CN113597602B - 从随机化意图向量邻近度创建意图识别模型 - Google Patents

从随机化意图向量邻近度创建意图识别模型 Download PDF

Info

Publication number
CN113597602B
CN113597602B CN202080021344.4A CN202080021344A CN113597602B CN 113597602 B CN113597602 B CN 113597602B CN 202080021344 A CN202080021344 A CN 202080021344A CN 113597602 B CN113597602 B CN 113597602B
Authority
CN
China
Prior art keywords
intent
vector
vectors
candidate
input
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202080021344.4A
Other languages
English (en)
Chinese (zh)
Other versions
CN113597602A (zh
Inventor
元中方
殷昆燕
杨远琳
刘桐
李贺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by International Business Machines Corp filed Critical International Business Machines Corp
Publication of CN113597602A publication Critical patent/CN113597602A/zh
Application granted granted Critical
Publication of CN113597602B publication Critical patent/CN113597602B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/10—Speech classification or search using distance or distortion measures between unknown speech and reference templates
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/1822—Parsing for meaning understanding
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Machine Translation (AREA)
  • Image Analysis (AREA)
CN202080021344.4A 2019-04-22 2020-04-02 从随机化意图向量邻近度创建意图识别模型 Active CN113597602B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US16/390,845 2019-04-22
US16/390,845 US11069346B2 (en) 2019-04-22 2019-04-22 Intent recognition model creation from randomized intent vector proximities
PCT/IB2020/053124 WO2020217121A1 (en) 2019-04-22 2020-04-02 Intent recognition model creation from randomized intent vector proximities

Publications (2)

Publication Number Publication Date
CN113597602A CN113597602A (zh) 2021-11-02
CN113597602B true CN113597602B (zh) 2025-05-23

Family

ID=72832787

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080021344.4A Active CN113597602B (zh) 2019-04-22 2020-04-02 从随机化意图向量邻近度创建意图识别模型

Country Status (6)

Country Link
US (2) US11069346B2 (https=)
JP (1) JP7507788B2 (https=)
CN (1) CN113597602B (https=)
DE (1) DE112020002042T5 (https=)
GB (1) GB2597166A (https=)
WO (1) WO2020217121A1 (https=)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11069346B2 (en) * 2019-04-22 2021-07-20 International Business Machines Corporation Intent recognition model creation from randomized intent vector proximities
KR102339085B1 (ko) * 2019-07-22 2021-12-14 엘지전자 주식회사 사용자의 어플리케이션 사용 기록을 고려하여 사용자의 음성을 인식하는 인공 지능 장치 및 그 방법
US11481599B2 (en) * 2019-09-04 2022-10-25 Tencent America LLC Understanding a query intention for medical artificial intelligence systems using semi-supervised deep learning
US11113588B2 (en) * 2019-10-02 2021-09-07 United States Of America As Represented By The Secretry Of The Navy Randomization-based hierarchical and associatively assisted vector learning for machine vision
KR102834613B1 (ko) 2019-12-09 2025-07-16 엘지전자 주식회사 인공 지능 모델에 대한 학습 데이터를 생성하는 인공 지능 장치 및 그 방법
US11538467B1 (en) * 2020-06-12 2022-12-27 Amazon Technologies, Inc. Calibrated noise for text modification
US12277390B2 (en) * 2021-02-02 2025-04-15 Samsung Electronics Co., Ltd. Electronic device for processing user's inquiry, and operation method of the electronic device
US11715469B2 (en) * 2021-02-26 2023-08-01 Walmart Apollo, Llc Methods and apparatus for improving search retrieval using inter-utterance context
CN114282535B (zh) * 2021-04-05 2024-12-17 北京智慧星光信息技术有限公司 基于上下文语义精准地域识别方法、系统及电子设备
CN112989800A (zh) * 2021-04-30 2021-06-18 平安科技（深圳）有限公司 基于Bert的篇章的多意图识别方法、设备及可读存储介质
US12314675B2 (en) * 2021-05-10 2025-05-27 Walden University, Llc System and method for a cognitive conversation service
CN115482811A (zh) * 2021-05-31 2022-12-16 华为技术有限公司 一种语音交互应答方法和电子设备
CN115706740A (zh) * 2021-08-13 2023-02-17 中国移动通信有限公司研究院 一种请求处理方法、装置、设备及可读存储介质
CN114238579B (zh) * 2021-12-20 2023-02-10 北京聆心智能科技有限公司 文本分析方法、装置、介质和计算设备
CN118484551B (zh) * 2024-07-09 2024-10-11 北京龙软科技股份有限公司 基于多维时空信息矢量图形的互生成式人工智能系统

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108363690A (zh) * 2018-02-08 2018-08-03 北京十三科技有限公司 基于神经网络的对话语义意图预测方法及学习训练方法

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1940915B (zh) * 2005-09-29 2010-05-05 国际商业机器公司 训练语料扩充系统和方法
US9135237B2 (en) * 2011-07-13 2015-09-15 Nuance Communications, Inc. System and a method for generating semantically similar sentences for building a robust SLM
US9275342B2 (en) * 2012-04-09 2016-03-01 24/7 Customer, Inc. Method and apparatus for intent modeling and prediction
CN103942198B (zh) 2013-01-18 2017-07-28 佳能株式会社 用于挖掘意图的方法和设备
CN104346406B (zh) 2013-08-08 2018-05-22 北大方正集团有限公司 训练语料扩充装置和训练语料扩充方法
US20180204184A1 (en) * 2014-03-26 2018-07-19 Unanimous A. I., Inc. Parallelized sub-factor aggregation in real-time swarm-based collective intelligence systems
US10191999B2 (en) * 2014-04-30 2019-01-29 Microsoft Technology Licensing, Llc Transferring information across language understanding model domains
JP6514503B2 (ja) * 2014-12-25 2019-05-15 クラリオン株式会社 意図推定装置、および意図推定システム
US10388274B1 (en) * 2016-03-31 2019-08-20 Amazon Technologies, Inc. Confidence checking for speech processing and query answering
US10453117B1 (en) * 2016-06-29 2019-10-22 Amazon Technologies, Inc. Determining domains for natural language understanding
CN107765883A (zh) * 2016-08-22 2018-03-06 富士通株式会社 输入法的候选词语的排序方法和排序设备
KR20180055189A (ko) 2016-11-16 2018-05-25 삼성전자주식회사 자연어 처리 방법 및 장치와 자연어 처리 모델을 학습하는 방법 및 장치
US10467509B2 (en) * 2017-02-14 2019-11-05 Microsoft Technology Licensing, Llc Computationally-efficient human-identifying smart assistant computer
US20180293221A1 (en) * 2017-02-14 2018-10-11 Microsoft Technology Licensing, Llc Speech parsing with intelligent assistant
CN107146610B (zh) * 2017-04-10 2021-06-15 易视星空科技无锡有限公司 一种用户意图的确定方法及装置
DK179549B1 (en) * 2017-05-16 2019-02-12 Apple Inc. FAR-FIELD EXTENSION FOR DIGITAL ASSISTANT SERVICES
CN107526725B (zh) 2017-09-04 2021-08-24 北京百度网讯科技有限公司 基于人工智能的用于生成文本的方法和装置
CN108090520A (zh) 2018-01-08 2018-05-29 北京中关村科金技术有限公司 意图识别模型的训练方法、系统、装置及可读存储介质
US10733375B2 (en) * 2018-01-31 2020-08-04 Apple Inc. Knowledge-based framework for improving natural language understanding
CN108460104B (zh) * 2018-02-06 2021-06-18 北京奇虎科技有限公司 一种实现内容定制的方法和装置
CN108829722B (zh) 2018-05-08 2020-10-02 国家计算机网络与信息安全管理中心 一种远程监督的Dual-Attention关系分类方法及系统
DK179822B1 (da) * 2018-06-01 2019-07-12 Apple Inc. Voice interaction at a primary device to access call functionality of a companion device
US10839159B2 (en) * 2018-09-28 2020-11-17 Apple Inc. Named entity normalization in a spoken dialog system
CN109582970B (zh) * 2018-12-12 2023-05-30 科大讯飞华南人工智能研究院（广州）有限公司 一种语义度量方法、装置、设备及可读存储介质
US11069346B2 (en) 2019-04-22 2021-07-20 International Business Machines Corporation Intent recognition model creation from randomized intent vector proximities

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108363690A (zh) * 2018-02-08 2018-08-03 北京十三科技有限公司 基于神经网络的对话语义意图预测方法及学习训练方法

Also Published As

Publication number Publication date
GB202115690D0 (en) 2021-12-15
GB2597166A (en) 2022-01-19
US11069346B2 (en) 2021-07-20
US20200335095A1 (en) 2020-10-22
US11521602B2 (en) 2022-12-06
DE112020002042T5 (de) 2022-01-27
US20210264906A1 (en) 2021-08-26
WO2020217121A1 (en) 2020-10-29
CN113597602A (zh) 2021-11-02
JP7507788B2 (ja) 2024-06-28
JP2022529664A (ja) 2022-06-23

Similar Documents

Publication Publication Date Title
CN113597602B (zh) 从随机化意图向量邻近度创建意图识别模型
US10909327B2 (en) Unsupervised learning of interpretable conversation models from conversation logs
US10929614B2 (en) Automated contextual dialog generation for cognitive conversation
US10937416B2 (en) Cross-domain multi-task learning for text classification
US11645470B2 (en) Automated testing of dialog systems
US11151324B2 (en) Generating completed responses via primal networks trained with dual networks
US10394963B2 (en) Natural language processor for providing natural language signals in a natural language output
US11182557B2 (en) Driving intent expansion via anomaly detection in a modular conversational system
CN110070862B (zh) 对话系统中基于本体的自动引导的方法和系统
US12198682B2 (en) Conversation generation using summary-grounded conversation generators
US11011161B2 (en) RNNLM-based generation of templates for class-based text generation
US10394861B2 (en) Natural language processor for providing natural language signals in a natural language output
US11281867B2 (en) Performing multi-objective tasks via primal networks trained with dual networks
CN113366510B (zh) 经由训练的原始网络与双网络来执行多目标任务
WO2023066238A1 (en) Adaptive answer confidence scoring by agents in multi-agent system
US20220358358A1 (en) Accelerating inference of neural network models via dynamic early exits
US10748525B2 (en) Multi-modal dialog agents representing a level of confidence in analysis
US20170193391A1 (en) Iterative interpolation of maximum entropy models
US12190067B2 (en) Context-based response generation
US20230015895A1 (en) Accelerating inference of transformer-based models
US11663402B2 (en) Text-to-vectorized representation transformation
US20220092403A1 (en) Dialog data processing
US12451141B2 (en) Generating multi-turn dialog datasets

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant