System and method for intelligently identifying names and models of commodities

A commodity name and intelligent identification technology, applied in the system field of intelligent information processing technology, can solve the problems of difficult subsequent processing of commodities, and achieve the effect of accurate search results

Inactive Publication Date: 2012-07-25
蒋永 +3
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the inconsistency of the description of the title of the product by the merchant, it becomes difficult for the computer to process the product. For example, for the same LCD monitor, the possible product name description is: 1) Super large LCD monitor for Valentine's Day gift; 2) Ultra-thin and ultra-wide Color LCD monitor with earphones

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
  • System and method for intelligently identifying names and models of commodities
  • System and method for intelligently identifying names and models of commodities

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Embodiment one: the following combination figure 2 And embodiment further illustrate the present invention.

[0026] 1) There are four products A: "headphones", product B: "mobile phones", product C: "wireless earphones"; product D: "smart phones"

[0027] 2) Manually process commodity A and commodity B through the learning system, commodity A: earphone, the learning system creates a feature word: earphone, and the rule: [headphone] -> earphone; commodity B: mobile phone, the learning system creates a feature word: mobile phone, And rules: [mobile phone] -> mobile phone.

[0028] 3) The system sees that commodity C and commodity D are automatically processed, and the characteristic word set for processing commodity C is: [earphones]. The corresponding rule for extracting the characteristic word set [earphones] from the knowledge database is: earphones, and the identified commodity name is: Headphones; the feature word set of product D is: [mobile phone], and the corre...

Embodiment 2

[0029] Embodiment 2: Now take the shopping search as an example. In the background, the user inputs a certain keyword such as earphones. His / her real wish is to be able to search for all earphones. When using a full-text search engine, for two products: 1) Earphones, 2) Earphones for mobile phones will both become key results, but how to distinguish these two products and give users an accurate and relevant result? According to this patented technology, the 1st) commodity will be recognized as a real "earphone", and the 2nd) commodity will be recognized as a mobile phone. In the end, there were two results in the search, but 1) the product name was identified as "headphones", which was the correct result, and 2) the product was also searched, but because the recognized product name was not "headphones", it was displayed as a relevant result to the user.

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 system for intelligently identifying names and models of commodities and a method for intelligently identifying names and models of commodities. The system comprises a knowledge database, a learning system and an identifying system. The system and the method can be used for solving the problem that further treatment is difficult to carry out by a computer due to the fact that the name commodities are not standard in the present electronic commerce. According to the system and the method, the names and models of the commodities based on manual training can be automatically identified, thereby providing a data preparation base for shopping search and other applications based on names and models of the commodities.

Description

technical field [0001] The invention relates to a product name and model intelligent identification system and method, in particular to a system and method of intelligent information processing technology for automatically identifying product names and models in the field of electronic commerce. Background technique [0002] Now the Internet has become an important way for people to shop and businesses to sell, and there are many websites that provide online commodity sales services. The application tools for shopping are gradually increasing, such as shopping search and LBS for shopping. However, due to the inconsistency of the description of the title of the product by the merchant, it becomes difficult for the computer to process the product. For example, for the same LCD monitor, the possible product name description is: 1) Super large LCD monitor for Valentine's Day gift; 2) Ultra-thin and ultra-wide Color LCD display with earphones. In view of the current situation, ...

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): G06Q30/00G06F17/30
Inventor 蒋永吴俊吴娟吴敏
Owner 蒋永
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