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

A recommendation method for vegetables

A method and technology for recommending dishes, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of not being able to recommend dishes that meet their tastes, etc.

Active Publication Date: 2019-02-01
KUNMING UNIV OF SCI & TECH
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the prior art, the present invention mainly solves the problem that if the customer has no order record, he cannot recommend dishes that meet his taste, making online ordering more friendly to new users

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 recommendation method for vegetables
  • A recommendation method for vegetables
  • A recommendation method for vegetables

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Embodiment 1: as Figure 1-3 As shown, the present invention provides a dish recommendation method, which can be applied to dish recommendation when customers can order meals. For example, assuming that there are multiple merchants in an ordering site, and each merchant also provides many different dishes, all these dishes can be called a dish set. When a registered user orders food online, dishes suitable for the customer's taste can be recommended to the customer.

[0031] Step 1. Classify and extract the different characteristic attributes of each dish one by one

[0032] Table 1 is a table of characteristic values ​​of a certain dish

[0033]

[0034] Step 2, quantify

[0035] Quantification of sweetness, definition

[0036] The sweetness of 10% sucrose aqueous solution at 20°C is 1.0, and the sweetness of other sugars is compared with it. Since this sweetness is relative, it is also called specific sweetness.

[0037] The type of ingredients is classified ...

example 1

[0062] Example 1: Assuming that a new user whose hometown address is filled in Beijing orders food, after the system queries the previous ordering records in Beijing area, and then calculates the characteristic values ​​of standard dishes in Beijing area, the assumption is:

[0063]

[0064] Then search for dishes with high similarity in the dishes provided by all merchants that can provide dishes.

[0065] For example, the eigenvalue table of sweet and sour pork tenderloin is

[0066]

[0067] compared with

[0068] X1=1, X2=0.8, X3=1.2, X4=0, X5=0.2, X6=0.55

[0069] Y1=1, Y2=0.8, Y3=1.1, Y4=0.1, Y5=0.2, Y6=0.5

[0070]

[0071] In this way, it can be compared that the sweet and sour pork tenderloin is more in line with the user's taste, and it is recommended to include it in the menu of recommended dishes.

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 relates to a vegetable recommendation method, belonging to the network technical field. The method comprises the following steps: obtaining vegetables in a vegetable collection; Obtain the user's hometown and permanent residence area; According to the similarity between the common dishes and the dishes in the dishes collection, the recommended dishes catalogue is obtained, and the similarity of the dishes is a measure of the difference of the dishes attributes according to the attributes of the dishes themselves. Use the dishes from the similar order menu as the recommended dishes. The invention can recommend the dishes which are more in line with the taste of the user even when the user does not have the history ordering record. Compared with the prior art, the invention mainly solves the problem that a customer can not recommend a dish conforming to his taste if he has no order record, and makes the online order more friendly to a new user.

Description

technical field [0001] The invention relates to a dish recommendation method, which belongs to the field of network technology. Background technique [0002] In the current online food ordering industry, recommending dishes to users is already a frequent behavior. However, in many cases, the recommended dishes on the website are often hot-selling dishes for a period of time. Sometimes some dish recommendations are generated based on the customer's historical ordering records when ordering online, but there is nothing for users who order for the first time. Good way to recommend. However, hot-selling dishes or dishes with high ratings often do not meet the user's own taste. Contents of the invention [0003] In view of this, the present invention provides a dish recommendation method to improve the rationality of dish recommendation. According to the similarity between the dishes, the present invention finds dishes with attributes similar to those in the user's hometown,...

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
IPC IPC(8): G06F16/9535G06Q50/12
CPCG06Q50/12
Inventor 黄思嘉杜庆治龙华邵玉斌
Owner KUNMING UNIV OF SCI & TECH