CNIPA.AI
Patent applicant records

APPLICANTS

Original name record: 北京鼎兴达信息科技股份有限公司

Browse source applicant names and unchanged name fields from imported patent records.

These are name-based results, not verified legal entities. Identical names may refer to different people or organizations; aliases and historical names are not merged.

This page matches the complete original name field. It may contain multiple applicants or another recorded party role. Name boundaries and legal identities have not been verified; punctuation is preserved, not split.

1 indexed patent records

№ CN121352140AInvention
Active

一种基于深度学习的班列到港预测方法

本发明公开了一种基于深度学习的班列到港预测方法，包括：步骤一：采集班列运行轨迹数据与运行环境数据；步骤二：进行特征编码，生成轨迹特征序列和环境特征序列；步骤三：将轨迹特征序列和环境特征序列输入至改进型AttentionTTE网络提取轨迹特征并融合环境语义，生成环境‑轨迹特征向量；步骤四：基于环境‑轨迹特征向量进行多任务预测；步骤五：基于多任务预测结果，执行调度控制操作；步骤六：实时采集反馈数据，并通过预测误差损失与目标感知对比损失联合优化改进型AttentionTTE网络和模型参数；步骤七：将优化后的模型参数进行版本并部署。本发明提升了班列到港预测的准确性与调度响应的智能化水平。

❖北京鼎兴达信息科技股份有限公司李慧; 王海燕; 傅卫国; 时圣师; 纪彩庆§ 1/9 ClaimsG06Q 10/04 (2023.01), G06F 18/213 (2023.01), G06F 18/2415 (2023.01) +77