Problem cluster-based automatic asking and answering method and device

An automatic question answering and questioning technology, applied in special data processing applications, instruments, unstructured text data retrieval, etc., can solve problems that cannot automatically provide user answers, and achieve the effect of efficient and accurate automatic question answering

Active Publication Date: 2014-05-21
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF5 Cites 73 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in actual use, even if there are already answers corresponding to substantially the same semantically identical questions in the question-answering database, du...

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
  • Problem cluster-based automatic asking and answering method and device
  • Problem cluster-based automatic asking and answering method and device
  • Problem cluster-based automatic asking and answering method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] figure 1 The flow chart of the method for establishing a question-and-answer database in cluster form provided by Embodiment 1 of the present invention, as shown in figure 1 As shown, the method may include the following steps:

[0070] Step 101: Semantic-based clustering is performed on all questions in the question-answer database to obtain more than one question cluster.

[0071] In the existing question-and-answer database, usually one question corresponds to more than one answer or there is a case where there is no corresponding answer for one question. This question-and-answer database is an existing database of the question-and-answer platform. By calculating the semantic similarity of all the questions in the question-answering database, the questions are clustered based on the semantic similarity, and finally each question cluster contains questions with the same or similar semantics. For example, the following questions are clustered into a question cluster:...

Embodiment 2

[0094] figure 2 The flow chart of the automatic question answering method applied to search engines provided by Embodiment 2 of the present invention, as figure 2 As shown, the method may include the following steps:

[0095] Step 201: Identify the query entered by the user into the search engine, and if it is identified as a question type query, proceed to step 202.

[0096] When identifying whether the query is a question type, it can be realized through a pre-established classifier. The training process of the classifier is briefly described as follows: firstly, the interrogative words and the demand words with interrogative intentions are expanded to obtain combined features such as one-element, two-element, and three-element. The ratio of the frequency information in the sentence type to extract the features corresponding to the question type. This classifier is able to identify not only question types that contain interrogative words, but also question types that ha...

Embodiment 3

[0131] Figure 5 The structural diagram of the automatic question-answering device provided for Embodiment 3 of the present invention, such as Figure 5 As shown, the device includes: a database building unit 500 and an automatic question answering unit 510 .

[0132] The database building unit 500 pre-clusters the questions in the question-and-answer database based on semantic similarity to obtain more than one question cluster, and determines the high-quality answers corresponding to the question clusters from the answers to the questions in the question clusters, thereby establishing a question-and-answer database in the form of clusters .

[0133] When determining the high-quality answers corresponding to the question clusters from the answers to the questions in the question clusters, one or a combination of the two methods of inter-question quality evaluation and single-question quality evaluation can be used.

[0134] The method of inter-question quality evaluation is...

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 provides a problem cluster-based automatic asking and answering method and device. The method comprises the steps of clustering problems in an asking and answering database based on semantic similarity in advance to obtain more than one problem clusters, and determining fine quality answers corresponding to the problem clusters from answers of the problems in the problem clusters, thus forming a cluster-format asking and answering database; when the problem input by a user is obtained, determining the problem cluster with the highest semantic similarity with the problem input by the user in the cluster-format asking and answering database and returning the fine quality answer corresponding to the problem cluster to the user. According to the problem cluster-based automatic asking and answering method and device, efficient accurate automatic asking and answering can be realized aiming at the problem of the user and the user demands can be better met.

Description

【Technical field】 [0001] The invention relates to the field of computer application technology, in particular to an automatic question answering method and device based on question clusters. 【Background technique】 [0002] With the rapid development of network technology, the network, especially the search engine, has become an important means for people to obtain information. Users can obtain the search results returned by the search engine by inputting a query in the search engine, and find the information they need. In many cases, the query entered by the user may be a problem, because the search results returned by the search engine include pages that meet certain requirements for similarity with the query, therefore, due to the various problems expressed by the user, often in the search results It can't meet the needs of users very well. Users need to find the desired information from hundreds or thousands of results, and the users who input the question query only want...

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): G06F17/30
CPCG06F16/31G06F16/35G06F16/951
Inventor 方高林
Owner BEIJING BAIDU NETCOM SCI & TECH 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