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

Catering industry dish sales predicting method based on deep learning

A technology of deep learning and forecasting methods, which is applied in forecasting, marketing, business, etc., can solve problems such as the decline of forecasting accuracy and poor fitting of nonlinear sequence data, so as to improve the forecasting accuracy rate, improve the accuracy rate, and reduce operating losses. Effect

Inactive Publication Date: 2018-08-03
XIAN UNIV OF TECH
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for predicting the sales volume of dishes in the catering industry based on deep learning. The historical data of the same working day as the holiday date is used to predict the sales of dishes during the holiday period, which leads to the problem that the prediction accuracy decreases

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
  • Catering industry dish sales predicting method based on deep learning
  • Catering industry dish sales predicting method based on deep learning
  • Catering industry dish sales predicting method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.

[0041] A method for predicting the sales volume of dishes in the catering industry based on deep learning, comprising the following steps:

[0042] The original data sequence is the daily sales data of dishes. According to the working day of the sales date, the original data sequence is divided into ordinary working day sales sequence and holiday sales sequence; the ordinary working day sequence includes 7 sequences from Monday sales data to Sunday sales data Data, holiday sales data contains 14 holiday data sequences;

[0043] For the forecast of sales on ordinary working days, the long-term and short-term memory network (LSTM) model in deep learning is used. The model includes an input layer, a hidden layer and an output layer. The hidden layer is composed of two LSTM layers, and tanh is used as the hierarchical activation function. The out...

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 catering industry dish sales predicting method based on deep learning. The method divides sales data according to the date of sales, and an ordinary working day sales predicting model and a holiday sales predicting model are established respectively. When the dish sales is predicted, the ordinary working day sales predicting model is used to predict the sales of ordinaryworking days in the future, and the holiday sales predicting model is used to predict the dish sales during holidays. According to the invention, the method performs well in both nonlinear data and holiday prediction, has the advantages of accurate prediction ability and strong robustness, and can fully reflect the regularity and characteristics of the dish sales. The predicting models can providea strong reference for the material purchase of an enterprise purchaser, and have a high application value.

Description

technical field [0001] The invention relates to the field of catering management, in particular to a method for predicting the sales volume of dishes in the catering industry based on deep learning. Background technique [0002] With the gradual prosperity of the world economy, the catering industry has also developed rapidly in recent decades, and various chain stores and restaurants have emerged in an endless stream. At the same time, the development of science and technology has made the intelligent transformation of the catering industry an irresistible trend. With the emergence of smart tools such as smart ordering, dish recommendation, and online payment, the competition in the catering industry is no longer limited to price competition and product quality competition. "Intelligence" has also become an important factor in the competition of the catering industry. In recent years, the rapid development of the Internet and information technology has led to a sharp incre...

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): G06Q10/04G06Q30/02G06Q50/12
CPCG06Q10/04G06Q30/0202G06Q50/12
Inventor 孙钦东曹晗
Owner XIAN UNIV OF TECH
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