- Print
- PDF
CLOVA Chatbot overview
- Print
- PDF
Available in Classic and VPC
CLOVA Chatbot is an interactive AI service that identifies intention in the user's questions and provides appropriate answers. You can use a chatbot builder provided by NAVER Cloud Platform to easily build a chatbot service that learns the conversation data entered for it to process and responds with appropriate answers to users' questions. CLOVA continues to improve the chatbot's features and research the optimal conversation model in order to produce the chatbot engine that understands the user's intentions behind their questions and provides accurate answers for them.
Applied technology and model
CLOVA is creating an excellent chatbot by analyzing Korean sentences perfectly through learning input using long-accumulated NAVER's data, know-how, latest deep learning technologies, and high-performance GPU environment. CLOVA Chatbot’s engine has the deep learning technology which reflects language model features applied. It means that it is able to learn similar meanings in context, sentences, and words, and to accurately recognize words entered wrongly such as typos.
NAVER 's natural language processing NLU engine owns the best morphological analysis technology which performs analyses in consideration of the linguistic nature of Korean with well-developed postpositions and endings. It provides features to analyze object names and statements for analyzing natural language intention, and to understand and analyze multiple natural languages so that their meanings can be extracted.
Process of natural language processing
The natural language processing engine goes through the process of feature extraction, model score calculation, and model ensemble to come up with the optimal response. When an original sentence, i.e., query, comes in, it extracts and categorizes features in the query such as word classes, entities, endings, and morphemes, and sends each feature to various models. Each model processes different feature values. One may focus on analyzing word classes to find answers, and another may look for answers focusing on the entities. A variety of such models is designed to individually calculate scores and then calculate the ensemble score among them to provide the most accurate answer.
Various features provided by CLOVA Chatbot
High correct answer rate for Korean
CLOVA Chatbot with multiple models applied has a high correct answer rate for Korean compared to other companies. Having tested multiple chatbots from different competing companies with the same test data revealed that CLOVA Chatbot scored higher even when the number of intents increased.
Multi-language support
CLOVA Chatbot supports various languages based on an algorithm model optimized for each language's characteristics. Currently a total of 6 languages is supported: Korean, Japanese, English, Chinese, Thai, and Indonesian.
Response composite provided
CLOVA Chatbot provides a response composite to give you more flexibility in creating chatbot responses. It doesn't stop at providing just text answers. Various response composites can be set such as text, button, multi-button, image, and carousel. You can combine multiple composites. They are converted to fit each messenger's specifications if connected to a messenger.
Various analysis indicators provided
CLOVA Chatbot provides various analytic indicators to continuously improve the conversation model. The utterance types reviewed in scenario modeling and the way users actually use it in the real service may differ, and the conversations implemented in the chatbot may not represent all users' utterance patterns. Therefore, the statistics data or data for analyzing utterance records of incoming users is provided.
Information on User Guide of CLOVA Chatbot
The user guide of CLOVA Chatbot consists of the following topics that will help you to effectively use the service. You can check the following information in each topic.
- CLOVA Chatbot overview: Introduction to CLOVA Chatbot, related supporting resources for use
- CLOVA Chatbot specifications: Required specifications to use CLOVA
- CLOVA Chatbot scenario: Guide to application and management of CLOVA Chatbot service in NAVER Cloud Platform Console
- Get started: how to start using CLOVA Chatbot
- Subscribe and unsubscribe: Guide to full process with using CLOVA Chatbot
- Managing CLOVA Chatbot permissions: How to manage CLOVA Chatbot permission using Sub Account
- Create CLOVA Chatbot
- Design chatbot: Things to take account before creating a chatbot
- Create domain: How to create domain, which is a base unit of the chatbot service
- Create conversation: How to create conversations
- Register common message: How to register common messages used by the chatbot
- Task: How to use task, which allows you to design complex conversations
- Build: How to build conversations created
- Test: How to test conversations built
- Manage CLOVA Chatbot conversation components
- Conversation component overview: List of conversation components provided by NAVER Cloud Platform
- Entity: How to use entity, where multiple words can be registered to be used like a dictionary
- Regular expression parameters: How to create frequently used regular expression parameters
- Action method: How to use action method which enables you to use data from an external system
- Utilization of Action Method V2: How to use Action Method V2.0
- [Form](/docs/en/chatbot-chatbot-3 -5): How to use form to request answers within the choices set by the user
- User variable: How to manage user variables
- Manage CLOVA Chatbot
- Manage domain: Information on the domain management and chatbot settings pages
- Manage statistics: How to view the chatbot's statistics data and user utterance records
- Relearn: How to relearn, which is to reflect actual user questions to the conversation to raise the response quality
- Manage domain group: How to manage domain groups
- Advanced utilization of CLOVA Chatbot
- Regular expression input methods: How to use regular expression syntax
- JSON editing mode: How to use JSON editing mode
- Conversation canvas: How to use conversation canvas
- Connecting CLOVA Chatbot with messenger
- Basic connection with API Gateway: Guide to basic connection with API Gateway to integrate chatbots with external channels
- Connect with LINE messenger: How to connect with LINE Messenger
- Connect with TalkTalk: How to connect with the NAVER TalkTalk service
- Connect with Facebook: How to connect with Facebook
- Connect with NAVER WORKS: How to connect with NAVER WORKS
- Connect with CLOVA Extensions: How to connect with CLOVA Extensions service
- CLOVA Chatbot Custom API Spec.: How to connect with a website
- Extended services connection of CLOVA Chatbot
- Connect with LINE API: How to connect with LINE Switcher API
- Connect with knowledge database: How to connect with NAVER's knowledge database
- Connect with LINE pay: How to connect with LINE pay
- Connect with NAVER pay: How to connect with NAVER pay
- Connect with OAuth: How to connect with authentication services
- Connect with multimedia intent: How to connect with OCR or image analysis solutions
- Connect with intension classifier: How to connect with solutions that analyze intention of the messages entered in the chatbot
- Connect with AiCall: How to connect with AiCall
- Troubleshooting
- CLOVA Chatbot execution examples: Guide to creating Chatbot using sample data
- CLOVA Chatbot glossary: Key terms to know when using CLOVA Chatbot
- CLOVA Chatbot release notes: Update history of CLOVA Chatbot guide
CLOVA Chatbot related resources
- Service description: https://www.ncloud.com/product/aiService/chatbot
- Pricing information:: https://www.ncloud.com/charge/calc/ko
- API Guide: https://api.ncloud-docs.com/docs/en/ai-application-service-chatbot
- Training videos
- About Service: https://youtu.be/u1TSKpvQKMs
- Create simple chatbot: https://youtu.be/9xauO9t8Fu8
- Build a chatbot service: https://youtu.be/u1TSKpvQKMs
- Development document:: https://developers.naver.com/docs/en/clova/custom_ext/README.md