Power supply service command system decision recommendation method and system based on intelligent agent

The intelligent agent-based supply service command system addresses the limitations of semi-automated systems by using Lora and reinforcement learning to enhance intent recognition and decision recommendations, improving accuracy and user interaction in supply service command systems.

CN119721750APending Publication Date: 2025-03-28STATE GRID FUJIAN ELECTRIC POWER RES INST +3
12 Cites 0 Cited by

Patent Information

Application Number
CN202411743076.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-29
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

Current supply service command systems are semi-automated and rely heavily on expert experience, with existing intent recognition technologies requiring extensive data annotation and struggling to accurately classify user requests in complex scenarios, such as customer service interactions in e-commerce platforms.

Method used

A method and system utilizing an intelligent agent to preprocess and train on supply service command system data, integrating Lora technology and reinforcement learning to identify user intent and generate decision recommendations through a language model, enabling automated intent recognition and streamlined user interactions.

Benefits of technology

The system enhances intent recognition accuracy and user interaction experience by leveraging deep learning and reinforcement learning, allowing for adaptive responses and continuous improvement through dynamic feedback, thereby improving service quality and user satisfaction.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a power supply service command system decision recommendation method and system based on an intelligent agent. The method comprises the following steps: acquiring and preprocessing data of a power supply service command system; training a preset agent through the preprocessed power supply service command system data, and identifying an intention in the text through the trained agent; acquiring text data input to the power supply service command system by a user, and identifying an intention by using an intelligent agent; calling a database of the power supply service command system, acquiring knowledge data corresponding to the identified intention, generating prompt words from the acquired knowledge data and the corresponding intention, and outputting the prompt words to a power supply service command model based on a language large model; and the power supply service command model outputs a decision recommendation result according to the input knowledge data and the corresponding intention.
Need to check novelty before this filing date? Find Prior Art