Method for predicting express delivery sequence with depth interpretability
A technology of sequence forecasting and time series forecasting, which is used in forecasting, instrumentation, data processing applications, etc., and can solve problems such as the lack of large-scale express delivery business.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0023] Further describe the technical scheme of the present invention below in conjunction with accompanying drawing:
[0024] Before describing the method of the present invention, the express sequence prediction problem is described and formally defined. The present invention takes time series prediction as the research background, and defines the problem as a multi-step time series prediction problem of the number of express parcels in the target area.
[0025] Formally, all parameters involved in the present invention are defined as follows:
[0026] The model contains two kinds of inputs X and Y, which represent external features and courier sequences respectively, and the model output is a sequence of length K, which represents the prediction result of the courier volume in the target area in the future K days. Given the time window length L of historical features and the length T of historical express sequences (where L≤T), the input sequence X contains N features, R...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


