ai物流智能调度效率对比_人工智能在物流中：人工智能改变物流的5种方式-CSDN博客

ai物流智能调度效率对比

A man who has been sleeping for twenty years and woke up in 2020 would find himself in a different transformational era. Along with numerous changes in ecology, politics, the way we live, and diseases we cure, he or she would be astonished by the consequences of the revolution that has redefined each of the aforementioned aspects of our lives. Digital revolution.

一个已经睡了二十年并在2020年醒来的男人会发现自己处在一个不同的转型时代。随着生态，政治，我们的生活方式和疾病的众多变化，他或她将对重新定义了我们生活中上述各个方面的革命的后果感到惊讶。数字革命。

Digitalization has reached more people than any other revolution. Since Gutenberg’s printing press, it has become the most outstanding event to mark a huge shift in the way we communicate. People have learned how to exhibit their intelligence by machines and systems that improve human thinking. Having crossed a few “AI winters” since the term coinage in 1956, artificial intelligence serves as a great benefit to all industries nowadays. And logistics is setting about its journey to make its way as an AI-driven industry.

数字化普及的人数超过任何其他革命。自古腾堡印刷机问世以来，这已成为标志着我们交流方式发生巨大变化的最杰出的盛会。人们已经学会了如何通过改善人类思维的机器和系统来展示自己的智慧。自从1956年造币一词以来，它已经度过了几个“人工智能冬天”，如今，人工智能为所有行业带来了巨大的好处。物流业正在迈向以AI驱动的行业之路。

物流中的AI：人工智能改变物流的五种方式 (AI in Logistics: five ways in artificial intelligence is transforming logistics)

人工智能释放了物流大数据的真正潜力 (AI unlocks the true potential of Big Data in Logistics)

Logistics companies receive a possibility to make clear predictions and optimize their performance using the power of Big Data. The high volume of structured and unstructured data is generated by supply chains on a daily basis. Big Data enables companies not only to exploit this information but also to adopt advanced predictive analytics and increased automation which drives strategic decisions.

物流公司可以利用大数据的力量做出清晰的预测并优化绩效。供应链每天都会生成大量的结构化和非结构化数据。大数据使公司不仅可以利用这些信息，而且可以采用高级预测分析和增强的自动化来驱动战略决策。

A well-known example of UPS has proved that proper logistics data analysis can save time, costs, and exclude safety risks. After data examination, the company revealed that trucks that turned left were stuck in the traffic what cost the company more fuel, time, and increased the number of delays. Now UPS tracks go straight or turn right in 90% of cases what saves the company 10m gallons of fuel and boost its delivery rate to 350,000 more packages annually.

UPS的一个著名例子证明，适当的物流数据分析可以节省时间，成本，并消除安全风险。经过数据检查后，该公司发现左转的卡车被堵在了车流中，这使该公司花费了更多的燃料，时间和更多的延误。现在，在90％的情况下，UPS轨道可以直行或右转，这为公司节省了1000万加仑的燃料，并将其交付率提高到每年增加35万包。

使用机器人可以替代物流中的劳动力 (Usage of robotics can substitute workforce in Logistics)

Artificial intelligence in Logistics also stands as a great benefit for the physical aspect of working. Robots are able to locate, move, sort, and track inventory augmenting the capabilities of the modern workforce.

物流中的人工智能也为工作的物理方面带来了巨大的好处。机器人能够定位，移动，分类和跟踪库存，从而增强了现代员工的能力。

Image for post — Usage of robotics can substitute workforce in Logistics

The Finnish company ZenRobotics has been developing intelligent robotic waste sorting systems since 2011. The engine ingests real-time data from three different cameras and sensor types and is trained to identify a wide variety of logos and labels. Such an implementation of machine learning in Logistics, allows the company to sort 4,000 unstructured recyclable items per hour.

芬兰公司ZenRobotics自2011年以来一直在开发智能的机器人废物分类系统。该引擎从三种不同的摄像头和传感器类型中提取实时数据，并经过培训以识别各种各样的徽标和标签。物流中机器学习的这种实现方式使公司每小时可以分类4,000个非结构化可回收物品。

人工智能促进仓库管理的物流自动化并优化供应链计划 (AI boosts logistic automation of warehouse management and optimizes supply chain planning)

Warehouse management can be also optimized by conducting accurate calculations of the number of items that need to be moved on a certain date and the amount of equipment needed to handle the process. With the help of machine learning in logistics, it is possible to spend less time establishing more detailed stock movement predictive analytics and increase the overall productivity of pick-and-pack processes. Logistic automation systems can also vastly improve the speed and accuracy of the communication process. The elements are enabled to conduct a dialogue with each other embracing system monitoring and control which ensures efficient warehouse management and provides the supply chains with contextual intelligence that allows making effective planning decisions based on the range of factors like the demand, possible transportation issues, and factory production planning.

仓库管理还可以通过精确计算特定日期需要搬运的物品数量和处理该流程所需的设备数量来进行优化。借助物流中的机器学习，可以花费更少的时间来建立更详细的库存移动预测分析，并提高分拣和包装流程的整体生产率。物流自动化系统还可以极大地提高通信过程的速度和准确性。这些元素能够相互进行对话，包括系统监视和控制，以确保有效的仓库管理并为供应链提供上下文智能，从而可以根据需求，可能的运输问题和工厂生产计划。

物流中的人工智能促进自动驾驶汽车 (AI in Logistics promotes autonomous vehicles)

The popularity of autonomous vehicles is rising with breakneck speed. And one of the reasons for this is the contribution the artificial intelligence makes to outperform human driving capabilities. AI allows the vehicle to perceive and predict the changes in its environment with the help of sensing technologies that perform together to produce a three-dimensional map of the vehicle’s environment including traffic signals and laws, interpreting road signs, identifying obstacles, etc. Without a possibility to hard-program a vehicle to react to every possible scenario, the capabilities of vehicles should be constantly improved with the help of AI as they enter the new surroundings.

自动驾驶汽车的普及程度正以惊人的速度增长。造成这种情况的原因之一是人工智能对超越人类驾驶能力的贡献。 AI使车辆能够借助传感技术感知并预测其环境的变化，这些传感技术共同产生车辆环境的三维地图，包括交通信号和法律，解释道路标志，识别障碍物等。可以对车辆进行硬编程以对每种可能的情况做出React的可能性，当车辆进入新环境时，应借助AI不断提高车辆的功能。

Traditional auto industry behemoths have embraced AI as a component of their development strategy, whereas, relatively new entrants like Tesla, Google, and others are actively using their own patent AI and manufacturing techniques to develop autonomous vehicles.

传统汽车行业的庞然大物已经将人工智能作为其发展战略的组成部分，而相对较新的进入者(如特斯拉，谷歌和其他公司)则积极利用自己的专利人工智能和制造技术来开发自动驾驶汽车。

客户体验 (Customer experience)

Most of the customers have just two touch points with logistic companies: checkout with an online retailer and receiving delivery or returning the item. While concerning businesses, the touch points are multiple: long-term contracts, operation of global supply chains, service level agreements, etc. AI in logistics can increase customer loyalty and retention through personalization of these touch points.

大多数客户与物流公司只有两个接触点：与在线零售商结账，接收交货或退货。在涉及业务时，接触点是多种多样的：长期合同，全球供应链运营，服务水平协议等。物流中的AI可以通过这些接触点的个性化来提高客户忠诚度和保留率。

One of the examples is a voice-based service that was adopted by DHL Parcel in 2017. Their customers became able to ask Amazon’s Alexa the shipment information about their parcels.

其中一个例子是DHL包裹在2017年采用的基于语音的服务。他们的客户开始向亚马逊的Alexa询问包裹的运输信息。

Logistics data analysis has the potential to take customer experience to the next level, delivering goods before they have even ordered them. Drawing predictions from logistical data services, analyzing browsing and purchase history, weather data, and social media chatters, companies can predict the next order a customer will make. Not to mention, demand prediction and shortening delivery time.

物流数据分析具有将客户体验提升到更高水平的潜力，甚至可以在订购之前交付货物。通过从物流数据服务中获取预测，分析浏览和购买历史，天气数据以及社交媒体聊天记录，公司可以预测客户的下一个订单。更不用说，需求预测和缩短交货时间。

结语 (Wrap up)

AI has already left the cinema and became an ordinary part of our everyday lives and most of the businesses. Though the future of artificial intelligence in Logistics is promising, some logistic networks have already shifted to a proactive and predictive paradigm and logistic automation with our help. And we strongly believe that the 21st century is the best time for “AI spring”.

人工智能已经离开电影院，并已成为我们日常生活和大多数企业的平凡部分。尽管物流业中人工智能的未来充满希望，但在我们的帮助下，一些物流网络已经转变为主动和可预测的范例以及物流自动化。我们坚信21世纪是“人工智能之春”的最佳时机。

If you are looking for a logistics software solution, inVerita is glad to help.

如果您正在寻找物流软件解决方案， inVerita很高兴为您提供帮助。

Originally published at inveritasoft.com on June 25, 2020.

最初于 2020 年6月25日 发布在 inveritasoft.com 上。