Launching multi-domain conversational AI, with simplicity and efficiency. We have developed our own platform and create customizable services to meet specific business improvement needs.
As an application software that takes full advantage of our platform’s functionality, we offer our English conversation, self-learning support agent.
Equmenopolis is focused on the idea of a pleasurable and entertaining “conversational experience”, and is researching the basic technologies that will recreate this experience in AI reality.
The technology seeds that originated our platform begun with the development of a fundamental two-way communication mechanism for interactive conversation in JST START (“Commercialization of Media Service Equipped with Social Conversation AI”).
With NEDO’s (New Energy and Industrial Technology Organization) support, we launched a project named “Online Language Learning Support AI that Grows with People”, and created an interactive English speaking ability assessment interview system. Concurrently, during the JST SBIR Phase 1 project (“Development of Highly Personalized Information Space Guide AI“), we have developed a conversational museum guide AI that provides personalized explanations for its users. Our museum guide was realized through the organization of vast amounts of data in AR/VR space. The guide and its technology has been repeatedly tested via trials and demonstrative presentations.
Our platform includes the fruits of these research projects, though we plan to further deepen our expertise through our offered services.
InteLLA (Intelligent Language Learning Assistant) employs dialogue system technology to adaptively change questions according to the language learner’s abilities and understanding, eliciting appropriate speech samples and effectively assessing the learner’s language proficiency. InteLLA is scheduled for commercial release in 2023.
The BLENDi (Blended Dialog) project is developing a smart space guide AI agent that can lead visitors through a ‘digital twin’ environment such as a science or art museum. The AI skillfully captures users’ implicit feedback and adaptively develops a unique story. This is achieved by organizing vast amounts of information both in advance and dynamically, in tune with user interests and curiosity.
We have defined the evaluation metrics through demonstrative experiments, studying criteria such as information transmission efficiency, the learning effects, and willingness to revisit a museum as the performance indicators for our AI guide. This service provides solutions to enhance museum functionality and optimize operating costs.