The invention provides a traffic prediction method based on a large model, and belongs to the technical field of intelligent traffic. The invention aims to realize efficient prediction of traffic data through an innovative space-time graph word segmentation device (STG-Tokenizer) and an adapter (STG-Adapter) by utilizing the strong semantic understanding and reasoning capability of the LLMs. The method mainly comprises the following parts: STG construction, an STG word segmentation device, an STG adapter, parameter fine tuning, model prediction, and performance evaluation and application. The word segmentation device module converts complex space-time graph data into simple marks and captures corresponding space and time relations. And the adapter module bridges the marked data with the LLMs through a linear coding layer and a decoding layer, so that the LLMs can understand the semantics of the traffic data. And the prediction model carries out prediction analysis on the traffic data by using the finely adjusted LLMs in combination with the STG-Tokenizer and the STG-Adapter. By designing the traffic prediction method based on the LLMs, the accuracy of traffic prediction is improved, and the method has wide application prospects and practical application value.

    本发明提供了一种基于大模型的交通预测方法,属于智慧交通技术领域。本发明旨在利用LLMs的强大语义理解和推理能力,通过创新的空间‑时间图分词器(STG‑Tokenizer)和适配器(STG‑Adapter),实现对交通数据的高效预测。本方法主要包括以下部分,STG构建、STG分词器、STG适配器、参数微调、预测模型、性能评估与应用。分词器模块将复杂的空间‑时间图数据转换为简洁的标记,捕获相应的空间和时间关系。适配器模块通过线性编码层和解码层,将标记化的数据与LLMs相桥接,使LLMs能够理解交通数据的语义。预测模型利用经过微调的LLMs,结合STG‑Tokenizer和STG‑Adapter,对交通数据进行预测分析。本发明通过设计基于LLMs的交通预测方法,提高了交通预测的精度,具有广泛的应用前景和实际应用价值。


    Access

    Download


    Export, share and cite



    Title :

    Traffic prediction method based on large model


    Additional title:

    一种基于大模型的交通预测方法


    Contributors:
    ZHANG QIANG (author) / SHEN BO (author)

    Publication date :

    2025-01-21


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Traffic flow prediction method and system based on large model

    YAO XINWEI / JIANG YIXUAN / QIN YANG et al. | European Patent Office | 2025

    Free access

    Traffic situation perception prediction method and system based on multi-modal traffic large model

    YAN JUN / DING LIZHU / WANG YANQING | European Patent Office | 2023

    Free access

    DeepTSP: Deep traffic state prediction model based on large-scale empirical data

    Yang Liu / Cheng Lyu / Yuan Zhang et al. | DOAJ | 2021

    Free access

    Progressive-based large-scale short-term traffic flow prediction method

    WANG CHEN / ZUO KAIZHONG / CHEN ZHANGYI et al. | European Patent Office | 2023

    Free access

    Traffic time prediction model training method, traffic time prediction method, and equipment

    YAN HUAN / LI YONG / JIN DEPENG | European Patent Office | 2021

    Free access