SERVICE LOCATION RECOMMENDATIONS USING PREDICTIVE ANALYSIS

• US 20150269150A1
• Filed: 03/19/2014
• Published: 09/24/2015
• Est. Priority Date: 03/19/2014
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Sou, Socheat, Carper, George P., Zhao, Howard R.
• Application Number:
  US14/219,075
• Publication Number:
  US 20150269150A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0261 based on user location
• CPC Class Codes: G06Q 30/0639 Item locations
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/40 for vehicles, e.g. vehicle-to-pedestrians [V2P]

Abstract

Service locations can be recommended based upon a user electronic device request specifying parameters that include a service type, an available time value and location information. Based upon the parameters, queries are sent to a service database to retrieve profile information about service locations that satisfy the service type and to a travel database to retrieve travel time information for the service locations that satisfy the service type. Time estimates for obtaining services at each of the service locations are generated by applying a service predicting algorithm using the profile information about service locations and the travel time information for the service locations. The service locations that satisfy the service type are filter as a function of the available time value and the time estimates. The filtering results are provided to the user device.

Claims

1. A computer-implemented method for recommending service locations, the method comprising:

receiving, from a user electronic device, a request specifying parameters that include a service type, an available time value and location information;

querying, based upon the parameters, a service database to retrieve profile information about service locations that satisfy the service type;

querying, based upon the parameters, a travel database to retrieve travel time information for the service locations that satisfy the service type;

generating time estimates for obtaining services at each of the service locations by applying a service predicting algorithm using the profile information about service locations and the travel time information for the service locations;

filtering the service locations that satisfy the service type as a function of the available time value and the time estimates; and

providing results of the filtering to the user electronic device.

2. The method of claim 1, further comprising generating the profile information about the service locations by applying natural language processing to unstructured data describing the service locations that satisfy the service type.

3. The method of claim 1, further comprising generating the profile information about the service locations by obtaining actual service times from mobile devices of individuals using the service locations.

4. The method of claim 1, wherein the service predicting algorithm is configured to weight the profile information about service locations according to an age of the data.

5. The method of claim 1, further comprising generating the profile information about the service locations by interfacing with a reservation system at a restaurant.

6. The method of claim 1, wherein the travel time information for the service locations that satisfy the service type is based upon a current location of the user electronic device.

7. The method of claim 1, further comprising querying, based upon the parameters, a travel database to retrieve travel time information from the service locations that satisfy the service type to a destination that is different than a current location of the user electronic device.

8. The method of claim 1, wherein the service type is restaurant.

9. The method of claim 8, further comprising generating the profile information about service locations by analyzing unstructured data from online reviews.

10. A system for recommending service locations, the system comprising:

one or more computer processor circuits configured with;

an input-output module configured to receive, from a user electronic device, a request specifying parameters that include a service type, an available time value and location information;

a query generation module configured to;

query, based upon the parameters, a service database to retrieve profile information about service locations that satisfy the service type;

query, based upon the parameters, a travel database to retrieve travel time information for the service locations that satisfy the service type;

a service predicting algorithm module configured to generate time estimates for obtaining services at each of the service locations by applying a service predicting algorithm that uses the profile information about service locations and the travel time information for the service locations; and

a filter module configured to filter the service locations that satisfy the service type as a function of the available time value and the time estimates.

11. The system of claim 10, wherein input-output module is further configured to provide results from the filter module to the user electronic device.

12. The system of claim 10, wherein the service predicting algorithm module is further configured to apply natural language processing to unstructured data describing the service locations that satisfy the service type.

13. The system of claim 10, wherein the service predicting algorithm module is further configured to obtain actual service times from mobile devices of individuals at the service locations.

14. The system of claim 10, wherein the service predicting algorithm module is further configured to weight the profile information about service locations according to an age of the data.

15. The system of claim 10, wherein the input-output module is further configured to interface with a reservation system at a restaurant.

16. The system of claim 10, wherein the query generation module is further configured to querying, based upon the parameters, the travel database to retrieve travel time information from the service locations that satisfy the service type to a destination that is different than a current location of the user electronic device.

17. The system of claim 16, wherein the query generation module is further configured to use global positioning system (GPS) data from the user electronic device to determine the current location of the user electronic device.

18. The system of claim 10, wherein service predicting algorithm module is configured to use evidence-based learning.

19. A computer program product for recommending service locations, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions readable by at least one processing circuit to cause the at least one processing circuit to perform a method comprising:

receiving, from a user electronic device, a request specifying parameters that include a service type, an available time value and location information;

querying, based upon the parameters, a service database to retrieve profile information about service locations that satisfy the service type;

querying, based upon the parameters, a travel database to retrieve travel time information for the service locations that satisfy the service type;

generating time estimates for obtaining services at each of the service locations by applying a service predicting algorithm that uses the profile information about service locations and the travel time information for the service locations;

filtering the service locations that satisfy the service type as a function of the available time value and the time estimates; and

providing results of the filtering to the user electronic device.