Item shipping screening and validation

• US 10,417,602 B2
• Filed: 04/18/2017
• Issued: 09/17/2019
• Est. Priority Date: 04/18/2017
• Status: Active Grant

• Current Assignee: International Bridge, Inc.
• Original Assignee: International Bridge, Inc.
• Inventors: Farley, John, Warr, John, Laghaeian, Cameron M.
• Primary Examiner(s): Mitchell, Nathan A
• Application Number:
  US15/490,520
• Publication Number:
  US 20180300668A1
• Time in Patent Office: 882 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/083 Shipping

Abstract

A method and system for vetting items being shipped across national boundaries using a new technology enabling an automated system is provided. In particular, the automated system screens items for shipping through customs and validating the items for shipment according to customs rules and regulations. The system identifies and applies the appropriate rules for customs and other responsible agencies pertaining to the eligibility of any item being imported into a particular country. The present invention utilizes an unconventional combination of image recognition technology, machine learning algorithms, and rule engine algorithms to categorize, identify, and apply the appropriate rules to each and every item being considered for importation to another country. Based on the specific combination of technological processes and systems, the present invention is configured to accept, reject, or submit products for further review in a consistent, predictable, and accurate manner, not previously achievable in prior systems and methods.

Claims

1. An automated machine-implemented method of customs approval, the method comprising:

receiving, using a data gathering and staging system and a processor, item data comprising a combination of description, meta-tags, and one or more images for each of one or more items;

scanning, using an image recognition system comprising an image recognition tool, the one or more images for each of the one or more items and capturing embedded data within the one or more images or the one or more items using the image recognition tool;

creating a list of identity markers for the item data based on the scanning of the one or more images for each of the one or more items, the embedded data captures by the image recognition tool, and the combination of description, meta-tags, and images included within the item data;

applying, using an algorithm module and the processor, a probability formula utilizing the list of identity markers to determine one or more categories matching one or more predefined categories for the one or more items based on key words and phrases located within the list of identity markers;

applying, using the rules engine and the processor, specific rules of shippability, based on the one or more predefined categories, to the item data of the one or more items;

classifying the one or more items associated with the item data as shippable or not shippable based on application of the specific rules of shippability to the one or more items; and

wherein the classifying further comprises transmitting, when one or more items are marked as one or more questionable items, item data associated with the one or more questionable items to a reviewer to determine shippability of the one or more questionable items.

2. The method of claim 1, wherein the item data is provided by a manufacturer, seller, logistics company, or reseller of the one or more items.

3. The method of claim 1, wherein the item data is obtained from a catalog or online information including the one or more items provided by a seller of the one or more items.

4. The method of claim 1, wherein description includes information related to at least one of physical attributes, functionality, and source material of the one or more items.

5. The method of claim 1, wherein the specific rules of shippability are derived from rules established by governmental or regulatory authorities within a particular destination country and applied to items based on information provided by a manufacturer, seller, logistics company, or reseller of the one or more items.

6. The method of claim 1, wherein the one or more items are marked as one or more questionable items if there is insufficient and/or contradicting information about the one or more items.

7. The method of claim 1, further comprising a reviewer updating the specific rules of shippability to include new rules or modified existing rules.

8. The method of claim 1, wherein the specific rules of shippability correspond to rules and regulations of a destination country, comprising one or more selected from the group consisting of:

regulations of a customs and regulations agency, rules governing intellectual property (IP), regulations prohibiting products, internal set rules of any other party, or a combination thereof.

9. The method of claim 1, wherein the one or more predefined categories are determined by the algorithm module comprising a linear classifier algorithm.

10. The method of claim 9, wherein the linear classifier algorithm determines whether the one or more items have been previously categorized.

11. The method of claim 9, wherein the applying the probability formula further comprises:

calculating a confidence factor and a threshold level for the confidence factor for each of the one or more categories for each of the one or more items

selecting the one or more categories with a highest confidence factor for each of the one or more items; and

wherein the classifying further comprises when the threshold level for the confidence factor is not achieved for a particular item, the particular item is classified as a questionable item and forwarded to a reviewer to determine the one or more categories.

12. The method of claim 11, further comprising training the algorithm module comprising machine algorithms with feedback, item data and input from a reviewer, wherein a decision of the reviewer is factored into the probability formula and resulting confidence factor next time an item with similar characteristics is encountered by the probability formula, causing the one or more items to be categorized with a higher confidence.

13. An automated machine-implemented system for customs approval, the system comprising:

a processor and a data gathering and staging system configured to receive item data that comprises a combination of description, meta-tags, and one or more images for each of one or more items;

an image recognition system comprising an image recognition tool configured to scan the one or more images for the one or more items and capture embedded data within the one or more images or the one or more items, wherein the image recognition system is configured to create a list of identity markers for the item data based on scanning of the one or more items, the embedded data captured by the image recognition tool, and the combination of description, meta-tags, and the one or more images included within the item data;

an algorithm module configured to apply, using the processor, a probability formula utilizing the list of identity markers to determine one or more categories matching one or more predefined categories for the one or more items based on key words and phrases located within the list of identity markers;

a rules engine configured to apply, using the processor, specific rules of shippability, based on the one or more predefined categories, to the item data of the one or more items, wherein the rules engine is configured to classify the one or more items associated with the item data as shippable, or not shippable, based on application of the specific rule of shippability used with the one or more categories of the one or more items; and

wherein the system is further configured to transmit, when one or more items are marked as questionable items, item data associated with the one or more questionable items to a reviewer to determine one or more categories, and shippability of the one or more questionable items.

14. The system of claim 13, wherein the item data is provided by a manufacturer, seller, logistics company, or reseller of the one or more items.

15. The system of claim 13, wherein the item data is obtained from a catalog including the one or more items provided by a seller of the one or more items.

16. The system of claim 13, wherein description includes information related to at least one of physical attributes, functionality, and source material of the one or more items.

17. The system of claim 13, wherein the specific rules of shippability are derived from rules established by governmental or regulatory authorities within a particular destination country and applied to items based on information provided by a manufacturer, seller, logistics company, or reseller of the one or more items.

18. The system of claim 13, wherein the system is further configured to mark the one or more items as one or more questionable items if there is insufficient and/or contradicting information about the one or more items.

19. The system of claim 13, wherein the system is further configured to allow a reviewer to update the specific rules of shippability to include new rules or modified existing rules.

20. The system of claim 13, wherein the specific rules of shippability correspond to rules and regulations of a destination country comprising one or more selected from the group consisting of:

regulations of a customs and regulations agency, rules governing intellectual property (IP), regulations prohibiting products, internal set rules of any other party, or a combination thereof.

21. The system of claim 13, wherein the algorithm module is configured to determine the one or more categories using a machine learning algorithm.

22. The system of claim 21, wherein the machine learning algorithm is configured to determine whether the one or more items have been previously categorized.

23. The system of claim 21, wherein the algorithm module is further configured to apply the probability formula by:

calculating a confidence factor and a threshold level for the confidence factor for each of the one or more categories for each of the one or more items;

selecting the one or more classes and the one or more categories with a highest confidence factor for each of the one or more items; and

when the threshold level for the confidence factor is not achieved for a particular item, the rules engine is further configured to ensure the particular item is classified as a questionable item and forwarded to a reviewer to determine the one or more categories.

24. The system of claim 23, wherein the algorithm module further comprises machine learning algorithms configured to be trained with feedback, item data and input from a reviewer, wherein a decision of the reviewer is factored into the probability formula and resulting confidence factor next time an item with similar characteristics is encountered by the probability formula, causing the one or more items to be categorized with a higher confidence.