CN107657491A - A kind of tensor resolution e-commerce user trust recommendation algorithm based on theme - Google Patents
A kind of tensor resolution e-commerce user trust recommendation algorithm based on theme Download PDFInfo
- Publication number
- CN107657491A CN107657491A CN201610588465.2A CN201610588465A CN107657491A CN 107657491 A CN107657491 A CN 107657491A CN 201610588465 A CN201610588465 A CN 201610588465A CN 107657491 A CN107657491 A CN 107657491A
- Authority
- CN
- China
- Prior art keywords
- theme
- user
- tensor
- commerce user
- commerce
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention proposes a kind of tensor resolution e-commerce user trust recommendation algorithm based on theme, for excavating user when different articles is chosen to the trusting degree of different friends;In to the e-commerce user trust recommendation based on theme, we carry out three's incidence relation of the theme of one user of analog subscriber one using three-dimensional tensor;Alternating least-squares (alternating least squares, the letter of use.Claim ALS) tensor N ranks approximation is realized, the algorithm of proposition comes to carry out theme trust recommendation to e-commerce user for TrustTensor algorithms.
Description
Technical field
The present invention is a kind of field of computer technology, is related to e-commerce technology.
Background technology
Ecommerce is typically referred in the extensive trade activity in all parts of the world, in the network environment that internet opens
Under, based on browser/server application mode, both parties carry out various commercial activities with not meeting, realize the net of consumer
Online transaction and online e-payment and various commercial activitys, transaction, finance activities and phase between upper shopping, trade company
A kind of new commercial operation pattern of the integrated service activity of pass;Commending system ecommerce (such as Amazon, eBay,
Netflix, Alibaba, bean cotyledon net, Dangdang.com etc.), information retrieval (such as iGoogle, GroupLens, Baidu etc.) and move
The numerous application fields of dynamic application, Electronic Tourism, Internet advertising etc. obtain greater advance.
The content of the invention
In the proposed algorithm trusted based on e-commerce user, the trusting relationship of user's folk prescription is entirely only considered,
But in the application of reality, for example therefore in electronic commerce network, there is many interest in user, in the friend of user
It is related to user interest;It is small with for example in the connoisseurship of small same aspect, each user has the field that itself is good at,
Some users may be familiar with electronic product, and some users are familiar with automobile product, and these characteristics determine each user small
The suggestion that small same friend is considered with aspect nationwide examination for graduation qualification is based on this thought, devises a kind of pushing away based on e-commerce user theme trust
Recommend algorithm.
In the e-commerce user trust recommendation of theme, we carry out the theme of one user of analog subscriber one using three-dimensional tensor
Three's incidence relation, the alternating least-squares (alternating least squares, abbreviation ALS) of use realize tensor N
Rank is approximate, and the algorithm of proposition is that TrustTensor algorithm alternating least-squares are iterative algorithm, and each iterative process is basis
Other N-1 basis matrix solves a basis matrix of tensors for example, in the l+1 times iterative basis matrix this U (n) l
During+1, according to other N-1 basis matrix U (1) l+1 ..., U (n-1) l+1, U (n+1) l ..., U (N) l:
First pass through and approximate tensor A is calculated to foretell formula·:
A·=A ×1 U(1)J l+1×2 U(2)J l+1 ...×(n-1) U(n-1)J l+1 ×(n+1) U(n+1)J l... ×N
U(n)J l。
Secondly, by tensor A ' expansion matrix uf (A·, n) carry out SVD basis matrix U (n) l+1 are calculated, calculate
The false code of method is described as follows (the TrustTensor algorithms based on theme)：
1. input:User-user-project tensor A, theme number R；
2. output:Core tensor C, foundation characteristic matrix U(1),U(2),U(3)；
3. initialize U(1),U(2),U(3)；
4. initialize C0=A×1 U(1)J×2 U(2)J×3 U(3)J；
5. Let l=0；
6. for each nЄ[1,2,3]；
7. A·=A；
8. For each m Є[1,n-1] and m≠n Do；
9. A·= A·×mU(m)J l+1；
10. End for；
11. For each m Є[n,3] Do；
12. A·= A·×mU(m)J l；
13. End for；
14. (U(n) l+1,Σ(n) l+1,V(n) l+1)=SVD(uf(A·,n),R)；
15. End for；
16. Cl+1=A×1 U(1)J l+1×2 U(2)J l+1×3U(3)J l+1；
17. if llCl+1ll2-llC1ll2≤QUIT。
Claims (2)
- A kind of 1. tensor resolution e-commerce user trust recommendation algorithm based on theme, it is characterised in that：Pass through The commending system of TrustTensor algorithms crosses the binary crelation excavated between e-commerce user and project, helps user from big The project (such as Web information, service, online commodity) that it may be interested is found in amount data, and generates personalized theme and pushes away Recommend to meet individual requirements.
- 2. according to the method for claim 1, it is characterised in that the community network based on users to trust and tensor resolution pushes away Recommend, the alternating least-squares of use realize that tensor N rank approximations develop rustTensor algorithms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610588465.2A CN107657491A (en) | 2016-07-25 | 2016-07-25 | A kind of tensor resolution e-commerce user trust recommendation algorithm based on theme |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610588465.2A CN107657491A (en) | 2016-07-25 | 2016-07-25 | A kind of tensor resolution e-commerce user trust recommendation algorithm based on theme |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107657491A true CN107657491A (en) | 2018-02-02 |
Family
ID=61126984
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610588465.2A Pending CN107657491A (en) | 2016-07-25 | 2016-07-25 | A kind of tensor resolution e-commerce user trust recommendation algorithm based on theme |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107657491A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109121A (en) * | 2023-04-17 | 2023-05-12 | 西昌学院 | User demand mining method and system based on big data analysis |
-
2016
- 2016-07-25 CN CN201610588465.2A patent/CN107657491A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109121A (en) * | 2023-04-17 | 2023-05-12 | 西昌学院 | User demand mining method and system based on big data analysis |
| CN116109121B (en) * | 2023-04-17 | 2023-06-30 | 西昌学院 | User demand mining method and system based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12014390B2 (en) | Systems and methods for shopping in an electronic commerce environment | |
| US9744466B2 (en) | Widgetized avatar and a method and system of creating and using same | |
| Lee et al. | Managing consumer privacy concerns in personalization: a strategic analysis of privacy protection | |
| JP5945369B2 (en) | Method and system for recommending target article information | |
| US8380577B2 (en) | Methods, systems, computer products, and website for progressive E-commerce | |
| US20100199200A1 (en) | Virtual Marketplace Accessible To Widgetized Avatars | |
| US20140081681A1 (en) | Self correcting online reputation | |
| US20120124192A1 (en) | Using behavioral data in rating user reputation | |
| US20090182612A1 (en) | System and method for online sizing and other applications involving a root measurable entity | |
| US20200118198A1 (en) | Systems and methods for sms e-commerce assistant | |
| WO2013145454A1 (en) | Information provision device, information provision method, information provision program, and computer-readable recording medium storing program | |
| CN103971256A (en) | Information push method and device | |
| Greenstein | Digitization and value creation | |
| Murni et al. | Analysis of The Influence of Trust, Easiness in Shopping, Product Quality to Customer Satisfaction To Increasiness in Shopping Consumer Loyalty Online Shopping | |
| CN111104606A (en) | Weight-based conditional wandering chart recommendation method | |
| WO2012103462A2 (en) | Systems and methods for shopping in an electronic commerce environment | |
| Sağlam et al. | The effects of E-satisfaction, E-brand loyalty and E-trust levels on consumer behavioral intentions: A study on online shoppers in turkey | |
| CN107657491A (en) | A kind of tensor resolution e-commerce user trust recommendation algorithm based on theme | |
| Orzoł et al. | E-commerce and the development of communication infrastructure in Poland | |
| WO2009136262A1 (en) | Reverse portal system and method | |
| KR20090034008A (en) | Method, system and server for providing combined information | |
| Ke | The e-commercial quality components impact on customers’ purchase intention | |
| CN106097010A (en) | A kind of merchandise news update method and device | |
| CN101989339A (en) | On-line book control system and method | |
| Choudhury et al. | A Comparative Study on'E-Commerce Verses M-Commerce: The Future of Online Marketing' |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180202 |