In response to the contradiction between the explosive data volume, application requirements and technical matching, Qihui Intelligent applied a new generation of time series database CnosDB to improve storage throughput and reduce storage costs.
Qihui Intelligent Application CnosDB creates a new generation of AI security platform
School is the "ivory tower" in people's minds, and it is also the safest and most secure place in everyone's mind. However, in recent years, campus safety incidents have occurred frequently in my country, with injuries such as fighting, molestation, and death occurring frequently, which have seriously affected students' physical and mental health and life safety. At the same time, issues such as insufficient campus security facilities and poor management have once again attracted people's attention.
In fact, my country's campus security is still in its infancy. The security facilities of many types of schools, such as junior high schools, technical schools, and universities, are not perfect. Some even some third- and fourth-tier urban schools do not have security systems at all. The installation of security systems on campus is a mandatory policy requirement of the Ministry of Education. Therefore, in the face of large-scale market demand, more and more investors are paying attention to this market, especially the use of artificial intelligence technology to promote the construction of safe campuses, which is an area of emphasis promoted by the country.
Qihui Intelligence, founded in 2016, is an AI security solution provider. Taking AI voice security as the entry point, the company has successfully created AIoT equipment for campus security, and at the same time, through a comprehensive set of digital operations that complement it System solutions provide digital empowerment for campus security to support its efficient operation and management. The company team is composed of people with many years of industry experience. At the same time, the team is also the team that provides the first batch of police voiceprint collection terminals and the first batch of AI voice alarm solutions on sale.
Qihui Intelligent Digital Operation System Solution
Business and application requirements
Currently, traditional campus security players in the market still focus on AI video surveillance. However, according to relevant industry data, more than 50% of campus violence incidents occur in private places such as dormitories and bathrooms. Since surveillance cameras cannot be installed in private places such as restrooms and dormitories, it is impossible to monitor what is happening inside in real time or collect evidence afterwards, making school violence difficult to prevent and treat.
At the same time, in recent years, as the AI capabilities of IoT devices have become stronger and stronger, such as speech recognition, image recognition, etc., we are also facing more serious security challenges as we move from the IoT era to the AIoT era. Because AIoT devices generally have networking capabilities, there is the possibility of network attacks and information theft by the network. Secondly, AIoT devices generally have sensors such as cameras and microphones. These sensors can obtain sensitive information around them. If this sensitive information is obtained through the network or SD card, emmc, etc., the security risk is high. Finally, there is the stability challenge of AIoT equipment. If an abnormality occurs during system operation, it will cause great losses.
Faced with the difficulty of surveillance cameras reaching monitoring blind spots and the industry's increasingly stringent requirements for data security, smart voice alarms that use AI voice recognition technology and have high data security are the industry's solutions. Qihui Intelligent's AIOT product "Yinzhi Sentry" faced the coexistence of three major challenges: outdoor & strong reverberation, long-distance sound pickup and ultra-short wake-up words, and handed over its own set of products that are extremely difficult to market. Product answers that combine algorithms, autonomous and controllable hardware supply chain and network architecture, and high data security.
Yinzhiyingwei
Challenges under traditional IT architecture
In order to make the system's massive data calculations more accurate and for the large-scale application of AI in the industry in the future, most companies hope to save longer-term historical data. However, in current industry applications, users are often unable to save data for more than 5 years due to the storage costs and memory access costs of ordinary disk arrays. At the same time, the database compression ratio is not high and the storage cost is high; and as time goes by, its cost will continue to rise. It is difficult for users to save long-term data, and a large amount of valid device data is overwritten and lost.
Taking Qihui Intelligence as an example, the "YinZhi Sentinel" and "YinZhi Shadow Guard" series products are in urgent need of improvements in database capabilities. Specifically, the "Intelligence Sentry" product and system platform does not require too much storage space at the customer application level, but due to its AIOT architecture and security alarm scenario requirements, the front-end equipment must have strong functional stability. This is the biggest challenge faced by Qihui Intelligence and even more AI security companies in the industry. Therefore, Qihui Intelligent's backend has a set of sophisticated real-time monitoring data feedback programs for equipment hardware stability. For example, the device reports heartbeat data, CPU temperature, disk usage, memory usage, etc. every five minutes. With the rapid development of Qihui Intelligent's business and the increase in equipment deployment points, that is, the rapid increase in the number of its digital intelligent operation system equipment on the cloud, Qihui Intelligent urgently needs a database with stronger data throughput capacity to replace its original IoT platform users Only PostgreSQL or MySQL databases can be selected.
According to Qihui Intelligence, taking every 100 regional platforms and 1,000 devices per platform as an example, each device needs to be connected to 6 smart sensors and collect data every 5 seconds on average. About 120,000 writes, that is, 100,000-level QPS. At the same time, with the rapid growth of the number of devices, the pressure of data writing will continue to increase in the future. Therefore, in the future data scale, traditional relational databases represented by MySQL and Oracle cannot complete the rapid and continuous storage of massive time series data due to storage structure limitations at the database design level. Secondly, Qihui Intelligence also needs to store monitoring data for a long time as a reference for system optimization and analysis to ensure that the system can be used stably in various scenarios, regions and different levels. Then the storage cost of the past database is too high to retain longer-term historical data more economically, which is an unknown degree of loss for system optimization work.
In addition, the illegal leakage, alteration or destruction of data is absolutely unacceptable to Qihui Intelligent. Therefore, the security of the database system is also an issue that Qihui Intelligent Platform continues to invest in solving.
Connect CnosDB to solve the problem
For a new generation of AI security manufacturers such as Qihui Intelligence that deploy AI computing power terminals at massive locations, with the growth of markets and scenarios, the amount of data begins to grow rapidly, and their requirements for data storage are also getting higher and higher. . In response to the contradiction between the explosive data volume, application requirements and technical matching, Qihui Intelligent applied a new generation of time series database CnosDB to improve storage throughput and reduce storage costs.
CnosDB is a time series database that is very suitable for Internet of Things scenarios. It has strong write throughput and efficient compression ratio. Compared with traditional relational databases, it can support larger-scale measurement points, and can support writing requirements of millions of QPS on ordinary servers. At the same time, through the new architecture design, CnosDB has excellent performance in data compression, which can reduce storage costs to the greatest extent, making it possible to retain longer-term data. According to Qihui Intelligence’s experience, its platform storage costs dropped by two-thirds after using CnosDB.
As far as security is concerned, CnosDB has taken various measures to ensure the security and confidentiality of data. First, it supports high encryption levels of authentication and access control. Secondly, CnosDB provides data encryption function, which can encrypt and store data to prevent unauthorized access. In addition, CnosDB also has data backup and recovery functions, which can restore data when data is lost or damaged. CnosDB has multi-level protection measures in terms of security, which can effectively help Qihui Intelligence protect data security.
New platform architecture
future
Through Qihui Intelligent's AIoT platform, the combination of technology and security software and hardware is realized to achieve an AI security management and control solution of pre-event prevention, mid-event early warning, and post-event tracing. This not only saves time and effort, but also solves the problem that traditional security can only collect evidence after the fact. And the pain point is that it is difficult to obtain evidence.
Qihui Intelligence has always been at the forefront of industry exploration. By applying various cutting-edge new technologies, its AI security platform has entered the stage of digitalization, integration and intelligence. Helping users realize the automation level of their security monitoring, improving users' intelligent analysis capabilities, and lightweight operation and maintenance has always been Qihui Intelligence's never-ending pursuit. Through in-depth cooperation with CnosDB, we believe that in the future we will give the campus a pure land and give children a blue sky.
Article source: https://www.m.czlyykt.com/6426.html
Introduction to CnosDB
CnosDB is a high-performance, easy-to-use open source distributed time series database that has been officially released and is fully open source.
Welcome to follow our community website: https://cn.cnosdb.com