Generating travel queries in response to free-text search queries

• US 10,423,684 B2
• Filed: 08/12/2016
• Issued: 09/24/2019
• Est. Priority Date: 10/24/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Carter, James, Daughtrey, Rodney S.
• Primary Examiner(s): Tran, Loc
• Application Number:
  US15/236,385
• Publication Number:
  US 20160350433A1
• Time in Patent Office: 1,138 Days
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06Q 50/14 Travel agencies

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating travel queries in response to free text queries. One of the methods includes receiving a free text query; generating a travel query from the free text query, wherein the travel query expressly specifies an origin location, a destination location, and a departure date, wherein each of the origin location, the destination location, and the departure date are expressly identified as such in the travel query; and submitting the travel query to a travel search engine. Optionally the method includes obtaining user information about a user associated with the free text query, obtaining popular travel information, and deriving origin or destination locations, or departure or return dates from the free text query, the user information, and the popular-travel information.

Claims

1. A system, comprising:

one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising;

receiving an input of a free text query, wherein the free text query is received as an input into a search interface for a general search engine presented on a client computing device;

using the free text query for the general search engine to derive terms corresponding to particular travel constraints including terms corresponding to a destination location and a departure date;

for each of the terms corresponding to particular travel constraints, determining a respective probability of the term being related to a request for travel information, comprising;

retrieving user account information corresponding to a user associated with the free text query and popular travel information, wherein the popular-travel information comprises information about travel that is popular with users;

determining the respective probability that the term is related to a request for travel information based on the user account information, the popular travel information, and the free text query;

determining whether a combined probability of the terms being related to a request for travel information exceeds a threshold value, wherein the combined probability is based on the respective probability of each term; and

in response to determining that the combined probability of the terms being related to a request for travel information exceeds the threshold value;

generating a travel query from the terms derived from the free text query, wherein the generated travel query expressly specifies the derived destination location and departure date as travel constraints; and

submitting the travel query to a travel search engine distinct from the general search engine to obtain travel search results based on the travel search query and to present the travel search results based on the travel search query via the client computing device.

2. The system of claim 1, wherein the travel query further expressly specifies an origin location, a duration of stay, or a return date, wherein the origin location, duration of stay, or return date is expressly identified as such.

3. The system of claim 1, wherein the one or more storage devices further store instructions that when executed by the one or more computers cause the one or more computers to perform one or more of:

deriving the origin location;

deriving the destination location; and

deriving the departure date.

4. The system of claim 3, wherein the popular-travel information comprises information about travel that is popular with users and wherein the one or more storage devices further store instructions that when executed by the one or more computers cause the one or more computers to derive the origin location from the user information and the popular-travel information.

5. The system of claim 3, wherein the one or more storage devices further store instructions that when executed by the one or more computers cause the one or more computers to derive the destination location from the free text query, the user information, and the popular-travel information.

6. The system of claim 3, wherein the one or more storage devices further store instructions that when executed by the one or more computers cause the one or more computers to derive the departure date from the free text query, the user information, and the popular-travel information.

7. The system of claim 1, wherein the operations further comprise:

deriving one or more of the origin location, the destination location, and the departure date from the free text query, the user information, and the popular-travel information.

18. The system of claim 1, further comprising:

receiving an input of a subsequent free text query, wherein the subsequent free text query is received as an input into the search interface for the general search engine presented on the client computing device;

using the subsequent free text query for the general search engine to derive terms corresponding to particular travel constraints;

for each term corresponding to a particular travel constraint, determining a subsequent respective probability of the term being related to a subsequent query for travel information;

determining whether a subsequent combined probability of the terms being related to a subsequent query for travel information exceeds a threshold value; and

in response to determining that the subsequent combined probability of the terms being related to a subsequent query for travel information not exceeding the threshold value, generating, by the general search engine, subsequent search results that satisfy the subsequent free text query input into the general search engine without using the travel search engine and presenting via the client computing device the subsequent search results that satisfy the subsequent free text query input into the general search engine.

8. A computer-implemented method, comprising:

receiving, by one or more computing devices associated with a general search engine, a free text query, wherein the free text query is input by a user into a search interface for the general search engine presented on a client computing device;

deriving, by the one or more computing devices and using the free text query, terms corresponding to particular travel constraints;

for each of the terms corresponding to particular travel constraints, determining a respective probability of the term being related to a request for travel information, comprising;

retrieving user account information corresponding to a user associated with the free text query and popular travel information, wherein the popular-travel information comprises information about travel that is popular with users; and

determining the respective probability that the term is related to a request for travel information based on the user account information, the popular travel information, and the free text query;

determining, by the one or more computing devices, whether a combined probability of the terms being related to a request for travel information exceeds a threshold value, wherein the combined probability is based on the respective probability of each term;

in response to determining that the combined probability exceeds the threshold value;

generating, by the one or more computing devices, a travel query from the terms derived from the free text query, wherein the generated travel query expressly specifies the travel constraints, and wherein each of the travel constraints are expressly identified as such in the travel query; and

submitting, by the one or more computing devices, the travel query to a travel search engine distinct from the general search engine to obtain travel search results based on the travel search query and to present the travel search results based on the travel search query via the client computing device; and

in response to the combined probability of the terms being related to a request for travel information not exceeding the threshold value, generating, by the one or more computing devices via the general search engine, search results that satisfy the free text query without using the travel search engine and presenting via the client computing device the search results that satisfy the free text query input into the general search engine.

9. The method of claim 8, further comprising:

generating the travel query from the free text query, the user information, and the popular-travel information.

10. The method of claim 9, wherein the user information identifies at least one of:

user travel preferences;

user location;

past user origin locations;

past user destination locations;

past user travel cost for travel that comprises the past user origin locations and the past user destination locations;

past user destination types;

past user departure dates;

past user durations of stay;

or

user contacts and the location of the contacts.

11. The method of claim 10, wherein generating the travel query comprises generating a travel query for air travel, and wherein, when the user information identifies past user origin locations and past user destination locations, the past user origin locations and past user destination locations comprise cities that have airports.

12. The method of claim 9, wherein the popular-travel information identifies at least one of:

popular origin locations;

popular destination locations;

estimated travel cost for travel that comprises the popular origin locations and the popular destination locations;

popular destination types;

popular departure dates;

popular durations of stay;

or

events and the location of the events.

13. The method of claim 12, wherein, when the popular-travel information identifies popular origin locations, the method further comprises:

selecting the popular origin locations from all origin locations within a predetermined maximum distance from a current user location, wherein the predetermined maximum distance is measured in terms of time of travel, cost of travel, or distance of travel from the current user location.

14. The method of claim 12, wherein, when the popular-travel information identifies popular destination locations, the method further comprises:

selecting the popular destination locations from all destination locations outside a predetermined minimum distance from a current user location, wherein the predetermined minimum distance is measured in terms of time of travel, cost of travel, or distance of travel from the current user location.

15. The method of claim 12, wherein, when the popular-travel information identifies popular destination types, the popular destination types comprise beach destinations, skiing destinations, mountain destinations, national park destinations, or romantic destinations.

16. The method of claim 12, wherein, when the popular-travel information identifies events and the locations of the events, the method further comprises:

obtaining information identifying the events and the location of the events from an online database of events.

19. The method of claim 8, further comprising:

receiving, by the one or more computing devices, an input of a subsequent free text query, wherein the subsequent free text query is received as an input into the search interface for the general search engine presented on the client computing device;

using, by the one or more computing devices, the subsequent free text query for the general search engine to derive terms corresponding to particular travel constraints;

for each term corresponding to a particular travel constraint, determining, by the one or more computing devices, a subsequent respective probability of the term being related to a subsequent query for travel information;

determining, by the one or more computing devices, whether a subsequent combined probability of the terms being related to a subsequent query for travel information exceeds a threshold value; and

in response to determining that the subsequent combined probability of the terms being related to a subsequent query for travel information not exceeding the threshold value, generating, by the one or more computing devices and via the general search engine, subsequent search results that satisfy the subsequent free text query input into the general search engine without using the travel search engine and presenting via the client computing device the subsequent search results that satisfy the subsequent free text query input into the general search engine.

17. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by one or more computing devices cause the one or more computing devices to perform operations comprising:

receiving a free text query, wherein the free text query is input by a user into a search interface for a general search engine presented on a client computing device;

using the free text query to derive terms corresponding to particular travel constraints;

determining, for each of the derived terms, a respective probability of being related to a query for travel information, comprising;

retrieving user account information corresponding to a user associated with the free text query and popular travel information, wherein the popular-travel information comprising information about travel that is popular with users;

based on the user account information, the popular travel information, and the free text query, determining the respective probability that the term is related to a query for travel information;

determining whether a combined probability of the terms being related to a query for travel information exceeds a threshold value;

in response to determining that the combined probability exceeds the threshold value;

generating a travel query from the terms derived from the free text query, wherein the travel query expressly specifies travel constraints, and wherein each of the travel constraints are expressly identified as such in the travel query; and

submitting the travel query to a travel search engine distinct from the general search engine to obtain travel search results based on the travel search query and to present the travel search results based on the travel search query via the client computing device.

20. The non-transitory computer storage medium of claim 17, wherein the computer program further comprises instructions that when executed by one or more computing devices cause the one or more computing devices to:

receive an input of a subsequent free text query, wherein the subsequent free text query is received as an input into the search interface for the general search engine presented on the client computing device;

use the subsequent free text query for the general search engine to derive terms corresponding to particular travel constraints;

for each term corresponding to a particular travel constraint, determine a subsequent respective probability of the term being related to a subsequent query for travel information;

determine whether a subsequent combined probability of the terms being related to a subsequent query for travel information exceeds a threshold value; and

in response to determining that the subsequent combined probability of the terms being related to a subsequent query for travel information not exceeding the threshold value, generate, by the general search engine, subsequent search results that satisfy the subsequent free text query input into the general search engine without using the travel search engine and presenting via the client computing device the subsequent search results that satisfy the subsequent free text query input into the general search engine.