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

Social network representation method based on bidirectional distance network embedding

A social network and directed distance technology, applied in the field of social network representation, can solve the problems of inaccurate representation of the structure and topology information of social relationship networks, no consideration of the direction and distance between nodes and nodes, and low ability to restore real social relationships. To achieve the effect of improving the effect and performance, improving the restoration ability, and improving the effectiveness

Pending Publication Date: 2019-07-09
HARBIN INST OF TECH AT WEIHAI +1
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention solves the problem that the existing network data representation technology does not consider the direction and distance of the edges between nodes, so that the structure and topology information of the social network is inaccurate, and the ability of network embedding to restore the real social relationship is low, so it will not be able to The problem of effectively processing network data and accurately and effectively controlling the development of events provides a social network representation method based on two-way distance network embedding

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
  • Social network representation method based on bidirectional distance network embedding
  • Social network representation method based on bidirectional distance network embedding
  • Social network representation method based on bidirectional distance network embedding

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0021] Specific implementation mode one: combine figure 1 To illustrate this embodiment, a social network representation method based on two-way distance network embedding given in this embodiment specifically includes the following steps:

[0022] Step 1. Read the nodes in the social relationship network, and uniquely encode the nodes to obtain the node code set; the original social relationship network includes the node set V and the directed edge set where v m ,v n ∈V, Represents the existence of a slave node v m point to v n side of v m follow v n ;

[0023] Step 2. Read the attention and followed relationship in the social relationship network, that is, the direction of the edge (directed edge) between nodes, and generate a sequence of upper neighbor nodes and lower neighbors with a window size of k for each node. node sequence, and record the directed distance from each neighbor node to the node; the above neighbor node is a node that directly or indirectly pay...

specific Embodiment approach 2

[0031] Specific implementation mode 2: The difference between this implementation mode and specific implementation mode 1 is that

[0032] The encoding method described in step 1 is one-hot encoding or binary encoding. The following uses one-hot encoding as an example to describe in detail:

[0033] Establish a mapping relationship from node set V to node one-hot encoding set D, such as (v i )→(0,0,0,1,...,000), where the number of one-hot encoding bits is equal to the number of nodes, and each node is only valid on its feature bit, that is, it is 1 in this position, and in other The values ​​on the feature bits are all 0, and the feature bits of each node are different.

[0034] Other steps and parameters are the same as those in the first embodiment.

specific Embodiment approach 3

[0035] Embodiment 3: The difference between this embodiment and Embodiment 2 is that in the sequence of neighbor nodes mentioned above in Step 2, each step of the walk in the generation process only focuses on the reverse edge, that is, the next node directly focuses on the current node the node;

[0036] Such as image 3 Shown is a schematic diagram of depth-first traversal (DFS) and breadth-first traversal (BFS) strategies in graph traversal. BFS pays more attention to micro-local information, and DFS pays more attention to macro-global information. The Bidirectional-Node-Walk strategy in the present invention separates the above and below sequences of nodes, and the generation strategy formula is as follows:

[0037]

[0038] Among them, t is the previous access node of the current access node, and x is the next node that may be accessed (x1, x2, and x3 in the figure refer to different next node x); d + (t,x) indicates the number of edges that are visited from the dire...

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 provides a social network representation method based on bidirectional distance network embedding, and belongs to the technical field of data mining and networks. The method comprises the following steps: firstly, reading nodes in a social relation network and encoding; secondly, reading a concerned and concerned relationship, respectively generating an upper text neighbor node sequence and a lower text neighbor node sequence with the window size of k for each node, and recording a directed distance from each neighbor node to the node; constructing a three-layer network embeddingmodel; learning by taking the node coding set as input, and continuously adjusting model hyper-parameters; and finally, taking the weight matrix of the hidden layer as a final network embedding result, and taking the vector representation of each row as the vector representation of the node. According to the method, the problems that the structure and topology information of the existing social relation network are inaccurate in representation, the capability of restoring the real social relation is low, network data cannot be effectively processed, and the development of events cannot be accurately and effectively controlled are solved. The method can be used for social network representation.

Description

technical field [0001] The invention relates to a social network representation method, which belongs to the field of data mining and network technology. Background technique [0002] Many complex systems process data in the form of network structures, such as social networks, biological networks, and information networks. As we all know, network data is usually complex and therefore difficult to process, mainly in terms of high computational complexity, low parallelism, and difficulty in utilizing existing machine learning, deep learning methods, etc. In order to process network data more effectively, the primary challenge is to find an efficient network data representation method, so that upper-level data analysis tasks, such as: data mining, analysis, prediction, etc., can be efficiently performed in limited space and time. As a very promising network representation method, network embedding can support a series of network processing and analysis tasks, such as: node cla...

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
IPC IPC(8): G06F16/9536G06Q50/00
CPCG06Q50/01
Inventor 朱东杰孙云栋杜海文王玉华李晓芳曲荣宁胡浩舒钰博吴峰孙一恒董爽爽张凯
Owner HARBIN INST OF TECH AT WEIHAI
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com