Method and apparatus for transaction verification

• US 8,438,089 B1
• Filed: 02/29/2012
• Issued: 05/07/2013
• Est. Priority Date: 02/10/2012
• Status: Active Grant

• Current Assignee: Nice Ltd
• Original Assignee: Nice Systems Limited (Nice Ltd)
• Inventors: Wasserblat, Moshe, Moretzky, Zvika, Ashkenazi, Tzach, Daya, Ezra, Pereg, Oren, Morgenstern, Yaron, Schonhage, Bastiaan, Fraser, Cromwell, Kristjansson, Gudmundur
• Primary Examiner(s): Norman, Samica L
• Application Number:
  US13/408,473
• Time in Patent Office: 433 Days
• Field of Search: 705/1, 705/26.8, 705/35, 705/39, 704/270, 726/2, 707/737
• US Class Current: 705/35
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03

Abstract

A transaction verification system and method may include receiving an interaction record describing communications between parties regarding a transaction event. The interaction record may include interactions having multiple communication formats. Transaction data describing transaction parameters input into a trading system during the transaction even may be compared to the interaction record. A matching score may be calculated that indicates a level of similarity between the interaction record and the transaction data. The matching score may be calculated for multiple of transaction events in an interaction log, and an interaction log score may be calculated.

Claims

1. A method for transaction verification, comprising:

receiving an interaction record describing communications between parties regarding a transaction event;

receiving transaction data describing transaction parameters from the transaction event; and

determining, by a processor, an indicator describing a level of similarity between the interaction record and transaction data.

2. The method of claim 1, wherein the communications between parties are in at least one communication format selected from the group consisting of voice communication, data communication, and in-person communication.

3. The method of claim 1, comprising associating an identification with the interaction record and transaction data.

4. The method of claim 1, comprising converting unstructured speech data from the interaction record into structured speech data, wherein the structured speech data describes words used in an interaction and location of the words in the interaction record.

5. The method of claim 1, comprising:

detecting interaction data within the interaction record, the interaction data comprising transaction parameters described by at least one party in the interaction record;

extracting interaction data from the interaction record; and

comparing the interaction data with the transaction data.

6. The method of claim 5, wherein detecting interaction data within the interaction record comprises:

determining, by a processor, an event confidence score indicating a probability that the interaction data describes the transaction;

comparing the event confidence score to a threshold confidence score; and

detecting interaction data if the event confidence score is greater than or equal to the threshold confidence score.

7. The method of claim 5, wherein determining, by a processor, an indicator describing a level of similarity between the interaction record and transaction data is based on the comparison between the interaction data and the transaction data.

8. The method of claim 5, wherein comparing the interaction data and transaction data comprises comparing respective data fields of the interaction data and the transaction data.

9. The method of claim 1, comprising:

receiving an interaction log comprising a plurality of interaction records describing communications regarding a plurality of transaction events;

receiving a plurality of transaction data describing transaction parameters from the plurality of transaction events;

determining an interaction log score based on indicators describing the similarity between each transaction record and corresponding transaction data.

10. The method of claim 1, comprising generating an alert if the matching score is below a pre-defined threshold matching score.

11. The method of claim 1, comprising displaying, by a processor, the interaction record, the transaction data, and the matching score in one visualization.

13. The transaction verification system of claim 11, wherein the processor is to associate an identification to the interaction record and transaction data.

14. The transaction verification system of claim 11, wherein the processor is to convert unstructured speech data from the interaction record into structured speech data, the structured speech data describing words used in an interaction and location of the words in the interaction record.

15. The transaction verification system of claim 11, wherein the processor is to:

detect interaction data within the interaction record, the interaction data comprising transaction parameters described by at least one party in the interaction record;

extract interaction data from the interaction record; and

compare the interaction data with the transaction data.

16. The transaction verification system of claim 11, wherein the transaction event describes a trading floor transaction.

12. A transaction verification system, comprising:

a memory storing interaction records and corresponding transaction data; and

a processor to;

receive an interaction record describing communications between parties regarding a transaction event, the transaction record in at least one communication format selected from the group consisting of voice communication, data communication, and in-person communication;

receive transaction data describing transaction parameters from the transaction event; and

determine a matching score indicating a level of similarity between the interaction record and transaction data.

17. A method comprising:

receiving a plurality of communications describing a transaction;

determining an indicator describing how accurately the transaction matches the description of the transaction in the plurality of communications.

18. The method of claim 17, wherein the plurality of communications between parties are in communication formats selected from the group consisting of voice communication, data communication, and in-person communication.

19. The method of claim 17, comprising associating an identification with the plurality of communications records and transaction.

20. The method of claim 17, comprising converting unstructured speech data from the plurality of communications into structured speech data, wherein the structured speech data describes words used in communications.