Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Task-oriented unstructured information intelligent question and answer system construction method

An unstructured, intelligent question answering technology, applied in the direction of unstructured text data retrieval, digital data information retrieval, semantic tool creation, etc., can solve problems such as no question answering system research, to reduce the work of manual screening of key information, search The effect of precise, efficient and convenient question-and-answer mechanism

Active Publication Date: 2019-05-24
THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
View PDF9 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the existing research on intelligent question answering is based on structured question answering based on knowledge graphs. Unstructured texts are subjected to open information extraction to generate knowledge graphs, and there is no in-depth research on question answering systems based on unstructured texts.

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
  • Task-oriented unstructured information intelligent question and answer system construction method
  • Task-oriented unstructured information intelligent question and answer system construction method
  • Task-oriented unstructured information intelligent question and answer system construction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] combine figure 1 , the present invention implements a task-oriented intelligent question answering system for unstructured information. Taking the task type "geographic information navigation" as an example, assuming that the user inputs a question in the system at this time: "How big is the area of ​​island A?", the user's expected The answer is a definite number. In the traditional retrieval mode, the user needs to click on the result links one by one to find the answer in the paragraphs. Concrete solution steps of the present invention are as follows:

[0047] Step 1: Preprocess the text, segment it into sentences and paragraphs, and use Lucene or Solr search engine to build index data for the text. The definition of the sentence index field is shown in Table 1.

[0048] Table 1

[0049] field name

field meaning

senID

Sentence ID

senContent

sentence content

senInParaLocation

The position of the sentence in the paragraph...

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 discloses a task-oriented unstructured information intelligent question and answer system construction method. According to the method, a user request is subjected to natural language processing, key words and sentence patterns of a request statement are identified, task types to which the user request belongs are matched, a query request expression is generated, and different searchconditions and sorting conditions are formulated according to different task types. Three expected answers which are mapped by the task is defined and comprise a weather type, a time type and a digital type, wherein the three types of questions can be directly and accurately answered to the questions of the user. And the system queries candidate results meeting conditions in sentences and paragraph indexes. The candidate sentences or paragraphs screen words conforming to task expectation answer types according to named entity recognition results, screen out results containing target type phrases, mark the results as target answers and highlight and display the target answers; Wherein the results which do not contain the target type phrases are ranked backwards. Finally, the answer is output.

Description

technical field [0001] The invention relates to the fields of Chinese natural language processing technology and information search technology, in particular to a method for constructing a task-oriented intelligent question answering system for unstructured information. Background technique [0002] Now the free sharing of various information resources around the world has resulted in the continuous generation of multi-source heterogeneous information, which is huge in quantity, complex and diverse in content, and the quality of information varies. In such a complex environment, the information space presents many uncertainties. The query of information is still through the traditional keyword query information. More complex requirements often cannot be completed in one query. It takes several rounds of query to obtain the key information. . The demand for a question answering system that can accurately understand natural language questions is becoming more and more urgent....

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): G06F16/31G06F16/332G06F16/36
Inventor 丁蔚然姜晓夏葛唯益王羽王振宇
Owner THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products