档案信息进行大数据应用的初步实践

Preliminary Practice of Application of Big Data in Archival Information

随着大数据在各行业应用的广泛深入,取得良好的成果,许多档案行业学者对档案信息在大数据应用方面进行了研究和实践,通过采用人工智能技术对档案信息进行预处理,如利用OpenCV算法对文本档案进行OCR识别,采用ASR技术对音视频档案进行语音识别,采用人工智能技术进行人脸识别等。对获得的数字化档案信息采用隐马尔科夫模型进行结构化,最后形成“一人一档,一事一档”等大数据应用实践。

With the extensive and in-depth application of big data in various industries,good results have been achieved,many scholars in the archives industry have studied and practiced the application of big data in archives information.They preprocess archives information by using artificial intelligence technology,such as OCR recognition of text archives by using OpenCV algorithm,ASR(automatic speech recognition)technology is used for speech recognition of audio and video archives,and artificial intelligence technology is used for face recognition.The obtained digital archives information is structured by hidden Markov model(HMM),and finally forms big data application practices such as“one file for one person,one file for one thing”.