Home >Technology peripherals >AI >Solve the artificial intelligence bottleneck and promote the development of the food delivery industry
In recent years, as the consumer Internet has moved deeper and deeper, the industrial Internet has become better and better, and the digital transformation of all walks of life is in full swing. In the face of an increasingly complex environment, digital and intelligent technologies with strong market penetration will work together and play a huge role in promoting economic development, empowering small and micro enterprises, and ensuring people's livelihood. In the emerging technology camp, the dividends released by artificial intelligence are making people's lives better.
Take the daily "ordering of takeout" as an example. Riders, users and merchants respectively constitute the epitome of employment, people's livelihood and economy. If artificial intelligence can realize the control of these three major groups Empowerment can meet the delivery needs in different scenarios, improve delivery efficiency and user experience, and thereby realize the vision of "let takeaways reach every corner of the world". The reason why artificial intelligence can play its role is inseparable from the upgrade of ICT infrastructure and the leap in deep learning framework.
A takeout delivered within 30 minutes has become a daily norm. However, it is not easy to do this: for example, if a rider delivers 5 orders, it will target 5 different merchants and users, and there will be tens of thousands of combinations of delivery routes. On popular food delivery platforms, the daily order volume during peak periods is huge, involving a large number of riders. To achieve the goal of 30-minute delivery, the number of route combinations is astronomical. At the same time, for the elderly and children, being able to complete the entire process of ordering takeout through voice operation without any barriers highlights the humanized design.
According to Meituan, one of the important tasks of the company’s “Technology Assists Life” project is to find the optimal solution for rider scheduling. While more than 10,000 engineers use artificial intelligence technology to improve efficiency, they also regularly work as riders to experience pain points in the food delivery process and continuously optimize solutions. In addition, the company's service engine combined with "intelligent interaction" technology has voice capabilities, allowing the elderly and children to obtain services in a convenient way of communication. Especially when the user's needs are delivered to the company's "Super Brain System", this large-scale, highly complex multi-person and multi-point real-time intelligent distribution dispatching system will perform rapid calculations, allowing users to obtain an unexpected service experience. Since 2016, Meituan has relied on more intelligent technologies to develop unmanned delivery in specific scenarios, which has been tested and made progress during the epidemic prevention and control period.
In the entire food delivery ecosystem, merchant groups are another core area of empowerment for Meituan. It is reported that in the "Meituan Merchant Brain", there are massive user evaluation analysis and knowledge correlation. Merchants only need a professional version of the SaaS cashier system to regularly obtain users' emotional curve changes, consumption levels, environmental preferences and similar merchants, etc. information. At the same time, with the help of intelligent analysis, merchants can also gain insights into service status, competitiveness, business districts, etc., providing a reference for decision-making from store opening to store operation management.
According to reports, food delivery is only part of Meituan’s overall ecological picture of building life services, and the complicated scenarios involved in technological empowerment are far more than this. In recent years, Meituan has established a strong artificial intelligence technology team to provide strong AI capability support for a complete service system such as merchant location selection, traffic diversion, takeout delivery, operation management, supply chain finance, and marketing promotion. However, with the rapid growth of users, the continuous upgrading of intelligent services, and the continuous increase in the scale and complexity of AI models, the company's business systems are facing increasingly severe performance challenges. How to resolve the challenges from the perspectives of infrastructure reconstruction and software optimization is problems it must face.
Take the application of the open source deep learning framework TensorFlow as an example: Meituan has made in-depth improvements from multiple dimensions based on Intel’s scalable processors and adopted the technical optimization plan recommended by the company. In order to further empower applications such as recommendation systems with AI, Meituan uses TensorFlow for model training and adopts distributed computing methods to solve the problem of model calculation and parameter update of massive parameters. However, with the rapid development of business, not only the scale and complexity of recommendation system models have also increased. A series of problems will also be exposed. The emergence of performance bottlenecks will cause the total cost of ownership to soar, which may have a negative impact on upper-level businesses.
In order to solve the performance bottleneck problem, there are two paths to choose from: one is to rapidly expand the scale of infrastructure construction, but it will increase cost pressure and increase the overall complexity of the system; the other is to start from the system and software Optimize at different levels to achieve higher economy and feasibility. After analyzing and positioning the TensorFlow framework and business, Meituan found that the load balancing of the TensorFlow cluster and the communication mechanism, latency, and single-instance performance of the distributed cluster in the business are all areas that urgently need to be optimized. Meituan is working with Intel to explore the second The path is imperative. After clarifying the direction, Meituan built the TensorFlow system on a server cluster based on Intel Scalable Processors, and used the CPU for TensorFlow model training. It also used the TensorFlow PS asynchronous training mode in the recommendation system scenario to support business distributed training needs. .
It is understood that Meituan has carried out comprehensive practices from multiple aspects such as single instance performance and distributed computing optimization. In terms of support capabilities, the new system can achieve hundreds of billions of parameter models, near-linear acceleration of distributed training of thousands of workers, complete training of a full year of samples within one day, and support online deep learning capabilities; various architectures and interfaces have also been updated. Friendly and recognized by Meituan’s business department.
The above is the detailed content of Solve the artificial intelligence bottleneck and promote the development of the food delivery industry. For more information, please follow other related articles on the PHP Chinese website!