Unlock instant, AI-driven research and patent intelligence for your innovation.

Recommendation method based on quantum heuristics

A recommended method and quantum technology, applied in quantum computers, special data processing applications, instruments, etc., can solve the problems of inability to guarantee Moore's Law, create social benefits, group polarization, etc., and achieve the effect of alleviating the cold start problem

Pending Publication Date: 2019-12-17
河南戎磐网络科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to solve the above technical problems, the present invention provides a recommendation method based on quantum heuristics to solve the ubiquitous problems of existing traditional algorithms, such as long training time, large resource occupation, "information cocoon room", "echo room", "group "Polarization" and other defects, but quantum algorithms cannot be put into commercial use immediately in the short term, and it is difficult to create social benefits in a short period of time, while the development of traditional electronic computing has stagnated, and the problem of Moore's Law 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Recommendation method based on quantum heuristics
  • Recommendation method based on quantum heuristics
  • Recommendation method based on quantum heuristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] S101: Collection of user scene information data:

[0047] The source data was collected in the user interaction module through CSV, and ten groups of MovieLens[1-10 groups] data sets were formed. This data set is called mlHatest-small, which includes 60,000 users, 1,000 movies and 100,023 ratings. The difference between it and other MovieLens datasets is that its scoring granularity is finer, and its scoring domain is 1-10, with 10 different scoring values. Its user-item rating matrix has a density of 1.7%.

[0048] Let’s start with the data: the MovieLens1M dataset is used in the implementation, which contains 100 million comments from 6,000 users on nearly 4,000 movies. The dataset is divided into three files: users.csv for user data, movies.scv for movie data, and ratings.csv for rating data.

[0049] 1.1 Data users (as shown in Table 1)

[0050] There are fields such as user ID, gender, age, occupation ID, and zip code respectively.

[0051] Format in the data: ...

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 provides a recommendation method based on quantum heuristics, and belongs to the technical field of the Internet, and the recommendation method based on quantum heuristics specifically comprises the following steps: collecting user scene information data; inputting user information data; extracting large-probability information quantity; complementing and filling the data information; preliminary sorting recommendation results; reprocessing the recommendation results. According to the recommendation method based on quantum heuristics, a quantum heuristics matrix completion modelcan be used in recommendation problems, and users and recommended items are combined into a preference matrix; the method is used for analyzing user behaviors and recommending content. The algorithm is a pure mathematical method, is essentially a matrix completion algorithm, does not need a training process of parameters, has less dependence on data, can alleviate the problem of cold start of users and information to a certain extent, can add a manual intervention mechanism to limit or prohibit certain vocabularies, and prevents the vocabularies from appearing in advance.

Description

technical field [0001] The invention belongs to the technical field of Internet recommendation algorithms, in particular to a recommendation method based on quantum inspiration. Background technique [0002] With the rapid development of the Internet, the information on the Internet is increasing exponentially every year. How to accurately obtain the required information in this massive information base has become a problem that people pay more and more attention to. Especially with the rapid popularization of various mobile terminal media platforms, the way people obtain information is also quietly changing. The "U.S. Social Media Platform News Usage Report" shows that 62% of American adults get news from social media; the "China Mobile Information Information Distribution Market Special Research Report" shows that in the domestic information information distribution market, the content pushed by algorithms has More than 50%; the survey by the Reuters Institute of Journal...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9535G06N10/00
CPCG06F16/9535G06N10/00
Inventor 李春光章丽娟刘旭胡漪逸孟凯强王亚龙赵治博朱晓贝李维超
Owner 河南戎磐网络科技有限公司