Unlock instant, AI-driven research and patent intelligence for your innovation.

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.

Pending Publication Date: 2020-03-17
NORTHWESTERN POLYTECHNICAL UNIV
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, in the field of smart cities, the use of urban multi-source big data to predict the express business volume has not yet been extensively carried out.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for predicting express delivery sequence with depth interpretability
  • Method for predicting express delivery sequence with depth interpretability
  • Method for predicting express delivery sequence with depth interpretability

Examples

Experimental program
Comparison scheme
Effect test

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...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a method for predicting an express delivery sequence with depth interpretability. The express delivery business volume of a target area in a future period of time is expressed as a time sequence formed by the everyday express delivery package volume in a continuous period of time, and the express delivery sequence prediction is the prediction of a multi-step time sequence. Compared with an existing method for predicting the express delivery business volume, the method for predicting the express delivery sequence with the depth interpretability has the characteristics that modeling is conducted on the complex coupling relation of multiple factors, and the influence weight is dynamically and adaptively distributed. Meanwhile, explanation can be provided for the prediction process of the method, the correlation relation between user express behaviors and influence factors is explored, and the method plays an extremely important role in the application scenes, such as resource scheduling and distribution, e-commerce promotion activities, etc.

Description

technical field [0001] The invention relates to the fields of smart cities and data mining, in particular to a method for predicting express delivery business volume by using a deep neural network. Background technique [0002] In recent years, with the development of the economy, the rise of online shopping has not only brought about commercial changes, but also gradually changed the shopping habits and concepts of traditional consumers. The development of the express logistics industry has closely linked the virtual network with the real society, providing great convenience for people's daily life. However, the increasing popularity of express delivery is also accompanied by new problems: On the one hand, within the daily time period, the express volume of different communities fluctuates within a certain range. If human resources such as sorting personnel, delivery personnel, and warehouse capacity remain unchanged, resources It will not be able to make full use of it; o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q10/08
CPCG06Q10/04G06Q10/083
Inventor 郭斌任思源刘佳琪李可於志文
Owner NORTHWESTERN POLYTECHNICAL UNIV