Reinsurance protocol generation method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the technical field of artificial intelligence, is suitable for the field of finance or medical treatment, and relates to a reinsurance protocol generation method and device, computer equipment and a storage medium. Performing model training operation on the initialized machine learning model according to the historical environment data and the historical compensation data to obtain a trained machine learning model; receiving a reinsurance protocol generation request sent by the user terminal; inputting the current environment data into the trained machine learning model for model prediction operation to obtain a model prediction result; acquiring a preset reinsurance protocol rule in a system database; and performing protocol construction operation according to the model prediction result and the reinsurance protocol rule to obtain a target reinsurance protocol. According to the method, the stability of the rule engine and the prediction capability of the machine learning model are fully combined, automatic and intelligent generation of the reinsurance protocol is realized, and the protocol making efficiency and accuracy are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and is suitable for the fields of finance or medicine, and in particular relates to a reinsurance agreement generation method and device, a computer device and a storage medium. BACKGROUND

[0002] Reinsurance is a mechanism by which an insurance company transfers part of its insurance liability to other insurance companies (reinsurance companies) in order to diversify risks.

[0003] The traditional reinsurance agreement formulation process usually relies on human experience and expert judgment, involving a large amount of data analysis, risk assessment and clause design. This process not only consumes time and effort, but is also susceptible to human factors, resulting in inaccurate agreement design. Therefore, the traditional reinsurance agreement formulation method has the problem of low efficiency and accuracy. SUMMARY

[0004] The embodiments of the present application aim to provide a reinsurance agreement generation method, device, computer device and storage medium to solve the problem of low efficiency and accuracy of the traditional reinsurance agreement formulation method.

[0005] To solve the above technical problems, the embodiments of the present application provide a reinsurance agreement generation method, which adopts the following technical solutions:

[0006] Read a system database, and obtain historical environmental data and historical claim data corresponding to the historical environmental data in the system database;

[0007] Construct an initialized machine learning model, and perform model training operation on the initialized machine learning model according to the historical environmental data and the historical claim data, to obtain a trained machine learning model;

[0008] Receive a reinsurance agreement generation request sent by a user terminal, wherein the reinsurance agreement generation request includes current environmental data;

[0009] Input the current environmental data into the trained machine learning model to perform model prediction operation, and obtain a model prediction result;

[0010] Obtain a preset reinsurance agreement rule in the system database;

[0011] Perform agreement construction operation according to the model prediction result and the reinsurance agreement rule, to obtain a target reinsurance agreement

[0012] To solve the above technical problems, the embodiments of the present application also provide a reinsurance agreement generation device, which adopts the following technical solutions:

[0013] a historical data acquisition module configured to read a system database to acquire historical environment data and historical claim data corresponding to the historical environment data in the system database;

[0014] a model training module configured to construct an initialized machine learning model and perform a model training operation on the initialized machine learning model according to the historical environment data and the historical claim data to obtain a trained machine learning model;

[0015] a request acquisition module configured to receive a reinsurance agreement generation request sent by a user terminal, wherein the reinsurance agreement generation request comprises current environment data;

[0016] a model prediction module configured to input the current environment data into the trained machine learning model to perform a model prediction operation and obtain a model prediction result;

[0017] an agreement rule acquisition module configured to acquire preset reinsurance agreement rules in the system database;

[0018] an agreement construction module configured to perform an agreement construction operation according to the model prediction result and the reinsurance agreement rules to obtain a target reinsurance agreement.

[0019] To solve the above technical problems, the embodiments of the present application further provide a computer device, which adopts the technical scheme as follows:

[0020] comprising a memory and a processor, the memory storing computer readable instructions, and the processor implementing the steps of the reinsurance agreement generation method as described above when executing the computer readable instructions.

[0021] To solve the above technical problems, the embodiments of the present application further provide a computer readable storage medium, which adopts the technical scheme as follows:

[0022] The computer readable storage medium stores computer readable instructions, and the computer readable instructions implement the steps of the reinsurance agreement generation method as described above when executed by a processor.

[0023] The present application provides a reinsurance agreement generation method, comprising: reading a system database, obtaining historical environmental data and historical claims data corresponding to the historical environmental data from the system database; constructing an initialization machine learning model, and performing a model training operation on the initialization machine learning model based on the historical environmental data and the historical claims data to obtain a trained machine learning model; receiving a reinsurance agreement generation request sent by a user terminal, wherein the reinsurance agreement generation request includes current environmental data; inputting the current environmental data into the trained machine learning model to perform a model prediction operation to obtain a model prediction result; obtaining preset reinsurance agreement rules from the system database; and performing an agreement construction operation based on the model prediction result and the reinsurance agreement rules to obtain a target reinsurance agreement. Compared with the prior art, the present application fully combines the stability of the rule engine and the predictive capability of the machine learning model, realizes the automated and intelligent generation of reinsurance agreements, and improves the efficiency and accuracy of agreement formulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0025] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0026] Figure 2 This is a flowchart of the implementation of the reinsurance agreement generation method provided in an embodiment of the present application;

[0027] Figure 3 2 is a schematic diagram of the structure of a reinsurance agreement generating device provided in an embodiment of the present application;

[0028] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terms used in the specification are intended to describe the particular embodiments and are not intended to limit the application; the terms "include" and "have" and their any variations used in the specification and the claims and the above description of drawings are intended to cover the non-exclusive inclusion; the terms "first", "second" and the like used in the specification and the claims and the above description of drawings are intended to distinguish different objects, not to describe a particular order.

[0030] Reference herein to "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. It is expressly understood that the embodiments described herein are merely examples and are not intended to limit the scope of the application.

[0031] In order to make the person skilled in the art better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings below.

[0032] As shown in Figure 1 The system architecture 100 can include a terminal device 101, a network 102 and a server 103, and the terminal device 101 can be a notebook computer 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103. The network 102 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0033] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0034] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing, in addition to the notebook computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an electronic book reader, an MP3 player (Movi ng Pi cture Experts Group Aud i o Layer III, dynamic image expert compression standard audio layer III), an MP4 (Movi ng Pi cture Experts Group Audio Layer IV, dynamic image expert compression standard audio layer IV) player, a laptop computer and a desktop computer, etc.

[0035] The server 103 can be a server providing various services, for example, a background server providing support for the page displayed on the terminal device 101.

[0036] It should be noted that the reinsurance agreement generation method provided in the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the reinsurance agreement generation apparatus is generally arranged in a server / terminal device.

[0037] It should be understood that, Figure 1 The number of terminal devices, networks and servers in

[0038] With reference to Figure 2 , a flow chart of one embodiment of the reinsurance agreement generation method according to the present application is shown. The reinsurance agreement generation method includes steps S201, S202, S203, S204, S205, S206 and S207.

[0039] In step S201, a system database is read, and historical environment data and historical claim data corresponding to the historical environment data are obtained from the system database.

[0040] In the embodiments of the present application, the system first reads historical environment data (such as market environment data, agricultural insurance related data, etc.) and historical claim data corresponding to these environment data from a plurality of data sources (including a system database) through a data acquisition module. These data are the basis for training a machine learning model and can reflect the claim situation in the past under different environmental conditions, providing learning samples for the model.

[0041] In step S202, an initialized machine learning model is constructed, and model training operation is performed on the initialized machine learning model according to the historical environment data and the historical claim data, to obtain a trained machine learning model.

[0042] In the embodiments of the present application, the system builds an initialized machine learning model, which can be a risk prediction model, a parameter optimization model, etc.

[0043] In the embodiments of the present application, the initialized model is trained using historical environmental data and historical claim data obtained from the system database. During the training process, the model learns the association pattern between the environmental data and the claim data, so as to make accurate predictions when encountering similar environments in the future.

[0044] In step S203, a reinsurance agreement generation request sent by a user terminal is received, wherein the reinsurance agreement generation request includes current environmental data.

[0045] In the embodiments of the present application, the user terminal refers to a terminal device for executing the image processing method for preventing misuse of certificates provided by the present application. The user terminal can be a mobile terminal such as a mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a navigation device, etc., and a fixed terminal such as a digital TV, a desktop computer, etc. It should be understood that the examples of the user terminal herein are only for easy understanding and do not limit the present application.

[0046] In the embodiments of the present application, the user inputs a question or consultation through their terminal device (such as a mobile phone, a computer, etc.), and the input is received by the system. The current environmental data is the specific content that the user wants the system to predict the parameters of the reinsurance agreement based on the current environmental data. Specifically, the current environmental data can be "transaction data or payment data or business data or purchase data" related to financial institutions (such as banks, etc.), and the current environmental data can also be medical data related to medical scenarios, such as personal health records, prescriptions, test reports, etc. It should be understood that the examples of the current environmental data herein are only for easy understanding and do not limit the present application.

[0047] In the embodiments of the present application, when the user initiates a reinsurance agreement generation request through the terminal, the system receives the request and extracts the current environmental data (such as the current market situation, specific risk factors, etc.) contained in the request.

[0048] In step S204, the current environmental data is input into the trained machine learning model for model prediction operation, and the model prediction result is obtained.

[0049] In the embodiments of the present application, the received current environmental data is input into the trained machine learning model, and the model predicts the claim trend, risk level, etc. under the current environment according to the learned pattern, and outputs the model prediction result.

[0050] In step S205, preset reinsurance agreement rules are obtained from the system database.

[0051] In the embodiments of the present application, the system obtains preset reinsurance agreement rules from the system database or the rule engine module, which include risk allocation rules, liability division rules, threshold setting rules, etc., and are the basic framework for formulating reinsurance agreements.

[0052] In step S206, agreement construction operations are performed according to the model prediction results and the reinsurance agreement rules, and a target reinsurance agreement is obtained.

[0053] In the embodiments of the present application, the system combines the model prediction results and the preset reinsurance agreement rules, and performs agreement construction through the agreement generation module. Specifically, the rule engine module provides preliminary agreement parameter suggestions, and the machine learning model module performs prediction and optimization on these parameters. Finally, the agreement generation module fuses the outputs of the rule engine and the machine learning model to generate a reinsurance agreement that meets industry specifications.

[0054] In the embodiments of the present application, a reinsurance agreement generation method is provided, which includes: reading a system database, obtaining historical environmental data and historical claim data corresponding to the historical environmental data in the system database; constructing an initialized machine learning model, and performing model training operations on the initialized machine learning model according to the historical environmental data and the historical claim data to obtain a trained machine learning model; receiving a reinsurance agreement generation request sent by a user terminal, wherein the reinsurance agreement generation request includes current environmental data; inputting the current environmental data into the trained machine learning model to perform model prediction operations and obtain model prediction results; obtaining preset reinsurance agreement rules in the system database; performing agreement construction operations according to the model prediction results and the reinsurance agreement rules to obtain a target reinsurance agreement. Compared with the prior art, the present application fully combines the stability of the rule engine and the prediction ability of the machine learning model, realizes the automatic and intelligent generation of the reinsurance agreement, and improves the efficiency and accuracy of agreement formulation.

[0055] In some optional implementation manners of the embodiments of the present application, after the step of reading the system database and obtaining the historical environmental data and the historical claim data corresponding to the historical environmental data in the system database, the following steps are further included:

[0056] The historical environmental data and the historical claim data are subjected to data cleaning, normalization processing, feature extraction operations, and standardization processing.

[0057] In the embodiments of the present application, the collected data is subjected to cleaning, normalization processing, and extraction of key features such as claim frequency, claim amount, agency risk level, capital, business size, etc.

[0058] In the embodiments of the present application, removing noise data is mainly used to check and remove outliers, error records or duplicate data in the data, which may interfere with the training effect of the model. Specifically, for missing values existing in the data set, interpolation, mean filling, median filling or using a machine learning model to predict filling can be used for processing to ensure the integrity of the data.

[0059] In the embodiments of the present application, normalization processing can be to unify the data range of different features to the same scale, for example, scaling the data to the range of [0, 1] or [-1, 1]. Normalization processing can avoid some features dominating the model training process due to too large numerical range, and ensure that the contributions of each feature in the model are relatively balanced. Normalization processing helps to speed up the convergence speed of the machine learning model and improve the training efficiency.

[0060] In the embodiments of the present application, features that have a key impact on the generation of reinsurance agreements are extracted from the original data, such as claim frequency, claim amount, institution risk level, capital, business size, etc. The extracted features are combined into a feature vector as input of the machine learning model. The construction of the feature vector needs to consider the correlation and redundancy between the features to optimize the performance of the model.

[0061] In the embodiments of the present application, standardization processing is usually to convert the data into a normal distribution with a mean of 0 and a standard deviation of 1. This helps to eliminate the dimensional difference between different features, so that the model can treat each feature more fairly. Standardization processing can improve the stability of the machine learning model and reduce the performance fluctuations of the model caused by the difference in data distribution.

[0062] Compared with the prior art, the present application can significantly improve the quality of the data by performing preprocessing operations on the collected data, providing strong support for subsequent machine learning model training and reinsurance agreement generation. These steps ensure that the data input into the model is accurate, consistent and representative, thereby improving the efficiency and accuracy of model training, and further improving the intelligent level of reinsurance agreement generation.

[0063] In some optional implementation manners of the embodiments of the present application, the step of inputting the current environment data into the trained machine learning model to perform model prediction operation and obtaining the model prediction result comprises the following steps:

[0064] Obtaining external environment data;

[0065] Performing data fusion operation on the current environment data and the external environment data to obtain fused environment data;

[0066] The fused environmental data is input into the trained machine learning model for model prediction operation, obtaining a model prediction result.

[0067] In the embodiments of the present application, external environmental data may come from multiple channels, including but not limited to weather forecasting systems, economic indicator databases, policy change announcements, international financial market dynamics, etc. These data sources provide rich information about the macro environment and potential risks. In order to ensure the timeliness and accuracy of the prediction results, it is necessary to obtain the latest and reliable external environmental data. This may involve cooperation with third-party data providers or the establishment of its own data collection and updating mechanism.

[0068] In the embodiments of the present application, before data fusion, the current environmental data and external environmental data need to be aligned and standardized. This includes unifying data formats, aligning timestamps, converting dimensions, etc. to ensure that data from different sources can be compared and analyzed under the same framework.

[0069] In the embodiments of the present application, data fusion can use multiple strategies such as weighted average, feature-level fusion, decision-level fusion, etc. The choice of fusion strategy depends on the characteristics of the data, the needs of the prediction task, and the compatibility of the model.

[0070] In the embodiments of the present application, when implementing data fusion, it is necessary to consider how to effectively combine internal and external environmental data to extract the most valuable information for reinsurance agreement generation. This may involve complex algorithms and computing processes such as feature engineering in machine learning, multi-modal data processing in deep learning, etc.

[0071] In the embodiments of the present application, the fused environmental data needs to be evaluated to ensure its quality and applicability. Evaluation indicators may include data integrity, consistency, accuracy, and relevance to the prediction task, etc.

[0072] In the embodiments of the present application, before inputting the fused environmental data into the machine learning model, necessary preprocessing and feature extraction work need to be done to ensure that the data meets the input requirements of the model.

[0073] In the embodiments of the present application, the trained machine learning model is used to predict the fused environmental data. This step involves the inference process of the model, that is, generating a prediction result according to the input data.

[0074] In the embodiments of the present application, the obtained model prediction result needs to be interpreted and analyzed to understand its specific impact on reinsurance agreement generation. This may include risk exposure prediction, claim probability estimation, protocol clause optimization recommendations, etc.

[0075] In the embodiments of the present application, the model prediction results are fed back to the reinsurance agreement generation system to guide the construction and optimization of the agreement. At the same time, the prediction results can also be used in other related business scenarios, such as risk assessment, pricing strategy formulation, etc.

[0076] Compared with the prior art, the present application can effectively integrate current environmental data and external environmental data, use a trained machine learning model for prediction, and obtain a prediction result with actual value. This process provides important data support and decision basis for the intelligent generation of reinsurance agreements.

[0077] In some optional implementation manners of the embodiments of the present application, after the step of constructing the agreement according to the model prediction results and the reinsurance agreement rules to obtain the target reinsurance agreement, the following steps are further included:

[0078] performing an evaluation operation on the target reinsurance agreement to obtain an agreement evaluation result;

[0079] performing a first parameter optimization operation on the target reinsurance agreement according to the agreement evaluation result to obtain a first optimized reinsurance agreement.

[0080] In the embodiments of the present application, first, the system will perform a risk exposure evaluation on the target reinsurance agreement. This step aims to analyze the potential loss impact of the agreement on the insurance institution under different risk scenarios. By simulating various possible risk events, the system can quantify the effectiveness of the agreement in reducing risks, thereby identifying potential risk concentration points or overexposed areas.

[0081] In the embodiments of the present application, next, the system will perform a financial impact evaluation on the agreement. This step focuses on the impact of the agreement on the insurance institution's capital, profit, cash flow, and other financial indicators. By comparing the financial situation before and after the implementation of the agreement, the system can evaluate the contribution of the agreement to the financial health of the insurance institution and whether it may cause unnecessary financial burden.

[0082] In the embodiments of the present application, in addition to risk and financial evaluation, the system will also perform a compliance check on the agreement to ensure that the agreement content complies with relevant laws and regulations, regulatory requirements, and industry standards. This step helps to avoid legal risks and regulatory penalties and ensures the stable operation of the insurance institution. The above evaluation results are integrated to form a comprehensive evaluation of the target reinsurance agreement. This evaluation result will serve as the basis for subsequent optimization work.

[0083] In the embodiments of the present application, based on the evaluation results, the system will adjust the key parameters in the target reinsurance agreement. These parameters may include the allocation ratio, threshold, liability division, etc., which directly affect the risk dispersion effect and financial impact of the agreement. By adjusting these parameters, the system aims to optimize the risk and return balance of the agreement, making it more in line with the interests of the insurance institutions.

[0084] In the embodiments of the present application, during the parameter adjustment process, the system may use optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.) to assist decision-making. These algorithms can search for optimal solutions in multi-dimensional parameter space, improving the efficiency and accuracy of parameter adjustment.

[0085] In the embodiments of the present application, after parameter adjustment and optimization algorithm application, the system will generate a first optimized reinsurance agreement. This agreement should have improved in terms of risk exposure, financial impact, and compliance compared to the original target agreement, and is more in line with the expectations and requirements of insurance institutions.

[0086] Compared with the prior art, the system of the present application can generate a more scientific, reasonable and insurance institution interest-compliant reinsurance agreement, providing strong support for the stable operation and sustainable development of insurance institutions.

[0087] In some optional implementation manners of the embodiments of the present application, after the step of constructing the agreement according to the model prediction results and the reinsurance agreement rules to obtain the target reinsurance agreement, the following steps are further included:

[0088] Sending the target reinsurance agreement to the user terminal to show the target reinsurance agreement to the user;

[0089] Receiving feedback information related to the target reinsurance agreement sent by the user terminal;

[0090] Performing a second parameter optimization operation on the target reinsurance agreement according to the feedback information to obtain a second optimized reinsurance agreement.

[0091] In the embodiments of the present application, the system will send the generated target reinsurance agreement to the user's terminal device, such as a computer, tablet or mobile phone, through a secure communication channel. This step ensures that the user can view the agreement content in a timely and convenient manner.

[0092] In the embodiments of the present application, user feedback may involve questions about agreement terms, suggested modifications, acceptance of specific terms, etc. The system should be able to record and organize these feedbacks for subsequent analysis and processing.

[0093] In the embodiments of the present application, after receiving the user feedback information, the system will conduct in-depth analysis on the collected user feedback, identify the issues of common concern, the acceptance of the protocol terms, and the potential improvement points. Based on the results of the feedback analysis, the system will adjust the key parameters in the target reinsurance agreement. These parameters may include the allocation ratio, threshold, liability division, etc., aiming to better meet the needs and expectations of users.

[0094] In the embodiments of the present application, during the parameter adjustment process, the system may again use optimization algorithms (such as reinforcement learning, genetic algorithm, etc.) to assist decision-making, ensuring that the adjusted agreement achieves a better balance between risk and return.

[0095] In the embodiments of the present application, after the parameter adjustment and optimization algorithm application, the system will generate a second optimized reinsurance agreement. This agreement, based on full consideration of user feedback, should be more in line with the actual needs and interests of users.

[0096] Compared with the prior art, the system of the present application not only can generate a reinsurance agreement that meets business rules and market demand, but also can continuously improve the applicability and satisfaction of the agreement through user interaction, laying a foundation for establishing a more stable and mutually trusted cooperative relationship between insurance institutions and users.

[0097] In some optional implementation manners of the embodiments of the present application, after the step of performing second parameter optimization operation on the target reinsurance agreement according to the feedback information to obtain a second optimized reinsurance agreement, the following steps are further included:

[0098] Performing model optimization operation on the trained machine learning model according to the second optimized reinsurance agreement and the current environmental data.

[0099] In the embodiments of the present application, after completing the second parameter optimization operation on the target reinsurance agreement and obtaining the second optimized reinsurance agreement, the system needs to further utilize this optimization result and the current environmental data to perform model optimization operation on the previously trained machine learning model. This step is crucial for continuously improving the prediction accuracy and adaptability of the model.

[0100] In the embodiments of the present application, first, the system needs to extract key features from the second optimized reinsurance agreement, which may include optimized allocation ratio, threshold, liability division, etc. These features reflect the specific impact of user feedback and market changes on the agreement. At the same time, the system also needs to obtain the latest current environmental data, including market trends, economic indicators, policy changes, etc., which have important influence on the formulation of reinsurance agreement.

[0101] In the embodiments of the present application, the extracted protocol features and current environmental data are preprocessed, including data cleaning, normalization, feature selection, etc., to ensure the quality and consistency of the data and provide a reliable foundation for model optimization.

[0102] In the embodiments of the present application, the trained machine learning model is evaluated before optimization to understand its performance on the current data set, including accuracy, recall rate, F1 score, etc., to determine the direction and focus of optimization.

[0103] In the embodiments of the present application, the parameters of the machine learning model are adjusted according to the features of the second optimized reinsurance agreement and the current environmental data. This may include adjusting the weights, biases, learning rates, etc. of the model to improve the model's fitting ability for specific data patterns.

[0104] In the embodiments of the present application, in addition to parameter adjustment, improvements can be made to the machine learning algorithm itself, such as introducing new feature engineering methods, using more advanced model architectures (such as deep learning models), ensemble learning, etc., to improve the predictive performance of the model.

[0105] In the embodiments of the present application, incremental learning is used, and the second optimized reinsurance agreement and its corresponding environmental data are added to the existing training set to retrain the model, so that the model can learn the latest market dynamics and user demand.

[0106] In the embodiments of the present application, cross-validation can be used to evaluate the performance of the optimized machine learning model to ensure the stability and generalization ability of the model on different data sets.

[0107] In the embodiments of the present application, comparative experiments can be designed to test the models before and after optimization on the same data set and compare their prediction accuracy, efficiency, etc. to quantify the optimization effect.

[0108] Compared with the prior art, the present application can use the second optimized reinsurance agreement and the current environmental data to continuously optimize the trained machine learning model, improve the prediction accuracy and adaptability of the model, and provide a more reliable and efficient tool for intelligent generation of reinsurance agreements.

[0109] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Artificial intelligence (AI) is the use of digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0110] The artificial intelligence basic technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric identification technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0111] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through computer readable instructions, and the computer readable instructions can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of each method. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) and other non-volatile storage media, or a random access memory (RAM) and the like.

[0112] It should be understood that, although each step in the flowchart of the accompanying drawings is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other orders. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or other steps, sub-steps or stages.

[0113] Further referring to Figure 3 , as an implementation of the method shown in Figure 2 , the present application provides an embodiment of a reinsurance agreement generation device, which corresponds to the method embodiment shown in Figure 2 , and the device can be applied to various electronic devices.

[0114] As shown in Figure 3 , the reinsurance agreement generation device 200 of the embodiment of the present application comprises:

[0115] The historical data acquisition module 210 is configured to read a system database, and acquire historical environmental data and historical claim data corresponding to the historical environmental data in the system database.

[0116] The model training module 220 is configured to construct an initialized machine learning model, and perform model training operation on the initialized machine learning model according to the historical environmental data and the historical claim data, to obtain a trained machine learning model.

[0117] The request obtaining module 230 is configured to receive a reinsurance agreement generation request sent by a user terminal, wherein the reinsurance agreement generation request comprises current environment data.

[0118] The model prediction module 240 is configured to input the current environment data into the trained machine learning model to perform a model prediction operation, and obtain a model prediction result.

[0119] The agreement rule obtaining module 250 is configured to obtain a preset reinsurance agreement rule from a system database.

[0120] The agreement construction module 260 is configured to perform an agreement construction operation according to the model prediction result and the reinsurance agreement rule, and obtain a target reinsurance agreement.

[0121] In the embodiment of the present application, a reinsurance agreement generation device 200 is provided, which comprises: a historical data obtaining module 210 configured to read a system database, and obtain historical environment data and historical claim data corresponding to the historical environment data from the system database; a model training module 220 configured to construct an initialized machine learning model, and perform a model training operation on the initialized machine learning model according to the historical environment data and the historical claim data, and obtain a trained machine learning model; a request obtaining module 230 configured to receive a reinsurance agreement generation request sent by a user terminal, wherein the reinsurance agreement generation request comprises current environment data; a model prediction module 240 configured to input the current environment data into the trained machine learning model to perform a model prediction operation, and obtain a model prediction result; an agreement rule obtaining module 250 configured to obtain a preset reinsurance agreement rule from the system database; and an agreement construction module 260 configured to perform an agreement construction operation according to the model prediction result and the reinsurance agreement rule, and obtain a target reinsurance agreement. Compared with the prior art, the present application fully combines the stability of the rule engine and the prediction ability of the machine learning model, realizes the automatic and intelligent generation of the reinsurance agreement, and improves the efficiency and accuracy of the agreement formulation.

[0122] In some optional implementation manners of the embodiment of the present application, the reinsurance agreement generation device 200 described above further comprises:

[0123] The preprocessing module is configured to perform data cleaning, normalization processing, feature extraction operation and standardization processing on the historical environment data and the historical claim data.

[0124] In some optional implementation manners of the embodiment of the present application, the model prediction module comprises:

[0125] The external data obtaining sub-module is configured to obtain external environment data.

[0126] The data fusion submodule is configured to perform a data fusion operation on the current environment data and the external environment data to obtain fused environment data.

[0127] The model prediction submodule is configured to input the fused environment data into the trained machine learning model to perform a model prediction operation to obtain a model prediction result.

[0128] In some optional implementations of the embodiments of the present application, the reinsurance agreement generation apparatus 200 further includes:

[0129] The agreement evaluation module is configured to perform an agreement evaluation operation on the target reinsurance agreement to obtain an agreement evaluation result.

[0130] The first parameter optimization module is configured to perform a first parameter optimization operation on the target reinsurance agreement according to the agreement evaluation result to obtain a first optimized reinsurance agreement.

[0131] In some optional implementations of the embodiments of the present application, the reinsurance agreement generation apparatus 200 further includes:

[0132] The agreement display module is configured to send the target reinsurance agreement to the user terminal to display the target reinsurance agreement to the user.

[0133] The feedback information acquisition module is configured to receive feedback information related to the target reinsurance agreement sent by the user terminal.

[0134] The second parameter optimization module is configured to perform a second parameter optimization operation on the target reinsurance agreement according to the feedback information to obtain a second optimized reinsurance agreement.

[0135] In some optional implementations of the embodiments of the present application, the reinsurance agreement generation apparatus 200 further includes:

[0136] The model optimization module is configured to perform a model optimization operation on the trained machine learning model according to the second optimized reinsurance agreement and the current environment data.

[0137] To solve the above technical problems, the embodiments of the present application further provide a computer device. For details, please refer to Figure 4 , Figure 4 The basic structure block diagram of the computer device of the embodiments of the present application is shown in FIG. 2.

[0138] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 which are communicatively connected by a system bus. It should be noted that the computer device 300 is only shown with components 310-330, but it should be understood that not all of the shown components are required to be implemented, and more or less components can be alternatively implemented. Among them, those skilled in the art can understand that the computer device herein is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0139] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The computer device can interact with the user through a keyboard, a mouse, a remote controller, a touchpad, a voice control device, and the like.

[0140] The memory 310 includes at least one type of readable storage medium, including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or a memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like. Of course, the memory 310 can also include both the internal storage unit and the external storage device of the computer device 300. In the embodiments of the present application, the memory 310 is generally used to store an operating system and various application software installed in the computer device 300, such as computer readable instructions of the reinsurance agreement generation method, and the like. In addition, the memory 310 can also be used to temporarily store various data that have been output or will be output.

[0141] The processor 320 may, in some embodiments, be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiments of the present application, the processor 320 is used to run computer readable instructions stored in the memory 310 or process data, for example, computer readable instructions of the reinsurance agreement generation method.

[0142] The network interface 330 can include a wireless network interface or a wired network interface, and is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0143] The computer device provided in the present application fully combines the stability of the rule engine and the prediction ability of the machine learning model, realizes the automatic and intelligent generation of the reinsurance agreement, and improves the efficiency and accuracy of the agreement making.

[0144] The present application also provides another implementation, that is, to provide a computer readable storage medium, the computer readable storage medium stores computer readable instructions, the computer readable instructions can be executed by at least one processor, so that the at least one processor executes the steps of the reinsurance agreement generation method as described above.

[0145] The computer readable storage medium provided in the present application fully combines the stability of the rule engine and the prediction ability of the machine learning model, realizes the automatic and intelligent generation of the reinsurance agreement, and improves the efficiency and accuracy of the agreement making.

[0146] Through the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) execute the methods described in various embodiments of the present application.

[0147] Obviously, the above-described embodiments are only some embodiments but not all the embodiments of the present application, the preferred embodiments of the present application are shown in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent replacements to some technical features therein. Any equivalent structure made by using the content of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the patent protection scope of the present application.

Claims

1. A method for generating a reinsurance agreement, characterized in that: The steps include: Reading a system database, and obtaining historical environmental data and historical claims data corresponding to the historical environmental data from the system database; Constructing an initialized machine learning model, and performing a model training operation on the initialized machine learning model based on the historical environmental data and the historical claims data to obtain a trained machine learning model; receiving a reinsurance agreement generation request sent by a user terminal, wherein the reinsurance agreement generation request includes current environment data; Inputting the current environment data into the trained machine learning model to perform a model prediction operation to obtain a model prediction result; Obtaining preset reinsurance agreement rules from the system database; An agreement construction operation is performed according to the model prediction result and the reinsurance agreement rules to obtain a target reinsurance agreement.

2. The reinsurance agreement generation method according to claim 1, characterized in that: After the step of reading the system database and obtaining the historical environmental data and the historical claims data corresponding to the historical environmental data in the system database, the following step is also included: The historical environmental data and the historical claims data are subjected to data cleaning, normalization, feature extraction and standardization.

3. The reinsurance agreement generation method according to claim 1, characterized in that: The step of inputting the current environment data into the trained machine learning model to perform a model prediction operation to obtain a model prediction result specifically includes the following steps: Obtain external environment data; Performing a data fusion operation on the current environment data and the external environment data to obtain fused environment data; The fusion environment data is input into the trained machine learning model to perform model prediction operation to obtain the model prediction result.

4. The reinsurance agreement generation method according to claim 1, wherein: After the step of constructing an agreement based on the model prediction results and the reinsurance agreement rules to obtain a target reinsurance agreement, the following steps are also included: performing an evaluation operation on the target reinsurance agreement to obtain an agreement evaluation result; A first parameter optimization operation is performed on the target reinsurance agreement according to the agreement evaluation result to obtain a first optimized reinsurance agreement.

5. The reinsurance agreement generation method according to claim 1, characterized in that: After the step of constructing an agreement based on the model prediction results and the reinsurance agreement rules to obtain a target reinsurance agreement, the following steps are also included: sending the target reinsurance agreement to the user terminal to display the target reinsurance agreement to the user; receiving feedback information related to the target reinsurance agreement sent by the user terminal; performing a second parameter optimization operation on the target reinsurance agreement based on the feedback information to obtain a second optimized reinsurance agreement.

6. The reinsurance agreement generation method according to claim 5, characterized in that: After the step of performing a second parameter optimization operation on the target reinsurance agreement according to the feedback information to obtain a second optimized reinsurance agreement, the method further includes the following steps: performing a model optimization operation on the trained machine learning model according to the second optimized reinsurance agreement and the current environmental data.

7. A reinsurance agreement generating device, characterized in that: include: A historical data acquisition module is used to read a system database and acquire historical environmental data and historical claims data corresponding to the historical environmental data from the system database; A model training module is used to construct an initialized machine learning model and perform a model training operation on the initialized machine learning model based on the historical environmental data and the historical claims data to obtain a trained machine learning model; a request acquisition module, configured to receive a reinsurance agreement generation request sent by a user terminal, wherein the reinsurance agreement generation request includes current environment data; A model prediction module is used to input the current environment data into the trained machine learning model to perform a model prediction operation and obtain a model prediction result; an agreement rule acquisition module, configured to acquire preset reinsurance agreement rules from the system database; An agreement construction module is used to perform an agreement construction operation based on the model prediction results and the reinsurance agreement rules to obtain a target reinsurance agreement.

8. The reinsurance agreement generating device according to claim 7, characterized in that: The device further comprises: The preprocessing module is used to perform data cleaning, normalization, feature extraction and standardization on the historical environmental data and the historical claims data.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the reinsurance agreement generation method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the reinsurance agreement generation method according to any one of claims 1 to 6.

Images