Product price data acquisition method and system

A data collection system and data collection technology, applied in the field of information collection, can solve the problems of system management and viewing without competing product prices, time-consuming and labor-consuming, etc., and achieve labor cost saving, low accuracy, and high similarity accuracy. Effect

Inactive Publication Date: 2016-08-31
数贸科技(北京)有限公司
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, there is no systematic management and viewing of the price situation of competing products for key transaction products on the platform. At present, it is mainly manually sorted through daily manual methods in various industries.
time and labor consuming

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
  • Product price data acquisition method and system
  • Product price data acquisition method and system
  • Product price data acquisition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] attached Figure 1-3 It can be seen that, as a product price data collection method, the establishment of a category mapping table inside and outside the station; discrimination of similar products; through http requests, based on web crawlers to capture product data of the target website,

[0060] 1) Build a text index for all participating products;

[0061] 2) Construct an image index of the main images of all products participating in the price comparison; based on text similarity discrimination; based on image similarity discrimination; product similarity fusion; similar product price comparison.

[0062] The steps of text similarity discrimination are as follows:

[0063] 1) Perform text word frequency statistics, calculate BM25 coefficient, and obtain preliminary target similar data range collection from text index;

[0064] 2) For the preliminary target similar data range set, calculate the Jaccard distance and the space vector cosine similarity distance based...

Embodiment 2

[0096] attached Figure 1-3 It can be seen that it is a product price data collection system, including an information processing server, and the information processing server includes: a proxy server for capturing data, a capturing server, and a server for calculating similar products.

[0097] The server processing content for calculating similar products includes: text similarity calculation processing steps, image similarity calculation processing steps, message queue processing steps, configuration file management processing steps, and product price comparison processing steps.

[0098] The text similarity calculation processing step further includes;

[0099] 1) Perform text word frequency statistics, calculate BM25 coefficient, and obtain preliminary target similar data range collection from text index;

[0100] 2) For the preliminary target similar data range set, calculate the Jaccard distance and the space vector cosine similarity distance based on the title dimensi...

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 present invention relates to a product price data acquisition method and system. The method comprises establishing a mapping matching table for categories on a website or out of the website; discriminating similar products; capturing product data of a target website on basis of a web crawler through http requests, and establishing a text index for all price comparison products; establishing an image index for main graphs of the all price comparison products; performing text-based similarity discrimination; performing image-based similarity discrimination; performing product similarity combination; and performing price comparison for similar products. According to the product price data acquisition method and system, manpower cost is saved, and characteristics and advantages of the products can be embodied through status analysis of competitors or similar products; and similar product calculation is carried out on basis of product text information and product main graph image characteristics, and similar accuracy is high.

Description

technical field [0001] The invention relates to an information collection method, in particular to a method for collecting Internet product price data. Background technique [0002] With the continuous enrichment of network resources and the continuous expansion of network information, people's dependence on the network is becoming stronger and stronger, but it also brings inconvenience to the service objects to quickly find the specific resources they need from the vast Internet resources; Information has infinite value since ancient times. With the continuous development of the times, human beings have entered the information age without knowing it. All walks of life are flooded with countless information, and the value of information lies in the circulation of data. If the data can be timely The real incomparable value of information can only be brought into play when it is circulated and transmitted; under the conditions of a market economy, data collection has become 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 Applications(China)
IPC IPC(8): G06F17/30G06Q30/02
CPCG06F16/951G06Q30/0201
Inventor 张宏志谢志胜顾锡栋陈磊杨秦郭田华
Owner 数贸科技(北京)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap