Network Security Internet Technology Development Database Servers Mobile Phone Android Software Apple Software Computer Software News IT Information

In addition to Weibo, there is also WeChat

Please pay attention

WeChat public account

Shulou

The digital platform "Mingdian Ancient Books", which is open for free and developed in cooperation with Peking University, has been launched.

2025-04-03 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >

Share

Shulou(Shulou.com)11/24 Report--

CTOnews.com, October 12 (Xinhua)-- according to Byte Jing, a digital platform for ancient books developed in cooperation with Peking University, "Mingdian Ancient Books" has been launched. At present, the platform has launched 390 classical ancient books, totaling more than 30 million words, which are free to the public. In the next three years, "Mingdian Ancient Books" will gradually complete the intelligent arrangement of 10,000 kinds of ancient books, basically covering the core bibliography of Confucianism, Taoism and Buddhism.

The home page of the website of the trial edition of "Mingdian Ancient Books", https://www.shidianguji.com/

According to incomplete statistics, there are about 200000 kinds of ancient books in China, of which 80,000 have completed digital image scanning, while only 30,000-40,000 have realized text digitization.

In order to facilitate the retrieval and reading of ancient books in the Library, the platform of "Mingdian Ancient Books" mainly adopts three artificial intelligence technologies:

First, character recognition, that is, using OCR (Optical character recognition) technology to recognize the photocopied images of ancient books into characters. At present, the average recognition accuracy of OCR in the industry is 93% to 94%, while Mingdian Ancient Books increases this figure to 96% to 97%.

Second, automatic punctuation, which refers to the automatic punctuation of ancient books that originally lack broken sentences by algorithm. For example, at the beginning of the Analects of Confucius, it is not said to learn while learning, and the result after automatic punctuation is "learning and learning, isn't it?"

Third, named entity recognition, that is, the identification of "proper nouns" in ancient books, including person names, place names, books, time, and official positions.

Byte beat said that compared with the same type of platform, the visit of "Mingdian Ancient Books" is relatively stable and fast. The functions of complex and simplified Chinese conversion and subject word retrieval make it easy to obtain the content efficiently. The platform also provides photocopies from authoritative sources, which are compared with the content of digital text. In addition, for more than a year, byte beat has funded the National Library to directed the restoration of 104 precious ancient books, and more than 50 volumes have been completed, including a number of rare style mine files.

CTOnews.com learned that in the future, Mingdian Ancient Books will also automatically collate and proofread, and open this ability free of charge to promote the digitization of the stock of ancient books. The platform will also open up the research ability of reading and retrieval of ancient books to the whole society, at the same time, scholars with documents will be encouraged to upload documents on their own, and users can also participate in re-creation and re-interpretation.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.

Views: 0

*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.

Share To

IT Information

Wechat

© 2024 shulou.com SLNews company. All rights reserved.

12
Report