Azure Cognitive Services: QnA Maker
Author: Ronald Fung
Creation Date: 31 May 2023
Next Modified Date: 31 May 2024
A. Introduction
QnA Maker is a cloud-based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custom knowledge base (KB) of information.
QnA Maker is commonly used to build conversational client applications, which include social media applications, chat bots, and speech-enabled desktop applications.
QnA Maker doesn’t store customer data. All customer data (question answers and chat logs) is stored in the region the customer deploys the dependent service instances in. For more details on dependent services see here.
This documentation contains the following article types:
The quickstarts are step-by-step instructions that let you make calls to the service and get results in a short period of time.
The how-to guides contain instructions for using the service in more specific or customized ways.
The conceptual articles provide in-depth explanations of the service’s functionality and features.
Tutorials are longer guides that show you how to use the service as a component in broader business solutions.
When to use QnA Maker
When you have static information - Use QnA Maker when you have static information in your knowledge base of answers. This knowledge base is custom to your needs, which you’ve built with documents such as PDFs and URLs.
When you want to provide the same answer to a request, question, or command - when different users submit the same question, the same answer is returned.
When you want to filter static information based on meta-information - add metadata tags to provide additional filtering options relevant to your client application’s users and the information. Common metadata information includes chit-chat, content type or format, content purpose, and content freshness.
When you want to manage a bot conversation that includes static information - your knowledge base takes a user’s conversational text or command and answers it. If the answer is part of a pre-determined conversation flow, represented in your knowledge base with multi-turn context, the bot can easily provide this flow.
B. How is it used at Seagen
As a biopharma research company that uses Microsoft Azure, you can use Azure Cognitive Services: QnA Maker to build a question and answer system that can answer common questions from your customers or patients. Here are some ways you can use Azure Cognitive Services: QnA Maker:
Drug information: You can use Azure Cognitive Services: QnA Maker to build a system that can answer common questions about drugs, such as dosages, side effects, and interactions.
Clinical trials: You can use Azure Cognitive Services: QnA Maker to build a system that can answer common questions about clinical trials, such as eligibility criteria, trial locations, and trial timelines.
Patient support: You can use Azure Cognitive Services: QnA Maker to build a system that can answer common questions about patient support, such as financial assistance programs, patient advocacy groups, and support services.
Disease information: You can use Azure Cognitive Services: QnA Maker to build a system that can answer common questions about diseases, such as symptoms, diagnosis, and treatment options.
Health and wellness: You can use Azure Cognitive Services: QnA Maker to build a system that can answer common questions about health and wellness, such as nutrition, exercise, and stress management.
Overall, Azure Cognitive Services: QnA Maker provides a powerful and flexible tool for building question and answer systems that can improve patient engagement and satisfaction, and that enable you to more effectively engage with your customers or patients. By leveraging the machine learning and AI capabilities of the service, you can build systems that are customized to meet the unique needs of your research or business, and that provide accurate, personalized answers to common questions that improve patient outcomes and satisfaction.
C. Features
Azure Cognitive Services: QnA Maker is a machine learning-based service that enables you to quickly and easily build a question and answer system to improve customer or patient engagement and satisfaction. Here are some of the key features of Azure Cognitive Services: QnA Maker:
Easy integration: Azure Cognitive Services: QnA Maker can be easily integrated with other Azure services, such as Azure Bot Service and Azure Functions, as well as third-party tools and services.
Multiple data sources: Azure Cognitive Services: QnA Maker can be configured to use multiple data sources, including websites, product manuals, and other documents, to build an accurate and comprehensive question and answer database.
Customization: Azure Cognitive Services: QnA Maker allows you to customize the question and answer database to meet your specific needs, such as by adding custom questions and answers, or editing existing ones.
Machine learning: Azure Cognitive Services: QnA Maker uses machine learning algorithms to learn from user behavior and improve the accuracy of answers over time.
Multi-language support: Azure Cognitive Services: QnA Maker provides support for multiple languages, which allows you to build question and answer systems that can be used by customers or patients around the world.
Analytics: Azure Cognitive Services: QnA Maker provides analytics and insights into user behavior and application performance, which allows you to optimize and improve your applications over time.
Cost-effective: Azure Cognitive Services: QnA Maker is a cost-effective solution for building question and answer systems, as it is available as a pay-as-you-go service and can be scaled up or down as needed.
Overall, Azure Cognitive Services: QnA Maker provides a powerful and flexible tool for building question and answer systems that can improve customer or patient engagement and satisfaction. By leveraging the machine learning and AI capabilities of the service, you can build systems that are customized to meet the unique needs of your research or business, and that provide accurate, personalized answers to common questions that improve patient outcomes and satisfaction.
D. Where Implemented
E. How it is tested
Testing Azure Cognitive Services: QnA Maker involves verifying that the service is accurately answering questions and providing appropriate answers to users. Here are some steps you can take to test Azure Cognitive Services: QnA Maker:
Verify configuration: Verify that Azure Cognitive Services: QnA Maker is properly configured and integrated with your Azure account and resources.
Test questions and answers: Test Azure Cognitive Services: QnA Maker by submitting sample questions and verifying that the service accurately answers them.
Test customization: Test the customization capabilities of Azure Cognitive Services: QnA Maker by configuring the question and answer database to meet your specific needs, and verifying that the service accurately answers questions based on your unique requirements.
Test integration: Test the integration capabilities of Azure Cognitive Services: QnA Maker by integrating it with other Azure services or third-party tools, and verifying that the service works seamlessly with your existing workflows and platforms.
Test multiple data sources: Test the ability of Azure Cognitive Services: QnA Maker to use multiple data sources by adding different types of data sources and verifying that the service accurately answers questions based on the data from those sources.
Test multi-language support: Test the multi-language support capabilities of Azure Cognitive Services: QnA Maker by submitting questions and verifying that the service accurately answers them in multiple languages.
Test analytics: Test the analytics capabilities of Azure Cognitive Services: QnA Maker by reviewing user behavior and application performance data, and using this data to optimize and improve your applications over time.
Test cost-effectiveness: Test the cost-effectiveness of Azure Cognitive Services: QnA Maker by monitoring usage and costs, and verifying that the service is a cost-effective solution for building question and answer systems.
Overall, testing Azure Cognitive Services: QnA Maker involves verifying that the service is properly configured and functioning as expected, testing questions and answers, customization, integration, multiple data sources, multi-language support, analytics, and cost-effectiveness. By testing Azure Cognitive Services: QnA Maker, you can ensure that you are effectively using the service to build question and answer systems that improve customer or patient engagement and satisfaction, and that you are benefiting from the accuracy, flexibility, and scalability it provides.
F. 2023 Roadmap
????
G. 2024 Roadmap
????
H. Known Issues
As with any software or service, there may be known issues or limitations that users should be aware of when using Azure Cognitive Services: QnA Maker. Here are some of the known issues for Azure Cognitive Services: QnA Maker:
Limited accuracy: While Azure Cognitive Services: QnA Maker provides accurate results in many cases, it may not always accurately answer questions, particularly in cases where the data is complex or contains subtle nuances.
Limited customization: Azure Cognitive Services: QnA Maker has limited customization options, which can limit the ability of users to configure the service to their specific needs.
Limited training data: Azure Cognitive Services: QnA Maker requires a large amount of high-quality training data to accurately answer questions, which can be difficult to obtain and may require significant time and resources.
Limited integration: Azure Cognitive Services: QnA Maker has limited integration with third-party tools and services, which can limit the ability of users to incorporate it into their existing workflows.
Cost: Azure Cognitive Services: QnA Maker can be expensive for users with limited budgets, particularly if they use it frequently or for large volumes of data.
Limited language support: Azure Cognitive Services: QnA Maker has limited language support, which can limit its usefulness for users who work with data in languages other than English.
Overall, while Azure Cognitive Services: QnA Maker offers a powerful and flexible tool for building question and answer systems that can improve customer or patient engagement and satisfaction, users must be aware of these known issues and take steps to mitigate their impact. This may include carefully configuring the service to meet the specific needs of their data, carefully monitoring the accuracy of the service to ensure that it is a good fit for their data requirements, and carefully integrating the service into their existing workflows to ensure that it is effectively utilized. By taking these steps, users can ensure that they are effectively using Azure Cognitive Services: QnA Maker to build question and answer systems that improve customer or patient engagement and satisfaction, and that they are benefiting from the accuracy, flexibility, and scalability it provides.
[x] Reviewed by Enterprise Architecture
[x] Reviewed by Application Development
[x] Reviewed by Data Architecture