Car insurance risk assessment method and device based on artificial intelligence, equipment and medium

Abstract

The embodiment of the invention provides a car insurance risk assessment method and device based on artificial intelligence, equipment and a medium, and belongs to the technical field of artificial intelligence and the technical field of financial science and technology. The method comprises the steps that vehicle basic risk information of a target vehicle is acquired through a vehicle insurance safety calculation node, a vehicle owner consumption information acquisition request is generated according to the target vehicle, and the vehicle owner consumption information acquisition request is sent to a consumption safety calculation node; in response to the vehicle owner consumption information acquisition request, target vehicle owner consumption information is acquired through the consumption safety calculation node, target vehicle owner consumption feature information is generated according to the target vehicle owner consumption information, and the target vehicle owner consumption feature information is sent to the vehicle insurance safety calculation node; and starting the target machine learning model through the vehicle insurance safety calculation node, and performing vehicle insurance risk assessment on the vehicle basic risk information and the target vehicle owner consumption feature information through the target machine learning model. According to the embodiment of the invention, the accuracy of vehicle insurance risk assessment can be improved, and the data security is ensured.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence technology and financial technology, and in particular to an artificial intelligence-based auto insurance risk assessment method and apparatus, equipment, and medium. Background Art

[0002] Auto insurance risk assessment refers to assessing the risk of insurance for a vehicle. Generally, the higher the risk, the higher the insurance price. Current auto insurance risk assessment methods mainly rely on driving-related information, such as the user's vehicle type, past accident records, etc. Driving-related information is difficult to fully reflect the user's actual risk level, affecting the reliability of auto insurance risk assessment. It is possible to consider conducting a comprehensive auto insurance risk assessment based on consumer information such as consumption frequency and consumption category. For example, in the insurance industry in the field of financial technology, auto insurance risk assessment is conducted based on consumer information, and then the insurance price is determined based on the risk. However, consumer information has high security requirements and is difficult to obtain or use directly.

[0003] Therefore, how to improve the accuracy of auto insurance risk assessment and ensure data security has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose an artificial intelligence-based auto insurance risk assessment method and device, equipment, and medium, aiming to improve the accuracy of auto insurance risk assessment and ensure data security.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a method for assessing automobile insurance risk based on artificial intelligence, the method comprising:

[0006] Obtaining basic vehicle risk information of the target vehicle through the vehicle insurance safety calculation node; wherein the basic vehicle risk information is encrypted information;

[0007] Generate a request for obtaining the vehicle owner's consumption information according to the target vehicle through the vehicle insurance safety computing node, and send the request for obtaining the vehicle owner's consumption information to the consumption safety computing node;

[0008] In response to the vehicle owner consumption information acquisition request, acquiring the target vehicle owner consumption information through the consumption security computing node;

[0009] Generate target vehicle owner consumption characteristic information by using the target vehicle owner consumption information through the consumption safety computing node;

[0010] Sending the target car owner's consumption feature information to the car insurance safety computing node through the consumption safety computing node;

[0011] The target machine learning model is started through the auto insurance safety calculation node, and the auto insurance risk assessment is performed on the basic risk information of the vehicle and the consumption characteristic information of the target vehicle owner through the target machine learning model.

[0012] In some embodiments, the performing auto insurance risk assessment on the basic vehicle risk information and the target vehicle owner consumption characteristic information by using the target machine learning model includes:

[0013] Performing overall information calculation on the basic risk information of the vehicle and the consumption characteristic information of the target vehicle owner through the target machine learning model to obtain overall risk information of the target vehicle;

[0014] Calculating the information ratio of the basic risk information of the vehicle and the overall risk information of the target vehicle through the target machine learning model to obtain a basic risk factor of the target vehicle;

[0015] The target machine learning model is used to calculate the information ratio of the target vehicle owner's consumption characteristic information and the target vehicle's overall risk information to obtain a target vehicle consumption risk factor;

[0016] The auto insurance risk assessment data is determined according to the target vehicle basic risk factor and the target vehicle consumption risk factor.

[0017] In some embodiments, after performing the auto insurance risk assessment on the basic vehicle risk information and the target vehicle owner consumption characteristic information by using the target machine learning model, the method further includes:

[0018] Performing a first pricing process on the target vehicle basic risk factor and the vehicle basic risk information through the vehicle insurance safety calculation node to obtain a first vehicle insurance pricing;

[0019] Through the auto insurance safety calculation node, a second pricing process is performed on the target vehicle consumption risk factor and the target vehicle owner consumption characteristic information to obtain a second auto insurance pricing;

[0020] The first auto insurance pricing and the second auto insurance pricing are jointly priced through the auto insurance safety calculation node to obtain target auto insurance price data.

[0021] In some embodiments, generating the target vehicle owner consumption characteristic information by using the target vehicle owner consumption information through the consumption safety computing node includes:

[0022] Extracting consumption characteristics from the consumption information of the target vehicle owner through the consumption safety computing node to obtain consumption characteristic information of the target vehicle owner;

[0023] The consumption characteristic information of the target vehicle owner is encrypted by the consumption safety computing node using a preset information encryption algorithm to obtain the consumption characteristic information of the target vehicle owner in an encrypted state; wherein the vehicle insurance safety computing node supports the information encryption algorithm.

[0024] In some embodiments, the target vehicle owner consumption characteristic information includes vehicle consumption frequency characteristic information;

[0025] The extracting consumption characteristics of the target vehicle owner's consumption information through the consumption safety computing node to obtain the target vehicle owner's consumption characteristic information includes:

[0026] Classifying the consumption information of the target vehicle owner to obtain candidate consumption categories;

[0027] The target vehicle owner consumption information is screened according to a preset reference vehicle consumption category and the candidate consumption category to obtain vehicle consumption information; wherein the reference vehicle consumption category represents a consumption category associated with the vehicle;

[0028] The vehicle consumption ratio analysis is performed based on the vehicle consumption information and the target vehicle owner consumption information to obtain the vehicle consumption frequency characteristic information.

[0029] In some embodiments, the target vehicle owner consumption characteristic information is encrypted information, and the target vehicle owner consumption characteristic information is encrypted by the consumer security computing node using a preset target private key and a homomorphic encryption algorithm;

[0030] After the first auto insurance pricing and the second auto insurance pricing are jointly priced by the auto insurance safety calculation node to obtain target auto insurance price data, the method further includes:

[0031] Decrypting the target auto insurance price data by using the homomorphic encryption algorithm and the target public key through the auto insurance security computing node to obtain the decrypted target auto insurance price data; wherein the target public key corresponds to the target private key;

[0032] The decrypted target vehicle insurance price data is sent to the target vehicle owner corresponding to the target vehicle through the vehicle insurance security calculation node.

[0033] In some embodiments, the target vehicle is a vehicle of a target vehicle owner using a vehicle insurance risk assessment client;

[0034] After the first auto insurance pricing and the second auto insurance pricing are jointly priced by the auto insurance safety calculation node to obtain target auto insurance price data, the method further includes:

[0035] In response to a target pricing inquiry request sent by the auto insurance risk assessment service end, sending the target auto insurance price to the auto insurance risk assessment service end through the auto insurance safety calculation node; wherein the target pricing inquiry request is generated based on an initial pricing inquiry request sent by the auto insurance risk assessment client;

[0036] The target auto insurance price data is sent to the auto insurance risk assessment client through the auto insurance risk assessment business end; wherein the auto insurance risk assessment client does not have permission to access the auto insurance safety computing node.

[0037] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a vehicle insurance risk assessment device based on artificial intelligence, the device comprising:

[0038] A basic risk information acquisition module is used to acquire the basic vehicle risk information of the target vehicle through the vehicle insurance safety calculation node; wherein the basic vehicle risk information is encrypted information;

[0039] A request generation module, configured to generate a request for obtaining the vehicle owner's consumption information according to the target vehicle through the vehicle insurance safety computing node, and send the request for obtaining the vehicle owner's consumption information to the consumption safety computing node;

[0040] A consumption information module, used to respond to the vehicle owner's consumption information acquisition request and acquire the target vehicle owner's consumption information through the consumption security computing node;

[0041] A characteristic information generating module, used for generating target vehicle owner consumption characteristic information by using the target vehicle owner consumption information through the consumption safety computing node;

[0042] A characteristic information sending module, used for sending the target car owner's consumption characteristic information to the car insurance safety computing node through the consumption safety computing node;

[0043] The risk assessment module is used to start the target machine learning model through the auto insurance safety calculation node, and perform auto insurance risk assessment on the vehicle basic risk information and the target vehicle owner consumption characteristic information through the target machine learning model.

[0044] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the artificial intelligence-based auto insurance risk assessment method described in the first aspect when executing the computer program.

[0045] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the artificial intelligence-based auto insurance risk assessment method described in the first aspect above.

[0046] The artificial intelligence-based auto insurance risk assessment method, device, equipment, and medium proposed in the present application obtain the encrypted basic vehicle risk information of the target vehicle through the auto insurance safety computing node; generate a request for obtaining the owner's consumption information according to the target vehicle through the auto insurance safety computing node, and send the request for obtaining the owner's consumption information to the consumer safety computing node; in response to the request for obtaining the owner's consumption information, generate target owner's consumption feature information according to the target owner's consumption information through the consumer safety computing node, and then send the target owner's consumption feature information to the auto insurance safety computing node; it can be seen that the auto insurance safety computing node cannot directly obtain the target owner's consumption information, but obtains the target owner's consumption feature information after the consumer safety computing node generates the target owner's consumption feature information according to the target owner's consumption information, thereby avoiding the leakage of the target owner's consumption information during the data transmission process and ensuring the security of the target owner's consumption information; then, the target machine learning model is started through the auto insurance safety computing node, and the auto insurance risk assessment is performed on the vehicle basic risk information and the target owner's consumption feature information through the target machine learning model, thereby improving the accuracy of the auto insurance risk assessment. It can be seen that the present application jointly conducts auto insurance risk assessment through the auto insurance safety calculation node and the consumer safety calculation node. During the above auto insurance risk assessment process, the auto insurance safety calculation node will not directly obtain the target car owner consumption information of the consumer safety calculation node, and the auto insurance safety calculation node will not directly send the basic vehicle risk information to the consumer safety calculation node, thus avoiding the leakage of the above data and ensuring data security. In summary, the present application can improve the accuracy of auto insurance risk assessment and ensure data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of an artificial intelligence-based auto insurance risk assessment method provided in an embodiment of the present application;

[0048] Figure 2 yes Figure 1 Flowchart of step 104 in;

[0049] Figure 3 yes Figure 2 Flow chart of step 201 in;

[0050] Figure 4 yes Figure 1 Flow chart of step 106 in;

[0051] Figure 5is a flow chart of an artificial intelligence-based auto insurance risk assessment method provided by another embodiment of the present application;

[0052] Figure 6 is a flow chart of an artificial intelligence-based auto insurance risk assessment method provided by another embodiment of the present application;

[0053] Figure 7 is a flow chart of an artificial intelligence-based auto insurance risk assessment method provided by another embodiment of the present application;

[0054] Figure 8 It is a schematic diagram of the structure of an automobile insurance risk assessment device based on artificial intelligence provided in an embodiment of the present application;

[0055] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0059] First, some nouns involved in this application are analyzed:

[0060] Artificial Intelligence (AI): It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science. AI attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0061] Privacy computing technology: It is a technology that enables data sharing and data analysis while protecting data privacy. Privacy computing technology can be used to ensure data security. Privacy computing technology specifically includes federated learning, multi-party computing, and homomorphic encryption.

[0062] Federated Learning (FL): is a distributed machine learning technology. In federated learning, multiple parties are allowed to collaborate in training machine learning models. Multiple parties can jointly train models without sharing original data, thus ensuring the security of original data.

[0063] Secure Multi-Party Computation (MPC): is a cryptographic technology that allows multiple parties to jointly calculate the result of a function while protecting the privacy of their respective data.

[0064] Homomorphic Encryption (HE): is an encryption method. By homomorphically encrypting the original data, the encrypted ciphertext can be directly calculated to obtain the calculation result, and the decrypted calculation result is the same as the result of the same calculation directly on the original data. Homomorphic encryption allows data to be effectively processed and analyzed even in an encrypted state.

[0065] The artificial intelligence-based auto insurance risk assessment method, device, equipment, and medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the artificial intelligence-based auto insurance risk assessment method in the embodiments of the present application is described.

[0066] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0067] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0068] The auto insurance risk assessment method based on artificial intelligence provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the auto insurance risk assessment method based on artificial intelligence, etc., but is not limited to the above forms.

[0069] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0070] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0071] Figure 1 is an optional flowchart of the method for assessing automobile insurance risk based on artificial intelligence provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps 101 to 106.

[0072] Step 101, obtaining basic vehicle risk information of a target vehicle through a vehicle insurance safety calculation node; wherein the basic vehicle risk information is encrypted information;

[0073] Step 102, generating a request for obtaining the vehicle owner's consumption information according to the target vehicle through the vehicle insurance safety computing node, and sending the request for obtaining the vehicle owner's consumption information to the consumption safety computing node;

[0074] Step 103, in response to the request for obtaining the consumption information of the vehicle owner, obtaining the consumption information of the target vehicle owner through the consumption security computing node;

[0075] Step 104, generating target vehicle owner consumption characteristic information using the target vehicle owner consumption information through the consumption safety computing node;

[0076] Step 105, sending the target car owner's consumption characteristic information to the car insurance safety computing node through the consumption safety computing node;

[0077] Step 106, start the target machine learning model through the auto insurance safety calculation node, and use the target machine learning model to conduct auto insurance risk assessment on the vehicle basic risk information and the target vehicle owner's consumption characteristic information.

[0078] The beneficial effects of the embodiments of the present application include but are not limited to: obtaining the encrypted basic vehicle risk information of the target vehicle through the auto insurance safety computing node; generating a request for obtaining the owner's consumption information according to the target vehicle through the auto insurance safety computing node, and sending the request for obtaining the owner's consumption information to the consumer safety computing node; in response to the request for obtaining the owner's consumption information, generating target owner's consumption characteristic information according to the target owner's consumption information through the consumer safety computing node, and then sending the target owner's consumption characteristic information to the auto insurance safety computing node; it can be seen that the auto insurance safety computing node cannot directly obtain the target owner's consumption information, but obtains the target owner's consumption characteristic information after the consumer safety computing node generates the target owner's consumption characteristic information according to the target owner's consumption information, thereby avoiding the leakage of the target owner's consumption information during the data transmission process and ensuring the security of the target owner's consumption information; then, starting the target machine learning model through the auto insurance safety computing node, and performing auto insurance risk assessment on the vehicle basic risk information and the target owner's consumption characteristic information through the target machine learning model, thereby improving the accuracy of the auto insurance risk assessment. It can be seen that the present application jointly conducts auto insurance risk assessment through the auto insurance safety calculation node and the consumer safety calculation node. During the above auto insurance risk assessment process, the auto insurance safety calculation node will not directly obtain the target car owner consumption information of the consumer safety calculation node, and the auto insurance safety calculation node will not directly send the basic vehicle risk information to the consumer safety calculation node, thus avoiding the leakage of the above data and ensuring data security. In summary, the present application can improve the accuracy of auto insurance risk assessment and ensure data security.

[0079] In step 101 of some embodiments, the basic vehicle risk information of the target vehicle can also be obtained from a preset vehicle information database through a vehicle insurance safety calculation node. The vehicle information database is maintained by the vehicle insurance safety calculation node, and the vehicle information database does not have the permission to be accessed by nodes other than the vehicle insurance safety calculation node. This embodiment can ensure that the basic vehicle risk information in the vehicle information database is not accessed by unauthorized nodes, thereby improving the data security of vehicle insurance risk assessment and reducing the risk of data leakage. The basic vehicle risk information can also be obtained by other means, not limited to this. It should be noted that vehicle insurance refers to vehicle insurance.

[0080] It should be noted that the auto insurance safety computing node may be a node in a distributed network, specifically a physical server or a virtual server. The auto insurance safety computing node is used to perform auto insurance risk assessment.

[0081] Specifically, the basic vehicle risk information includes at least one of: basic vehicle information, owner's driving behavior information, vehicle geographical information and vehicle insurance policy information.

[0082] In some embodiments, the basic risk information of the vehicle may be encrypted information obtained by encrypting with a preset information encryption algorithm. Specifically, the information encryption algorithm may be a homomorphic encryption algorithm, a public key encryption algorithm, and a symmetric encryption algorithm. The information encryption algorithm may also be other common encryption algorithms, without limitation. Among them, both the auto insurance safety computing node and the consumer safety computing node support the above-mentioned information encryption algorithm, that is, the configuration, hardware resources and software environment of the auto insurance safety computing node and the consumer safety computing node server are compatible with the requirements of the information encryption algorithm, so that the algorithm can run normally on the auto insurance safety computing node and the consumer safety computing node.

[0083] In some embodiments, the target machine learning model can be obtained by training the preset initial machine learning model. Specifically, the maximum likelihood estimation (MLE) or the least squares method (LeastSquares) can be used to train the preset initial machine learning model.

[0084] In step 102 of some embodiments, the auto insurance safety computing node is connected to the consumer safety computing node. Specifically, the auto insurance safety computing node and the consumer safety computing node can be two different servers. In another embodiment, the auto insurance safety computing node and the consumer safety computing node are respectively located in different network areas separated by a certain physical distance. For example, the auto insurance safety computing node is located in area A, the consumer safety computing node is located in area B, and area A and area B are 10 kilometers apart.

[0085] In step 103 of some embodiments, obtaining the target car owner's consumption information through the consumption safety computing node may also include: obtaining the target car owner's consumption information from a preset consumption information database through the consumption safety computing node. The consumption information database is maintained by the consumption safety computing node, and the consumption information database does not have the permission to be accessed by nodes other than the consumption safety computing node. This embodiment can ensure that the target car owner's consumption information in the consumption information database is not accessed by unauthorized nodes, thereby improving the data security of the auto insurance risk assessment and reducing the risk of data leakage. The target car owner's consumption information can also be obtained by other means, not limited to this.

[0086] It should be noted that the owner consumption information acquisition request has the information of the target vehicle, such as the identification, serial number or license plate number of the target vehicle. The target owner consumption information refers to the consumption information of the target owner of the target vehicle. For example, the target owner can perform consumption operations on the client, and the client stores the consumption information generated by the target owner's consumption operation in the consumption safety computing node, which can be specifically stored in the consumption information database of the consumption safety computing node, or in other storage media of the consumption safety computing node, which is not limited in the embodiments of the present application.

[0087] In step 104 of some embodiments, the target vehicle owner's consumption characteristic information is generated by the consumption safety computing node using the target vehicle owner's consumption information. Specifically, the target vehicle owner's consumption characteristic information is obtained by extracting characteristics of the target vehicle owner's consumption information through the consumption safety computing node.

[0088] In some embodiments, it should be noted that the target car owner's consumption information is the original consumption data, such as the target car owner's consumption receipt, the consumption amount within a preset period (such as one month), etc. The target car owner's consumption feature information is the data after feature extraction from the original consumption data, and the target car owner's consumption feature information is associated with the auto insurance risk. Specifically, the target car owner's consumption feature information can be the target car owner's credit score, payment ability score, etc.

[0089] It should be noted that the consumption safety computing node will send the information obtained after feature extraction based on the target car owner's consumption information (that is, the target car owner's consumption feature information) to the auto insurance safety computing node to avoid the auto insurance safety computing node directly obtaining the target car owner's consumption information, which can improve data security. At the same time, the accuracy of auto insurance risk assessment can also be improved with the help of the target car owner's consumption feature information.

[0090] Specifically, the target vehicle owner's consumption characteristic information may also include consumption health condition characteristic information. For example, if the target vehicle owner has outstanding debt information, and the duration of the outstanding debt information is greater than a preset outstanding debt duration threshold, or the amount of outstanding debt information is greater than a preset outstanding debt amount threshold, then the value of the consumption health condition characteristic information is relatively low.

[0091] In step 105 of some embodiments, the target car owner's consumption characteristic information is sent to the auto insurance safety computing node through the consumer safety computing node, which may be after the target car owner's consumption characteristic information is encrypted by the consumer safety computing node, and then the encrypted target car owner's consumption characteristic information is sent to the auto insurance safety computing node. That is, the target car owner's consumption characteristic information received by the auto insurance safety computing node is encrypted information. It should be noted that the consumer safety computing node and the auto insurance safety computing node use the same or corresponding encryption and decryption algorithms to encrypt or decrypt the target car owner's consumption characteristic information to ensure that the target car owner's consumption characteristic information can be processed normally on the above two nodes. Among them, the encryption and decryption algorithms may include symmetric encryption algorithms and asymmetric encryption algorithms, such as key encryption algorithms, homomorphic encryption algorithms, etc.

[0092] In step 106 of some embodiments, the target machine learning model may be a machine learning model pre-deployed on a car insurance safety computing node. In another embodiment, the target machine learning model can perform a car insurance weight analysis on the basic risk information of the vehicle and the consumption characteristic information of the target owner to obtain the corresponding weights, and then perform weighted calculations based on the weights to achieve the function of car insurance risk assessment. It should be noted that the target machine learning model can select common machine learning models, such as deep learning models, reinforcement learning models, and linear regression analysis models.

[0093] In some embodiments, it should be noted that nodes other than the auto insurance safety calculation node do not have the authority to start the target machine learning model, nor can they perform operations such as model training on the target machine learning model. The beneficial effect of this embodiment is that, by means of authority control, it is ensured that only the auto insurance safety calculation node has the authority to start the target machine learning model, which can prevent the basic risk information of the vehicle and the target owner's consumption characteristic information from being leaked during the process of the target machine learning model performing auto insurance risk assessment on the basic risk information of the vehicle and the target owner's consumption characteristic information, thereby improving the security of auto insurance risk assessment.

[0094] In some embodiments, in the application scenario of financial technology, after the auto insurance risk assessment is performed, the auto insurance risk assessment data of the target car owner can be obtained, so as to perform auto insurance pricing, provide reference information when settling claims, and recommend auto insurance related insurance products based on the auto insurance risk assessment data. For example, the auto insurance price of the target car owner can be adjusted according to the auto insurance risk assessment data to achieve auto insurance pricing. When the auto insurance risk assessment data is greater than or equal to the preset risk threshold, the auto insurance price is increased; when the auto insurance risk assessment data is less than the risk threshold, the auto insurance price is reduced. In another embodiment, the claim settlement conditions of the auto insurance can be adjusted according to the auto insurance risk assessment data. In another embodiment, when the auto insurance risk assessment data is greater than the preset risk discount threshold, information about auto insurance products with premium discounts can also be sent to the target car owner. It can be seen that the embodiment of the present application can perform personalized and targeted auto insurance risk assessments based on different target car owner vehicle consumption characteristic information, thereby improving the flexibility and accuracy of auto insurance pricing. In addition, the consumption information of the target car owner is processed on a node different from the auto insurance safety calculation node (i.e., the consumption safety calculation node) to generate the consumption characteristic information of the target car owner, and then the consumption characteristic information of the target car owner is sent to the auto insurance safety calculation node so that the auto insurance safety calculation node can perform auto insurance risk assessment. The above two nodes jointly realize auto insurance pricing, greatly reduce the risk of data leakage, and improve the data security of auto insurance risk assessment.

[0095] See also Figure 2In some embodiments, step 104 may include but is not limited to steps 201 to 202:

[0096] Step 201, extracting consumption characteristics of the target car owner's consumption information through the consumption security computing node to obtain the target car owner's consumption characteristic information;

[0097] Step 202, encrypt the target car owner's consumption characteristic information by using a preset information encryption algorithm through the consumption safety computing node to obtain the target car owner's consumption characteristic information in an encrypted state; wherein the car insurance safety computing node supports the information encryption algorithm.

[0098] The advantage of this embodiment is that consumption characteristics of the target car owner's consumption information are extracted through the consumption safety computing node to obtain the target car owner's consumption characteristic information, and the target car owner's consumption characteristic information is encrypted by the consumption safety computing node using a preset information encryption algorithm to obtain the encrypted target car owner's consumption characteristic information, thereby improving the security of the auto insurance risk assessment.

[0099] It should be noted that the information encryption algorithm is an algorithm supported by the auto insurance safety computing node to ensure that the target car owner's consumption characteristic information can be calculated normally on both the auto insurance safety computing node and the consumption safety computing node.

[0100] In step 201 of some embodiments, the target car owner's consumption characteristic information may include at least one of a credit score and a payment ability score. It should be noted that the target car owner's consumption characteristic information is used to characterize the target car owner's consumption ability. Among them, the credit score is used to characterize the target car owner's credit risk and can reflect the possibility of the target car owner repaying the debt. The payment ability score is used to characterize the association between the target car owner's assets and historical expenditures.

[0101] In step 202 of some embodiments, the information encryption algorithm may be a common information encryption algorithm, such as an RSA encryption algorithm, an ECC (elliptic curve cryptography) encryption algorithm, and an ElGamal encryption algorithm.

[0102] See also Figure 3 In some embodiments, the target vehicle owner's consumption characteristic information includes vehicle consumption frequency characteristic information. Step 201 may include but is not limited to steps 301 to 303:

[0103] Step 301, classify the consumption information of the target car owner to obtain candidate consumption categories;

[0104] Step 302, filtering the target vehicle owner's consumption information according to the preset reference vehicle consumption category and the candidate consumption category to obtain vehicle consumption information; wherein the reference vehicle consumption category represents the consumption category associated with the vehicle;

[0105] Step 303 , analyzing the vehicle consumption ratio based on the vehicle consumption information and the target vehicle owner consumption information to obtain vehicle consumption frequency characteristic information.

[0106] The advantage of this embodiment is that after classifying the target car owner's consumption information to obtain candidate consumption categories, the target car owner's consumption information is screened according to the preset reference vehicle consumption categories and the candidate consumption categories to obtain vehicle consumption information, and the vehicle consumption proportion is analyzed based on the vehicle consumption information and the target car owner's consumption information to obtain vehicle consumption frequency feature information, and the vehicle consumption information associated with the vehicle can be screened out from the target car owner's consumption information, thereby realizing feature extraction of the target car owner's consumption information, and then the vehicle consumption frequency feature information after feature extraction is sent to the motor vehicle insurance security calculation node, thereby improving the data security of motor vehicle insurance risk assessment and avoiding data leakage.

[0107] In step 301 of some embodiments, the consumption categories of the target vehicle owner's consumption information may be classified to obtain candidate consumption categories. The candidate consumption categories may be consumption categories of the target vehicle owner's consumption information. Specifically, the candidate consumption categories include at least one of the following categories: daily necessities category, medical category, entertainment category, and initial vehicle consumption category. The initial vehicle consumption category may be a category that is the same as or associated with the reference vehicle consumption category.

[0108] In step 302 of some embodiments, the reference vehicle consumption categories may include vehicle appliance categories (such as tires), vehicle maintenance and repair categories (such as car washing, generator repair), etc.

[0109] In step 303 of some embodiments, the vehicle consumption frequency characteristic information can be used to characterize the proportion of vehicle consumption information in the target vehicle owner's consumption information. Specifically, the greater the proportion of vehicle consumption information in the target vehicle owner's consumption information, the greater the value of the vehicle consumption frequency characteristic information. When the vehicle consumption frequency characteristic information is greater than a preset vehicle consumption frequency threshold, it indicates that the target vehicle owner has a strong purchasing power in terms of vehicles, and the target vehicle owner's auto insurance risk assessment data characterizes a low risk. Specifically, the vehicle consumption frequency characteristic information can be 20 times per month.

[0110] See also Figure 4 In some embodiments, the vehicle insurance risk assessment of the basic risk information of the vehicle and the consumption characteristic information of the target vehicle owner by the target machine learning model in step 106 may include but is not limited to steps 401 to 404:

[0111] Step 401, using a target machine learning model to perform overall information calculation on the basic risk information of the vehicle and the consumption characteristic information of the target vehicle owner to obtain the overall risk information of the target vehicle;

[0112] Step 402, calculating the information ratio of the basic risk information of the vehicle and the overall risk information of the target vehicle through the target machine learning model to obtain the basic risk factor of the target vehicle;

[0113] Step 403, calculating the information ratio of the target vehicle owner's consumption characteristic information and the target vehicle's overall risk information through the target machine learning model to obtain the target vehicle consumption risk factor;

[0114] Step 404, determining the auto insurance risk assessment data according to the target vehicle basic risk factor and the target vehicle consumption risk factor.

[0115] The advantage of this embodiment is that, through the target machine learning model, the basic risk information of the vehicle and the consumption characteristic information of the target owner are calculated as a whole to obtain the overall risk information of the target vehicle, and then the basic risk information of the vehicle and the overall risk information of the target vehicle are calculated as a proportion to obtain the basic risk factor of the target vehicle; the consumption characteristic information of the target owner and the overall risk information of the target vehicle are calculated as a proportion to obtain the consumption risk factor of the target vehicle; the motor vehicle insurance risk assessment data is determined based on the basic risk factor of the target vehicle and the consumption risk factor of the target vehicle, thereby improving the accuracy of the motor vehicle insurance risk assessment.

[0116] In step 401 of some embodiments, the overall risk information of the target vehicle may include basic risk information of the vehicle and consumption characteristic information of the target owner. For example, the overall risk information of the target vehicle may be a queue, and the elements in the queue are the basic risk information of the vehicle and the consumption characteristic information of the target owner. In another embodiment, the basic risk information of the vehicle and the consumption characteristic information of the target owner may be integrated to obtain the overall risk information of the target vehicle, which is not limited in the embodiments of the present application.

[0117] In step 402 of some embodiments, the target vehicle basic risk factor is used to characterize the weight of the vehicle basic risk information, that is, the proportion of the vehicle basic risk information in the overall risk information of the target vehicle.

[0118] In step 403 of some embodiments, the target vehicle consumption risk factor is used to characterize the weight of the target vehicle owner's consumption characteristic information, that is, the proportion of the target vehicle owner's consumption characteristic information in the overall risk information of the target vehicle.

[0119] It should be noted that the value range of the target vehicle basic risk factor and the target vehicle consumption risk factor is [0, 1]. In some embodiments, the sum of the target vehicle basic risk factor and the target vehicle consumption risk factor is 1.

[0120] In step 404 of some embodiments, the auto insurance risk assessment data may be determined by weighted summation.

[0121] See also Figure 5 In some embodiments, after step 106, the auto insurance risk assessment method may also include but is not limited to steps 501 to 503:

[0122] Step 501, performing a first pricing process on a target vehicle basic risk factor and vehicle basic risk information through a vehicle insurance safety calculation node to obtain a first vehicle insurance pricing;

[0123] Step 502, performing a second pricing process on the target vehicle consumption risk factor and the target vehicle owner consumption characteristic information through the vehicle insurance safety calculation node to obtain a second vehicle insurance pricing;

[0124] Step 503: Perform joint pricing processing on the first auto insurance pricing and the second auto insurance pricing through the auto insurance safety calculation node to obtain target auto insurance price data.

[0125] The advantage of this embodiment is that, through the auto insurance safety calculation node, the first auto insurance pricing is determined according to the target vehicle basic risk factor and the vehicle basic risk information, and the second auto insurance pricing is determined according to the target vehicle consumption risk factor and the target vehicle owner consumption characteristic information, and then the first auto insurance pricing and the second auto insurance pricing are jointly priced to obtain the target auto insurance price data, thereby realizing auto insurance pricing and improving the accuracy of auto insurance pricing.

[0126] In step 501 of some embodiments, a first pricing process is performed on the target vehicle basic risk factor and the vehicle basic risk information, which may be to multiply the target vehicle basic risk factor and the vehicle basic risk information.

[0127] In step 502 of some embodiments, a second pricing process is performed on the target vehicle consumption risk factor and the target vehicle owner consumption characteristic information, which may be to multiply the target vehicle consumption risk factor and the target vehicle owner consumption characteristic information.

[0128] In step 503 of some embodiments, the first auto insurance pricing and the second auto insurance pricing are jointly priced, which can be performed by summing the first auto insurance pricing, the second auto insurance pricing and a preset offset factor through a linear model. The offset factor is the offset factor of the linear model of the auto insurance safety calculation node. It should be noted that in some embodiments, the target auto insurance price data is the auto insurance price obtained after the target car owner performs operations such as auto insurance purchase or auto insurance price inquiry.

[0129] See also Figure 6In some embodiments, the target car owner's consumption characteristic information is encrypted information, and the target car owner's consumption characteristic information is encrypted by the consumer security computing node using a preset target private key and a homomorphic encryption algorithm. After step 503, the auto insurance risk assessment method may also include but is not limited to steps 601 to 602:

[0130] Step 601, decrypting the target auto insurance price data by using the homomorphic encryption algorithm and the target public key through the auto insurance security computing node to obtain the decrypted target auto insurance price data; wherein the target public key corresponds to the target private key;

[0131] Step 602: Send the decrypted target auto insurance price data to the target vehicle owner corresponding to the target vehicle through the auto insurance security computing node.

[0132] The advantage of this embodiment is that the consumption security computing node homomorphically encrypts the consumption characteristic information of the target car owner through a homomorphic encryption algorithm, and the homomorphic encryption algorithm ensures that the auto insurance security computing node can operate on the encrypted consumption characteristic information of the target car owner to obtain the target auto insurance price data; then, the auto insurance security computing node decrypts the target auto insurance price data, thereby further improving the data security of the auto insurance risk assessment.

[0133] In step 601 of some embodiments, the homomorphic encryption algorithm may be an algorithm pre-set in the vehicle insurance safety computing node, and the vehicle insurance safety computing node may be able to support the operation of the algorithm.

[0134] In step 602 of some embodiments, the target car owner does not have the authority to directly access the auto insurance safety calculation node. The auto insurance safety calculation node needs to send the decrypted target auto insurance price data to the intermediate node (such as the auto insurance risk assessment business end and the auto insurance risk assessment client), and then the intermediate node forwards the target auto insurance price data to the target car owner.

[0135] See also Figure 7 In some embodiments, the target vehicle is a vehicle of a target vehicle owner using a vehicle insurance risk assessment client. After step 503, the vehicle insurance risk assessment method may also include but is not limited to steps 701 to 702:

[0136] Step 701, in response to a target pricing query request sent by the auto insurance risk assessment business end, sending a target auto insurance price to the auto insurance risk assessment business end through the auto insurance safety calculation node; wherein the target pricing query request is generated based on an initial pricing query request sent by the auto insurance risk assessment client;

[0137] Step 702: Send the target auto insurance price data to the auto insurance risk assessment client through the auto insurance risk assessment business terminal; wherein the auto insurance risk assessment client does not have the authority to access the auto insurance security computing node.

[0138] The advantage of this embodiment is that the auto insurance risk assessment client does not have the authority to access the auto insurance safety calculation node, thereby ensuring the security of information in the auto insurance safety calculation node (such as vehicle basic risk information and target car owner consumption characteristic information) and improving the data security of auto insurance risk assessment.

[0139] It should be noted that there may be multiple auto insurance risk assessment clients. For example, there may be a large number of auto insurance risk assessment clients, each of which needs to obtain target auto insurance price data, and these auto insurance risk assessment clients have different IP addresses. If the auto insurance risk assessment client can directly access the auto insurance safety computing node, then the auto insurance safety computing node needs to allow access by nodes or terminals with multiple different IP addresses. In this case, it is difficult to accurately determine whether each terminal is authorized, resulting in unauthorized terminals possibly attacking the auto insurance safety computing node to obtain the above data in the auto insurance safety computing node, causing data leakage. Taking this situation into account, the auto insurance safety computing node of the embodiment of the present application does not grant access rights to the auto insurance risk assessment client, but instead transfers information through the auto insurance risk assessment business end, thereby sending the target auto insurance price data to the auto insurance risk assessment client, thereby improving the data security of the auto insurance risk assessment.

[0140] In step 701 of some embodiments, the target car owner uses a car insurance risk assessment client, and the target car owner can send a target pricing inquiry request to the car insurance risk assessment service end through the car insurance risk assessment client.

[0141] In step 702 of some embodiments, the auto insurance risk assessment business end may be a terminal or server with a graphical user interface, thereby realizing visualization of target auto insurance pricing results and improving the convenience for target car owners to obtain target auto insurance price data.

[0142] It should be noted that the non-Company software tools or components appearing in the embodiments of the present application are merely examples and do not represent actual use.

[0143] See also Figure 8 The embodiment of the present application also provides an artificial intelligence-based vehicle insurance risk assessment device, which can implement the above-mentioned artificial intelligence-based vehicle insurance risk assessment method, and the device includes:

[0144] The basic risk information acquisition module 801 is used to acquire the basic vehicle risk information of the target vehicle through the vehicle insurance safety calculation node; wherein the basic vehicle risk information is encrypted information;

[0145] The request generation module 802 is used to generate a request for obtaining the vehicle owner's consumption information according to the target vehicle through the vehicle insurance safety computing node, and send the request for obtaining the vehicle owner's consumption information to the consumption safety computing node;

[0146] The consumption information module 803 is used to respond to the vehicle owner's consumption information acquisition request and acquire the target vehicle owner's consumption information through the consumption security computing node;

[0147] The characteristic information generating module 804 is used to generate the target vehicle owner's consumption characteristic information by using the target vehicle owner's consumption information through the consumption safety computing node;

[0148] The characteristic information sending module 805 is used to send the target car owner's consumption characteristic information to the car insurance safety computing node through the consumption safety computing node;

[0149] The risk assessment module 806 is used to start the target machine learning model through the auto insurance safety calculation node, and perform auto insurance risk assessment on the vehicle basic risk information and the target vehicle owner consumption characteristic information through the target machine learning model.

[0150] In some embodiments, the device further includes: a first vehicle insurance pricing module, configured to perform a first pricing process on the target vehicle basic risk factor and the vehicle basic risk information through the vehicle insurance safety calculation node to obtain a first vehicle insurance pricing;

[0151] A second auto insurance pricing module is used to perform a second pricing process on the target vehicle consumption risk factor and the target vehicle owner consumption characteristic information through the auto insurance safety calculation node to obtain a second auto insurance pricing;

[0152] The joint pricing module is used to perform joint pricing processing on the first auto insurance pricing and the second auto insurance pricing through the auto insurance safety calculation node to obtain target auto insurance price data.

[0153] In some embodiments, the device further includes: a decryption module, which is used to decrypt the target auto insurance price data by using a homomorphic encryption algorithm and a target public key through an auto insurance security computing node to obtain the decrypted target auto insurance price data; wherein the target public key corresponds to a target private key; wherein the target car owner consumption feature information is encrypted information, and the target car owner consumption feature information is encrypted by the consumption security computing node using a preset target private key and a homomorphic encryption algorithm;

[0154] The first price data sending module is used to send the decrypted target auto insurance price data to the target vehicle owner corresponding to the target vehicle through the auto insurance safety computing node.

[0155] In some embodiments, the apparatus further comprises: a request sending module, configured to respond to a target pricing inquiry request sent by the auto insurance risk assessment service end, and send the target auto insurance price to the auto insurance risk assessment service end through the auto insurance safety calculation node; wherein the target pricing inquiry request is generated based on an initial pricing inquiry request sent by the auto insurance risk assessment client;

[0156] The second price data sending module is used to send the target auto insurance price data to the auto insurance risk assessment client through the auto insurance risk assessment business terminal; wherein the auto insurance risk assessment client does not have the authority to access the auto insurance security computing node.

[0157] The specific implementation of the artificial intelligence-based vehicle insurance risk assessment device is basically the same as the specific implementation of the above-mentioned artificial intelligence-based vehicle insurance risk assessment method, and will not be repeated here.

[0158] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned auto insurance risk assessment method based on artificial intelligence when executing the computer program. The electronic device may include any intelligent terminal such as a tablet computer and a car computer.

[0159] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0160] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0161] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the vehicle insurance risk assessment method based on artificial intelligence in the embodiment of this application;

[0162] Input / output interface 903, used to implement information input and output;

[0163] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0164] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0165] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0166] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned artificial intelligence-based auto insurance risk assessment method is implemented.

[0167] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0168] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0169] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0170] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0171] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0172] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0173] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0174] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0175] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0177] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or 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 multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0178] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for assessing automobile insurance risk based on artificial intelligence, characterized in that: The method comprises: Obtaining basic vehicle risk information of the target vehicle through the vehicle insurance safety calculation node; wherein the basic vehicle risk information is encrypted information; Generate a request for obtaining the vehicle owner's consumption information according to the target vehicle through the vehicle insurance safety computing node, and send the request for obtaining the vehicle owner's consumption information to the consumption safety computing node; In response to the vehicle owner consumption information acquisition request, acquiring the target vehicle owner consumption information through the consumption security computing node; Generate target vehicle owner consumption feature information by using the target vehicle owner consumption information through the consumption safety computing node; Sending the target car owner's consumption feature information to the car insurance safety computing node through the consumption safety computing node; The target machine learning model is started through the auto insurance safety calculation node, and the auto insurance risk assessment is performed on the basic risk information of the vehicle and the consumption characteristic information of the target vehicle owner through the target machine learning model.

2. The method according to claim 1, characterized in that The performing auto insurance risk assessment on the basic risk information of the vehicle and the consumption characteristic information of the target vehicle owner by using the target machine learning model includes: Performing overall information calculation on the basic risk information of the vehicle and the consumption characteristic information of the target vehicle owner through the target machine learning model to obtain overall risk information of the target vehicle; Calculating the information ratio of the basic risk information of the vehicle and the overall risk information of the target vehicle through the target machine learning model to obtain a basic risk factor of the target vehicle; The target machine learning model is used to calculate the information ratio of the target vehicle owner's consumption characteristic information and the target vehicle's overall risk information to obtain a target vehicle consumption risk factor; The auto insurance risk assessment data is determined according to the target vehicle basic risk factor and the target vehicle consumption risk factor.

3. The method according to claim 2, characterized in that After the vehicle basic risk information and the target vehicle owner consumption characteristic information are evaluated for auto insurance risk by the target machine learning model, the method further includes: Performing a first pricing process on the target vehicle basic risk factor and the vehicle basic risk information through the vehicle insurance safety calculation node to obtain a first vehicle insurance pricing; Through the auto insurance safety calculation node, a second pricing process is performed on the target vehicle consumption risk factor and the target vehicle owner consumption characteristic information to obtain a second auto insurance pricing; The first auto insurance pricing and the second auto insurance pricing are jointly priced through the auto insurance safety calculation node to obtain target auto insurance price data.

4. The method according to any one of claims 1 to 3, characterized in that: The generating target vehicle owner consumption characteristic information by using the target vehicle owner consumption information through the consumption safety computing node includes: Extracting consumption characteristics from the consumption information of the target vehicle owner through the consumption safety computing node to obtain consumption characteristic information of the target vehicle owner; The consumption characteristic information of the target vehicle owner is encrypted by the consumption safety computing node using a preset information encryption algorithm to obtain the consumption characteristic information of the target vehicle owner in an encrypted state; wherein the vehicle insurance safety computing node supports the information encryption algorithm.

5. The method according to claim 4, characterized in that The target vehicle owner consumption characteristic information includes vehicle consumption frequency characteristic information; The extracting consumption characteristics of the target vehicle owner's consumption information through the consumption safety computing node to obtain the target vehicle owner's consumption characteristic information includes: Classifying the consumption information of the target vehicle owner to obtain candidate consumption categories; The target vehicle owner consumption information is screened according to a preset reference vehicle consumption category and the candidate consumption category to obtain vehicle consumption information; wherein the reference vehicle consumption category represents a consumption category associated with the vehicle; The vehicle consumption ratio analysis is performed based on the vehicle consumption information and the target vehicle owner consumption information to obtain the vehicle consumption frequency characteristic information.

6. The method according to claim 3, characterized in that The target car owner consumption characteristic information is encrypted information, and the target car owner consumption characteristic information is encrypted by the consumer security computing node using a preset target private key and a homomorphic encryption algorithm; After the first auto insurance pricing and the second auto insurance pricing are jointly priced by the auto insurance safety calculation node to obtain target auto insurance price data, the method further includes: Decrypting the target auto insurance price data by using the homomorphic encryption algorithm and the target public key through the auto insurance security computing node to obtain the decrypted target auto insurance price data; wherein the target public key corresponds to the target private key; The decrypted target vehicle insurance price data is sent to the target vehicle owner corresponding to the target vehicle through the vehicle insurance security calculation node.

7. The method according to claim 3, characterized in that The target vehicle is a vehicle of a target vehicle owner using the auto insurance risk assessment client; After the first auto insurance pricing and the second auto insurance pricing are jointly priced by the auto insurance safety calculation node to obtain target auto insurance price data, the method further includes: In response to a target pricing inquiry request sent by the auto insurance risk assessment service end, sending the target auto insurance price to the auto insurance risk assessment service end through the auto insurance safety calculation node; wherein the target pricing inquiry request is generated based on an initial pricing inquiry request sent by the auto insurance risk assessment client; The target auto insurance price data is sent to the auto insurance risk assessment client through the auto insurance risk assessment business end; wherein the auto insurance risk assessment client does not have permission to access the auto insurance safety computing node.

8. An artificial intelligence-based vehicle insurance risk assessment device, characterized in that: The device comprises: A basic risk information acquisition module is used to acquire the basic vehicle risk information of the target vehicle through the vehicle insurance safety calculation node; wherein the basic vehicle risk information is encrypted information; A request generation module, configured to generate a request for obtaining the vehicle owner's consumption information according to the target vehicle through the vehicle insurance safety computing node, and send the request for obtaining the vehicle owner's consumption information to the consumption safety computing node; A consumption information module, used to respond to the vehicle owner's consumption information acquisition request and acquire the target vehicle owner's consumption information through the consumption security computing node; A characteristic information generating module, used for generating target vehicle owner consumption characteristic information by using the target vehicle owner consumption information through the consumption safety computing node; A characteristic information sending module, used for sending the target car owner's consumption characteristic information to the car insurance safety computing node through the consumption safety computing node; The risk assessment module is used to start the target machine learning model through the vehicle insurance safety calculation node, and perform a vehicle insurance risk assessment on the vehicle basic risk information and the target vehicle owner consumption characteristic information through the target machine learning model.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the artificial intelligence-based auto insurance risk assessment method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the artificial intelligence-based auto insurance risk assessment method according to any one of claims 1 to 7 is implemented.

Images