Strategy customization method and device based on evaluation model, electronic equipment and medium

Abstract

The embodiment of the invention provides a strategy customization method and device based on an evaluation model, electronic equipment and a medium, and belongs to the technical field of financial science and technology. The method comprises the following steps: acquiring to-be-evaluated insurance data and user demand information, and acquiring environmental factor information and historical insurance policy data of to-be-insured property; performing data analysis on the historical insurance policy data to determine risk factors; inputting the risk factor into a preset evaluation model for quantitative evaluation, and outputting an insurance policy loss ratio; determining an insurance influence value according to the insurance policy loss ratio and the historical insurance policy data; setting a risk grade table according to the insurance influence value; inputting the to-be-assessed insurance data and the environmental factor information into an assessment model for risk assessment, and outputting a risk assessment result; determining a target risk interval and a target risk amount threshold; and generating a target insurance strategy according to the target risk amount threshold, the insurance company information and the user demand information. According to the embodiment of the invention, different strategies can be formulated according to personalized requirements of users.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a strategy customization method, device, electronic device and medium based on an evaluation model. Background Art

[0002] With the development of the economy and the progress of society, property insurance plays an increasingly important role in protecting the property safety of individuals and enterprises. In the current field of property insurance, although insurance products play a vital role in the protection of personal and corporate property, traditional evaluation and management methods face many challenges. These methods often rely on manual operations and outdated models, resulting in inefficient data processing and difficulty in quickly responding to market changes and customer needs. At the same time, due to the lack of refined risk assessment tools, these traditional methods are also insufficient in accuracy and often cannot accurately predict and quantify risks, resulting in insurance pricing or compensation decisions that may deviate from the actual risk level, and it is impossible to formulate suitable strategies for users based on their personalized needs, further reducing user satisfaction. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose a policy customization method, device, electronic device and medium based on an evaluation model, which can improve the accuracy of risk assessment and formulate different strategies according to the personalized needs of users.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a strategy customization method based on an evaluation model, the method comprising:

[0005] Obtaining insurance data to be evaluated and user demand information, and obtaining environmental factor information of the property to be insured corresponding to the insurance data to be evaluated and historical insurance policy data of the property to be insured, wherein the historical insurance policy data includes insurance policy information and insurance company information, and the environmental factor information is used to characterize information on risk factors affecting the property to be insured;

[0006] Performing data analysis on the historical policy data to determine risk factors;

[0007] Input the risk factor into a preset evaluation model for quantitative evaluation, and output the policy loss ratio, wherein the policy loss ratio is used to characterize the profit and loss situation of the policy corresponding to the policy information;

[0008] Determine an insurance impact value according to the insurance policy claim ratio and the historical insurance policy data, wherein the insurance impact value is used to characterize the degree of influence of the insurance policy information on the insurance company corresponding to the insurance company information;

[0009] A risk level table is set according to the insurance impact value, wherein the risk level table includes a plurality of risk intervals, and each risk interval is set with a risk amount threshold;

[0010] Inputting the insurance data to be evaluated and the environmental factor information into the evaluation model for risk evaluation, and outputting the risk evaluation result;

[0011] Determine a target risk interval corresponding to the risk assessment result in the risk level table, and determine a target risk amount threshold corresponding to the target risk interval;

[0012] A target insurance policy is generated according to the target risk amount threshold, the insurance company information and the user demand information.

[0013] In some embodiments, the performing of data analysis on the historical policy data to determine the risk factors includes:

[0014] Standardizing the historical policy data to obtain multiple policy fields;

[0015] Performing data association operations on all the policy fields through a preset claims system to obtain target policy data;

[0016] Based on the preset single variable method, parameters of the target policy data are selected to determine the risk factors.

[0017] In some embodiments, the data association operation is performed on all the policy fields through a preset claim settlement system to obtain target policy data, including:

[0018] Performing data association operation on all the fields of the insurance policy through a preset claim system to obtain associated data and discrete data;

[0019] For each discrete data, creating a discrete variable corresponding to the discrete data, and setting an original variable value of the discrete variable;

[0020] Replacing the original variable value of the discrete variable based on a preset conversion rule to obtain a target discrete value;

[0021] updating the discrete data according to the target discrete value, and generating policy data according to the updated discrete data and the associated data;

[0022] The insurance policy data is cleaned to obtain target insurance policy data.

[0023] In some embodiments, the insurance company information includes operating cost information and the company's total insurance policy premium; the determining of the insurance impact value based on the insurance policy claim ratio and the historical insurance policy data includes:

[0024] Determining, based on the policy information, the policy premium of the policy corresponding to the policy information;

[0025] Determining the company loss ratio of the insurance company corresponding to the insurance company information according to the operating cost information;

[0026] Determine the policy impact value according to the policy claim ratio, the company claim ratio and the policy premium;

[0027] Calculate the ratio of the policy impact value to the company's total policy premium to determine the insurance impact value.

[0028] In some embodiments, setting a risk level table according to the insurance impact value includes:

[0029] When the insurance impact value is greater than a first preset impact value, a first risk interval is generated according to the first preset impact value, and a first amount is determined as a risk amount threshold of the first risk interval;

[0030] When the insurance impact value is greater than the second preset impact value and less than or equal to the first preset impact value, a second risk interval is generated according to the first preset impact value and the second preset impact value, and the second amount is determined as the risk amount threshold of the second risk interval;

[0031] When the insurance impact value is less than or equal to the second preset impact value, a third risk interval is generated according to the second preset impact value, and a third amount is determined as a risk amount threshold of the third risk interval;

[0032] Among them, the first preset impact value is greater than the second preset impact value, and the first amount, the second amount and the third amount decrease in sequence.

[0033] In some embodiments, the insurance company information includes an insurance premium rate; generating a target insurance policy according to the target risk amount threshold, the insurance company information, and the user demand information includes:

[0034] Determining an interval rule corresponding to the target risk interval according to the insurance company information, wherein the interval rule is a rule that limits application scenarios of the property to be insured;

[0035] Determine the intended insured amount, insurance period and compensation amount of the property to be insured according to the user demand information;

[0036] When the intended insured amount is less than or equal to the target risk amount threshold, and the insurance period and the compensation amount meet the interval rule, a target insurance policy is generated based on the insurance premium rate, the intended insured amount, the insurance period and the compensation amount.

[0037] In some embodiments, after determining the intended insured amount, insurance period, and compensation amount of the property to be insured according to the user demand information, the method further includes:

[0038] When the intended insurance amount is greater than the target risk amount threshold, the insurance period does not comply with the interval rule, or the compensation amount does not comply with the interval rule, a target insurance policy is generated based on the target risk amount threshold, the insurance premium rate and the interval rule.

[0039] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a policy customization device based on an evaluation model, the device comprising:

[0040] A data acquisition module, used to acquire the insurance data to be evaluated and user demand information, and to acquire the environmental factor information of the property to be insured corresponding to the insurance data to be evaluated and the historical insurance policy data of the property to be insured, wherein the historical insurance policy data includes insurance policy information and insurance company information;

[0041] A data analysis module, used to analyze the historical policy data and determine risk factors;

[0042] A quantitative evaluation module, used to input the risk factor into a preset evaluation model for quantitative evaluation and output a policy loss ratio, wherein the policy loss ratio is used to characterize the profit and loss situation of the policy corresponding to the policy information;

[0043] An impact value determination module, used to determine an insurance impact value according to the insurance policy claim ratio and the historical insurance policy data, wherein the insurance impact value is used to characterize the degree of influence of the insurance policy information on the insurance company corresponding to the insurance company information;

[0044] A level table setting module, used to set a risk level table according to the insurance impact value, wherein the risk level table includes a plurality of risk intervals, and each of the risk intervals is set with a risk amount threshold;

[0045] A risk assessment module, used for inputting the insurance data to be assessed and the environmental factor information into the assessment model for risk assessment and outputting the risk assessment result;

[0046] A risk determination module, used to determine a target risk interval corresponding to the risk assessment result in the risk level table, and determine a target risk amount threshold corresponding to the target risk interval;

[0047] A policy generation module is used to generate a target insurance policy based on the target risk amount threshold, the insurance company information and the user demand information.

[0048] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, an electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the policy customization method based on the evaluation model as described in the first aspect when executing the computer program.

[0049] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the policy customization method based on the evaluation model as described in the first aspect.

[0050] The present application proposes a strategy customization method, device, electronic device and storage medium based on an evaluation model. First, the insurance data to be evaluated and user demand information are obtained, and the environmental factor information of the property to be insured corresponding to the insurance data to be evaluated and the historical policy data of the property to be insured are obtained, so as to facilitate the subsequent judgment of the physical environment in which the property to be insured is located and the factors that may cause risks to the property to be insured. Then, data analysis is performed on the historical policy data. The risk factors affecting the property to be insured are analyzed through the historical policy data to determine the risk factors, so as to facilitate the subsequent analysis of the compensation situation under different risk factors. The risk factors are input into a preset evaluation model for quantitative evaluation, the various risks faced by the property to be insured are evaluated, and the policy compensation ratio is output, so as to obtain the profit and loss situation of the policy corresponding to the policy information under different risk factors, so as to facilitate the subsequent risk evaluation of the insurance product. Afterwards, the insurance impact value is determined according to the policy compensation ratio and the historical insurance data, so as to determine the degree of influence of the policy information on the insurance company corresponding to the insurance company information, and it is possible to draw conclusions based on the policy compensation ratio. By analyzing the impact of policy information in combination with other historical insurance data, the impact of policy information on insurance companies can be accurately analyzed, thereby improving the accuracy of policy analysis. A risk level table is then set according to the insurance impact value, thereby dividing multiple risk intervals and realizing accurate division of risks of different levels. Finally, the insurance data to be evaluated and the environmental factor information are input into the evaluation model for risk assessment, and the risk assessment results are output. This can accurately assess the risk level of a specific type of insurance, realize accurate assessment of the insurance data to be evaluated, and improve the accuracy and efficiency of property insurance assessment. The target risk interval corresponding to the risk assessment result is determined in the risk level table, which can accurately determine the risk level of the property to be insured, and determine the target risk amount threshold corresponding to the target risk interval, thereby determining the maximum amount threshold that the property to be insured can bear based on the risk assessment result, and then generating a target insurance strategy based on the target risk amount threshold, insurance company information, and user demand information, thereby being able to customize different insurance strategies based on user needs and improve user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flow chart of a strategy customization method based on an evaluation model provided in an embodiment of the present application;

[0052] Figure 2 yes Figure 1 Flow chart of step S102 in FIG.

[0053] Figure 3 yes Figure 2 Flow chart of step S202 in FIG.

[0054] Figure 4 yes Figure 1 Flow chart of step S104 in FIG.

[0055] Figure 5 yes Figure 1 Flow chart of step S105 in FIG.

[0056] Figure 6 yes Figure 1 Flow chart of step S108 in FIG.

[0057] Figure 7 is a flow chart of a strategy customization method based on an evaluation model provided in another embodiment of the present application;

[0058] Figure 8 is a schematic diagram of the structure of a strategy customization device based on an evaluation model provided in an embodiment of the present application;

[0059] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0063] First, some nouns involved in this application are analyzed:

[0064] Natural Language Processing (NLP): NLP uses computers to process, understand, and apply human languages ​​(such as Chinese, English, etc.). NLP is a branch of artificial intelligence and an interdisciplinary subject between computer science and linguistics. It is often referred to as computational linguistics. Natural language processing includes grammatical analysis, semantic analysis, and text understanding. Natural language processing is commonly used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information intent recognition, information extraction and filtering, text classification and clustering, public opinion analysis, and opinion mining. It involves data mining related to language processing, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computing.

[0065] One-Hot Encoding (OHE): One-Hot Encoding is a method for handling categorical variables that converts each category into a binary vector with one position as 1 to represent the current category and the rest as 0.

[0066] Label Encoding (LE): Label encoding maps each category of a categorical variable to a unique integer and is often used to convert text categories into numerical values ​​that can be processed by machine learning algorithms.

[0067] Structured Query Language (SQL): SQL is a programming language used to manage and manipulate relational databases. It allows users to perform various database operations such as querying, inserting, updating, and deleting data.

[0068] JOIN: In SQL, JOIN is an operation used to combine rows from two or more tables into a result set, usually based on related column values. There are many types of JOIN, such as INNER JOIN, LEFT JOIN, RIGHT JOIN, etc.

[0069] The evaluation model-based policy customization method and device, electronic device, and storage medium provided in the embodiments of the present application can improve the accuracy of risk assessment and formulate different policies based on the personalized needs of users.

[0070] The following examples are used to illustrate the present invention in detail. First, the strategy customization method based on the evaluation model in the example of the present application is described.

[0071] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0072] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include computer vision technology, robotics technology, biometrics technology, module management technology of online meeting systems, natural language processing technology, and machine learning / deep learning.

[0073] The policy customization method based on the evaluation model provided in the embodiment of the present application relates to the field of financial technology technology. The policy customization method based on the evaluation model provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the policy customization method based on the evaluation model, etc., but is not limited to the above forms.

[0074] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data information types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0075] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with the relevant laws, regulations, and standards of the relevant countries and regions. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0076] With the development of the economy and the progress of society, property insurance plays an increasingly important role in protecting the property safety of individuals and enterprises. In the current field of property insurance, although insurance products play a vital role in the protection of personal and corporate property, traditional evaluation and management methods face many challenges. These methods often rely on manual operations and outdated models, resulting in inefficient data processing and difficulty in quickly responding to market changes and customer needs. At the same time, due to the lack of refined risk assessment tools, these traditional methods are also insufficient in accuracy and often cannot accurately predict and quantify risks, resulting in insurance pricing or compensation decisions that may deviate from the actual risk level, and it is impossible to formulate suitable strategies for users based on their personalized needs, further reducing user satisfaction.

[0077] In order to solve the above problems, the present embodiment provides a strategy customization method, device, electronic device and storage medium based on an evaluation model. First, the insurance data to be evaluated and user demand information are obtained, and the environmental factor information of the property to be insured corresponding to the insurance data to be evaluated and the historical policy data of the property to be insured are obtained, so as to facilitate the subsequent judgment of the physical environment in which the property to be insured is located and the factors that may cause risks to the property to be insured. Then, data analysis is performed on the historical policy data. The risk factors affecting the property to be insured are analyzed through the historical policy data to determine the risk factors, so as to facilitate the subsequent analysis of the compensation situation under different risk factors. The risk factors are input into a preset evaluation model for quantitative evaluation, and the various risks faced by the property to be insured are evaluated. The policy claim ratio is output, so as to obtain the profit and loss situation of the policy corresponding to the policy information under different risk factors, so as to facilitate the subsequent risk evaluation of the insurance product. Afterwards, the insurance impact value is determined according to the policy claim ratio and the historical insurance data, so as to determine the degree of influence of the policy information on the insurance company corresponding to the insurance company information, so as to be able to determine the degree of influence of the policy information on the insurance company corresponding to the insurance company information. Based on the analysis of the impact of policy information combined with other historical insurance data, the impact of policy information on the insurance company can be accurately analyzed, the accuracy of policy analysis can be improved, and then the risk level table is set according to the insurance impact value, so as to divide multiple risk intervals and realize the accurate division of risks of different levels. Finally, the insurance data to be evaluated and the environmental factor information are input into the evaluation model for risk assessment, and the risk assessment results are output. The risk level of a specific type of insurance can be accurately assessed, and the accurate assessment of the insurance data to be evaluated can be realized, which improves the accuracy and efficiency of property insurance assessment. The target risk interval corresponding to the risk assessment result is determined in the risk level table, which can accurately determine the risk level of the property to be insured, and determine the target risk amount threshold corresponding to the target risk interval, so that the maximum amount threshold that the property to be insured can bear can be determined according to the risk assessment result, and then the target insurance strategy is generated according to the target risk amount threshold, insurance company information and user demand information, so that different insurance strategies can be customized according to user needs to improve user satisfaction.

[0078] The following is a detailed description with reference to the accompanying drawings.

[0079] Figure 1 is an optional flow chart of a strategy customization method based on an evaluation model provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S108.

[0080] Step S101, obtaining insurance data to be evaluated and user demand information, and obtaining environmental factor information of the property to be insured corresponding to the insurance data to be evaluated and historical insurance policy data of the property to be insured.

[0081] It should be noted that the historical policy data includes policy information and insurance company information, and the environmental factor information is used to characterize the risk factors that affect the property to be insured.

[0082] In step S101 of some embodiments, the embodiments of the present application first obtain the insurance data to be evaluated and the user demand information, wherein the insurance data to be evaluated includes the property to be insured, and obtains the environmental factor information and historical policy data of the property to be insured, so as to determine the environment in which the property to be insured is located, and further determine which factors in the environment in which the property to be insured is located that can pose risks to it, and determine the previous insurance status of the property to be insured through the historical policy data, so as to facilitate the subsequent analysis of the compensation status under different risk situations.

[0083] It should be noted that the insurance data to be evaluated in the embodiment of the present application is data related to the property to be insured, such as property type, property value, property maintenance information, etc. Environmental factor information is external data related to the property to be insured, and these data are risk factors affecting the insurance property, such as climate conditions, public security conditions, market price fluctuations, etc., which facilitates the subsequent accurate assessment of the risks of the insurance property.

[0084] Understandably, a building located in a seismic zone may face a higher risk of earthquakes, or a property near a coastline may be more vulnerable to storms and flooding. Understanding these environmental factors can help insurers quantify potential losses, allowing for more accurate risk assessments.

[0085] Step S102, analyzing historical policy data to determine risk factors.

[0086] In step S102 of some embodiments, data analysis is performed on historical policy data, and one or more variables that may affect the claims ratio are selected and determined as risk factors. The risk factors can be quickly identified, providing the insurance company with clear decision support information, facilitating the subsequent prediction of the claims ratio through risk factors.

[0087] Step S103, input the risk factor into the preset evaluation model for quantitative evaluation, and output the policy claim ratio.

[0088] It should be noted that the policy claim ratio is used to represent the profit and loss situation of the policy corresponding to the policy information.

[0089] It is worth noting that the evaluation model in the embodiment of the present application is a multiple linear regression model.

[0090] In step S103 of some embodiments, the risk factor is input into a preset assessment model for quantitative assessment. Specifically, the assessment model in the embodiments of the present application uses the risk factor as a variable, trains the assessment model through the risk factor, adjusts the model parameters, and then evaluates the impact of different features on the model performance. The most influential feature is selected, and the assessment model is trained based on the feature. Thereafter, the risk factor is input into the trained assessment model, the impact of each risk factor on the claims ratio is evaluated, and the policy claims ratio is output, thereby identifying and quantifying key risk factors, providing a basis for risk management, providing more personalized insurance services, and meeting the risk management needs of different users.

[0091] Step S104, determining the insurance impact value according to the policy claim ratio and historical policy data.

[0092] It should be noted that the insurance impact value is used to represent the degree of influence of the policy information on the insurance company corresponding to the insurance company information.

[0093] In step S104 of some embodiments, the insurance impact value is determined based on the policy claim ratio and historical policy data, so that the degree of influence of the policy on the insurance company corresponding to the insurance company information can be determined through the insurance impact value, and the benefits and risks of the policy can be evaluated through the insurance impact value.

[0094] Step S105, setting a risk level table according to the insurance impact value, wherein the risk level table includes multiple risk intervals, and each risk interval is set with a risk amount threshold.

[0095] In step S105 of some embodiments, a risk level table is set according to the insurance impact value, so that the risk interval can be divided into different risk levels, which is convenient for the subsequent formulation of insurance policies.

[0096] Step S106, input the insurance data to be evaluated and the environmental factor information into the evaluation model for risk evaluation, and output the risk evaluation result.

[0097] In step S106 of some embodiments, the insurance data to be evaluated and the environmental factor information are input into the evaluation model for risk assessment, so that the evaluation model can consider multiple factors to perform risk assessment on the insurance data to be evaluated, for example, considering factors such as the value of the property, geographical location, nature of use, and past loss records. By comprehensively considering multiple factors such as property value, geographical location, nature of use, and past loss records, the evaluation model can provide a more comprehensive evaluation result, which can better reflect the actual risk status of the insured object, thereby improving the accuracy of risk assessment and the reliability of prediction.

[0098] Step S107, determining a target risk interval corresponding to the risk assessment result in the risk level table, and determining a target risk amount threshold corresponding to the target risk interval.

[0099] In step S107 of some embodiments, after determining the risk assessment result, the embodiments of the present application need to determine the risk level of the risk assessment result. Specifically, the target risk interval corresponding to the risk assessment result is determined in the risk level table, and the target risk amount threshold corresponding to the target risk interval is determined. This can determine the risk level of the risk assessment result and the maximum tolerance amount in the target risk interval corresponding to the risk level, so as to facilitate the subsequent determination of the appropriate insurance amount, and further generate a reasonable insurance policy to avoid the situation where the insurance amount of the insured property is inconsistent with its corresponding risk interval.

[0100] Step S108, generating a target insurance policy according to the target risk amount threshold, insurance company information and user demand information.

[0101] In step S108 of some embodiments, a target insurance policy is generated based on the target risk amount threshold, insurance company information, and user demand information. The insurance policy can be adjusted and optimized based on customer needs and feedback, and the target insurance policy can be personalized to improve customer satisfaction and the competitiveness of the insurance business.

[0102] See also Figure 2 In some embodiments, step S102 may also include but is not limited to steps S201 to S203.

[0103] Step S201, standardize the historical policy data to obtain multiple policy fields.

[0104] In step S201 of some embodiments, during the data analysis of historical policy data, since the policies of the same insurance product may come from different systems, for example, offline policies, online policies, third-party policies, etc., different data sources lead to incomplete uniformity of historical policy data. Therefore, the embodiment of the present application first standardizes the historical policy data. Specifically, the integrity of the historical policy data is first checked, and missing values ​​and outliers are processed. After checking the integrity of the historical policy data, all historical policy data are converted into a unified format so that data from different sources can be compared and analyzed under the same standards. Data recognition is then performed on the data after format conversion to identify and divide the fields and records that need to be corrected to obtain multiple policy fields. For each policy field, data correction is performed on the policy field to correct errors in the data, such as spelling errors, format errors, etc., to improve the accuracy of the data. Finally, the policy field after data correction is converted into a unified coding standard to obtain multiple standardized policy fields, thereby ensuring the consistency of the policy fields and improving the accuracy and reliability of the data.

[0105] It is understandable that the historical policy data is not completely unified. For example, some address data is accurate to the city, while some only have specific street names without describing the specific city. In this case, it is necessary to standardize the fields with only specific street names. The detailed address can be obtained by querying the street name in the map database, and the standard address can be obtained by passing in the detailed address.

[0106] Step S202, performing data association operation on all insurance policy fields through a preset claims system to obtain target insurance policy data.

[0107] In step S202 of some embodiments, in order to obtain all data in the historical policy data, the embodiments of the present application perform data association operations on all policy fields through a preset claims system, thereby determining the associated data and discrete data in the policy fields, and performing corresponding processing on the discrete data to obtain the target policy data, which is convenient for subsequent enhancement of the model processing capability, improving the prediction accuracy, and enhancing the flexibility of data analysis.

[0108] It should be noted that the claims system in the embodiment of the present application stores multiple claims information, and each claim information is provided with a corresponding field identifier.

[0109] Step S203, selecting parameters for the target policy data based on a preset single variable method to determine the risk factors.

[0110] In step S203 of some embodiments, the embodiments of the present application perform parameter selection on the target policy data based on a preset single variable method. Specifically, the data type of the target policy data is determined, multiple data types are selected, one or more variables that may affect the claims ratio are selected, and the variables are determined as risk factors. The risk factors that can be quickly identified provide clear decision support information for the insurance company, facilitating the subsequent prediction of the claims ratio through risk factors.

[0111] It is understandable that the risk factors of the embodiments of the present application include but are not limited to customer scenarios, work locations, additional conditions, rates, etc., and the embodiments of the present application do not impose specific limitations.

[0112] See also Figure 3 In some embodiments, step S202 may also include but is not limited to steps S301 to S305.

[0113] Step S301, performing data association operation on all policy fields through a preset claim settlement system to obtain associated data and discrete data.

[0114] In step S301 of some embodiments, in the process of performing data association operations on all policy fields, the embodiments of the present application perform data association operations on all policy fields through a preset claims system. Specifically, the claim fields in the claims system are matched with the policy fields, the common fields between the policy fields and the claims system are found, the associated fields between the two are determined, and then an SQL query statement is written, using the JOIN clause to specify how to associate the two tables. Thereafter, the SQL query statement is run to retrieve and integrate the data, and the retrieved data is used as associated data, that is, data corresponding to the policy fields exists in the claims system, and the unretrieved data is used as discrete data, that is, data corresponding to the policy fields does not exist in the claims system, and associated data and discrete data are obtained, so that the relationship between the data can be clarified to ensure the consistency and accuracy of the data.

[0115] It is understandable that an insurance policy may have multiple claim data, and multiple claim data are stored in the claim system as an example, where the claim data includes but is not limited to claim data, report information, etc. At this time, the data association operation is performed on all insurance policy fields through the preset claim system, and the details of the insurance policy's claim data can be queried.

[0116] Step S302: for each discrete data, create a discrete variable corresponding to the discrete data, and set the original variable value of the discrete variable.

[0117] Step S303: replace the original variable value of the discrete variable based on a preset transformation rule to obtain a target discrete value.

[0118] Step S304, updating the discrete data according to the target discrete value, and generating the insurance policy data according to the updated discrete data and the associated data.

[0119] In steps S303 to S304 of some embodiments, in the process of processing discrete data, for each discrete data, a discrete variable corresponding to the discrete data is created, and the original variable value of the discrete variable is set, so that the meanings represented by them can be reflected by setting the original variable value, such as "social security participation", "labor dispatch", "this city", "this province". Then, the original variable value of the discrete variable is replaced based on the preset conversion rule to obtain the target discrete value. Specifically, the embodiment of the present application traverses each row of the discrete data, checks the original variable value of the discrete variable to be converted, and then replaces the original variable value with 1 and 0 according to the designed rules. After that, the discrete data is updated according to the target discrete value, and the converted target discrete value is integrated back into the original discrete data, and the insurance policy data is generated according to the updated discrete data and the associated data, so as to facilitate the subsequent enhancement of the model processing capability, improve the prediction accuracy, and enhance the flexibility of data analysis.

[0120] It should be noted that the serialized data in the embodiment of the present application can express the original state more finely. For example, the location of work can be divided into "whether in this city" and "whether in this province", which can more accurately capture the differences between individuals.

[0121] It can be understood that the conversion rules in the embodiments of the present application can be set according to the needs of the user. For example, for binary categorical variables, such as "yes / no", "yes / no", etc., they can be directly converted to 1 and 0; for multi-category variables, one-hot encoding or label encoding, etc. can be used. The embodiments of the present application do not make specific restrictions.

[0122] Step S305, clean up the policy data to obtain target policy data.

[0123] In step S305 of some embodiments, the policy data is cleaned up. Specifically, the policy data is checked for errors, duplications or inconsistencies, and duplicate records are deleted and erroneous values ​​are repaired, thereby cleaning up some invalid data, improving the accuracy and consistency of the data, and ensuring the reliability of the analysis results. In addition, the embodiments of the present application will also take appropriate methods to process blank or missing fields in the policy data, such as deletion, filling or interpolation, so as to reduce the incompleteness of the data, obtain the target policy data, and improve the quality of the target policy data.

[0124] See also Figure 4 In some embodiments, step S104 may also include but is not limited to steps S401 to S404.

[0125] It should be noted that the insurance company information includes operating cost information and the company's total policy premiums, wherein the operating cost information is used to characterize the operating conditions of the insurance company, and the company's total policy premiums are the total premiums of all the company's policies.

[0126] Step S401, determining the policy premium of the insurance policy corresponding to the policy information according to the policy information.

[0127] Step S402, determining the company claims ratio of the insurance company corresponding to the insurance company information according to the operating cost information.

[0128] Step S403, determining the policy impact value according to the policy claim ratio, the company claim ratio and the policy premium.

[0129] Step S404, calculate the ratio of the insurance policy impact value to the company's total insurance policy premium to determine the insurance impact value.

[0130] In steps S401 to S404 of some embodiments, in the process of determining the insurance impact value based on the policy claims ratio and historical policy data, the embodiment of the present application first determines the policy premium of the policy corresponding to the policy information based on the policy information, that is, the policy premium of a single policy, and then determines the company claims ratio of the insurance company corresponding to the insurance company information based on the operating cost information, so as to obtain the simple claims ratio of the company's profit. Thereafter, the policy impact value is determined based on the policy claims ratio, the company claims ratio and the policy premium. Specifically, the difference between the policy claims ratio and the company claims ratio is first calculated, and then the difference is multiplied by the policy premium to obtain the policy impact value. Finally, the ratio of the policy impact value to the company's total policy premium is calculated to determine the insurance impact value, so that the degree of impact of the policy on the insurance company corresponding to the insurance company information can be determined through the insurance impact value, and the benefits and risks of the policy can be evaluated through the insurance impact value.

[0131] It should be noted that the company's claims ratio is used to represent the minimum claims ratio required for user liability insurance to make a profit under the current operating conditions of the insurance company. For example, the premium of a policy is 100 yuan, and the various costs required for the insurance company's operation (marketing expenses, employee wages, workplace rent, etc.) allocated to this policy is 48 yuan. It can be seen that the simple claims ratio of the institution's profit is 52%.

[0132] It is understandable that the larger the policy premium and the higher the compensation ratio, the greater the impact, which further reflects that the lower the quality of the policy, the greater the loss of the insurance company.

[0133] See also Figure 5 In some embodiments, step S105 may also include but is not limited to steps S501 to S503.

[0134] Step S501: When the insurance impact value is greater than a first preset impact value, a first risk interval is generated according to the first preset impact value, and a first amount is determined as a risk amount threshold of the first risk interval.

[0135] Step S502: When the insurance impact value is greater than the second preset impact value and less than or equal to the first preset impact value, a second risk interval is generated according to the first preset impact value and the second preset impact value, and the second amount is determined as the risk amount threshold of the second risk interval.

[0136] Step S503: When the insurance impact value is less than or equal to the second preset impact value, a third risk interval is generated according to the second preset impact value, and the third amount is determined as the risk amount threshold of the third risk interval.

[0137] It should be noted that the first preset impact value is greater than the second preset impact value, and the first amount, the second amount and the third amount decrease in sequence.

[0138] In steps S501 to S503 of some embodiments, in the process of setting the risk level table according to the insurance impact value, the embodiments of the present application will compare the insurance impact value with different preset impact values. When the insurance impact value is greater than the first preset impact value, a first risk interval is generated according to the first preset impact value, that is, the value greater than the first preset impact value is determined as the value of the first risk interval, and the first amount is determined as the risk amount threshold of the first risk interval, that is, the maximum insurance amount that the first risk interval can bear; when the insurance impact value is greater than the second preset impact value and is less than or equal to the first preset impact value, a second risk interval is generated according to the first preset impact value and the second preset impact value. , wherein the first preset impact value and the second preset impact value are the two endpoints of the second risk interval respectively, and the second amount is determined as the risk amount threshold of the second risk interval, that is, the maximum insurance amount that the second risk interval can bear; when the insurance impact value is less than or equal to the second preset impact value, a third risk interval is generated according to the second preset impact value, that is, a value less than the second preset impact value is determined as the data of the third risk interval, and the third amount is determined as the risk amount threshold of the third risk interval, that is, the maximum insurance amount that the third risk interval can bear, thereby realizing the division of different risk intervals, and being able to divide the risk intervals into different risk levels, which is convenient for the subsequent formulation of insurance strategies.

[0139] It is worth noting that in the embodiment of the present application, the first preset impact value is greater than the second preset impact value, and the first amount, the second amount and the third amount decrease in sequence. Specifically, the embodiment of the present application takes the first preset impact value of 0.1% and the second preset impact value of -0.1% as an example to illustrate, and determines the interval greater than 0.1% as the first risk interval, the interval between -0.1% and 0.1% as the second risk interval, and the interval less than -0.1% as the third risk interval. The first risk interval is set to a high risk interval, the second risk interval is set to a medium risk interval, and the third risk interval is set to a low risk interval.

[0140] It is understandable that for insurance impact values ​​in the high-risk range, the embodiments of the present application will provide more comprehensive and high-value protection, such as adding additional insurance, increasing the amount of compensation, etc. For insurance impact values ​​in the low-risk range, a relatively simple and economical insurance plan can be provided.

[0141] See also Figure 6 In some embodiments, step S108 may also include but is not limited to steps S601 to S603.

[0142] It should be noted that insurance company information includes insurance premium rates.

[0143] Step S601, determining interval rules corresponding to the target risk interval according to insurance company information.

[0144] It should be noted that the interval rules are rules that limit the application scenarios of the property to be insured.

[0145] In step S601 of some embodiments, in the process of generating a target insurance policy based on the target risk amount threshold, insurance company information and user demand information, different risk intervals in the embodiments of the present application are configured with different interval rules, so the interval rules corresponding to the target risk interval are first determined based on the insurance company information, so as to facilitate the subsequent setting of different insurance policies according to the interval rules.

[0146] It is understandable that the embodiments of the present application will design corresponding interval rules for different risk levels, wherein the interval rules include core terms such as coverage items, deductibles, and compensation ratios.

[0147] Step S602, determining the intended insurance amount, insurance period and compensation amount of the property to be insured according to the user demand information.

[0148] In step S602 of some embodiments, the intended insured amount, insurance period and compensation amount of the property to be insured are determined based on the user demand information, so that the amount of insurance the user wants to insure the property to be insured can be determined through the intended insured amount, the number of years the user wants to insure the property to be insured can be determined through the insurance period, and the compensation amount for the property to be insured can be determined through the compensation amount, so that user needs can be clearly determined, which is convenient for formulating different insurance strategies in combination with user needs.

[0149] It is worth noting that user demand information also includes users' special demand information, such as emergency rescue, property repair assistance, legal advice, etc.

[0150] Step S603, when the intended insurance amount is less than or equal to the target risk amount threshold, and the insurance period and compensation amount meet the interval rule, a target insurance policy is generated according to the insurance premium rate, intended insurance amount, insurance period and compensation amount.

[0151] In step S603 of some embodiments, when the intended insurance amount is less than or equal to the target risk amount threshold, it means that the amount the user wants to insure is within the target risk amount threshold and is the maximum amount that the risk level of the target risk interval can bear, and the insurance period and compensation amount comply with the interval rules, indicating that the insurance period and compensation amount comply with the restriction requirements of the interval rules. At this time, the target insurance policy can be directly generated based on the insurance premium rate, intended insurance amount, insurance period and compensation amount, and the insurance policy can be adjusted and optimized according to customer needs and feedback, so that the target insurance policy can be personalized and generated while meeting user requirements, thereby improving customer satisfaction and the competitiveness of the insurance business.

[0152] It is worth noting that in the process of generating a target insurance policy based on insurance premiums, intended insured amounts, insurance periods, and compensation amounts, the embodiments of the present application can also obtain special demand information from user demand information, and then customize personalized terms based on the special demand information, such as special deductible agreements, value-added service terms, etc., to meet the specific requirements of customers.

[0153] See also Figure 7 , Figure 7 is a flow chart of a strategy customization method based on an evaluation model provided in another embodiment of the present application. Figure 7 The method may include but is not limited to step S701.

[0154] Step S701, when the intended insurance amount is greater than the target risk amount threshold, the insurance period does not meet the interval rules, or the compensation amount does not meet the interval rules, a target insurance policy is generated according to the target risk amount threshold, the insurance premium rate and the interval rules.

[0155] In step S701 of some embodiments, when the intended insurance amount exceeds the target risk amount threshold, that is, the intended insurance amount exceeds the maximum amount that the risk level of the target risk interval can bear, the insurance period exceeds the preset insurance period in the interval rules, or the compensation amount exceeds the preset compensation amount in the interval rules, it means that the current user needs are difficult to meet or there are risks, and it is necessary to generate a target insurance policy based on the target risk amount threshold, the insurance premium rate and the interval rules to ensure that the insurance amount can fully cover possible losses and is not too high to cause excessive premium burden, thereby improving the flexibility of policy generation, further improving user satisfaction, and reducing claims costs and risks.

[0156] See also Figure 8 The embodiment of the present application also provides a strategy customization device based on an evaluation model, the device comprising:

[0157] The data acquisition module 801 is used to acquire the insurance data to be evaluated and the user demand information, and acquire the environmental factor information of the property to be insured corresponding to the insurance data to be evaluated and the historical insurance policy data of the property to be insured, wherein the historical insurance policy data includes the insurance policy information and the insurance company information;

[0158] Data analysis module 802, used to analyze historical policy data and determine risk factors;

[0159] The quantitative evaluation module 803 is used to input the risk factors into the preset evaluation model for quantitative evaluation and output the policy loss ratio, wherein the policy loss ratio is used to characterize the profit and loss situation of the policy corresponding to the policy information;

[0160] An impact value determination module 804 is used to determine an insurance impact value based on the insurance policy claim ratio and historical insurance policy data, wherein the insurance impact value is used to represent the degree of impact of the insurance policy information on the insurance company corresponding to the insurance company information;

[0161] The level table setting module 805 is used to set a risk level table according to the insurance impact value, wherein the risk level table includes multiple risk intervals, and each risk interval is set with a risk amount threshold;

[0162] The risk assessment module 806 is used to input the insurance data to be assessed and the environmental factor information into the assessment model for risk assessment and output the risk assessment result;

[0163] The risk determination module 807 is used to determine the target risk interval corresponding to the risk assessment result in the risk level table, and determine the target risk amount threshold corresponding to the target risk interval;

[0164] The policy generation module 808 is used to generate a target insurance policy according to the target risk amount threshold, insurance company information and user demand information.

[0165] The specific implementation of the policy customization device based on the evaluation model is basically the same as the specific implementation of the policy customization method based on the evaluation model mentioned above, and will not be repeated here.

[0166] The embodiment of the present application also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned policy customization method based on the evaluation model. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0167] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0168] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0169] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the policy customization method based on the evaluation model in the embodiment of this application;

[0170] Input / output interface 903, used to implement information input and output;

[0171] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0172] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0173] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0174] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned policy customization method based on the evaluation model is implemented.

[0175] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0176] The policy customization method, device, electronic device and storage medium based on the evaluation model provided in the embodiments of the present application first obtain the insurance data to be evaluated and the user demand information, and obtain the environmental factor information of the property to be insured corresponding to the insurance data to be evaluated and the historical policy data of the property to be insured, so as to facilitate the subsequent judgment of the physical environment of the property to be insured and the factors that may cause risks to the property to be insured, and then perform data analysis on the historical policy data, analyze the risk factors affecting the property to be insured through the historical policy data, determine the risk factors, and facilitate the subsequent analysis of the compensation situation under different risk factors, input the risk factors into the preset evaluation model for quantitative evaluation, evaluate the various risks faced by the property to be insured, and output the policy claim ratio, so as to obtain the profit and loss situation of the policy corresponding to the policy information under different risk factors, so as to facilitate the subsequent risk evaluation of the insurance product, and then determine the insurance impact value according to the policy claim ratio and the historical insurance data, so as to determine the degree of influence of the policy information on the insurance company corresponding to the insurance company information, and on the basis of the policy claim ratio By combining other historical insurance data to analyze the impact of policy information, it is possible to accurately analyze the impact of policy information on insurance companies, improve the accuracy of policy analysis, and then set a risk level table based on the insurance impact value, thereby dividing multiple risk intervals and realizing accurate division of risks of different levels. Finally, the insurance data to be evaluated and the environmental factor information are input into the evaluation model for risk assessment, and the risk assessment results are output. It is possible to accurately assess the risk level of a specific type of insurance, realize accurate assessment of the insurance data to be evaluated, and improve the accuracy and efficiency of property insurance assessment. The target risk interval corresponding to the risk assessment result is determined in the risk level table, which can accurately determine the risk level of the property to be insured, and determine the target risk amount threshold corresponding to the target risk interval, so that the maximum amount threshold that the property to be insured can bear can be determined based on the risk assessment result, and then the target insurance strategy is generated based on the target risk amount threshold, insurance company information and user demand information, so that different insurance strategies can be customized according to user needs to improve user satisfaction.

[0177] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0178] It can be understood by those skilled in the art that Figure 1-9 The technical solutions shown in the figure do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown in the figure, or a combination of certain steps, or different steps.

[0179] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0180] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0181] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0182] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0183] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0184] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0185] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0186] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0187] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A strategy customization method based on an evaluation model, characterized in that: The method comprises: Obtaining insurance data to be evaluated and user demand information, and obtaining environmental factor information of the property to be insured corresponding to the insurance data to be evaluated and historical insurance policy data of the property to be insured, wherein the historical insurance policy data includes insurance policy information and insurance company information, and the environmental factor information is used to characterize information on risk factors affecting the property to be insured; Performing data analysis on the historical policy data to determine risk factors; Input the risk factor into a preset evaluation model for quantitative evaluation, and output the policy loss ratio, wherein the policy loss ratio is used to characterize the profit and loss situation of the policy corresponding to the policy information; Determine an insurance impact value according to the insurance policy claim ratio and the historical insurance policy data, wherein the insurance impact value is used to characterize the degree of influence of the insurance policy information on the insurance company corresponding to the insurance company information; A risk level table is set according to the insurance impact value, wherein the risk level table includes a plurality of risk intervals, and each risk interval is set with a risk amount threshold; Inputting the insurance data to be evaluated and the environmental factor information into the evaluation model for risk evaluation, and outputting the risk evaluation result; Determine a target risk interval corresponding to the risk assessment result in the risk level table, and determine a target risk amount threshold corresponding to the target risk interval; A target insurance policy is generated according to the target risk amount threshold, the insurance company information and the user demand information.

2. The strategy customization method based on the evaluation model according to claim 1, characterized in that: The performing of data analysis on the historical policy data to determine the risk factors includes: Standardizing the historical policy data to obtain multiple policy fields; Performing data association operations on all the policy fields through a preset claims system to obtain target policy data; Based on the preset single variable method, parameters of the target policy data are selected to determine the risk factors.

3. The strategy customization method based on the evaluation model according to claim 2 is characterized in that: The preset claim settlement system performs data association operation on all the policy fields to obtain target policy data, including: Performing data association operation on all the fields of the insurance policy through a preset claim system to obtain associated data and discrete data; For each discrete data, creating a discrete variable corresponding to the discrete data, and setting an original variable value of the discrete variable; Replacing the original variable value of the discrete variable based on a preset conversion rule to obtain a target discrete value; updating the discrete data according to the target discrete value, and generating policy data according to the updated discrete data and the associated data; The insurance policy data is cleaned to obtain target insurance policy data.

4. The strategy customization method based on the evaluation model according to claim 1, characterized in that: The insurance company information includes operating cost information and the company's total insurance premium; the insurance impact value is determined based on the insurance policy claim ratio and the historical insurance policy data, including: Determining, based on the policy information, the policy premium of the policy corresponding to the policy information; Determining the company loss ratio of the insurance company corresponding to the insurance company information according to the operating cost information; Determine the policy impact value according to the policy claim ratio, the company claim ratio and the policy premium; Calculate the ratio of the policy impact value to the company's total policy premium to determine the insurance impact value.

5. The strategy customization method based on the evaluation model according to claim 1, characterized in that: The step of setting a risk level table according to the insurance impact value comprises: When the insurance impact value is greater than a first preset impact value, a first risk interval is generated according to the first preset impact value, and a first amount is determined as a risk amount threshold of the first risk interval; When the insurance impact value is greater than the second preset impact value and less than or equal to the first preset impact value, a second risk interval is generated according to the first preset impact value and the second preset impact value, and the second amount is determined as the risk amount threshold of the second risk interval; When the insurance impact value is less than or equal to the second preset impact value, a third risk interval is generated according to the second preset impact value, and a third amount is determined as a risk amount threshold of the third risk interval; Among them, the first preset impact value is greater than the second preset impact value, and the first amount, the second amount and the third amount decrease in sequence.

6. The strategy customization method based on the evaluation model according to claim 1, characterized in that: The insurance company information includes insurance premium rates; generating a target insurance policy according to the target risk amount threshold, the insurance company information and the user demand information includes: Determining an interval rule corresponding to the target risk interval according to the insurance company information, wherein the interval rule is a rule that limits application scenarios of the property to be insured; Determine the intended insured amount, insurance period and compensation amount of the property to be insured according to the user demand information; When the intended insured amount is less than or equal to the target risk amount threshold, and the insurance period and the compensation amount meet the interval rule, a target insurance policy is generated based on the insurance premium rate, the intended insured amount, the insurance period and the compensation amount.

7. The strategy customization method based on the evaluation model according to claim 6 is characterized in that: After determining the intended insured amount, insurance period and compensation amount of the property to be insured according to the user demand information, the method further includes: When the intended insurance amount is greater than the target risk amount threshold, the insurance period does not comply with the interval rule, or the compensation amount does not comply with the interval rule, a target insurance policy is generated based on the target risk amount threshold, the insurance premium rate and the interval rule.

8. A strategy customization device based on an evaluation model, characterized in that: The device comprises: A data acquisition module, used to acquire the insurance data to be evaluated and user demand information, and to acquire the environmental factor information of the property to be insured corresponding to the insurance data to be evaluated and the historical insurance policy data of the property to be insured, wherein the historical insurance policy data includes insurance policy information and insurance company information; A data analysis module, used to analyze the historical policy data and determine risk factors; A quantitative evaluation module, used to input the risk factor into a preset evaluation model for quantitative evaluation and output a policy loss ratio, wherein the policy loss ratio is used to characterize the profit and loss situation of the policy corresponding to the policy information; An impact value determination module, used to determine an insurance impact value according to the insurance policy claim ratio and the historical insurance policy data, wherein the insurance impact value is used to characterize the degree of influence of the insurance policy information on the insurance company corresponding to the insurance company information; A level table setting module, used to set a risk level table according to the insurance impact value, wherein the risk level table includes a plurality of risk intervals, and each risk interval is set with a risk amount threshold; A risk assessment module, used for inputting the insurance data to be assessed and the environmental factor information into the assessment model for risk assessment and outputting the risk assessment result; A risk determination module, used to determine a target risk interval corresponding to the risk assessment result in the risk level table, and determine a target risk amount threshold corresponding to the target risk interval; A policy generation module is used to generate a target insurance policy based on the target risk amount threshold, the insurance company information and the user demand information.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the policy customization method based on the evaluation model described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the strategy customization method based on the evaluation model according to any one of claims 1 to 7 is implemented.

Images