Computer implemented methods and apparatus for recommending events

• US 9,892,170 B2
• Filed: 02/01/2017
• Issued: 02/13/2018
• Est. Priority Date: 01/21/2013
• Status: Active Grant

• Current Assignee: Salesforce.com, Inc.
• Original Assignee: Salesforce.com, Inc.
• Inventors: Palmert, Joel, Meng, Xiao
• Primary Examiner(s): Casanova, Jorge A
• Application Number:
  US15/422,178
• Publication Number:
  US 20170154048A1
• Time in Patent Office: 377 Days
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Disclosed are methods, apparatus, systems, and computer-readable storage media for recommending an event to a user. In some implementations, one or more servers receive information identifying a plurality of events. The one or more servers store data of the plurality of events in a first one or more data tables having an action field, an item field, and a user field, and analyze the data of the first one or more data tables to generate one or more pairs, each pair including information identifying a set of events and a target event. The one or more servers may calculate a similarity score for each of the one or more pairs and store the respective similarity score in a second one or more data table having a set field, a target event field, and a similarity score field.

Claims

1. A system for identifying an event to a user, the system comprising:

a database system implemented using a server system including one or more hardware processors, the one or more hardware processors configured to;

monitor events performed in the database system by users;

identify a pair of the events including a first event and an associated second target event, the first event including a first action with a first action type associated with a first item and the second target event including a second action with a second action type associated with a second item, the first action type being different from the second action type;

determine a similarity score for the pair of events based on at least a frequency of the users performing the first event in association with performing the second target event;

monitor actions for an identified user; and

notify the identified user of the second target event based on a similarity of the actions with the first event and the similarity score for the pair of events.

2. The system of claim 1, the server system further configured to use collaborative filtering to determine the similarity score.

3. The system of claim 1, the server system further configured to:

determine an action identifier, an item identifier, and a user identifier for each of the events;

store the action identifier in an action field of a database table;

store the item identifier in an item field of the database table; and

store the user identifier in a user field of the database table.

4. The system of claim 3, the server system further configured to analyze the action identifier, item identifier, and user identifier for each of the events in the database table to generate the pair of events.

5. The system of claim 1, the server system further configured to store the pair of events and the similarity score in a database table, wherein the database table includes a first event field storing the first event, a second target event field storing the second target event, and a similarity score field storing the similarity score.

6. The system of claim 1, the server system further configured to transmit, to a computing device associated with the identified user for displaying on a user interface, a message indicating other users performing the first event have also performed the second tartlet event.

7. The system of claim 1, the server system further configured to transmit, to a computing device associated with the identified user for displaying on a user interface, a recommendation that the identified user perform the second target event.

8. The system of claim 1, the server system further configured to transmit, to a computing device associated with the identified user, instructions for arranging or rearranging displayed data on a user interface to highlight the second target event.

9. The system of claim 1, wherein the first action views the first item and the second action purchases the second item.

10. A method for identifying events in a database system, comprising:

monitoring, by one or more hardware processors in the database system, events performed by users;

identifying, by the database system, a pair of the events including a first event and a second event, the first event including a first action associated with a first item and the second event including a second action type associated with a second item;

generating, by the database system, a similarity score for the pair of events based at least on a frequency of the users performing the first event in association with performing the second target event;

monitoring, by the database system, user actions performed by an identified user; and

notifying, by the database system, the identified user of the second event based on a comparison of the user actions with the first event and the similarity score between the first event and the second event.

11. The method of claim 10, further comprising using, by the database system, collaborative filtering for generating the similarity score.

12. The method of claim 10, further comprising sending, by the database system, a message to a computing system associated with the identified user for displaying on a user interface, the message recommending the second item in the second event.

13. The method of claim 10, further comprising:

determining an action identifier, an item identifier, and a user identifier for each of the events;

storing the action identifier in an action field of a database table;

storing the item identifier in an item field of the database table;

storing the user identifier in a user field of the database table; and

identifying the pair of the events based on the action identifier, item identifier, and user identifier for each of the events stored in the database table.

14. The method of claim 10, further comprising:

identifying multiple pairs of the events based on a frequency of the users performing each of the events in each of the multiple pairs of the events;

generating similarity scores for each of the multiple pairs of the events;

selecting at least one of the multiple pairs of events based on a comparison of the user actions with the first event in each of the multiple pairs of events and the similarity scores for the multiple pairs of events; and

notifying the identified user of the second event in the selected multiple pairs of the events.

15. The method of claim 10, further comprising sending a message to a computing system associated with the identified user, the message indicating other users performing the first event have also performed the second event.

16. The method of claim 10, further comprising transmitting, to a computing device associated with the identified user, instructions for arranging or rearranging displayed data and/or user interface components on a user interface to highlight the second event.

17. The method of claim 10, wherein the first action views the first item and the second action purchases the second item.

18. A computer program product comprising program code to be executed by at least one processor when retrieved from a non-transitory computer-readable storage medium for identifying events, the program code comprising instructions configured to cause the processor to:

monitor events occurring in a computer system, each of the events including an action and an item;

identify event pairs each including a set of events and an associated target event;

derive collaborative filtering similarities for the event pairs based on a frequency of performing the set of events in association with performing the associated target event;

identify actions associated with a first user;

identify at least one of the set of events similar to the user actions; and

transmit a recommendation to a computing device associated with the first user that includes the target event associated with the identified at least one set of events.

19. The computer program product of claim 18, the instructions further configured to cause the processor to indicate in the recommendation that other users performing the identified set of events have also performed the associated target event.

20. The computer program product of claim 18, wherein a first action type for at least some of the set of events are different from a second action type for the associated target event.