From December 14 to 15, 2023, the highly anticipated "2023 Chongli Snow Ruyi Public Security Summit Forum - AI Empowerment of Public Security Practical Combat Exploration" was successfully held at the National Ski Jumping Center (Snow Ruyi) in Chongli District, Zhangjiakou City. The forum focused on exploring the application and empowerment effect of large models in the field of public security, providing a high-end exchange platform to promote technological innovation and progress in the field of public security. During the forum, more than 300 public security industry experts from 31 provinces (cities, autonomous regions) and more than 50 leading enterprises in the field of artificial intelligence, such as Shuguang, iFLYTEK, Rayan, YITU, and Hizhi, participated in this grand event. Xu Yan, Vice President of R&D at YITU TECH., attended the meeting and delivered a keynote speech, sharing YITU's progress and achievements in the field of large models.

Starting in 2022, large models represented by ChatGPT have opened a new era of artificial intelligence, providing strong technical support for the comprehensive application and further development of artificial intelligence in the field of urban public security. At this annual technology summit forum of the public security industry, YITU brought a deep understanding of "new security, true intelligence" and years of industry practical experience, showing the strong strength of YITU's "QuestMind" LVLM to the experts and industry partners on the scene.

In the past ten years, video intelligence has developed rapidly from perception to cognition from L1 to L5. Starting in 2023, multi-modal large models have brought a qualitative leap in the development of video intelligence, truly entering the L5 stage of video situational understanding. From the early "seeing" to "seeing clearly," to today's "understanding" under the empowerment of large models, the technological evolution has evolved from the early image structuralized tags to today's semantic understanding of videos; from the traditional numerous discriminative task models to vision-based multi-modal large models; from the AI computing power of end-side cameras to the AI computing power of cloud-side centralized servers; from the recognition of people and vehicles to the recognition of long-tail objects; from tag-based screening interaction to semantic-based multi-modal human-computer interaction. Large models have truly brought public security video intelligence into the "new security" era of "true intelligence."

YITU TECH. has been focusing on using advanced artificial intelligence technology to empower urban public safety for many years. As early as 2019, it began to research and develop large models based on Transformers and combined image perception, video perception with large models, taking the lead in practice in the field of urban public security, and promoting the transformation of key technologies into real combat effectiveness and productivity.

The"QuestMind" LVLM of YITU, which can converse, think, and evolve, supports massive video semantic searches, supports text-based video searches, and has the ability to search at the level of hundreds of millions of seconds on a single machine. It can quickly and accurately lock the target based on features; relying on YITU's full-stack artificial intelligence capabilities, it can achieve one-stop model training, development, and release, zero-sample cold start, and on-site algorithm iteration, continuously upgrading in actual combat, getting better and better, greatly shortening the model modeling and development cycle, and maximizing video value with the smallest model cost; at the same time, commonly used algorithms for key area scenarios can be built-in to achieve out-of-the-box use; AI Agent can make machines understand human needs and automatically generate the required algorithms based on simple instructions, truly making everyone an algorithm engineer.

At present, YITU's "QuestMind" LVLM has been deployed in dozens of projects nationwide and is the first truly combat-proven and commercially available multi-modal large model in the industry.

The application of artificial intelligence in the field of urban public safety is not just a matter of application, but essentially a system project driven by artificial intelligence, integrating big data and cloud computing. YITU has been deeply involved in urban security for more than ten years, focusing on the deep integration of technology and application. Today, with the empowerment of large models, companies with independent core technologies that can solve practical problems for customers and improve productivity exponentially, "true intelligence" enterprises, will become the real mainstay in the tide of the "new security" era.

You can copy the link to share to others: https://www.yitutech.com/node/909