Order estimation method and device

A technology of orders and historical orders, applied in the field of neural networks

Inactive Publication Date: 2021-12-03
大汉电子商务有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

How the neural network is structured for this deployment structure, there is currently no solution

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
  • Order estimation method and device
  • Order estimation method and device
  • Order estimation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The technical solution in this application will be described below with reference to the accompanying drawings.

[0042] see figure 1 , the embodiment of the present application provides an order estimation system, and the order estimation system may include: network devices, such as a first device, a second device, and so on. The network device may include a server, such as a data server, a network server, etc., and may be a single server, or may also be a server cluster.

[0043] The server can automatically collect order data from the Internet. These order data are usually multi-dimensional, that is, the order data can contain various data related to the order, such as product type, product model, order type, order price, order time, etc. Wait. Since these orders are signed orders, these orders are also called historical orders. The server can build a model for subsequent analysis and processing of orders based on the data of historical orders, such as an order mo...

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 an order estimation method and device, and can realize that a neural network still has good robustness in a business clustering deployment scene. For example, the constructed order pre-estimation neural network can pre-estimate the price trend of the product by analyzing the order, so that an early warning effect on the abnormal change of the order price can be achieved. The method comprises the following steps: acquiring multi-dimensional data of a historical order; acquiring a first basic matrix and a second basic matrix, wherein the first basic matrix is determined according to a first reference matrix of each device in the device cluster, the second basic matrix is determined according to a second reference matrix of each device in the device cluster, the first device belongs to the device cluster, and both the first reference matrix and the second reference matrix are matrices pre-trained by corresponding equipment; combining the first basic matrix and the second basic matrix to construct an order estimation neural network; and processing the current order through the order estimation neural network, and estimating the price trend of the order.

Description

technical field [0001] The present application relates to the technical field of neural networks, and in particular to an order estimation method and device. Background technique [0002] At present, neural networks have been widely used in various fields, such as sales, security, and so on. Among them, for businesses in different fields, different neural network structures can be constructed, and different training methods can be used to train the neural network, and finally the neural network can have better robustness for the business in this field. [0003] However, with the development of technology, services are gradually deployed in clusters. How neural networks are structured for this deployment structure is currently unresolved. Contents of the invention [0004] The embodiments of the present application provide an order estimation method and device, which can construct a neural network with a corresponding structure for business cluster deployment, so that the...

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): G06Q30/06G06Q30/02G06N3/08
CPCG06Q30/0635G06Q30/0206G06N3/08
Inventor 付胜龙王钰贺金生万世红宋军袁彬陈灏肖朝斌张思伟
Owner 大汉电子商务有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap