Recurrent neural network method for improving time sequence data mining capability of recommendation model

A cyclic neural network and time series data technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problem of failing to directly use the time information of sequence data, and achieve the effect of improving mining ability and accuracy.

Inactive Publication Date: 2018-04-13
ZHEJIANG UNIV
View PDF3 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The Long Short Term Memory (LSTM) model is one of the models that utilize temporal information in neural net

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
  • Recurrent neural network method for improving time sequence data mining capability of recommendation model
  • Recurrent neural network method for improving time sequence data mining capability of recommendation model
  • Recurrent neural network method for improving time sequence data mining capability of recommendation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In order to make the purpose, technical solution and advantages of the present invention clearer, a model combining cyclic neural network structures such as LSTM and time gates will be used below (for the convenience of description, Time-LSTM will be used to refer to the combination model hereinafter) to The time gate is further described in terms of specific functions.

[0052] Such as figure 1 As shown, it is a flow chart of the cyclic neural network method for improving the time-series data mining ability of the recommendation model in the present invention.

[0053] First, according to step 1, modify the traditional neural network and add time gate components to the network.

[0054] In order to modify a traditional neural network, a brief overview of its basic model is first given. Such as figure 2 As shown, the basic LSTM model has three gate structures: input gate, forget gate, and output gate.

[0055] Input gate: The role of the input gate is to determine ...

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 recurrent neural network method for improving the time sequence data mining capability of a recommendation model. The method includes the following steps that: step 1, time gate-based network transformation is performed on a conventional neural network; step 2, interaction interval time-added time sequence data are inputted into a model; step 3, the prediction values of the model on each item of the sequence are calculated; step 4, the loss value of the model is calculated, if the loss value is lower than a preset value and tends to be stable, step 6 is executed, otherwise, step 5 is executed; step 5, the gradient of each parameter is calculated according to the loss value, the parameters are updated, the method returns to the step 3; and step 6, the interest of auser is predicted based on the current model. With the method of the invention adopted, the time information mining capacity of the neural network in the recommendation field can be improved, and themodel can process long-term general features and short-term temporary features contained in long-term data more easily, and can perform even better in a personalized recommendation system.

Description

technical field [0001] The invention relates to the field of machine learning and personalized recommendation, in particular to a cyclic neural network method for improving the time series data mining ability of a recommendation model. Background technique [0002] The rapid development of the information society has accumulated a large amount of data, and the historical data generated by users on the Internet reflects their own interests and hobbies. These data provide Internet vendors with the possibility to predict user interests and make targeted recommendations. The recommendation system is an effective way for Internet manufacturers to recommend products to users, and its accuracy directly affects the return rate of manufacturers' advertising investment and the user's consumption experience. [0003] At present, the recommendation system has been widely used in the fields of commodities, music, news and so on. The recommendation model mostly uses the user's purchase ...

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): G06Q30/06G06F17/30G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06Q30/0631G06F16/9535
Inventor 祝宇李昊蔡登
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap