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

Sorting method for user comments, electronic device and computer storage medium

A user comment and sorting method technology, which is applied in the sorting method of user comments, electronic equipment and computer storage media, can solve the problems of being unable to sort, unable to dig out a large number of semantic connections of comments, etc., and achieve the effect of reasonable sorting results

Active Publication Date: 2018-09-04
ZHANGYUE TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the process of realizing the present invention, the inventors found that the above-mentioned methods in the prior art have at least the following problems: in the single-feature index method and the multi-feature weight fusion method, only some manually set features are used for sorting, Moreover, the weight of each feature is also set manually, and the way of setting manually is bound to have great subjectivity. Moreover, in the way of setting manually, it is impossible to dig out the potential semantic links between a large number of comments, and then it is impossible to make more accurate comments. Accurate and fair sorting

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
  • Sorting method for user comments, electronic device and computer storage medium
  • Sorting method for user comments, electronic device and computer storage medium
  • Sorting method for user comments, electronic device and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0019] figure 1 A flow chart of a method for sorting user comments provided by Embodiment 1 of the present invention is shown. Such as figure 1 As shown, the method includes the following steps:

[0020] Step S110: Determine the latent semantic features corresponding to each review sample and the latent semantic features corresponding to user comments through the first machine learning algorithm, and determine the feature vector of the review sample according to the latent semantic features corresponding to each review sample.

[0021] Wherein, the first machine learning algorithm can be flexibly set by those skilled in the art, which is not limited in the present invention. Preferably, the first machine learning algorithm is an algorithm that facilitates the mining of deep connections between semantics, for example, word2vec algorithm, LDA algorithm.

[0022] Specifically, in this step, the pre-selected comment samples and the user comments to be sorted are added to the sa...

Embodiment 2

[0034] figure 2 A flow chart of the method for sorting user comments provided by Embodiment 2 of the present invention is shown. Such as figure 2 As shown, the method includes the following steps:

[0035] Step S210: Determine the latent semantic features corresponding to each review sample and the latent semantic features corresponding to user comments through the first machine learning algorithm.

[0036] Specifically, in this embodiment, comments in an e-book are mainly used as an example for illustration. Correspondingly, several book reviews need to be selected in advance as review samples. In order to comprehensively cover various types of e-books, multiple reviews from various types of e-books can be selected as samples, for example, select comments from various types of e-books such as emotional type, historical type, humanistic type, popular science type, etc. as a sample and classify the samples according to the book type. Preferably, in order to improve the a...

Embodiment 3

[0060] Embodiment 3 of the present application provides a non-volatile computer storage medium, the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the method for sorting user comments in any of the above method embodiments.

[0061] Specifically, the executable instructions can be used to make the processor perform the following operations: determine the latent semantic features corresponding to each comment sample and the latent semantic features corresponding to user comments through the first machine learning algorithm, and according to the latent semantic features corresponding to each comment sample The semantic feature determines the feature vector of the comment sample; through the second machine learning algorithm, combined with the sample annotation results of each comment sample, the feature vector of each comment sample is trained to obtain a comment ranking model; according to the corresponding ...

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 discloses a sorting method of user comments, electronic equipment and a computer storage medium. The method includes: using a first machine learning algorithm to determine the hidden semantic feature corresponding to each comment sample and the hidden semantic feature of each user comment, and determining the feature vector of each comment sample according to the hidden semantic feature corresponding to each comment sample; using a second machine learning algorithm and the sample labeling result of each comment sample to train the feature vector of each comment sample so as to obtain a comment sorting model; determining the feature vector of each user comment according to the hidden semantic feature of each user comment, and using the comment sorting model to determine the evaluation score corresponding to the feature vector of each user comment; sorting the user comments according to the evaluation scores corresponding the feature vectors of the user comments. By the sorting method, the quality of each comment can be well determined so as to allowing the sorting result to be reasonable.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method for sorting user comments, electronic equipment and computer storage media. Background technique [0002] In order to enhance the interaction between users and facilitate users to express their emotions, many applications support the comment function. For example, audio-visual playback applications allow users to fill in audio-visual comments such as after-views for watched audio-visual content, and e-book reading applications allow users to fill in book reviews for e-books they have read. For example, a book review mainly refers to: a user's evaluation of the content in the book and the expression of personal feelings and opinions after reading a certain book. Through book reviews, channels of information exchange can be constructed between authors and readers, and between readers. The quality of book reviews can often affect other users' reading choices. Therefore, mining an...

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 Patents(China)
IPC IPC(8): G06F17/30
CPCG06F16/9535G06F16/9577
Inventor 柳燕煌王海璐
Owner ZHANGYUE TECH 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