attributes of the inventory records.

3. The method according to claim 1, further comprising generating a new category for a set of metadata attributes of an inventory record when an association between an inventory record and at least one existing category cannot be determined.

4. The method according to claim 1, wherein an inventory record comprises an expiry date.

5. The method according to claim 1, wherein equivalent phrases for inventory records are grouped into equivalent phrase classes, wherein the equivalent phrase class are stored in an equivalent phrase class database.

6. The method according to claim 5, further comprising:

receiving a natural language search query;

applying semantic natural language parsing to the natural language search query to determine keywords and phraseology for the natural language search query;

comparing the keywords and phraseology to the equivalent phrase classes stored in the equivalent phrase class database; and

returning at least one inventory record that corresponds to the natural language search query when any of the keywords or phraseology substantially corresponds to at least one equivalent phrase.

7. The method according to claim 1, further comprising:

receiving a natural language search query that comprises a multifaceted travel itinerary;

determining itinerary components included in the natural language search query;

parsing the itinerary to generate categorized search request components;

constructing a multifaceted itinerary search request that includes at least a portion of the categorized search request components;

matching inventory records to the categorized search request components included in the multifaceted itinerary search request; and

returning at least one itinerary response that includes matching itinerary components.

8. The method according to claim 1, further comprising applying heuristic logic to the natural language search query to learn equivalent phrases for natural language search query when at least a portion of the natural language search query does not correspond to at least one of the generated equivalent phrases.

9. The method according to claim 1, further comprising determining dependencies for a metadata attribute, the dependency comprising at least one or more of a location dependency, a temporal dependency, a traveler preference dependency, or any combinations thereof.

10. A method for managing an exchange that fulfills natural language travel requests, the method comprising:

receiving a bid from a first party, the bid comprising a set of metadata attributes;

parsing the bid to;

evaluate the set of metadata attributes for the bid; and

determine at least one category to associate with the bid based upon the set of metadata attributes of the bid;

generating equivalent phrases for the set of metadata attributes of the bid by applying pattern recognition artificial intelligence to the set of metadata attributes, the equivalent phrases representing available bid queries; and

placing the bid request in an exchange system for fulfillment, the bid request comprising at least one of the available bid queries.

11. The method according to claim 10, further comprising allowing multiple additional parties to fulfill different portions of a bid request.

12. The method according to claim 10, wherein the bid request includes a travel itinerary received as a natural language query.

13. A system for managing an exchange that fulfills natural language itinerary requests, the system comprising:

a memory for storing executable instructions;

a processor for executing the instructions;

a publishing module stored in memory and executable by the processor to receive a plurality of inventory records from a plurality of suppliers, each of the plurality of inventory records pertaining to an available offering, the offering being defined by a set of metadata attributes; and

a pattern recognition artificial intelligence engine stored in memory and executable by the processor to generate equivalent phrases for the set of metadata attributes from each inventory record by applying pattern recognition artificial intelligence to the set of metadata attributes, the equivalent phrases representing possible natural language queries to which an inventory record may correspond.

14. The system according to claim 13, wherein the pattern recognition artificial intelligence engine further parses the plurality of inventory records to:

evaluate the set of metadata attributes for each inventory record; and

determine at least one category to associate with an inventory record based upon the set of metadata attributes of the inventory records.

15. The system according to claim 13, wherein the pattern recognition artificial intelligence engine further generates a new category for a set of metadata attributes of an inventory record when an association between an inventory record and at least one existing category cannot be determined.

16. The system according to claim 13, wherein an inventory record comprises an expiry date.

17. The method according to claim 13, further comprising a search module stored in memory and executable by the processor to receive a natural language search query;

and parse the natural language search query to determine keywords or phraseology for the natural language search query.

18. The method according to claim 17, wherein the pattern recognition artificial intelligence engine:

compares the parsed keywords and phraseology to equivalent phrases; and

returns at least one inventory record that corresponds to the natural language search query when any of the keywords or phraseology substantially corresponds to at least one equivalent phrase.

19. The system according to claim 13, further comprising a search module that:

receives a natural language search query that comprises a multifaceted travel itinerary;

determines itinerary components included in the natural language search query; and

constructs a multifaceted itinerary search request that includes at least a portion of the categorized search request components.

20. The method according to claim 19, wherein the pattern recognition artificial intelligence engine:

matches inventory records to the categorized search request components included in the multifaceted itinerary search request; and

returns at least one itinerary response that includes matching itinerary components.