Individual recommending method based on multi-view anchor graph Hash technology
An anchor graph hashing and recommendation method technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as affecting computing efficiency, unable to fully represent user characteristics, etc., to achieve the effect of improving quality
Active Publication Date: 2016-09-21
ZHEJIANG UNIV
View PDF3 Cites 14 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, these methods only use the data of users in a single view, and cannot fully represent the characteristics of users. In addition, traditional methods usually directly use user behavior data to calculate the similarity between users, resulting in a large number of high-dimensional vector operations. computational efficiency
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
[0048] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0049] Such as figure 1 As shown, a kind of personalized recommendation method based on multi-view anchor graph hash technology of the present invention comprises the following steps:
[0050]1) According to the behavior data of training users in different views, construct a multi-view anchor graph representation of user data; specifically include the following sub-steps:
[0051] 1.1) For the behavior data matrix of the training user in the i-th view where N represents the number of training users, d i Indicates the dimension of user data under the i-th view, and uses the K-means clustering method to generate T i cluster center, as the anchor point of the data under this view, T i The value of is related to the number of users, generally around N / 200, but it must be greater than the set number of bits R of the hash code;
[0052] 1.2) Horizontally conn...
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 an individual recommending method based on a multi-view anchor graph Hash technology. The method comprises the steps of 1), establishing multi-view anchor graph representation of user data according to behavior data of a user in different views; 2), generating user Hash codes in continuous space by use of the obtained multi-view anchor graph and the behavior data of the user; 3), quantifying the Hash codes in the continuous space, thereby obtaining binary Hash codes corresponding to the user; 4), searching similar users for the target user by use of the obtained user Hash codes; and 5), calculating the preference degree of the target user to the candidate objects by taking the preferred object set corresponding to the similar users as a recommending candidate list, and returning a plurality of objects of which the preference degree is the maximum as a recommending result. According to the method, the data of the user in different views is integrated, the quality of the recommending result is improved, moreover, the similar users are searched rapidly by use of the Hash codes with reserved similarity, and the calculating efficiency of the recommending result is improved.
Description
technical field [0001] The invention relates to a personalized recommendation technology, in particular to a personalized recommendation method based on a multi-view anchor graph hashing technology. Background technique [0002] With the continuous development of information technology and network technology, the information and resources on the Internet have experienced explosive growth. However, the huge amount of information and the existence of a large number of low-quality and low-value information mixed in it make the efficiency of users' acquisition and utilization of information continue to decline. In order to deal with the problem of information acquisition under massive data scale, personalized recommendation system is an effective solution. The personalized recommendation system predicts the user's preference through different methods based on the user's personal data, behavior data, social relationship and other information, so as to actively push some specific...
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): G06F17/30
CPCG06F16/9535
Inventor 张寅魏宝刚金登科
Owner ZHEJIANG UNIV