Butt-joint insurance service full-process management method and device

Abstract

The invention relates to the technical field of digital data processing, in particular to a docking insurance business full-process management method and device, and the method comprises the steps: collecting customer personal information and vehicle insurance demand information; determining a first risk level of the customer based on the personal information and a rule matching model; matching an insurance product according to the first risk level and insurance demand information; generating a corresponding electronic contract after the insurance product is matched, and enabling the customer to pay and confirm; after the contract is signed, historical driving data of the customer is continuously obtained, and a second risk level is judged based on the historical driving data after the insurance policy renewal time is up; adjusting the renewal amount based on the second risk level to obtain an adjusted insurance policy; and sending the adjustment insurance policy to the client. Therefore, risk assessment and price assessment can be better carried out based on more accurate customer data, and the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital data processing, and particularly to a method and device for managing the entire process of docking insurance business. Background Art

[0002] The full-process management of insurance business covers starting from market research and product development, designing corresponding insurance products by deeply understanding customer needs; then conducting risk assessment and pricing, establishing a reasonable risk model to determine appropriate insurance rates; subsequently, promoting products to the market through multi-channel sales and distribution strategies; after receiving an insurance application, implementing an underwriting decision-making process according to established standards; when the insured makes a claim request, the claims settlement team is responsible for quickly and accurately handling compensation matters; at the same time, providing high-quality customer service and relationship maintenance to enhance customer satisfaction.

[0003] In the above process, customer data is generally collected only once at the time of signing, and the risk situation of the customer is judged based on the customer's claim records. The data collected and judged in this way is relatively single, and it is impossible to accurately judge the true risk situation of the customer, so a reasonable insurance premium cannot be given, reducing the work operation efficiency. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and device for managing the entire process of docking insurance business, aiming to better conduct risk assessment and price assessment based on more accurate customer data and improve work efficiency.

[0005] To achieve the above object, in a first aspect, the present invention provides a method for managing the entire process of docking insurance business, including collecting customer personal information and vehicle insurance demand information;

[0006] Determining the first risk level of the customer based on the personal information and the rule matching model;

[0007] Matching insurance products according to the first risk level and the insurance demand information;

[0008] Generating a corresponding electronic contract after matching the insurance product and asking the customer to pay and confirm;

[0009] Continuously obtaining the customer's historical driving data after signing the contract, and judging the second risk level based on the historical driving data when the policy renewal time arrives;

[0010] Adjusting the renewal amount based on the second risk level to obtain an adjusted policy;

[0011] Sending the adjusted policy to the customer.

[0012] Wherein, the specific steps of collecting the customer personal information and the vehicle insurance demand information include:

[0013] Obtain the customer's personal information, where the personal information includes name, contact information, address, driving record, vehicle model, and mileage.

[0014] Format the personal information and store it in a database.

[0015] Send a message update request to the customer at preset time intervals to update the personal information.

[0016] Among them, the specific steps for determining the customer's first risk level based on the personal information and the rule matching model include:

[0017] Set weight values for each item in the personal information.

[0018] Normalize the data of each item.

[0019] Calculate the first risk level according to the combination of the weight values of each item.

[0020] Among them, the specific steps for matching insurance products according to the first risk level and insurance demand information include:

[0021] Obtain existing insurance product information, where the insurance product information includes coverage and premium.

[0022] Set corresponding risk levels for each insurance product.

[0023] Match the customer's first risk level with the risk level of the insurance product to obtain the target insurance product.

[0024] Among them, the specific steps for generating a corresponding electronic contract and asking the customer to confirm the payment after matching the insurance product include:

[0025] Generate an electronic contract containing insurance terms.

[0026] Send the electronic contract to the customer by email and invite the customer to sign the electronic contract through electronic signature technology.

[0027] Provide a payment success notice to the customer after receiving the payment.

[0028] Among them, the specific steps for continuously obtaining the customer's historical driving data after signing the contract and judging the second risk level based on the historical driving data after the policy renewal time arrives include:

[0029] Connect to the vehicle-mounted positioning structure port of the customer to collect positioning data.

[0030] Remove the incorrect data points in the positioning data.

[0031] Format the positioning data to obtain the target data.

[0032] Using a convolutional neural network to generate an accident probability prediction model based on driving mileage, average speed, acceleration, night driving frequency, and geographical location in the target data;

[0033] Before the end of each insurance policy period, update the driving data within the most recent preset time period.

[0034] Among them, the specific steps of using the convolutional neural network to generate an accident probability prediction model based on driving mileage, average speed, acceleration, night driving frequency, and geographical location in the target data include:

[0035] Collect a historical driving data set, which also includes information on whether an accident has occurred;

[0036] Format the historical driving data and set the accident probability label corresponding to each record;

[0037] Train the convolutional network model based on the training set in the historical driving data set to obtain an accident probability prediction model.

[0038] Among them, the specific steps of adjusting the renewal amount based on the second risk level to obtain an adjusted insurance policy include:

[0039] Set a benchmark rate for each risk level based on historical data;

[0040] Match the corresponding target benchmark rate based on the second risk level;

[0041] Calculate the new premium according to the target benchmark rate.

[0042] In a second aspect, the present invention also provides a full-process management device for docking insurance business, including an information acquisition module, a first risk level calculation module, an insurance matching module, a transaction module, a second risk level calculation module, an adjustment module, and a sending module;

[0043] The information acquisition module is used to collect customer personal information and vehicle insurance demand information;

[0044] The first risk level calculation module is used to determine the first risk level of the customer based on personal information and a rule matching model;

[0045] The insurance matching module is used to match insurance products according to the first risk level and insurance demand information;

[0046] The transaction module is used to generate a corresponding electronic contract and let the customer pay and confirm after matching an insurance product;

[0047] The second risk level calculation module is configured to continuously obtain the customer's historical driving data after the contract is signed, and determine the second risk level based on the historical driving data after the policy renewal time arrives;

[0048] The adjustment module is configured to adjust the renewal amount based on the second risk level to obtain an adjusted policy;

[0049] The sending module is configured to send the adjusted policy to the customer.

[0050] A method and device for docking the entire process of insurance business of the present invention first requires comprehensively and accurately collecting the customer's personal information (such as age, gender, occupation, etc.) and their specific needs for vehicle insurance (such as the scope of protection desired, budget, etc.). This stage is the foundation of the entire process, ensuring that subsequent risk assessment and service matching can be based on true and reliable data. Using advanced data analysis techniques and rule matching models, determine the initial insurance risk level of each customer according to the information obtained in the first step. This step is crucial for understanding the unique situation of each customer and helps to provide a more personalized service plan for the customer.

[0051] Based on the customer's preliminary risk rating and their specific needs, screen out the most suitable product combination from the existing insurance product library and recommend it to the customer, and automatically generate an electronic contract containing all necessary terms for the customer to review. At the same time, provide an online payment option to facilitate the quick completion of the transaction process. Once the contract is signed and takes effect, the insurance company will collect the customer's relevant historical data such as driving behavior regularly or irregularly. These data may come from various channels such as vehicle networking devices and smartphone applications, and are used to more deeply understand the customer's actual usage situation.

[0052] When the policy renewal time point arrives, recalculate the customer's insurance risk level based on the latest accumulated historical driving records and other relevant information. This process helps to identify customers who exhibit good driving habits and have a low risk, so as to provide them with more favorable prices; at the same time, corresponding measures can be taken for high-risk users to reduce potential losses. According to the results of the second risk assessment, make appropriate adjustments to the fee part of the original policy terms to form a new policy plan. Subsequently, timely convey the latest quotation information and relevant change explanations to the customer through email, text message or a dedicated APP, etc., to ensure transparency and facilitate communication between the two parties. After the customer agrees to the new policy conditions, formally update the insurance agreement content under their account and charge the fees in accordance with the agreed method. Throughout the process, the insurance company is always committed to providing an efficient and convenient service experience, and continuously optimizing its own management system to adapt to the challenges brought by market changes and technological progress.

[0053] Through the above steps, not only can more accurate risk management for each policyholder be achieved, but also the user risk can be further evaluated by combining the behavioral data after the customer signs the contract to provide a more competitive insurance policy, thereby improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0055] Figure 1 It is a flowchart of a method for managing the entire process of docking insurance business of the present invention.

[0056] Figure 2 It is a flowchart of the present invention for collecting customer personal information and vehicle insurance demand information.

[0057] Figure 3 It is a flowchart of the present invention for determining the first risk level of a customer based on personal information and a rule matching model.

[0058] Figure 4 It is a flowchart of the present invention for matching insurance products according to the first risk level and insurance demand information.

[0059] Figure 5 It is a flowchart of the present invention for generating a corresponding electronic contract after matching the insurance product and asking the customer to pay and confirm.

[0060] Figure 6 It is a flowchart of the present invention for continuously obtaining the customer's historical driving data after signing the contract and judging the second risk level based on the historical driving data when the insurance policy renewal time arrives.

[0061] Figure 7 It is a flowchart of the present invention for generating an accident probability prediction model using a convolutional neural network based on the driving mileage, average speed, acceleration, night driving frequency, and geographical location in the target data.

[0062] Figure 8 It is a flowchart of the present invention for adjusting the renewal amount based on the second risk level to obtain an adjusted insurance policy. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where like or similar reference numerals denote like or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0064] First Embodiment

[0065] Please refer to Figures 1 to 8 , the present invention provides a full-process management method for docking insurance business, including:

[0066] S101 Collect customer personal information and vehicle insurance demand information;

[0067] The specific steps include:

[0068] S201 Obtain customer personal information, where the personal information includes name, contact information, address, driving record, vehicle model, and mileage;

[0069] Ask the customer about and record their basic information through online forms, telephone interviews, or face-to-face communication.

[0070] The name is used to identify the customer's identity. The contact information (phone number / email) facilitates subsequent communication.

[0071] The address is used to understand the customer's place of residence and helps to evaluate regional risk factors.

[0072] The driving record includes but is not limited to driver's license type, date of first obtaining the driver's license, and whether there are any violation records recently, which helps to judge driving habits.

[0073] The vehicle model is used to determine the specific vehicle type, and there may be different insurance terms for different types of cars.

[0074] The mileage is used as the annual driving distance affects the calculation of the insurance rate.

[0075] S202 Format the personal information and store it in the database;

[0076] Sort out the information collected according to the company's internal data management specifications and enter it into the designated data management system in a structured form. Ensure compliance with all applicable data protection laws and regulations, such as GDPR or other local privacy regulations, and take appropriate measures to protect personal privacy and security.

[0077] S203 Send an information update request to the customer at preset time intervals to update the personal information.

[0078] Set a reasonable period (such as once every six months or once a year), and invite customers to log in to the system to check and update their personal information via email, text message reminders, etc. Maintaining the timeliness and accuracy of information in the database is crucial for providing continuous high-quality customer service. It is also a great opportunity to strengthen the connection with customers and deepen mutual understanding through regular communication.

[0079] Throughout the process, it is important to ensure transparency, clearly inform customers why these information are needed and how they will be used, while also ensuring that the entire operation complies with the requirements of relevant laws and regulations. In addition, an effective mechanism should be established to handle any questions or concerns that customers may raise regarding the use of their personal information.

[0080] S102 Determine the first risk level of the customer based on personal information and the rule matching model;

[0081] The specific steps include:

[0082] S301 Set weight values for each item in the personal information;

[0083] According to historical data analysis, industry standards, and the company's internal experience, assign a specific weight value to each personal attribute related to insurance risk (such as driving record, vehicle model, etc.).

[0084] A driving record may be given a higher weight because good driving habits usually mean lower risk. Age is also an important factor; young drivers tend to have a higher accident rate, so they may have a different weight. By quantifying the importance of different factors, the final risk assessment becomes more scientific and reasonable.

[0085] S302 Normalize the data for each item;

[0086] Standardize the collected data to ensure they are in the same dimension for fair comparison during subsequent calculations. Data conversion can be achieved through methods such as min-max normalization, Z-score standardization, etc. This avoids the problem that some features may be over-amplified or ignored during the calculation due to large differences in the original data.

[0087] S303 Calculate the first risk level based on the combination of weight values for each item.

[0088] Combine the normalized data for each item and their corresponding weight values, and use weighted summation or other mathematical models to comprehensively evaluate the customer's insurance risk level.

[0089] Formula example: Assume that Wi represents the weight of the i-th item, and Xi′ represents the normalized value of this item. Then the total risk score R can be obtained in the following way:

[0090]

[0091] Based on the obtained risk score R, customers are classified into different risk levels, such as low risk, medium risk, high risk, etc.

[0092] S103 Match insurance products according to the first risk level and insurance demand information;

[0093] The specific steps include:

[0094] S401 Obtain existing insurance product information, where the insurance product information includes coverage and premium;

[0095] Collect and organize the detailed information of all existing insurance products of the company. The coverage includes, but is not limited to, different types of protection such as vehicle damage, third-party liability, theft, etc. The premium is based on different protection contents and service levels, and each insurance product will have different fee standards. Thus, a comprehensive and detailed insurance product database can be established to provide basic data support for the subsequent matching process.

[0096] S402 Set corresponding risk levels for each insurance product;

[0097] According to the design characteristics of the insurance product (such as coverage scope, deductible setting, etc.), assign one or more suitable risk levels to each insurance product.

[0098] For example, a basic auto insurance designed for low-risk customers may be marked as applicable to "low risk". A comprehensive insurance providing wider coverage and including high compensation amounts may be suitable for customers in the "medium to high risk" group. Expert review, historical data analysis, etc. can also be used to determine the applicable risk level of each product.

[0099] S403 Match the customer's first risk level with the risk level of the insurance product to obtain the target insurance product.

[0100] Use algorithms or manual review methods to compare the customer's first risk level with the risk levels of each insurance product, and find the most suitable insurance product combination. Specifically, first exclude those insurance products that are clearly not in line with the customer's risk level. For the remaining eligible products, further consider other specific needs of the customer (such as the additional services desired, budget constraints, etc.) for refined matching; finally, generate a list containing several optimal options for the customer to refer to and choose.

[0101] This process can be automated by building an intelligent recommendation system that can quickly process large amounts of data and continuously optimize the recommendation accuracy through machine learning.

[0102] S104 generates the corresponding electronic contract after matching the insurance product and asks the customer to pay and confirm.

[0103] The specific steps include:

[0104] S501 generates an electronic contract containing insurance terms.

[0105] Automatically generate a detailed electronic contract based on the matched insurance product information.

[0106] The basic information includes the names and contact information of the applicant and the insured, etc. The insurance terms list in detail the key terms such as the scope of insurance liability, deductible, compensation limit, etc. The premium and payment method clearly state the total premium amount and the recommended payment method (such as lump-sum payment or installment payment).

[0107] Ensure that all information is accurate and use clear and easy-to-understand language to describe complex terms to avoid understanding barriers caused by legal terms.

[0108] S502 sends the electronic contract to the customer via email and invites the customer to sign the electronic contract through electronic signature technology.

[0109] Use the email system to send the generated electronic contract to the customer's designated email address and attach instructions for electronic signature. Select a secure and reliable third-party electronic signature service provider, such as DocuSign or Adobe Sign, to ensure the security and legality of the signature process. Enclose a simple operation guide with the email to help the customer complete the electronic signature process smoothly.

[0110] Set up a reminder mechanism. If the customer does not complete the signature within a certain period of time, automatically send a reminder email or text message.

[0111] S503 provides a payment success notification to the customer after receiving the payment.

[0112] Once it is detected that the customer has successfully paid the premium, immediately send a payment success confirmation notice via email or text message, etc. The payment details include the payment date, payment amount, etc. The insurance policy number provides a unique insurance policy number for subsequent inquiries and services. The next steps inform the customer what to do next, such as waiting for the insurance company to review and receiving the official policy documents, etc.

[0113] S105 continuously obtains the customer's historical driving data after the contract is signed and judges the second risk level based on the historical driving data when the policy renewal time arrives.

[0114] The specific steps include:

[0115] S601 Connect to the in-vehicle positioning structure port of the customer to collect positioning data;

[0116] Execute the content to connect to the vehicle's built-in GPS or other positioning systems of the customer to ensure that the geographical location information of the vehicle can be obtained regularly or in real time.

[0117] S602 Remove the incorrect data points from the positioning data;

[0118] Use data cleaning techniques to remove invalid or abnormal data points, such as incorrect records caused by position drift due to signal loss, equipment failures, etc. Statistical methods (such as Z-score detection) or machine learning algorithms can be used to identify and eliminate outliers.

[0119] S603 Format the positioning data to obtain the target data;

[0120] Convert the cleaned original positioning data into a standard format suitable for further processing. The formatting process includes, but is not limited to, operations such as timestamp unification and coordinate standardization, ensuring that all data points are comparable.

[0121] S604 Use a convolutional neural network to generate an accident probability prediction model based on the driving mileage, average speed, acceleration, night driving frequency, and geographical location in the target data;

[0122] The specific steps include:

[0123] S701 Collect a historical driving data set, which also includes information on whether an accident has occurred;

[0124] Extract a large amount of historical data containing driving behavior characteristics from the database, and record the corresponding accident situations of these data. In addition to the internally accumulated data, data sharing with other insurance companies can also be considered to increase the sample size and diversity.

[0125] S702 Format the historical driving data and set the accident probability label corresponding to each record;

[0126] According to the accident information in the historical data, assign the corresponding accident probability label to each record for supervised learning.

[0127] Simple binary classification (with or without an accident) or more complex multi-level classification (accidents of different severities) can be used.

[0128] S703 Train the convolutional network model based on the training set in the historical driving data set to obtain an accident probability prediction model.

[0129] Use deep learning models such as convolutional neural networks (CNNs) to train on a large amount of labeled historical data to build a model that can predict the probability of future accidents. Training details include selecting appropriate network architectures, optimizers, loss functions, etc., and adjusting hyperparameters through methods such as cross-validation to improve the generalization ability of the model.

[0130] S605 Update the driving data within the most recent preset time period before the end of each insurance policy period.

[0131] When each insurance policy is about to expire, re-collect and analyze the customer's driving data over a recent period of time to reflect the latest changes in driving habits. Usually, data from the past year or half-year is selected as a reference, but it can be flexibly set according to business needs. Use the pre-trained accident probability prediction model, combine the latest data to calculate a new risk level, and provide a basis for the renewal decision.

[0132] S106 Adjust the renewal amount based on the second risk level to obtain an adjusted insurance policy;

[0133] The specific steps include:

[0134] S801 Set benchmark rates for each risk level based on historical data;

[0135] Use historical data and statistical analysis methods to set corresponding benchmark rates for different risk levels. Data sources include but are not limited to past claim records, accident rates, repair costs, etc.

[0136] Data analysis is carried out through statistical methods such as regression analysis and time series analysis to find the relationship between different risk levels and actual claims. Refer to the average rate level in the industry and combine the company's own historical data to determine the benchmark rates.

[0137] S802 Match the corresponding target benchmark rate based on the second risk level;

[0138] According to the benchmark rate table determined in the previous step, find the specific rate corresponding to the customer's current risk level.

[0139] First, clarify the customer's latest risk level. Look up the rate corresponding to this risk level in the benchmark rate table. Ensure that the benchmark rate table is up-to-date and has considered all possible factors affecting the rate.

[0140] S803 Calculate the new premium according to the target benchmark rate.

[0141] Use the matched target benchmark rate, combined with other relevant factors (such as vehicle model, insurance coverage, etc.), to calculate the new premium that the customer needs to pay when renewing the insurance.

[0142] Calculation formula:

[0143] New premium = Target benchmark rate × Insurance coverage coefficient × Other adjustment factors

[0144] The adjustment factors can include but are not limited to factors such as vehicle value, driver age, regional risk index, etc.

[0145] Promptly inform the customer of the calculated new premium, provide a detailed breakdown of the fees, and explain the basis for each fee.

[0146] S107 Send the adjusted policy to the customer.

[0147] Based on the new premium calculated in the previous step and the relevant terms, generate a detailed adjusted policy document.

[0148] The basic information in the document content includes the names, contact information, etc. of the applicant and the insured. The insurance terms detail key terms such as the scope of insurance liability, deductible amount, compensation limit, etc. The premium and payment method clearly state the amount of the new premium and the recommended payment method (such as one-time payment or installment payment). The renewal date indicates the start and end times of the validity period of the policy. Other important matters such as the conditions for terminating the contract, renewal policy, etc. Select a suitable communication channel (usually email, or it can also be text message, letter, etc.) to send the adjusted policy document to the customer.

[0149] Second Embodiment

[0150] The present invention also provides a device for the full-process management of docking insurance business, including an information acquisition module, a first risk level calculation module, an insurance matching module, a transaction module, a second risk level calculation module, an adjustment module, and a sending module; the information acquisition module is used to collect the customer's personal information and vehicle insurance demand information; the first risk level calculation module is used to determine the customer's first risk level based on the personal information and the rule matching model; the insurance matching module is used to match insurance products according to the first risk level and the insurance demand information; the transaction module is used to generate a corresponding electronic contract after matching the insurance product and let the customer make a payment confirmation; the second risk level calculation module is used to continuously obtain the customer's historical driving data after the contract is signed, and judge the second risk level based on the historical driving data when the policy renewal time arrives; the adjustment module is used to adjust the renewal amount based on the second risk level to obtain an adjusted policy; the sending module is used to send the adjusted policy to the customer.

[0151] In this embodiment, the information acquisition module collects the customer's personal information (such as age, gender, occupation, etc.) and their specific requirements for vehicle insurance (such as coverage scope, insurance amount, etc.). This information serves as the basis for all subsequent steps. The first risk level calculation module, based on the collected customer personal information and in combination with a preset risk assessment rule model, can determine an initial risk level for each customer. Such rating helps the insurance company to more accurately understand the potential risk level of each customer. The insurance matching module, according to the first risk level obtained in the first step and the specific requirements put forward by the customer, will select the most suitable several options from the existing insurance product library for the customer to choose. The aim is to ensure that the provided insurance plan meets the customer's needs and can reasonably control risks.

[0152] The transaction module generates the corresponding electronic contract text and guides the customer to complete the payment process to confirm the purchase. This step ensures the transparency and security of the whole process. The second risk level calculation module uses the customer's driving behavior data (such as mileage, violation records, etc.) accumulated during this period to re-evaluate the customer's latest risk situation. This can help the company to more dynamically adjust its service strategy. The adjustment module will make corresponding adjustments to the renewal premium based on the updated second risk level. If the customer has good driving habits, they may enjoy a lower price; vice versa. This way encourages safe driving while also ensuring the company's interests.

[0153] Finally, the adjusted policy details will be directly sent to the customer by means of email or text message, etc. This not only improves the communication efficiency but also enables the customer to timely understand their latest insurance status.

[0154] This management system greatly improves the work efficiency and service quality by automating most of the processes, and at the same time provides a more personalized and flexible service experience for customers.

[0155] What is disclosed above is only a preferred embodiment of the present invention. Of course, it cannot be used to limit the scope of the rights of the present invention. Those of ordinary skill in the art can understand the implementation of all or part of the above processes, and the equivalent changes made according to the claims of the present invention still fall within the scope covered by the invention.

Claims

1. A full-process management method for docking insurance business It is characterized in that it includes: collecting customers' personal information and vehicle insurance demand information; determining the first risk level of the customer based on the personal information and the rule matching model; matching insurance products according to the first risk level and the insurance demand information; generating a corresponding electronic contract after matching the insurance product and asking the customer to pay and confirm; continuously obtaining the customer's historical driving data after signing the contract, and judging the second risk level based on the historical driving data when the policy renewal time arrives; adjusting the renewal amount based on the second risk level to obtain an adjusted policy; sending the adjusted policy to the customer.

2. A full-process management method for docking insurance business according to claim 1, characterized in that the specific steps of collecting customers' personal information and vehicle insurance demand information include: obtaining customers' personal information, where the personal information includes name, contact information, address, driving record, vehicle model, and driving mileage; formatting the personal information and storing it in a database; sending an information update request to the customer at preset time intervals to update the personal information.

3. A full-process management method for docking insurance business according to claim 2, characterized in that the specific steps of determining the first risk level of the customer based on the personal information and the rule matching model include: setting weight values for each item in the personal information; normalizing the data of each item; calculating the first risk level according to the combination of the weight values of each item.

4. A full-process management method for docking insurance business according to claim 3, characterized in that the specific steps of matching insurance products according to the first risk level and the insurance demand information include: obtaining existing insurance product information, where the insurance product information includes coverage and premium; setting corresponding risk levels for each insurance product; matching the first risk level of the customer and the risk level of the insurance product to obtain the target insurance product.

5. A full-process management method for docking insurance business according to claim 4, characterized in that the specific steps of generating a corresponding electronic contract after matching the insurance product and asking the customer to pay and confirm include: generating an electronic contract containing insurance terms; sending the electronic contract to the customer by email and inviting the customer to sign the electronic contract through electronic signature technology; providing a payment success notice to the customer after receiving the payment.

6. A full-process management method for docking insurance business according to claim 5, characterized in that the specific steps of continuously obtaining the customer's historical driving data after signing the contract and judging the second risk level based on the historical driving data when the policy renewal time arrives include: docking with the vehicle-mounted positioning structure port of the customer to collect positioning data; removing the error data points in the positioning data; formatting the positioning data to obtain target data; using a convolutional neural network to generate an accident probability prediction model based on the driving mileage, average speed, acceleration, night driving frequency, and geographical location in the target data; updating the driving data in the most recent preset time period before the end of each policy period.

7. A full-process management method for docking insurance business according to claim 6, characterized in that The specific steps of generating an accident probability prediction model based on the driving mileage, average speed, acceleration, night driving frequency, and geographical location in the target data using a convolutional neural network are as follows: Collect a historical driving data set, which also includes information on whether an accident has occurred; Format the historical driving data and set the accident probability label corresponding to each record; Train the convolutional network model based on the training set in the historical driving data set to obtain an accident probability prediction model.

8. The full-process management method for docking insurance services according to claim 7, wherein The specific steps of adjusting the renewal amount based on the second risk level to obtain an adjusted insurance policy are as follows: Set a benchmark rate for each risk level based on historical data; Match the corresponding target benchmark rate based on the second risk level; Calculate the new premium according to the target benchmark rate.

9. A full-process management device for docking insurance services, which adopts the full-process management method for docking insurance services according to any one of claims 1 to 8, wherein It includes an information acquisition module, a first risk level calculation module, an insurance matching module, a transaction module, a second risk level calculation module, an adjustment module, and a sending module; The information acquisition module is used to collect customer personal information and vehicle insurance demand information; The first risk level calculation module is used to determine the first risk level of the customer based on personal information and a rule matching model; The insurance matching module is used to match insurance products according to the first risk level and insurance demand information; The transaction module is used to generate a corresponding electronic contract and let the customer pay and confirm after an insurance product is matched; The second risk level calculation module is used to continuously obtain the customer's historical driving data after the contract is signed, and judge the second risk level based on the historical driving data when the insurance policy renewal time arrives; The adjustment module is used to adjust the renewal amount based on the second risk level to obtain an adjusted insurance policy; The sending module is used to send the adjusted insurance policy to the customer.

Images