A radio station recommendation method and system
A recommendation method and radio technology, applied in the fields of electrical digital data processing, instruments, calculations, etc., can solve the problems of low diversity of songs and the inability to guarantee the pleasantness of songs, etc.
Active Publication Date: 2021-03-19
BEIJING KUWO TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Manually edited radio stations, the variety of songs in the radio station is not high, and the song's goodness cannot be guaranteed
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
[0023] The technical solutions of the present invention will be described in further detail below with reference to the accompanying drawings and embodiments.
[0024] figure 1 A schematic structural diagram of a station recommendation method provided by an embodiment of the present invention. Such as figure 1 As shown, the steps of the station's recommended method include:
[0025] Step S100: Obtain the user's preference score for playing songs according to the user's listening behavior and the source of the song, and then form the user's preference matrix for listening to songs according to the preference score;
[0026] Calculate the preference score of the song according to the user's listening behavior and source of listening to the song. The behavior of listening to songs is divided into active listening to songs and passive listening to songs. Active song listening behaviors include: heart, cancel heart, download, favorite, search, purchase, local upload; passive so...
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 relates to a radio station recommendation method and system. The radio station recommendation method comprises the steps that according to a song listening behavior and a song listeningsource of a user, preference scores of played songs of the user are obtained, and then a user song listening preference matrix is formed according to the preference scores, wherein the song listeningbehavior comprises an active song listening behavior. According to the active song listening behavior and the preference scores of the played songs of the user, a playing list is generated, song wordvectors corresponding to all the songs in the playing list are obtained by using a deep learning tool, the similarity of each song with the other songs in the playing list is calculated, and a user song listening similar matrix is formed according to the similarities of all the songs in the playing list. According to the user song listening preference matrix and the user song listening similar matrix, the songs are selected, the similar score of each song in the selected songs is calculated, and final recommended songs are obtained. According to the final recommended songs, a song radio station is established and recommended to the user. According to the radio station recommendation method and system, the songs which are matched with the user are selected to establish the radio station according to a user information label, and the quality of the radio station and the pleasant listening degrees and diversity of the songs are guaranteed.
Description
technical field [0001] The invention relates to personalized recommendation of big data and machine learning algorithms, in particular to a radio station recommendation method and system. Background technique [0002] Currently, radio stations are generally edited manually, and each user sees the same radio interface. The effect of this manual recommendation is very poor, and the efficiency is not high. [0003] Manually edited radio stations are mainly popular songs, old songs and other songs, and the recommendation form is single. [0004] Currently, the recommendation of radio stations is done by manual editors. The workload is heavy, the editing efficiency is not high, and the songs in the same radio station are not highly relevant, which cannot meet the needs of every user for listening to songs. In order to improve work efficiency and radio recommendation relevance, machine learning algorithms are used instead of manual editing strategies. [0005] The radio station...
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): G06F16/635
CPCG06F16/637
Inventor 王志鹏高玉敏
Owner BEIJING KUWO TECH