Systems and methods for determining predicted distribution of future transportation service time point

Patent metadata

Field	Value
Publication number	US-10740701-B2
Application number	US-201715721836-A
Country	US
Kind code	B2
Filing date	Sep 30, 2017
Priority date	Mar 3, 2016
Publication date	Aug 11, 2020
Grant date	Aug 11, 2020

Abstract

The present disclosure relates to systems and methods for determining a predicted distribution of future transportation service time point. The systems may perform the methods to obtain historical service time points of transportation service requests occurred in a predetermined region; determine a variance of the historical service time points; determine a predicted distribution of future transportation service time point in the predetermined region based on the variance; and store the predicted distribution in a database.

First claim

We claim:

1. A system specially configured to improve vehicle supply management of online transportation services, comprising: a internal communication bus; one or more storage media electronically connected to the internal communication bus, including a set of instructions for determining a predicted distribution of future transportation service time point; and logic circuits electronically connected to the at least one storage medium via the bus, wherein during operation, the logic circuits load the set of instructions and: receive a real-time request of a transportation service frequency that is associated with a first predetermined time period from a user terminal; obtain electronic signals from the bus, the electronic signals encoding individual historical service time points of transportation service requests in the first predetermined time period occurred in a predetermined region, which includes a position located by a position locating device associated with the user terminal; determine a graph of a predicted distribution of individual future transportation service time point in the predetermined region based on a variance of a number count of the individual historical service time points, wherein the predicted distribution of individual future transportation service time point is normal distribution, and the predicted distribution of individual future transportation service time is further determined based on a combination of a plurality of weighted first normal distributions; obtain a result transportation service frequency graph by applying the first predetermined time period to the predicted distribution; and send out, via the Internet, electronic signals encoding the result transportation service frequency graph to the user terminal in real time and the result transportation service frequency graph is displayed on a user interface of the user terminal.

2. The system of claim 1 , wherein to determine the variance of the number count of the individual historical service time points, the logic circuits further:
determine an average of the number count of the individual historical service time points;
determine a number of the individual historical service time points; and
determine the variance of the number count of the individual historical service time points based on the average of the number count of the individual historical service time points and the number of the individual historical service time points.

3. The system of claim 2 , wherein to determine the variance of the number count of the individual historical service time points, the logic circuits further:
determine that the number of historical transportation service requests in a second predetermined time period is smaller than a first threshold, so that accuracy of the predicted distribution of future transportation service time point is lower than a second threshold value;
determine a correction coefficient relating to the number of the historical service time points; and
apply the correction coefficient to the variance of the individual historical service time points to increase prediction accuracy.

4. The system of claim 2 , wherein to determine the predicted distribution of future transportation service time point based on the variance, the logic circuits further:
determine a fluctuation range relating to the variance; and
determine the predicted distribution of future transportation service time point based on the fluctuation range.

5. The system of claim 4 , wherein to determine the fluctuation range relating to the variance, the logic circuits further:
determine a standard deviation of the individual historical service time points;
determine a distribution model relating to the variance based on the variance, the standard deviation, and the number of the individual historical service time points; and
determine the fluctuation range relating to the variance based on the distribution model.

6. The system of claim 5 , wherein the distribution model is a distribution model relating to a quadratic sum of multiple normal distribution variables.

7. The system of claim 4 , wherein to determine the predicted distribution of future transportation service time point based on the variance, the logic circuits further:
obtain a plurality of variance values based on the fluctuation range relating to the variance;
for each of the plurality of variance values, determine a first predicted distribution of future transportation service time point based on the variance value; and
determine a second predicted distribution of future transportation service time point based on a plurality of first predicted distributions of future transportation service time point.

8. The system of claim 7 , wherein to determine the first predicted distribution of future transportation service time point based on the variance value, the logic circuits further:
determine an expectation of the individual historical service time points;
determine a normal distribution based on the expectation and the variance value; and
determine the first predicted distribution of future transportation service time point based on the normal distribution.

9. The system of claim 7 , wherein to determine the second predicted distribution of future transportation service time point, the logic circuits further:
weigh the plurality of first predicted distributions of future transportation service time point; and
determine the second predicted distribution of future transportation service time point based on the weighing result.

10. A method implemented on at least one electronic device to improve vehicle supply management of online transportation services, comprising:
receiving, by the at least one electronic device, a real-time request of a transportation service frequency that is associated with a first predetermined time period from a user terminal;
obtaining, by the at least one electronic device, individual historical service time points of transportation service requests in the first predetermined time period occurred in a predetermined region, which includes a position located by a position locating device associated with the user terminal;
determining, by the at least one electronic device, a graph of a predicted distribution of individual future transportation service time point in the predetermined region based on a variance of a number count of the individual historical service time points, wherein the predicted distribution of individual future transportation service time point is normal distribution, and the predicted distribution of individual future transportation service time is further determined based on a combination of a plurality of weighted normal distributions;
obtaining, by the at least one electronic device, a result transportation service frequency graph by applying the first predetermined time period to the predicted distribution; and
sending, via the Internet, by the at least one electronic device, the result transportation service frequency graph to the user interface of the user terminal and the result transportation service frequency graph is displayed on a user interface of the user terminal.

11. The method of claim 10 , wherein the determining of the variance of the number count of the individual historical service time points includes:
determining, by the at least one electronic device, an average of the number count of the individual historical service time points;
determining, by the at least one electronic device, a number of the individual historical service time points; and
determining, by the at least one electronic device, the variance of the number count of the individual historical service time points based o

Assignees

• Beijing Didi Infinity Technology & Dev Co Ltd

Inventors

• Zhang Lingyu
• Cheng Wei

Classifications

• G06Q10/0283

  for travel seating · CPC title

• G06Q10/0631 Primary

  Resource planning, allocation, distributing or scheduling for enterprises or organisations · CPC title

• G06Q10/04 Primary

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title

• G06F17/18

  for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title

• H04W4/029

  Location-based management or tracking services · CPC title