Recommendation engine for interactive search forms

• US 9,268,759 B2
• Filed: 12/17/2012
• Issued: 02/23/2016
• Est. Priority Date: 12/17/2012
• Status: Active Grant

• Current Assignee: Amadeus S.A.S. (Amadeus Global Travel Distribution S.A.)
• Original Assignee: Amadeus S.A.S. (Amadeus Global Travel Distribution S.A.)
• Inventors: Robelin, Charles-Antoine, Benzine, Benjamin, Rothe, Ingolf Tobias
• Primary Examiner(s): Baderman, Scott
• Assistant Examiner(s): Kells, Asher
• Application Number:
  US13/716,864
• Publication Number:
  US 20140173404A1
• Time in Patent Office: 1,163 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 40/174 Form filling; Merging

Abstract

Systems, methods, and computer program products for interacting with an interactive form. A plurality of values for a plurality of controls of an interactive form are received at a server. The server determines a plurality of recommendation rules based upon the values for interrelated controls. Each value comprises a portion of a travel-related search query entered into one control of the interactive form by each of a plurality of users. Each recommendation rule logically connects two or more of the interrelated controls.

Claims

1. A method comprising:

receiving at a server a plurality of values for a plurality of controls of an interactive form, each value comprising a portion of a travel-related search query entered into one of the controls of the interactive form by each of a plurality of users;

determining with the server a plurality of recommendation rules based upon the values for interrelated controls, each recommendation rule logically connecting two or more of the interrelated controls;

computing the plurality of recommendation rules using collaborative historical data in a history database; and

aggregating at least one data set within the collaborative historical data in the history database according to increasing coarse granularity if a size of the data set is below a threshold, wherein aggregation of the at least one data set based on the increasing coarse granularity improves a statistical significance of the plurality of recommendation rules.

2. The method of claim 1 further comprising:

generating at the server at least one recommended value for one of the controls of the interactive form using the recommendation rules; and

communicating at least one recommended value from the server to a client device.

3. The method of claim 2 further comprising:

storing the at least one recommended value in a local cache at the client device.

4. The method of claim 1 further comprising:

communicating at least one of the recommendation rules from the server to a client device; and

generating at least one recommended value for one of the controls at the client device using the at least one of the recommendation rules.

5. The method of claim 1 wherein each travel-search query is received from a client device, and the recommendation rules are asynchronously determined in relation to a receipt time of each travel-search query.

6. The method of claim 1 further comprising:

storing the values received at the server in a database,

wherein the server reads the values from the database to determine the recommendation rules.

7. The method of claim 6 wherein the values are stored as aggregated data for a plurality of overlapping geographic regions of different sizes.

8. The method of claim 1 wherein determining with the server the recommendation rules based upon the values for controls comprises:

applying a plurality of predefined business rules and a plurality of static parameters at the server to determine the recommendation rules.

9. The method of claim 1 wherein determining with the server the recommendation rules based upon the values for controls comprises:

applying a predictive algorithm to compute the recommendation rules based upon probabilistic relationships between the values for the controls.

10. A computer program product comprising:

a computer readable storage medium; and

program code stored on the computer readable medium and configured to, upon execution by at least one processor, determine a plurality of recommendation rules by;

receive at a server a plurality of values for a plurality of controls of an interactive form, each value comprising a portion of a travel-related search query entered into one of the controls of the interactive form by each of a plurality of users;

determine with the server the plurality of recommendation rules based upon the values for interrelated controls, each recommendation rule logically connecting two or more of the interrelated controls;

compute the plurality of recommendation rules using collaborative historical data in a history database; and

aggregate at least one data set within the collaborative historical data in the history database according to increasing coarse granularity if a size of the data set is below a threshold, wherein aggregation of the at least one data set based on the increasing coarse granularity improves a statistical significance of the plurality of recommendation rules.

11. An apparatus comprising:

a server including a processor; and

program code configured to be executed by the processor to interact with an interactive form, the program code configured to cause the processor to receive a plurality of values for a plurality of controls of the interactive form, and determine a plurality of recommendation rules based upon the values for interrelated controls using collaborative historical data in a history database, wherein each value represents a portion of a travel-related search query entered into one of the controls by a plurality of users of the interactive form, and each recommendation rule logically connecting two or more of the interrelated controls, the program code configured to cause the processor to aggregate at least one data set within the collaborative historical data in the history database according to increasing coarse granularity if a size of the data set is below a threshold, wherein aggregation of the at least one data set based on the increasing coarse granularity improves a statistical significance of the plurality of recommendation rules.

12. The apparatus of claim 11 further comprising:

program code configured to cause the processor to generate at least one recommended value for one of the controls of the interactive form using the recommendation rules; and

program code configured to cause the processor to communicate at least one recommended value from the server to a client device.

13. The apparatus of claim 11 further comprising:

a recommendation rules database coupled with the processor; and

program code configured to cause the processor to store the recommendation rules in the recommendation rules database.

14. The apparatus of claim 11 further comprising:

program code configured to cause the processor to communicate at least one of the recommendation rules from the server to a client device.

15. The apparatus of claim 11 further comprising:

a database coupled with the server, the database configured to store the values received at the server,

wherein the server is configured to read the values from the database to determine the recommendation rules.

16. The apparatus of claim 15 wherein the database stores the values as aggregated data for a plurality of overlapping geographic regions of different sizes.

17. The apparatus of claim 11 further comprising:

a first database containing a plurality of predefined business rules; and

a second database containing a plurality of static parameters,

wherein the processor determines the recommendation rules based upon the predefined business rules in the first database and the static parameters in the second database.

18. The apparatus of claim 11 wherein the program code configured to cause the processor to determine the recommendation rules relating the interrelated controls for the values for interrelated controls comprises:

program code configured to cause the processor to apply a predictive algorithm to compute the recommendation rules based upon probabilistic relationships between the values for the controls.