This project aims to construct a knowledge graph system applied to the field of traditional Chinese medicine (TCM) by extracting entities (such as drugs, diseases, etc.) and their relationships from TCM medical case data and storing them in a Neo4j database. The project process includes data reading, entity recognition and extraction, data formatting, and data import into the database. The project not only improved the individual's proficiency in Python data processing techniques (including regular expressions and JSON parsing) but also enhanced their skills in knowledge graph construction and database operations. In the future, there is a desire to further improve technical capabilities, explore more cutting-edge technologies in the TCM field, and promote project progress through collaboration, contributing to the modernization of TCM and intelligent healthcare services.

This paper conducts research on data intelligent generation and analysis based on the ChatGPT model. To explore ChatGPT's performance and limitations in machine translation tasks, the concepts of the Transformer model and previous studies were reviewed to gain a deep understanding of the principles and roles of components such as attention mechanisms, encoders, decoders, and word embeddings. By controlling ChatGPT through code for machine translation and performing manual verification, the model's limitations in handling synonyms, technical terms, and specific domain languages were identified.

This paper aims to design a news recommendation model based on user preferences to address the issues in recommendation systems under large datasets. Initially, four datasets—click_history, news, news_embedding, and user_predict—were integrated into a single table, followed by data cleaning and feature engineering. Due to the large volume of data, this paper proposes necessary data filtering for the training and testing sets, utilizing temporal data to construct user feature vectors and news feature vectors. One challenge is how to effectively integrate user preferences and news features into the model to avoid overfitting or underfitting. In the model design and building phase, different methods were attempted to merge the information of users and news. Ultimately, the user preference features were processed using a fully connected layer, and the news embedding vectors were handled using an LSTM model. These two data parts were then combined into another fully connected layer, using ReLU as the activation function and CELoss as the loss function. Subsequently, the model's hyperparameters were adjusted and evaluated, achieving favorable model performance. The prediction accuracy for recommending news to users in user_predict was calculated as an evaluation criterion. Finally, this paper proposes directions for generalization and optimization in three aspects: data processing, model design, and experimental design. This includes data processing methods, potential improvements or mechanisms that could be incorporated into the model, and hyperparameter tuning. The paper primarily proposes data filtering to solve the problem of excessive data scale, which may aid in addressing recommendation system issues under large-scale datasets.

With the development of agricultural modernization, accelerating agricultural mechanization has become an important direction for the development of agriculture in China. However, agricultural mechanization is uneven and insufficient in terms of regions, industries, crop varieties, and production stages. Although there are already a large number of agricultural machinery products on the market, most of them are designed for large-scale crops in northern arid lands, lacking machinery suitable for barley and adaptable to small plots and sloping farmlands in the Qinghai-Tibet Plateau region. The development of a barley harvester adapted to plateau mountainous areas contributes to the development of special agricultural machinery in China, improves the uneven development of agricultural mechanization, and promotes agricultural development in plateau mountainous areas. This paper conducts research on the actual terrain of the Qinghai-Tibet Plateau, barley planting conditions, and harvester operational conditions. Based on the production needs of barley agriculture, the design is optimized and improved. Following the principle of overall coordination, the overall structural parameters of the harvester suitable for the operational requirements of plateau mountainous areas are determined. The structural design of key components such as wheelbase, axle spacing, ground clearance, harvesting mechanical arm, and harvesting mechanism is detailed. Additionally, SolidWorks software is used for three-dimensional modeling of the barley harvester. CAE technology is employed to analyze the static and dynamic performance of critical chassis components, validate theoretical calculations, and confirm final structural parameters. Furthermore, a dynamics characteristic model is established based on the optimized parameters to theoretically analyze the stability of the entire machine and verify whether the designed plateau barley harvester meets field operation requirements. Finally, Bluetooth communication technology is utilized to autonomously design control hardware and software, achieving intelligent control of the machinery.