scholarly journals Extracting Latent Beliefs and using Epistemic Reasoning to Tailor a Chatbot

Author(s):  
Amit Sangroya ◽  
C. Anantaram ◽  
Pratik Saini ◽  
Mrinal Rawat

During dialog with a customer for addressing his/her complaint the chatbot may pose questions or observations based on its underlying model. Sometimes the questions or observations posed may not be relevant given the nature of complaint and the current set of beliefs that the customer holds. In this paper we present a framework to build conversation system that addresses customer complaints in a meaningful manner using domain understanding, opinion analysis and epistemic reasoning. Extraction of latent beliefs assists in performing epistemic reasoning to maintain a meaningful conversation with the customer.

2019 ◽  
Vol 1 (2) ◽  
pp. 96
Author(s):  
Septiyan Budi Santoso ◽  
Heribertus Budi Santoso ◽  
Ana Komari

This study aims to determine how high the level of customer satisfaction with the service of PLN Rayon Kediri Kota, to determine the quality of service to customer satisfaction PLN Rayon Kediri Kota, to determine the response of the PLN Kediri Kota in dealing with customer complaints. This research was conducted in the work area of PLN Rayon Kediri Kota. The research time was on March 18, 2017 to March 24, 2017. In writing this thesis, the author uses primary data collection techniques, namely by distributing questionnaires to PLN Rayon Kediri Kota customers who come to the payment counter. and PLN District Kediri City services. Based on the results of the research, the quality of service conducted by PLN District Kediri Kota is sufficient to satisfy its customers, as evidenced by the results of a questionnaire that has been conducted on 100 respondents of PLN Rayon Kediri City.Penelitian ini bertujuan untuk mengetahui seberapa tinggi tingkat kepuasan pelanggan terhadap pelayanan PLN Rayon Kediri Kota, Untuk mengetahui kualitas pelayanan terhadap kepuasan pelanggan PLN Rayon Kediri Kota, Untuk mengetahui respons pihak PLN Kediri Kota dalam menghadapi keluhan pelanggannya. Penelitian ini dilakukan di wilayah kerja PLN Rayon Kediri Kota. Waktu penelitian pada tanggal 18 Maret 2017 sampai dengan 24 Maret 2017. Dalam penulisan skripsi ini, penulis menggunakan teknik pengumpulan data primer yaitu dengan membagikan kuesioner terhadap pelanggan PLN Rayon Kediri Kota yang datang ke loket pembayaran dan pelayanan PLN Rayon Kediri Kota. Berdasarkan hasil penelitian kualitas pelayanan yang dilakukan oleh PLN Rayon Kediri Kota sudah cukup memuaskan pelanggannya terbukti dengan hasil kuesioner yang telah dilakukan terhadap 100 responden PLN Rayon Kediri Kota.


2018 ◽  
Vol 3 (1) ◽  
pp. 001
Author(s):  
Zulhendra Zulhendra ◽  
Gunadi Widi Nurcahyo ◽  
Julius Santony

In this study using Data Mining, namely K-Means Clustering. Data Mining can be used in searching for a large enough data analysis that aims to enable Indocomputer to know and classify service data based on customer complaints using Weka Software. In this study using the algorithm K-Means Clustering to predict or classify complaints about hardware damage on Payakumbuh Indocomputer. And can find out the data of Laptop brands most do service on Indocomputer Payakumbuh as one of the recommendations to consumers for the selection of Laptops.


2017 ◽  
pp. 96-103 ◽  
Author(s):  
Gillian Eggleston ◽  
Isabel Lima ◽  
Emmanuel Sarir ◽  
Jack Thompson ◽  
John Zatlokovicz ◽  
...  

In recent years, there has been increased world-wide concern over residual (carry-over) activity of mostly high temperature (HT) and very high temperature (VHT) stable amylases in white, refined sugars from refineries to various food and end-user industries. HT and VHT stable amylases were developed for much larger markets than the sugar industry with harsher processing conditions. There is an urgent need in the sugar industry to be able to remove or inactivate residual, active amylases either in factory or refinery streams or both. A survey of refineries that used amylase and had activated carbon systems for decolorizing, revealed they did not have any customer complaints for residual amylase. The use of high performance activated carbons to remove residual amylase activity was investigated using a Phadebas® method created for the sugar industry to measure residual amylase in syrups. Ability to remove residual amylase protein was dependent on the surface area of the powdered activated carbons as well as mixing (retention) time. The activated carbon also had the additional benefit of removing color and insoluble starch.


2014 ◽  
Vol 36 (8) ◽  
pp. 1650-1658
Author(s):  
Yu-Ming LIN ◽  
Tao ZHU ◽  
Xiao-Ling WANG ◽  
Ao-Ying ZHOU

2021 ◽  
Vol 1757 (1) ◽  
pp. 012116
Author(s):  
Jiaqian Zhou ◽  
Jihou Wang ◽  
Qintao Li ◽  
Yulian Wen ◽  
Yan Zhang ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document