Research And Application Of Information Extraction And Analysis Of Archaeological Excavations

With the development of archeological excavations and digital archeology,more and more relics have been excavated.These are the marks left by the ancient Chinese culture and are of great significance for the study of the development of ancient Chinese society and culture.To deal with repetitive text data,it takes a lot of manual work for archeologists.Natural language processing technology,as an important branch of artificial intelligence,can solve this problem.Data mining technology can be used to find hidden rules in large amounts of data and can be used in improving the efficiency of archaeologists' research,or finding new directions for archeologists.Based on the data of Liangzhu site,this paper conducts technical research on the two aspects of data preprocessing in archeology and settlement level analysis of archeological sites.In archaeological data preprocessing,the effect of the traditional maximal matching method and the word segmentation method based on the hidden Markov model is compared in the archeological data.Then,the effect of segmentation improves after archeological data added to the user dictionary.Based on the result of the segmentation,this paper did the work of extracting the attribute information about the cultural relics from the large section of text into the relational database,and compared the two methods of pattern matching and entity recognition.After the optimization,the experimental results show Entity recognition technology can extract more archaeological information.In the archeological data analysis,C4.5 decision tree algorithm and multi-classification SVM model were respectively used to classify the settlement level of archaeological sites.The current method of artificial judgment is based on the experience of archaeologists and can not simply be expressed in the form of rules.Through the method of data statistics and analysis,this paper combines the settlement level with the predicted population and the grade of utensils,and achieves a better classification and forecasting effect.Experimental results show that using multi-classification SVM model can achieve better classification results.At last,this article introduces the design and implementation of archeology data management system,which is a system to achieve the collection,integration,management,statistics,analysis and other functions of archaeological data.The data integration module integrates the archeology data preprocessing technology,and the analysis module realizes the classification prediction of the settlement level.