The use of virtual agents (bots) has become essential for providing online assistance to customers. However, even though a lot of effort has been dedicated to the research, development, and deployment of such virtual agents, customers are frequently frustrated with the interaction with the virtual agent and require a human instead. We suggest that a holistic approach, combining virtual agents and human operators working together, is the path to providing satisfactory service. However, implementing such a holistic customer service system will not, and cannot, be achieved using any single AI technology or branch. Rather, such a system will inevitably require the integration of multiple and diverse AI technologies, including natural language processing, multi-agent systems, machine learning, reinforcement learning, and behavioral cloning; in addition to integration with other disciplines such as psychology, business, sociology, economics, operation research, informatics, computer-human interaction, and more. As such, we believe this customer service application offers a rich domain for experimentation and application of multidisciplinary AI. In this paper, we introduce the holistic customer service application and discuss the key AI technologies and disciplines required for a successful AI solution for this setting. For each of these AI technologies, we outline the key scientific questions and research avenues stemming from this setting. We demonstrate that integrating technologies from different fields can lead to a cost-effective successful customer service center. The challenge is that there is a need for several communities, each with its own language and modeling techniques, different problem-solving methods, and different evaluation methodologies, all of which need to work together. Real cooperation will require the formation of joint methodologies and techniques that could improve the service to customers, but, more importantly, open new directions in cooperation of diverse communities toward solving joint difficult tasks.

Call centers, in which human operators attend clients using textual chat, are very common in modern e-commerce. Training enough skilled operators who are able to provide good service is a challenge. We propose a methodology for the development of an assisting agent that provides online advice to operators while they attend clients. The agent is easy-to-build and can be introduced to new domains without major effort in design, training and organizing sknowledge of the professional discipline. We demonstrate the applicability of the system in an experiment that realizes its full life-cycle on a specific domain, and analyze its capabilities.

Robot teams are very useful in patrol tasks, where the robots are required to repeatedly visit a target area in order to detect an adversary. In this work we examine the Fence Patrol problem, in which the robots must travel back and forth along an open polyline and the adversary is aware of the robots' patrol strategy. Previous work has suggested non-deterministic patrol schemes, characterized by a uniform policy along the entire area, guaranteeing that the minimal probability of penetration detection throughout the area is maximized. We present a patrol strategy with a non-uniform policy along different points of the fence, based on the location and other properties of the point. We explore this strategy in different kinds of tracks and show that the minimal probability of penetration detection achieved by this non-uniform (variant) policy is higher than former policies. We further consider applying this model in multi-robot scenarios, exploiting robot cooperation to enhance patrol efficiency. We propose novel methods for calculating the variant values, and demonstrate their performance empirically.

Obtaining an objective assessment of pain is an important challenge for clinicians. The purpose of this study is to examine the connections between subjective reports of pain and measureable biosignals of human speech prosody, as a step towards coping with this challenge. Patients reporting pain were voice-recorded to attain reports on different levels of pain. Recording was done in the patients' natural environment at the medical center. Features were extracted from the voice-recordings, including features that were exclusively developed for this study. A machine-learning based classification process was performed in order to distinguish between samples with "no significant pain" and with "significant pain" reported. This classification process distinguished well between the two categories. Moreover, features developed during this study improved classification results in comparison to classification based solely on knownfeatures. Results indicate that there is evidence of a connection between measureable biosignal parameters of speech and the simultaneous self-reported pain level. This finding might be useful for developing future methods to more objective assessment of pain.