A method for predicting bus ladder ticket price
A forecasting method and ticket price technology, applied in forecasting, special data processing applications, instruments, etc., can solve problems such as high cost, impact on industry development, and difficulty in understanding passengers' money investment, so as to achieve high forecasting accuracy and improve query speed , optimized pressure effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0060] Such as figure 1 As shown, a bus ladder fare prediction method includes the following steps:
[0061] a. Create database Sqlserver;
[0062] b. Collect the returned data, and transmit the returned data to the database Sqlserver; the returned data includes vehicle ID, door closing time, door closing time, number of people getting on and off, and GPS data of the door opening location;
[0063] c. Clean the returned data, generate station information table, line information table, vehicle line association table, station ladder fare table, line passenger flow table and line station distance table;
[0064] d. Periodically migrate the data in the database Sqlserver to the distributed system storage database HBase;
[0065] e. According to the station information table, line information table, vehicle line association table, station ladder fare table, line passenger flow table and line station distance table, calculate the forecasted revenue data of a certain car for a day....
Embodiment 2
[0068] On the basis of embodiment 1, this embodiment also includes the following steps:
[0069] Compare and evaluate the actual revenue data with the predicted revenue data. If the ratio is between 0.95-1.05, the predicted revenue data is valid; otherwise, it is invalid, and the predicted revenue data is calculated again.
[0070] This technical solution is used to calculate the fare forecast revenue. After calculating the predicted revenue value of a line, it is compared with the real revenue data. After testing, the accuracy of the algorithm is more than 95%. It can be used as the basis for revenue, mastering and forecasting Bus revenue, which is convenient for the management and arrangement of fares, transportation routes, and train numbers for vehicles.
Embodiment 3
[0072] In this embodiment, on the basis of embodiment 2, said step a includes the following steps:
[0073] Optimize the database Sqlserver. If the amount of data stored in the database Sqlserver exceeds 2G, partition and create a partition index. When the amount of data stored in the database Sqlserver exceeds 2G, partition the table, create a partition index, optimize the query, and improve the query speed. The query speed can reach hundreds of thousands per second, and the database throughput can reach 100MB / s.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


