KMITL Expo 2026 LogoKMITL 66th Anniversary Logo

The Application of AI Chatbots and Lean Principles to Reduce Waiting Time for Customers and Vendors to Enhance Service Quality

The Application of AI Chatbots and Lean Principles to Reduce Waiting Time for Customers and Vendors to Enhance Service Quality

Abstract

This research aims to reduce the time required to resolve customer issues by focusing on improvements based on lean principles and the application of technology. The researcher conducts the case study at Nexter Digital and Solution Co., Ltd. to enhance workflows, establish new work standards, and integrate Bot technology into the processes to reduce resolution time and set new performance benchmarks for the company. The research proposes key ideas, such as identifying the root cause of problems, reducing redundant processes, implementing Lean methodologies, and applying technology to streamline operations. The research identifies two main issues to be resolved. The first involves addressing customer complaints, where the results show that the average resolution time reduces from 5 days to 3 days, representing a 38% decrease. The second issue involves solving problems for vendors, where the results show that the average response time reduces from 20 minutes to within 1 minute, a 98.5% decrease. The findings from both cases not only improve customer service but also establish a new standard for responding to and resolving internal issues more efficiently.

Objective

ในยุคที่เทคโนโลยีและการแข่งขันทางธุรกิจพัฒนาอย่างรวดเร็ว คุณภาพการบริการเป็นปัจจัยสำคัญที่ทำให้บริษัทเติบโตอย่างยั่งยืน โดยผู้วิจัยได้เล็งเห็นความสำคัญของการยกระดับคุณภาพการบริการเพื่อตอบสนองลูกค้าของทางบริษัท เน็กซเตอร์ ดิจิตอล แอนด์ โซลูชั่น จำกัด โดยประยุกต์ใช้แนวคิด Lean เพื่อลดความสูญเสียในกระบวนการทำงาน พร้อมกับนำเทคโนโลยีบอทเข้ามาช่วยเสริมในการแก้ไขปัญหา ซึ่งช่วยลดเวลาการจัดการปัญหาได้อย่างมีประสิทธิภาพและเพิ่มความพึงพอใจของลูกค้า โดยนำเทคโนโลยีสมัยใหม่ เช่น AI และระบบอัตโนมัติ ยังช่วยให้การทำงานมีความรวดเร็วและแม่นยำ ลดความผิดพลาดจากมนุษย์ อีกทั้งยังช่วยวิเคราะห์ข้อมูลเพื่อการตัดสินใจที่ดีขึ้น จากการศึกษา พบว่าบริษัทยังขาดกระบวนการทำงานที่ชัดเจน มีเวลาเฉลี่ยในการแก้ปัญหาที่ค่อนข้างนาน และพนักงานมีภาระงานที่มากเกินไป การปรับปรุงกระบวนการทำงานจึงเน้นการสร้างผังขั้นตอนที่ชัดเจน ลดเวลาการแก้ไขปัญหาให้เหมาะสม และปรับภาระงานของพนักงานให้เหมาะสม เพื่อลดระยะเวลาการรอคอยและเพิ่มความพึงพอใจให้กับลูกค้า

Other Innovations

CLASSIFICATION OF OTITIS MEDIA TYPE USING OTOSCOPIC IMAGES

คณะวิทยาศาสตร์

CLASSIFICATION OF OTITIS MEDIA TYPE USING OTOSCOPIC IMAGES

Otitis Media is an infection of the middle ear that can occur in individuals of all ages. Diagnosis typically involves analyzing images taken with an otoscope by specialized physicians, which relies heavily on medical experience to expedite the process. This research introduces computer vision technology to assist in the preliminary diagnosis, aiding expert decision-making. By utilizing deep learning techniques and convolutional neural networks, specifically the YOLOv8 and Inception v3 architectures, the study aims to classify the disease and its five characteristics used by physicians: color, transparency, fluid, retraction, and perforation. Additionally, image segmentation and classification methods were employed to analyze and predict the types of Otitis Media, which are categorized into four types: Otitis Media with Effusion, Acute Otitis Media with Effusion, Perforation, and Normal. Experimental results indicate that the classification model performs moderately well in directly classifying Otitis Media, with an accuracy of 65.7%, a recall of 65.7%, and a precision of 67.6%. Moreover, the model provides the best results for classifying the perforation characteristic, with an accuracy of 91.8%, a recall of 91.8%, and a precision of 92.1%. In contrast, the classification model that incorporates image segmentation techniques achieved the best overall performance, with an mAP50-95 of 79.63%, a recall of 100%, and a precision of 99.8%. However, this model has not yet been tested for classifying the different types of Otitis Media.

Read more
WALL DEFECT DETECTION USING IMAGE PROCESSING TECHNIQUES

คณะวิศวกรรมศาสตร์

WALL DEFECT DETECTION USING IMAGE PROCESSING TECHNIQUES

This project aims to develop an AI-powered system for detecting and classifying wall cracks using image processing. It identifies different crack types, assesses severity, and ensures accuracy across various image conditions. The goal is to support preventive maintenance by enabling early detection of structural issues, reducing repair costs, and improving safety.

Read more
Wildland Fire Fighter Suit

คณะสถาปัตยกรรม ศิลปะและการออกแบบ

Wildland Fire Fighter Suit

The forest firefighting suit consists of the following components and uses: The forest firefighting suit is designed and developed to be suitable for the behavior of the officers and the conditions of the work area, consisting of a shirt and pants. The material used in the sewing of the suit is aramid fabric, which has the property of being able to prevent the spread of fire, to prevent the officers from burning while performing their duties in the event that the forest fire spreads close to them, which is different from the current suits that cannot prevent fires. The shirt is designed with a mesh on the side of the body to release internal heat so that air can circulate well. The sleeves at the elbows have a support point to prevent contact with the ground or obstacles. The collar has a slot for a portable fan and a fan air circulation channel on the back, which can be turned on while performing forest firefighting duties, helping to prevent the body temperature from getting too hot, reducing the risk of heatstroke. When the fan battery runs out, it can be removed for charging and put back in when needed. The pants are designed with mesh on the inside or in blind spots to release internal heat so that air can circulate well. The pants at the knees have a support point to prevent contact with the ground or obstacles. The forest firefighting suit, consisting of a shirt and pants, has been designed and developed to be able to be produced domestically, reducing imports from abroad

Read more