A restaurant ordering recommendation method and system based on multi-user information fusion and entropy
A recommendation method and multi-user technology, applied in digital data information retrieval, data processing applications, character and pattern recognition, etc., to achieve the effect of improving accuracy, improving accuracy and user experience, and eliminating waste
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0049] like figure 1 As shown, this embodiment provides a restaurant ordering recommendation method based on multi-user information fusion and entropy, including:
[0050] S101: Obtain historical ordering data and weight information, generate a weighted frequent pattern tree, and determine an association rule between dishes and dishes, the number of dishes and the number of diners; the weight information is a weight value that carries the number of diners.
[0051] Among them, determining the association rules between the dishes and the dishes can update the recommendation results in real time and improve the accuracy of the recommendation; determining the association rules between the number of dishes and the number of diners can provide users with different sizes of meals. Control waste.
[0052] This embodiment generates a weighted frequent pattern tree WFP-Tree (Weighted Frequent Pattern-tree) based on the WFP-growth (Weighted Frequent Pattern-growth) algorithm, and then ...
Embodiment 2
[0126] This embodiment provides a restaurant ordering recommendation system based on multi-user information fusion and entropy, which includes:
[0127] A weighted frequent pattern tree generation module, which is used to obtain historical ordering data and weight information, generate a weighted frequent pattern tree, and obtain association rules between dishes and dishes, dishes and the number of diners; the weight information is the number of people carrying diners weight value;
[0128] The candidate subset calculation module is used to calculate the candidate subset of recommended dishes to each user under the same table number based on the weighted frequent pattern tree, entropy and the recommendation matrix of similarity; wherein, each recommended dish carries a gain value information;
[0129] The multi-user information fusion module is used to merge all the candidate subsets under the same table number, add the gain values of the overlapping dishes, sort the dishes...
Embodiment 3
[0132] This embodiment provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the method for restaurant ordering recommendation based on multi-user information fusion and entropy described in the first embodiment above A step of.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


