Travel time prediction method, apparatus and server

An information processing apparatus, comprising:

• interface circuitry configured to
• obtain a request to estimate a travel time of a target travel route from a starting point to an end point, and
• obtain road traffic information along the target travel route at a current time;
• and
• processing circuitry configured to calculate the estimated travel time of the target travel route based on a travel time calculation model according to the obtained road traffic information and historical travel data, the historical travel data including a plurality of historical travel routes, respective road traffic information for each of the plurality of historical travel routes, and a respective actual travel time of each of the plurality of historical travel routes, wherein:
• the travel time calculation model is obtained by training a machine learning algorithm with a plurality of training samples from the historical travel data,
• the travel time calculation model is verified by inputting a plurality of verification samples from the historical travel data into the travel time calculation model to calculate a quality evaluation parameter of the travel time calculation model,
• the quality evaluation parameter is calculated based on differences between actual travel times of the historical travel routes associated with the plurality of verification samples and corresponding estimated travel times of the historical travel routes associated with the plurality of verification samples that are obtained through the travel time calculation model, and
• the travel time calculation model is verified based on the quality evaluation parameter being equal to or larger than a preset value.

A non-transitory computer readable storage medium storing instructions which when executed by at least one processor cause the at least one processor to perform:

• obtaining a request to estimate a travel time of a target travel route from a starting point to an end point;
• obtaining road traffic information along the target travel route at a current time;
• and
• calculating the estimated travel time of the target travel route based on a travel time calculation model according to the obtained road traffic information and historical travel data, the historical travel data including a plurality of historical travel routes, respective road traffic information for each of the plurality of historical travel routes, and a respective actual travel time of each of the plurality of historical travel routes, wherein:
• the travel time calculation model is obtained by training a machine learning algorithm with a plurality of training samples from the historical travel data,
• the travel time calculation model is verified by inputting a plurality of verification samples from the historical travel data into the travel time calculation model to calculate a quality evaluation parameter of the travel time calculation model,
• the quality evaluation parameter is calculated based on differences between actual travel times of the historical travel routes associated with the plurality of verification samples and corresponding estimated travel times of the historical travel routes associated with the plurality of verification samples that are obtained through the travel time calculation model, and
• the travel time calculation model is verified based on the quality evaluation parameter being equal to or larger than a preset value.