BT Technol J Vol 18 No 1 January 2000 91 Towards human-centred intelligent systems — the intelligent assistant D Djian, N Azarmi, B Azvine, K C Tsui and W Wobcke In this paper, we describe some abstract features of human/machine interaction systems that are required for the production of intelligent behaviour. We introduce a subset of intelligent systems called human-centred intelligent systems (HCIS) and argue that such systems must be autonomous, robust and adaptive in order to be intelligent. We also propose soft computing as a promising new technique that can be used to build HCIS, and present examples where this is already being done. The paper defines flexibility to be a combination of the often-conflicting requirements of robustness and adaptability, and based on this we claim that the right balance between these two features is necessary to achieve intelligent behaviour. We describe the intelligent assistant (IA) system and its various components which automatically perform helpful tasks for its user, so as to enable the user to improve productivity. These tasks include time, information and communication manage- ment. Time management involves planning and scheduling, decision making and learning user habits. Information management involves information seeking and filtering, information fusion, decision making and learning user preferences. Communication management involves recognising user behaviour and learning user priorities. All these tasks depend on many factors including the type of activity, its orginator, the mood of the user, past experience, and the priority of the task. The IA uses a multimodal interface with conventional interfaces such as keyboard and mouse enhanced to include vision, speech and natural language processing. The inclusion of such extra modalities extends the capabilities of existing systems at the cost of introducing extra complexity. The IA is ‘smart’ because it has the knowledge about tasks and the capability to learn and adapt to new interactions with its user and with other systems. 1. Introduction 2. Communications management • to provide support to initiate outgoing communications, • to handle incoming interruptions. This paper focuses on the second of these, which usually affects the concentration of a user and reduces their productivity. 3. Information management T he objective of the information management components of the intelligent assistant (IA) is to assist the user to gather the required information. They provide a more natural way of specifying what is required and an enhanced search strategy that is tailored to the user’s interests. There are two components in the IA for information management — the Yellow Pages assistant and Web assistant. 4. Time management 5. User interactions management F or a computer to effectively communicate with humans it must possess communication capabilities that are similar to those of a human, i.e. it must be able to see, hear and speak. It must also be able to understand and, if necessary, question. The key point is that it is the combination of these capabilities that allows humans to communicate effectively and naturally. Limiting the communication by blocking some of these modalities clearly reduces the amount of information conveyed. This E arly attempts at building systems with comparable cognitive capability to the human brain have not been as successful as predicted. The problems of knowledge representation, commonsense knowledge and reasoning, real-time problem solving, vision, speech, and language processing have not as yet yielded to classical AI techniques. Despite the difficulties, AI has been successfully applied in some areas such as expert systems, classification, planning, scheduling, game playing and robotics. The focus is on systems that can augment the cognitive capabilities of humans, i.e. a human-machine symbiosis or human-centred intelligent system (HCIS). I n a modern office environment there are two main issues in managing communication: T he diary assistant helps the user with time management by maintaining a schedule of tasks. The user is able to enter and edit tasks, move tasks from one day to another, save and load particular day sequences, and invoke the scheduling capabilities of the assistant.