Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

End-Cloud Collaboration Framework for Advanced AI Customer Service in E-commerce

Liangyu Teng, Yang Liu, Jing Liu, Liang Song

TL;DR

This paper implements in-depth corpus collection and introduces an online evolutive learning strategy that enables the end model to continuously iterate and upgrade based on guidance from the cloud model and real-time user feedback, establishing a practical benchmark for customer service model development.

Abstract

In recent years, the e-commerce industry has seen a rapid increase in the demand for advanced AI-driven customer service solutions. Traditional cloud-based models face limitations in terms of latency, personalized services, and privacy concerns. Furthermore, end devices often lack the computational resources to deploy large AI models effectively. In this paper, we propose an innovative End-Cloud Collaboration (ECC) framework for advanced AI customer service in e-commerce. This framework integrates the advantages of large cloud models and mid/small-sized end models by deeply exploring the generalization potential of cloud models and effectively utilizing the computing power resources of terminal chips, alleviating the strain on computing resources to some extent. Specifically, the large cloud model acts as a teacher, guiding and promoting the learning of the end model, which significantly reduces the end model's reliance on large-scale, high-quality data and thereby addresses the data bottleneck in traditional end model training, offering a new paradigm for the rapid deployment of industry applications. Additionally, we introduce an online evolutive learning strategy that enables the end model to continuously iterate and upgrade based on guidance from the cloud model and real-time user feedback. This strategy ensures that the model can flexibly adapt to the rapid changes in application scenarios while avoiding the uploading of sensitive information by performing local fine-tuning, achieving the dual goals of privacy protection and personalized service. %We make systematic contributions to the customized model fine-tuning methods in the e-commerce domain. To conclude, we implement in-depth corpus collection (e.g., data organization, cleaning, and preprocessing) and train an ECC-based industry-specific model for e-commerce customer service.

End-Cloud Collaboration Framework for Advanced AI Customer Service in E-commerce

TL;DR

This paper implements in-depth corpus collection and introduces an online evolutive learning strategy that enables the end model to continuously iterate and upgrade based on guidance from the cloud model and real-time user feedback, establishing a practical benchmark for customer service model development.

Abstract

In recent years, the e-commerce industry has seen a rapid increase in the demand for advanced AI-driven customer service solutions. Traditional cloud-based models face limitations in terms of latency, personalized services, and privacy concerns. Furthermore, end devices often lack the computational resources to deploy large AI models effectively. In this paper, we propose an innovative End-Cloud Collaboration (ECC) framework for advanced AI customer service in e-commerce. This framework integrates the advantages of large cloud models and mid/small-sized end models by deeply exploring the generalization potential of cloud models and effectively utilizing the computing power resources of terminal chips, alleviating the strain on computing resources to some extent. Specifically, the large cloud model acts as a teacher, guiding and promoting the learning of the end model, which significantly reduces the end model's reliance on large-scale, high-quality data and thereby addresses the data bottleneck in traditional end model training, offering a new paradigm for the rapid deployment of industry applications. Additionally, we introduce an online evolutive learning strategy that enables the end model to continuously iterate and upgrade based on guidance from the cloud model and real-time user feedback. This strategy ensures that the model can flexibly adapt to the rapid changes in application scenarios while avoiding the uploading of sensitive information by performing local fine-tuning, achieving the dual goals of privacy protection and personalized service. %We make systematic contributions to the customized model fine-tuning methods in the e-commerce domain. To conclude, we implement in-depth corpus collection (e.g., data organization, cleaning, and preprocessing) and train an ECC-based industry-specific model for e-commerce customer service.

Paper Structure

This paper contains 11 sections, 1 equation, 3 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. End-Cloud Collaboration
  4. Large Language Models
  5. Fine-tuning Technicals
  6. End-Cloud Collaboration Framework for Advanced E-commerce Customer Service Model
  7. Experiment
  8. Datasets
  9. Environment and Parameter Setup
  10. Experimental Results
  11. Conclusion

Figures (3)

  • Figure 1: ECC framework for advanced e-commerce customer service model.
  • Figure 2: Examples of dialogue results from the end model ChatGLM3-6B.
  • Figure 3: Visualization results of the end model ChatGLM3-6B under different fine-tuning methods. Here, (a) represents the original model, (b) represents the model fine-tuned with Prefix-Tuning after 3,000 steps, (c) represents the model fine-tuned with P-Tuning v2 after 3,000 steps, (d) represents the model fine-tuned with LoRA after 3,000 steps, (e) represents the model fine-tuned with LoRA after 5,000 steps, and (f) represents the model fine-tuned with LoRA after 15,000 steps. Besides, the input 1-5 are the same as the ones in Table \ref{['tab:results']} with the same order.