A method and system for intelligent customer service based on multi-feature fusion

A multi-feature fusion, intelligent customer service technology, applied in neural learning methods, special data processing applications, instruments, etc., can solve problems such as the inability to meet the requirements of similarity calculation accuracy, achieve good accuracy and generalization ability, and improve intelligence. , the effect of simple operation

Active Publication Date: 2022-05-17
华云天下(南京)科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the existing method has a good effect on the similarity calculation of intelligent customer service data sentences, it still cannot meet the accuracy requirements of similarity calculation.

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 intelligent customer service based on multi-feature fusion
  • A method and system for intelligent customer service based on multi-feature fusion
  • A method and system for intelligent customer service based on multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention is further analyzed below in conjunction with specific embodiment.

[0042] An intelligent customer service method based on multi-feature fusion, the customer service system adopted includes a data acquisition module, a data preprocessing module and a similarity identification module. The data preprocessing module includes removing useless characters, removing stop words, Chinese error correction, Chinese word segmentation and vectorization. Similarity recognition module includes preprocessing layer, feature extraction module, feature fusion layer, classification layer and output layer. The feature extraction module includes a semantic feature module and a morphological feature module. The semantic feature module is used to extract the semantic feature of the sentence pair composed of the question sentence S1 and the corpus sentence S2 to obtain the semantic feature matrix; the morphological feature module is used to perform the morphological feat...

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 customer service method and system based on multi-feature fusion. The traditional intelligent customer service system uses a single feature to calculate the similarity between the user's question sentence and the corpus sentence to retrieve the answer. The present invention is as follows: First, a corpus and a user query data set are established. The corpus contains the question and answer information needed to overcome. Multiple sentence pairs with the same semantics and multiple sentence pairs with different semantics are extracted from the corpus to form a user query data set. 2. Preprocess the sentences in the corpus; Chinese word segmentation is included in the preprocessing to obtain the vocabulary. 3. Establish and train the similarity recognition module. Fourth, use the similarity recognition module to judge whether the user question sentence S1 is synonymous with each corpus sentence S2; when a sentence in the corpus is synonymous with the user question sentence S1, push the corresponding reply information of the sentence to the user. The method of the invention improves the intelligence of the customer service system by introducing the multi-head attention mechanism.

Description

technical field [0001] The present invention relates to the technical field of natural language processing and intelligent customer service, in particular to an intelligent customer service method and system based on multi-feature fusion. Background technique [0002] Intelligent customer service is a major research hotspot in the financial field, the core of which is to quickly and accurately answer users' inquiries. The traditional intelligent customer service system mainly calculates the similarity between the user's question statement and the corpus statement through a single feature, and retrieves the answer through matching. Although user question sentences and corpus sentences contain similar keywords, the semantic logic may be quite different. Sentence similarity is the key technology to realize intelligent customer service, and it is a subset of text similarity recognition. The method based on deep learning is an important method for text similarity calculation. I...

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): G06F16/332G06K9/62G06F40/247G06F40/289G06F40/30G06N3/04G06N3/08
CPCG06F16/3329G06F40/247G06F40/289G06F40/30G06N3/044G06N3/045G06F18/22G06F18/253
Inventor 李美玲李秀梅孙军梅任亚伟
Owner 华云天下(南京)科技有限公司
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