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

Cross-social media user identity recognition method and system based on attention mechanism

A user identification and social media technology, applied in the field of cross-social media user identification based on the attention mechanism, can solve problems such as ignoring generated data and poor model interpretability, achieve good behavior characteristics, good user matching, and improve reliability explanatory effect

Active Publication Date: 2019-09-06
SHANDONG UNIV
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, existing technologies mainly rely on user configuration information (username, birthday, gender) and social network structure, ignoring richer user-generated data, making the model less interpretable

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
  • Cross-social media user identity recognition method and system based on attention mechanism
  • Cross-social media user identity recognition method and system based on attention mechanism
  • Cross-social media user identity recognition method and system based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] In order to achieve the above purpose, this embodiment realizes cross-social media user identity identification by learning the accurate representation of user multi-source heterogeneous data and combining the internal timing relationship of user-generated data. Since different modalities in user-generated data have different confidence levels in cross-social media user identification, the attention mechanism is introduced to realize the automatic allocation of different modal confidence levels, thereby improving the modeling performance and model accuracy of cross-social media user identification. interpretability. Specifically, the present embodiment provides a cross-social media user identification method based on attention time perception user modeling, comprising the following steps:

[0033] S1: Capture different modal data of users on different social media, and use different models to learn the potential representation of data for different modal data;

[0034]...

Embodiment 2

[0076] The purpose of this embodiment is to provide a cross-social media user identification system.

[0077] In order to achieve the above object, the present embodiment provides a cross-social media user identification system based on attention mechanism, including:

[0078] The data acquisition module captures data of different modalities of users on different social media;

[0079] The data representation module, for data of different modalities, uses different models to learn the potential representation of data;

[0080] The model training module and the user similarity calculation module combine the temporal relationship and the confidence of different modal data to calculate the similarity of data between users on different social media; the probability calculation module uses a multi-layer perceptron to calculate the similarity between users Mapped to the probability space, the probability that users on different social media point to the same user entity; use cross-...

Embodiment 3

[0083] The purpose of this embodiment is to provide an electronic device.

[0084] In order to achieve the above object, this embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, when the processor executes the program, it realizes:

[0085] For data of different modalities, different models are used to learn the potential representation of the data, and the user identification model is trained:

[0086] Calculate the similarity of data between users on different social media by combining the temporal relationship and the confidence of different modal data;

[0087] Use a multi-layer perceptron to map the similarity between users to a probability space, and obtain the probability that users on different social media point to the same user entity;

[0088] Using cross entropy to construct the objective function, iteratively optimize and solve the model parameters;

[0089] The mod...

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 a cross-social media user identity recognition method and method based on an attention mechanism. The method comprises the following steps: acquiring data of different modalities of a plurality of users on different social media to serve as training data; for data of different modalities, respectively adopting different models to learn potential representations of the data,and training a user identity recognition model; calculating the similarity of the data between the users on different social media by combining a time sequence relation and confidence coefficients ofthe data of different modalities; mapping the similarity between the users to a probability space by using a multi-layer perceptron to obtain the probability that the users on different social mediapoint to the same user entity; constructing an objective function by adopting cross entropy, and carrying out iterative optimization solution on model parameters, wherein the model is used for determining whether to point to the same user or not according to different modal data on different social media. According to the method, the difference of data transmission of different modes of data is considered, and the user identity recognition accuracy is higher.

Description

technical field [0001] The invention relates to the technical field of user identification, in particular to an attention mechanism-based cross-social media user identification method and system. Background technique [0002] In today's era when cross-social media is becoming more mature and user-generated data is gradually becoming multi-sourced, users' multi-source heterogeneous data can often reflect their daily life from different angles and reflect their attributes from different aspects. The organic integration of user behavior data scattered on multiple social media brings the possibility of in-depth understanding of user behavior, analysis of user characteristics, and comprehensive user modeling. In essence, user identification across social media is the premise of subsequent user integration, so it has attracted the attention of many researchers. However, existing techniques mainly rely on user profile information (username, birthday, gender) and social network str...

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): G06K9/62G06Q50/00G06N3/04G06N3/08
CPCG06Q50/01G06N3/084G06N3/044G06N3/045G06F18/22
Inventor 崔思伟宋雪萌陈潇琳尹建华刘萌甘甜
Owner SHANDONG 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

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