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

Knowledge base question and answer extraction method and system, mobile terminal and storage medium

A mobile terminal and knowledge base technology, applied in the field of knowledge base, can solve problems such as low efficiency of question and answer extraction, and achieve the effect of improving accuracy and improving extraction efficiency

Active Publication Date: 2020-02-21
XIAMEN KUAISHANGTONG TECH CORP LTD
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the embodiments of the present invention is the low efficiency of question and answer extraction due to the manual way of extracting high-quality question and answer pairs from real dialogues

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
  • Knowledge base question and answer extraction method and system, mobile terminal and storage medium
  • Knowledge base question and answer extraction method and system, mobile terminal and storage medium
  • Knowledge base question and answer extraction method and system, mobile terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] see figure 1 , is a flow chart of the knowledge base question and answer extraction method provided in the first embodiment of the present invention, including steps:

[0046] Step S10, obtaining artificial question and answer data, and performing question sentence recognition on the artificial question and answer data, so as to obtain customer question sentences;

[0047] Wherein, the artificial question-and-answer data are question-and-answer information between different artificial customer service personnel and customers, and the question-sentence recognition is used to obtain the question sentences raised by users in the artificial question-and-answer data. Preferably, the question-sentence recognition can use semantic judgment, characteristic words Judgment and acquisition of sentences by means of judgment or punctuation judgment;

[0048] Specifically, when the question sentence is judged in a semantic manner, the semantics of the question and answer sentence at...

Embodiment 2

[0062] see figure 2 , is a flow chart of the knowledge base question and answer extraction method provided in the second embodiment of the present invention, including steps:

[0063] Step S11, obtaining artificial question and answer data, inputting the artificial question and answer data into the question recognition model, and controlling the question recognition model to perform question analysis;

[0064] Among them, the question recognition model is used to classify texts, and a sentence can be characterized by binary classification, and the question sentence can be represented as 1, and the non-question sentence can be represented as 0, so as to construct a training data set, and Machine learning or deep learning models can be used to train the question recognition model; specifically, the artificial question and answer data is input into the trained question recognition model to obtain the question analysis results;

[0065] Preferably, before the step of controlling...

Embodiment 3

[0105] see image 3 , is a schematic structural diagram of the knowledge base question and answer extraction system 100 provided by the third embodiment of the present invention, including: a question recognition module 10, a response query module 11, a matching degree calculation module 12 and a storage module 13, wherein:

[0106] The question recognition module 10 is configured to obtain artificial question-answer data, and perform question recognition on the artificial question-answer data, so as to obtain customer question sentences.

[0107] Wherein, the question recognition module 10 is also used to: input the artificial question and answer data into the question recognition model, and control the question recognition model to perform question analysis; according to the analysis results of the question recognition model, The sequence judges the question sentence on the sentences in the artificial question answering data, so as to obtain the customer question sentence. ...

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 is suitable for the technical field of knowledge bases, and provides a knowledge base question and answer extraction method and system, a mobile terminal and a storage medium, and the method comprises the steps: obtaining manual question and answer data, and carrying out the question recognition of the manual question and answer data, so as to obtain a client questioning sentence; carrying out response query in the manual question and answer data according to the client question to acquire customer service answer information, wherein a plurality of customer service answering sentences are stored in the customer service answer information; calculating question-answer matching degrees between the customer questioning sentences and the customer service answering sentences respectively, and setting the customer service answering sentence corresponding to the maximum value in the question-answer matching degrees and the customer questioning sentences as question-answer pairs;and extracting and storing the question-answer pairs in a question-answer knowledge base. According to the method, based on automatic acquisition of the client questioning sentences and the customer service answering sentences and calculation design of the question-answer matching degree between the client questioning sentences and the corresponding customer service answering sentences, high-quality question-answer pairs can be automatically extracted from real manual question and answer data, and the extraction efficiency of the question-answer pairs is improved.

Description

technical field [0001] The invention belongs to the technical field of knowledge bases, and in particular relates to a method, system, mobile terminal and storage medium for extracting questions and answers from knowledge bases. Background technique [0002] With the development and popularization of artificial intelligence, there are more and more applications of intelligent customer service robots in various industries. For intelligent customer service robots in all fields, the knowledge question and answer database seems to be indispensable, and the knowledge question and answer database is given How to extract high-quality question and answer pairs based on real manual customer service chat records, and automatically build a knowledge base for customer service robots is a research hotspot and difficulty for FAQ robots. [0003] Since the existing FAQ automatic extraction algorithms are immature, many of them use manual methods to extract high-quality question-answer pair...

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): G06F16/332G06F40/279G06N3/04G06N3/08
CPCG06F16/3329G06N3/08G06N3/045
Inventor 詹威肖龙源蔡振华李稀敏刘晓葳王静
Owner XIAMEN KUAISHANGTONG TECH CORP LTD
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