AI-102 Question #111: Real Exam Question with Answer & Explanation

Question

Case Study 2 - Contoso, Ltd. General Overview Contoso, Ltd. is an international accounting company that has offices in France. Portugal, and the United Kingdom. Contoso has a professional services department that contains the roles shown in the following table. Infrastructure Contoso has the following subscriptions: - Azure - Microsoft 365 - Microsoft Dynamics 365 Azure Active (Azure AD) Directory Contoso has Azure Active Directory groups for securing role-based access. The company uses the following group naming conventions: - ICountryJ-[Levell-[Role] - [Level]-[Role] Intellectual Property Contoso has the intellectual property shown in the following table. Text-based content is provided only in one language and is not translated. Planned Projects Contoso plans to develop the following: - A document processing workflow to extract information automatically from PDFs and images of financial documents - A customer-support chatbot that will answer questions by using FAQs - A searchable knowledgebase of all the intellectual property Technical Requirements Contoso identifies the following technical requirements: - All content must be approved before being published. - All planned projects must support English, French, and Portuguese. - All content must be secured by using role-based access control (RBAC). - RBAC role assignments must use the principle of least privilege. - RBAC roles must be assigned only to Azure Active Directory groups. - Al solution responses must have a confidence score that is equal to or greater than 70 percent. - When the response confidence score of an Al response is lower than 70 percent, the response must be improved by human input. Chatbot Requirements Contoso identifies the following requirements for the chatbot: - Provide customers with answers to the FAQs. - Ensure that the customers can chat to a customer service agent. - Ensure that the members of a group named Management-Accountants can approve the FAQs. - Ensure that the members of a group named Consultant-Accountants can create and amend the FAQs. - Ensure that the members of a group named the Agent-CustomerServices can browse the FAQs. - Ensure that access to the customer service agents is managed by using Omnichannel for Customer Service. - When the response confidence score is low. - Ensure that the chatbot can provide other response options to the customers. Document Processing Requirements Contoso identifies the following requirements for document processing: - The document processing solution must be able to process standardized financial documents that have the following characteristics: - Contain fewer than 20 pages. - Be formatted as PDF or JPEG files. - Have a distinct standard for each office. - The document processing solution must be able to extract tables and text from the financial documents. - The document processing solution must be able to extract information from receipt images. - Members of a group named Management-Bookkeeper must define how to extract tables from the financial documents. - Members of a group named Consultant-Bookkeeper must be able to process the financial documents. Knowledgebase Requirements Contoso identifies the following requirements for the knowledgebase: - Supports searches for equivalent terms - Can transcribe jargon with high accuracy - Can search content in different formats, including video - Provides relevant links to external resources for further research You are developing the knowledgebase. You use Azure Video Analyzer for Media (previously Video indexer) to obtain transcripts of webinars. You need to ensure that the solution meets the knowledgebase requirements. What should you do?

Options

• ACreate a custom language model
• BConfigure audio indexing for videos only
• CEnable multi-language detection for videos
• DBuild a custom Person model for webinar presenters

Explanation

--- Can transcribe jargon with high accuracy Video Indexer (VI), the AI service for Azure Media Services enables the customization of language models by allowing customers to upload examples of sentences or words belonging to the vocabulary of their specific use case. Since speech recognition can sometimes be tricky, VI enables you to train and adapt the models for your specific domain. Harnessing this capability allows organizations to improve the accuracy of the Video Indexer generated transcriptions in https://azure.microsoft.com/en-us/blog/new-ways-to-train-custom-language-models-effortlessly/

No community discussion yet for this question.