核保方法、装置、设备以及存储介质
By generating a target graph network and using a graph convolutional neural network for automated underwriting, the problems of high cost and poor scalability of manual underwriting are solved, and efficient and accurate underwriting results are achieved.
CN115994829BActive Publication Date: 2026-07-17TENCENT TECHNOLOGY (SHENZHEN) CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TENCENT TECHNOLOGY (SHENZHEN) CO LTD
- Filing Date
- 2021-10-20
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies rely on manual underwriting processes, resulting in high costs, poor scalability, insufficient predictive performance, and a lack of sufficient labeled data that limits model performance.
Method used
By generating a target graph network, and utilizing the examination items, results, and physical status nodes in the medical examination report, combined with a graph convolutional neural network, automated underwriting is performed, reducing the consumption of human and material resources.
Benefits of technology
It enables a highly efficient underwriting process that requires no human intervention, reduces underwriting costs, and improves the accuracy and scalability of underwriting results.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115994829B_ABST
Abstract
本申请公开了一种核保方法、装置、设备以及存储介质，属于计算机技术领域。通过本申请实施例提供的技术方案，在进行核保时，能够获取目标对象的相关信息，基于该相关信息来生成目标图网络，由于目标图网络包括多个与该目标对象相关的节点，那么目标图网络也就能够完整的反映目标对象的情况，通过对目标图网络进行处理就能够得到目标对象的核保结果，核保过程无需人工参与，减少了耗费的人力和物力，降低了核保成本。
Need to check novelty before this filing date? Find Prior Art