Amazon Web Services 亚马逊云科技
AIF-C01 AIF-C01 系列
AIF-CO1 AWS Certified Al Practitioner Exam(Al1-CO1)
AIF-CO1 AWS 认证人工智能从业者考试 （Al1-CO1）
Question #:1 问题 #：1
A company has built a solution by using generative AI. The solution uses large language models (LLMs) to translate training manuals from English into other languages. The company wants to evaluate the accuracy of the solution by examining the text generated for the manuals.
一家公司使用生成式 AI 构建了解决方案。该解决方案使用大型语言模型 （）LLMs 将培训手册从英语翻译成其他语言。该公司希望通过检查为手册生成的文本来评估解决方案的准确性。
Which model evaluation strategy meets these requirements?
哪种模型评估策略满足这些要求？
A. Bilingual Evaluation Understudy (BLEU)
A. 双语评估替补 （BLEU）
B. Root mean squared error (RMSE)
B. 均方根误差 （RMSE）
C. Recall-Oriented Understudy for Gisting Evaluation (ROUGE)
C. 用于 Gisting 评估的以回忆为导向的替补 （ROUGE）
D. F1 score D. F1 分数
Answer: A 答案：A
Explanation 解释
BLEU (Bilingual Evaluation Understudy) is a metric used to evaluate the accuracy of machine-generated translations by comparing them against reference translations. It is commonly used for translation tasks to measure how close the generated output is to professional human translations.
BLEU（双语评估替补）是一种指标，用于通过将机器生成的翻译与参考翻译进行比较来评估机器生成的翻译的准确性。它通常用于翻译任务，以衡量生成的输出与专业人工翻译的接近程度。
- Option A (Correct): “Bilingual Evaluation Understudy (BLEU)”:This is the correct answer because BLEU is specifically designed to evaluate the quality of translations, making it suitable for the company’s use case.
选项 A（正确）：“双语评估替补 （BLEU）”：这是正确答案，因为 BLEU 专为评估翻译质量而设计，使其适合公司的用例。
- Option B:“Root mean squared error (RMSE)” is incorrect because RMSE is used for regression tasks to measure prediction errors, not translation quality.
选项 B：“均方根误差 （RMSE）”不正确，因为 RMSE 用于回归任务来衡量预测误差，而不是翻译质量。
- Option C:“Recall-Oriented Understudy for Gisting Evaluation (ROUGE)” is incorrect as it is used to evaluate text summarization, not translation.
选项 C：“Recall-Oriented Understudy for Gisting Evaluation （ROUGE）”是不正确的，因为它用于评估文本摘要，而不是翻译。
- Option D:“F1 score” is incorrect because it is typically used for classification tasks, not for evaluating translation accuracy.
选项 D：“F1 分数”不正确，因为它通常用于分类任务，而不是用于评估翻译准确性。
AWS AI Practitioner References:
AWS AI 从业者参考资料：
Model Evaluation Metrics on AWS:AWS supports various metrics like BLEU for specific use cases, such as evaluating machine translation models.
AWS 上的模型评估指标：AWS 支持针对特定使用案例（例如评估机器翻译模型）的各种指标（如 BLEU）。
Question #:2 问题 #：2
A company manually reviews all submitted resumes in PDF format. As the company grows, the company expects the volume of resumes to exceed the company’s review capacity. The company needs an automated system to convert the PDF resumes into plain text format for additional processing.
公司手动审核所有提交的 PDF 格式简历。随着公司的发展，该公司预计简历的数量将超过公司的审核能力。该公司需要一个自动化系统将 PDF 简历转换为纯文本格式以进行额外处理。
Which AWS service meets this requirement?
哪些 AWS 服务满足此要求？
A. Amazon Textract A. 亚马逊 Textract
B. Amazon Personalize
C. Amazon Lex
D. Amazon Transcribe D. 亚马逊转录
Answer: A 答案：A
Explanation 解释
Amazon Textract is a service that automatically extracts text and data from scanned documents, including PDFs. It is the best choice for converting resumes from PDF format to plain text for further processing.
Amazon Textract 是一项自动从扫描的文档（包括 PDF）中提取文本和数据的服务。它是将简历从 PDF 格式转换为纯文本以进行进一步处理的最佳选择。
- Amazon Textract: 亚马逊 Textract：
- Extracts text, forms, and tables from scanned documents accurately.
从扫描的文档中准确提取文本、表单和表格。
- Ideal for automating the process of converting PDF resumes into plain text format.
非常适合自动化将 PDF 简历转换为纯文本格式的过程。
- Why Option A is Correct:
为什么选项 A 是正确的：
- Automation of Text Extraction:Textract is designed to handle large volumes of documents and convert them into machine-readable text, perfect for the company’s need.
文本提取自动化：Textract 旨在处理大量文档并将其转换为机器可读的文本，非常适合公司的需求。
- Scalability and Efficiency:Supports scalability to handle a growing volume of resumes as the company expands.
可扩展性和效率：支持可扩展性，以处理随着公司扩张而不断增长的简历量。
Why Other Options are Incorrect:
为什么其他选项不正确：
- B. Amazon Personalize:Used for creating personalized recommendations, not for text extraction.
B. Amazon Personalize：用于创建个性化推荐，而不是用于文本提取。
C. Amazon Lex:A service for building conversational interfaces, not for processing documents.
C. Amazon Lex：用于构建对话界面的服务，而不是用于处理文档的服务。
- D. Amazon Transcribe:Used for converting speech to text, not for extracting text from documents.
D. Amazon Transcribe：用于将语音转换为文本，而不是用于从文档中提取文本。
Question #:3 问题 #：3
A company wants to use language models to create an application for inference on edge devices. The inference must have the lowest latency possible.
一家公司希望使用语言模型创建用于边缘设备推理的应用程序。推理必须具有尽可能低的延迟。
Which solution will meet these requirements?
哪种解决方案将满足这些要求？
A. Deploy optimized small language models (SLMs) on edge devices.
A. 在边缘设备上部署优化的小语言模型 （SLM）。
B. Deploy optimized large language models (LLMs) on edge devices.
B. 在边缘设备上部署优化的大型语言模型 （LLMs）。