对呼叫/联系中心系统中多标签短信分类的再培训策略的分析
Katarzyna Poczeta1, Mirosław Płaza2, Michał Zawadzki2
1Faculty of Electrical Engineering, Automatics Control and Computer Science, Kielce University of Technology, 25-314, Kielce, Poland. k.piotrowska@tu.kielce.pl.
Scientific reports
|May 2, 2024
概括
重新训练人工智能模型改善了动态呼叫中心数据中的文本分类. 这种人工智能再培训过程通过适应不断变化的数据来提高效率,有利于业务应用.
科学领域:
- 人工智能的人工智能
- 自然语言处理自然语言处理.
- 机器学习 机器学习
背景情况:
- 数据驱动的AI模型可以随着数据特性随着时间的推移而降低性能.
- 呼叫/联系中心系统,特别是文本分类模块,由于营销活动而面临动态数据变化.
- 保持高分类效率需要适应性人工智能技术,如模型再培训.
研究的目的:
- 描述和评估呼叫/联系中心系统中多标签文本分类模型的再培训过程.
- 调查再培训对面对不断变化的数据模型的影响.
- 为了比较不同再培训策略的有效性.
主要方法:
- 从变压器 (BERT) 模型中重新训练人工神经网络和双向编码器表示.
- 利用波兰呼叫中心档案和英语公共数据集进行再培训.
- 将再培训策略与使用Emotica指标的基线参考模型进行比较.
主要成果:
- 通过Emotica指标测量,分类效率提高了多达5%.
- 证明整合再培训过程为测试的AI解决方案带来了切实可见的好处.
- 该研究证实了适应性学习在现实世界商业应用中的价值.
结论:
- 模型再培训是维持人工智能性能在通话中心等动态环境中的关键技术.
- 实施的再培训策略有效地提高了分类准确性.
- 这项研究为改善商业环境中人工智能驱动的文本分类提供了实际框架.
相关概念视频
02:16Stereotype Content Model
14.7K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.7K
01:23Reinforcement
202
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
202