Insurance method, device, system, equipment, medium, product and chip
By acquiring underwriting and quotation data from auto insurance policies and using predictive models to forecast insurance outcomes, the problem of unknown results in online insurance applications has been solved, thereby improving the success rate and efficiency of insurance applications.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING XIAOMI PAYMENT TECH CO LTD
- Filing Date
- 2024-12-20
- Publication Date
- 2026-06-23
Smart Images
Figure CN122264951A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of insurance application technology, and in particular to an insurance application method, apparatus, system, equipment, medium, product and chip. Background Technology
[0002] By purchasing car insurance, car owners can transfer the economic risks arising from natural disasters, traffic accidents, etc., to insurance companies, thereby receiving corresponding compensation when losses occur and reducing their financial burden.
[0003] In related technologies, when purchasing car insurance online, users can only find out whether the application was successful or not after submitting the application. If the online application fails, the user needs to continuously adjust the application information and submit the application again until the application is successful, resulting in a low success rate. Summary of the Invention
[0004] This disclosure aims to at least partially address one of the technical problems in the related art.
[0005] The first aspect of this disclosure provides a method for insurance application, including:
[0006] Obtain the insurance policy to be insured, wherein the insurance policy to be insured includes at least one of underwriting data and quotation data, wherein the underwriting data is used to determine the underwriting result corresponding to the insurance policy to be insured, and the quotation data is used to determine the quotation result corresponding to the insurance policy to be insured;
[0007] Determine the predicted insurance application result corresponding to the policy to be insured, wherein the predicted insurance application result is used to characterize the predicted result of using the policy to be insured for insurance purposes;
[0008] Output the predicted insurance results.
[0009] A second aspect of this disclosure provides an insurance underwriting device, comprising:
[0010] The acquisition module is used to acquire insurance policies to be insured, wherein the insurance policies to be insured include at least one of underwriting data and quotation data, wherein the underwriting data is used to determine the underwriting result corresponding to the insurance policies to be insured, and the quotation data is used to determine the quotation result corresponding to the insurance policies to be insured;
[0011] The determining module is used to determine the predicted insurance result corresponding to the policy to be insured, and the predicted insurance result is used to characterize the predicted result of using the policy to be insured for insurance purposes;
[0012] The output module is used to output the predicted insurance result.
[0013] A third aspect of this disclosure provides an insurance underwriting system, comprising:
[0014] The processing module is used to obtain the insurance policy to be insured, determine the predicted insurance result corresponding to the insurance policy to be insured, and output the predicted insurance result to the application module. The insurance policy to be insured includes at least one of underwriting data and quotation data. The underwriting data is used to determine the underwriting result corresponding to the insurance policy to be insured, and the quotation data is used to determine the quotation result corresponding to the insurance policy to be insured. The predicted insurance result is used to characterize the predicted result of using the insurance policy to be insured for insurance purposes.
[0015] The application module is used to output the predicted insurance results to the user.
[0016] A fourth aspect of this disclosure provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the insurance application method as proposed in the first aspect of this disclosure.
[0017] The fifth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the insurance underwriting method as proposed in the first aspect of this disclosure.
[0018] A sixth aspect of this disclosure provides a computer program product including computer instructions that, when executed by a processor, implement the steps of the insurance underwriting method as described in the first aspect.
[0019] A seventh aspect of this disclosure provides a chip including processing circuitry configured to perform the insurance underwriting method proposed in the first aspect.
[0020] The insurance application methods, devices, systems, equipment, media, products, and chips disclosed herein have the following beneficial effects:
[0021] In this embodiment, the insurance policy to be insured is obtained, the predicted insurance result corresponding to the policy is determined, and finally the predicted insurance result is output. Therefore, the insurance result of the policy to be insured can be predicted before the user submits the insurance application, and the predicted result can be displayed to the user. This allows the user to know whether the insurance application will be successful before submitting the application, and further, if the predicted result indicates failure, the user can modify the insurance information, thereby improving the success rate of the insurance application.
[0022] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description
[0023] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:
[0024] Figure 1 This is a schematic flowchart illustrating an insurance underwriting method provided in an embodiment of the present disclosure.
[0025] Figure 2 A flowchart illustrating an insurance underwriting method provided in another embodiment of this disclosure;
[0026] Figure 3 A flowchart illustrating an insurance underwriting method provided in another embodiment of this disclosure;
[0027] Figure 4 This is a schematic diagram of the structure of an insurance application device provided in an embodiment of the present disclosure;
[0028] Figure 5 This is a schematic diagram of the structure of an insurance underwriting system provided in an embodiment of the present disclosure;
[0029] Figure 6 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown;
[0030] Figure 7 This is a schematic diagram of the structure of a chip proposed in an embodiment of this disclosure. Detailed Implementation
[0031] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.
[0032] The following description, with reference to the accompanying drawings, describes an insurance application method, apparatus, system, device, medium, product, and chip according to embodiments of the present disclosure.
[0033] Figure 1 This is a schematic flowchart illustrating an insurance underwriting method provided in an embodiment of this disclosure.
[0034] It should be noted that the insurance application method of this embodiment can be applied to an insurance application device. In some possible embodiments, the device can be configured in an electronic device or chip so that the electronic device or chip can perform the insurance application function.
[0035] like Figure 1 As shown, this insurance application method may include the following steps:
[0036] Step 101: Obtain the insurance policy to be purchased.
[0037] The insurance policy to be insured can be an insurance policy that the user has already filled out online and is ready to submit an application for. Insurance policies include, but are not limited to, auto insurance policies and life insurance policies. In this embodiment, an auto insurance policy is used as an example to describe the method provided in this disclosure.
[0038] The policy to be insured includes at least one of underwriting data and quotation data. The underwriting data is used to determine the underwriting result of the policy to be insured, and the quotation data is used to determine the quotation result of the policy to be insured.
[0039] In some embodiments, underwriting data and quotation data may partially overlap. For example, underwriting data may include information such as the insurance application date, appointment scheduling date, policy issuance method, vehicle sales order number, insurance company, insurance company location, vehicle delivery center, agency, vehicle model, vehicle price, vehicle purpose, and type of insurance. Quotation data may include information such as the insurance application date, appointment scheduling date, insurance package, whether a service package is purchased, insured's age, whether the vehicle's specifications match the insured's, vehicle sales order number, insurance company, insurance company location, vehicle delivery center, agency, vehicle model, vehicle price, vehicle purpose, and type of insurance.
[0040] In some embodiments, in response to the completion of the insurance application information, a policy to be applied for is obtained. Thus, without any user intervention, a policy to be applied for can be obtained, allowing for prediction of the policy's application outcome.
[0041] The insurance information may include the insurance application date, appointment scheduling date, insurance package, whether a service package has been purchased, the insured's age, whether the indicators match the insured, vehicle sales order number, insurance company, location of the insurance company, vehicle delivery center, agency, vehicle model, vehicle price, vehicle purpose, type of insurance, and policy issuance method, etc. This disclosure does not limit these details.
[0042] In some embodiments, in response to receiving a policy prediction instruction, the policy to be insured is obtained. Thus, the user can choose whether or not to have the outcome of the policy predicted.
[0043] In some embodiments, a pre-insurance policy prediction instruction is determined to have been received in response to a prediction control in the display interface being touched. The prediction control can be a control in the display interface used to trigger a prediction of the underwriting outcome of the policy to be insured.
[0044] In some embodiments, a prediction instruction may be determined to have been received upon receiving a voice message from a user instructing the prediction of the insurance outcome of the policy to be applied for.
[0045] Step 102: Determine the predicted insurance result corresponding to the policy to be insured. The predicted insurance result is used to characterize the predicted result of using the policy to be insured for insurance purposes.
[0046] In some embodiments, the policy to be insured can be input into an insurance outcome prediction model to obtain a predicted insurance outcome. The insurance outcome prediction model can be pre-trained.
[0047] In some embodiments, predicting the insurance application outcome can include successful or unsuccessful application; that is, the insurance application outcome prediction model can predict whether the application outcome of the policy to be applied for will be successful or unsuccessful. If the insurance application outcome prediction model can predict whether the application outcome of the policy to be applied for will be successful or unsuccessful, then the training data for the insurance application outcome prediction model can be successfully applied-for policies and their associated successful application labels, and unsuccessfully applied-for policies and their associated unsuccessful application labels.
[0048] In some embodiments, predicting the insurance application outcome can include the reasons for successful or unsuccessful application; that is, the insurance application outcome prediction model can predict whether the application outcome of the policy to be applied for will be successful or unsuccessful. If the insurance application outcome prediction model can predict whether the application outcome of the policy to be applied for will be successful or unsuccessful, then the training data for the insurance application outcome prediction model can be successfully applied-for policies and their associated successful application labels, and unsuccessfully applied-for policies and their associated unsuccessful application reason labels.
[0049] The reasons for insurance failure can include duplicate insurance, inability to insure vehicle damage insurance, inability to insure third-party liability insurance, etc. This disclosure does not specify any limitations.
[0050] In some embodiments, the structure of the insurance outcome prediction model can be Text Convolutional Neural Networks (TextCNN), decision tree model, Support Vector Machine (SVM), etc. This disclosure does not limit it.
[0051] In some embodiments, the insurance application outcome prediction model can also predict the underwriting outcome corresponding to the underwriting data and the quotation outcome corresponding to the quotation data, and then determine the predicted insurance application outcome based on the underwriting outcome and the quotation outcome. This includes: determining the predicted insurance application outcome as successful if both the underwriting outcome and the quotation outcome indicate success; or determining the predicted insurance application outcome as unsuccessful if the underwriting outcome and / or the quotation outcome indicate failure; or determining the reason for failure corresponding to the underwriting outcome and / or the quotation outcome as the predicted insurance application outcome if the underwriting outcome and / or the quotation outcome indicate a reason for failure.
[0052] Step 103: Output the predicted insurance results.
[0053] In some embodiments, the predicted insurance application result can be displayed as a floating window on the current insurance application interface. Alternatively, the predicted insurance application result can be output via voice prompts. Alternatively, the predicted insurance application result can be output via customer service hotline. This disclosure does not specifically limit the display format of the predicted insurance application result on the display interface.
[0054] In some embodiments, if the predicted insurance application result is either successful or unsuccessful, the predicted insurance application result is output. This can remind the user whether the current insurance application information is sufficient for successful application. If the predicted insurance application result is unsuccessful, the user can adjust the insurance application information until the predicted insurance application result is successful before submitting the application, thereby improving the success rate of insurance application.
[0055] In some embodiments, if the predicted insurance application result is either successful or due to reasons for failure, the predicted insurance application result is output. If the predicted result is successful, the user is reminded that the insurance application can be successful based on the current insurance information, so the user can directly submit the application. If the predicted result is due to reasons for failure, the user is reminded of the reasons for failure based on the current insurance information, so the user can adjust the policy to be applied for according to the reasons for failure, and submit the application after the predicted result is successful. This can not only improve the success rate of insurance applications, but also improve the efficiency of insurance applications.
[0056] In some embodiments, if the predicted insurance application result is successful, a prompt may be displayed to ask the user whether to submit the policy to be applied for. Upon receiving the user's submission instruction, the policy to be applied for is submitted. The prompt may be displayed in the form of a pop-up window. This disclosure does not limit this. Therefore, if the predicted insurance application result is successful, the user may be prompted to submit the policy to be applied for.
[0057] In some embodiments, if the predicted insurance application result is successful, the user can be redirected to the policy submission page to decide whether to submit the policy.
[0058] In this embodiment, the insurance policy to be insured is obtained, the predicted insurance result corresponding to the policy is determined, and finally the predicted insurance result is output. Therefore, the insurance result of the policy to be insured can be predicted before the user submits the insurance application, and the predicted result can be output to the user. This allows the user to know whether the insurance application will be successful before submitting the application, and thus, if the predicted result indicates failure, the user can modify the insurance information, improving the success rate of the insurance application.
[0059] Figure 2This is a flowchart illustrating an insurance underwriting method provided in one embodiment of the present disclosure, as shown below. Figure 2 As shown, this insurance application method may include the following steps:
[0060] Step 201: Obtain the insurance policy to be purchased.
[0061] The specific implementation of this step can be found in the detailed description of the relevant steps in other embodiments of this disclosure, for example, the implementation of step 101, which will not be described in detail here.
[0062] Step 202: Determine the predicted insurance result corresponding to the policy to be insured. The predicted insurance result is used to characterize the predicted result of using the policy to be insured for insurance purposes.
[0063] The specific implementation of this step can be found in the detailed description of the relevant steps in other embodiments of this disclosure, for example, the implementation of step 102, which will not be described in detail here.
[0064] Step 203: If the predicted insurance outcome indicates that the insurance application will fail, determine the target solution.
[0065] In some embodiments, if the predicted insurance outcome includes reasons for successful or unsuccessful insurance application, then if the predicted insurance outcome is a reason for unsuccessful insurance application, the target solution is determined to be the solution corresponding to the reason for unsuccessful insurance application.
[0066] If the predicted insurance result is the reason for the insurance failure, then the predicted insurance result indicates that the insurance has failed.
[0067] In some embodiments, if the predicted insurance outcome includes successful insurance application or unsuccessful insurance application, in the case where the predicted insurance outcome is unsuccessful insurance application, the reason for the unsuccessful insurance application can be determined first, and then the target solution can be determined based on the reason for the unsuccessful insurance application, or the reason for the unsuccessful insurance application can be determined as the target solution.
[0068] In some embodiments, if the predicted insurance application result is failure, the policy to be applied for can be input into the failure reason prediction model to obtain the reason for the failure.
[0069] Among them, the failure cause prediction model can be generated by training based on the failed insurance policies and the corresponding reasons for the failure.
[0070] The failure cause prediction model can be a text convolutional neural network (TextCNN), a decision tree model, a support vector machine (SVM), etc. This disclosure does not limit it.
[0071] In some embodiments, when the predicted insurance application result is an application failure, a first label corresponding to the underwriting data in the policy to be applied for and a second label corresponding to the quotation data in the policy to be applied for can be determined. If the first label belongs to the underwriting failure reason label, the target solution is determined to include the solution associated with the first label; if the second label belongs to the quotation error reason label, the target solution is determined to include the solution associated with the second label. This allows for a more accurate determination of the target solution.
[0072] In some embodiments, underwriting data can be input into a first prediction model to obtain a first label.
[0073] The first prediction model is generated based on the first dataset, which contains the first sample underwriting data and associated successful underwriting labels, the second sample underwriting data and associated failure underwriting reason labels. The first sample underwriting data is the underwriting data in the successfully underwritten policies, and the second sample underwriting data is the underwriting data in the failed underwriting policies.
[0074] The first sample of underwriting data can include information such as the application date, appointment scheduling date, policy issuance method, vehicle sales order number, insurance company, insurance company location, vehicle delivery center, agency, vehicle model, vehicle price, vehicle purpose, and type of insurance in successfully underwritten policies.
[0075] The second sample of underwriting data can include information such as the application date, appointment scheduling date, policy issuance method, vehicle sales order number, insurance company, insurance company location, vehicle delivery center, agency, vehicle model, vehicle price, vehicle purpose, and type of insurance in the policies that failed to be underwritten.
[0076] The reasons for underwriting failure may include duplicate insurance coverage due to a Vehicle Identification Number (VIN), missing operational information, incorrect owner information, etc. This disclosure does not limit these reasons.
[0077] In some embodiments, the quotation data can be input into a second prediction model to obtain a second label.
[0078] The second prediction model can be generated based on the second dataset, which includes a correct quote label associated with the first sample quote data, the second sample quote data and an associated quote error reason label. The first sample quote data is the quote data in the correct quote policy, and the second sample quote data is the quote data in the incorrect quote policy.
[0079] The first sample of quotation data can include the insurance application date, appointment scheduling date, insurance package, whether a service package is purchased, the insured's age, whether the indicators match the insured, vehicle sales order number, insurance company, insurance company's location, vehicle delivery center, agency, vehicle model, vehicle price, vehicle purpose, and type of insurance, etc., as shown in the quotation guarantee policy.
[0080] The second sample of quotation data can include information such as the policy application date, appointment scheduling date, insurance package, whether a service package was purchased, the insured's age, whether the indicators match the insured, vehicle sales order number, insurance company, insurance company's location, vehicle delivery center, agency, vehicle model, vehicle price, vehicle purpose, and type of insurance in the erroneous policy.
[0081] The error quote reason label may include reasons such as vehicle type not supporting insurance or roadside assistance not being insurable. This disclosure does not limit this.
[0082] In some embodiments, the first prediction model and the second prediction model can be classification models, such as TextConvolutional Neural Networks (TextCNN), decision tree models, support vector machines (SVM), etc. This disclosure does not limit them in this regard.
[0083] In some embodiments, solutions associated with each underwriting failure reason label and solutions associated with each quotation error reason label can be predetermined. Then, if the first label is an underwriting failure reason label and the second label is a quotation correctness label, the target solution is determined to be the solution associated with the first label. If the first label is an underwriting success label and the second label is a quotation error reason label, the target solution is determined to be the solution associated with the second label. If the first label is an underwriting failure reason label and the second label is a quotation error reason label, the target solution is determined to be both the solution associated with the first label and the solution associated with the second label.
[0084] Step 204: Display the target solution.
[0085] In this embodiment of the disclosure, after determining the target solution, the target solution can be displayed on the display interface, so that the user can adjust the insurance policy to be purchased according to the solution, and submit the insurance application after predicting that the insurance result is successful. This can not only improve the success rate of insurance purchase, but also improve the efficiency of insurance purchase.
[0086] In some embodiments, the predicted insurance outcome and target solution may also be displayed on the display interface.
[0087] In this embodiment, the proposed insurance policy is obtained, the predicted insurance result corresponding to the policy is determined, and if the predicted result indicates insurance failure, a target solution is determined and displayed. Therefore, even when the predicted result indicates insurance failure, a target solution can be determined and displayed on the interface. This allows users to adjust the proposed insurance policy based on the target solution, improving both the success rate and efficiency of the insurance application process.
[0088] Figure 3 This is a flowchart illustrating an insurance underwriting method provided in one embodiment of the present disclosure, as shown below. Figure 3 As shown, this insurance application method may include the following steps:
[0089] Step 301: Obtain the insurance policy to be purchased.
[0090] Step 302: Input the underwriting data into the first decision tree to obtain the first label corresponding to the underwriting data.
[0091] The first decision tree is used to predict the underwriting results of the policy to be insured, i.e., the first label.
[0092] The first decision tree is generated based on the first dataset, which includes the first sample underwriting data and associated successful underwriting labels, the second sample underwriting data and associated failure underwriting reason labels. The first sample underwriting data is the underwriting data in the successfully underwritten policies, and the second sample underwriting data is the underwriting data in the failed underwriting policies.
[0093] In some embodiments, a first dataset is obtained, wherein the first dataset includes a first sample underwriting data and associated underwriting success labels, a second sample underwriting data and associated underwriting failure reason labels, the first sample underwriting data being underwriting data from successfully underwritten policies, the second sample underwriting data being underwriting data from unsuccessfully underwritten policies, and a first decision tree is generated based on the first dataset.
[0094] In some embodiments, underwriting failure feedback data corresponding to the second sample underwriting data is obtained, and the underwriting failure feedback data is input into the underwriting tag generation model to obtain the underwriting failure reason tag associated with the second sample underwriting data.
[0095] It should be noted that underwriting failure feedback data is usually irregular text, and its meaning is often difficult to understand. Therefore, in this embodiment of the disclosure, it is necessary to process the underwriting failure feedback data to obtain failure reason tags associated with the failed insurance policies.
[0096] In some embodiments, the underwriting label generation model can be a large model. It can also be other neural network models. This disclosure does not limit it in this regard.
[0097] The term "large model" can also be referred to as a "large language model" (LLM). Examples of large models include ChatGPT and GPT-4 (Generative Pre-trained Transformer 4). This disclosure does not impose any limitations on this terminology.
[0098] In some embodiments, algorithms such as Classification and Regression Tree (CART) and Iterative Dichotomiser 3 (ID3) can be used to process the first dataset and generate the first decision tree.
[0099] Step 303: Input the quotation data into the second decision tree to obtain the second label corresponding to the quotation data.
[0100] The second decision tree is generated based on the second dataset, which includes the correct quote label associated with the first sample quote data, the second sample quote data and the associated quote error reason label. The first sample quote data is the quote data in the policy with correct quotes, and the second sample quote data is the quote data in the policy with incorrect quotes.
[0101] In some embodiments, a second dataset is obtained, wherein the second dataset includes a quote correct label associated with the first sample quote data, the second sample quote data and an associated quote error reason label, the first sample quote data being the quote data in the quote correct policy, and the second sample quote data being the quote data in the quote error policy, and a second decision tree is generated based on the second dataset.
[0102] The error quote reason label may include reasons such as vehicle type not supporting insurance or roadside assistance not being insurable. This disclosure does not limit this.
[0103] In some embodiments, the quotation error feedback data corresponding to the second sample quotation data is obtained, and the quotation error feedback data is input into the quotation label generation model to obtain the underwriting failure reason label associated with the second sample quotation data.
[0104] It should be noted that the pricing error feedback data is usually irregular text, and its meaning is often difficult to understand. Therefore, in this embodiment of the disclosure, the pricing error feedback data needs to be processed to obtain the pricing error reason label associated with the failed insurance policy.
[0105] For example, the error feedback data for a quote could be: "20001-Quote Abnormal [[Premium Calculation] Premium calculation failed, error message: [Quote Engine: Third-Party Liability Insurance has been purchased, the limit is doubled on statutory holidays, and the vehicle must be a private family vehicle!]{SDE_UUID: 20240602151031AGKC}|[Premium Calculation] Premium calculation failed, error message: [Quote Engine: Third-Party Liability Insurance has been purchased, the limit is doubled on statutory holidays, and the vehicle must be a private family vehicle!]{SDE_UUID: 20240602151031AGKC}]".
[0106] In some embodiments, the quote label generation model can be a large model or other neural networks. This disclosure does not limit it in this regard.
[0107] In some embodiments, the quotation label generation model and the underwriting label generation model can be the same large model or different large models. This disclosure does not limit this.
[0108] In some embodiments, if the quotation label generation model and the underwriting label generation model are different large models, the large model can be fine-tuned based on a portion of underwriting failure feedback data and associated underwriting failure reason labels to obtain the underwriting label generation model. Similarly, the large model can be fine-tuned based on a portion of quotation error feedback data and associated quotation error reason labels to obtain the quotation label generation model.
[0109] In some embodiments, if the quotation label generation model and the underwriting label generation model are the same large model, then the large model is fine-tuned based on a portion of the underwriting failure feedback data and the associated underwriting failure reason labels, and a portion of the quotation error feedback data and the associated quotation error reason labels, to obtain the fine-tuned large model.
[0110] In some embodiments, algorithms such as Classification and Regression Tree (CART) and Iterative Dichotomiser 3 (ID3) can be used to generate a second decision tree.
[0111] In some embodiments, the leaf nodes of the second decision tree are the insurance success label and the quote error reason label.
[0112] Step 304: Determine the predicted insurance outcome based on the first label and the second label.
[0113] In some embodiments, the predicted insurance outcome is determined to include a first label and a second label, and the first label and the second label can be directly displayed in the display interface.
[0114] In some embodiments, if the first label is an underwriting failure reason label, the predicted underwriting result is determined to indicate underwriting failure.
[0115] In some embodiments, if the second label is a quote error reason label, it is determined that the predicted insurance outcome indicates an insurance failure.
[0116] In some embodiments, if the first label is an underwriting failure reason label and the second label is a quotation error reason label, the predicted insurance result is determined to be an insurance failure.
[0117] In some embodiments, if the first label is an underwriting success label and the second label is a quote correct label, the predicted insurance result is determined to be an insurance success.
[0118] Step 305: Output the predicted insurance results.
[0119] In this embodiment, the process involves obtaining the policy to be insured, inputting the underwriting data into a first decision tree to obtain a first label corresponding to the underwriting data, inputting the quotation data into a second decision tree to obtain a second label corresponding to the quotation data, determining the predicted insurance result based on the first and second labels, and finally outputting the predicted insurance result. Therefore, by inputting the underwriting data from the policy to be insured into the first decision tree to predict the underwriting result, and inputting the quotation data from the policy to be insured into the second decision tree to predict the quotation result, the predicted quotation result can be determined more accurately, thereby outputting the predicted insurance result and improving insurance efficiency and success rate.
[0120] To achieve the above embodiments, this disclosure also proposes an insurance underwriting device.
[0121] Figure 4 This is a schematic diagram of the insurance application device provided in an embodiment of this disclosure.
[0122] like Figure 4 As shown, the insurance application device 400 may include:
[0123] The acquisition module 401 is used to acquire the insurance policy to be insured, wherein the insurance policy to be insured includes at least one of underwriting data and quotation data. The underwriting data is used to determine the underwriting result corresponding to the insurance policy to be insured, and the quotation data is used to determine the quotation result corresponding to the insurance policy to be insured.
[0124] The determination module 402 is used to determine the predicted insurance result corresponding to the policy to be insured. The predicted insurance result is used to characterize the predicted result of using the policy to be insured for insurance purposes.
[0125] Output module 403 is used to output the predicted insurance results.
[0126] In some embodiments, the output module 403 is used for:
[0127] In cases where the predicted insurance outcome indicates insurance failure, identify the target solution;
[0128] Display the target solution.
[0129] In some embodiments, the output module 403 is used for:
[0130] Determine the first label corresponding to the underwriting data and the second label corresponding to the quotation data;
[0131] If the first label is a label indicating a reason for underwriting failure, the target solution is determined to include the solution associated with the first label; and / or,
[0132] If the second label is a label indicating a pricing error, the target solution should include the solution associated with the second label.
[0133] In some embodiments, the output module 403 is used for:
[0134] If the predicted insurance application result is successful, a prompt will be displayed on the screen, indicating whether the user should submit the insurance policy.
[0135] Upon receiving a submission instruction from the user, submit the insurance policy to be purchased.
[0136] In some embodiments, the acquisition module 401 is used for:
[0137] Upon completion of the insurance application information, obtain the insurance policy to be applied for; or,
[0138] In response to receiving a policy prediction instruction, retrieve the policies to be insured.
[0139] In some embodiments, the determining module 402 is configured to:
[0140] Input the underwriting data into the first decision tree to obtain the first label corresponding to the underwriting data;
[0141] Input the quote data into the second decision tree to obtain the second label corresponding to the quote data;
[0142] Based on the first and second labels, the predicted insurance outcome is determined.
[0143] In some embodiments, the determining module 402 is configured to:
[0144] If the first label falls under the underwriting failure reason label, the predicted underwriting outcome indicates underwriting failure; and / or,
[0145] If the second label is a label indicating a pricing error, the predicted insurance outcome indicates that the insurance application has failed.
[0146] In some embodiments, the determining module 402 is configured to:
[0147] If the first label is "underwriting success" and the second label is "correct quote", the predicted insurance result is determined to be "successful insurance".
[0148] In some embodiments, a first generation module is further included, configured to:
[0149] Obtain the first dataset, which includes the first sample underwriting data and associated successful underwriting labels, and the second sample underwriting data and associated failure underwriting reason labels. The first sample underwriting data is the underwriting data in the successfully underwritten policies, and the second sample underwriting data is the underwriting data in the failed underwriting policies.
[0150] Generate the first decision tree based on the first dataset.
[0151] In some embodiments, the first generation module is configured to:
[0152] Obtain the underwriting failure feedback data corresponding to the second sample underwriting data;
[0153] Input the underwriting failure feedback data into the underwriting label generation model to obtain the underwriting failure reason label associated with the second sample underwriting data.
[0154] In some embodiments, a second generation module is further included, for:
[0155] Obtain the second dataset, which includes the correct quote label associated with the first sample quote data, the second sample quote data and the associated quote error reason label. The first sample quote data is the quote data in the policy with correct quotes, and the second sample quote data is the quote data in the policy with incorrect quotes.
[0156] Generate a second decision tree based on the second dataset.
[0157] In some embodiments, the second generation module is configured to:
[0158] Obtain the pricing error feedback data corresponding to the second sample pricing data;
[0159] Input the pricing error feedback data into the pricing label generation model to obtain pricing error reason labels associated with the second sample pricing data.
[0160] The functions and specific implementation principles of the modules described in this embodiment can be found in the above method embodiments, and will not be repeated here.
[0161] The insurance application device of this disclosure acquires the insurance policy to be applied for, determines the predicted application result corresponding to the policy, and outputs the predicted application result. Therefore, before a user submits an application, the application result can be predicted and displayed to the user. This allows the user to know whether the application will be successful before submission, and further, if the prediction result indicates failure, to modify the application information, thereby improving the success rate.
[0162] To implement the above embodiments, this disclosure also proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the insurance application method proposed in the foregoing embodiments of this disclosure.
[0163] Figure 5 This is a schematic diagram of the structure of the insurance underwriting system provided in an embodiment of this disclosure.
[0164] like Figure 5 As shown, the insurance application device 500 may include:
[0165] The processing module 501 is used to obtain the insurance policy to be insured, determine the predicted insurance result corresponding to the insurance policy to be insured, and output the predicted insurance result to the application module. The insurance policy to be insured includes at least one of underwriting data and quotation data. The underwriting data is used to determine the underwriting result corresponding to the insurance policy to be insured, the quotation data is used to determine the quotation result corresponding to the insurance policy to be insured, and the predicted insurance result is used to characterize the predicted result of using the insurance policy to be insured for insurance purposes.
[0166] Application module 502 is used to output the predicted insurance results to the user.
[0167] In some embodiments, the processing module 501 can be deployed on a server or on a terminal. The application module 502 is deployed on the terminal.
[0168] When the processing module 501 is deployed in the server, the terminal can send the insurance policy to be insured to the processing module 501 of the server. The processing module 501 of the server determines the predicted insurance result corresponding to the insurance policy to be insured and outputs the predicted insurance result to the application module 502 of the terminal. Then, the application module 502 of the terminal can output the predicted insurance result to the user.
[0169] When the processing module 501 is deployed in the terminal, the processing module 501 of the terminal can directly obtain the insurance policy to be insured, determine the predicted insurance result corresponding to the insurance policy to be insured, and output the predicted insurance result to the application module 502 of the terminal. Then, the application module 502 of the terminal can output the predicted insurance result to the user.
[0170] In some embodiments, the processing module 501 is further configured to determine a target solution and output the target solution to the application module when the predicted insurance result indicates insurance failure; the application module is further configured to display the target solution.
[0171] In some embodiments, the processing module 501 is configured to:
[0172] Determine the first label corresponding to the underwriting data and the second label corresponding to the quotation data;
[0173] If the first label is a label indicating a reason for underwriting failure, the target solution is determined to include the solution associated with the first label; and / or,
[0174] If the second label is a label indicating a pricing error, the target solution should include the solution associated with the second label.
[0175] In some embodiments, the processing module is configured to output a prompt to the application module when the predicted insurance application result is successful, wherein the prompt is used to prompt the user whether to submit the insurance policy to be applied for; the application module is configured to display the prompt; and the processing module is configured to submit the insurance policy to be applied for upon receiving the user's submission instruction.
[0176] In some embodiments, the processing module 501 is configured to:
[0177] Upon completion of the insurance application information, obtain the insurance policy to be applied for; or,
[0178] In response to receiving a policy prediction instruction, retrieve the policies to be insured.
[0179] In some embodiments, the processing module 501 is further configured to:
[0180] Input the underwriting data into the first decision tree to obtain the first label corresponding to the underwriting data;
[0181] Input the quote data into the second decision tree to obtain the second label corresponding to the quote data;
[0182] Based on the first and second labels, the predicted insurance outcome is determined.
[0183] In some embodiments, the processing module 501 is further configured to:
[0184] If the first label falls under the underwriting failure reason label, the predicted underwriting outcome indicates underwriting failure; and / or,
[0185] If the second label is a label indicating a pricing error, the predicted insurance outcome indicates that the insurance application has failed.
[0186] In some embodiments, the processing module 501 is further configured to:
[0187] If the first label is "underwriting success" and the second label is "correct quote", the predicted insurance result is determined to be "successful insurance".
[0188] The functions and specific implementation principles of the modules described in this embodiment can be found in the above method embodiments, and will not be repeated here.
[0189] The insurance application system in this embodiment can obtain the insurance policy to be applied for through a processing module, determine the predicted application result corresponding to the policy, and finally output the predicted application result to the application module, which then outputs the predicted application result to the user. Therefore, before the user submits the application, the application result can be predicted and displayed to the user. This allows the user to know whether the application will be successful before submission, and further, if the prediction result indicates failure, the user can modify the application information to improve the success rate.
[0190] Figure 6 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Figure 6 The electronic device 12 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.
[0191] like Figure 6 As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).
[0192] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.
[0193] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.
[0194] Memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and / or cache memory 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disc drive for reading and writing to a removable non-volatile optical disc (e.g., a compact disc read-only memory (CD-ROM), a digital video disc read-only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.
[0195] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this disclosure.
[0196] Electronic device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with electronic device 12, and / or with any device that enables electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, electronic device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0197] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the methods mentioned in the foregoing embodiments.
[0198] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the insurance application method proposed in the foregoing embodiments of this disclosure.
[0199] To implement the above embodiments, this disclosure also provides a computer program product, including computer instructions, which, when executed by a processor, implement the insurance application method proposed in the foregoing embodiments of this disclosure.
[0200] To implement the above embodiments, this disclosure also proposes a chip, including: the chip includes a processing circuit configured to perform the insurance application method provided in the foregoing embodiments.
[0201] Figure 7 This is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. See also... Figure 7 The diagram shown is a schematic representation of the structure of chip 700, but is not limited thereto.
[0202] Chip 700 includes processing circuitry 701, which is configured to perform any of the above methods.
[0203] In some embodiments, chip 700 further includes one or more interface circuits 702. Optionally, interface circuit 702 is connected to memory 703, and interface circuit 702 can be used to receive signals from memory 703 or other devices, and interface circuit 702 can be used to send signals to memory 703 or other devices. For example, interface circuit 702 can read instructions stored in memory 703 and send the instructions to processing circuit 701.
[0204] In some embodiments, the interface circuit 702 performs at least one of the communication steps such as sending and / or receiving in the above method, and the processing circuit 701 performs other steps.
[0205] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc., can be used interchangeably.
[0206] In some embodiments, chip 700 further includes one or more memories 703 for storing instructions. Optionally, all or part of the memories 703 may be located outside of chip 700.
[0207] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0208] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0209] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.
[0210] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.
[0211] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0212] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
[0213] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0214] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.
Claims
1. An insurance underwriting method, characterized in that, The method includes: Obtain the insurance policy to be insured, wherein the insurance policy to be insured includes at least one of underwriting data and quotation data, wherein the underwriting data is used to determine the underwriting result corresponding to the insurance policy to be insured, and the quotation data is used to determine the quotation result corresponding to the insurance policy to be insured; Determine the predicted insurance application result corresponding to the policy to be insured, wherein the predicted insurance application result is used to characterize the predicted result of using the policy to be insured for insurance purposes; Output the predicted insurance results.
2. The method according to claim 1, characterized in that, The output of the predicted insurance result includes: If the predicted insurance outcome indicates that the insurance application will fail, determine the target solution; The target solution is shown.
3. The method according to claim 2, characterized in that, The determination of the target solution includes: Determine the first label corresponding to the underwriting data and the second label corresponding to the quotation data; If the first tag belongs to the underwriting failure reason tag, the target solution is determined to include the solution associated with the first tag; and / or, If the second label belongs to the "quotation error reason" label, the target solution is determined to include the solution associated with the second label.
4. The method according to claim 1, characterized in that, The output of the predicted insurance result includes: If the predicted insurance application result is successful, a prompt message will be displayed, which will ask the user whether to submit the insurance policy to be applied for. Upon receiving a submission instruction from the user, the insurance policy to be purchased is submitted.
5. The method according to claim 1, characterized in that, The process of obtaining the insurance policy to be purchased includes: In response to the completion of the insurance application information, the policy to be applied for is obtained; or, In response to receiving a policy prediction instruction, the policy to be insured is obtained.
6. The method according to any one of claims 1-5, characterized in that, Determining the predicted insurance application result corresponding to the policy to be insured includes: The underwriting data is input into the first decision tree to obtain the first label corresponding to the underwriting data; The quotation data is input into the second decision tree to obtain the second label corresponding to the quotation data; The predicted insurance result is determined based on the first tag and the second tag.
7. The method according to claim 6, characterized in that, Determining the predicted insurance result based on the first tag and the second tag includes: If the first tag belongs to the underwriting failure reason tag, it is determined that the predicted insurance result indicates insurance failure; and / or, If the second label belongs to the quotation error reason label, the predicted insurance result indicates that the insurance application has failed.
8. The method according to claim 6, characterized in that, Determining the predicted insurance result based on the first tag and the second tag includes: If the first label is an underwriting success label and the second label is a quote correct label, the predicted insurance result is determined to be an insurance success.
9. The method according to claim 6, characterized in that, Before inputting the underwriting data into the first decision tree to obtain the first label corresponding to the underwriting data, the method further includes: Obtain a first dataset, wherein the first dataset includes a first sample underwriting data and associated underwriting success labels, a second sample underwriting data and associated underwriting failure reason labels, wherein the first sample underwriting data is the underwriting data in the successfully underwritten policies, and the second sample underwriting data is the underwriting data in the unsuccessfully underwritten policies; The first decision tree is generated based on the first dataset.
10. The method according to claim 9, characterized in that, The method further includes: Obtain the underwriting failure feedback data corresponding to the second sample underwriting data; The underwriting failure feedback data is input into the underwriting tag generation model to obtain the underwriting failure reason tag associated with the second sample underwriting data.
11. The method according to claim 6, characterized in that, Before inputting the quotation data into the second decision tree to obtain the second label corresponding to the quotation data, the method further includes: Obtain a second dataset, wherein the second dataset includes a quote correct label associated with the first sample quote data, a second sample quote data and an associated quote error reason label, wherein the first sample quote data is the quote data in the quote correct policy, and the second sample quote data is the quote data in the quote error policy; The second decision tree is generated based on the second dataset.
12. The method according to claim 11, characterized in that, The method further includes: Obtain the quotation error feedback data corresponding to the second sample quotation data; The quoted error feedback data is input into the quoted label generation model to obtain the quoted error reason label associated with the second sample quoted data.
13. An insurance application device, characterized in that, The device includes: The acquisition module is used to acquire insurance policies to be insured, wherein the insurance policies to be insured include at least one of underwriting data and quotation data, wherein the underwriting data is used to determine the underwriting result corresponding to the insurance policies to be insured, and the quotation data is used to determine the quotation result corresponding to the insurance policies to be insured; The determining module is used to determine the predicted insurance result corresponding to the policy to be insured, and the predicted insurance result is used to characterize the predicted result of using the policy to be insured for insurance purposes; The output module is used to output the predicted insurance result.
14. An insurance underwriting system, characterized in that, The system includes: The processing module is used to obtain the insurance policy to be insured, determine the predicted insurance result corresponding to the insurance policy to be insured, and output the predicted insurance result to the application module. The insurance policy to be insured includes at least one of underwriting data and quotation data. The underwriting data is used to determine the underwriting result corresponding to the insurance policy to be insured, and the quotation data is used to determine the quotation result corresponding to the insurance policy to be insured. The predicted insurance result is used to characterize the predicted result of using the insurance policy to be insured for insurance purposes. The application module is used to output the predicted insurance results to the user.
15. The system according to claim 14, characterized in that, The processing module is also used to determine a target solution and output the target solution to the application module when the predicted insurance result indicates that the insurance application has failed. The application module is also used to display the target solution.
16. The system according to claim 15, characterized in that, The processing module is further configured to: Determine the first label corresponding to the underwriting data and the second label corresponding to the quotation data; If the first tag belongs to the underwriting failure reason tag, the target solution is determined to include the solution associated with the first tag; and / or, If the second label belongs to the "quotation error reason" label, the target solution is determined to include the solution associated with the second label.
17. The system according to claim 14, characterized in that, The processing module is used to output a prompt to the application module when the predicted insurance application result is successful. The prompt is used to prompt the user whether to submit the insurance policy to be applied for. The application module is used to display the prompt content; The processing module is used to submit the insurance policy to be purchased upon receiving a submission instruction from the user.
18. The system according to claim 14, characterized in that, The processing module is used for: In response to the completion of the insurance application information, the policy to be applied for is obtained; or, In response to receiving a policy prediction instruction, the policy to be insured is obtained.
19. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the insurance underwriting method as described in any one of claims 1-12.
20. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the insurance application method as described in any one of claims 1-12.
21. A computer program product comprising computer instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1-12.
22. A chip, characterized in that, The chip includes a processing circuit configured to perform the insurance underwriting method as described in any one of claims 1-12.