Personal Assistant Agents Research Articles

Using psychological characteristics of situations for social situation comprehension in support agents

Support agents that help users in their daily lives need to take into account not only the user’s characteristics, but also the social situation of the user. Existing work on including social context uses some type of situation cue as an input to information processing techniques in order to assess the expected behavior of the user. However, research shows that it is important to also determine the meaning of a situation, a step which we refer to as social situation comprehension. We propose using psychological characteristics of situations, which have been proposed in social science for ascribing meaning to situations, as the basis for social situation comprehension. Using data from user studies, we evaluate this proposal from two perspectives. First, from a technical perspective, we show that psychological characteristics of situations can be used as input to predict the priority of social situations, and that psychological characteristics of situations can be predicted from the features of a social situation. Second, we investigate the role of the comprehension step in human–machine meaning making. We show that psychological characteristics can be successfully used as a basis for explanations given to users about the decisions of an agenda management personal assistant agent.

Mobile Apps as Personal Assistant Agents: the JaCa-Android Framework for programming Agents-based applications on mobile devices

A relevant application domain for agent-based software is given by mobile and wearable applications. In this context, the impressive progress of technologies in the last decade makes it possible to explore the use of agent-oriented programming languages and frameworks based on cognitive architectures, such as the Belief–Desire–Intention (BDI) one. Accordingly, in this paper we provide a comprehensive description of the JaCa-Android approach, a framework based on the JaCaMo platform that allows for designing and programming smart mobile apps using cognitive agents based on the BDI architecture and the Agents & Artifacts environment conceptual model. In these years, the framework has been applied in real-world projects and application domains, and extended and evolved accordingly. The aim of the paper is to report our experience about designing and programming mobile apps as personal assistant agents, as well as to discuss in detail the architecture of the framework.

BDI personal medical assistant agents: The case of trauma tracking and alerting.

Personal assistant agents can have an important role in healthcare as a smart technology to support physicians in their daily work, helping to tackle the increasing complexity of their task environment. In this paper we present and discuss a personal medical assistant agent technology for trauma documentation and management, based on the Belief-Desire-Intention (BDI) architecture. The purpose of the personal assistant agent is twofold: to assist the Trauma Team in doing precision tracking during a trauma resuscitation, so as to (automatically) produce an accurate documentation of the trauma, and to generate alerts at real-time, to be eventually displayed either on smart-glasses or room-display.

Neural Networks for Survey Researchers

Neural networks are currently one of the most popular and fastest growing approaches to machine learning, driving advances in deep learning for difficult real-world applications ranging from image recognition to speech understanding in personal assistant agents to automatic language translation. Although not yet as commonly employed in survey research as other types of machine learning, neural networks offer natural extensions of well-known linear and logistic regression techniques in order to learn non-linear functions predicting or describing nearly any real-world process or problem (provided there are sufficient data and an appropriate set of parameters). Moreover, neural networks offer great potential towards more intelligent surveys in the future (e.g., adaptive design tailored to individual respondents’ characteristics and behavior, automated digital interviewers, analysis of rich multimedia data provided by respondents). Neural networks can learn for both regression and classification tasks without requiring assumptions about the underlying relationships between predictive variables and outcomes. In this article, we describe what neural networks are and how they learn (with tips for setting up a neural network), consider their strengths and weaknesses as a machine learning approach, and illustrate how they perform on a classification task predicting survey response from respondents’ (and nonrespondents’) prior known demographics.

PACMAN: Personal Agent for Access Control in Social Media

Given social media users’ plethora of interactions, appropriately controlling access to such information becomes a challenging task for users. Selecting the appropriate audience, even from within their own friend network, can be fraught with difficulties. PACMAN is a potential solution for this dilemma problem. It’s a personal assistant agent that recommends personalized access control decisions based on the social context of any information disclosure by incorporating communities generated from the user’s network structure and utilizing information in the user’s profile. PACMAN provides accurate recommendations while minimizing intrusiveness.

Evaluating intelligent knowledge systems: experiences with a user-adaptive assistant agent

This article examines experiences in evaluating a user-adaptive personal assistant agent designed to assist a busy knowledge worker in time management. We examine the managerial and technical challenges of designing adequate evaluation and the tension of collecting adequate data without a fully functional, deployed system. The CALO project was a seminal multi-institution effort to develop a personalized cognitive assistant. It included a significant attempt to rigorously quantify learning capability, which this article discusses for the first time, and ultimately the project led to multiple spin-outs including Siri. Retrospection on negative and positive experiences over the 6 years of the project underscores best practice in evaluating user-adaptive systems. Lessons for knowledge system evaluation include: the interests of multiple stakeholders, early consideration of evaluation and deployment, layered evaluation at system and component levels, characteristics of technology and domains that determine the appropriateness of controlled evaluations, implications of ‘in-the-wild’ versus variations of ‘in-the-lab’ evaluation, and the effect of technology-enabled functionality and its impact upon existing tools and work practices. In the conclusion, we discuss—through the lessons illustrated from this case study of intelligent knowledge system evaluation—how development and infusion of innovative technology must be supported by adequate evaluation of its efficacy.

Assistant agents to advice users in hybrid structured 3D virtual environments

ABSTRACTHybrid structured 3D Virtual Environments model serious activities in immersive 3D spaces, where participants are human and software agents, and their interactions are regulated by an Organization Centered Multi‐Agent System (OCMAS). In this context, both OCMAS social model and the tasks that users need to accomplish can be rather complex, and thus, users may benefit from having an assistance service. Hence, we propose personal assistant agents (PA), which, based on knowledge about the OCMAS specification and current system state, provide the user with an advice (a plan) to achieve her or his goal. Additionally, we implement this service with PLAN-EA, an Extension of the A * algorithm that generates plans for a user whose actions may depend on other users’ actions. Thus, PAs provide plans that do not only include assisted user actions but also other users’ ones. We illustrate our approach by means of v‐mWater—an online water market—and make a comparative analysis, with and without assistance, where efficiency—in terms of number of user actions—shows an improvement (7 vs 10.8), efficacy—percentage of completed tasks—also improves (93% vs 77%), and assistance's overall satisfaction is positive. Copyright © 2014 John Wiley & Sons, Ltd.

An ambient agent system assisting humans in complex tasks by analysis of a human's state and performance

Human task performance varies depending on the task, environment, and states of the human over time. To ensure high effectiveness and efficiency in the execution of complex tasks, adaptive automated assistance of the human may be required. In this paper, a generic design for a multi-agent system architecture is presented and a personal assistant agent is described that makes use of the proposed architecture. The agent constantly monitors the task execution and well-being of the human via non-intrusive sensors, and intervenes when a problem is detected. A human is given a complex task, while the future performance is predicted using observations and a dynamical model for the human's work pressure and exhaustion. If the predicted exhaustion becomes too high, the ambient agent can assist the human in a number of ways. Experiments with humans show that the support system increases performance with around 13%, and that it enhances the feeling of control of the situation.

THE DESIGN OF A PROACTIVE PERSONAL AGENT FOR TASK MANAGEMENT

Personal assistant agents capable of proactively offering assistance can be more helpful to their users through their ability to perform tasks that otherwise would require user involvement. This article characterizes the properties desired of proactive behavior by a personal assistant agent in the realm of task management and develops an operational framework to implement such capabilities. We present an extended agent architectural model that features a meta-level layer charged with identifying potentially helpful actions and determining when it is appropriate to perform them. The reasoning that answers these questions draws on a theory of proactivity that describes user desires and a model of helpfulness. Operationally, assistance patterns represent a compiled form of this knowledge, instantiating meta-reasoning over the agent's beliefs about its user's activities as well as over world state. The resulting generic framework for proactive goal generation and deliberation has been implemented as part of a personal assistant agent in the computer desktop domain.

A Model for Context Aware Mobile Payment

With the advent of mobile networks and mobile devices, mobile payment has been attractive to many ecommerce users. Mobile environment features a wide range and an increasing number of access devices and network technologies. Context-aware content/service adaptation is deemed necessary to ensure best user experience. We developed an Adaptation Management Framework (AMF) Mobile Payment Service which manages the complexity of dynamic and autonomous mobile payment service. In this Framework, a personal assistant agent is presented for automatic and intelligent payment and a model is implemented for inference and making appropriate decisions. To evaluate the suggested framework, context data were collected from content providers and a mobile network operator. The obtained results confirm the efficiency of the method.

Electric Elves: What Went Wrong and Why

Software personal assistants continue to be a topic of significant research interest. This article outlines some of the important lessons learned from a successfully-deployed team of personal assistant agents (Electric Elves) in an office environment. In the Electric Elves project, a team of almost a dozen personal assistant agents were continually active for seven months. Each elf (agent) represented one person and assisted in daily activities in an actual office environment. This project led to several important observations about privacy, adjustable autonomy, and social norms in office environments. In addition to outlining some of the key lessons learned we outline our continued research to address some of the concerns raised.

Expert System for Developing Self-regulated Learning Skills

Expert system for teaching programming languages is presented in this paper. Many teachers can cooperate together to put the curriculum of one/more computer programming language(s). Their contributions may include: (a) add or modify the commands’ structure that will be taught; (b) generate different tutoring dialogs for the same command; and (c) generate different tutoring styles. On the contrary, the students can access the system through WWW, select any language they want to learn as well as the style of presentation they prefer and they can exchange their experiences. A personal assistant agent for teachers and students with an adaptive interface, and tutoring agent has been built. The tutoring agent resides on the server side and communicates via HTTP and IIOP with both the personal assistant agent for teachers and personal assistant agent for students on the client’s side. This structure allows customization of the personal assistant agent for teachers and students to the needs of the teachers and students, without putting extra burden on the server. In addition, this allows having many teacher agents attending to the needs of a single or multiple student agent(s).

Giving Personal Assistant Agents a Case-Based Memory

We consider Personal Assistant (PA) agents as cognitive agents capable of helping users handle tasks at their workplace. A PA must communicate with the user using casual language, sub-contract the requested tasks, and present the results in a timely fashion. This leads to fairly complex cognitive agents. However, in addition, such an agent should learn from previous tasks or exchanges, which will increase its complexity. Learning requires a memory, which leads to the two following questions: Is it possible to design and build a generic model of memory? If it is, is it worth the trouble? The article tries to answer the questions by presenting the design and implementation of a memory for PA agents, using a case approach, which results in an improved agent model called MemoPA.

Preferences in Interactive Systems: Technical Challenges and Case Studies

Interactive artificial intelligence systems employ preferences in both their reasoning and their interaction with the user. This survey considers preference handling in applications such as recommender systems, personal assistant agents, and personalized user interfaces. We survey the major questions and approaches, present illustrative examples, and give an outlook on potential benefits and challenges.

Personal assistant agents for collaborative design environments

Intelligent software agents have been recognized as a promising approach for the development of collaborative engineering environments. This paper presents our recent work on developing personal assistant agents to support users working within collaborative design environments (CDE). It describes a cognitive user model as a composition of the user's interest and behavior models. An intelligent assistance architecture is proposed to integrate these models with other environment models as well as inference, knowledge update and collaboration components. All these models and components collectively enable personal assistant agents to effectively work with the corresponding users to achieve their goals in a collaborative environment. The proposed user model is implemented in a coordinated, intelligent, rational agent (CIR-Agent) model on a FIPA (Foundation for Intelligent Physical Agents)-compliant platform. Two case studies have been carried out to demonstrate the proposed agent-based intelligent assistance approach.

Privacy Loss in Distributed Constraint Reasoning: A Quantitative Framework for Analysis and its Applications

It is critical that agents deployed in real-world settings, such as businesses, offices, universities and research laboratories, protect their individual users' privacy when interacting with other entities. Indeed, privacy is recognized as a key motivating factor in the design of several multiagent algorithms, such as in distributed constraint reasoning (including both algorithms for distributed constraint optimization (DCOP) and distributed constraint satisfaction (DisCSPs)), and researchers have begun to propose metrics for analysis of privacy loss in such multiagent algorithms. Unfortunately, a general quantitative framework to compare these existing metrics for privacy loss or to identify dimensions along which to construct new metrics is currently lacking. This paper presents three key contributions to address this shortcoming. First, the paper presents VPS (Valuations of Possible States), a general quantitative framework to express, analyze and compare existing metrics of privacy loss. Based on a state-space model, VPS is shown to capture various existing measures of privacy created for specific domains of DisCSPs. The utility of VPS is further illustrated through analysis of privacy loss in DCOP algorithms, when such algorithms are used by personal assistant agents to schedule meetings among users. In addition, VPS helps identify dimensions along which to classify and construct new privacy metrics and it also supports their quantitative comparison. Second, the article presents key inference rules that may be used in analysis of privacy loss in DCOP algorithms under different assumptions. Third, detailed experiments based on the VPS-driven analysis lead to the following key results: (i) decentralization by itself does not provide superior protection of privacy in DisCSP/DCOP algorithms when compared with centralization; instead, privacy protection also requires the presence of uncertainty about agents' knowledge of the constraint graph. (ii) one needs to carefully examine the metrics chosen to measure privacy loss; the qualitative properties of privacy loss and hence the conclusions that can be drawn about an algorithm can vary widely based on the metric chosen. This paper should thus serve as a call to arms for further privacy research, particularly within the DisCSP/DCOP arena.

E-commerce oriented software agents: Towards legal programming: a legal analysis of ecommerce and personal assistant agents using a process/IT view of the firm

Agent-based technologies and processing may answer some of the legal difficulties raised by traditional online commerce, introducing elements of compliance, control, flexibility and personalisation. However as they mediate commercial relationships with third parties, software agents in turn raise new legal difficulties, while potentially heightening user fears and mistrust. The autonomy, adaptivity and interactivity of agents, combined with the advent of ubiquitous computing, introduce a new set of legal dimensions including the liability of agent users, the automation of notification and consent or the attribution of responsibility, as well as new fears for users. This article presents a process oriented analysis of agent activities, within the context of augmented reality: the application of Internet technologies to the real world, specifically in this case to supermarket shopping. Specific areas of difficulty are contract and consumer protection law, as well as privacy. These topics are highlighted, together with trust issues raised in Multi-Agent Systems which will be discussed in a later article in this series.

Adaptive Meeting Scheduling for Large-Scale Distributed Groupware

This paper introduces a novel approach of collective scheduling among a community of distributed users. This approach, named Distributed Adaptive Scheduling (DAS), deploys flexible, lightweight agents to quickly find and suggest suitable solutions of scheduling for a large number of users. The DAS agents can move from one machine to another to co-ordinate mutually acceptable solutions for a proposed meeting. They also possess behavioural intelligence, by making adaptive decisions about next actions according to current environment and conditions. As a consequence, quick and efficient scheduling can be achieved for users located at different places. Experimental results have proved that DAS is especially suitable for large-scale distributed scheduling, and scheduling with complex calendars. The DAS approach has been successfully integrated with a personal assistant agent platform to provide completely automatic meeting scheduling for both stationary and mobile users.

A Movie Recommendation System—An Application of Voting Theory in User Modeling

Our research agenda focuses on building software agents that can employ user modeling techniques to facilitate information access and management tasks. Personal assistant agents embody a clearly beneficial application of intelligent agent technology. A particular kind of assistant agents, recommender systems, can be used to recommend items of interest to users. To be successful, such systems should be able to model and reason with user preferences for items in the application domain. Our primary concern is to develop a reasoning procedure that can meaningfully and systematically tradeoff between user preferences. We have adapted mechanisms from voting theory that have desirable guarantees regarding the recommendations generated from stored preferences. To demonstrate the applicability of our technique, we have developed a movie recommender system that caters to the interests of users. We present issues and initial results based on experimental data of our research that employs voting theory for user modeling, focusing on issues that are especially important in the context of user modeling. We provide multiple query modalities by which the user can pose unconstrained, constrained, or instance-based queries. Our interactive agent learns a user model by gaining feedback aboutits recommended movies from the user. We also provide pro-active information gathering to make user interaction more rewarding. In the paper, we outline the current status of our implementation with particular emphasis on the mechanisms used to provide robust and effective recommendations.

Expert tutoring system for teaching computer programming languages

This paper presents an Expert tutoring system (E-TCL) for teaching computer programming languages through WWW. In this version, many teachers can cooperate together to put the curriculum of one/more computer programming language(s). Their contributions may include: (a) add or modify the commands' structure that will be taught; (b) generate different tutoring dialogs for the same command; and (c) generate different tutoring styles. On the contrary, the students can access the system through WWW, select any language they want to learn as well as the style of presentation they prefer and they can exchange their experiences. A personal assistant agent for teachers (PAA-T), a personal assistant agent for students (PAA-S) with an adaptive interface, and tutoring agent (TA) has been built. The TA resides on the server side and communicates via HTTP and IIOP with both the PAA-T and PAA-S on the clients side. This structure allows customization of the PAA-T and PAA-S to the needs of the teachers and students, without putting extra burden on the server. In addition, this allows having many teacher agents attending to the needs of a single or multiple student agent(s).