Important item reading accuracy 92%* / Automatically reads 50 items regardless of format

Our original high-precision AI-OCR "Flax Scanner" has 50 items for Bill of Lading (B/L), a trade document that is widely used around the world but has different formats for each country and company. "Flax Scanner for Trade Document Bill of Lading General-purpose Model", which automatically recognizes and extracts text data, will be on sale from February 26, 2024.

Bill of Lading = Bill of Lading. A type of trade document that certifies a transportation contract.

"Flax Scanner for Trade Documents Bill of Lading General-purpose Model" allows AI to automatically read 50 items (*see attached document) organized by frequency of use, priority, etc. from the items listed on the form. . Additionally, 16 of the most important items can be read with high accuracy, with an average character accuracy of 92.49%* and an average item accuracy of 89.42%*.

It can be implemented by a wide range of companies that handle trade documents, such as exporters/importers (manufacturers/trading companies, etc.), shipping companies, airlines, forwarders, insurance companies (non-life insurance), banks, etc., and the system can be easily used using the UI. In addition to providing only the API, we can also provide customization proposals such as detailed tuning settings.

Cinnamon AI will continue to promote DX in the trading industry by developing versatile and highly accurate AI-OCR models that can be quickly introduced without the cost and time required to build a dedicated model. Masu.

*All values are based on our test data.

■Development background

One of the trade operations in Japan involves checking and inputting necessary items from trade-related forms (trade documents). The format of the forms differs depending on the country and company, so experience and skills are required to confirm the necessary information, and the time-consuming input process is an issue. Additionally, because it is costly to tune each form and develop a dedicated AI-OCR model, there were a limited number of companies that could introduce it.

To address this issue, Cinnamon AI has so far developed a dedicated AI-OCR system that specializes in forms in the trade industry.Flax Scanner for trade documents”, “Flax Scanner for trade documents Commercial Invoice general purpose model”, and the “Join the trade consortiumWe have focused on promoting DX by introducing AI in the trading industry, and have built up a track record of implementation and know-how.

In order to help more companies introduce AI-OCR, we have started selling the "Bill of Lading general-purpose model" following the "Commercial Invoice general-purpose model". In the future, Cinnamon AI aims to expand the development and introduction of general-purpose AI-OCR for each form, such as Packing List and Arrival Notice, which are in demand following Commercial Invoice and Bill of Lading.

*The "Commercial Invoice general-purpose model" announced on August 9, 2023 has been updated, and the 24 items with higher importance have an average accuracy of 94.42% per character (previous average 92.49%), and an average accuracy of 91.00% per item (Previous average 89.42%) The reading accuracy has improved.

■Main target companies

Exporters/importers (manufacturers/trading companies, etc.), shipping companies, airlines, forwarders, insurance companies (non-life insurance), banks

■High-precision general-purpose AI-OCR that supports various formats realized with advanced AI technology

"Flax Scanner for Trade Document Bill of Lading General-purpose Model" is an AI solution that minimizes the man-hours and costs required for practical AI-OCR implementation for any company that handles trade documents. Most AI-OCR is developed using a "coordinate definition type" that predefines where and what to write from a formatted document, but in global trade transactions, there are countless formats. Therefore, it is virtually impossible to handle this using the "coordinate definition type". The development of AI-OCR that can read a wide variety of forms and documents requires an advanced technology called a "feature learning type" that does not require the coordinates of extraction items to be defined in advance. The "For Trade Documents Bill of Lading general-purpose model" was developed using this "feature learning type."

"Feature learning type" AI-OCR allows AI to learn from a huge amount of data, finds features (patterns and consistency), and allows the AI to identify what kind of data the target data is. It is possible. Additionally, because it does not require coordinates to be defined in advance, it is the perfect technology for reading trade documents that come in a myriad of formats.

Cinnamon AI has advanced AI technology that allows AI to understand meaning and read data from a wide range of formats like a human, and these are collectively referred to as IDP (intelligent document processing = automatic knowledge extraction technology). Excellent in the technical field called for. IDP is a very important technology that is the basis for realizing hyper-automation in enterprises.

<Reference materials>

 "Flax Scanner for Trade Documents Bill of Lading General-purpose Model"

◇50 items to read
Based on interviews with a wide range of companies that handle trade documents, such as exporters/importers (manufacturers/trading companies, etc.), shipping companies, airlines, forwarders, insurance companies (non-life insurance), banks, etc., we have developed the following 50 items as a general-purpose Bill of Lading model. has been decided as the item to be read.
(Highly important items are *)
Items marked with (details) are read in table format.

◇Reading accuracy (test data value by Cinnamon AI)
Important item accuracy ●Character unit accuracy: Average 92.49% / ●Item accuracy: Average 89.42%
All item accuracy ●Character unit accuracy: average 91.30% / ●item accuracy: average 87.45%

No.	Reading item name
1	Shipper/Exporter Name*
2	Shipper/Exporter Address
3	Shipper/Exporter Phone No.
4	Consignee Name
5	Consignee Address
6	Consignee Phone No.
7	Consignee Personal Contact Details
8	Notify Party Name
9	Notify Party Address
10	Notify Party Phone No.
11	Booking No.
12	Export References
13	Bill of Lading No. /Waybill No. *
14	Shipping Company*
15	Forwarding Agent-References FMC No. *
16	Pre-Carriage by
17	Place of Receipt/Place of Acceptance
18	Ocean Vessel*
19	Voyage No. *
20	Port of Loading*
21	Port of Discharge /To*
22	Final Place of Delivery*
23	Final Destination
24	Type of Movement/Type of Service
25	Marks & Nos.
26	Container No. (Details)*
27	Seal No. (details)
28	Type/Kind of Containers
29	Type/Kind of Packages/Units/Blocks (details)
30	Number of Packages/Units/Blocks (details)
31	Description of Goods/Item Description*
32	Gross Weight/Weight KGM (details)*
33	Gross Measurement/Measurement M3 (details)*
34	Total Gross Weight*
35	Total Gross Measurement*
36	Total Number of Containers or Packages
37	Responsibility for the Freight
38	Rate (details)
39	Currency (details)
40	Prepaid (details)
41	Collect (details)
42	Exchange Rate
43	Freight and Charges Payable at
44	Prepaid at
45	Place of Date
46	Place of Issue
47	Number of Original B(s)/L
48	Date Cargo Received
49	Date Laden on Board the Vessel*
50	SIGNED BY: