Automatic commodity recommendation method and system for unmanned lipstick vending machine

A recommendation method and technology of vending machines, which are applied in the direction of coinless or similar appliances, commerce, and coin-operated equipment for distributing discrete items, etc., which can solve problems such as difficulty in mining and inability to obtain user preference information

Pending Publication Date: 2021-05-04
JILIN UNIV
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, offline unmanned vending systems, such as unmanned lipstick vending machines, have a small number of products and often face different random users, so it is difficult to mine user preference information and cannot recommend products accurately and conveniently

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
  • Automatic commodity recommendation method and system for unmanned lipstick vending machine
  • Automatic commodity recommendation method and system for unmanned lipstick vending machine
  • Automatic commodity recommendation method and system for unmanned lipstick vending machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Embodiment 1 Knowledge framework of the present invention

[0026] Knowledge framework network of the present invention such as figure 1 shown. Use frame notation to describe knowledge. The knowledge frame of this method combines information from four aspects: user personal characteristics, user needs, lipstick attributes, and common sense knowledge. Common sense knowledge is a description similar to expert knowledge, including: young people are suitable for light colors, Matte lipsticks are not suitable for users who have a high demand for moisturization. The logical rules use a number of common sense knowledge to narrow the scope of conditions. For example, young people are suitable for light colors, and there are red, peach, and pink in aftermarket machines. Dark skin is not suitable for peach and pink. Pink, so the recommended results are basically locked in red. The specific thresholds of the rule conditions and the characteristics of different dimensions can be ...

Embodiment 2

[0027] Embodiment 2 The recommendation model of the present invention

[0028] The recommended model of the present invention is as figure 2 shown. When there is no user preference, the lipstick color is recommended according to the user's age, lip shape, face shape and skin color; the lipstick type is recommended according to the occasion, durability and moisture requirements; the lipstick brand is recommended according to the budget; when there is a user preference, it is recommended according to the corresponding preference Colour, type and brand. The user's preference may have multiple values. For example, there is only a preference for color, or a preference for both color and brand, but there is no preference for type, and the type is recommended according to other dimensions of the user. The value of the recommended result can only be the existing lipstick attribute value in the vending machine. For example, if there is no black lipstick on the vending machine, the ...

Embodiment 3

[0030]实施例3本发明的推荐方法流程

[0031]本发明的推荐方法流程如 图3所示。首先，通过建立不同的向量，对知识进行描述，即限定推理模型中考虑的不同维度，对知识描述的具体方法，是将不同维度映射成逻辑程序对知识的表征形式。例如，age(X,a0)表示年龄维度上，用户X的值先抽象为a0，通过获取用户相应的信息，为程序实例化。映射成逻辑程序的方法包括通过编辑器，实现逻辑程序的表达形式。

[0032]然后，根据推荐模型，对规则进行描述，即根据不同用户维度的组合，确定一个口红维度上的推荐结果，推荐结果的值不能超出售货机的口红特征，将不同维度上的推荐结果组合成推荐结果向量，产生不同的推荐结果向量。例如，用户的预算是200元，根据售货机特定情况，将170元和210元对应的口红品牌，都作为品牌推荐结果，这样就可能组合出两个推荐结果，然后分别判断能否成立，如果都成立，将结果都反馈给用户，令其选择。上述推荐结果的产生，按照推理模型实施，推理模型中的问题按照模型规范描述，并设计相应的逻辑程序规则语句，通过求解逻辑程序实现；

[0033]最后，根据售货机口红特征情况，确定在不同口红维度上，不能同时成立的值，并以这些值作为条件，制定相应的逻辑程序约束规则，实现推荐结果和售货机中的口红能否匹配的判断。例如，售货机有红色的口红，有哑光口红，但是没有红色哑光口红，即"红色”和"哑光”是在不同口红维度上，不能同时成立的值，所以如果推荐结果包括，红色和哑光，它被约束规则限制而不能作为口红推荐，只能反应售货机缺货，这一过程同样通过逻辑程序主体实现。

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 an automatic commodity recommendation method and system for an unmanned lipstick vending machine, and belongs to the technical fields of artificial intelligence and computers. The method mainly comprises the following steps: establishing a personal feature vector and a demand vector of a user, and acquiring values of the user in different dimensions in the vectors; establishing a lipstick attribute vector and a vector space thereof, and determining values in different dimensions in the vector according to characteristics of lipsticks in different vending machines; according to the combination of different user dimensions, determining a recommendation result on one lipstick dimension; and judging whether the recommendation result vector can be matched with the lipstick attribute vector space or not. The recommendation method based on logical reasoning is provided aiming at the characteristics that an offline unmanned lipstick vending machine is small in commodity type and number, and user preference information is difficult to mine; an established logic rule comprises non-monotonous logic semantics, so that the vending machine can continuously adjust a recommendation result when new information of a user appears, and the contradiction with the recommendation result due to stockout is avoided.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and computer technology, and relates to an automatic commodity recommendation method and system for an unmanned lipstick vending machine. Background technique [0002] With the development of the application of unmanned vending system based on computer and artificial intelligence technology, accurate, fast and convenient product recommendation based on the unmanned vending system has become one of the main extended functions of the application. The traditional recommendation method is based on the application of big data, mining multiple purchase information and preference information of the same user to recommend related products. However, offline unmanned vending systems, such as unmanned lipstick vending machines, have a small number of products and often face different random users, so it is difficult to mine user preference information and cannot recommend products accurately and conven...

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): G06Q30/02G07F11/00
CPCG06Q30/0282
Inventor 顾海军王义功刘浩予杨昆姜宗林朱书村黄台虎苗欣刘美琪杨雪
Owner JILIN UNIV
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