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

An e-commerce recommendation technology and system based on analysis of soft set decision rules

An e-commerce and soft decision-making technology, applied in the computer field, can solve the problems of sparse overall distribution of e-commerce product sales data, affecting the application of correlation analysis technology, disliking e-commerce product ratings or verbal evaluation, etc. Avoid the effect of incomplete data and obvious effect

Active Publication Date: 2021-12-24
XIANGNAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These are the defects of the existing association relationship analysis technology, and it is these defects that affect the application of the existing association relationship analysis technology
[0007] 2. The basis of existing recommendation methods for e-commerce recommendations requires users to rate or evaluate e-commerce products, but in reality, most users of e-commerce platforms do not like to rate or verbally evaluate e-commerce products. E-commerce The platform only has e-commerce product sales data, and the overall distribution of e-commerce product sales data is also sparse

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
  • An e-commerce recommendation technology and system based on analysis of soft set decision rules
  • An e-commerce recommendation technology and system based on analysis of soft set decision rules
  • An e-commerce recommendation technology and system based on analysis of soft set decision rules

Examples

Experimental program
Comparison scheme
Effect test

example 6

[0126] Example 6. A probabilistic decision soft set (F, C, D) is shown in Table 1 below.

[0127] Table 1 Probabilistic Decision Soft Set (F, C, D)

[0128] e 1

e 2

e 3

d u 1

1 0 0 0 u 2

1 0 1 1 u 3

0 0 1 0 u 4

1 1 1 1

[0129] Among them, U={u 1 ,u 2 ,u 3 ,u 4}, the normal probability distribution on U is: P({u 1})=1 / 3,P({u 2})=1 / 3,P({u 3})=1 / 6,P({u 4})=1 / 6, condition parameter set C={e 1 ,e 2}, the meaning of the parameter is e 1 ="headache", e 2 = "muscle pain", e 3 = "fever", the decision parameter set D = {d}, the meaning of the parameter is d = "flu".

[0130] The basic soft truth of each decision rule is: τ(e 1 →d)=2 / 3,τ(e 2 →d)=1,τ(e 3 → d) = 5 / 6.

[0131] The conditional soft truth of each decision rule is: γ(e 1 →d)=3 / 5, γ(e 2 →d)=1,γ(e 3 → d) = 3 / 4.

[0132] The joint soft truth of each decision rule is: ρ(e 1 →d)=5 / 9, ρ(e 2 →d)=1 / 6, ρ(e 3 → d) = 5 / 9.

example 7

[0133] Example 7. (1) The three truth values ​​of a decision rule describe the numerical characteristics of the decision rule from three different perspectives. Generally speaking, the soft truth focuses on the validity of the decision rule; the conditional soft truth emphasizes the condition The certainty of the implication relationship between the attribute and the decision attribute; the joint soft truth takes into account both the validity of the decision rule and the support strength of the conditional attribute to the decision rule.

[0134] (2) It can also be seen from Example 6 that although the decision rule e 2 → d has high validity and certainty (strength 1), decision rule e 2 → condition attribute e in d 2 The support strength for the decision rule is very low (strength is 1 / 6). Intuitively, we can understand it as: Since u 2 also satisfy e 1 and e 3 , thus supporting the decision rule e 2 → Evidence u of d 2 May not actually work. In other words, u 2 His "f...

example 8

[0170] Example 8. Analysis of decision rules for some patient decision information systems.

[0171] Table 2 Certain Patient Decision Information Systems

[0172]

[0173]

[0174] For the convenience of description, the above attributes and attribute values ​​are respectively symbolized, where a = "headache", b = "muscle pain", c = "body temperature", d = "flu". a = two attribute values ​​of "headache" Yes and no respectively use a 1 ,a 2 Represent; b = "muscle pain" two attribute values ​​yes, no use b respectively 1 ,b 2 Indicate; the three attribute values ​​of c = "body temperature" are very high, high, and normal, respectively use c 1 ,c 2 ,c 3 Represent; the two attribute values ​​of d=“influenza” are yes and no respectively use d 1 , d 2 .Using the rough set theory to reduce the attributes of the information system, the minimum attribute reduction set is {headache (a), body temperature (c)}. The reduced and symbolized attribute table is converted into a s...

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 belongs to the field of computer technology, discloses an e-commerce recommendation technology and system based on the analysis of soft set decision rules, and establishes a propositional logic reasoning language based on soft sets. In the reasoning language, the atomic formula is the parameter e in the soft set , the function value F(e) of the parameter e is the assignment set of the atomic formula e, and the soft decision rule is an implication logic formula composed of atomic formulas on the decision soft set; the introduction of soft truth, conditional soft truth and joint soft truth , soft similarity, logical soft distance and other quantitative indicators to evaluate soft decision rules from different aspects of sufficiency, necessity and rationality; transform the decision system into a decision soft set, and propose a soft decision rule extraction method for incomplete decision systems; Data analysis methods based on propositional logic and soft sets are applied to e-commerce recommendation. The present invention demonstrates that the methods proposed by the present invention are all effective through practical examples; the theoretical analysis of the present invention is innovative, the method structure is novel, and the technical means are practical.

Description

technical field [0001] The invention belongs to the field of computer technology, and in particular relates to an e-commerce recommendation technology and system based on analysis of soft set decision rules. Background technique [0002] Soft set theory is a mathematical theory to describe and deal with uncertainty established by Professor Molodtsov. A soft set is a two-tuple composed of a parameter set and a set-valued mapping on the power set of the domain of discourse, or a soft set is a whole composed of some subsets organized by certain parameters on the domain of discourse. The subset corresponding to each parameter in the soft set is called an approximate set. In the soft set theory, there is no restriction on the approximate set. The approximate set can be an empty set, and the intersection of the approximate sets corresponding to different parameters may be non-empty. This makes the soft set concept cover a very wide range, and has the characteristics of flexibilit...

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 Patents(China)
IPC IPC(8): G06Q30/06G06K9/62G06F16/26
CPCG06F16/26G06Q30/0631G06F18/24147
Inventor 吴霞钟嘉鸣张家录谷玉
Owner XIANGNAN UNIV
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