Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A tire enterprise sales forecasting method based on data diversity and task diversity

A forecasting method and a variety of technologies, applied in data processing applications, electrical digital data processing, digital data information retrieval, etc., can solve problems such as huge impact and large differences

Active Publication Date: 2021-06-04
FUDAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the retail and wholesale market of tires, the demand estimation of primary dealers is greatly affected by market changes, and there is a large difference between the demand estimated based on experience and the real order. The sales plan accuracy rate of the tire retail and wholesale market is less than 50%. Reasonable product inventory is required

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
  • A tire enterprise sales forecasting method based on data diversity and task diversity
  • A tire enterprise sales forecasting method based on data diversity and task diversity
  • A tire enterprise sales forecasting method based on data diversity and task diversity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be described in further detail below in conjunction with the examples.

[0051] (1) System design and data preprocessing: According to the dimension that needs to be predicted, the sales forecasting system first extracts the sales data under this dimension from the database, and then sorts it according to time. In order to ensure the rationality of the prediction, the sales data after the time when the user requests the parameters is directly deleted. If there is a discontinuous gap in the sales data before this time due to data loss or other reasons, it will be ignored directly and handed over to the follow-up logic. to process.

[0052] There are two ways to load external data sources. One is to construct a training set or test set based on the loaded sales data, and query the external data of the corresponding time from the database each time. The advantage of this method is that the logic is clear and easy to implement, and the disadvanta...

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 belongs to the technical field of industrial big data application, and specifically relates to a tire enterprise sales prediction method based on data diversity and task diversity. The method of the present invention includes five parts: (1) topic feature extraction, which extracts the characteristics of semi-structured data about the tire industry through the LDA model; (2) structural feature extraction, which maps the tire industry enterprises to heterogeneous (3) Network structure expansion, aiming at the problem of network sparsity, through the fusion of topic features and structural features, expand the relationship graph between enterprises and find potential correlation factors; (4) Use the LASSO method (5) factor feature extraction and time series analysis, through the effective integration and utilization of multiple data sets related to sales (tire demand planning, OEM product sales, tire sales Cargo data, etc.) to predict, through the experimental data verification, can improve the accuracy of tire sales forecast.

Description

technical field [0001] The invention belongs to the technical field of industrial big data application, and in particular relates to a tire enterprise sales prediction method. Background technique [0002] With the deep integration of informatization and industrialization, information technology has penetrated into all links of the industrial chain of industrial enterprises, barcodes, two-dimensional codes, RFID, industrial sensors, industrial automatic control systems, industrial Internet of Things, ERP, CAD / CAM / CAE / Technologies such as CAI have been widely used in industrial enterprises, especially the application of new generation information technologies such as the Internet, mobile Internet, and Internet of Things in the industrial field, and the data owned by industrial enterprises is also increasingly abundant. The amount of data generated, collected and processed by industrial equipment is far greater than the data generated by computers and humans in enterprises. I...

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 Patents(China)
IPC IPC(8): G06F16/2458G06Q10/06
CPCG06Q10/06375G06F16/2462G06F16/2465
Inventor 李敏波廖倡许晓彬
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com