Cross border transaction machine translation

• US 9,940,658 B2
• Filed: 12/30/2014
• Issued: 04/10/2018
• Est. Priority Date: 02/28/2014
• Status: Active Grant

• Current Assignee: PayPal, Inc. (PayPal Holdings, Inc.)
• Original Assignee: PayPal, Inc. (PayPal Holdings, Inc.)
• Inventors: Delingat, Marc, Sawaf, Hassan, Nagarur, Kiran Reddy, Vardi, Yoram, Cozzi, Alex
• Primary Examiner(s): Airapetian, Mila
• Application Number:
  US14/586,862
• Publication Number:
  US 20150248718A1
• Time in Patent Office: 1,197 Days
• Field of Search: 705 1454, 707760
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy

Abstract

A user query for items is received in a first language and translated from the first language to a second language. A result set in the second language that meets the query is obtained and is translated into the first language for presentation to the user. User feedback is used to build an ontology for optimizing the translation from the first language to the second language based on query context and the feedback. Query context may include information determined by learning semantic relationships between keywords in the query. Optimizing may include building an ontology used by a machine translator to translate key words from the first language to the second language. The number of items in the result set are measured or information is abstracted from the feedback and correlated to ontological information of the result set. The system adapts to changes in meanings in the first language over time.

Claims

1. A computer implemented method comprising:

receiving a query from a client machine for items, in which the query is in a first language;

translating the query into a second language, including optimizing, for ecommerce, a translation of the query from the first language into the second language based at least in part on an ontology;

obtaining a result set of items in the second language that meet the query;

translating the result set into the first language for presentation to the client machine; and

monitoring feedback from the client machine, including observing actions a user of the client machine takes relative to the result set, the actions including the user purchasing a product from the result set and placing a product watch from the result set; and

building the ontology based at least on part of the observed actions such that the ontology reflects language changes over time.

2. The method of claim 1, the method further comprising building the ontology based on query context and explicit user feedback, including a rating submitted by the user of the client machine, the rating associated with user perception of a relevance of the results of the query.

3. The method of claim 2 wherein the query context comprises information determined by learning semantic relationships between keywords in the query.

4. The method of claim 2, wherein building the ontology comprises at least one of measuring a number of items in the result set or abstracting information from the feedback and correlating the feedback to ontological information of the result set.

5. The method of claim 1 wherein the query comprises a plurality of queries received over time.

6. One or more computer-readable hardware storage device having embedded therein a set of instructions which, in response to being executed by one or more processors of a computer, causes the computer to execute operations comprising:

receiving a query from a client machine for items, the query in a first language;

translating the query into a second language, including optimizing, for ecommerce, a translation of the query from the first language into the second language based at least in part on an ontology;

obtaining a result set of items in the second language that meet the query;

translating the result set into the first language for presentation to the client machine; and

monitoring feedback from the client machine, including observing actions a user of the client machine takes relative to the result set, the actions including the user purchasing a product from the result set and placing a product watch from the result set; and

building the ontology based at least on part of the observed actions such that the ontology reflects language changes over time.

7. The one or more computer readable hardware storage device of claim 6, the operations further comprising building the ontology based at least in part on query context and explicit user feedback, including a rating submitted by the user of the client machine, the rating associated with user perception of a relevance of the results of the query.

8. The one or more computer readable hardware storage device of claim 7 wherein the query context comprises information determined from learning semantic relationships between keywords in the query.

9. The one or more computer readable hardware storage device of claim 6, wherein building the ontology comprises at least one of measuring a number of items in the result set or abstracting information from the feedback and correlating the feedback to ontological information of the result set.

10. The one or more computer readable hardware storage device of claim 6, wherein the query comprises a plurality of queries received over time.

11. A non-transitory computer-readable medium having encoded therein programing code executable by one or more hardware processors to perform operations comprising:

receiving a query from a client machine for items, the query in a first language;

translating the query into a second language, including optimizing, for ecommerce, a translation of the query from the first language into the second language based at least in part on an ontology;

obtaining a result set of items in the second language that meet the query;

translating the result set into the first language for presentation to the client machine; and

monitoring feedback from the client machine, including observing actions a user of the client machine takes relative to the result set, the actions including the user purchasing a product from the result set and placing a product watch from the result set; and

to build the ontology based at least on part of the observed actions such that the ontology reflects language changes over time.

12. The computer-readable medium of claim 11, the operations further comprising building the ontology based at least in part on the observed actions and further based at least in part on explicit user feedback, including a rating submitted by the user of the client machine, the rating associated with user perception of a relevance of the results of the query.

13. The computer-readable medium of claim 12, the operations further comprising determining the query context by learning semantic relationships between keywords in the query.

14. The computer-readable medium of claim 11, the operations further comprising measuring a number of items in the result set or abstract information from the feedback and to correlate the feedback to ontological information of the result set.

15. The computer-readable medium of claim 11 wherein the query comprises a plurality of queries received over time.