R&D - Chinese characters full-text format search database.
►Developed a Chinese characters full-text search database with customized full-text search database and index creation based on the inverted index, resulting in higher efficiency of exact search of Chinese characters than the current database software (SQL Like).
►Implemented the search algorithm, indexing, and sorting functions using NLP techniques such as HMM, SVM, TF-IDF, and inverted index.
►Designed and implemented non-dictionary-based, word segmentation, word vector, and article categorization by SVM to improve the accuracy of search results.
►Optimized the search engine's performance, reducing the search time by 90% and improving the scalability of the system.
Skills: Full-text search database, inverted index, NLP, HMM, SVM, TF-IDF, non-dictionary-based search