Knowledge question and answer intelligent search method based on block decomposition

An intelligent search and knowledge technology, applied in the fields of natural language processing and information retrieval, can solve problems such as unexplainable reasons and motivations, black-box opacity of neural network algorithms, etc.

Pending Publication Date: 2022-01-28
THE FOURTH INST OF NUCLEAR ENG OF CNNC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the development of neural network algorithms, some neural network methods have gradually been applied in this field, but the black box and opacity of neural network algorithms make researchers often unable to explain the reasons and motivations of their speculations

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
  • Knowledge question and answer intelligent search method based on block decomposition
  • Knowledge question and answer intelligent search method based on block decomposition
  • Knowledge question and answer intelligent search method based on block decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] A knowledge question answering intelligent search method based on block decomposition, comprising the following steps:

[0037] Step S1: Store the data in the knowledge base in the database (the database uses SQL Server), the specific operation steps are as follows:

[0038] Click "Data Import" on the page, select the database to be imported, and click "Upload" to complete the data import. These data come from the data in the knowledge base, including all the data sets that you want to complete.

[0039] Step S2: Preprocess the knowledge data imported into the database, and convert it into a triple data set of structured data for reading the system model, which can be used for subsequent knowledge base construction. Specific steps are as follows:

[0040] Step S2.1: Entity extraction: Named entity recognition, including entity detection and classification.

[0041] Step S2.2: Perform triple relation extraction: a data set can be represented as a set of head entity-re...

Embodiment 2

[0067] In this embodiment, an experiment is conducted to verify the effectiveness of the block decomposition-based knowledge question answering intelligent search method described in the first embodiment.

[0068] In this embodiment, the knowledge question answering intelligent search model based on block decomposition of the present invention is compared with existing models such as TransE, DisMult, ANALOG, ComplEx, ConvE, and CrossE. In order to evaluate the performance of different models, this embodiment adopts four evaluation indexes: MRR, Hit@10, Hit@3, Hit@1.

[0069] MRR is the mean value of Mean Reciprocal Rank, which is the reciprocal, and the calculation formula is as follows:

[0070] Among them, |Q| is the total number of predicted results, rank i Indicates the ranking of the expected output results in the actual results.

[0071] Hit@n: It is the percentage that represents the top n. The higher the value, the better the performance. In this embodiment, Hit@...

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 knowledge question and answer intelligent search method based on block decomposition, and the method comprises the following steps: preprocessing knowledge data imported into a database, and converting the knowledge data into a triple data set of structured data; coding the triple data set of the converted structured data by adopting One-hot coding; segmenting the data set into a training set and a test set, and constructing a knowledge question and answer intelligent search model by adopting a BTD tensor decomposition algorithm. According to the method, the three-order binary tensor problem is converted into a three-order binary tensor problem in mathematics, the missing subject or object entity can be predicted, all real triple subsets are used for learning embedding vectors of entities and relations, the method is more generalized decomposition based on mathematical tensors, and formed factors can be decomposed more accurately. According to the method, under the characteristics of low search accuracy and poor user search experience, search complementation can be performed in a more accurate manner after a large amount of data training, so that an efficient and accurate search system is realized.

Description

technical field [0001] The invention belongs to the fields of natural language processing and information retrieval, and in particular relates to an intelligent search method for knowledge question answering based on block decomposition. Background technique [0002] Intelligent search engine is a new generation of search engine combined with artificial intelligence technology. In the vast ocean of information, people can only rely on search engines to quickly obtain the information they need in the knowledge base. As an important task in intelligent search, link prediction aims to satisfy people's increasingly complex search tasks based on the existing knowledge base. It is essentially a graph of nodes and edges, where nodes are entities and edges are relationships. Generally, a fact in the real world is described in the form of a triple (head entity, relation, tail entity). With the development of computer technology and the times, the data we store is increasing at an a...

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): G06F16/31G06F40/295G06F16/25G06F16/242G06F16/28
CPCG06F16/313G06F40/295G06F16/254G06F16/243G06F16/284
Inventor 霍晨琛吴卫芳郭九江曾晨喻梅许林英肖诗伟王新锐张丽丽
Owner THE FOURTH INST OF NUCLEAR ENG OF CNNC
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