Interest recommendation method and system based on user sequence click behavior
An interest recommendation, user technology, applied in special data processing applications, instruments, electrical digital data processing and other directions, can solve the problem of not considering the internal structure of the sequence, only considering the item sequence pattern, ignoring the item sequence conversion relationship, etc. Conducive to parallel processing, easy parallel processing, and improved recommendation performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0053] Example one
[0054] figure 1 It is a flowchart of an interest recommendation method based on a user's sequential click behavior involved in this embodiment. The interest recommendation method first divides the user's interaction sequence into different sessions according to the user's preferences in a certain period of time, and then combines the user interest in each session and the interest interaction between different sessions to implement sequence recommendation , To effectively make up for the existing sequence recommendation methods ignore the inherent structure of user sequence behavior and ignore the conversion relationship between items.
[0055] See attached figure 1 , The method of interest recommendation based on user sequence click behavior includes the following steps:
[0056] S101: Obtain a user's historical interactive item sequence.
[0057] Specifically, the user's historical interaction item data is acquired to form the user's historical interaction item ...
Example Embodiment
[0106] Example two
[0107] Figure 4 It is a structural diagram of an interest recommendation system based on a user's sequential click behavior involved in this embodiment. Such as Figure 4 As shown, the system includes:
[0108] The data acquisition module is used to acquire the user's historical interactive item data to form the user's historical interactive item sequence;
[0109] Model building module, used to build interest recommendation model;
[0110] The session division module is used to divide the user's historical interactive item sequence by using the interest recommendation model;
[0111] The in-session interest extraction module is used to extract each in-session interest obtained after division;
[0112] The activation module is used to assign different weights to the interest in each conversation to obtain the user's conversation interest sequence;
[0113] Inter-session interest interaction module, used to interact the interests between different sessions to obtain ...
Example Embodiment
[0115] Example three
[0116] This embodiment provides a computer-readable storage medium with a computer program stored on the computer-readable storage medium, and when the program is executed by a processor, the following steps are implemented:
[0117] Obtain the user's historical interactive item data to form the user's historical interactive item sequence;
[0118] Construct an interest recommendation model;
[0119] Use the interest recommendation model to divide the user's historical interactive item sequence into conversations;
[0120] Extract the interests in each session obtained after division, and perform weighting processing on the interests in each session to obtain the user's session interest sequence;
[0121] Interact the interests between different sessions to obtain a dynamic interaction model between different sessions;
[0122] Input the user's conversational interest sequence into the dynamic interaction model between different conversations, and predict the target...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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