Technology peripherals
AI
Solve the artificial intelligence bottleneck and promote the development of the food delivery industry
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.
The power of technology changes the takeout ecology
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.
Providing solutions to problems
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!
Hot AI Tools
Undresser.AI Undress
AI-powered app for creating realistic nude photos
AI Clothes Remover
Online AI tool for removing clothes from photos.
Undress AI Tool
Undress images for free
Clothoff.io
AI clothes remover
Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!
Hot Article
Hot Tools
Notepad++7.3.1
Easy-to-use and free code editor
SublimeText3 Chinese version
Chinese version, very easy to use
Zend Studio 13.0.1
Powerful PHP integrated development environment
Dreamweaver CS6
Visual web development tools
SublimeText3 Mac version
God-level code editing software (SublimeText3)
Hot Topics
1386
52
Bytedance Cutting launches SVIP super membership: 499 yuan for continuous annual subscription, providing a variety of AI functions
Jun 28, 2024 am 03:51 AM
This site reported on June 27 that Jianying is a video editing software developed by FaceMeng Technology, a subsidiary of ByteDance. It relies on the Douyin platform and basically produces short video content for users of the platform. It is compatible with iOS, Android, and Windows. , MacOS and other operating systems. Jianying officially announced the upgrade of its membership system and launched a new SVIP, which includes a variety of AI black technologies, such as intelligent translation, intelligent highlighting, intelligent packaging, digital human synthesis, etc. In terms of price, the monthly fee for clipping SVIP is 79 yuan, the annual fee is 599 yuan (note on this site: equivalent to 49.9 yuan per month), the continuous monthly subscription is 59 yuan per month, and the continuous annual subscription is 499 yuan per year (equivalent to 41.6 yuan per month) . In addition, the cut official also stated that in order to improve the user experience, those who have subscribed to the original VIP
Context-augmented AI coding assistant using Rag and Sem-Rag
Jun 10, 2024 am 11:08 AM
Improve developer productivity, efficiency, and accuracy by incorporating retrieval-enhanced generation and semantic memory into AI coding assistants. Translated from EnhancingAICodingAssistantswithContextUsingRAGandSEM-RAG, author JanakiramMSV. While basic AI programming assistants are naturally helpful, they often fail to provide the most relevant and correct code suggestions because they rely on a general understanding of the software language and the most common patterns of writing software. The code generated by these coding assistants is suitable for solving the problems they are responsible for solving, but often does not conform to the coding standards, conventions and styles of the individual teams. This often results in suggestions that need to be modified or refined in order for the code to be accepted into the application
Can fine-tuning really allow LLM to learn new things: introducing new knowledge may make the model produce more hallucinations
Jun 11, 2024 pm 03:57 PM
Large Language Models (LLMs) are trained on huge text databases, where they acquire large amounts of real-world knowledge. This knowledge is embedded into their parameters and can then be used when needed. The knowledge of these models is "reified" at the end of training. At the end of pre-training, the model actually stops learning. Align or fine-tune the model to learn how to leverage this knowledge and respond more naturally to user questions. But sometimes model knowledge is not enough, and although the model can access external content through RAG, it is considered beneficial to adapt the model to new domains through fine-tuning. This fine-tuning is performed using input from human annotators or other LLM creations, where the model encounters additional real-world knowledge and integrates it
Seven Cool GenAI & LLM Technical Interview Questions
Jun 07, 2024 am 10:06 AM
To learn more about AIGC, please visit: 51CTOAI.x Community https://www.51cto.com/aigc/Translator|Jingyan Reviewer|Chonglou is different from the traditional question bank that can be seen everywhere on the Internet. These questions It requires thinking outside the box. Large Language Models (LLMs) are increasingly important in the fields of data science, generative artificial intelligence (GenAI), and artificial intelligence. These complex algorithms enhance human skills and drive efficiency and innovation in many industries, becoming the key for companies to remain competitive. LLM has a wide range of applications. It can be used in fields such as natural language processing, text generation, speech recognition and recommendation systems. By learning from large amounts of data, LLM is able to generate text
Five schools of machine learning you don't know about
Jun 05, 2024 pm 08:51 PM
Machine learning is an important branch of artificial intelligence that gives computers the ability to learn from data and improve their capabilities without being explicitly programmed. Machine learning has a wide range of applications in various fields, from image recognition and natural language processing to recommendation systems and fraud detection, and it is changing the way we live. There are many different methods and theories in the field of machine learning, among which the five most influential methods are called the "Five Schools of Machine Learning". The five major schools are the symbolic school, the connectionist school, the evolutionary school, the Bayesian school and the analogy school. 1. Symbolism, also known as symbolism, emphasizes the use of symbols for logical reasoning and expression of knowledge. This school of thought believes that learning is a process of reverse deduction, through existing
To provide a new scientific and complex question answering benchmark and evaluation system for large models, UNSW, Argonne, University of Chicago and other institutions jointly launched the SciQAG framework
Jul 25, 2024 am 06:42 AM
Editor |ScienceAI Question Answering (QA) data set plays a vital role in promoting natural language processing (NLP) research. High-quality QA data sets can not only be used to fine-tune models, but also effectively evaluate the capabilities of large language models (LLM), especially the ability to understand and reason about scientific knowledge. Although there are currently many scientific QA data sets covering medicine, chemistry, biology and other fields, these data sets still have some shortcomings. First, the data form is relatively simple, most of which are multiple-choice questions. They are easy to evaluate, but limit the model's answer selection range and cannot fully test the model's ability to answer scientific questions. In contrast, open-ended Q&A
AlphaFold 3 is launched, comprehensively predicting the interactions and structures of proteins and all living molecules, with far greater accuracy than ever before
Jul 16, 2024 am 12:08 AM
Editor | Radish Skin Since the release of the powerful AlphaFold2 in 2021, scientists have been using protein structure prediction models to map various protein structures within cells, discover drugs, and draw a "cosmic map" of every known protein interaction. . Just now, Google DeepMind released the AlphaFold3 model, which can perform joint structure predictions for complexes including proteins, nucleic acids, small molecules, ions and modified residues. The accuracy of AlphaFold3 has been significantly improved compared to many dedicated tools in the past (protein-ligand interaction, protein-nucleic acid interaction, antibody-antigen prediction). This shows that within a single unified deep learning framework, it is possible to achieve
SOTA performance, Xiamen multi-modal protein-ligand affinity prediction AI method, combines molecular surface information for the first time
Jul 17, 2024 pm 06:37 PM
Editor | KX In the field of drug research and development, accurately and effectively predicting the binding affinity of proteins and ligands is crucial for drug screening and optimization. However, current studies do not take into account the important role of molecular surface information in protein-ligand interactions. Based on this, researchers from Xiamen University proposed a novel multi-modal feature extraction (MFE) framework, which for the first time combines information on protein surface, 3D structure and sequence, and uses a cross-attention mechanism to compare different modalities. feature alignment. Experimental results demonstrate that this method achieves state-of-the-art performance in predicting protein-ligand binding affinities. Furthermore, ablation studies demonstrate the effectiveness and necessity of protein surface information and multimodal feature alignment within this framework. Related research begins with "S
