Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Improved content-based television music recommendation method

A recommendation method, music technology, applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve the problem of not being able to broaden the dimension of interest, and achieve the effect of reducing the amount of data calculation, improving comfort, and improving computing efficiency

Active Publication Date: 2020-12-11
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this algorithm can only recommend items contained in the dimension of interest represented by the user’s historical behavior data for the user, but cannot broaden the dimension of interest for the user based on the current interest, and recommend items of different dimensions

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Improved content-based television music recommendation method
  • Improved content-based television music recommendation method
  • Improved content-based television music recommendation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Such as figure 1 , figure 2 As shown, an improved content-based TV music recommendation method, including:

[0032] S1. Obtain the dimensions in the user's historical data information; the dimensions described in the present invention can be understood as types of data information.

[0033] S2. Obtain the user collection corresponding to each dimension;

[0034] S3. Calculate the corresponding Jaccard similarity between each dimension according to the user collection; the calculation formula for calculating the Jaccard similarity is J(A, B)=(A∩B) / (A∪B), where A and B respectively represent the corresponding user collection in one dimension.

[0035] S4. Perform interest scoring on dimensions;

[0036] S5. Obtain the data information under each dimension and sort according to the degree of interest of all users;

[0037] S6. Select the top X dimension of dimension interest score and the corresponding top Y dimension of Jaccard similarity to form a dimension set;

...

Embodiment 2

[0046] On the basis of Example 1, such as image 3 As shown, in this embodiment, a specific music recommendation is taken as an example for description. An improved content-based TV music recommendation method, including:

[0047] S11. Sorting the user's historical data information by interest degree; extracting the music data listened to by the user in the past three months, and according to the existing data, the frequency of listening to music and the percentage of listening time of the song are used for weighted summation as the user's rating of the song. Sort by rating.

[0048] S12. Extract the dimensions of all the interest information of the top W; extract all the interest dimensions of the top 20 songs scored by users, the complete set of interest dimensions are: pop, rock, hip-hop, light music, jazz, classical, folk, electronic, R&B, blues, Country, folk songs.

[0049] S2. Obtain the collection of users corresponding to each dimension; extract the collection of l...

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

No PUM Login to View More

Abstract

The invention relates to the technical field of personalized recommendation, aims to solve the problem that a traditional contented algorithm cannot perform extended recommendation on interest dimensions, and particularly relates to an improved content-based television music recommendation method, which comprises the following steps: S1, obtaining dimensions in historical data information of a user; S2, obtaining a user set corresponding to each dimension; S3, calculating the corresponding Jaccard similarity between the dimensions according to the user set; S4, scoring interest of dimensions;S5, acquiring data information under each dimension and sorting the data information according to interest of all users; S6, selecting the dimension of the top X of the dimension interest score ranking and the corresponding dimension of the top Y of the Jaccard similarity ranking to form a dimension set; S7, selecting the data information of the top Z of each dimension in the dimension set to forma candidate set M; S8, acquiring a candidate set N for the historical information of the user by adopting a contented algorithm; and S9, combining the candidate set M and the candidate set N to obtain a recommendation set U. By adopting the method, the dimension of personalized recommendation and the diversity of recommendation can be broadened.

Description

technical field [0001] The invention relates to the technical field of personalized recommendation, in particular to an improved content-based TV music recommendation method. Background technique [0002] The principle of the content-based algorithm is to obtain the user's interest preference according to the user's historical behavior, and recommend items similar to his interest preference for the user. The implementation steps are as follows: Mining the user's basic information and historical behavior data, constructing User characteristics; mining the basic information of items to construct item content information features; recommending to users based on the similarity between user features and item content features. This algorithm is often used when the recommendation system has a certain amount of user data after the cold start phase. However, this algorithm can only recommend items included in the dimension of interest represented by the user's historical behavior da...

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
no application Login to View More
IPC IPC(8): G06F16/635
CPCG06F16/635
Inventor 何林凯
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com