WO2023011093A1 - Procédé et appareil d'apprentissage de modèle de tâche, et dispositif électronique et support de stockage - Google Patents
Procédé et appareil d'apprentissage de modèle de tâche, et dispositif électronique et support de stockage Download PDFInfo
- Publication number
- WO2023011093A1 WO2023011093A1 PCT/CN2022/104081 CN2022104081W WO2023011093A1 WO 2023011093 A1 WO2023011093 A1 WO 2023011093A1 CN 2022104081 W CN2022104081 W CN 2022104081W WO 2023011093 A1 WO2023011093 A1 WO 2023011093A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- training
- sample
- samples
- test set
- test
- Prior art date
Links
- 238000012549 training Methods 0.000 title claims abstract description 341
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012360 testing method Methods 0.000 claims abstract description 129
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000010801 machine learning Methods 0.000 abstract description 4
- 238000003058 natural language processing Methods 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 128
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Definitions
- an electronic device including:
- FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure.
- the original labels of the training samples in the training set and the test samples in the testing set can be removed, and a first label such as 0 is configured for all training samples in the training set to identify that these training samples are all samples in the training set. Configure a second label such as 1 for all test samples in the test set to identify that these samples are all samples in the test set.
- the combined sample set can be randomly split to obtain a new training set and a new test set.
- training samples with high weights are more likely to be selected to participate in training, which can make the task model more inclined to learn training samples with high weights, that is, training samples that are more similar to the test set. It can overcome the problem of training set and sample set distribution offset.
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
La présente divulgation se rapporte au domaine technique de l'intelligence artificielle telle que l'apprentissage automatique et le traitement de langage naturel. Elle concerne un procédé et un appareil d'apprentissage de modèle de tâche, ainsi qu'un dispositif électronique et un support de stockage. La solution de mise en œuvre spécifique consiste à : acquérir les similarités entre des échantillons d'apprentissage d'un ensemble d'apprentissage et un ensemble d'essai; configurer les poids des échantillons d'apprentissage correspondants en fonction des similarités entre les échantillons d'apprentissage de l'ensemble d'apprentissage et de l'ensemble d'essai; et apprendre un modèle de tâche en fonction des échantillons d'apprentissage de l'ensemble d'apprentissage et des poids des échantillons d'apprentissage correspondants. Au moyen de la présente divulgation, la précision d'un modèle de tâche appris peut être améliorée efficacement.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110891285.2 | 2021-08-04 | ||
CN202110891285.2A CN113807391A (zh) | 2021-08-04 | 2021-08-04 | 任务模型的训练方法、装置、电子设备及存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023011093A1 true WO2023011093A1 (fr) | 2023-02-09 |
Family
ID=78893267
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/104081 WO2023011093A1 (fr) | 2021-08-04 | 2022-07-06 | Procédé et appareil d'apprentissage de modèle de tâche, et dispositif électronique et support de stockage |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113807391A (fr) |
WO (1) | WO2023011093A1 (fr) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113807391A (zh) * | 2021-08-04 | 2021-12-17 | 北京百度网讯科技有限公司 | 任务模型的训练方法、装置、电子设备及存储介质 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160078359A1 (en) * | 2014-09-12 | 2016-03-17 | Xerox Corporation | System for domain adaptation with a domain-specific class means classifier |
CN105574547A (zh) * | 2015-12-22 | 2016-05-11 | 北京奇虎科技有限公司 | 适应动态调整基分类器权重的集成学习方法及装置 |
CN110515836A (zh) * | 2019-07-31 | 2019-11-29 | 杭州电子科技大学 | 一种面向软件缺陷预测的加权朴素贝叶斯方法 |
CN113807391A (zh) * | 2021-08-04 | 2021-12-17 | 北京百度网讯科技有限公司 | 任务模型的训练方法、装置、电子设备及存储介质 |
CN114187979A (zh) * | 2022-02-15 | 2022-03-15 | 北京晶泰科技有限公司 | 数据处理、模型训练、分子预测和筛选方法及其装置 |
-
2021
- 2021-08-04 CN CN202110891285.2A patent/CN113807391A/zh active Pending
-
2022
- 2022-07-06 WO PCT/CN2022/104081 patent/WO2023011093A1/fr unknown
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160078359A1 (en) * | 2014-09-12 | 2016-03-17 | Xerox Corporation | System for domain adaptation with a domain-specific class means classifier |
CN105574547A (zh) * | 2015-12-22 | 2016-05-11 | 北京奇虎科技有限公司 | 适应动态调整基分类器权重的集成学习方法及装置 |
CN110515836A (zh) * | 2019-07-31 | 2019-11-29 | 杭州电子科技大学 | 一种面向软件缺陷预测的加权朴素贝叶斯方法 |
CN113807391A (zh) * | 2021-08-04 | 2021-12-17 | 北京百度网讯科技有限公司 | 任务模型的训练方法、装置、电子设备及存储介质 |
CN114187979A (zh) * | 2022-02-15 | 2022-03-15 | 北京晶泰科技有限公司 | 数据处理、模型训练、分子预测和筛选方法及其装置 |
Non-Patent Citations (2)
Title |
---|
WANG LINGDI, XU HUA: "An Adaptive Ensemble Algorithm Based on Clustering and AdaBoost", JILIN DAXUE XUEBAO (LIXUE BAN) - UNIVERSITY. JOURNAL (SCIENCE EDITION), JILIN DAXUE CHUBANSHE, CHANGCHUN, CN, vol. 56, no. 4, 26 July 2018 (2018-07-26), CN , pages 917 - 924, XP093031569, ISSN: 1671-5489, DOI: 10.13413/j.cnki.jdxblxb.2018.04.25 * |
ZENG XI, LING-JUN KONG, WEN-JIE ZHAN: "Spectral Reflectance Reconstruction Based on Vector Angle Sample Selection", BAOZHUANG GONGCHENG - PACKAGING ENGINEERING, ZHONGGUO BINGQI GONGYE DI-59 YANJIUSUO, CN, vol. 39, no. 15, 10 August 2018 (2018-08-10), CN , pages 216 - 220, XP093031576, ISSN: 1001-3563, DOI: 10.19554/j.cnki.1001-3563.2018.15.034 * |
Also Published As
Publication number | Publication date |
---|---|
CN113807391A (zh) | 2021-12-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3955204A1 (fr) | Procédé et appareil de traitement de données, dispositif électronique et support de mémoire | |
US20220374678A1 (en) | Method for determining pre-training model, electronic device and storage medium | |
CN115082920A (zh) | 深度学习模型的训练方法、图像处理方法和装置 | |
CN113657483A (zh) | 模型训练方法、目标检测方法、装置、设备以及存储介质 | |
WO2023011093A1 (fr) | Procédé et appareil d'apprentissage de modèle de tâche, et dispositif électronique et support de stockage | |
CN113392920B (zh) | 生成作弊预测模型的方法、装置、设备、介质及程序产品 | |
CN114821063A (zh) | 语义分割模型的生成方法及装置、图像的处理方法 | |
CN114462598A (zh) | 深度学习模型的训练方法、确定数据类别的方法和装置 | |
CN116342164A (zh) | 目标用户群体的定位方法、装置、电子设备及存储介质 | |
CN114692778A (zh) | 用于智能巡检的多模态样本集生成方法、训练方法及装置 | |
CN114078274A (zh) | 人脸图像检测方法、装置、电子设备以及存储介质 | |
CN114492364A (zh) | 相同漏洞的判断方法、装置、设备和存储介质 | |
CN114417822A (zh) | 用于生成模型解释信息的方法、装置、设备、介质和产品 | |
CN114067805A (zh) | 声纹识别模型的训练与声纹识别方法及装置 | |
CN114238611A (zh) | 用于输出信息的方法、装置、设备以及存储介质 | |
CN114021642A (zh) | 数据处理方法、装置、电子设备和存储介质 | |
CN113806541A (zh) | 情感分类的方法和情感分类模型的训练方法、装置 | |
CN111325350A (zh) | 可疑组织发现系统和方法 | |
US20240037410A1 (en) | Method for model aggregation in federated learning, server, device, and storage medium | |
CN114844889B (zh) | 视频处理模型的更新方法、装置、电子设备及存储介质 | |
CN114066278B (zh) | 物品召回的评估方法、装置、介质及程序产品 | |
CN113408664B (zh) | 训练方法、分类方法、装置、电子设备以及存储介质 | |
CN114547448B (zh) | 数据处理、模型训练方法、装置、设备、存储介质及程序 | |
US20220385583A1 (en) | Traffic classification and training of traffic classifier | |
CN115471717B (zh) | 模型的半监督训练、分类方法装置、设备、介质及产品 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
NENP | Non-entry into the national phase |
Ref country code: DE |