	US 12,229,703 B1
	Intelligent analysis method for operational supervision of public transportation industry and system thereof
Tao Zhang, Nanjing (CN); Qi Tao, Nanjing (CN); Zaixiang Wei, Nanjing (CN); Yan Peng, Nanjing (CN); Ying Hu, Nanjing (CN); Fei Ren, Nanjing (CN); Jian Wang, Nanjing (CN); Qi Zhang, Nanjing (CN); and Menghan Yao, Nanjing (CN)
Assigned to Nan Jing Intelligent Transportation Information Co. Ltd, Nanjing (CN)
Filed by Nan Jing Intelligent Transportation Information Co. Ltd, Nanjing (CN)
Filed on May 14, 2024, as Appl. No. 18/664,056.
Claims priority of application No. 202311233186.0 (CN), filed on Sep. 22, 2023.
Int. Cl. G06Q 10/0637 (2023.01); G06Q 50/40 (2024.01); G08G 1/01 (2006.01)

CPC G06Q 10/0637 (2013.01) [G06Q 50/40 (2024.01); G08G 1/0125 (2013.01)]

7 Claims

1. An intelligent method for optimizing operational supervision of smart public transportation vehicles comprising:

executing a program stored in a memory through a processor to be configured to function as:

S1—operation information collection, comprising dividing operation areas for smart public transportation vehicles and obtaining basic vehicle information, road network traffic light information, congestion information, platform monitoring information, historical platform passenger flow information, charging station information, and vehicle dispatching and operation information of target smart vehicles within operation areas, wherein the basic vehicle information comprises vehicle energy information, GPS location information and current number of passengers in vehicles;

S2—calculation of basic vehicle information and platform passenger flow information, comprising analyzing and estimating energy of the target smart vehicles through the vehicle energy information, the GPS location information and the vehicle dispatching and operation information to obtain remaining energy information of the target smart vehicles; and based on the platform monitoring information within the operation areas, obtaining number of passengers waiting at platforms within the operation areas and real-time platform passenger flows on operation lines, and forming platform congestion information after analyzing and estimating number of passengers getting off at stations based on the historical platform passenger flow information;

S3—current operation analysis of target smart vehicles, comprising based on the remaining energy information and the charging station information of the target smart vehicles, and combined with platform congestion information on routes where the target smart vehicles travel, using a greedy algorithm to analyze and obtain current preferred dispatching operation lines on the routes where the target smart vehicles travel, so as to park and charge, which specifically comprises as follows:

S301—determining operation parameters of operation lines which comprise basic vehicle information, road network traffic light information, congestion information, platform monitoring information, historical platform passenger flow information, charging station information, and vehicle dispatching and operation information, and designing dispatching and operation models of smart public transportation vehicles;

S302—taking current operation durations of the target smart vehicles as preferred targets, namely, constraining issues of charging, entering stations to pick up passengers and travelled distances during operation of dispatching operation lines where the target smart vehicles travels; and

S303—using the greedy algorithm to optimize and solve the issues of charging, entering stations to pick up passengers and travelled distances in S302 based on the dispatching and operation models of smart public transportation vehicles and the current operation durations of the target smart vehicles, to obtain optimized charging station terminals for the target smart vehicles

wherein the issues of S303 are optimized and solved through following equations:

wherein t_crepresents an operation duration of an ith target smart vehicle, and w_irepresents a pick-up duration of the ith target smart vehicle entering a station; and

wherein s_irepresents a travelled distance of the ith target smart vehicle, and p_irepresents a charging duration of the ith target smart vehicle;

x refers to a solution vector and is defined as X={X1,X2,X3, . . . ,Xn}, wherein x is a decision variable vector of a length n, f(x) represents an objective function, and G(x) represents a constraint function;

S4—current data update and calibration of the target smart vehicles, comprising performing real-time updates and calibration of time which the target smart vehicles take to charging station terminals based on the current preferred dispatching operation lines and updated platform congestion information, charging station information and remaining energy information;

S5—automatic adjustment of dispatching operation plans for smart public transportation vehicles within operation areas, comprising automatically adjusting dispatching operation plans of smart public transportation vehicles at the charging station terminals based on operation lines of smart public transportation vehicles and real-time collected remaining platform congestion information, charging station information and remaining energy information;

S6—real-time updates of real-time data of online vehicles within the operation areas; and

S7—automatically generating optimized routes to the optimized charging station terminals for the target smart vehicles, controlling the target smart vehicles to travel on the optimized routes, displaying the optimized charging station terminals and the optimized routes to the optimized charging station terminals on the target smart vehicles, and automatically adjusting operation plans of the target smart vehicles to maximize operation durations of the target smart vehicles and an increase of vehicle travelled distances of the target smart vehicles, improve an operation effect of the target smart vehicles, and allow the target smart vehicles to be charged timely.