A method for long-tail recommendation problem based on extracting effective multi-objective groups
A multi-objective, multi-objective optimization technology, applied in the field of long-tail recommendation problems, can solve problems such as slow training speed, difficulty in adjusting multiple target relationships, increased difficulty and time complexity, etc., to achieve the effect of improved results
Active Publication Date: 2022-07-15
ZHEJIANG UNIV CITY COLLEGE
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In multi-objective optimization, increasing the objective function will lead to a large number of iterations, slow training speed, and it is difficult to adjust the relationship between multiple objectives
In a collaborative filtering model combined with a neural network, adjusting the model structure will inevitably lead to an increase in the difficulty and time complexity of sample training under complex models
Moreover, these two methods will inevitably encounter the problem of difficult training when faced with small sample data
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
[0047] In order to make those skilled in the art better understand the technical solutions of the present invention, the preferred embodiments of the present invention will be described below with reference to specific examples, but it should be understood that the accompanying drawings are only used for exemplary descriptions, and should not be construed as comprehension of the present invention. Limitation; in order to better illustrate this embodiment, some parts of the drawings will be omitted, enlarged or reduced, which do not represent the size of the actual product; for those skilled in the art, some well-known structures and their descriptions in the drawings may be The omission is understandable. The positional relationships described in the drawings are only for exemplary illustration, and should not be construed as limiting the present invention.
[0048] The present invention will be further described below in conjunction with the accompanying drawings and embodime...
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 present invention provides a method for solving the long-tail recommendation problem based on extracting effective multi-target groups. S1: Obtaining a historical scoring data set: S2: Constructing a two-dimensional weighted similarity of users based on the modified cosine distance and Euclidean distance: S3 : Re-ranking model based on multi-objective optimizer to find the best similar user groups for recommendation. The invention fully exploits user preferences, not only pays attention to the accuracy of the overall recommendation, but also considers the accuracy and coverage of long-tail items.
Description
technical field [0001] The invention relates to the technical field of recommendation decision-making systems, and can be used in the fields of commodity recommendation, behavior decision-making, risk warning and the like. Specifically, it relates to a method for solving the long-tail recommendation problem based on extracting effective multi-objective groups. Background technique [0002] In the fields of product recommendation, decision support, risk warning, etc., if there are a large number of candidates, how to choose the appropriate behavior is a difficult point, and a recommendation system needs to be used. Most traditional recommendation algorithms tend to pursue a high recommendation accuracy rate, which results in the recommendation rate of popular options even exceeding their actual popularity, while the resource utilization and sales potential of non-popular options are ignored. This is a typical long-term trend. tail problem. For example, long-tail products of...
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 Patents(China)
IPC IPC(8): G06F16/9535G06F16/9536G06K9/62
CPCG06F16/9535G06F16/9536G06F18/22
Inventor 金苍宏邵育华何琴芳缪锋王硕苹吴明晖
Owner ZHEJIANG UNIV CITY COLLEGE