Recommendation method and system based on metadata enhancement
A recommendation method and metadata technology, applied in the field of recommendation methods and systems based on metadata enhancement, can solve problems such as sparse data and poor performance in cold start scenarios
Active Publication Date: 2021-09-28
四川省人工智能研究院(宜宾)
View PDF13 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Aiming at the above-mentioned deficiencies in the prior art, the present invention provides a metadata-enhanced recommendation method and system to solve the problem of poor performance of the existing computer personalized recommendation technology in sparse data and cold start scenarios
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0058] The specific embodiments of the present invention are described below so that those skilled in the art can understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes Within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are included in the protection list.
[0059] Such as figure 1 As shown, in one embodiment of the present invention, a kind of recommendation method based on metadata enhancement comprises the following steps:
[0060] S1. Training a cross-domain adaptive encoding and decoding model through user preference data.
[0061] Wherein, the user preference data includes: source domain user item connection content, target domain user item connection content, source dom...
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
Login to View More Abstract
The invention discloses a recommendation method and system based on metadata enhancement, and relates to the technical field of computer personalized recommendation, and the method comprises the steps: training a cross-domain adaptive coding and decoding model through user preference data; performing meta-enhancement on the score of the target domain user item combination through the trained cross-domain adaptive coding and decoding model; performing meta-learning training on the recommendation model; and performing item recommendation on the user through the trained recommendation model. Before meta-learning training of a recommendation model, a cross-domain adaptive coding and decoding model is trained through user preference data, and meta-enhancement is performed on data required by meta-learning training of the recommendation model by using the cross-domain adaptive coding and decoding model. The problem of overfitting caused by sparse user and project data and lack of cold start processing capability of existing meta-learning training of a recommendation model is effectively solved, and preferred projects can be accurately recommended for the user.
Description
technical field [0001] The invention relates to the technical field of computer personalized recommendation, in particular to a metadata-enhanced recommendation method and system. Background technique [0002] Computer-based personalized recommendation technology is one of the most critical and effective methods to alleviate information overload, and it is also a key factor in various applications, such as online e-commerce sites Amazon, Netflix, Yelp, online education and news systems. Typically, recommender systems recommend personalized lists containing the most interesting items to a specific user. [0003] The existing recommendation system is mainly based on the user's previous behavioral interaction, such as purchase records, ratings, click actions, viewing records, etc., so it is also called collaborative filtering (CF, collaborative filtering) recommendation system, which has proved to be very successful. The categories of CF recommender systems include: user-based...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9536G06Q30/06G06N3/04
CPCG06F16/9536G06Q30/0631G06N3/045
Inventor 许辉李长宇张艳邵杰
Owner 四川省人工智能研究院(宜宾)