# US 8,751,419 B2 · Shipping system and method with taxonomic tariff harmonization > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,751,419 B2 - Document ID: US8751419B2 - Status: Granted - Kind: B2 - Application number: 13/277,141 - Filed: 2011-10-19 - Published: 2012-05-24 - Granted: 2014-06-10 - Earliest claimed: 2010-11-19 - Assignees: Shipjo, LLC - Applicants: Kotaro Shimogori - Inventors: Kotaro Shimogori - Web page: https://patentgrep.com/patent/US8751419B2 ## CPC - G06N 20/00: Machine learning - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A system, method and computer-readable medium for providing a harmonized classification code for a good based on input including a database adapted to store content including a harmonized tariff classification code module for storing a data structure representing a harmonized classification code tree, the harmonized classification code tree having one or more harmonized classification codes in which the good can be classified, a keywords module for associating and storing keyword data related to the good with one of the harmonized classification codes; and a learning module for learning keywords from the input and associating the learned key words with the one harmonized classification code for the good. ## Claims ### Claim 1 A system for delivering a harmonized classification code for a good based on input, comprising: a database adapted to store content including a harmonized tariff classification code module for storing a data structure representing a harmonized classification code tree, the harmonized classification code tree having one or more harmonized classification codes in which the good can be classified; a keywords module for associating and storing keyword data related to the good with one of the harmonized classification codes; and a learning module for learning keywords from the input, for determining a keyword group and a keyword group count from the learned keywords, and associating the learned key words and keyword group count with the one harmonized classification code for the good. ### Claim 2 (depends on 1) The system of claim 1 including a processor configured to receive a query over an application programming interface requesting the harmonized classification code for the good based on the input, the processor accessing the database to retrieve a corresponding group of harmonized classification codes associated with the good. ### Claim 3 (depends on 2) The system of claim 2 including an application programming interface displaying the group of harmonized classification codes retrieved by the processor, selecting one harmonized classification code from the group of harmonized classification codes and selecting the input and the processor determining a count of keywords from the input. ### Claim 4 (depends on 3) The system of claim 3 wherein the processor increments the keyword group count, and the application programming interface comparing the incremented keyword group count from the input to a predetermined keyword count. ### Claim 5 (depends on 4) The system of claim 4 wherein the processor updates the determined keyword count and appending the selected input to the keyword group if the determined keyword count from the input is greater than or equal to the predetermined keyword count. ### Claim 6 (depends on 1) The system of claim 1 wherein the learning module includes a module of words the learning module will ignore when learning keywords from the input. ### Claim 7 A method for providing a harmonized classification code for a good based on input comprising: storing content including a harmonized tariff classification code module for storing a data structure representing a harmonized classification code tree in a database, the harmonized classification code tree having one or more harmonized classification codes in which the good can be classified, associating and storing keyword data related to the good with one of the harmonized classification codes in a keywords module; and learning keywords from input, for determining a keyword group and a keyword group count from the learned keywords, and associating the learned key words and keyword group count with the one harmonized classification code for the good. ### Claim 8 (depends on 7) The method of claim 7 including receiving a query over an application programming interface requesting the harmonized classification code for the good based on the input, and accessing the database to retrieve a corresponding group of harmonized classification codes associated with the good. ### Claim 9 (depends on 8) The method of claim 8 including displaying the group of harmonized classification codes retrieved, selecting one harmonized classification code from the retrieved group of harmonized classification codes, and selecting the input and determining a count of keywords from the input. ### Claim 10 (depends on 9) The method of claim 9 including the step of incrementing the keyword group count, and comparing the incremented keyword group count from the input to a predetermined keyword count. ### Claim 11 (depends on 10) The method of claim 10 including updating the determined keyword count and appending the selected input to the keyword group if the determined keyword count from the input is greater than or equal to the predetermined keyword count. ### Claim 12 (depends on 7) The method of claim 7 wherein learning keywords from the input includes learning words to ignore. ### Claim 13 A non-transitory computer-readable medium having programming instructions stored thereon for providing a harmonized classification code for a good based on input including: storing content including a harmonized tariff classification code module for storing a data structure representing a harmonized classification code tree in a database, the harmonized classification code tree having one or more harmonized classification codes in which the good can be classified, associating and storing keyword data related to the good with one of the harmonized classification codes in a keywords module; and learning keywords from input, for determining a keyword group and a keyword group count from the learned keywords, and associating the learned key words and keyword group count with the one harmonized classification code for the good. ### Claim 14 (depends on 13) The non-transitory computer-readable medium of claim 13 including receiving a query over an application programming interface requesting the harmonized classification code for the good based on the input, and accessing the database to retrieve a corresponding group of harmonized classification codes associated with the good. ### Claim 15 (depends on 14) The non-transitory computer-readable medium of claim 14 including displaying the group of harmonized classification codes retrieved, selecting one harmonized classification code from the retrieved group of harmonized classification codes and selecting the input and determining a count of keywords from the input. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15 including the step of incrementing the keyword group count, and comparing the incremented keyword group count from the input to a predetermined keyword count. ### Claim 17 (depends on 16) The non-transitory computer-readable medium of claim 16 including updating the determined keyword count and appending the selected input to the keyword group if the determined keyword count from the input is greater than or equal to the predetermined keyword count. ### Claim 18 (depends on 13) The non-transitory computer-readable medium of claim 13 wherein learning keywords from the input includes learning words to ignore.