Vertical domain-oriented intelligent question and answer system

A vertical field, intelligent question answering technology, applied in special data processing applications, instruments, electronic digital data processing and other directions, can solve the problem of lack of semantic analysis of vocabulary, lack of semantic analysis in vertical fields, and not considering the weight of field vocabulary, so as to improve accuracy. rate effect

Active Publication Date: 2016-08-10
QINGDAO PENGHAI SOFT CO LTD
View PDF1 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, when calculating the similarity of words in the existing technology, there is a similarity calculation method based on "HowNet", but it lacks sufficient semantic analysis for professional vert...

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
  • Vertical domain-oriented intelligent question and answer system
  • Vertical domain-oriented intelligent question and answer system
  • Vertical domain-oriented intelligent question and answer system

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0062] Example 1: Question: "Wyeth Huishi_Golden Pack Jianerle Milk Powder 2 Stages 400g Where is the place of origin?" In Chinese "A of B", in the case of A modifying B, add "Suzhou" to the vocabulary .

[0063] 4) The concepts in the domain ontology are words with a high degree of correlation with the system, and as the depth of the concept increases, the more detailed information the concept carries, so the weight of words in domain knowledge is higher than that of general words, and the weight of words increases with the vocabulary increased in depth.

[0064] Weight w0 = 1 +α

[0065] Among them, α is an adjustable parameter to adjust the weight of the concept. In this paper, the value of α is set to 1, which means that the weight of the concept in the domain ontology is between 1-2.

[0066] like image 3 , with "Thing" as the root node, the depth is 0, and the depth of "Wyeth" is 3, namely: = 3, = 5, the weight of the word "Wyeth" is Weight 惠氏 = 1 + = 1....

example 2

[0068] Example 2: Aiming at the relationship between milk powder and baby's age, the effect of constructed ontology information on semantic analysis.

[0069] like Image 6 , according to the number of stages of milk powder and the age suitable for the baby, construct the corresponding field ontology, and the system will recognize "four months" as "0-6 months", so as to find the questions containing "0-6 months" in the standard answer , the display content on the reply output module is as follows:

[0070]

[0071] like Figure 5 , the user enters the question "Why does rice noodles have a hala taste?", the system standardizes the words while segmenting the word, and standardizes "ha la taste" as "odor"; removes stop words, and converts "yes" and "ah" Remove; check the inverted index table of the database for questions containing [reason, rice noodles, smell], sort the questions according to the number of keywords, and take the first 15 questions as candidate questions; u...

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 vertical domain-oriented intelligent question and answer system. The system comprises a question asking module (1), a preprocessing module (2), a word segmentation and vocabulary standardization module (3), a word purification module (4), a synonym expansion module (5), a vocabulary expansion or deletion module (6), a sentence similarity calculation module (7) and an answer output module (8). The system calculates the similarity of question sentences of a user through domain ontology construction and depends on a word segmentation technology, domain ontology construction and ontology similarity calculation. The system has the advantages that a question asking intention of the user can be understood more accurately by applying a domain ontology technology through a sentence similarity algorithm, the sentence similarity can be calculated, and the accuracy of the question and answer system can be improved.

Description

technical field [0001] The invention relates to an intelligent question answering system oriented to the vertical field, which has great significance and effect on the accuracy of semantic analysis in the vertical field. Background technique [0002] According to the realization technology of question answering system, it includes: question answering system based on frequently asked questions (FAQ), question answering system based on information retrieval, question answering system based on question classification and question answering system based on Resource Description Framework (ResourceDescription Framework) RDF query. [0003] The Q&A system based on the frequently asked questions set constructs frequently asked questions (FAQ) question and answer pairs, and the implementation depends on the calculation of the similarity between the user's questions and the questions in the FAQ. In the development process of the FAQ question answering system, it is necessary to identi...

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): G06F17/30G06F17/27
CPCG06F16/3329G06F16/3344G06F40/30
Inventor 张振峰于忠清刘晓强
Owner QINGDAO PENGHAI SOFT CO LTD
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