Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Personal Service Eco-System and Virtual Personal Assistant: Decentralizing Service Delivery as a User-Centric Paradigm
Authors: Zhongjie Wang (Harbin Institute of Technology, China), Xiaofei Xu (Harbin Institute of Technology, China)
The ultimate goal of service delivery is to realize the “value” expected by customers. User demands are usually coarse-grained, i.e., a demand needs to be fulfilled by the collaboration of multiple services. However, current service delivery paradigm is “Service-Centric”, i.e., massive customers are aggregated around each service, and a customer has to select multiple services and coordinate them manually, which would be rather time-consuming and error-prone. And, it is rather difficult for a customer to completely and timely perceive all the services and their dynamic changes in the global service market in order to make the best choice of services and avoid unanticipated services (and their changes) that would damage his experience during value realization.
To address these issues, our work is to decentralize service delivery relationships by shifting to “customer-centric” paradigm where customers hold the initiative role and massive services are affiliated around each user. This is similar as the idea “Solid” launched by ACM Turing Award Laureate Tim Berners-Lee in October 2018.
We present a concept “Personal Service Ecosystem (PSE)”. Each user has a PSE, and services that he perceives and uses are considered as “species” in his ecosystem. Among these services there are competitions and collaborations. PSE delineates the “external service world” that a customer has explored in terms of his preference. PSE’s structural model and mathematical properties are demonstrated. A method for recovering/visualizing PSE from a user’s personal data is presented, and a method for identifying the evolution of PSE is proposed to detect the preference evolution of a user.
Based on PSE, Virtual Personal Assistant (VPA) is designed with four components: (1) Personal Date Cloud (PDC), a cloud-based location for storing personal data. (2) Personal Sensor (PS), a tool that constantly monitors PSE changes and extracts underlying changes of user preferences. It also monitors changes of user context and predicts implicit demands of the user. (3) Service Collaboration Planner (SCP), a tool that selects optimal services and coordinate them to fulfill an explicit/implicit demand. If services in PSE are insufficient, new external services are recommended to the user. (4) External Service Sensor (ESS), a tool that helps a user monitor changes of external service market and each service. Acquiring such changes timely helps the user adjust his behaviors accordingly and facilitate more accurate service selection.
In recent years ACM Turing Award Laureate Raj Reddy introduced two important concepts in his AI-related talks: Cognition Amplifiers and Guardian Angels. PDC, PS and SCP constitute a user’s Cognition Amplifiers, and ESS is considered as his Guardian Angels. The transformation from “Service-Centric” to “Customer-Centric” and the design of PSE and VPA would significantly improve user experiences by amplifying their cognitions and guarding them for avoiding unanticipated external service changes.