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

Intelligent question and answer sentence pair semantic matching method and device for government affair consultation service

A consulting service and intelligent question answering technology, applied in the fields of natural language processing and artificial intelligence, it can solve the problems of limited representation ability of single-layer network, loss of semantic information, and noise of coding results.

Pending Publication Date: 2020-11-27
QILU UNIV OF TECH
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the representation ability of a single-layer network is limited after all. Therefore, in order to improve the representation ability of the network and extract deeper and richer semantic features, the depth of the network is usually increased.
However, the encoding results of each layer in the deep network structure are not all valid information. In this case, two problems will arise: first, if only the output of the last layer of the network is taken as the encoding result, then it must be It will cause the loss of semantic information; second, if the output results of each layer of the network are directly combined, such as connection or addition, then the final encoding result will inevitably have a lot of noise
Therefore, the existing deep network structure still has the above-mentioned drawbacks that cannot be ignored for text semantic coding.

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
  • Intelligent question and answer sentence pair semantic matching method and device for government affair consultation service
  • Intelligent question and answer sentence pair semantic matching method and device for government affair consultation service
  • Intelligent question and answer sentence pair semantic matching method and device for government affair consultation service

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0113] as attached Figure 8 As shown, the main framework structure of the present invention includes a multi-granularity embedding module, a gated deep feature residual fusion network module, a semantic feature interactive matching module and a label prediction module. Among them, the multi-granularity embedding module performs embedding operations on the input sentence at word granularity and word granularity, and passes the result to the model's gated deep feature residual fusion network module. The gated deep feature residual fusion network module contains several layers of coding structures, such as Figure 7 As shown, the word embedding representation and word embedding representation output by the multi-granularity embedding module are first selectively fused through the gating mechanism to obtain the gated embedding fusion representation. At the same time, the word embedding representation and word embedding representation before fusion are passed to The first layer o...

Embodiment 2

[0119] as attached figure 1 As shown, the intelligent question-and-answer sentence-to-semantic matching method for government affairs consulting services of the present invention, the specific steps are as follows:

[0120] S1. Construct a sentence pair semantic matching knowledge base, as attached figure 2 As shown, the specific steps are as follows:

[0121] S101. Downloading datasets on the network to obtain original data: downloading datasets that have been published on the network for semantic matching of sentence pairs or artificially constructed datasets, and using them as raw data for constructing a knowledge base for semantic matching of sentence pairs.

[0122] For example: According to the historical records of government consultation, the question sentence pairs contained in it can be collected, a data set of government consultation question sentence pairs can be manually constructed, and the original data used to construct the semantic matching knowledge base of...

Embodiment 3

[0245] as attached Figure 6 As shown, the intelligent question-and-answer sentence-to-semantic matching device based on the government consultation service of Embodiment 2, the device includes,

[0246] The sentence-pair semantic matching knowledge base construction unit is used to obtain a large amount of sentence-pair data, and then preprocess it to obtain a sentence-pair semantic matching knowledge base that meets the training requirements; the sentence-pair semantic matching knowledge base construction unit includes,

[0247] The sentence-pair data acquisition unit is responsible for downloading the sentence-pair semantic matching datasets that have been published on the network or artificially constructed datasets, and using them as the original data for constructing the sentence-pair semantic matching knowledge base;

[0248] The original data hyphenation preprocessing or word segmentation preprocessing unit is responsible for preprocessing the raw data used to construc...

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 an intelligent question and answer sentence pair semantic matching method and device for government affair consultation service, and belongs to the technical field of artificial intelligence and natural language processing. The technical problem to be solved by the invention is how to capture deeper semantic context features and interaction information between sentences andreduce the loss of semantic information, so intelligent semantic matching of sentence pairs is realized. The adopted technical scheme is as follows: a sentence pair semantic matching model composed of a multi-granularity embedding module, a gating deep feature residual fusion network module, a semantic feature interaction matching module and a label prediction module is constructed and trained; and gated deep feature residual fusion expression of sentence information is achieved, meanwhile, final matching tensors of sentence pairs are generated through an attention mechanism and a gating mechanism, and the matching degree of the sentence pairs is judged, so that the purpose of intelligent semantic matching of the sentence pairs is achieved. The device comprises a sentence pair semantic matching knowledge base construction unit, a training data set generation unit, a sentence pair semantic matching model construction unit and a sentence pair semantic matching model training unit.

Description

technical field [0001] The invention relates to the technical fields of artificial intelligence and natural language processing, in particular to an intelligent question-and-answer sentence-pair semantic matching method for government consultation services. Background technique [0002] The people need to understand the relevant policies and documents formulated by the government when handling their daily affairs. In order to better serve the people, governments at all levels need to set up government consultation related service agencies to provide government consultation for the people. As the demand for government consultation continues to grow, the work pressure of relevant institutions continues to increase. Although the demand for government affairs consultation is constantly increasing, the vast majority of consultations are repeated consultations. For these repeated consultations, the historical consultation library can be mined and answered automatically. Intelli...

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 Applications(China)
IPC IPC(8): G06F40/211G06F40/30G06K9/62G06F16/332G06F16/33
CPCG06F40/211G06F40/30G06F16/3344G06F16/3329G06F18/214Y02D10/00
Inventor 鹿文鹏于瑞
Owner QILU UNIV OF TECH
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