公司规模
Large Corporate
产品
- Impetus Analytics Module
- Event Store/Indexer Abstraction Layer
- Publish Module
技术栈
- Text Categorization Algorithm
- Matrix Decomposition
实施规模
- Enterprise-wide Deployment
影响指标
- Productivity Improvements
- Digital Expertise
技术
- 分析与建模 - 大数据分析
- 分析与建模 - 自然语言处理 (NLP)
适用行业
- 电信
适用功能
- 商业运营
服务
- 数据科学服务
关于客户
本案例研究中的客户是一家提供全国性电信服务的大型电信公司。他们需要一个可以对文本数据进行实时、多语言分类和情绪分析的系统。该公司处理大量不同类型的数据,例如网络日志、电子邮件、聊天和文件。他们需要一个解决方案,可以提取和解析这些数据,以非常高的准确度应用实时多语言分类和情绪分析,存储元数据和原始二进制数据以供查询,并满足冷数据 5 秒的查询 SLA。
挑战
客户是一家大型电信公司,提供全国性电信服务,需要一套能够对文本数据进行实时、多语言分类和情绪分析的系统。他们正在寻找一种解决方案,能够以极高的吞吐量存储、索引和查询 PB 级数据。关键要求包括能够提取和解析大量数据 [250M (15 TB) 条记录/天],这些记录类型各异,例如网络日志、电子邮件、聊天和文件。他们还需要以极高的准确率(四个九)应用实时多语言分类和情绪分析,存储元数据和原始二进制数据以供查询,并满足冷数据 5 秒的查询 SLA。
解决方案
Impetus 提供的解决方案由三个模块组成。分析模块负责执行文本分类和情感分析。它实现了基于矩阵分解的文本分类算法。传入的测试文档必须经过一系列预处理和数值计算。Impetus 设计了分类器以实现极低的延迟。事件存储/索引器抽象层负责根据配置存储和索引信息。发布模块负责将分析结果或事件数据发布到外部系统。
运营影响
数量效益
Case Study missing?
Start adding your own!
Register with your work email and create a new case study profile for your business.
相关案例.
![](/files/casestudy/Vodafone-Hosted-On-AWS.png)
Case Study
Vodafone Hosted On AWS
Vodafone found that traffic for the applications peak during the four-month period when the international cricket season is at its height in Australia. During the 2011/2012 cricket season, 700,000 consumers downloaded the Cricket Live Australia application. Vodafone needed to be able to meet customer demand, but didn’t want to invest in additional resources that would be underutilized during cricket’s off-season.
![](/files/casestudy/SKT--Construction-of-Smart-Office-Environment.png)
Case Study
SKT, Construction of Smart Office Environment
SK T-Tower is the headquarters of SK Telecom. Inside the building, different types of mobile devices, such as laptops, smartphones and tablets, are in use, and with the increase in WLAN traffic and the use of quality multimedia data, the volume of wireless data sees an explosive growth. Users want limitless Internet access in various places in addition to designated areas.