Smart systems for universities powered by artificial intelligence have been massively developed to help humans in various tasks. The chatbot concept is not something new in today’s society which is developing with recent technology. College students or candidates of college students often need actual information like asking for something to customer service, especially during this pandemic, when it is difficult to have an immediate face-to-face meeting. Chatbots are functionally helping in several things such as curriculum information, admission for new students, schedule info for any lecture courses, students grade information, and some adding features for Muslim worships schedule, also weather forecast information. This Chatbot is developed by deep learning models, which was adopted by an artificial intelligence model that replicates human intelligence with some specific training schemes. This kind of deep learning is based on RNN which has some specific memory savings scheme for the deep learning model, specifically this chatbot using LSTM which already integrates by RASA framework. LSTM is also known as Long Short Term Memory which efficiently saves some required memory but will remove some memory that is not needed. This Chatbot uses the Facebook platform because the Facebook users have already reached up to 60.8% of its entire population in Indonesia.

Smart systems have been massively developed to help humans in various tasks. Deep Learning technologies push even further in creating accurate assistant systems due to the explosion of data lakes. One of the smart system tasks is disseminating ‘users needed information’, which is crucial in the tourism sector to promote local tourism destinations. In this research, we design a local tourism specific image captioning model, which will later support the development of AI-powered systems that assist various users. The model is developed using a visual Attention mechanism and uses the state-of-the-art feature extractor architecture EfficientNet. A local tourism dataset is collected and used in the research and two different captions: captions that describe the image literally and captions that represent human logical responses when seeing the image. The two kinds of captions make the captioning model more humane when implemented in the assistance system. We compared two different models using EfficientNet architectures (BO and B4) with other well-known VGG16 and InceptionV3. The best BLEU scores we get are 73.39 and 24.51 for the training set and the validation set, respectively, using EfficientNetB0. The captioning result using the developed model shows that the model can produce logical caption for local tourism-related images.

Intelligent systems for universities that are powered by artificial intelligence have been developed on a large scale to help people with various tasks. The chatbot concept is nothing new in today's society, which is developing with the latest technology. Students or prospective students often need actual information, such as asking customer service about the university, especially during the current pandemic, when it is difficult to hold a personal meeting in person. Chatbots utilized functionally as lecture schedule information, student grades information, also with some additional features for Muslim prayer schedules and weather forecast information. This conversation bot was developed with a deep learning model adopted by an artificial intelligence model that replicates human intelligence with a specific training scheme. The deep learning implemented is based on RNN which has a special memory storage scheme for deep learning models, in particular in this conversation bot using GRU which is integrated into RASA chatbot framework. GRU is also known as Gated Recurrent Unit, which effectively stores a portion of the memory that is needed, but removes the part that is not necessary. This chatbot is represented by a web application platform created by React JavaScript, and has 0.99 Average Precision Score.