scholarly journals Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use

2019 ◽  
Vol 7 ◽  
pp. 375-386
Author(s):  
Janarthanan Rajendran ◽  
Jatin Ganhotra ◽  
Lazaros C. Polymenakos
Keyword(s):  
Customer Service ◽  
User Behavior ◽  
Wait Time ◽  
Test Time ◽  
Dialog Systems ◽  
User Behaviors ◽  
Human Agent ◽  
Task Success ◽  
End To End ◽  
Reduce Wait Time

Neural end-to-end goal-oriented dialog systems showed promise to reduce the workload of human agents for customer service, as well as reduce wait time for users. However, their inability to handle new user behavior at deployment has limited their usage in real world. In this work, we propose an end-to-end trainable method for neural goal-oriented dialog systems that handles new user behaviors at deployment by transferring the dialog to a human agent intelligently. The proposed method has three goals: 1) maximize user’s task success by transferring to human agents, 2) minimize the load on the human agents by transferring to them only when it is essential, and 3) learn online from the human agent’s responses to reduce human agents’ load further. We evaluate our proposed method on a modified-bAbI dialog task, 1 which simulates the scenario of new user behaviors occurring at test time. Experimental results show that our proposed method is effective in achieving the desired goals.

scholarly journals Learning Conversational Systems that Interleave Task and Non-Task Content

2017 ◽  
Author(s):  
Zhou Yu ◽  
Alexander Rudnicky ◽  
Alan Black
Keyword(s):  
Customer Service ◽  
Service Providers ◽  
Dialog Systems ◽  
Dialog System ◽  
Task Success ◽  
Personal Assistants ◽  
Task Oriented ◽  
Smooth Transitions ◽  
Oriented System ◽  
Task Content

Task-oriented dialog systems have been applied in various tasks, such as automated personal assistants, customer service providers and tutors. These systems work well when users have clear and explicit intentions that are well-aligned to the systems' capabilities. However, they fail if users intentions are not explicit.To address this shortcoming, we propose a framework to interleave non-task content (i.e.everyday social conversation) into task conversations. When the task content fails, the system can still keep the user engaged with the non-task content. We trained a policy using reinforcement learning algorithms to promote long-turn conversation coherence and consistency, so that the system can have smooth transitions between task and non-task content.To test the effectiveness of the proposed framework, we developed a movie promotion dialog system. Experiments with human users indicate that a system that interleaves social and task content achieves a better task success rate and is also rated as more engaging compared to a pure task-oriented system.

Design Approach Does Affect Customer Behavior: “Action-Objects” Increase “Cut-Throughs”

2002 ◽  
Vol 46 (4) ◽  
pp. 578-582
Author(s):  
Robert R. Bushey ◽  
Kurt M. Joseph ◽  
John M. Martin
Keyword(s):  
Customer Service ◽  
Interface Design ◽  
User Behavior ◽  
Usability Study ◽  
User Behaviors ◽  
Specific Object ◽  
General Object ◽  
Design Style ◽  
The Impact ◽  
Ivr Systems

This paper investigates the impact of touch-tone IVR design styles on user behavior. The design of the touch-tone IVR systems is a critical component of delivering customer service. A well-designed system allows the customers to accomplish their goals and sets a positive tone to their interaction with the organization. Four design styles were considered: Action-Specific Object, Action-General Object, Specific Object, and General Object. Three user behaviors were considered: Cut-Through, Full Menu, and Beyond Full Menu. A usability study was conducted to quantify the impact of design styles on user behavior. Results indicate that design style does impact user behavior. The Action-Specific Object style produced the most Cut-Through behaviors and the fewest Beyond Full Menu behaviors compared to the other design styles. The results from this paper suggest that the interface design style should match the customer's mental model.

Mobile User Behaviors in China

2015 ◽  
pp. 1110-1128
Author(s):  
Minglong Lei ◽  
Weidong Liu ◽  
Yusong Gao ◽  
Tingshao Zhu
Keyword(s):  
Mobile Phones ◽  
User Behavior ◽  
Mobile User ◽  
User Behavior Analysis ◽  
Related Literature ◽  
User Behaviors ◽  
Analysis Process ◽  
Mobile Industry ◽  
The Mainland Of China ◽  
The Relationship

The development of the mobile industry makes it necessary for scholars to study mobile user behaviors in the mainland of China. This article is divided into three main parts after a brief introduction of the current Chinese mobile phone market. The first part is to demonstrate mobile use and its influencing factors in the mainland of China, and then to determine the mostly studied mobile usages among those articles. The second part pays attention to the effect brought by the use of mobile phones, and then checks the relationship between mobile addiction and other social behaviors. The last part is to illustrate the methods employed in the mobile user behavior analysis. After stating the analysis process of user behaviors, the authors attempted to summarize the main features extracted from data mining technology. Finally, the authors put forward some possible directions under the topic of mobile user behavior after careful review of the related literature.

Knowledge Discovery from Online Communities

Data Mining ◽  
2013 ◽  
pp. 1230-1252
Author(s):  
Luca Cagliero ◽  
Alessandro Fiori
Keyword(s):  
Data Mining ◽  
Social Networks ◽  
Social Network ◽  
User Behavior ◽  
Network Models ◽  
Social Model ◽  
User Generated Content ◽  
Growth Trend ◽  
User Behaviors ◽  
Application Systems

This chapter presents an overview of social network features such as user behavior, social models, and user-generated content to highlight the most notable research trends and application systems built over such appealing models and online media data. It first describes the most popular social networks by analyzing the growth trend, the user behaviors, the evolution of social groups and models, and the most relevant types of data continuously generated and updated by the users. Next, the most recent and valuable applications of data mining techniques to social network models and user-generated content are presented. Discussed works address both social model extractions tailored to semantic knowledge inference and automatic understanding of the user-generated content. Finally, prospects of data mining research on social networks are provided as well.

scholarly journals Improving the wait time to triage at the emergency department

2020 ◽  
Vol 9 (1) ◽  
pp. e000708 ◽  
Author(s):  
Yuzeng Shen ◽  
Lin Hui Lee
Keyword(s):  
Emergency Department ◽  
Wait Time ◽  
Baseline Period ◽  
Quality Improvement Effort ◽  
Nurse Clinician ◽  
Reduce Wait Time ◽  
Key Steps ◽  
Improvement Effort ◽  
Period Duration ◽  
Nursing Manpower

Triaging of patients at the emergency department (ED) is one of the key steps prior to initiation of doctor consult. To improve the overall wait time to consultation, we have identified the need to reduce the wait time to triage for ED patients. We seek to determine if the implementation of a series of plan, do, study, act (PDSA) cycles would improve the wait time to triage within 1 year. The interventions related to the PDSA cycles include the refining of triage criteria, ‘eyeball’ triage by senior nurses to facilitate direct bedding of patients, formation of a triage nurse clinician role, and a needs analysis of required nursing manpower. The baseline period for this study was from January 2017 to April 2017, with the results following implementation of the respective PDSA cycles sequentially tracked from May 2017 to March 2019. There was an improvement in the wait time to triage from a baseline duration of 18 min to the postimplementation period duration of 13 min, with a 25% decrease in variance from 16 to 12 min. The improvements were sustained. Strategies to further reduce wait time to triage at the ED are discussed. We also highlight the importance of adequate triage manpower, data-driven decision making and continued engagement of stakeholders in enabling positive outcomes from this quality improvement effort.

Impact of bookshelf locations using eye-tracking methodology

2020 ◽  
Vol 41 (8/9) ◽  
pp. 617-629
Author(s):  
Sho Sato ◽  
Yukari Eto ◽  
Kotomi Iwaki ◽  
Tadashi Oyanagi ◽  
Yu Yasuma
Keyword(s):  
Eye Tracking ◽  
User Behavior ◽  
Public Library ◽  
Gaze Behavior ◽  
Content Type ◽  
User Behaviors ◽  
Significant Relationships ◽  
Vertical Location ◽  
The Right ◽  
The Impact

PurposeThis study aimed to understand better the user gaze behavior on bookshelves using eye-tracking technology.Design/methodology/approachAn eye-tracking experiment in a public library with 11 participants was performed. The impact of vertical shelf location of books on the number of times the books are looked at, the impact of horizontal location and the relationship between user behavior and location impact were examined by the findings.FindingsThe results showed that the vertical location of books has a significant impact on the number of times the books are looked at. More than 80% of the time spent looking at bookshelves was spent on books on the top to fourth rows. It was also revealed that the horizontal location of books has a little impact. Books located on the left side of shelves will be looked at significantly more often than those on the right side. No significant relationships between type of user behaviors and location impact were observed.Originality/valueThe study explored the impact of the vertical location of books on time spent looking at bookshelves using eye-tracking methodology. Few published studies do such experiments to address user gaze behavior on bookshelves. The study explored that the vertical location of books has a great impact, and horizontal location has a little impact on user gaze behavior.

Success in Business-to-Business E-Commerce

2011 ◽  
pp. 127-145
Author(s):  
Pauline Ratnasingham
Keyword(s):  
Customer Service ◽  
Operating Cost ◽  
Cost Savings ◽  
The Internet ◽  
Administrative Costs ◽  
Trading Partners ◽  
End To End ◽  
Internal Networks ◽  
Common Architecture ◽  
Business To Business

The growth of business-to-business e-commerce has highlighted the importance of computer and communications technologies and trading partner trust for the development and maintenance of business relationships. Cisco Systems Incorporation, an international company, is now the second largest company in the world, behind Microsoft. Its solid financial performance is partly due to its early focus on the Internet as a channel to cut administrative costs, and boost customer service satisfaction. Cisco International provides end-to-end networking solutions which customers use to build a unified information infrastructure of their own, or to connect to someone else’s network. The end-to-end networking solutions provide a common architecture that delivers consistent network services to all users (Cisco Fact Sheet, 2000). Cisco network solutions connect people, computing devices and computer networks, allowing trading partners to access or transfer information without regard to differences in time, place or type of computer systems. By using networked applications over the Internet on its own internal networks, Cisco globally is gaining contributions of at least NZ$825 million a year in operating cost savings and revenue enhancements (Cisco Newsroom, 2001).

They Know What You Will Do Next Click

2020 ◽  
pp. 100-122
Author(s):  
Serra Çelik
Keyword(s):  
Focus Group ◽  
User Behavior ◽  
Web Usage Mining ◽  
Web Log ◽  
Web Usage ◽  
User Behaviors ◽  
Log Files ◽  
The Web

This chapter focuses on predicting web user behaviors. When web users enter a website, every move they make on that website is stored as web log files. Unlike the focus group or questionnaire, the log files reflect real user behavior. It can easily be said that having actual user behavior is a gold value for the organizations. In this chapter, the ways of extracting user patterns (user behavior) from the log files are sought. In this context, the web usage mining process is explained. Some web usage mining techniques are mentioned.

scholarly journals Learning Personalized End-to-End Goal-Oriented Dialog

2019 ◽  
Vol 33 ◽  
pp. 6794-6801 ◽  
Author(s):  
Liangchen Luo ◽  
Wenhao Huang ◽  
Qi Zeng ◽  
Zaiqing Nie ◽  
Xu Sun
Keyword(s):  
User Satisfaction ◽  
State Of The Art ◽  
User Preferences ◽  
Task Completion ◽  
Dialog Systems ◽  
Performance Improvements ◽  
Human Evaluation ◽  
Proposed Model ◽  
End To End ◽  
Qualitative Performance

Most existing works on dialog systems only consider conversation content while neglecting the personality of the user the bot is interacting with, which begets several unsolved issues. In this paper, we present a personalized end-to-end model in an attempt to leverage personalization in goal-oriented dialogs. We first introduce a PROFILE MODEL which encodes user profiles into distributed embeddings and refers to conversation history from other similar users. Then a PREFERENCE MODEL captures user preferences over knowledge base entities to handle the ambiguity in user requests. The two models are combined into the PERSONALIZED MEMN2N. Experiments show that the proposed model achieves qualitative performance improvements over state-of-the-art methods. As for human evaluation, it also outperforms other approaches in terms of task completion rate and user satisfaction.

scholarly journals Nonindependent Session Recommendation Based on Ordinary Differential Equation

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Zhenyu Yang ◽  
Mingge Zhang ◽  
Guojing Liu ◽  
Mingyu Li
Keyword(s):  
Neural Network ◽  
Differential Equation ◽  
Neural Networks ◽  
Ordinary Differential Equation ◽  
Differential Equations ◽  
Ordinary Differential Equations ◽  
Deep Neural Networks ◽  
Semantic Information ◽  
User Behavior ◽  
User Behaviors

The recommendation method based on user sessions is mainly to model sessions as sequences in the assumption that user behaviors are independent and identically distributed, and then to use deep semantic information mining through Deep Neural Networks. Nevertheless, user behaviors may be a nonindependent intention at irregular points in time. For example, users may buy painkillers, books, or clothes for different reasons at different times. However, this has not been taken seriously in previous studies. Therefore, we propose a session recommendation method based on Neural Differential Equations in an attempt to predict user behavior forward or backward from any point in time. We used Ordinary Differential Equations to train the Graph Neural Network and could predict forward or backward at any point in time to model the user's nonindependent sessions. We tested for four real datasets and found that our model achieved the expected results and was superior to the existing session-based recommendations.

Sign in / Sign up

Export Citation Format

Share Document