Knowledge reasoning method and device applied to intelligent interaction

A technology of knowledge reasoning and intelligent interaction, applied in reasoning methods, special data processing applications, electrical digital data processing, etc., can solve problems such as inaccurate, irrelevant, and difficult to reason out

Active Publication Date: 2019-04-12
安徽省泰岳祥升软件有限公司
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this example, the relationship between the four corpora is relatively loose, so when using the knowledge reasoning method based on statistics to infer the answer to the question, it is difficult to infer the answer "in the living room", but other inaccurate or inaccurate results will be obtained. completely irrelevant answer

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 reasoning method and device applied to intelligent interaction
  • Knowledge reasoning method and device applied to intelligent interaction
  • Knowledge reasoning method and device applied to intelligent interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] The embodiments of the present application are described in detail below.

[0070] Memory networks (MemNN for short) is a kind of deep learning model, including memory module (memory), and 4 components I, G, O, R. Please combine figure 1 , the memory module is an array of objects (an array indexed by mi and ci, where i is the index number of the input information in the memory module); component I is used to convert the input information (Sentences) into internal feature representations in the memory network; Component G is used to update the memory module with input information; component O is used to extract the appropriate memory from the memory module according to the given new input information (Question q), and return an output vector (o); component R is used to Convert the output vector back to the desired format, such as text or predicted answer (PredictedAnswer), etc. Before using the memory network, it needs to use the corpus to train the model to calculate ...

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 embodiment of the invention discloses a knowledge reasoning method applied to intelligent interaction, which is applied to knowledge reasoning of intelligent interaction, and comprises the following steps: obtaining a problem text and a reasoning corpus, the reasoning corpus comprising unstructured information and triple information; storing the unstructured information and the triple information into a first memory module and a second memory module; Calculating the relevancy between the question text and unstructured information and triple information in the first memory module; Performing weighted summation on the unstructured information and the triple information in the second memory module and the correlation degree to obtain an output value; and generating an answer according tothe output value. According to the scheme, scattered unstructured information and structured triple information are introduced to serve as input information of the memory network, and answers of questions are reasoned out together, so that more accurate and satisfactory answers are given.

Description

[0001] This application claims the priority of the Chinese patent application with the application number 201810569701.5 and the title of the invention "Knowledge Reasoning Method and Device Applied to Intelligent Interaction" filed with the China Patent Office on June 5, 2018, the entire contents of which are incorporated herein by reference In this application. technical field [0002] The invention relates to the fields of intelligent question answering and knowledge reasoning, in particular to a knowledge reasoning method and device applied to intelligent interaction. Background technique [0003] In the field of intelligent question answering, not all questions can be answered using existing knowledge bases. This is mainly due to the limited coverage of the knowledge base itself. Specifically, the information contained in the corpus includes two parts, one part is the information directly expressed by itself, and the other part is the implicit information. When buildi...

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): G06F16/332G06N5/04
CPCG06N5/04
Inventor 杨凯程蒋宏飞
Owner 安徽省泰岳祥升软件有限公司
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