Supercharge Your Innovation With Domain-Expert AI Agents!

Service recommendation method and system, and server

A technology for service recommendation and user service, which is applied in the field of service recommendation methods, systems and servers, can solve the problem of low prediction accuracy of service recommendation methods, and achieve the effect of increasing reliability

Active Publication Date: 2018-09-21
WENZHOU UNIVERSITY
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a service recommendation method, system and server to solve the problem of low prediction accuracy of the service recommendation method in the prior art

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
  • Service recommendation method and system, and server
  • Service recommendation method and system, and server
  • Service recommendation method and system, and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] This embodiment of the present invention selects user service training data from the database, predicts the unsampled data by using the method in this embodiment, and compares the predicted data with the sampled real data to verify the service in this embodiment. Validity of the recommended method. Among them, since the service recommendation mechanism is related to two factors, one is the service function, and the other is the service quality. The parameters affecting the service quality are the service response time and the data throughput. In this embodiment, the service response time and data throughput are analyzed by The two data subsets are recommended respectively to verify the applicability of the service recommendation method in this embodiment to the data.

[0075] see figure 1 , showing a schematic diagram of the implementation flow of the service recommendation method provided by the embodiment of the present invention, and the details are as follows:

[...

Embodiment 2

[0137] Corresponding to the service recommendation method provided in the first embodiment above, image 3 A schematic structural diagram of a service recommendation system provided by an embodiment of the present invention is shown, and the details are as follows:

[0138] The service recommendation system provided in this embodiment includes: an information collection module 301 , a matrix decomposition module 302 , a similarity calculation module 303 , a first prediction module 304 , a second prediction module 305 , and a recommendation module 306 .

[0139] The information collection module 301 acquires the service quality information of each service in the recommended service set for each user in the user set, and constructs a user service matrix.

[0140] A matrix decomposition module 302, connected to the information collection module 301, is configured to perform matrix decomposition on the user service matrix to obtain a user relationship matrix and a service relation...

Embodiment 3

[0170] see Figure 5 , showing a schematic diagram of the implementation flow of another service recommendation method provided by an embodiment of the present invention, which is described in detail as follows:

[0171] Step S501, initialize matrix decomposition parameters, the number of adjacent users and fusion parameters; wherein the matrix decomposition parameters include a minimum convergence threshold and a maximum number of iterations.

[0172] Step S502, initialize the user relationship matrix and the service relationship matrix; when performing matrix decomposition, first generate a random matrix for the user relationship matrix and the service relationship matrix, and then update the user relationship matrix and the service relationship matrix by an iterative method.

[0173] Step S503: Calculate the loss function between the product of the user service matrix, the user relationship matrix and the service relationship matrix; here, the predicted value and the real v...

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 is suitable for the technical field of network recommendation, and provides a service recommendation method and system, and a server. The method comprises the steps of obtaining servicequality information of services in a to-be-recommended service set by users in a user set, and constructing a user service matrix; performing matrix decomposition on the user service matrix to obtaina user relationship matrix and a service relationship matrix; according to the user relationship matrix, calculating and correcting a user similarity matrix; performing multiplication operation on theuser relationship matrix and the service relationship matrix to obtain a first predicted recommendation result; according to the corrected user similarity matrix and observation values of the users,obtaining a second predicted recommendation result; and performing weighted fusion on the first predicted recommendation result and the second predicted recommendation result to obtain a user servicerecommendation matrix. According to the method, the problem of inaccurate user similarity matrix caused by data sparseness is solved by adopting random walk; the matrix dimensions are reduced by adopting the matrix decomposition method; and the service recommendation precision is improved by combining the random walk and the matrix decomposition method.

Description

technical field [0001] The invention belongs to the technical field of network recommendation, and in particular relates to a service recommendation method, system and server. Background technique [0002] Service-Oriented Architecture (Service-Oriented Architecture, SOA), as a new distributed computing model, has played an important role in the fields of e-commerce and application integration. The core idea of ​​SOA is to emphasize the service as the basic unit, to discover and combine a series of services that meet the needs of users. Wherein, in a distributed environment, various functions are provided to end users or other services in the form of services. [0003] With the rapid development of SOA and Web services, the number of Web services available on the network has increased dramatically, so the recommendation mechanism based on Web services has become a major concern. The web service recommendation mechanism mainly considers two aspects, one is service function,...

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): G06F17/30
Inventor 李俊林坚
Owner WENZHOU UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com