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

Method for recommending items based on a word vector model

A recommendation method and word vector technology, which is applied in the field of recommendation system to achieve the effect of improving calculation speed, maintaining accuracy and improving effect

Active Publication Date: 2019-03-08
NANJING UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the word vector model, through the calculation of the vector space, the relationship between the upper and lower meanings, the total score relationship, the semantic relationship (similar relationship, opposite relationship, etc.) between words and the corresponding relationship between word pairs can be obtained, which greatly expands the language The ability to process is difficult for traditional natural language models to complete

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
  • Method for recommending items based on a word vector model
  • Method for recommending items based on a word vector model
  • Method for recommending items based on a word vector model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention mainly uses a word vector model to measure the similarity between referee documents, and recommends legal articles to the referee documents through a collaborative filtering recommendation strategy. The overall process of the recommended method is as follows: figure 1 shown. Its specific implementation is as follows:

[0043] 1. The main flow of the method is as follows: figure 2 shown in the upper part.

[0044] (1) Step 1: Obtain the case basic information set A of the written judgment documents set 1 ={a 1 , a 2 ,...,a N} and the referenced set of statutes F 1 ={f 1 , f 2 ,..., f N}.

[0045] (2) Step 2, use word segmentation tool to A 1 The basic situation of each case in a i Carry out word segmentation to obtain the basic situation set A of the case after word segmentation 2 ={a' 1 , a' 2 ,...,a′ N}.

[0046] (3) Step 3, for A 2 The basic situation of each case in a″ i Remove the stop words and obtain the cleaned up case b...

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 method for recommending items based on a word vector model, and belongs to the collaborative filtering recommendation technology in the technical field of recommendation system. The collaborative filtering is a technology for recommending or screening information for things by virtue of similar things. Recommendation rules needs to obtain other documents with similar circumstances by virtue of the basic case conditions in the judgment documents, and then recommend rules according to a plurality of precedents. Compared with the existing method, the method of the invention has the remarkable advantages that after the word vector model is introduced, the similarity degree of the basic information of two cases can be expressed more accurately through the calculation of the word vector, so as to find out the document with more similar case situation for the judgment document; and according to several similar cases of documents a variety of collaborative filtering recommendation strategies can be adopted to obtain more accurate recommendation results.

Description

technical field [0001] The invention belongs to the technical field of recommendation systems, in particular to a collaborative filtering recommendation technology in the technical field of recommendation systems, which is a technology for recommending laws and regulations according to the basic conditions of litigation cases. Background technique [0002] In recent years, guided by the concept of "big data, big structure, and big services", the Supreme People's Court has actively promoted and implemented the strategic deployment of comprehensive law-based governance, and vigorously promoted the informatization construction of the people's courts. Judgment documents, as the carrier of legal trial activity records, fully reflect the objective process of the parties' claims, proof and cross-examination, and comprehensively expound the legal basis, factual evidence and reasoning process for the formation of the judgment result. Judgment documents are an important type of judici...

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): G06F16/9535G06F17/27
CPCG06F40/216G06F40/279G06F40/30
Inventor 葛季栋李传艺王子安冯奕雷妙妙周筱羽骆斌
Owner NANJING UNIV
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com