Data generation method and device based on artificial intelligence, computer equipment and medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to a data generation method and device based on artificial intelligence, computer equipment and a storage medium. Performing data assessment on the target health data based on the health risk assessment model to obtain a health risk assessment result; performing data evaluation on the target health data based on a health improvement potential evaluation model to obtain a health improvement potential evaluation result; performing data scoring on the target health data based on a living habit scoring model to obtain a living habit score; generating a health score based on the health risk assessment result, the health improvement potential assessment result and the living habit score; generating target insurance premium discount data based on the health score; and sending the target insurance premium discount data to the customer. In addition, the health score may be stored in a blockchain. The method can be applied to an insurance premium processing scene in the financial field, and compared with an existing evaluation mode based on static information, the method has higher accuracy and flexibility.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology and can be applied to the field of financial technology, and in particular to data generation methods, devices, computer equipment and storage media based on artificial intelligence. Background Art

[0002] In the traditional insurance industry, premium pricing has long relied primarily on static customer information, such as age, gender, occupation, and medical history. While these factors can reflect a customer's health risk level to a certain extent, their fixed nature and lags make it difficult to comprehensively and real-timely assess the dynamic changes in a customer's health status. Specifically, static information often only provides a snapshot of a customer's health status at a specific point in time, failing to capture subsequent trends of improvement or deterioration. This makes it difficult to accurately match premium pricing to a customer's actual current and future health risks.

[0003] This pricing method based on static information has the following drawbacks: 1. Lack of precision: Because it does not take into account the dynamic changes in the customer's health status, the premium pricing may be too high or too low, and cannot accurately reflect the customer's true risk level. For customers whose health status continues to improve, excessively high premiums may constitute an unfair financial burden; while for customers whose health risks gradually increase, excessively low premiums may expose the insurance company to the risk of claims. 2. Lack of flexibility: The static pricing model cannot incentivize customers to actively improve their health status. If customers know that their premiums will not be adjusted due to changes in health behaviors, they will lack the motivation to adopt a healthy lifestyle, such as regular exercise and a balanced diet. This is not only detrimental to the customer's personal health management, but also goes against the original intention of insurance to promote the overall health level of society.

[0004] Furthermore, with technological advancements and rising awareness of health management, customers are increasingly demanding personalized and dynamic insurance services. Traditional static pricing models are no longer able to meet the diverse demands of the market, creating an urgent need for a new mechanism that can assess customer health status in real time and dynamically adjust premium pricing. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to propose a data generation method, device, computer equipment and storage medium based on artificial intelligence to solve the technical problem that the existing pricing method based on static information has low accuracy and flexibility.

[0006] In a first aspect, a data generation method based on artificial intelligence is provided, comprising:

[0007] Obtaining the customer's target health data; wherein the target health data includes basic health data, exercise data, and life habit data;

[0008] Performing data evaluation on the target health data based on a preset health risk assessment model to obtain corresponding health risk assessment results;

[0009] Performing data evaluation on the target health data based on a preset health improvement potential evaluation model to obtain corresponding health improvement potential evaluation results;

[0010] Scoring the target health data based on a preset lifestyle habit scoring model to obtain a corresponding lifestyle habit score;

[0011] generating a health score corresponding to the customer based on the health risk assessment result, the health improvement potential assessment result, and the lifestyle score;

[0012] generating target premium discount data corresponding to the customer based on the health score;

[0013] The target premium discount data is sent to the customer.

[0014] In a second aspect, a data generation device based on artificial intelligence is provided, comprising:

[0015] A first acquisition module is used to acquire the customer's target health data; wherein the target health data includes basic health data, exercise data, and life habit data;

[0016] A first evaluation module is used to perform data evaluation on the target health data based on a preset health risk evaluation model to obtain a corresponding health risk evaluation result;

[0017] A second evaluation module is used to perform data evaluation on the target health data based on a preset health improvement potential evaluation model to obtain a corresponding health improvement potential evaluation result;

[0018] A scoring module is used to score the target health data based on a preset lifestyle scoring model to obtain a corresponding lifestyle score;

[0019] A first generating module is configured to generate a health score corresponding to the customer based on the health risk assessment result, the health improvement potential assessment result, and the lifestyle score;

[0020] A second generating module is configured to generate target premium discount data corresponding to the customer based on the health score;

[0021] The first sending module is used to send the target premium discount data to the customer.

[0022] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned artificial intelligence-based data generation method when executing the computer program.

[0023] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based data generation method are implemented.

[0024] In the solution implemented by the above-mentioned artificial intelligence-based data generation method, device, computer equipment and storage medium, the customer's target health data is first obtained; wherein, the target health data includes basic health data, exercise data and lifestyle data; then, the target health data is evaluated based on a preset health risk assessment model to obtain a corresponding health risk assessment result; and the target health data is evaluated based on a preset health improvement potential assessment model to obtain a corresponding health improvement potential assessment result; and the target health data is scored based on a preset lifestyle scoring model to obtain a corresponding lifestyle score; then, a health score corresponding to the customer is generated based on the health risk assessment result, the health improvement potential assessment result and the lifestyle score; subsequently, target premium discount data corresponding to the customer is generated based on the health score; and finally, the target premium discount data is sent to the customer. This application obtains the customer's target health data, and then processes the target health data based on the health risk assessment model, the health improvement potential assessment model, and the lifestyle scoring model. It generates a health score corresponding to the customer based on the health risk assessment results, the health improvement potential assessment results, and the lifestyle score output by the model, and then generates target premium discount data corresponding to the customer based on the health score, and sends the target premium discount data to the customer. By combining the use of the health risk assessment model, the health improvement potential assessment model, and the lifestyle scoring model, this application can update the health score and premium discount data in real time according to changes in the customer's health data. Compared with the existing evaluation method based on static information, the premium processing method of this application has higher accuracy and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] 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.

[0026] Figure 1is an exemplary system architecture diagram to which the present application may be applied;

[0027] Figure 2 is a flow chart of an embodiment of an artificial intelligence-based data generation method according to the present application;

[0028] Figure 3 is a structural diagram of an embodiment of an artificial intelligence-based data generation device according to the present application;

[0029] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0031] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0033] like Figure 1 As shown, system architecture 100 may include a terminal device 101, a network 102, and a server 103. Terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. Network 102 is a medium for providing a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0034] The user can use the terminal device 101 to interact with the server 103 via 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.

[0035] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0036] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0037] It should be noted that the artificial intelligence-based data generation method provided in the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based data generation device is generally set in the server / terminal device.

[0038] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0039] Continue to refer Figure 2 , shows a flow chart of an embodiment of the data generation method based on artificial intelligence according to the present application. According to different needs, the order of the steps in the flow chart can be changed, and some steps can be omitted. The data generation method based on artificial intelligence provided by the embodiment of the present application can be applied to any scenario that requires premium processing, and the data generation method based on artificial intelligence can be applied to products in these scenarios, for example, premium processing scenarios in the financial insurance field. The data generation method based on artificial intelligence includes the following steps:

[0040] Step S201, obtaining the customer's target health data; wherein the target health data includes basic health data, exercise data and life habit data.

[0041] In this embodiment, the data generation method based on artificial intelligence is executed on the electronic device (e.g. Figure 1 The server / terminal device shown in the figure) can obtain the customer's target health data through a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wi deband) connection, and other wireless connection methods currently known or developed in the future. The execution subject of this application is a premium processing system, which can be referred to as the system. This application can be applied to business scenarios of intelligent generation of premium discount data in the financial insurance field. Among them, the customer's health data can be collected in real time through smart wearable devices (such as smart bracelets, smart watches) or health monitoring apps, including but not limited to: basic health data: heart rate, blood pressure, blood oxygen, weight, height, BMI, etc.; exercise data: number of steps, exercise duration, exercise intensity, etc.; life habit data: sleep quality, diet records, smoking and drinking conditions, etc. In addition, the specific implementation process of obtaining the customer's target health data will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0042] Step S202: performing data evaluation on the target health data based on a preset health risk evaluation model to obtain a corresponding health risk evaluation result.

[0043] In this embodiment, by inputting the target health data into the above-mentioned health risk assessment model, the health risk assessment model will perform a health risk assessment on the target health data, predict the risk of chronic diseases or major diseases in the future, and output the corresponding health risk assessment results (such as the probability of disease risk). The specific construction process of the above-mentioned health risk assessment model will be further described in detail in the subsequent specific embodiments of this application and will not be elaborated on here.

[0044] Step S203 , performing data evaluation on the target health data based on a preset health improvement potential evaluation model to obtain a corresponding health improvement potential evaluation result.

[0045] In this embodiment, by inputting the target health data into the above-mentioned health improvement potential assessment model, the health improvement potential assessment model will assess the possibility of health improvement based on the changing trend of the customer's health data and output the corresponding health improvement potential assessment result (such as the improvement possibility level). The construction process of the above-mentioned health improvement potential assessment model includes the following: Model selection: Since the health improvement potential assessment needs to assess the possibility of health improvement based on the changing trend of the customer's health data, the time series analysis model can well process time series data and capture the changing patterns of the data. Therefore, a time series analysis model, such as the ARIMA model, is selected. Data preparation: The customer's health data over a period of time, such as heart rate, blood pressure, exercise data, etc., is selected and arranged in chronological order to form time series data. Model training: Stationarity test and seasonality analysis are performed on the time series data. Based on the analysis results, appropriate ARIMA model parameters (p, d, q) are selected. The model is trained using historical time series data to estimate the model parameters. Model evaluation: The model's fitting effect and predictive ability are evaluated through indicators such as residual analysis and prediction error to ensure that the model can accurately assess the customer's health improvement potential, thereby constructing the required health improvement potential assessment model.

[0046] Step S204: scoring the target health data based on a preset lifestyle habit scoring model to obtain a corresponding lifestyle habit score.

[0047] In this embodiment, by inputting the target health data into the above-mentioned lifestyle scoring model, the lifestyle scoring model will evaluate the rationality of the customer's health behavior based on their lifestyle habits such as diet, exercise, and sleep, and output a corresponding lifestyle score (such as excellent, good, average, or poor). Among them, the construction process of the above-mentioned lifestyle scoring model includes: Model selection: The lifestyle scoring requires a classification and evaluation of the customer's lifestyle habits such as diet, exercise, and sleep. The decision tree model can divide the data into different categories based on different feature conditions and intuitively display the evaluation rules of lifestyle habits. Therefore, the decision tree model is selected. Data preparation: Features related to the customer's lifestyle habits are extracted from the data, such as diet records (regularity, food types, etc.), exercise data (number of steps, exercise duration, etc.), sleep quality (sleep duration, sleep depth, etc.) as independent variables, and the lifestyle score level is used as the dependent variable. Model training: The decision tree model is trained using the training set. By adjusting the model parameters, such as the tree depth and splitting criteria, the model structure is optimized to improve the model's classification accuracy. Model evaluation: Use indicators such as confusion matrix, accuracy, and precision to evaluate the accuracy of the model's lifestyle scoring, and then build a lifestyle scoring model that meets performance requirements.

[0048] Step S205 , generating a health score corresponding to the customer based on the health risk assessment result, the health improvement potential assessment result, and the lifestyle score.

[0049] In this embodiment, the specific implementation process of generating the health score corresponding to the customer based on the health risk assessment results, the health improvement potential assessment results and the lifestyle score will be described in further detail in subsequent specific embodiments of this application and will not be elaborated on here.

[0050] Step S206: Generate target premium discount data corresponding to the customer based on the health score.

[0051] In this embodiment, the specific implementation process of generating the target premium discount data corresponding to the customer based on the health score will be further described in detail in subsequent specific embodiments of this application and will not be elaborated on here.

[0052] Step S207: Send the target premium discount data to the customer.

[0053] In this embodiment, the specific implementation process of sending the target premium discount data to the customer will be further described in detail in subsequent specific embodiments of this application and will not be elaborated on here.

[0054] The present application first obtains the target health data of the customer; wherein the target health data includes basic health data, exercise data and lifestyle data; then the target health data is evaluated based on a preset health risk assessment model to obtain a corresponding health risk assessment result; and the target health data is evaluated based on a preset health improvement potential assessment model to obtain a corresponding health improvement potential assessment result; and the target health data is scored based on a preset lifestyle scoring model to obtain a corresponding lifestyle score; then a health score corresponding to the customer is generated based on the health risk assessment result, the health improvement potential assessment result and the lifestyle score; subsequently, target premium discount data corresponding to the customer is generated based on the health score; and finally, the target premium discount data is sent to the customer. The present application obtains the target health data of the customer, and then processes the target health data based on a combination of a health risk assessment model, a health improvement potential assessment model and a lifestyle scoring model, and generates a health score corresponding to the customer based on the health risk assessment result, the health improvement potential assessment result and the lifestyle score output by the model, and then generates target premium discount data corresponding to the customer based on the health score, and sends the target premium discount data to the customer. This application combines the use of health risk assessment models, health improvement potential assessment models and lifestyle habit scoring models to update health scores and premium discount data in real time based on changes in customer health data. Compared with existing assessment methods based on static information, the premium processing method of this application has higher accuracy and flexibility.

[0055] In some optional implementations, before step S202, the electronic device may further perform the following steps:

[0056] Obtain customer health data for a pre-collected historical time period.

[0057] In this embodiment, all customer health data within a historical time period can be queried from a database storing customer health data. The time period for the historical time period is not specifically limited and can be set according to actual business needs, such as within the past year.

[0058] Corresponding health sample data is constructed based on the customer health data.

[0059] In this embodiment, the corresponding processed data can be obtained by performing data cleaning and data annotation on the customer's health data, and then features related to health risks, such as age, gender, basic health data (heart rate, blood pressure, blood oxygen, etc.), family medical history, etc., are selected from the processed data as independent variables, and whether the customer suffers from chronic diseases or major diseases is used as the dependent variable to construct the corresponding health sample data.

[0060] The healthy sample data is divided into a training set and a test set.

[0061] In this embodiment, the above-mentioned healthy sample data can be divided into a training set and a test set according to a preset division ratio. There is no specific limitation on the selection of the division ratio, and it can be set according to actual business needs, for example, it can be set to 7:3.

[0062] The preset machine learning model is trained based on the training set to obtain a trained first model.

[0063] In this embodiment, the selection of the above-mentioned machine learning model can be determined based on actual processing requirements. Since the purpose of health risk assessment is to predict the customer's future risk of chronic diseases or major diseases, the logistic regression model is selected because it is simple to understand and highly interpretable, and can output the impact of each feature on risk. Specifically, the logistic regression model is trained using the above-mentioned training set to obtain a first model with risk assessment function.

[0064] The first model is evaluated based on the test set to obtain a corresponding evaluation result, and the first model is optimized based on the evaluation result to obtain a corresponding second model.

[0065] In this embodiment, the trained first model can be evaluated on the test set by using indicators such as accuracy, recall rate, and F1 value, and the first model can be adapted and optimized based on the obtained evaluation results. Specifically, the model parameters, such as regularization parameters, can be adjusted to prevent model overfitting and improve the accuracy and generalization ability of the model on the test set, until a second model that can accurately predict the customer's health risks is obtained.

[0066] The second model is used as the health risk assessment model.

[0067] This application obtains customer health data collected in advance within a historical time period; then constructs corresponding health sample data based on the customer health data, and divides the health sample data into a training set and a test set; then trains a preset machine learning model based on the training set to obtain a trained first model; subsequently, performs a model evaluation on the first model based on the test set to obtain a corresponding evaluation result, and optimizes the first model based on the evaluation result to obtain a corresponding second model; finally, the second model is used as the health risk assessment model. This application constructs health sample data based on customer health data collected in advance, and divides the health sample data into a training set and a test set, then trains a preset machine learning model based on the use of the training set to obtain a trained first model, then performs a model evaluation on the first model based on the use of the test set, and optimizes the first model based on the obtained evaluation result to efficiently and accurately construct a health risk assessment model that can accurately predict the customer's health risk situation, effectively improving the construction efficiency of the health risk assessment model and ensuring the model prediction effect of the obtained health risk assessment model.

[0068] In some optional implementations of this embodiment, step S205 includes the following steps:

[0069] Get the preset weight distribution strategy.

[0070] In this embodiment, the above-mentioned weight distribution strategy can be constructed according to actual business needs, or a weight distribution algorithm can be used, etc.

[0071] Based on the weight allocation strategy, a first weight, a second weight, and a third weight corresponding to the health risk assessment result, the health improvement potential assessment result, and the lifestyle habit score, respectively, are generated.

[0072] In this embodiment, a health score for a customer can be generated based on a preset weighting strategy, taking into account the health risk assessment results, health improvement potential assessment results, and lifestyle score. For example, the health risk assessment results can be weighted 40% (i.e., the first weight), the health improvement potential assessment results can be weighted 30% (i.e., the second weight), and the lifestyle score can be weighted 30% (i.e., the third weight).

[0073] Based on the first weight, the second weight and the third weight, the health risk assessment result, the health improvement potential assessment result and the lifestyle habit score are calculated and processed using a preset scoring formula to obtain a corresponding initial health score.

[0074] In this embodiment, the above-mentioned scoring formula can specifically adopt a weighted summation formula, and the above-mentioned first weight, second weight, third weight, health risk assessment results, health improvement potential assessment results and lifestyle habit scores can be calculated and processed based on the weighted summation formula to obtain the calculated initial health score.

[0075] The initial health score is normalized to obtain a processed designated health score.

[0076] In this embodiment, the generated initial health score is normalized and converted into a specific score range, such as 0-100 points, so as to more intuitively display the customer's health status.

[0077] The designated health score is used as the health score of the client.

[0078] This application obtains a preset weight allocation strategy; then generates a first weight, a second weight, and a third weight corresponding to the health risk assessment result, the health improvement potential assessment result, and the lifestyle score based on the weight allocation strategy; then, based on the first weight, the second weight, and the third weight, uses a preset scoring formula to calculate and process the health risk assessment result, the health improvement potential assessment result, and the lifestyle score to obtain a corresponding initial health score; subsequently, normalizes the initial health score to obtain a processed designated health score; and uses the designated health score as the health score of the customer. This application generates a first weight, a second weight, and a third weight corresponding to the health risk assessment result, the health improvement potential assessment result, and the lifestyle score based on the use of a weight allocation strategy; then, based on the obtained weights, uses a scoring formula to calculate and process the health risk assessment result, the health improvement potential assessment result, and the lifestyle score to obtain an initial health score, and normalizes the initial health score to obtain an accurate health score, thereby ensuring the data accuracy of the obtained health score.

[0079] In some optional implementations, step S206 includes the following steps:

[0080] Get preset premium discount rules.

[0081] In this embodiment, the process of generating premium discount rules involves: the insurance company's market research team collects information on premium discount strategies from other insurance companies in the same industry, including information on discount criteria (such as health scores and health improvement behaviors), discount interval settings, and discount percentage ranges. This data is obtained through participating in industry seminars, reviewing professional reports, and communicating with peers. Then, customer surveys and focus group discussions are conducted to understand customer expectations and needs for premium discounts. For example, customers are asked whether they are willing to improve their health to obtain premium discounts, and which health behaviors they believe should be included in the discount calculation. Furthermore, considering the insurance company's own cost structure and profitability targets, the impact of different discount rules on premium revenue and profits is evaluated, and corresponding premium discount rules are constructed. For example, the balance between the company's potential reduction in premium revenue and the reduced claims costs due to improved health of customers is calculated by granting larger discounts to customers with higher health scores.

[0082] A corresponding premium discount mapping table is constructed based on the premium discount rules.

[0083] In this embodiment, the premium discount mapping table is a data table constructed based on premium discount rules and stores pre-defined health score intervals and corresponding premium discount ratios. The process of dividing health score intervals includes: data statistical analysis: performing statistical analysis on historical customer health score data to determine the distribution of scores, such as mean, standard deviation, quartiles, etc. Based on these statistical indicators, the health scores are divided into different intervals, such as a low score interval (0-40 points), a medium-low score interval (41-60 points), a medium-high score interval (61-80 points), and a high score interval (81-100 points). Risk assessment integration: combining the health risk assessment results, a risk assessment is performed on each score interval. For example, customers in the low score interval have relatively high health risks, while customers in the high score interval have relatively low health risks. Based on the risk assessment results, a corresponding premium discount ratio is set for each interval, such as a 0% discount ratio for the low score interval, a 5% discount ratio for the medium-low score interval, a 10% discount ratio for the medium-high score interval, and a 15% discount ratio for the high score interval. In addition, after the health scores are divided into different score intervals, each interval will correspond to a different premium discount ratio. The discount ratio is positively correlated with the customer's health status and health improvement behavior. That is, the higher the health score, the greater the premium discount ratio.

[0084] In addition, additional premium discounts are offered to customers who actively engage in health improvement behaviors, such as increasing their exercise and improving their eating habits. Specifically, dynamic premium discounts, health point rewards, and health goal achievement rewards can be used to incentivize customers to continue participating in health management. For example, customers who complete their daily exercise goals can receive additional premium discounts; customers who achieve preset health goals (such as weight loss, blood pressure standards, etc.) can earn health points, which can be used to offset premiums or redeem health services.

[0085] A data query is performed on the premium discount mapping table based on the health score to find a specified premium discount ratio that matches the health score.

[0086] In this embodiment, the designated score interval of the customer's health score can be first determined from the premium discount mapping table, and then the premium discount ratio corresponding to the designated score interval can be obtained as the designated premium discount ratio.

[0087] The designated premium discount ratio is used as the target premium discount data.

[0088] The present application obtains preset premium discount rules; then constructs a corresponding premium discount mapping table based on the premium discount rules; then performs a data query on the premium discount mapping table based on the health score to find out the specified premium discount ratio that matches the health score; and subsequently uses the specified premium discount ratio as the target premium discount data. The present application improves the intelligence of constructing the premium discount mapping table by obtaining preset premium discount rules and constructing a corresponding premium discount mapping table based on the premium discount rules. Furthermore, based on the use of the premium discount mapping table, the target premium discount data that matches the health score can be quickly and accurately queried, thereby improving the query efficiency and query accuracy of the target premium discount data.

[0089] In some optional implementations, step S207 includes the following steps:

[0090] Corresponding discount notification information is generated based on the target premium discount data.

[0091] In this embodiment, the target premium discount data can be filled into a preset discount notification information template to generate corresponding discount notification information. The discount notification information template is a pre-built template that the user uses to clearly inform the customer of the premium discount ratio, discount basis (health score and health improvement behavior), discount effective time and other information. Exemplarily, the content of the discount notification information template may include: "Dear customer, based on your health score and health improvement behavior of continuously increasing the amount of exercise, you will receive a premium discount of XXX, which will take effect when the next premium is paid."

[0092] Obtaining the customer's preference information.

[0093] In this embodiment, the customer's customer portrait data can be obtained, and then the customer's preference information can be extracted from the customer portrait data.

[0094] The discount notification information is personalized based on the preference information to obtain corresponding target discount notification information.

[0095] In this embodiment, the content of health advice can be personalized according to the customer's preferences and characteristics. For example, for customers who prefer visual information, health advice can be presented in the form of charts, pictures, etc.; for customers who prefer text descriptions, detailed text descriptions can be provided. In addition, when conveying health advice, important information such as health goals, key action steps, expected results, etc. should be highlighted so that customers can quickly understand and grasp it. In addition, in addition to the health advice itself, customers can also be provided with relevant support resources, such as health consultation hotlines, online health communities, health lecture information, etc., to help customers better implement health advice.

[0096] A target notification method corresponding to the customer is determined based on the preference information.

[0097] In this embodiment, appropriate notification methods can be selected based on customer preferences and actual conditions, such as SMS, email, mobile APP push, etc., to ensure that customers can receive premium discount notifications in a timely and accurate manner.

[0098] Based on the target notification method, the target discount notification information is sent to the customer.

[0099] In this embodiment, a push process of sending target discount notification information to customers may be performed using a target notification method selected according to user preference information.

[0100] The present application generates corresponding discount notification information based on the target premium discount data; then obtains the customer's preference information; then personalizes the discount notification information based on the preference information to obtain the corresponding target discount notification information; and determines the target notification method corresponding to the customer based on the preference information; and subsequently sends the target discount notification information to the customer based on the target notification method. The present application generates corresponding discount notification information based on the target premium discount data, and then personalizes the discount notification information based on the obtained customer's preference information to obtain the target discount notification information, thereby improving the personalization and intelligence of the generated target discount notification information. In addition, the target notification method corresponding to the customer will be determined based on the preference information, and then the target discount notification information will be sent to the customer based on the target notification method, thereby effectively improving the push intelligence of the target discount notification information and improving the user experience.

[0101] In some optional implementations of this embodiment, step S201 includes the following steps:

[0102] Get the preset query conditions.

[0103] In this embodiment, the query conditions can be constructed based on the actual need to extract the required data. For example, the query conditions can include parameters such as customer ID and time range.

[0104] Based on the query conditions, the initial health data of the customer is collected from a preset data source using a designated monitoring tool.

[0105] In this embodiment, the designated monitoring tool may include a smart wearable device, a health monitoring app, etc. Correspondingly, the preset data source may include data uploaded by the smart wearable device, data manually input by the health monitoring app, and data synchronized from a customer during a physical examination at another medical institution. Specifically, by utilizing the designated monitoring tool, according to the above query conditions, for example, according to parameters such as customer ID and time range, all health data records of the customer within a specific time period are filtered out from the preset data source to obtain the above initial health data.

[0106] The initial health data is cleaned to obtain corresponding first health data.

[0107] In this embodiment, the above-mentioned data cleaning process includes removing duplicate data, correcting erroneous data, and handling missing data. Among them, removing duplicate data includes: using a specific data cleaning script to check whether there are duplicate records in the data set. For completely identical records, only one is retained. Correcting erroneous data includes: identifying erroneous data by setting reasonable data ranges and rules. For erroneous data, you can try to correct it based on surrounding data or historical data, or directly mark it as a missing value. Handling missing data includes: analyzing the causes and distribution of missing data. If there is a small amount of missing data, you can use methods such as mean filling, median filling, or mode filling to fill it in; if there is a large amount of missing data, you can consider deleting the record or using more complex interpolation methods, such as multiple interpolation.

[0108] Perform data standardization processing on the first health data to obtain corresponding second health data.

[0109] In this embodiment, the above-mentioned data standardization processing includes unit unification, format specification and normalization processing. Among them, unit unification includes: since data from different devices and sources may use different units, for example, weight may be in kilograms or pounds, and blood pressure may be in millimeters of mercury or kilopascals. All data need to be converted into a unified unit for subsequent analysis and comparison. Format specification includes: standardizing the format of the data, for example, the date and time format is unified to "YYYY-MM-DD HH:MM:SS" to ensure the consistency and readability of the data. Normalization processing: For data of different dimensions, such as heart rate, blood pressure, weight, etc., normalization processing is performed to convert them into the same numerical range, such as [0,1], to eliminate the impact of the dimension on the data analysis results.

[0110] The second health data is used as the target health data.

[0111] This application obtains preset query conditions; then based on the query conditions, uses a designated monitoring tool to collect the customer's initial health data from a preset data source; then performs data cleaning on the initial health data to obtain corresponding first health data; subsequently performs data standardization on the first health data to obtain corresponding second health data, and uses the second health data as the target health data. This application obtains the customer's initial health data from a preset data source using a designated monitoring tool based on the obtained query conditions, and then performs data cleaning and standardization on the initial health data to ensure that health data from different sources are comparable, thereby obtaining accurate target health data and improving the accuracy and standardization of the generated target health data.

[0112] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:

[0113] Determine whether the health score is less than a preset score threshold.

[0114] In this embodiment, there is no specific limitation on the value of the above-mentioned scoring threshold, which can be set according to actual business needs. If the above-mentioned health score is detected to be less than the scoring threshold, it is determined that the customer has a high health risk.

[0115] If so, call the preset medical knowledge base.

[0116] In this embodiment, a database containing rich medical knowledge (i.e., a medical knowledge base) is pre-established, covering the prevention, treatment, and rehabilitation of various diseases, as well as recommendations on diet, exercise, and psychological adjustment for different health conditions. Medical experts are also invited to participate in the recommendation formulation process to provide professional advice and guidance.

[0117] Obtaining a preset health goal corresponding to the customer.

[0118] In this embodiment, personalized health goals can be jointly developed with the customer based on the customer's health status and needs. For example, for a customer with mild hypertension, the goal can be to control blood pressure within a normal range.

[0119] Based on the medical knowledge base and the preset health goals, the target health data is processed for suggestion generation to obtain corresponding health improvement suggestions.

[0120] In this embodiment, personalized health improvement suggestions can be generated for customers based on their target health data and health goals, combined with a medical knowledge base and expert experience. For example, for customers with poor exercise data and mild fatty liver disease, appropriate exercise methods and intensities are recommended based on their physical condition (such as age, weight, cardiopulmonary function, etc.) and health goals (reducing the degree of fatty liver disease), such as swimming three times a week for more than 45 minutes each time; for customers with unreasonable eating habits, a reasonable diet structure is recommended based on their nutritional needs (such as the intake ratio of protein, carbohydrates, fat, vitamins, etc.) and health conditions (such as whether they suffer from diabetes, high blood pressure, etc.), such as increasing the intake of whole grains and beans and reducing the intake of processed foods.

[0121] The health improvement suggestion is sent to the client.

[0122] In this embodiment, the generated health improvement suggestions can be refined to specify specific implementation steps and timelines. At the same time, the feasibility of the health improvement suggestions is analyzed, taking into account the client's actual circumstances (such as time, financial conditions, and location) to ensure that the suggestions are feasible. The refined health suggestions are then sent to the client.

[0123] This application determines whether the health score is less than a preset score threshold; if so, calls a preset medical knowledge base; then obtains the preset health goal corresponding to the customer; then generates and processes the target health data based on the medical knowledge base and the preset health goal to obtain corresponding health improvement suggestions; and subsequently sends the health improvement suggestions to the customer. When this application detects that the customer's health score is less than the preset score threshold, it will determine that the customer has a higher health risk, and then obtain the customer's preset health goal, and based on the use of the medical knowledge base, it generates and processes the target health data to obtain health improvement suggestions, and then sends the health improvement suggestions to the customer, thereby achieving the intelligent and accurate provision of targeted and effective health improvement suggestions to customers, which helps to improve the customer's health and enhance the customer's user experience.

[0124] In some optional implementations, the user information obtained is obtained with the user's consent and complies with relevant laws and policies.

[0125] In addition, any software tools or components not provided by our company that appear in the embodiments of this application are merely examples and do not represent actual use.

[0126] In addition, this application has designed a personalized premium discount calculation method based on health scores and health improvement behaviors, which can dynamically adjust the premium discount ratio according to the customer's health status and behavioral performance, thereby achieving precise incentives. Moreover, this application has built a complete health incentive closed loop by integrating health monitoring technology, model technology and insurance services, realizing the in-depth integration of health data and insurance services, and promoting the digital transformation of the insurance industry. This application has also designed a set of multi-dimensional health incentive mechanisms, including dynamic premium discounts, health points rewards, health goal achievement rewards, etc., which can effectively stimulate customers' motivation to improve their health and enhance customer participation and satisfaction.

[0127] This application also has the following benefits: (1) Providing personalized health management and premium discount services to help customers reduce premium expenses and improve their health; through health incentive mechanisms, improving customers' health awareness and quality of life. (2) Reducing customers' health risks and reducing compensation pressure; improving customer stickiness and enhancing market competitiveness; promoting the digital transformation of insurance services and improving operational efficiency. (3) Promoting the popularization of healthy lifestyles and reducing the incidence of chronic diseases and major diseases; promoting the coordinated development of the insurance industry and the health management industry, and promoting the digital upgrade of the health industry.

[0128] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0129] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned target premium discount data, the above-mentioned target premium discount data can also be stored in a node of a blockchain.

[0130] The blockchain referred to in this application refers to a new application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (to prevent counterfeiting) and generate the next block. Blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer.

[0131] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. 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 achieve optimal results.

[0132] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0133] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware via computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0134] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0135] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a data generation device based on artificial intelligence. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0136] like Figure 3 As shown, the artificial intelligence-based data generation device 300 of this embodiment includes: a first acquisition module 301, a first evaluation module 302, a second evaluation module 303, a scoring module 304, a first generation module 305, a second generation module 306, and a first sending module 307. Among them:

[0137] The first acquisition module 301 is used to acquire the target health data of the customer; wherein the target health data includes basic health data, exercise data and life habit data;

[0138] A first evaluation module 302 is configured to perform data evaluation on the target health data based on a preset health risk evaluation model to obtain a corresponding health risk evaluation result;

[0139] The second evaluation module 303 is used to perform data evaluation on the target health data based on a preset health improvement potential evaluation model to obtain a corresponding health improvement potential evaluation result;

[0140] Scoring module 304, configured to score the target health data based on a preset lifestyle scoring model to obtain a corresponding lifestyle score;

[0141] A first generating module 305 is configured to generate a health score corresponding to the client based on the health risk assessment result, the health improvement potential assessment result, and the lifestyle score;

[0142] A second generating module 306 is configured to generate target premium discount data corresponding to the customer based on the health score;

[0143] The first sending module 307 is configured to send the target premium discount data to the customer.

[0144] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based data generation method in the aforementioned embodiment, and will not be repeated here.

[0145] In some optional implementations of this embodiment, the artificial intelligence-based data generation device further includes:

[0146] The second acquisition module is used to obtain the customer health data collected in advance within the historical time period;

[0147] A construction module, configured to construct corresponding health sample data based on the customer health data;

[0148] A division module, used to divide the health sample data into a training set and a test set;

[0149] A training module, configured to train a preset machine learning model based on the training set to obtain a trained first model;

[0150] an optimization module, configured to perform a model evaluation on the first model based on the test set to obtain a corresponding evaluation result, and perform a model optimization on the first model based on the evaluation result to obtain a corresponding second model;

[0151] A determination module is used to use the second model as the health risk assessment model.

[0152] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based data generation method in the aforementioned embodiment, and will not be repeated here.

[0153] In some optional implementations of this embodiment, the first generating module 305 includes:

[0154] The first acquisition submodule is used to obtain a preset weight distribution strategy;

[0155] A first generating submodule is configured to generate, based on the weight allocation strategy, a first weight, a second weight, and a third weight corresponding to the health risk assessment result, the health improvement potential assessment result, and the lifestyle habit score, respectively;

[0156] a calculation submodule, configured to calculate and process the health risk assessment result, the health improvement potential assessment result, and the lifestyle habit score based on the first weight, the second weight, and the third weight using a preset scoring formula to obtain a corresponding initial health score;

[0157] a processing submodule, configured to perform normalization processing on the initial health score to obtain a processed designated health score;

[0158] The first determination submodule is configured to use the designated health score as the health score of the customer.

[0159] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based data generation method in the aforementioned embodiment, and will not be repeated here.

[0160] In some optional implementations of this embodiment, the second generating module 306 includes:

[0161] The second acquisition submodule is used to obtain the preset premium discount rules;

[0162] A construction submodule, configured to construct a corresponding premium discount mapping table based on the premium discount rule;

[0163] A query submodule, configured to query the premium discount mapping table based on the health score to find a specified premium discount ratio that matches the health score;

[0164] The second determining submodule is configured to use the designated premium discount ratio as the target premium discount data.

[0165] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based data generation method in the aforementioned embodiment, and will not be repeated here.

[0166] In some optional implementations of this embodiment, the first sending module 307 includes:

[0167] A second generating submodule is configured to generate corresponding discount notification information based on the target premium discount data;

[0168] A third acquisition submodule is used to obtain the customer's preference information;

[0169] an adjustment submodule, configured to perform personalized adjustment on the discount notification information based on the preference information to obtain corresponding target discount notification information;

[0170] a third determining submodule, configured to determine a target notification method corresponding to the customer based on the preference information;

[0171] A sending submodule is used to send the target discount notification information to the customer based on the target notification method.

[0172] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based data generation method in the aforementioned embodiment, and will not be repeated here.

[0173] In some optional implementations of this embodiment, the first obtaining module 301 includes:

[0174] The fourth acquisition submodule is used to obtain preset query conditions;

[0175] A collection submodule, configured to collect the initial health data of the client from a preset data source using a designated monitoring tool based on the query condition;

[0176] a cleaning submodule, configured to perform data cleaning processing on the initial health data to obtain corresponding first health data;

[0177] a standardization submodule, configured to perform data standardization processing on the first health data to obtain corresponding second health data;

[0178] The fourth determining submodule is configured to use the second health data as the target health data.

[0179] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based data generation method in the aforementioned embodiment, and will not be repeated here.

[0180] In some optional implementations of this embodiment, the artificial intelligence-based data generation device further includes:

[0181] A judgment module, used to judge whether the health score is less than a preset score threshold;

[0182] A calling module, for calling a preset medical knowledge base if yes;

[0183] A third acquisition module is used to acquire a preset health goal corresponding to the customer;

[0184] A third generating module is configured to generate suggestions for the target health data based on the medical knowledge base and the preset health goals to obtain corresponding health improvement suggestions;

[0185] The second sending module is used to send the health improvement suggestion to the customer.

[0186] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based data generation method in the aforementioned embodiment, and will not be repeated here.

[0187] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0188] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations 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.

[0189] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0190] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for data generation methods based on artificial intelligence. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0191] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or process data, such as executing computer-readable instructions for the artificial intelligence-based data generation method.

[0192] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0193] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based data generation method.

[0194] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, 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 number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0195] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.

Claims

1. A data generation method based on artificial intelligence, characterized in that: The steps include: Obtaining the customer's target health data; wherein the target health data includes basic health data, exercise data, and lifestyle data; Performing data evaluation on the target health data based on a preset health risk assessment model to obtain corresponding health risk assessment results; Performing data evaluation on the target health data based on a preset health improvement potential evaluation model to obtain corresponding health improvement potential evaluation results; Scoring the target health data based on a preset lifestyle habit scoring model to obtain a corresponding lifestyle habit score; generating a health score corresponding to the customer based on the health risk assessment result, the health improvement potential assessment result, and the lifestyle score; generating target premium discount data corresponding to the customer based on the health score; The target premium discount data is sent to the customer.

2. The artificial intelligence-based data generation method according to claim 1, characterized in that: Before the step of performing data evaluation on the target health data based on the preset health risk evaluation model to obtain the corresponding health risk evaluation result, the method further includes: Obtaining customer health data collected in advance within a historical time period; Constructing corresponding health sample data based on the customer health data; Dividing the health sample data into a training set and a test set; Training a preset machine learning model based on the training set to obtain a trained first model; Performing model evaluation on the first model based on the test set to obtain a corresponding evaluation result, and performing model optimization on the first model based on the evaluation result to obtain a corresponding second model; The second model is used as the health risk assessment model.

3. The artificial intelligence-based data generation method according to claim 1, characterized in that: The step of generating a health score corresponding to the customer based on the health risk assessment result, the health improvement potential assessment result, and the lifestyle score specifically includes: Get the preset weight distribution strategy; generating, based on the weight allocation strategy, a first weight, a second weight, and a third weight corresponding to the health risk assessment result, the health improvement potential assessment result, and the lifestyle habit score, respectively; Based on the first weight, the second weight, and the third weight, a preset scoring formula is used to calculate the health risk assessment result, the health improvement potential assessment result, and the lifestyle habit score to obtain a corresponding initial health score; Normalizing the initial health score to obtain a processed designated health score; The designated health score is used as the health score of the client.

4. The artificial intelligence-based data generation method according to claim 1, characterized in that: The step of generating target premium discount data corresponding to the customer based on the health score specifically includes: Obtain preset premium discount rules; Constructing a corresponding premium discount mapping table based on the premium discount rule; Performing a data query on the premium discount mapping table based on the health score to find a specified premium discount ratio that matches the health score; The designated premium discount ratio is used as the target premium discount data.

5. The artificial intelligence-based data generation method according to claim 1, characterized in that: The step of sending the target premium discount data to the customer specifically includes: generating corresponding discount notification information based on the target premium discount data; obtaining preference information of the customer; Personalizing the discount notification information based on the preference information to obtain corresponding target discount notification information; determining a target notification method corresponding to the customer based on the preference information; Based on the target notification method, the target discount notification information is sent to the customer.

6. The artificial intelligence-based data generation method according to claim 1, characterized in that: The steps of obtaining the target health data of the customer specifically include: Get the preset query conditions; Based on the query conditions, using a designated monitoring tool to collect the initial health data of the customer from a preset data source; Performing data cleaning on the initial health data to obtain corresponding first health data; performing data standardization processing on the first health data to obtain corresponding second health data; The second health data is used as the target health data.

7. The artificial intelligence-based data generation method according to claim 1, characterized in that: After the step of sending the target premium discount data to the customer, the method further includes: Determining whether the health score is less than a preset score threshold; If so, call the preset medical knowledge base; Obtaining a preset health goal corresponding to the client; Performing suggestion generation processing on the target health data based on the medical knowledge base and the preset health goals to obtain corresponding health improvement suggestions; The health improvement suggestion is sent to the client.

8. A data generation device based on artificial intelligence, characterized in that: include: A first acquisition module is used to acquire the customer's target health data; wherein the target health data includes basic health data, exercise data, and life habit data; A first evaluation module is used to perform data evaluation on the target health data based on a preset health risk evaluation model to obtain a corresponding health risk evaluation result; A second evaluation module is used to perform data evaluation on the target health data based on a preset health improvement potential evaluation model to obtain a corresponding health improvement potential evaluation result; A scoring module is used to score the target health data based on a preset lifestyle scoring model to obtain a corresponding lifestyle score; A first generating module is configured to generate a health score corresponding to the customer based on the health risk assessment result, the health improvement potential assessment result, and the lifestyle score; A second generating module is configured to generate target premium discount data corresponding to the customer based on the health score; The first sending module is used to send the target premium discount data to the customer.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the artificial intelligence-based data generation method as described in any one of claims 1 to 7 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 artificial intelligence-based data generation method according to any one of claims 1 to 7.

Images