Recommended content determination method and device and storage medium

A technology for recommending content and determining methods, applied in biological neural network models, marketing, advertising, etc., can solve problems such as inability to personalize recommendations for new content and new users, modeling of new content and new users

Inactive Publication Date: 2021-05-07
SENSOR NETWORKS TECH BEIJING CO LTD
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a method, device, and storage medium for determining recommended content, to at least solve the probl

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
  • Recommended content determination method and device and storage medium
  • Recommended content determination method and device and storage medium
  • Recommended content determination method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0024] Example 1

[0025] According to an embodiment of the present invention, a method for determining recommended content is provided, such as figure 1 As shown, the method includes:

[0026] S102, according to the prediction neural network model, determine the predicted click probability corresponding to the multiple content to be recommended corresponding to the user, wherein the prediction neural network model is obtained by training according to the user's user characteristics, the user's historical browsing content and the content to be recommended;

[0027] S104 , sort a plurality of to-be-recommended contents according to the predicted click probability to determine target recommended contents.

[0028] In the related art, there are generally a plurality of contents to be recommended for a user, which are located in the to-be-recommended contents library, and are ready to be recommended for the user. For example, content that is displayed for the user when the user ...

Example Embodiment

[0048] Example 2

[0049] According to an embodiment of the present invention, there is also provided a recommended content determination device for implementing the above recommended content determination method, such as Figure 4 As shown, the device includes:

[0050] 1) A determination unit 40, configured to determine the respective predicted click probabilities corresponding to a plurality of contents to be recommended corresponding to the user according to the predicted neural network model, wherein the predicted neural network model is based on the user characteristics of the user, the user's The historical browsing content and the content to be recommended are obtained from training;

[0051] 2) The processing unit 42, configured to sort the plurality of contents to be recommended according to the predicted click probability to determine the target recommended contents.

[0052] Optionally, in this embodiment, it also includes:

[0053] 1) a first acquiring unit, co...

Example Embodiment

[0058] Example 3

[0059] Embodiments of the present invention also provide a storage medium. Optionally, a storage medium, the storage medium includes a stored program, wherein when the program runs, the above-mentioned method for determining recommended content is executed.

[0060] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0061] S1, according to the prediction neural network model to determine the respective predicted click probabilities corresponding to the multiple contents to be recommended corresponding to the user, wherein the predicted neural network model is based on the user characteristics of the user, the user's historical browsing content and the to-be-recommended content content training;

[0062] S2 sorts the plurality of contents to be recommended according to the predicted click probability to determine the target recommended contents.

[0063] Optionally, in this embodimen...

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 embodiment of the invention relates to a recommendation content determination method and device and a storage medium. The method comprises the steps of determining predicted click probabilities corresponding to multiple to-be-recommended contents corresponding to a user according to a predicted neural network model, and sorting the multiple to-be-recommended contents according to the predicted click probabilities to determine target recommended contents. According to the invention, the technical problem that accurate personalized recommendation cannot be carried out for new contents and new users due to the fact that a recommendation system in the related technology cannot carry out modeling on the new contents and the new users is solved.

Description

technical field [0001] The present invention relates to the field of advertisement delivery, in particular to a method, device and storage medium for determining recommended content. Background technique [0002] With the research and development of deep learning technology, the application of deep learning to recommendation systems is also known as a research hotspot. More and more recommendation systems have begun to adopt deep learning technology, and have achieved significant performance improvements. The solutions represented by (DeepNeural Networks for YouTube Recommendations) and (DSSM) use user behavior data and apply deep learning to the recommendation system, which has achieved significant improvement. [0003] In this type of algorithm based on user behavior, there is a cold start problem of new content and new users. This problem is due to the lack of user behavior of new content and new users, and it is difficult for deep learning algorithms to model them, so ...

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): G06F16/9535G06N3/04G06Q30/02
CPCG06F16/9535G06Q30/0255G06Q30/0271G06N3/047G06N3/045
Inventor 桑文锋曹犟刘耀洲付力力胡士文
Owner SENSOR NETWORKS TECH BEIJING CO LTD
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