Autonomous construction method of report generation agent based on knowledge enhanced large model

By constructing a domain knowledge graph and progressive knowledge injection, combined with supervised fine-tuning of task planning and tool call demonstration sample libraries and reinforcement learning training, the problem of insufficient domain knowledge fusion and adaptability to complex tasks of existing intelligent agents is solved, and the intelligent agent can make efficient autonomous decisions and generate reports in the business environment.

CN122114187BActive Publication Date: 2026-07-07西安圣瞳科技有限公司
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
西安圣瞳科技有限公司
Filing Date
2026-04-28
Publication Date
2026-07-07

AI Technical Summary

Technical Problem

Existing report generation agents are insufficient in terms of domain knowledge integration and adaptability to complex tasks, making it difficult to accurately match business needs and make autonomous decisions.

Method used

By constructing a domain knowledge graph, integrating domain knowledge into a general large language model using a progressive knowledge injection algorithm, and combining task planning with a sample library of tool calls for supervised fine-tuning, reinforcement learning training is conducted in multiple rounds of complex task environments to form an agent behavior experience pool for near-end policy optimization.

Benefits of technology

It improves the ability of intelligent agents to adapt to business domain knowledge, enhances the rationality and flexibility of autonomous decision-making, and enables efficient report generation in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122114187B_ABST
    Figure CN122114187B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of artificial intelligence large model, specifically to a report generation agent autonomous construction method based on knowledge enhanced large model, which comprises: knowledge extraction on business domain structured documents and unstructured texts and construction of domain knowledge graph, adoption of an improved progressive knowledge injection algorithm to integrate knowledge into general large language model parameters to form a knowledge enhanced base model. Extraction of task planning sequences and operation trajectories generated by historical reports to construct a demonstration sample library, and fine tuning of a primary report generation agent through a behavior cloning strategy. A reinforcement learning training field containing multiple rounds of complex tasks and diversified environmental disturbances is built, interactive data is collected to form a behavior experience pool, decision parameters are iteratively updated based on proximal policy optimization, and autonomous construction of the agent is completed. This method can improve the effect of domain knowledge fusion and enhance the task planning and autonomous decision-making ability of the agent in complex scenarios.
Need to check novelty before this filing date? Find Prior Art