Unlock instant, AI-driven research and patent intelligence for your innovation.
Movie recommendation method and system based on user demand and label association degree
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of user needs and recommendation methods, which is applied in the fields of data mining and information processing, and can solve problems such as low accuracy, reduced recommendation efficiency, and existing accuracy
Active Publication Date: 2021-07-06
HEFEI UNIV OF TECH
View PDF7 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] 1. The recommendation algorithm needs to rely on the scoring information of other users to make judgments, so it is necessary to collect and process the information of other users, thereby reducing the recommendation efficiency
[0005] 2. There are still problems with the accuracy of the recommendation algorithm. The recommendation algorithm recommends based on other people's ratings, so the recommended movies may not be the type you want to watch, so its accuracy is not high.
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0094] Assume that the desired tags entered by user A are "science fiction" and "United States", so that the target item can be obtained as "science fiction, United States".
[0095] Movies 1, 4, 5, and 8 all contain the tags "Science Fiction, America" at the same time, so the support of the target item is 40%. In this way, in this embodiment, the minimum support degree a0=30% can be set.
[0096] Referring to Table 1, in the present embodiment, according to the minimum support, frequent items as shown in Table 1 can be filtered out from the original items:
[0097] Table 1: The first frequent item statistics table
[0098]
[0099] Table 2: Candidate statistical table composed of frequent items in Table 1
[0100]
[0101]
[0102] From Table 2, the frequent items "United States, science fiction, superhero" and "superhero, comic book adaptation" can be filtered out, and "United States, science fiction, superhero" contains target items. Therefore, "United States,...
Embodiment 2
[0112] Compared with Embodiment 1, this embodiment has the minimum confidence b0=50%.
[0113] In this way, in this embodiment, the confidence degree of the preliminary item is 40%<b0, so the frequent set of the preliminary item "United States, science fiction, superhero, comic book adaptation" is obtained, specifically refer to Table 2:
[0114] "United States, science fiction, superhero, comic book adaptation" = "United States, science fiction, superhero" + "superhero, comic book adaptation"
[0115] Thus, the target supplementary item "USA, science fiction, superhero" can be obtained.
[0116] Confidence of the "USA, Sci-Fi, Superhero" = 30% / 50% = 60% > b0.
[0117] Therefore, in this embodiment, the target associated item is "superhero"; then, high-quality movies with movie tags containing "superhero" can be screened and recommended to user A.
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
A movie recommendation method based on user requirements and label association degrees comprises the steps of acquiring movie labels input by a user to serve as target labels, and combining all the target labels to form target items; obtaining the target item and all film tags except the target tag contained in the film in the film library as original items, and obtaining the original item with the support degree greater than or equal to the minimum support degree a0 as a frequent item; combining every two frequent items as candidate items, and marking the candidate items of which the support degree is greater than or equal to the minimum support degree a0 as transition items; updating the frequent items into transition items, and merging every two transition items again; screening the candidate items containing the target items to serve as preparation items; dividing the preparatory items into target items and associated items, wherein the associated items comprise all film tags except the target items in the preparatory items. And then recommending the movie to the user according to the association item, so that association between the recommended movie and the interest tendency of the user is ensured, and accurate orientation of the movie recommended to the user is realized.
Description
technical field [0001] The present invention relates to the field of data mining and information processing, in particular to a method and system for recommending movies based on user requirements and tag relevance. Background technique [0002] With the development of Internet technology and people's higher and higher requirements, and in recent years, data mining has been widely used in various industries, such as user-oriented movie recommendations. The existing movie recommendation algorithm is mainly based on collaborative filteringalgorithm. Its function is mainly to find similar users through one's own hobbies and then recommend similar users' hobbies. [0003] Collaborative filtering algorithms are based on the idea of similar item attributes or user ratings. Its main idea is to make recommendations based on users with similar opinions. It is an information filtering algorithm that relies on a large amount of user information. From a large number of users, find...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More