Granted Patent B2

US 10,902,033 · App. 15/829,634 · Granted Jan 26, 2021

Abstract

Claims (52)

1. A system comprising:

one or more hardware processors; and

a memory storing instructions that, when executed by the one or more hardware processors, causes the one or more hardware processors to perform operations comprising:

extracting ticket data from content of a ticket;

determining, based on the extracted ticket data, whether the ticket indicates an issue with a trip involving a point of interest (POI);

based on the determining, extracting trip data from a trip log corresponding to the trip involving the POI identified from the ticket;

identifying, from a data storage, stored attributes of the POI;

analyzing the extracted ticket data, extracted trip data, and attributes to select a workflow to improve accuracy of the POI, the analyzing comprising determining a priority level to verify accuracy of the POI, the determining the priority level comprises determining a priority score based on two or more of a weighted average of trip counts to the POI, a weight average of trip costs to the POI, a weighted average of trip lengths, a metric of a category assigned to the POI, or a metric of likelihood of non-retention of a user associated with the ticket, the workflow being selected from a plurality of different workflows based on the priority level; and

triggering the workflow selected based on the determined priority level.

2. The system of claim 1 , wherein the priority level is high, and the workflow comprises triggering an operator to verify the accuracy of the POI.

3. The system of claim 1 , wherein the priority level is medium, and the workflow comprises triggering a user generated content (UGC) process, the UGC process comprising:

causing a user interface to be presented on a user device of a user that has an association with the POI, the user interface presenting a query regarding verifying the address;

receiving a response to the query via the user interface from the user device; and

using the response to verify the address.

4. The system of claim 1 , wherein the priority level is low, and the workflow process comprises storing the extracted ticket data to the data storage in response to the priority level being low.

5. The system of claim 1 , wherein the determining whether the ticket indicates an issue with the trip involving the POI comprises using the extracted ticket data to determine a probability that the ticket involves the POI by applying a classification model to the extracted ticket data.

6. The system of claim 5 , wherein the classification model comprises a logistic regression model.

7. The system of claim 1 , wherein the extracting ticket data from the content of the ticket comprises applying a natural language processing model to the ticket.

8. The system of claim 1 , wherein the extracting trip data from the trip log comprises detecting a drop-off location a threshold distance from an entered destination.

9. The system of claim 1 , wherein the analyzing further comprises determining, using a deep learning model, an accuracy score based on a sequence of characters from the ticket.

10. A method comprising:

extracting ticket data from content of a ticket;

determining, based on the extracted ticket data, whether the ticket indicates an issue with a trip involving a point of interest (POI);

based on the determining, extracting trip data from a trip log corresponding to the trip involving the POI identified from the ticket;

identifying, from a data storage, stored attributes of the POI;

analyzing, by one or more hardware processors, the extracted ticket data, extracted trip data, and attributes to select a workflow to improve accuracy of the POI, the analyzing comprising determining a priority level to verify accuracy of the POI, the workflow being selected from a plurality of different workflows based on the priority level, the workflow comprising:

triggering an operator to verify the accuracy of the POI for a high priority level,

triggering a user generated content (UGC) process for a medium priority level, the operator being different from a user associated with the POI that is involved in the UGC process, and

storing the extracted ticket data to the data storage for a low priority level; and

triggering the workflow selected based on the determined priority level.

11. The method of claim 10 , wherein the triggering the user generated content (UGC) process comprises:

causing a user interface to be presented on a user device of a user that has an association with the POI, the user interface presenting a query regarding verifying the address;

receiving a response to the query via the user interface from the user device; and

using the response to verify the address.

12. The method of claim 10 , wherein the determining whether the ticket indicates an issue with the trip involving the POI comprises using the extracted ticket data to determine a probability that the ticket involves the POI by applying a classification model to the extracted ticket data.

13. The method of claim 12 , wherein the classification model comprises a logistic regression model or a classification tree model.

14. The method of claim 10 , wherein the extracting trip data from the trip log comprises detecting a drop-off location a threshold distance from an entered destination.

15. The method of claim 10 , wherein the determining the priority level comprises determining a priority score, the determining the priority score being based on two or more of a weighted average of trip counts to the POI, a weight average of trip costs to the POI, a weighted average of trip lengths, a metric of a category assigned to the POI, or a metric of likelihood of non-retention of a user associated with the ticket.

16. The method of claim 10 , wherein the analyzing further comprises determining, using a deep learning model, an accuracy score based on a sequence of characters from the ticket.

17. A method comprising:

extracting ticket data from content of a ticket;

determining, based on the extracted ticket data, whether the ticket indicates an issue with a trip involving a point of interest (POI);

based on the determining, extracting trip data from a trip log corresponding to the trip involving the POI identified from the ticket;

identifying, from a data storage, stored attributes of the POI;

analyzing the extracted ticket data, extracted trip data, and attributes to select a workflow to improve accuracy of the POI, the analyzing comprising determining a priority level to verify accuracy of the POI, the determining the priority level comprises determining a priority score based on two or more of a weighted average of trip counts to the POI, a weight average of trip costs to the POI, a weighted average of trip lengths, a metric of a category assigned to the POI, or a metric of likelihood of non-retention of a user associated with the ticket, the workflow being selected from a plurality of different workflows based on the priority level; and

triggering the workflow selected based on the determined priority level.

18. The method of claim 17 , wherein the priority level is high, and the workflow comprises triggering an operator to verify the accuracy of the POI.

19. The method of claim 17 , wherein the priority level is medium, and the workflow comprises triggering a user generated content (UGC) process, the UGC process comprising:

causing a user interface to be presented on a user device of a user that has an association with the POI, the user interface presenting a query regarding verifying the address;

receiving a response to the query via the user interface from the user device; and

using the response to verify the address.

20. The method of claim 17 , wherein the priority level is low, and the workflow comprises storing the ticket data to the data storage in response to the priority level being low.

Assignments (8)