A method and device for question answering knowledge graph based on path search
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A knowledge graph and path search technology, applied in character and pattern recognition, digital data information retrieval, unstructured text data retrieval, etc. Accurate, Solve Complex Problems and Multi-Problem Effectiveness
Active Publication Date: 2022-05-03
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF9 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] The present invention provides a method and device for knowledge graph question answering based on path search to solve the problem of semantic understanding of questions in the prior art, due to the excessive number of candidate items, complex structure, and inconspicuous features, which can only be solved Single-subject substantive issues that do not involve complex issues and multiple issues
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0057] see figure 1 , a knowledge map question answering method based on path search. The present invention is mainly applied to the field of question answering based on knowledge map. By analyzing the question and combining the content of the knowledge map, the answer to the question is obtained. The specific implementation steps are as follows:
[0058]s1: Obtain the user's input questions and perform simple natural language processing.
[0059] s2: Analyze the question sentence, and identify the search point and constraint point of the question sentence.
[0060] s3: Construct a target point recognition model, which is a multi-classification model to identify the target point of the question sentence.
[0061] s4: For each target point of the question sentence, search in the knowledge map centered on the search point of the question sentence, and obtain multiple candidate paths that meet the target point of the question sentence.
[0062] s5: According to the constraint p...
Embodiment 2
[0085] figure 2 A knowledge map question answering device based on path search is presented, including:
[0086]User interaction module: It is used to interact with users. First, it receives user input questions, inputs them into the following modules, and then obtains the results returned from the following modules, and outputs the results as answers to users.
[0087] Search point and constraint point identification module: used to train the sequence labeling model of search items and constraint items, and identify question search points and constraint points through the sequence labeling model, and map them to the knowledge graph.
[0088] Target point recognition module: used to train the target point recognition model of the question sentence, and identify the target point of the question sentence through the target point recognition model.
[0089] Path search module: It is used to search for qualified candidate paths in the knowledge map according to the question sear...
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
The invention discloses a path search-based knowledge map question answering method and device. The method includes: obtaining user input questions and performing simple natural language processing; analyzing the questions and identifying the search points and constraint points of the questions; constructing The target point recognition model identifies the target point of the question; for each target point of the question, with the search point of the question as the center, searches in the knowledge map to obtain multiple candidate paths that meet the target point of the question; according to The constraint points of the question sentence, increase the constraint conditions of the candidate path; filter the candidate path to obtain one or more candidate paths that meet the conditions; according to the obtained path, combined with the storage method of the knowledge graph, convert it into an executable query statement, and get Final Answer; returns the resulting final result to the user as an answer. The invention can realize the semantic understanding of natural language question sentences, deeply analyze the question sentences, and use the path search algorithm to retrieve relevant answers with accurate content.
Description
technical field [0001] The present invention relates to the field of computer technology, in particular to a method and device for question answering of knowledge graphs based on path search. Background technique [0002] As a research direction that has attracted much attention and has broad development prospects in the field of artificial intelligence and natural language processing, the question answering system is an advanced form of information retrieval system, which can answer the questions raised by users in natural language in accurate and concise natural language. question. Question answering based on knowledge graphs introduces background knowledge in open fields or special fields when answering questions, making answering questions more in line with human thinking, and accurate and fast. In recent years, it has served our daily life in the form of customer service robots or search engines in various fields such as encyclopedia knowledge quizzes, financial fields...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more