From the initial camera survey to the subsequent application of the claims system, and now to the mobile survey, the insurance company spent 10 years and only realized the electronicization of accident photos and claims data. But this year, big changes happened.
Four companies, Ant Financial, Ping An of China, PICC and PICC, have entered the field of loss assessment from different angles with the help of technology.
Among them, Ant Financial and Ping An of China focus on the efficiency of loss assessment, and the newly launched intelligent loss assessment tool aims to greatly improve the efficiency of simple claim settlement. When the efficiency of damage assessment in simple cases reaches the second level, there will really be no need to wait for simple car repairs in the future.
The People's Insurance Company of China has developed and purchased a variety of accident vehicle detection tools. If you want to know the damage of the vehicle without disassembly and inspection, the focus is on the quality of claims settlement. China Baoxin relies on the industry's most complete database to focus on anti-fraud, and the probability of insurance fraud is expected to be reduced.
Now, this intelligent loss determination competition has begun. Who will have the last laugh?
The battle between loss-defining treasure and AI intelligent flash compensation
Ant Financial is the first giant to announce this year that it will empower artificial intelligence to determine losses. The company’s launch of Dingshengbao in June gave it another identity - a technology provider for the insurance industry.
Jianjie News learned that Dingshengbao uses artificial intelligence to simulate the manual work process in the auto insurance loss assessment process to help insurance companies realize automatic loss assessment for simple cases. Behind the scenes is the application of image recognition technology in the insurance field. AI is used as the eyes and brain of the loss assessor, using algorithms to identify accident photos and determine damaged parts and the extent of the loss. Then, by connecting with the repair price library of the cooperative insurance company, damaged parts, repair plans and repair prices can be given within a few seconds.
This is the first time that image loss assessment technology has been commercialized in the field of auto insurance. However, this loss-assessment tool, which claims to "revolutionize the lives of 100,000 claims settlement people," has been questioned by many in the claims field since its launch.
The first point of doubt lies in the massive amount of historical image data. To achieve the effect of image recognition and damage assessment, machine learning is required from massive historical car insurance accident photos. "70% of the premium income of the auto insurance industry is in the hands of the three major property and casualty insurance giants PICC, Ping An and China Pacific Insurance, which means that about 70% of insurance claims data is in the hands of these large companies," said Wei Ran, founder of A6 Studio, a senior claims adjuster. He said that these are the core data of insurance companies. These three companies are capable of data analysis, and it is unlikely that they will be shared with Ant Financial. In fact, PICC, Ping An and China Pacific Insurance are all promoting artificial intelligence.
An insider from Ant Financial’s insurance business group told Jiemian News that a large number of historical auto insurance photos are indeed needed to train the machine. Dingshangbao’s machine learning partners are large and medium-sized insurance companies such as Continental Property Insurance and Taiping Property and Casualty Insurance. , there is enough historical data for machine learning. This person further added, "Different insurance companies have different car models and photo shooting specifications. Some companies take more flat shots, some take more overhead shots, some emphasize detail shooting, and some like to make annotations. We use various Photos from various insurance companies are 'fed' to machine learning, so that Dingshengbao can cover all car models and adapt to photos taken in different weather and different shooting methods."
Another issue that has been questioned more is the localization of accessories prices. The most important part of determining the damage is to determine the repair price, which involves the price of accessories, auxiliary materials and labor hours in various regions across the country. As an Internet financial company, Ant Financial obviously does not have access to this data. In this regard, the above-mentioned insider of Ant Financial’s insurance business group said, “In essence, Dingshengbao does not involve this part. Dingshengbao only does the picture recognition and loss determination in the previous stage, and the system will automatically submit the results to the insurance company. Pricing The power is still in the hands of the insurance companies, and each insurance company determines the price based on its own price database and outputs the maintenance plan."
In addition to technical doubts, the industry is most worried about moral hazard issues. Some senior claims adjusters interviewed by Jiemian News generally said that they have not seen the anti-fraud function of Dingshengbao and are worried that insurance fraudsters will use this loophole to bring risks to insurance companies' risk control.
According to Jiemian News reporter, after discussions with cooperative insurance companies, Dingshangbao has some anti-fraud designs on the logical relationship between accessories and the authenticity of accidents, which are used to judge the authenticity of accidents and provide early warning. Some cases that do not comply with the logic of accessories loss. However, the above-mentioned people from Ant Financial’s insurance business group also admitted that currently only some simple anti-fraud measures can be done. “We will continue to deepen in this direction in the future. This is a process of continuous optimization,” he said.
The days when Ant Financial monopolized the field of intelligent loss determination amid skepticism did not last long. Last month, Ping An of China announced the launch of its own smart loss assessment product - AI Smart Flash Compensation, which is the first smart loss assessment tool launched by an insurance institution.
Similar to Dingshengbao, AI smart flash compensation also uses image recognition technology and machine learning to train on massive historical real claim image data to achieve image recognition and loss determination. Jiemian News learned that "it has a large amount of historical car damage picture data" is the main advantage of this part. Ping An of China has a property and casualty insurance market share of 19.83, which means it has about 20% of the industry’s vehicle damage data. Ping An of China publicly stated that AI intelligent flash compensation is currently the only artificial intelligence loss assessment and risk control product that has been put into use in real production environments.
However, after careful comparison, Jiemian News found that the biggest difference between Dingshengbao and AI smart flash compensation lies in the automatic pricing process. The pricing work of Dingshengbao is sent back to the insurance company, while the AI ??smart flash compensation is based on Ping An Property & Casualty Insurance and has built a nationwide labor-hour accessory pricing system that is accurate to counties and cities, and does its own pricing. Because of this, AI Smart Flash Compensation is the first intelligent tool that integrates loss determination and pricing.
In addition, AI smart flash compensation has not been questioned by "moral hazard". The reason is that when the AI ????Smart Flash Claims was released, it was disclosed that it has built a full risk factor library from underwriting to claims settlement, covering the main "individual case" and "group" risks in the entire claim settlement process, and achieving intelligent interception and post-event intelligent screening of risks. check.
The person in charge of the R&D Center of Kaitaiming Technology, a third-party risk control company that cooperates with Ping An on this technology, told Jiemian News that they hired experienced car repairmen to write down their vehicle maintenance experiences one by one. Every day's accident experience becomes a new rule written down. "Human experience is written and compiled into computer logic rules. These logic rules become interception rules when placed in the system. There are currently more than 40,000 rules."
"These rules are like spiders weaving Network, normal cases will slip through the grid, and problem cases will be intercepted if a certain rule is triggered, and the claims adjuster needs to take them out for a closer look. "The person in charge said that this set of rules is very important to the professionalism of the auto repair shop. Insurance fraud interception is the most effective because they conduct insurance fraud based on vehicle maintenance logic and body structure logic.
These intelligent loss assessment tools cost both parties a lot of manpower and material resources. Ping An of China disclosed that it has invested nearly 1 billion US dollars in innovation in the field of financial technology every year in the past five years. Industry insiders estimate that Ant Financial’s investment should also be at the level of 100 million yuan.
Interestingly, both Ant Financial and Ping An of China provide their loss assessment products for free to insurance industry partners. Ant Financial stated that it is currently not considering charging for the project, while Ping An of China has given its partner institutions a three-month free period. The industry expects that it may move to a charging model in the future, and technology output will become a new profit point for Ping An of China.
But there is no free lunch in the world. The purpose of these two free loss assessment products is to run data. "As far as I know, the loss assessment product solutions of Ant Financial and Ping An of China have the same logic," Wei Ran told Jiemian News. The two companies gave their tools to other insurance companies for free in order to run more insurance data. , so that the results of tool loss determination become more and more accurate.
In an interview with Jiemian News, we learned that between Ant Financial and Ping An, insurance companies are more willing to cooperate with Ant Financial. At present, dozens of insurance companies have expressed their intention to cooperate, and Ant Financial is arranging successive connections. Ping An of China previously announced that more than 10 insurance companies have signed letters of intent to cooperate in AI intelligent flash claims.
A person in charge of the auto insurance business of a small insurance company explained to Jiemian News, "After all, Ping An is a competitor of the insurance company, and there will be some concerns when handing over the company's core claims data to competitors. Ant Financial is positioned as a technology company, and insurance is only a part of its entire ecosystem. It is more of a service to insurance companies, which will make insurance companies feel more at ease."
Another advantage of Ant Financial is that it has a large amount of "human data", which is what insurance companies lack. For example, Ant Financial’s “auto insurance score” launched in May can provide accurate portraits and risk analysis of car owners. It is understood that within 100 days of its launch, there have been 18 cooperative insurance companies for auto insurance coverage, with an average daily call frequency of 1 million. Auto insurance points are mainly used in the auto insurance pricing process. AXA Tianping, one of the first companies to introduce auto insurance points, revealed that after the introduction of auto insurance points, 65% of user risk identification results have changed.
Since the two companies’ loss-assessment products were launched, there have been constant discussions about the PK between the two companies. Yin Ming, president of Ant Financial's insurance business group, told Jiemian News: "Ant is a platform and will not compete with insurance companies. On the contrary, we welcome insurance companies to join the field of insurance technology."
In Yin Ming’s view, the ultimate winner of insurance technology is not any one institution, but the entire industry and insurance consumers.
It is not a competition of competition
Unlike Ant Financial and Ping An of China, which entered the field of loss assessment from intelligent software, PICC is deeply involved in loss assessment hardware.
This leading property and casualty insurance company launched 6 technological claims tools in September, two of which are customized products for PICC Property and Casualty Insurance Company, one jointly developed by PICC Property and Casualty Insurance Company and manufacturers, and one for PICC Property and Casualty Insurance Company. The property and casualty insurance claims expert invented and holds a national invention and innovation patent, as well as two PICC property and casualty insurance procurement products.
The most important of these is the engine connecting rod-free measurement tool. This tool has changed the way that the engine of a wading vehicle must be disassembled to determine the loss history. It was independently developed by the PICC Auto Insurance Claims Department and has National utility model invention patent. Owners whose cars have been flooded can use this disassembly-free measurement tool to avoid engine disassembly during vehicle maintenance, and accurately detect whether the engine connecting rod is damaged within half an hour to five hours, thus reducing the need for This eliminates the waiting time for repairs and maintains the engine's original condition.
Xiao Shenfei, the claims department of PICC Property and Casualty Insurance Company, the developer of this tool, told Jiemian News that a car involved in a water-related accident involving an engine loss is a relatively complex case. The traditional detection method requires dismantling the engine, which wastes a lot of manpower and material resources. It consumes a lot of damage assessment time. "What's more important is that in the past, the right to dismantle and inspect was in the hands of the maintenance party. Neither the insurance company nor the car owner could stop it from wantonly dismantling for their own benefit. With this tool, car owners and insurance companies have a Initiative. ”
In addition, PICC Property and Casualty Insurance has also customized two exclusive devices-the electronic control system diagnostic instrument and the cloud diagnostic equipment. The electronic control system diagnostic instrument is used for daily damage assessment of the electronic control system. Through the on-board diagnostic port, it can quickly determine the fault scope, determine the fault type, and analyze the cause of the fault. Cloud diagnostic equipment is mainly aimed at high-end vehicles, compatible with original factory diagnosis of many imported and joint venture high-end brand models, and can achieve remote control and detection. For example, if the car engine is missing a cylinder or the lights are not bright, you can plug these two devices into the on-board diagnostic port and scan them, and the results will be available in a few minutes. Especially for high-end vehicles, there is no need to wait in line at the auto repair shop for inspection.
“These tools independently developed and purchased by PICC Property & Casualty Insurance have broken through the technical barriers of the auto repair industry chain, and have also innovatively mastered the 'disassembly and inspection-free' technology, which can quickly handle large and complex cases in the future, especially For high-end car cases, this may form PICC’s core advantage in loss determination and claims,” said an industry insider.
A person from the PICC Property and Casualty Insurance Claims Division told Jiemian News that although loss determination is complicated, there are still rules to be found. This series of tools is to standardize the behavior of loss determination. In the past, manual loss assessment mainly relied on the experience of each loss assessor, which was difficult to integrate. "Now through image damage assessment and intelligent loss assessment, information can be collected and organized, and can be analyzed and managed in the background. This is the biggest role."
“Through data analysis, we understand the parts of each type of vehicle that are prone to accidents, and we also find the parts that require cost control. This is not aimed at customers, but to affect the parts of the accident, and even coordinate with the maintenance industry. . The insurance company’s backend has more precise cost control over a certain type of accident and a certain type of vehicle, which is the biggest cost management,” he added.
Compared with the three business giants Ant Financial, Ping An and PICC, China Insurance Information Technology Management Co., Ltd. (hereinafter referred to as China Insurance) is more like an industry platform.
China Insurance, established in early 2014 with the approval of the State Council, is known as the "UnionPay" of the insurance industry. It was established with funding from the China Insurance Guarantee Fund to strengthen the public infrastructure construction of the insurance industry and comprehensively improve the insurance industry. It is born based on the informatization level of operation and management.
Auto insurance data was the first data that China Insurance Company integrated. Because of this, China Insurance Company has the most comprehensive claims data in the industry. Relying on its data advantages, China Baoxin launched the “Loss Assessment Cloud”.
The damage assessment cloud includes accident vehicle damage assessment systems, anti-fraud systems, statistical analysis systems and other application systems. After the insurance company cooperates with China Baoxin to use the loss assessment cloud, it can query data such as vehicle modelling, accessory selection, and damage assessment pricing. Different from the strong functionality of the loss assessment products of other commercial giants, the loss assessment cloud is positioned as an auxiliary operating platform and ecological platform for auto insurance claims settlement.
In an interview with Jiemian News, we learned that the industry generally regards the loss determination cloud as a supplementary tool for the loss determination process, and attaches great importance to its application in anti-fraud. In the past, insurance data usage standards and data formats were inconsistent across regions. After the establishment of China Insurance, it broke down the data barriers between regions and insurance companies, standardized the collection of 54 anti-fraud data elements, and unified data standards.
Based on the use of auto insurance platform data, China Insurance has developed an auto insurance anti-fraud information system and built its own risk database to realize insurance fraud clue identification, fraud risk early warning, fraud information sharing and other functions. It provides information and data support for companies to combat insurance fraud, especially cross-company fraud cases that are difficult for a single insurance company to detect.
Like Ant Financial and Ping An of China, China Baoxin, as an industry platform, is also open to companies in all industries. Previously, Dingsheng Cloud had launched the first batch of data testing work for 10 insurance companies. The person in charge of the auto insurance business of the above-mentioned small insurance company believes that as an industry platform with the strongest data, China Insurance will attract more insurance companies.
The entry of four giants will benefit the entire insurance industry. The experiment of image recognition in the field of auto insurance has begun, and its application in other insurance types in the future is also worth looking forward to. For insurance consumers, no matter which service they enjoy, it can improve their claims settlement experience.
In the view of Zhong Cheng, President of Anxin Insurance, several companies have their own advantages. Ping An's AI smart flash claims connect image recognition and back-end databases relatively well, solving the uncertainty and standardization issues in the loss determination process. This reduces a lot of online and offline claims settlement work and improves a lot of efficiency. At the same time, the intelligent interception function of AI intelligent flash compensation will intercept problematic cases. At this time, China Insurance Industry Data System will be used to query the vehicle's historical accident data, and at the same time, supplemented by the car owner's credit score, a more reasonable judgment can be made. “The most important thing is that insurance companies must actually use these tools to see their role in risk identification and processes.”
“Insurance companies should all use it. We plan to cooperate with Ant Financial, Ping An of China and China Baoxin,” Zhong Cheng said.
Extended reading: How to buy insurance, which one is better, and step-by-step instructions to avoid these "pitfalls" of insurance