An intelligent question answering method for search engine knowledge base
A search engine and intelligent question answering technology, applied in the field of question answering, can solve problems such as inapplicable reasoning process, large computing resources, consumption, etc., to achieve the effect of efficient and accurate intelligent question answering
Active Publication Date: 2022-04-22
SHANDONG ARTIFICIAL INTELLIGENCE INST +1
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] 1) Traditional semantic analysis and information retrieval methods need to manually write a large number of templates or define a large number of rules
[0004] 2) Some deep learning methods can only deal with simple problems, cannot apply to complex reasoning processes, and consume a lot of computing resources
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0022] Attached below figure 1 The present invention will be further described.
[0023] An intelligent question answering method oriented to a search engine knowledge base, comprising the following steps:
[0024] a) Set the search questions and corresponding answers in the search engine, and obtain the entity e of the question through natural language processing tools s The query relationship with the question r q , set the answer corresponding to the question as e o , using natural language processing Embedding to convert the entity e of the problem s , query relation r q and the answer e o Mapped to a dense low-latitude vector space, the vector representation of the entity of the problem is obtained ε s , the vector representation of the query relation γ q and the vector representation of the entity of the answer ε o ;
[0025] b) Entity e extracted according to the search question s and relation r q , the path of the answer to the reasoning question based on th...
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
Login to View More Abstract
An intelligent question answering method for search engine knowledge base, based on search engine knowledge base, through dynamic search path reasoning and deep reinforcement learning, to construct a symbolic Markov reasoning path, based on LSTM and feedforward neural network, to realize path information encoding and calculate the action space probability distribution, while setting the judgment condition according to the vector representation of the search reasoning path. Based on the judgment condition and the reasoning path when searching for the answer to the question, the intelligent question answering of the search engine based on the knowledge base is realized. This method does not need to define rules, does not limit the length of the reasoning path, and can be used in the complex question-and-answer reasoning process based on the search engine knowledge base to achieve efficient and accurate search engine intelligent question answering.
Description
technical field [0001] The invention relates to the field of intelligent question answering of search engines, in particular to an intelligent question answering method for search engine knowledge bases. Background technique [0002] The intelligent question answering of the search engine, that is, given a natural language question to the search engine, the corresponding entity is searched from the existing knowledge base as the answer to the question. Specifically, it involves entity recognition and relationship extraction for questions, linking to the corresponding entities and relationships in the knowledge base, querying, matching and reasoning out candidate answers, and obtaining the target answer. Today, the reasoning process of intelligent question answering in the field of search engines mainly faces the following problems: [0003] 1) The traditional semantic analysis and information retrieval methods need to manually write a large number of templates or define a l...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/332G06F16/953G06N3/04G06N3/08G06N5/02G06N5/04
CPCG06F16/3329G06F16/953G06N5/02G06N3/08G06N5/04G06N3/044
Inventor 舒明雷刘浩周书旺高天雷许继勇
Owner SHANDONG ARTIFICIAL INTELLIGENCE INST