Skip to content

Our newest innovation: chatbots and satellite imaging

Geocento has recently commenced an InnovateUK project which will apply Chatbot natural language processing to the satellite imaging business with the aim of making the process of discovering and ordering imagery much easier. We are currently in the process of designing the intents associated with user interactions, the workflows and entities (key parameters) associated with these interactions and the information needed to fulfil an enquiry.

A Chatbot is a computer program or artificial intelligence which conducts a conversation via auditory or textual methods with a human. These programs are designed to simulate how a human would behave as a conversational partner. Chatbots are typically used in dialogue systems for various practical purposes including customer service or information acquisition and as such are potentially very relevant to the satellite imaging business. Some chatbots use sophisticated natural language processing systems, but many simpler systems scan for keywords within the input, then provide a reply with the most matching keywords, or the most similar wording pattern, from a database.

The aim of the project is to help make our interactions with our clients more efficient for them and us, ensuring that information needed to fulfil an enquiry is complete and obtained as easily as possible. Part of the innovation involves using our EarthImages API as one source of information to answer questions posed by the client, within the Chatbot environment, for example in relation to whether there is fresh imagery of a region. We are finding that the process of designing the Chatbot is extremely valuable in its own right, providing a framework within which to articulate the thinking, logic, methods of expression and intents of the range of users.

We are currently working on the design of the Chatbot. We will then move onto the implementation later during the summer. Please do get in touch with us via our contact page if you wish to find out more. We will report on results in a later blog.