A method and system for unstructured text intelligent question answering

An intelligent question answering and unstructured technology, applied in unstructured text data retrieval, neural learning methods, text database query, etc., can solve problems such as coarse answer granularity, not particularly precise, limited question types, etc., to achieve accurate answers Effect

Active Publication Date: 2020-09-08
EMOTIBOT TECH LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] To sum up, the current unstructured text intelligent question answering technology mainly has the following defects: it needs to build a question answering library in advance; the returned answers may be too coarse or too fine, and not particularly accurate; the types of questions that can be answered accurately are limited; use big data

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
  • A method and system for unstructured text intelligent question answering
  • A method and system for unstructured text intelligent question answering
  • A method and system for unstructured text intelligent question answering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] Embodiments of the present invention provide a method for unstructured text intelligent question answering, such as figure 1 shown, including:

[0050] S1, the encoding layer encodes the acquired text and question separately to obtain the text hidden vector and the question hidden vector;

[0051]S2, the information fusion layer fuses the text hidden vector and the question hidden vector, and obtains a fused association vector group;

[0052] S3. The decoding layer decodes the text according to the association vector group, obtains the answer to the question, and outputs the answer.

[0053] Preferably, the specific method of S1 is:

[0054] S11, acquiring the input text and question;

[0055] S12: Segment the text and the question to obtain a text phrase and a question phrase;

[0056] S13: Mapping each word in the text phrase and the question phrase to a corresponding word vector to obtain a text word vector and a question word vector;

[0057] S14: Encoding the ...

Embodiment 1

[0083] Example 1: Story Understanding

[0084] The text reads: On the trees in spring, tender buds grow; on the trees in summer, they are covered with fat leaves; on the trees in autumn, the leaves are painted with bright red and golden; under the trees in winter, the leaves fall and turn into soil. Fallen leaves are the stamps of nature. Send them to you, to me, and to everyone throughout the year.

[0085] The question is: what grows on the tree in spring?

[0086] After the present embodiment analyzes the text and the question, the start position and the end position of the answer are calculated, and the text content between the start position and the end position is extracted as the answer to the question. The answer is: grow a tender bud petal

Embodiment 2

[0087] Example 2: Understanding legal provisions

[0088] The text is: Chapter Four Museum Social Services

[0089] Article 28 The museum shall be open to the public within 6 months from the date of obtaining the registration certificate.

[0090] Article 29 Museums shall announce the specific opening hours to the public. During national statutory holidays and school winter and summer vacations, museums should be open.

[0091] Article 30 Museums holding exhibitions shall abide by the following regulations:

[0092] The theme and content should conform to the basic principles established by the Constitution, safeguard national security and national unity, and promote patriotism...

[0093] The question is: How long should the museum be open to the public?

[0094] This embodiment analyzes the text and the question, calculates the start position and end position of the answer, and extracts the text content between the start position and the end position as the answer to the...

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 present invention belongs to the technical field of computer intelligent dialogue, and provides a method and system for unstructured text intelligent question answering, including: S1, the encoding layer encodes the acquired text and questions respectively, to obtain text hidden vectors and question hidden vectors; S2, the information fusion layer fuses the text hidden vector and the question hidden vector, and obtains a fused association vector group; S3, the decoding layer decodes the text according to the association vector group, and obtains the question , and output said answer. The present invention can directly give answers to questions about unstructured texts, and does not need to establish a question-and-answer library in advance; there is no limit to the type of questions; the returned answers are relatively accurate; data-driven, effectively utilizing big data.

Description

technical field [0001] The invention belongs to the technical field of computer intelligent dialogue, and in particular relates to a method and system for unstructured text intelligent question answering. Background technique [0002] Unstructured text intelligent question answering refers to any given piece of unstructured text, and any question that satisfies the following conditions for the text, that is, the answer to the question appears in the given unstructured text. In this case, the intelligent question answering system should be able to find out the corresponding answer to answer the question. [0003] At present, there are four main technologies for unstructured text intelligent question answering, but each has its own shortcomings: [0004] Based on the method of question answering library, it is difficult to construct question answering library, especially in the situation where the unstructured text cannot be known in advance. At the same time, considering th...

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 Patents(China)
IPC IPC(8): G06F16/332G06F16/33G06F40/289G06N3/04G06N3/08
CPCG06F16/3329G06F16/3344G06N3/08G06F40/289G06N3/045
Inventor 简仁贤王海波
Owner EMOTIBOT TECH 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