Automatic driving automobile insurance product design system and method

Abstract

The invention discloses an automatic driving automobile insurance product design system. The system comprises an insurance object identification module, a data collection and processing module and an automobile insurance factor determination module. The insurance buying object identification module is used for classifying insurance buying objects based on the vehicle type and the Internet of Vehicles data to obtain multiple types of insurance buying objects; the data collecting and processing module is used for acquiring basic data of the insured object and determining index data corresponding to the insured object based on the basic data; and the vehicle insurance factor determination module is used for constructing a combined prediction model and inputting the index data into the combined prediction model to obtain a vehicle insurance factor corresponding to the insured object. And accurate determination of the vehicle insurance quotation and the responsibility division of the automatic driving vehicle is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of vehicle insurance technology, and more specifically to a system and method for designing an insurance product for an autonomous driving vehicle. Background Art

[0002] At present, the existing auto insurance system is built based on the situation where traditional vehicles are insured vehicles. However, with the emergence and upgrading of autonomous driving systems, the control of the vehicle is gradually transferred from human drivers to the autonomous driving vehicle itself, and the accident responsibility is also transferred to related companies such as vehicle manufacturers and software suppliers.

[0003] General auto insurance quotes generally only consider static information such as the insurance period, basic driver information and vehicle configuration, but do not take into account influencing factors such as driving environment and driving behavior, as well as relevant characteristics of autonomous vehicles. They are unable to measure the impact of the software and hardware risks of the autonomous driving system itself on the risk of accidents, and are not applicable when the insured vehicle is an autonomous vehicle. Since the insured object is only simply distinguished based on the insurance period, number of seats, etc., there is a lack of factors directly related to the owner's driving habits and vehicle model, which are directly related to the frequency and amount of claims, which will lead to low accuracy and unfair settings in auto insurance quotes.

[0004] Traditional auto insurance is designed for traditional manual cars, not self-driving cars. The main responsible party is usually the driver, which is not suitable for self-driving cars and is only applicable to cars without self-driving functions or with only partial driving assistance functions. In other words, the premise of traditional auto insurance is that the driver controls the driving and operation of the car throughout or most of the time, and the main responsible party for traffic accidents is often the driver. Conditional, advanced or even fully self-driving vehicles obviously do not meet this requirement.

[0005] Therefore, how to accurately determine the insurance quote and liability division for autonomous vehicles is an issue that technical personnel in this field urgently need to solve. Summary of the invention

[0006] In view of this, the present invention provides a system and method for designing an insurance product for an autonomous driving vehicle, which at least solves some of the problems existing in the prior art and helps to accurately determine the insurance quotation and liability division of the autonomous driving vehicle.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] An autonomous driving automobile insurance product design system, comprising: an insured object identification module, a data collection and processing module, and an automobile insurance factor determination module;

[0009] The insured object identification module is used to classify the insured objects based on vehicle type and Internet of Vehicles data to obtain multiple categories of insured objects;

[0010] The data collection and processing module is used to obtain the basic data of the insured object and determine the indicator data corresponding to the insured object based on the basic data;

[0011] The vehicle insurance factor determination module is used to construct a combined prediction model and input the indicator data into the combined prediction model to obtain the vehicle insurance factor corresponding to the insured object.

[0012] Preferably, the insured object identification module includes: a data acquisition unit and an object identification unit;

[0013] The data acquisition unit is used to acquire the vehicle type and the Internet of Vehicles data of several months before the insurance is purchased;

[0014] The object identification unit is used to make a judgment based on the vehicle type and the Internet of Vehicles data. When the vehicle type is an ordinary vehicle, it is judged whether there is corresponding Internet of Vehicles data. If so, it is determined to be an experienced driver as the first object, otherwise it is determined to be a novice driver as the second object; when the vehicle type is an autonomous driving vehicle, it is judged whether there is corresponding Internet of Vehicles data. If so, it is determined to be an experienced autonomous driving vehicle as the third object, otherwise it is determined to be a new autonomous driving vehicle as the fourth object.

[0015] Preferably, the data collection and processing module includes: a data collection unit and an indicator data acquisition unit;

[0016] The data collection unit is used to obtain the basic data of the insured person: driver information, vehicle information, automatic driving system information, UBI variable information and vehicle-road collaboration information;

[0017] The indicator data acquisition unit is used to determine, based on the basic information, that the first object selects the corresponding driver information, the vehicle information and the vehicle-road collaborative information as the first data set; determines that the second object selects the corresponding driver information, the vehicle information, the UBI variable information and the vehicle-road collaborative information as the second data set; determines that the third object selects the corresponding vehicle information, the automatic driving system information, and the vehicle-road collaborative information as the third data set; determines that the fourth object selects the corresponding vehicle information, the automatic driving system information, the UBI variable information and the vehicle-road collaborative information as the fourth data set; and is also used to obtain first indicator data, second indicator data, third indicator data and fourth indicator data based on the first data set, the second data set, the third data set and the fourth data set.

[0018] Preferably, the vehicle insurance factor determination module includes: a prediction model building unit and a vehicle insurance factor prediction unit;

[0019] The prediction model building unit is used to build a combined prediction model;

[0020] The vehicle insurance factor prediction unit is used to input the first index data, the second index data, the third index data and the fourth index data into the combined prediction model respectively to obtain the vehicle insurance factors corresponding to the first object, the second object, the third object and the fourth object, and the vehicle insurance factors include: claim frequency and claim intensity.

[0021] Preferably, it also includes: a car insurance quotation module;

[0022] The car insurance quotation module is used to obtain the car insurance premium corresponding to the insured object based on the car insurance factor, and obtain the final car insurance quotation corresponding to the insured object based on the car insurance premium.

[0023] Preferably, it also includes: an association rule module;

[0024] The association rule module is used to collect and perform data analysis based on traffic accident reports, calculate the correlation between different traffic accidents, obtain association rules, and determine the exit scenario data of the autonomous driving vehicle based on the association rules.

[0025] Preferably, the association rule module comprises: a data processing unit, an association unit and an analysis unit;

[0026] The data processing unit is used to collect a plurality of traffic accident reports and process the traffic accident reports to obtain a traffic accident data set;

[0027] The association unit is used to calculate the association degree based on the traffic accident data set to obtain all frequent item sets, and generate the association rules based on all the frequent item sets;

[0028] The analysis unit is used to determine the exit scenario data of the autonomous driving vehicle based on the association rule.

[0029] Preferably, it also includes: a vehicle insurance liability division module;

[0030] The auto insurance liability division module is used to obtain a first weight coefficient for the disengagement scenario part based on the disengagement scenario data, obtain and obtain a second weight coefficient and a third weight coefficient corresponding to the automatic mode and the manual mode of the autonomous driving vehicle respectively based on the driving risk coefficient, determine the liability ratio between the car owner and the autonomous driving car manufacturer based on the first weight coefficient, the second weight coefficient and the third weight coefficient, and obtain the auto insurance payment amount of the car owner and the autonomous driving car manufacturer based on the liability ratio and the final auto insurance quotation.

[0031] Preferably, the vehicle insurance liability division module includes: a first coefficient determination unit, a risk coefficient determination unit, a second coefficient determination unit, a third coefficient determination unit, a liability division unit and a vehicle insurance division unit;

[0032] The first coefficient determination unit is used to calculate the premium weight coefficient of the disengagement part of the autonomous driving vehicle based on the disengagement scenario data as the first weight coefficient;

[0033] The risk coefficient determination unit is used to obtain the driving risk coefficient based on the number of accidents of different severity and the corresponding average compensation value per accident;

[0034] The second coefficient determination unit is configured to obtain, based on the driving risk coefficient, a premium weight coefficient of the autonomous driving vehicle in the autonomous driving mode as the second weight coefficient;

[0035] The third coefficient determination unit is configured to obtain, based on the driving risk coefficient, a premium weight coefficient of the automatic driving vehicle in the manual driving mode as the third weight coefficient;

[0036] The responsibility division unit is used to determine the responsibility ratio of the vehicle owner and the responsibility ratio of the autonomous driving vehicle manufacturer based on the first weight coefficient, the second weight coefficient and the third weight coefficient;

[0037] The car insurance division unit is used to obtain the car insurance payment amount of the car owner and the car insurance payment amount of the autonomous driving car manufacturer based on the final car insurance quotation, the car owner's liability ratio and the autonomous driving car manufacturer's liability ratio.

[0038] A method for designing an insurance product for an autonomous driving vehicle, comprising:

[0039] Classify the insured objects based on vehicle type and Internet of Vehicles data to obtain multiple categories of insured objects;

[0040] Acquire basic data of the insured person, and determine indicator data corresponding to the insured person based on the basic data;

[0041] A combined prediction model is constructed, and the indicator data is input into the combined prediction model to obtain the vehicle insurance factor corresponding to the insured object.

[0042] It can be seen from the above technical solution that, compared with the prior art, the present invention discloses a system and method for designing an insurance product for an autonomous driving vehicle. By taking into consideration influencing factors such as the driving environment and driving behavior as well as relevant characteristics of the autonomous driving vehicle, the insurance quotation for the autonomous driving vehicle can be determined more accurately. By formulating association rules, the disengagement scenario of the autonomous driving vehicle can be accurately determined, and the liability ratio of the car owner and the autonomous driving vehicle manufacturer can be obtained in combination with the driving risk coefficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0044] Figure 1 A schematic diagram of the structure of an autonomous driving automobile insurance product design system provided in Example 1 of the present invention.

[0045] Figure 2 A schematic diagram of the structure of an autonomous driving automobile insurance product design system provided in Example 2 of the present invention.

[0046] Figure 3 This is a flow chart of the object identification unit provided by the present invention.

[0047] Figure 4 A flow chart of a method for generating association rules by an association unit provided by the present invention.

[0048] Figure 5 A flow chart of a method for designing an insurance product for an autonomous driving vehicle provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Example 1

[0051] like Figure 1As shown, the embodiment of the present invention discloses an autonomous driving automobile insurance product design system, including: an insured object identification module, a data collection and processing module, and an automobile insurance factor determination module;

[0052] The insured object identification module is used to classify the insured objects according to the vehicle type and the Internet of Vehicles data to obtain multiple categories of insured objects;

[0053] The data collection and processing module is used to obtain the basic data of the insured person and determine the indicator data corresponding to the insured person based on the basic data;

[0054] The motor vehicle insurance factor determination module is used to construct a combined prediction model and input indicator data into the combined prediction model to obtain the motor vehicle insurance factor corresponding to the insured object.

[0055] Preferably, the final car insurance quotation is determined based on the car insurance factors corresponding to the insured object.

[0056] Example 2

[0057] like Figure 2 As shown, the embodiment of the present invention discloses an autonomous driving automobile insurance product design system, including: an insured object identification module, a data collection and processing module, and an automobile insurance factor determination module;

[0058] The insured object identification module is used to classify the insured objects according to the vehicle type and the Internet of Vehicles data to obtain multiple categories of insured objects.

[0059] Preferably, the insured object identification module includes: a data acquisition unit and an object identification unit;

[0060] A data acquisition unit, used to acquire vehicle type and Internet of Vehicles data for several months before insurance;

[0061] like Figure 3 As shown, the object discrimination unit is used to make judgments based on the vehicle type and the Internet of Vehicles data. When the vehicle type is an ordinary vehicle, it is judged whether there is Internet of Vehicles data for the three months before insurance. If so, the driver is determined to be an experienced driver as the first object, otherwise, the driver is determined to be a novice driver as the second object. When the vehicle type is an autonomous driving vehicle, it is judged whether the Internet of Vehicles data for the three months before insurance is available. If so, the driver is determined to be an experienced autonomous driving vehicle as the third object, otherwise, the driver is determined to be a new autonomous driving vehicle as the fourth object.

[0062] Preferably, the Internet of Vehicles data includes at least: mileage, driving behavior and driving environment.

[0063] Preferably, for an autonomous vehicle (AV) in autonomous driving mode, the autonomous driving system is regarded as the actual driver in this mode. Fatal errors, hacker intrusions or system failures in the driving process can be externalized as driving behavior patterns such as turning, braking and accelerating. These driving behavior patterns can be applied to both the driver and the autonomous driving system, and it is also possible to determine whether there is Internet of Vehicles data for several months before the insurance is taken out.

[0064] Preferably, this embodiment obtains Internet of Vehicles data for the three months before insurance.

[0065] The data collection and processing module is used to obtain the basic data of the insured object and determine the indicator data corresponding to the insured object based on the basic data.

[0066] Preferably, the data collection and processing module includes: a data collection unit and an indicator data acquisition unit;

[0067] Data collection unit, used to obtain basic data of the insured: driver information, vehicle information, autonomous driving system information, UBI variable information and vehicle-road collaboration information;

[0068] The indicator data acquisition unit is used to determine the first object to select the corresponding driver information, vehicle information and vehicle-road cooperative information as the first data set based on the basic information; determine the second object to select the corresponding driver information, vehicle information, UBI variable information and vehicle-road cooperative information as the second data set; determine the third object to select the corresponding vehicle information, automatic driving system information and vehicle-road cooperative information as the third data set; determine the fourth object to select the corresponding vehicle information, automatic driving system information, UBI variable information and vehicle-road cooperative information as the fourth data set; and is also used to obtain the first indicator data, the second indicator data, the third indicator data and the fourth indicator data based on the first data set, the second data set, the third data set and the fourth data set.

[0069] Preferably, the driver information is obtained based on the policyholder, and the driver information includes the nature of the driver; the autonomous driving system information and vehicle information are obtained based on the autonomous driving vehicle manufacturer and software supplier, and the autonomous driving system information includes: hardware conditions and software conditions, and the vehicle information includes: basic vehicle information and vehicle configuration; UBI variable information is obtained based on the Internet of Vehicles data acquisition terminal, and the UBI variable information includes: PAYD variables and PHYD variables; the vehicle-road collaboration information is obtained based on the vehicle-mounted equipment and road test unit, and the vehicle-road collaboration information includes: the degree of vehicle networking and the degree of road intelligence.

[0070] Preferably, starting from the five dimensions of driver information, vehicle information, automatic driving system information, UBI variable information and vehicle-road cooperative information, a rate factor system that considers both static and dynamic attributes is obtained by comprehensively using qualitative and quantitative analysis methods. Among them, driver information, vehicle information and automatic driving system information belong to static attributes, while UBI variable information and vehicle-road cooperative information belong to dynamic attributes.

[0071] Preferably, the third-level indicator data corresponding to each information in the first data set are collectively used as the first indicator data; the third-level indicator data corresponding to each information in the second data set are collectively used as the second indicator data; the third-level indicator data corresponding to each information in the third data set are collectively used as the third indicator data; the third-level indicator data corresponding to each information in the fourth data set are collectively used as the fourth indicator data.

[0072] Preferably, the driver information classification index and specific description are shown in Table 1:

[0073] Table 1 Driver information classification indicators and specific descriptions

[0074]

[0075] Preferably, the secondary classification indicators of vehicle information B are vehicle basic information B1 and vehicle configuration B2, which are further divided into three levels of classification indicators. The vehicle information classification indicators and their specific descriptions are shown in Table 2:

[0076] Table 2 Vehicle information classification indicators and specific descriptions

[0077]

[0078] Preferably, the classification indicators and specific descriptions of the information of the automobile automatic driving system are shown in Table 3:

[0079] Table 3 Classification indicators and specific descriptions of information on the vehicle's automatic driving system

[0080]

[0081]

[0082] Preferably, the UBI variable information classification indicators and specific descriptions are shown in Table 4:

[0083] Table 4 UBI variable information classification indicators and specific descriptions

[0084]

[0085]

[0086] Preferably, the vehicle-road cooperative information classification indicators and specific descriptions are shown in Table 5:

[0087] Table 5 Classification indicators and specific descriptions of vehicle-road collaboration

[0088]

[0089] The motor vehicle insurance factor determination module is used to construct a combined prediction model and input indicator data into the combined prediction model to obtain the motor vehicle insurance factor corresponding to the insured object.

[0090] Preferably, the vehicle insurance factor determination module includes: a prediction model building unit and a vehicle insurance factor prediction unit;

[0091] A prediction model building unit, used for building a combined prediction model;

[0092] The vehicle insurance factor prediction unit is used to input the first indicator data, the second indicator data, the third indicator data and the fourth indicator data into the combined prediction model respectively to obtain the vehicle insurance factors corresponding to the first object, the second object, the third object and the fourth object. The vehicle insurance factors include: claim frequency and claim intensity.

[0093] Preferably, the first indicator data, the second indicator data, the third indicator data and the fourth indicator data are preprocessed before being input into the model: missing value processing, outlier processing and converting categorical data into processable numerical data. In particular, for disordered features, one-hot encoding is used to binarize and eliminate the data.

[0094] Preferably, in this embodiment, the combined prediction model adopts the XGBoost+LR combined model, the corresponding indicator data is input into the XGBoost model for training, the tree learned by the XGBoost model is used to construct new features, and these new features are added to the original features to train the LR model together, and finally a trained XGBoost+LR combined model is obtained for predicting claim frequency and claim intensity.

[0095] Preferably, the XGBoost model consists of a series of weak learners (CART regression trees). These trees are added gradually, and each tree tries to correct the errors of the previous tree; XGBoost can use multi-core processors for parallel computing in the process of building each tree, thereby speeding up training, providing accurate predictions and processing large amounts of data.

[0096] Preferably, the LR model of this embodiment adopts a linear regression model.

[0097] Preferably, it also includes: a car insurance quotation module;

[0098] The auto insurance quotation module is used to obtain the auto insurance premium corresponding to the insured object based on the auto insurance factor, and obtain the final auto insurance quotation corresponding to the insured object based on the auto insurance premium.

[0099] Preferably, the auto insurance premium P of the i-th insured object i for:

[0100] P i =S i ×F i +correlation(S i ,F i )i=1,2,3,4

[0101] Among them, S i and F i They represent the claim intensity and claim frequency of the i-th insured object, correlation(S i ,F i ) represents a function that measures the dependency between claim intensity and claim frequency.

[0102] Preferably, the final rate P is obtained based on the car insurance premium:

[0103] P=I1[aT1+bT2]+(1-I1)T2

[0104] T1=I3P4+(1-I3)P3

[0105] T2=I2P2+(1-I2)P1

[0106]

[0107]

[0108]

[0109] Among them, a represents the proportion of autonomous driving mileage, which is the ratio of autonomous driving mileage to total mileage in the past three months, T1 represents the autonomous driving auto insurance premium, b represents the proportion of manual driving mileage, which is the ratio of manual driving mileage to total mileage in the past three months, and T2 represents the pure premium of manual driving or the traditional vehicle insurance premium.

[0110] Preferably, the final car insurance quotation is obtained based on the final rate P, and the final premium = basic premium * P.

[0111] Preferably, it also includes: an association rule module;

[0112] The association rule module is used to collect and perform data analysis based on traffic accident reports, calculate the correlation between different traffic accidents, obtain association rules, and determine the exit scenario data of the autonomous driving vehicle based on the association rules.

[0113] Preferably, the association rule module includes: a data processing unit, an association unit and an analysis unit;

[0114] A data processing unit, used for collecting a number of traffic accident reports and processing the traffic accident reports to obtain a traffic accident data set;

[0115] An association unit is used to calculate the association degree based on the traffic accident data set, obtain all frequent item sets, and generate association rules based on all frequent item sets;

[0116] An analysis unit is used to determine the disengagement scenario data of the autonomous driving vehicle based on the association rules.

[0117] Preferably, the data processing unit performs processing based on the traffic accident report, specifically including: performing feature engineering on the data of a total of N traffic accident reports to obtain a data set D of N traffic accident reports:

[0118] D=(T d ) d∈[1,N] ,T d ∈I m

[0119] T d =(I j ) j∈[1,m]

[0120] Among them, T d represents the item set corresponding to the dth traffic accident, I m Represents the space of m-dimensional itemsets.

[0121] Preferably, Figure 4 As shown, the association unit generates association rules based on all frequent item sets, including:

[0122] Starting from a single item, generate a set C1 of candidate item sets;

[0123] Set the support threshold, calculate the support of each candidate item set, remove the item sets with support less than the threshold, and obtain the frequent item set set L1;

[0124] Based on the frequent itemset L in the frequent itemset set L1 k Generate the candidate item set C for the next level k+1 , by connecting L k And remove the infrequent subsets to get the candidate item set C k+1 , calculate each candidate item set C k+1 , filter out the item sets whose support is less than the support threshold and get L k+1 , repeat this process until no new frequent item sets can be generated, and all frequent item sets are obtained;

[0125] For each frequent item set F, generate all possible non-empty subsets G and H = FG;

[0126] Set the confidence threshold, calculate the confidence of each rule G→H, and retain the rules whose confidence is greater than or equal to the minimum confidence threshold as association rules.

[0127] Preferably, the analysis unit is further used to evaluate the generated association rules, calculate the support of the generated rules, sort the rules from high to low according to the support, and observe and analyze the top rules to derive the correlation between the factors affecting traffic accidents. The support rate calculation formula is:

[0128]

[0129] Among them, X and Y represent two item sets in a generated association rule, σ(X∪Y) represents the number of transactions that contain both X and Y item sets, and N represents the total number of transactions in traffic accidents.

[0130] Preferably, based on the association rule results, it can be obtained that: the scenarios in which most autonomous driving traffic accidents occur are not significantly different from those in which traditional manual driving cars are involved, that is, the scenarios that traditional manual driving car insurance deals with can also deal with scenarios in which autonomous driving car traffic accidents occur; however, there is an interesting feature in these association rules, that is, many item sets containing CONVENTIONAL have high support, but FULL-MANUAL does not have high support, which indicates that many traffic accidents may involve scenarios unique to autonomous driving cars - "disengagement".

[0131] Preferably, it also includes: a vehicle insurance liability division module;

[0132] The auto insurance liability division module is used to obtain a first weight coefficient of the disengagement scenario part based on the disengagement scenario data, obtain and obtain a second weight coefficient and a third weight coefficient corresponding to the automatic mode and the manual mode of the autonomous driving vehicle respectively based on the driving risk coefficient, determine the liability ratio between the car owner and the autonomous driving car manufacturer based on the first weight coefficient, the second weight coefficient and the third weight coefficient, and obtain the auto insurance payment amount of the car owner and the autonomous driving car manufacturer based on the liability ratio and the final auto insurance quotation.

[0133] Preferably, the vehicle insurance liability division module includes: a first coefficient determination unit, a risk coefficient determination unit, a second coefficient determination unit, a third coefficient determination unit, a liability division unit and a vehicle insurance division unit;

[0134] A first coefficient determination unit, configured to calculate a premium weight coefficient of a disengagement portion of the autonomous driving vehicle based on the disengagement scenario data as a first weight coefficient;

[0135] A risk factor determination unit, used for obtaining a driving risk factor based on the number of accidents of different severity and the corresponding average compensation value per accident;

[0136] A second coefficient determination unit, configured to obtain a premium weight coefficient of the autonomous driving vehicle in the autonomous driving mode based on the driving risk coefficient as a second weight coefficient;

[0137] A third coefficient determination unit, configured to obtain a premium weight coefficient of the automatic driving vehicle in a manual driving mode based on the driving risk coefficient as a third weight coefficient;

[0138] A responsibility division unit, used to determine the responsibility ratio of the vehicle owner and the responsibility ratio of the autonomous driving vehicle manufacturer based on the first weight coefficient, the second weight coefficient and the third weight coefficient;

[0139] The auto insurance division unit is used to obtain the auto insurance payment amount of the car owner and the auto insurance payment amount of the autonomous driving car manufacturer based on the final auto insurance quotation, the liability ratio of the car owner and the liability ratio of the autonomous driving car manufacturer.

[0140] Preferably, the first coefficient determination unit calculates the first weight coefficient W D Specifically include:

[0141] W D =L A ÷MPD×APD×C D

[0142] L=L C +L A

[0143] Among them, L represents the total mileage of the autonomous vehicle in the past year, L C represents the manual driving mileage of the autonomous vehicle, L A represents the autonomous driving mileage of the autonomous vehicle, MPD represents the average driving distance of the autonomous vehicle each time it disengages in the past year, APD represents the average number of accidents caused by each disengagement, and C D Indicates the average compensation amount for each accident.

[0144] Preferably, the risk coefficient determination unit calculates the driving risk coefficient R, specifically including:

[0145]

[0146] Q=Q1+Q2+Q3+Q4

[0147] Q×C=Q1×C1+Q2×C2+Q3×C3+Q4×C4

[0148] Among them, MPA represents the average mileage per accident, Q represents the total number of traffic accidents that occurred in a specific area (a city, town, or special zone) in the past year, the severity of traffic accidents is divided into four levels: 1, 2, 3, and 4, Q1, Q2, Q3, and Q4 correspond to the number of accidents of different severity, C represents the average amount of compensation for each loss, and C1, C2, C3, and C4 correspond to the average compensation of different degrees.

[0149] Preferably, the second coefficient determination unit calculates the second weight coefficient W A Specifically include:

[0150]

[0151] Among them, L Aj represents the mileage of the autonomous driving vehicle in the jth specific area in automatic mode, R Aj Represents the risk factor of the autonomous driving car driving in automatic mode in the j-th specific area.

[0152] Preferably, the average mileage per accident MPA is replaced by the average mileage per accident MPA in automatic mode driving Aj , replace the average amount of compensation for each loss C with the average amount of compensation for each loss C under automatic driving mode Aj , put it into the driving risk coefficient formula, and get R Aj .

[0153] Preferably, the third coefficient determination unit calculates and obtains the third weight coefficient W C Specifically include:

[0154]

[0155] Among them, L Cj represents the mileage of the manual mode driving of the autonomous driving car in the jth specific area, R Cj is the risk factor of manual mode driving of the autonomous vehicle in the jth specific area.

[0156] Preferably, the average mileage per accident MPA is replaced by the average mileage per accident MPA under manual mode driving Cj , replace the average amount of compensation for each loss C with the average amount of compensation for each loss C under automatic driving mode Cj , put it into the driving risk coefficient formula, and get R Cj .

[0157] Preferably, the responsibility division unit determines the proportion of responsibility borne by the vehicle owner and the proportion of responsibility borne by the autonomous vehicle manufacturer, specifically including:

[0158] The proportion of responsibility borne by the car owner Puser :

[0159]

[0160] The proportion of responsibility borne by autonomous vehicle manufacturers manufacturer :

[0161]

[0162] Preferably, the auto insurance division unit divides the final auto insurance quote into user and P manufacturer Multiplying them together gives the corresponding amount the car owner pays for auto insurance and the amount the self-driving car manufacturer pays for auto insurance.

[0163] Example 3

[0164] like Figure 5 As shown, a method for designing an insurance product for an autonomous driving vehicle includes:

[0165] Classify the insured objects based on vehicle type and Internet of Vehicles data to obtain multiple categories of insured objects;

[0166] Obtain the basic data of the insured person, and determine the indicator data corresponding to the insured person based on the basic data;

[0167] Construct a combined prediction model and input the indicator data into the combined prediction model to obtain the auto insurance factor corresponding to the insured object.

[0168] Example 4

[0169] A method for designing an insurance product for an autonomous driving vehicle, comprising:

[0170] Classify the insured objects based on vehicle type and Internet of Vehicles data to obtain multiple categories of insured objects;

[0171] Obtain the basic data of the insured person, and determine the indicator data corresponding to the insured person based on the basic data;

[0172] Construct a combined prediction model and input the index data into the combined prediction model to obtain the corresponding auto insurance factor of the insured object;

[0173] Obtaining the corresponding auto insurance premium of the insured object based on the auto insurance factor, and obtaining the corresponding final auto insurance quotation of the insured object based on the auto insurance premium;

[0174] Collect and analyze data based on traffic accident reports, calculate the correlation between different traffic accidents, obtain association rules, and determine the exit scenario data of the autonomous driving vehicle based on the association rules;

[0175] Obtaining a first weight coefficient of the detached scene portion based on the detached scene data;

[0176] Obtaining and obtaining, based on the driving risk coefficient, a second weight coefficient and a third weight coefficient corresponding to the automatic mode and the manual mode of the automatic driving vehicle respectively;

[0177] Determining the proportion of liability borne by the vehicle owner and the autonomous vehicle manufacturer based on the first weighting coefficient, the second weighting coefficient, and the third weighting coefficient;

[0178] The car insurance payment amount for the car owner and the autonomous vehicle manufacturer is obtained based on the liability ratio and the final car insurance quote.

[0179] Example 5

[0180] Based on the same inventive concept, the present invention also provides a computer device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0181] Memory, used to store computer programs;

[0182] The processor, when used to execute the program stored in the memory, can implement an autonomous driving automobile insurance product design method as in Example 3 or 4.

[0183] The electronic device may include: a processor, a communications interface, a memory, and a communications bus, wherein the processor, the communications interface, and the memory communicate with each other via the communications bus. The processor may call logic instructions in the memory to execute a self-driving car insurance product design method in Embodiment 3 or 4.

[0184] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0185] Through the above technical solutions, it can be known that the present invention discloses a system and method for designing an insurance product for an autonomous driving vehicle. By taking into account influencing factors such as the driving environment and driving behavior and relevant characteristics of the autonomous driving vehicle, the insurance quotation for the autonomous driving vehicle can be determined more accurately; by formulating association rules, the disengagement scenario of the autonomous driving vehicle can be accurately determined, and the liability ratio of the car owner and the autonomous driving vehicle manufacturer can be obtained in combination with the driving risk coefficient.

[0186] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0187] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A self-driving car insurance product design system, characterized in that: include: Insured object identification module, data collection and processing module and automobile insurance factor determination module; The insured object identification module is used to classify the insured objects based on vehicle type and Internet of Vehicles data to obtain multiple categories of insured objects; The data collection and processing module is used to obtain the basic data of the insured object and determine the indicator data corresponding to the insured object based on the basic data; The vehicle insurance factor determination module is used to construct a combined prediction model and input the indicator data into the combined prediction model to obtain the vehicle insurance factor corresponding to the insured object.

2. The autonomous driving car insurance product design system according to claim 1, characterized in that: The insured object identification module includes: a data acquisition unit and an object identification unit; The data acquisition unit is used to acquire the vehicle type and the Internet of Vehicles data of several months before the insurance is purchased; The object identification unit is used to make a judgment based on the vehicle type and the Internet of Vehicles data. When the vehicle type is an ordinary vehicle, it is judged whether there is corresponding Internet of Vehicles data. If so, it is determined to be an experienced driver as the first object, otherwise it is determined to be a novice driver as the second object; when the vehicle type is an autonomous driving vehicle, it is judged whether there is corresponding Internet of Vehicles data. If so, it is determined to be an experienced autonomous driving vehicle as the third object, otherwise it is determined to be a new autonomous driving vehicle as the fourth object.

3. The autonomous driving car insurance product design system according to claim 2, characterized in that: The data collection and processing module includes: a data collection unit and an indicator data acquisition unit; The data collection unit is used to obtain the basic data of the insured person: driver information, vehicle information, automatic driving system information, UBI variable information and vehicle-road collaboration information; The indicator data acquisition unit is used to determine, based on the basic information, that the first object selects the corresponding driver information, the vehicle information and the vehicle-road collaborative information as the first data set; determines that the second object selects the corresponding driver information, the vehicle information, the UBI variable information and the vehicle-road collaborative information as the second data set; determines that the third object selects the corresponding vehicle information, the automatic driving system information, and the vehicle-road collaborative information as the third data set; determines that the fourth object selects the corresponding vehicle information, the automatic driving system information, the UBI variable information and the vehicle-road collaborative information as the fourth data set; and is also used to obtain first indicator data, second indicator data, third indicator data and fourth indicator data based on the first data set, the second data set, the third data set and the fourth data set.

4. The autonomous driving car insurance product design system according to claim 3, characterized in that: The vehicle insurance factor determination module includes: a prediction model building unit and a vehicle insurance factor prediction unit; The prediction model building unit is used to build a combined prediction model; The vehicle insurance factor prediction unit is used to input the first index data, the second index data, the third index data and the fourth index data into the combined prediction model respectively to obtain the vehicle insurance factors corresponding to the first object, the second object, the third object and the fourth object, and the vehicle insurance factors include: claim frequency and claim intensity.

5. The autonomous driving car insurance product design system according to claim 1, characterized in that: Also includes: Auto insurance quotation module; The car insurance quotation module is used to obtain the car insurance premium corresponding to the insured object based on the car insurance factor, and obtain the final car insurance quotation corresponding to the insured object based on the car insurance premium.

6. The autonomous driving car insurance product design system according to claim 5, characterized in that: Also includes: Association rules module; The association rule module is used to collect and perform data analysis based on traffic accident reports, calculate the correlation between different traffic accidents, obtain association rules, and determine the exit scenario data of the autonomous driving vehicle based on the association rules.

7. The autonomous driving car insurance product design system according to claim 6, characterized in that: The association rule module includes: a data processing unit, an association unit and an analysis unit; The data processing unit is used to collect a plurality of traffic accident reports and process the traffic accident reports to obtain a traffic accident data set; The association unit is used to calculate the association degree based on the traffic accident data set to obtain all frequent item sets, and generate the association rules based on all the frequent item sets; The analysis unit is used to determine the exit scenario data of the autonomous driving vehicle based on the association rule.

8. The autonomous driving car insurance product design system according to claim 6, characterized in that: Also includes: Motor insurance liability division module; The auto insurance liability division module is used to obtain a first weight coefficient for the disengagement scenario part based on the disengagement scenario data, obtain and obtain a second weight coefficient and a third weight coefficient corresponding to the automatic mode and the manual mode of the autonomous driving vehicle respectively based on the driving risk coefficient, determine the liability ratio between the car owner and the autonomous driving car manufacturer based on the first weight coefficient, the second weight coefficient and the third weight coefficient, and obtain the auto insurance payment amount of the car owner and the autonomous driving car manufacturer based on the liability ratio and the final auto insurance quotation.

9. The autonomous driving car insurance product design system according to claim 8, characterized in that: The vehicle insurance liability division module includes: a first coefficient determination unit, a risk coefficient determination unit, a second coefficient determination unit, a third coefficient determination unit, a liability division unit and a vehicle insurance division unit; The first coefficient determination unit is used to calculate the premium weight coefficient of the disengagement part of the autonomous driving vehicle based on the disengagement scenario data as the first weight coefficient; The risk coefficient determination unit is used to obtain the driving risk coefficient based on the number of accidents of different severity and the corresponding average compensation value per accident; The second coefficient determination unit is configured to obtain, based on the driving risk coefficient, a premium weight coefficient of the autonomous driving vehicle in the autonomous driving mode as the second weight coefficient; The third coefficient determination unit is configured to obtain, based on the driving risk coefficient, a premium weight coefficient of the automatic driving vehicle in the manual driving mode as the third weight coefficient; The responsibility division unit is used to determine the responsibility ratio of the vehicle owner and the responsibility ratio of the autonomous driving vehicle manufacturer based on the first weight coefficient, the second weight coefficient and the third weight coefficient; The car insurance division unit is used to obtain the car insurance payment amount of the car owner and the car insurance payment amount of the autonomous driving car manufacturer based on the final car insurance quotation, the car owner's liability ratio and the autonomous driving car manufacturer's liability ratio.

10. A method for designing an insurance product for an autonomous driving vehicle, applied to an insurance product design system for an autonomous driving vehicle as claimed in any one of claims 1 to 9, characterized in that: include: Classify the insured objects based on vehicle type and Internet of Vehicles data to obtain multiple categories of insured objects; Acquire basic data of the insured person, and determine indicator data corresponding to the insured person based on the basic data; A combined prediction model is constructed, and the indicator data is input into the combined prediction model to obtain the vehicle insurance factor corresponding to the insured object.

Images