本研究引入了一种基于人工智能的餐厅餐饮系统,该系统允许非接触式通信、定制膳食建议和满意度预测。通过将 NLP 与 LDA、Conv-RNN 和 Conv-LSTM 结合使用,它超越了基于规则的技术,具有更高的准确性、精确度、召回率并降低错误率,展示了人工智能在食品服务行业的革命性潜力。
Access restricted. Please log in or start a trial to view this content.
Access restricted. Please log in or start a trial to view this content.
Access restricted. Please log in or start a trial to view this content.
Access restricted. Please log in or start a trial to view this content.
Access restricted. Please log in or start a trial to view this content.
| Name | Company | Catalog Number | Comments |
|---|---|---|---|
| 程序设计语言 | Python(用于模型开发、自然语言处理和深度学习) | https://www.python.org/ | Python 3.8+ |
| 数据库 | MySQL 或 SQLite(用于存储用户交互日志) | https://www.mysql.com/;https://www.sqlite.org/ | MySQL 8.0 或 SQLite3 |
| 数据 | 用户查询来自本地餐厅点餐聊天机器人 | 手动注释 | |
| 深度学习框架 | 张量流 / Keras | https://www.tensorflow.org/;Keras 2.11 & rarr;https://keras.io/ | TensorFlow 2.11 或 Keras 2.11 |
| 开发环境 | Jupyter Notebook / Google Colab | https://jupyter.org/;https://colab.research.google.com/ | JupyterLab 3+ / Colab(免费) |
| 评估指标 | scikit-learn指标:精度、回忆、交叉熵、R&UP2; | https://scikit-learn.org/ | SCICKIT-Learn 1.0+ |
| 自然语言工具包 | spaCy / NLTK(用于意图检测预处理) | https://spacy.io/;https://www.nltk.org/ | spaCy 3.0 / NLTK 3.6 |
| 循环神经网络模型 | RNN,LSTM,Conv-LSTM | https://keras.io/ | 在 Keras 中实现 |
| 系统硬件 | Intel Core i7,16GB 内存,NVIDIA GTX 1660 Ti GPU | 本地系统 | |
| 主题建模工具 | Gensim(用于潜在狄利克雷分配) | https://radimrehurek.com/gensim/ | Gensim 4.1.2 |
| 可视化工具 | Matplotlib,Seaborn(用于性能图绘制) | https://seaborn.pydata.org/;https://matplotlib.org/ | Matplotlib 3.5+,Seaborn 0.11 |
| 词嵌入 | Word2Vec / GloVe 预训练嵌入 | https://nlp.stanford.edu/projects/glove/ | GloVe(100D),斯坦福NLP |
Access restricted. Please log in or start a trial to view this content.
Request permission to reuse the text or figures of this JoVE article
Request Permission