news News from Cinnamon AI
- press
Started offering on-premises version of full text AI-OCR “Flax Scanner Zenbuyommon”
Securely convert documents from the manufacturing and construction industries, which have a huge amount of knowledge, into data.
From October 3, 2023, our company will provide an on-premises version of "Flax Scanner Zenbuyommon," an original full-text AI-OCR that can automatically recognize characters from technical document images and convert them into text data with high precision. start. The on-premises version, which can be used without connecting to an external network, has an extremely high security level and can be introduced with confidence by companies with a lot of knowledge, such as manufacturing and construction industries.
[Introduction video] https://www.youtube.com/watch?v=4wQTMhhlJO4
"Flax Scanner Zenbuyommon" can extract and digitize text data from many materials (paper documents and PDF data) such as technical documents such as drawings, blueprints, and specifications, catalogs, and work instructions. It is an AI product that can. By converting a huge amount of knowledge, which is a company's asset, into data that is easy to use, we promote corporate DX, such as improving productivity, sophistication of planning, inheritance of know-how, and labor saving in inventory management.
■ No need to define coordinates. A wide variety of documents can be read with 91%* high accuracy AI-OCR.
"Flax Scanner Zenbuyommon" does not require "coordinate definition (technique to define in advance what is written where)" used in many AI-OCRs, so it can be easily introduced. . It can also read various types of documents, including specifications, reports, inspection records, drawings, experiment/test data, instruction manuals, manuals, specialized magazines, research materials, and contracts, including specialized industry terminology. Is possible. Furthermore, it can read kanji, hiragana, katakana, alphanumeric characters, symbols and units, and achieves high reading accuracy of 91% or higher* for both handwritten and printed characters. *Our test data value.
■Development background
Many companies in the manufacturing and construction industries still store large amounts of paper documents, and they may not be able to access the information they need unless they go to a warehouse or archive to look for it. Another issue is that even if documents are converted into PDF data, they can only be searched by file name, making it difficult to effectively utilize the large amount of stored technical assets.
"Flax Scanner Zenbuyommon" converts all the characters written in a document into text data, making it possible to perform a comprehensive search on the entire text of the document. At the same time, document content can be analyzed using natural language processing and generative AI technology, so digitizing documents can be considered the first step in leveraging knowledge.
Image of knowledge utilization using “Flax Scanner Zenbuyommon”
■ “Flax Scanner Zenbuyommon” on-premise version is recommended for companies with the following needs.
- I want to digitize and utilize highly confidential technical documents.
- I want to build an environment on my own hardware or private cloud and use AI-OCR.
- I want to freely customize performance such as processing limit and processing speed.
◇ Now recruiting free trials ◇
"Flax Scanner Zenbuyommon" offers a free trial.
・Trial version application: https://go.cinnamon.ai/zenbu_yomumon_LP1.html
・Download all materials: https://go.cinnamon.ai/wp_zenbu_yomumon_dl.html
■Provided plans (3 types)
① Monthly usage (on-premises version)NEW!
A plan that is built in the customer's environment and allows the customer to upload/download files themselves.
Regarding costs,Our inquiry form (Click here)Please contact us.
➁ Monthly usage (cloud environment)
A plan that allows customers to upload/download files themselves on the web screen.
[Initial cost] 0 yen
[Monthly cost] Minimum 1,000 pages per month from 50,000 yen (excluding tax)
[LLM Option Powered by Azure OpenAI Service] 10,000 yen per month (excluding tax)
③ Spot use
A plan in which we receive the target image file, perform OCR processing at our company, and then return it all at once.
【Basic charge】
2 million yen (excluding tax) + number of pages processed x 6 yen (excluding tax)
■File formats compatible with “Flax Scanner Zenbuyommon”
【input】6 types of image file formats (PDF / JPG / JPEG / PNG / TIFF / TIF) can be universally imported (full text AI-OCR processing).
【output】Output is possible in 3 types of files depending on the purpose
– Excel(lmage line report)
This is the OCR reading output result of the image file and text. You can check OCR results with images and text.
– Excel(line report)
The OCR reading output result is text only.
– PDF(With transparent text) *The original file can only be output in PDF format.
This is a file with AI-OCR reading results added as transparent text to the original image PDF file.
It is a Searchable PDF that allows full text search.
Output file image of the result of converting to text with "Zenbuyommon"