Umeå University's logo

Supporting human actors in daily living activities for improving health and wellbeing is a fundamental goal for assistive technology. The personalisation of the support provided by assistive technology in the form of digital coaching requires user models that handle potentially conflicting goals and motives. The aim of this research is to extend a motivational model implemented in an assistive technology, into a multipurpose motivational model for the human actor who is to be supported, which can be translated into a multipurpose goal model for a team of assistive agents. A team of assistive agents is outlined with supplementary goals following the human’s different properties. A method for generating multipurpose arguments relating to different motives were developed, and implemented in a human-agent dialogue system. The results are exemplified based on a use case from an earlier pilot user study of the assistive technology. Future work includes user studies to validate the model.

A common conversation between an older adult and a nurse about health-related issues includes topics such as troubles with sleep, reasons for walking around nighttime, pain conditions, etc. Such a dialogue can be regarded as a "natural" dialogue emerging from the participating agents' lines of thinking, their roles, needs and motives, while switching between topics as the dialogue unfolds. The purpose of this work is to define a generic conceptual model of purposeful human-agent dialogue activity including different types of argumentation dialogues, suitable for health-related topics. This is done based on analyses of a scenario, persona and models of human behaviour. The model will be shared between the human and the agent, allowing for adaptation to the human's reasoning, needs and motives.

The goal of this study is to develop a computer-interpretable model for activity detection and representation, based on existing informal models of how humans perform activity. Appropriate detection of purposeful human activity is an essential functionality of active assistive technology aiming at providing tailored support to individuals for improving activity performance and completion. The main contribution is the design of a model for detection and representation of human activities based on three categories of instruments, which is implemented as two generic and supplementary terminology models: an event ontology and a core ontology. The core ontology is extended for each new knowledge domain into a domain ontology. The model builds the base for personalization of services generated by the cooperative reasoning performed by a human collaborating with an intelligent and social software agent. Ongoing and future work includes user studies in the different application domains.

Supporting human actors in daily living activities for improv- ing health and wellbeing is a fundamental goal for assistive technology. The personalization of the support provided by assistive technology in the form of digital coaching requires user models that handle potentially conflicting goals and motives. The aim of this research is to extend a motivational model implemented in an assistive technology, and outline a team of assistive agents with supplementary goals following the human’s different properties, orchestrated by a companion agent based on the multipurpose motivational model for the human actor who is to be supported. The multi- purpose motivational model and supportive arguments relating to different motives are exemplified based on a use case from an earlier pilot user study of the assistive technology. Future work includes user studies to validate the model.

The main purpose of assistive technology is to support an individual's daily activities, in order to increase ability, autonomy, relatedness and quality of life. The aim for the work presented in this article is to develop automated methods to tailor the behavior of the assistive technology for the purpose to provide just-in-time, adaptive interventions targeting multiple domains. This requires methods for representing and updating the user model, including goals, preferences, abilities, activity and its situation. We focus the assessment and intervention tasks typically performed by therapists and provide knowledge-based technology for supporting the process. A formative evaluation study was conducted as a part of a participatory action research process, involving two rehabilitation experts, two young individuals and one senior individual as end-user participants, in addition to knowledge engineers. The main contribution of this work is a theory-based method for assessing the individual's goals, preferences, abilities and motives, which is used for building a holistic user model. The user model is continuously updated and functions as the base for tailoring the system's assistive behavior during intervention and follow-up.

A common conversation between an older adult and a nurse about health-related issues includes topics such as troubles with sleep, reasons for walking around nighttime, pain conditions, etc. This dialogue emerges from the participating human's lines of thinking, their roles, needs and motives, while switching between topics as the dialogue unfolds. This paper presents a dialogue system that enables a human to engage in a dialogue with a software agent to reason about health-related issues in a home environment. The purpose of this work is to conduct a pilot evaluation study of a prototype system for human-agent dialogues, which is built upon a set of semantic models and integrated in a web application designed for older adults. Focus of the study was to receive qualitative results regarding purpose and content of the agent-based dialogue system, and to evaluate a method for the agent to evaluate its behavior based on the human agent's perception of appropriateness of moves. The participants include five therapists and 11 older adults. The results show users' feedback on the purpose of dialogues and the appropriateness of dialogues presented to them during the interaction with the software agent.

The aim of this research is to develop new theories, methods and technology, which enables adaptive and personalised dialogues between a human and a software agent, to handle everyday queries about health that are perceived as meaningful and useful to the human. Some of the challenges to build such human-agent dialogue system are the following. The agent needs to have knowledge about the human, the topic of the dialogue, the knowledge domain of the topic, and also about the physical and social environment. Moreover, the agent must know about itself, its role, purpose and limitations. It must know how to be cooperative and be able to behave and express with empathy while conducting a dialogue activity. In some situations, it needs to reason and make decisions about a topic together with the human and about its own behavior. To be able to do this, it needs the capability to evaluate its behavior in the context in which the dialogue takes place. These challenges are addressed by developing formal semantic models to provide the agent with tools to build their knowledge and to be able to reason and make decisions. These models were developed based on literature studies, theories of human activity, argumentation theory, personas and scenarios.

The models were formalised and implemented using Semantic Web technology, and integrated into a human-agent dialogue system. The system was evaluated with a group of therapists and a group of elderly people, who showed curiosity and interest in having dialogues with a software agent on various topics.

The formal models that the agent constructs are adapted to the specific situation and to the human actor participating in a dialogue. They are based on four models: a model with knowledge about the human actor, a model of itself, a domain model, and a dialogue activity model. The dialogue activity is based on argumentation schemes, which function as patterns of reasoning and for the dialogue execution. These models allow the agent and the human actor to conduct flexible and nested sub-dialogues with different purposes within a main dialogue about a topic. The agent can adapt its moves to the human actor's trail of reasoning, to the human's priorities and goals, and to some human's emotional state. A method for the agent to be able to evaluate its behavior was also developed and evaluated. The proportion of appropriate moves in relation to the local context of earlier moves in the dialogue was 90% in the pilot study, which indicates that the agent's strategies for selecting moves can be improved.

Future research will focus on further development of reasoning methods, learning and assessment methods, and interface design. The results will be applied to additional knowledge domains to test its domain independence and will be evaluated with different groups of potential users.

This paper proposes a cognitive architecture of an intelligent agent that can have a dialogue with a human agent on health-related topics. This architecture consists of four main components, namely, the Belief Base, the Dialogue Manager, the Task Manager and the Plan Generator. Each component has sub-components that perform a set of tasks for the purpose to enable the agent to be enrolled in a dialogue. In this paper the particular sub-component of the Dialogue Manager, the Dialogue Strategy has been discussed in detail. A notion of scheme is introduced, which functions as a template with variables that are instantiated each time a state is entered. The agent’s dialogue strategy is implemented as a combination of the schemes and the state transitions that the agent makes in response to the human’s request. We used a combination of finite-state and agent-based dialogue strategies for dialogue management. This combined dialogue strategy enables a multi-topic dialogue between a human and an agent.

In this paper, an argumentation-based deliberative approach for fusing contextual information obtained from heterogeneous sources using a multi-agent system is introduced. The system is characterized by three different agents: an Environment Agent, an Activity Agent and a Coach Agent. These agents consider data from heterogenous sources of data. As a method for aggregating data and supporting decision-making, so-called agreement rules are instrumental in the argumentation-based deliberative method. The aggregation rules will be associated to specific beliefs related to the services of each agent.

A common conversation between an older adult and a nurse about health-related issues includes topics such as troubles with sleep, reasons for walking around nighttime, pain conditions, etc. Such a dialogue can be regarded as a "natural" dialogue emerging from the participating agents' lines of thinking, their roles, needs and motives, while switching between topics as the dialogue unfolds. The purpose of this work is to define a generic model of purposeful human-agent dialogues suitable for health-related topics. This is done based on analyses of scenarios, personas and models of human behavior. The results include four models, which need to be included in a software agent's belief base; i) a user model, ii) a model of the domain knowledge related to the topic of the dialogue, iii) an agent model, and iv) a dialogue activity model. The models were implemented into a prototype system for human-agent dialogues, which was evaluated by therapists and a group of older adults.