Unlock instant, AI-driven research and patent intelligence for your innovation.
Comment recommendation system and method based on deep learning
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 recommendation system and deep learning technology, applied in special data processing applications, instruments, biological neural network models, etc., can solve problems such as poor recommendation interpretation ability
Active Publication Date: 2020-07-03
HARBIN UNIV OF SCI & TECH
View PDF6 Cites 5 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] The present invention is mainly to solve the problem that the existing recommendation system only gives recommendation scores and thus has poor recommendation interpretation ability
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
specific Embodiment approach 1
[0096] This implementation mode is a comment recommendation system based on deep learning, and the system includes:
[0097] (S1) The feature extraction unit performs word segmentation for comments related to users and products, and uses pre-trained characters and word vectors to obtain text feature representations through text feature processors; for product images, use image feature processors to obtain image features; for User and product attributes use attribute processors to obtain attribute characteristics; including:
[0098] (S11) preprocessing module: obtain the sth pair of users user A and product item B Initial representations of corresponding text, images, and attributes;
[0099] For the words / characters in the text, use the StanfordNLP word segmentation tool and the Glove word embedding tool to process, and obtain the vector representation of the text, that is, the text in vector form;
[0100] For the image, each pixel in the image is represented by the RGB v...
specific Embodiment approach 2
[0176] Specific implementation mode two: combination figure 1 This embodiment will be described.
[0177] This embodiment is a method for recommending comments based on deep learning, and the method includes the following steps:
[0179] (S11) preprocessing step: obtain the sth pair of users user A and product item B Corresponding texts, images and initial representations of attributes; the texts include product description texts, product review texts, and user review texts; the images are product images; the attributes include product attributes and user attributes;
[0180] For the words / characters in the text, use word segmentation tools and word embedding tools to obtain the vector representation of the text;
[0181] For the image, each pixel in the image is represented by the RGB values of the three primary colors;
[0182] For attributes, use feature values to represent;
[0183...
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 a comment recommendation system and method based on deep learning, and belongs to the technical field of information dissemination. The problem that an existing recommendationsystem only gives recommendation scores, and consequently the recommendation interpretation capacity is poor is mainly solved. According to the system, comment text feature representation is acquiredby using a character and word-level bidirectional recurrent neural network; acquiring image features by using a convolutional neural network; obtaining attribute feature representation by using a decompositionmachine neural network; and a memory mechanism is used for solving the cold start problem of users and products in the recommendation system; and obtaining a relationship between the user and the product by using a bilinear tensor mechanism to jointly generate scores and comments. The method is mainly used for comment recommendation in information dissemination.
Description
technical field [0001] The invention relates to a comment recommendation system and method. It belongs to the field of information communication technology. Background technique [0002] The recommendation system is an important intelligent task, which recommends products of interest to users through the powerful computing power of computers. With the development of information technology and the change of people's lifestyle, people's life begins to rely more and more on information, including the dependence on recommended information. [0003] The recommendation system has experienced collaborative filtering recommendation, content-based recommendation, knowledge-based recommendation and hybrid recommendation system, and gradually developed to today's deep learning-based recommendation system. The deep neural network partially solves the gradient dispersion and explosion, and has developed rapidly in recent years, and has been applied to the recommendation system and achi...
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