Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020140612 - CONVOLUTIONAL NEURAL NETWORK-BASED INTENTION RECOGNITION METHOD, APPARATUS, DEVICE, AND MEDIUM

Publication Number WO/2020/140612
Publication Date 09.07.2020
International Application No. PCT/CN2019/117097
International Filing Date 11.11.2019
IPC
G06F 16/33 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
30of unstructured textual data
33Querying
G10L 25/30 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
25Speech or voice analysis techniques not restricted to a single one of groups G10L15/-G10L21/129
27characterised by the analysis technique
30using neural networks
CPC
G06F 16/33
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
30of unstructured textual data
33Querying
G06K 9/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G10L 15/26
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
26Speech to text systems
G10L 25/30
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
25Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
27characterised by the analysis technique
30using neural networks
Applicants
  • 平安科技(深圳)有限公司 PING AN TECHNOLOGY (SHENZHEN) CO., LTD. [CN]/[CN]
Inventors
  • 王健宗 WANG, Jianzong
  • 程宁 CHENG, Ning
  • 肖京 XIAO, Jing
Agents
  • 深圳众鼎专利商标代理事务所(普通合伙) SHENZHEN ZHONGDING INTELLECTUAL PROPERTY AGENCY
Priority Data
201910007860.004.01.2019CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) CONVOLUTIONAL NEURAL NETWORK-BASED INTENTION RECOGNITION METHOD, APPARATUS, DEVICE, AND MEDIUM
(FR) PROCÉDÉ DE RECONNAISSANCE D'INTENTION BASÉ SUR UN RÉSEAU NEURONAL CONVOLUTIF, APPAREIL, DISPOSITIF ET SUPPORT
(ZH) 基于卷积神经网络的意图识别方法、装置、设备及介质
Abstract
(EN)
The present application discloses a convolutional neural network-based intention recognition method, an apparatus, a device and a medium, being applied to the field of deep learning technology, and being used for solving the problem of low accuracy of intention recognition. Said method provided in the present application comprises: acquiring a target text of which the intention is to be recognized; performing vectorization processing on the target text, to obtain a target vector; putting the target vector, as an input, into a pre-trained convolutional neural network, to obtain a target result vector outputted by the convolutional neural network, respective elements in the target result vector being respectively first probability values corresponding to respective preset user intentions, a first probability value characterizing the probability that the target text indicates the corresponding preset user intention; and determining the preset user intention having the highest first probability value as a target user intention corresponding to the target text.
(FR)
La présente invention concerne un procédé de reconnaissance d'intention basé sur un réseau neuronal convolutif, un appareil, un dispositif et un support, appliqués au domaine de la technologie d'apprentissage profond, et étant utilisés pour résoudre le problème de faible précision de reconnaissance d'intention. Ledit procédé de la présente invention consiste à : acquérir un texte cible dont l'intention doit être reconnue ; effectuer un traitement de vectorisation sur le texte cible, pour obtenir un vecteur cible ; fournir le vecteur cible, en tant qu'entrée, à un réseau neuronal convolutif préentraîné pour obtenir un vecteur de résultat cible produit par le réseau neuronal convolutif, des éléments respectifs dans le vecteur de résultat cible étant respectivement des premières valeurs de probabilité correspondant à des intentions d'utilisateur prédéfinies respectives, une première valeur de probabilité caractérisant la probabilité que le texte cible indique l'intention d'utilisateur prédéfinie correspondante ; et déterminer l'intention d'utilisateur prédéfinie ayant la première valeur de probabilité la plus élevée comme étant une intention d'utilisateur cible correspondant au texte cible.
(ZH)
本申请公开了一种基于卷积神经网络的意图识别方法、装置、设备及介质,应用于深度学习技术领域,用于解决意图识别准确性低下的问题。本申请提供的方法包括:获取待识别意图的目标文本;对所述目标文本进行向量化处理,得到目标向量;将所述目标向量作为输入投入至预先训练好的卷积神经网络,得到所述卷积神经网络输出的目标结果向量,所述目标结果向量中的各个元素分别为各个预设用户意图对应的第一概率值,第一概率值表征了所述目标文本属于对应的预设用户意图的概率;将第一概率值最高的预设用户意图确定为所述目标文本对应的目标用户意图。
Also published as
Latest bibliographic data on file with the International Bureau