Chakavian Artificial Intelligence (CAI)

AI recognizing items in old photo
AI recognizing items in old photo

The idea of Chakavian artificial intelligence project is to create a system that will communicate with the user in the Chakavian language.

Methodological approach

The age of the digital assistants is rising, with different computer-assisted conversation modules emerging from various technology companies such as IBM, Google, Amazon, Apple, Microsoft, Facebook. The conversation module, sometimes also called a chatbot (Raj 2018, Goyal et al. 2018), is a machine learning system that allows human users to have conversational experience about some domain of knowledge.

The process of creating a conversation module is comprised of several phases that include: defining the conversation domain, classification of intent, building the conversational database, chatbot customization and personality. The domain is defined as a set of interactional procedures and informational resources that a particular chatbot should be used for. The classification deals with the categorization and identification of user’s intents to provide an appropriate response for the given domain. Intents have Training Phrases, which are examples of different syntactic-semantic constructions a user might elicit in a conversation about the given domain in order to express a particular intent for information that is retrieved from a Chatbot, ie. the database of responses.

Why Museums Assistant is needed

Heritage Museum of Drenova is a small regional museum operated by volunteers and local NGO Without Borders Society. This creates several “operational” challenges as the museum is opened on demand, volunteers are not always readily available, so valuable artifacts present in the museum are not always publicly available. The way around this problem is to digitize all materials and publish them on the web site – but to navigate between thousands of documents can be a problem for the occasional visitor. A possible solution represents the introduction of a museum assistant in the form of chatbots that would help visitors both in the virtual world and in physical visits in the premises of the museum.

Chatbot advantages

Chatbots have a number of advantages precisely if they are used in situations where there are not enough skilled staff or should serve a large number of simultaneous users:

Accessibility: Museum assistant is easily accessible over the WEB or mobile application. The user can open the website and start asking questions or begin resolving their queries regarding museum content or activities. A basic set of information can be returned back, or museum visit with live guidance could be arranged.

Efficiency: Is users are interested in particular information that is already digitized, Museum Assistant can help to find appropriate content “in real time” boosting research productivity and reducing travel costs to physical museum.

Availability: Chatbots are available 24 hours per day, 7 days per week. They will do the same tasks or new tasks every time with the same efficiency and performance.

Scalability:  In case of great interest of visitors, or the arrival of larger groups, the Museum assistant provides individual experience in reviewing the material, the number of users that can simultaneously administer it is virtually unlimited.

Cost: Costs are particularly important for NGOs that base their work on volunteers. Any system that can facilitate operation and reduce operating costs is welcome, in which case the funds can be directed for further research or improvement of the contents of the museum

Insights: Your sales representative might not be able to remember the behavior of the user and give you exclusive insight about the consumer behavioral pattern, but your bots can using latest techniques of machine learning and data science.