Method and apparatus for providing availability of airline seats

• US 20020133382A1
• Filed: 03/15/2002
• Published: 09/19/2002
• Est. Priority Date: 02/04/1999
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: ITA Software, Inc. (Alphabet Inc.)
• Inventors: Galperin, Gregory R., DeMarcken, Carl G.
• Granted Patent: US 8,239,219 B2
• Time in Patent Office: Days
• US Class Current: 705/5
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events
• CPC Class Codes: G06Q 10/025 Coordination of plural reservations, e.g. plural trip segments, transportation combined with accommodation
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data

Abstract

A computer program product, method and system for producing seat availability information for a mode of travel such as airline travel produce a prediction of availability of a seat in accordance with an availability query. The prediction is used in place of making an actual query to an airline or other travel mode availability system.

Claims

1. A computer program product residing on a computer readable medium comprises instructions for causing a computer to:

produce a prediction of availability of a seat for a mode of transportation in accordance with an availability query.

2. The computer program product of claim 1 wherein instructions that cause the computer to provide a prediction of availability comprise instructions to cause the computer to:

access a database of stored query results to produce a prediction in response to the query.

3. The computer program product of claim 1 wherein instructions that cause the computer to access the database further comprise instructions that cause a computer to:

receive the availability query and determine whether the availability query corresponds to or is similar to a query stored in the database; and

retrieve a stored answer associated with a query stored in the database, that corresponds to or is similar to availability query or otherwise send an actual availability query to the airline reservation system.

4. The computer program product of claim 3 wherein instructions that cause the computer to access the database further comprise instructions for causing the computer to:

determine whether the retrieved, stored answer is stale and, if the retrieved stored answer is stale,

send an actual availability query to an availability system; and

if the retrieved, stored answer is not stale, return the retrieved, stored answer as the prediction.

5. The computer program product of claim 4 wherein instructions that cause the computer to access the database further comprise instructions for causing a computer to:

use a model-based predictor to provide a prediction of the answer to the query if there is no availability query found in the database.

6. The computer program product of claim 1 wherein the predictor comprises instructions for causing the computer to:

parse the availability query to produce a set of features for use by an availability model.

7. The computer program product of claim 1 wherein the instructions that cause the computer to produce a prediction comprise instructions for causing the computer to:

determine features of the availability query; and

apply determined features of the query to an availability model.

8. The computer program product of claim 7 wherein the availability model is a statistical or deterministic classifier that is trained using historical availability queries.

9. The computer program product of claim 8 wherein the statistical or deterministic classifier is a linear or quadratic discriminator, factorial model, decision tree, decision list, neural network, sigmoidal network, Bayesian network, naive Bayesian network, Markov random field, maximum entropy model, exponential or log linear model, nearest neighbor model, radial basis model or support vector model.

10. The computer program product of claim 1 wherein instructions that cause the computer to provide a predicted answer of availability comprise instructions that cause a computer to simulate an airline'"'"'s availability system.

11. The computer program product of claim 1 wherein instructions that cause the computer to provide a prediction of availability comprise instructions to cause the computer to:

access a database that has probability estimates stored as a function of booking codes.

12. The computer program product of claim 11 wherein the database that has probability estimates stored as a function of booking codes further has probability estimates stored as a function of booking codes, time before departure and airline.

13. The computer program product of claim 1 wherein instructions that cause the computer to provide a prediction of availability comprise instructions that cause a computer to:

access a database that has true/false indications stored as a function of booking codes.

14. The computer program product of claim 13 wherein the true/false indications are further stored as functions of booking codes, time before departure, and airline.

15. The computer program product of claim 1 wherein the prediction includes a number of seats that are available.

16. The computer program product of claim 1 wherein the prediction includes a number of seats that are available on a booking code basis.

17. The computer program product of claim 1 wherein the prediction includes a confidence factor indicating how likely it is that the prediction is correct.

19. The method of claim 18 wherein producing further comprises:

accessing a database of stored query results to produce the prediction.

20. The method of claim 19 further comprising:

receiving the availability query and determine whether the availability query corresponds to or is similar to a query stored in the database; and

retrieving a stored answer associated with a query stored in the database that corresponds to or is similar to availability query or otherwise send an actual availability query to the airline reservation system.

21. The method of claim 19 further comprising:

determining whether the retrieved, stored answer is stale and, if the retrieved stored answer is stale,

sending an actual availability query to the airline, and

if the retrieved, stored answer is not stale,

returning the retrieved, stored answer as the prediction.

22. The method of claim 18 wherein providing a predicted availability answer further comprises:

sending the query to a model-based predictor to provide a prediction of the answer to the query.

23. The method of claim 22 further comprising:

parsing the availability query to produce a set of features for use by an availability model; and

applying selected ones of the determined features of the query to the availability model.

24. The method of claim 1 wherein the availability model is a statistical or deterministic classifier.

25. The method of claim 1 wherein providing a predicted availability answer comprises:

simulating an airline'"'"'s availability system.

26. The method of claim 1 wherein providing a prediction of availability comprises:

accessing a database that has probability estimates stored as a function of booking codes.

18. A method for providing availability information for a seat on an airline, comprises:

producing a prediction of availability of the seat in accordance with an availability query.

27. A system for producing an availability answer in response to a query for airline seat availability information, comprises:

a predictor that is responsive to the query and produces an answer that corresponds to a prediction of airline seat availability.