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

Goods source optimal allocation model construction method, optimal allocation model and optimal allocation method

A technology for building methods and models, applied in the field of deep learning, to achieve the effect of assisting decision-making, reducing human operation errors, and accurate supply of goods

Active Publication Date: 2020-01-21
INSPUR SOFTWARE CO LTD
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical task of the present invention is to solve the problem of how to intelligently and optimally allocate commodity sources in the marketing system by providing a method for constructing an optimal allocation model of goods sources, an optimal allocation model, and an optimal allocation method for the above deficiencies.

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
  • Goods source optimal allocation model construction method, optimal allocation model and optimal allocation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] A method for constructing a supply optimization model of the present invention includes the following steps:

[0050] S100, constructing a BP neural network model and an LSTM cyclic neural network model, the BP neural network model is used for data feature learning on retailer basic information data, and the LSTM cyclic neural network model is used for circulating retailer historical order data long-term memory learning;

[0051] Collect basic retailer information data and retailer historical order data, and divide retailer basic information data and retailer historical order data into test samples and training samples;

[0052]S200. Taking the retailer's basic information data in the training sample as the first-level input parameter, training the BP neural network model model through the first-level input parameter, outputting the retailer's supply history distribution data, and obtaining the trained BP neural network model;

[0053] Taking the output historical dist...

Embodiment 2

[0069] An optimal matching model of goods sources according to the present invention, which is a model constructed by a method for constructing an optimal matching model of goods sources disclosed in Embodiment 1, including a trained BP neural network model and a trained LSTM cyclic neural network model.

[0070] After training, the BP neural network model is used to learn the data characteristics of the retailer's basic information data. After the training, the LSTM cycle neural network model is used to perform cyclic long-term memory learning on the retailer's historical order data. After the above training, the BP neural network model and training The post-LSTM cycle neural network model obtains the historical distribution data of retailer's supply.

[0071] In this embodiment, both the BP neural network model and the LSTM cyclic neural network model include an input layer, a hidden layer and an output layer. There are five hidden layers in the BP neural network model, and ...

Embodiment 3

[0073] A method for optimal matching of goods sources based on deep learning of the present invention comprises the following steps:

[0074] S100. Using the method for constructing an optimized supply matching model disclosed in Embodiment 1, construct an optimal matching model for supply sources, the model including a trained BP neural network model and a trained LSTM cyclic neural network model;

[0075] S200. Collect retailer basic information data and retailer historical order data;

[0076] S300, using the retailer's basic information data as a first-level input parameter, and inputting the first-level input parameter into the trained BP neural network model to obtain the retailer's supply history distribution data;

[0077] The historical distribution data of the retailer's supply of goods and the historical ordering data of the retailer are used as the secondary input parameters, and the secondary input parameters are input into the trained LSTM cyclic neural network m...

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 discloses a goods source optimal allocation model construction method, an optimal allocation model and an optimal allocation method, belongs to the field of deep learning, and aims to solve the technical problem of how to intelligently and optimally allocate goods sources in a marketing system. The method comprises the following steps: S100, constructing a BP neural network model andan LSTM recurrent neural network model; collecting retailer basic information data and retailer historical ordering data; S200, training a BP neural network model by using the retailer basic information data in the training sample; training an LSTM recurrent neural network model according to the output retailer goods source historical distribution data and the retailer historical ordering data inthe training sample; and S300, if the model accuracy does not accord with the threshold, circularly executing the step S200 until the model accuracy reaches the threshold. The model is the goods source optimal allocation model constructed by the method. According to the optimal allocation method, parameter decision-making goods source optimal allocation is carried out through the optimal allocation model constructed through the method.

Description

technical field [0001] The present invention relates to the field of deep learning, in particular to a method for constructing a supply optimization model, an optimization model and an optimization method. Background technique [0002] Deep learning is a kind of machine learning, and machine learning is the only way to realize artificial intelligence. The concept of deep learning originates from the research of artificial neural networks, and a multi-layer perceptron with multiple hidden layers is a deep learning structure. Deep learning combines low-level features to form more abstract high-level representation attribute categories or features to discover distributed feature representations of data. The motivation for studying deep learning is to build a neural network that simulates the human brain for analysis and learning, which imitates the mechanism of the human brain to interpret data, such as images, sounds, and texts. [0003] A neural network is a set of algorith...

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): G06Q10/04G06Q10/06G06N3/04G06N3/08
CPCG06Q10/04G06Q10/067G06N3/049G06N3/08G06N3/044G06N3/045Y02P90/30
Inventor 马秀霖
Owner INSPUR SOFTWARE CO LTD
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