Data tracking analysis management platform based on digital life insurance enterprise

Abstract

The invention discloses a data tracking analysis management platform based on a digital life insurance enterprise, and the platform comprises a management platform, and the operation process of the management platform specifically comprises the following steps: obtaining multi-source customer data; performing structured processing on the multi-source customer data to generate a customer portrait data set containing a customer label set; generating an initial risk prediction set based on the customer tag set; monitoring a customer behavior event and external environment data in real time, and generating a dynamic adjustment signal according to a preset trigger rule; risk re-evaluation is carried out, and an updated risk prediction set and a differentiated insurance strategy are generated; and generating a visual analysis report according to the customer portrait data set. The method has the following advantages and effects that a closed-loop management platform is constructed through multi-source data dynamic fusion and label weight real-time iteration, dynamic risk assessment is finally achieved, and the risk response speed and customer service accuracy of life insurance enterprises are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of insurance technology, and in particular to a data tracking, analysis and management platform based on digital life insurance companies. Background Art

[0002] With the advent of the digital age, life insurance companies are increasingly relying on technology to enhance their market competitiveness, improve operational efficiency, and enhance customer service levels.

[0003] In the process of digital transformation of the life insurance industry, the core bottleneck faced by traditional management platforms lies in the static nature of risk assessment and the lack of dynamic response capabilities. Existing technologies usually rely on historical policy data and basic customer attributes. Once set, their weight coefficients (such as the weights of labels such as health status and behavioral preferences) are permanently fixed and cannot be dynamically adjusted according to real-time customer behavior events (such as abnormal health monitoring data, delayed renewal) or sudden changes in the external environment (such as economic fluctuations, medical policy adjustments). For example, when a customer's health monitoring device continuously detects abnormal physiological indicators, the traditional management platform cannot correct the health label weight in real time, making it difficult to timely increase the risk level and trigger an early warning; similarly, in the face of changes in customer renewal willingness caused by sudden economic downturns, there is a lack of a quantitative correlation mechanism between external environmental data and risk transmission paths, resulting in risk assessment results lagging behind actual risk evolution. This static defect makes the generation and adjustment of insurance strategies heavily dependent on manual experience and periodic batch updates, making it difficult to achieve individualized, real-time, and precise risk control, exacerbating corporate risk exposure and customer churn risks. Therefore, there is an urgent need for a technical solution that supports dynamic fusion of multi-source data and real-time iteration of label weights to break through the static limitations of traditional management platforms. Summary of the invention

[0004] The purpose of the present invention is to provide a data tracking, analysis and management platform based on digital life insurance companies to solve the problems raised in the background technology.

[0005] The above technical objectives of the present invention are achieved through the following technical solutions: A data tracking and analysis management platform based on a digital life insurance company includes a management platform, and the operation process of the management platform specifically includes the following steps: S100, obtaining multi-source customer data; wherein the multi-source customer data includes basic customer information, insurance policy records, health monitoring data, consumer behavior data and claims records; S200, performing structured processing on multi-source customer data to generate a customer portrait data set; wherein the customer portrait data set includes at least one customer tag set, and the customer tag set includes a risk level tag, a behavior preference tag, a health status tag, and the dynamic weight values ​​corresponding to each of them; S300, generating an initial risk prediction set based on the customer tag set; S400, real-time monitoring of customer behavior events and external environment data, and generating dynamic adjustment signals according to preset trigger rules; S500, re-evaluating the risk based on the dynamic adjustment signal and the initial risk prediction set to generate an updated risk prediction set; wherein the updated risk prediction set is used to correct the dynamic weight value in the customer portrait data set and generate a differentiated insurance strategy; S600. Generate a visual analysis report based on the customer portrait data set.

[0006] By adopting the above technical solutions, multi-source heterogeneous data from IoT devices, mobile terminals, and enterprise databases are integrated to cover multi-dimensional information such as customer health, behavior, and economic environment, and to build a panoramic customer view; through real-time and batch mixed collection modes, the synchronous processing of high-frequency health data and low-frequency economic data is taken into account to ensure data timeliness and integrity; based on real-time monitoring of customer behavior events and the external environment, a risk reassessment mechanism is triggered to solve the problem of strategy lag caused by data update delays in traditional models; differentiated insurance strategies combine customer risk levels, dynamic weight distribution, and external environmental influences to support personalized premium fluctuations and customized coverage, thereby improving customer satisfaction and corporate risk-return ratio; through dynamic fusion of multi-source data and real-time iteration of label weights, a closed-loop management platform is built, which ultimately realizes the dynamic nature of risk assessment and significantly improves the risk response speed and customer service accuracy of life insurance companies.

[0007] It is further configured that the structured processing of multi-source customer data in S200 includes: S210, associating and mapping the basic customer information with the insurance policy record through the unique customer identification code to generate a basic customer file; S220, using a K-means clustering algorithm to classify the health monitoring data, generate health status labels, and calculate a first dynamic weight value corresponding to each health status label based on a time series analysis method; wherein the calculation process of the first dynamic weight value is: according to the ratio of the mean of the health monitoring data within a preset time window to the standard deviation of the health monitoring data, multiplied by a preset normalization coefficient, to obtain a weight value of the health status label; S230, performing sentiment polarity analysis on text information in the consumer behavior data through natural language processing technology, generating behavior preference labels, and calculating a second dynamic weight value of each behavior preference label based on a TF-IDF algorithm; wherein the second dynamic weight value is calculated by extracting a weight value of a keyword through a TF-IDF algorithm, and then multiplying the weight value by a preset behavior influence factor to generate a weight value of the behavior preference label; S240, matching the historical claims records with the preset risk event library, marking the risk level labels, and simulating the probability of occurrence and impact intensity of the risk events through the Monte Carlo simulation algorithm, and calculating the third dynamic weight value of each risk level label; wherein the third dynamic weight value is calculated by: multiplying the simulated probability of occurrence of the event by the impact coefficient, and then multiplying by the preset risk adjustment factor to generate the weight value of the risk level label; S250. Integrate the health status label and its first dynamic weight value, the behavior preference label and its second dynamic weight value, the risk level label and its third dynamic weight value to generate a customer label set, and aggregate all customer label sets into a customer portrait data set; wherein, the customer portrait data set is stored in a distributed database, supporting real-time query and batch update.

[0008] By adopting the above technical solution, the basic information of customers and the insurance policy records are associated and mapped through a unique customer identification code. The management platform can achieve accurate management of customer data and avoid erroneous analysis caused by information redundancy or data missing. This process generates basic customer files and provides a solid data foundation for subsequent data analysis. In the process of data processing, the K-means clustering algorithm is used to classify health monitoring data and generate health status labels. The dynamic weight value of the health status label is calculated by time series analysis, so that the customer's health status label not only reflects the customer's current health status, but also can be dynamically adjusted with the change of time and the change of customer health data. The calculation process of the first dynamic weight value accurately evaluates the customer's health risk through the ratio of the mean and standard deviation of the health monitoring data and the preset normalization coefficient. At the same time, the sentiment polarity analysis of consumer behavior data and the basic The behavioral preference labels generated by the TF-IDF algorithm can accurately reflect the customer's consumption behavior patterns; these labels and their corresponding dynamic weight values ​​not only help insurance companies better understand customer needs, but also provide support for subsequent insurance product design and risk assessment; the combination of natural language processing technology and TF-IDF algorithm enables the platform to have a deeper understanding of customer behavior and can predict their potential claims needs and health risks through their consumption behavior; by matching the risk event library of historical claims records, the platform can analyze the customer's historical claims data in real time, assess the customer's risk level, and calculate the probability of occurrence and impact intensity of risk events through the Monte Carlo simulation algorithm to further refine risk predictions; this dynamic and comprehensive customer label collection provides insurance companies with an accurate and real-time updated customer portrait, which helps to formulate personalized and differentiated insurance strategies.

[0009] It is further configured that generating the initial risk prediction set in S300 includes: S310, calculating a comprehensive risk score of the customer based on the first dynamic weight value, the second dynamic weight value, and the third dynamic weight value in the customer tag set; S320, dividing the risk level according to the comprehensive risk score and generating an initial risk prediction set; wherein, S310 specifically includes the following sub-steps: Respectively obtain a first dynamic weight value of the health status label, a second dynamic weight value of the behavior preference label, and a third dynamic weight value of the risk level label; Multiply each dynamic weight value by its corresponding preset risk factor, where the preset risk factor includes a health risk factor, a behavioral risk factor, and a risk event factor; The result of multiplying each dynamic weight value by its corresponding preset risk factor is added together to generate a comprehensive risk score for the customer; S320 specifically includes the following sub-steps: Preset risk level threshold table to define the comprehensive risk score intervals corresponding to low risk, medium risk, and high risk; Match the customer's comprehensive risk score with the risk level threshold table to determine the customer's risk level; A list of events associated with risk levels is extracted from a preset risk event library to generate an initial risk prediction set; wherein the initial risk prediction set includes event name, event probability, impact coefficient and priority score; wherein the priority score is calculated based on the weighted sum of the event probability and the impact coefficient.

[0010] By adopting the above technical solution, the management platform can calculate the customer's comprehensive risk score by combining the dynamic weight values ​​in the health status label, behavioral preference label and risk level label in the customer label set. The comprehensive risk score not only takes into account the customer's health status, consumption behavior and historical claims record, but also integrates the customer's performance in different environments, such as changes in health data, changes in consumption patterns, etc.; this makes the management platform more comprehensive and accurate in risk prediction and can better reflect the customer's actual risk level; in the process of generating the initial risk prediction set, the management platform matches the customer's comprehensive risk score with low risk, medium risk and high risk through a preset risk level threshold table, thereby dividing the customer's risk level. This process can provide a basis for subsequent insurance product pricing, risk assessment and decision making; the generation of the initial risk prediction set not only depends on the customer's health status and behavioral characteristics, but also combines external environmental factors. Through this comprehensive risk prediction, insurance companies can promptly discover potential risks and make reasonable decisions, thereby realizing refined risk management.

[0011] A further configuration is to perform conflict detection on the multi-dimensional label set of the same customer in S320. If the logical relationship between the health status label and the risk level label is inconsistent, a manual review process is triggered; wherein the logical relationship contradiction is defined as: the health status label indicates low risk and the risk level label indicates high risk, or the health status label indicates high risk and the risk level label is not adjusted synchronously.

[0012] By adopting the above technical solution, through conflict detection on the multi-dimensional label set of the same customer, the management platform can ensure that the logical relationship between the customer's health status label and the risk level label is always consistent. If the health status label indicates low risk and the risk level label indicates high risk, or the health status label indicates high risk and the risk level label is not adjusted synchronously, the management platform will automatically trigger the manual review process. This can effectively reduce the erroneous judgment caused by data contradictions, thereby improving the accuracy of risk prediction; the above conflict detection mechanism not only improves the accuracy of the data, but also ensures the reliability of the system output results through manual review. In the complex risk prediction process, the combination of automation and manual intervention can improve the robustness of the system and avoid errors that may be caused by single automated judgment.

[0013] It is further configured that generating the dynamic adjustment signal in S400 includes: S410, setting a trigger rule base; The trigger rules in the trigger rule library include: If the health monitoring data exceeds the threshold range for N consecutive days, a health risk warning will be triggered; If the economic volatility index in the external environment data exceeds the volatility threshold, it will trigger a reassessment of economic risks; If the customer fails to complete the policy renewal operation within the preset time, the churn risk mark will be triggered; S420, monitoring customer behavior events and external environment data streams in real time through an event-driven architecture; S430: When it is detected that a behavior event matches a trigger rule, a dynamic adjustment signal including an event type, a timestamp, and an impact range is generated.

[0014] By adopting the above technical solutions, customer behavior events and external environment data streams can be monitored in real time, so that dynamic adjustment signals can be quickly generated when customer behavior changes; through the event-driven architecture, the management platform can respond to changes in customer behavior and external environment in real time, and generate dynamic adjustment signals containing event type, timestamp and scope of impact; these dynamic adjustment signals not only provide real-time data for subsequent risk reassessment, but also help insurance companies quickly adjust risk forecasts and strategies when facing emergencies, and improve their response capabilities.

[0015] It is further configured that, in S500, risk reassessment is performed based on the dynamic adjustment signal and the updated risk prediction set, including: S510, receiving a dynamic adjustment signal and parsing event type, timestamp and impact range parameters, extracting an abnormal feature vector associated with a customer tag set; wherein the abnormal feature vector includes health monitoring deviation, economic fluctuation sensitivity and policy renewal hysteresis period; S520, constructing a risk transmission model based on the Bayesian network, performing joint probability distribution calculation on the abnormal feature vector and the probability of occurrence of events in the initial risk prediction set, and generating a dynamic correction coefficient; S530, iteratively correcting the first dynamic weight value, the second dynamic weight value, and the third dynamic weight value in the customer portrait data set based on the dynamic adjustment signal; S540, generating an updated risk prediction set based on the revised first dynamic weight value, the second dynamic weight value, and the third dynamic weight value, and updating the customer risk level; S550, generating differentiated insurance strategies; S560. Write the updated risk prediction set and differentiated insurance strategies into the customer portrait data set, overwriting the original dynamic weight values ​​and risk prediction results.

[0016] By adopting the above technical solution, the management platform can make timely adjustments when risks change by re-evaluating risks based on dynamic adjustment signals and updated risk prediction sets; in addition, by iteratively correcting the customer portrait data set based on dynamic adjustment signals, the customer's health status label, behavioral preference label and risk level label can be adjusted according to real-time feedback, thereby continuously optimizing the customer's risk assessment; this iterative correction process helps to continuously improve customer portraits, ensure that risk predictions are always consistent with the customer's actual situation, and improve the accuracy and flexibility of predictions.

[0017] It is further configured that the process of generating the dynamic correction coefficient in S520 includes: S520.1. According to the event type in the dynamic adjustment signal, the corresponding weight matrix is ​​matched from the preset conduction path weight matrix library; wherein the conduction path weight matrix is ​​a three-dimensional tensor structure, the dimensions of which include event type dimension, abnormal feature vector dimension and risk event dimension, and the matrix element value is the conditional probability weight obtained by historical data training; S520.2. Input the abnormal feature vector into the pre-trained random forest model, and output the probability of the risk transmission intensity of the abnormal feature to the risk event; wherein the random forest model uses health monitoring deviation, economic fluctuation sensitivity and policy renewal hysteresis period as input features, and the probability of risk transmission intensity as output target, and the random forest model is trained offline through the dynamic weight value of the historical claims records and customer label set in the risk event library; S520.3. Extract the current timestamp and the reference timestamp of the probability of occurrence of the corresponding event in the initial risk prediction set, and calculate the time difference between the two; substitute the time difference and the preset decay period parameter into the decay function to generate the time decay coefficient, and the decay period parameter is dynamically set according to the event type defined in the trigger rule library in S410; S520.4. Weighted fusion of the matching weight values ​​in the conduction path weight matrix, the risk conduction intensity probability and the time attenuation coefficient output by the random forest model to generate a dynamic correction coefficient; S520.5. Normalize the dynamic correction coefficient.

[0018] By adopting the above technical solutions, the relationship between different risk factors can be accurately simulated, and the dynamic correction coefficient can be calculated, so as to add more dynamic factors to the risk prediction process and improve the accuracy of the prediction; by combining the event type, abnormal feature vector and risk event dimension, the platform can more accurately evaluate the risk performance of customers in specific situations and make corresponding risk adjustments accordingly. This method based on three-dimensional matrix and random forest model can achieve efficient and accurate calculation when dealing with complex and multivariate risk predictions, thereby providing more reliable risk assessment results.

[0019] It is further configured that the process of iteratively correcting the first dynamic weight value, the second dynamic weight value and the third dynamic weight value in the customer portrait data set based on the dynamic adjustment signal in S530 is: S530.1. If the dynamic adjustment signal is a health risk warning, perform the following steps: Based on the standard deviation ratio of the health monitoring deviation and the mean of the health monitoring data calculated in S220, combined with the dynamic correction coefficient, a weighted linear interpolation method is used to update the first dynamic weight value corresponding to the health status label; Triggering the Monte Carlo simulation recalculation of the risk level label, using the updated first dynamic weight value and the dynamic correction coefficient as input parameters, and regenerating the third dynamic weight value; If the difference between the regenerated third dynamic weight value and the original value exceeds a preset threshold, a secondary correction of the cross-label association influence matrix is ​​triggered until the weight value change converges within the threshold; S530.2. If the dynamic adjustment signal is an economic risk reassessment, perform the following steps: Extract the sensitivity of economic fluctuations, calculate the deviation coefficient between the economic fluctuation index and the preset industry benchmark, add the product of the deviation coefficient and the dynamic correction coefficient to the risk adjustment factor corresponding to the third dynamic weight value of the risk level label, and generate the corrected third dynamic weight value; S530.3. If the dynamic adjustment signal is a loss risk marker, perform the following steps: A negative correlation function is constructed based on the inverse of the policy renewal lag period, and the second dynamic weight value of the behavior preference label and the weighted value of the dynamic correction coefficient are substituted into the function to recalculate the behavior risk coefficient; Next, a revised second dynamic weight value is generated based on the updated behavior risk coefficient.

[0020] By adopting the above technical solutions, the management platform can accurately correct the dynamic weight values ​​in the customer portrait data set according to different types of dynamic adjustment signals; each signal type will trigger a specific correction algorithm to ensure that the customer risk assessment always meets its latest behavior and environmental characteristics; for example, in the case of health risk warning, the dynamic weight value of the health status label is updated through weighted linear interpolation to better reflect the customer's health status. Through this iterative correction process, the management platform can not only respond to changes in customer behavior in a timely manner, but also make targeted adjustments for different types of risks, improving the flexibility and accuracy of insurance policies.

[0021] Further configuration is that, in S540, an updated risk prediction set is generated based on the revised first dynamic weight value, the second dynamic weight value and the third dynamic weight value, and the process of updating the customer risk level is: S540.1. Re-input the revised first dynamic weight value, second dynamic weight value, and third dynamic weight value into S310 to calculate the comprehensive risk score, and then perform weighted correction on the event occurrence probability in combination with the dynamic correction coefficient to obtain a revised comprehensive risk score; S540.2. Update the customer risk level based on the matching result between the revised comprehensive risk score and the risk level threshold table in S310; S540.3. Extract the implicit relationship between the health status label and the risk level label through the association analysis algorithm to generate a cross-label association influence matrix; S540.4. Generate an updated risk prediction set based on the updated customer risk level, the cross-tag association impact matrix, and the event list associated with the risk level in the risk event library in S320.

[0022] By adopting the above technical solution, combined with the cross-label association analysis algorithm and the risk event library, it is possible to discover the implicit relationship between the health status label and the risk level label through association analysis, thereby generating a cross-label association impact matrix; the cross-label association impact matrix can help the management platform to more accurately consider the mutual influence between different labels when updating the customer's risk level, and provide richer data support for subsequent risk prediction and decision-making; through this process, the management platform can provide each customer with a more personalized risk assessment, and at the same time, when the customer's risk changes, timely adjust the risk prediction set and insurance strategy to ensure the scientificity and timeliness of the decision.

[0023] Further configuration is that the process of generating a differentiated insurance policy in S550 is: S550.1. Matching a benchmark insurance plan from a preset strategy library based on the updated customer risk level, dynamic weight value distribution characteristics and dynamic correction coefficient; S550.2. Optimize the parameters of the benchmark insurance scheme through genetic algorithms to generate differentiated insurance strategies; S550.3. Perform logical conflict detection on the optimized differentiated insurance strategy: If it is detected that the premium floating interval has an opposite trend to the first dynamic weight value of the health status tag, and the dynamic correction coefficient is lower than the preset threshold, and there is no external environmental data to support the reverse adjustment, the strategy backtracking mechanism is triggered to readjust the preset risk factor weight ratio in S310; If no logical conflict is detected, the differentiated insurance policy is confirmed as the final output policy.

[0024] By adopting the above technical solution and optimizing the benchmark insurance plan through genetic algorithms, the platform can generate personalized insurance strategies based on the specific circumstances of each customer. This process can ensure that each customer's insurance plan matches their risk characteristics, thereby improving customer satisfaction and enhancing customer trust in insurance products. By performing logical conflict detection on the optimized insurance strategy, the management platform can avoid insurance strategy conflicts caused by improper parameter settings.

[0025] In summary, the present invention has the following beneficial effects: Through the dynamic fusion of multi-source data and real-time iteration of label weights, a closed-loop management platform is built, which ultimately realizes the dynamic risk assessment and significantly improves the risk response speed and customer service accuracy of life insurance companies. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic diagram of the process of an embodiment; Figure 2 It is a sub-step of S200 in the embodiment; Figure 3 It is a sub-step of S300 in the embodiment; Figure 4 It is a sub-step of S400 in the embodiment; Figure 5 It is a sub-step of S500 in the embodiment. DETAILED DESCRIPTION

[0027] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0028] As attached Figures 1 to 5 As shown; This embodiment discloses a data tracking and analysis management platform based on a digital life insurance company, including a management platform. The operation process of the management platform specifically includes the following steps: S100, obtaining multi-source customer data; wherein the multi-source customer data includes basic customer information, insurance policy records, health monitoring data, consumer behavior data and claims records, and the multi-source customer data is collected in real time or in batches through IoT devices, mobile terminal applications and enterprise databases; Specifically, this platform adopts a microservice architecture and is deployed on a cloud server cluster, including a data collection layer, a computing engine layer, a decision layer, and an interaction layer. The data collection layer connects to smart wearable devices, mobile apps, government public databases, and enterprise ERP systems through an API gateway; the computing engine layer implements real-time stream processing and batch computing based on the Spark distributed framework; the decision layer has a built-in risk model library and strategy optimization engine; the interaction layer provides a visual dashboard and a dual-end push interface, specifically the customer WeChat applet and the salesperson's PC terminal.

[0029] S200, performing structured processing on multi-source customer data to generate a customer portrait data set; wherein the customer portrait data set includes at least one customer tag set, each customer tag set is uniquely associated with a customer, and the customer tag set includes a risk level tag, a behavior preference tag, a health status tag, and their corresponding dynamic weight values; S300, generating an initial risk prediction set based on the customer tag set, the initial risk prediction set is used to push to the business decision terminal; S400, real-time monitoring of customer behavior events and external environment data, and generating dynamic adjustment signals according to preset trigger rules; customer behavior events include policy renewal operations, abnormal changes in health data, and claim application submissions, and external environment data include economic fluctuation index, medical policy updates, and natural disaster warnings; S500, re-evaluating the risk based on the dynamic adjustment signal and the initial risk prediction set to generate an updated risk prediction set; wherein the updated risk prediction set is used to correct the dynamic weight value in the customer portrait data set and generate a differentiated insurance strategy; S600. Generate a visual analysis report based on the customer portrait data set, and push differentiated insurance strategies to customer terminals and business decision terminals.

[0030] Specifically, the structured processing of multi-source customer data in S200 includes: S210, associating and mapping the basic customer information with the insurance policy record through the unique customer identification code to generate a basic customer file; In this embodiment, a mapping relationship between the customer ID and the policy number is established, and the household registration address and occupation type fields are merged to generate a basic file; S220, using a K-means clustering algorithm to classify the health monitoring data, generate health status labels, and calculate a first dynamic weight value corresponding to each health status label based on a time series analysis method; wherein the calculation process of the first dynamic weight value is: according to the ratio of the mean of the health monitoring data within a preset time window to the standard deviation of the health monitoring data, multiplied by a preset normalization coefficient, to obtain a weight value of the health status label; In this embodiment, K-means clustering can be performed on the customer's blood pressure data for the past three months to generate a "blood pressure fluctuation type" health label; the mean μ=128 and the standard deviation σ=8 are calculated for the 30-day window period, then the first dynamic weight value = (μ / σ) × normalization coefficient, the normalization coefficient is set to 0.5, and the calculated first dynamic weight value is 8; S230, performing sentiment polarity analysis on text information in the consumer behavior data through natural language processing technology, generating behavior preference labels, and calculating a second dynamic weight value of each behavior preference label based on a TF-IDF algorithm; wherein the second dynamic weight value is calculated by extracting a weight value of a keyword through a TF-IDF algorithm, and then multiplying the weight value by a preset behavior influence factor to generate a weight value of the behavior preference label; In this example, NLP sentiment analysis is performed on the customer service dialogue text of "I feel that the critical illness insurance coverage is not enough" in the mobile APP, and the BERT model is used to identify "insufficient coverage" as a negative keyword. The TF-IDF score is calculated as 0.12, multiplied by the behavior factor 0.8, and the second dynamic weight value is 0.096; S240, matching the historical claims records with the preset risk event library, marking the risk level labels, and simulating the probability of occurrence and impact intensity of the risk events through the Monte Carlo simulation algorithm, and calculating the third dynamic weight value of each risk level label; wherein the third dynamic weight value is calculated by: multiplying the simulated probability of occurrence of the event by the impact coefficient, and then multiplying by the preset risk adjustment factor to generate the weight value of the risk level label; In this embodiment, it is detected that the customer applied for lung cancer claims in 2021, matching the "malignant tumor" entry in the risk event library; Monte Carlo simulation is performed 100,000 times, and the probability of recurrence within 5 years is found to be 18%, the impact coefficient is 0.7, and the adjustment factor is 1.2. The third dynamic weight value is 0.151.

[0031] S250. Integrate the health status label and its first dynamic weight value, the behavior preference label and its second dynamic weight value, the risk level label and its third dynamic weight value to generate a customer label set, and aggregate all customer label sets into a customer portrait data set; wherein, the customer portrait data set is stored in a distributed database, supporting real-time query and batch update.

[0032] Specifically, generating an initial risk prediction set in S300 includes: S310, calculating a comprehensive risk score of the customer based on the first dynamic weight value, the second dynamic weight value, and the third dynamic weight value in the customer tag set; S320, dividing the risk levels according to the comprehensive risk scores and generating an initial risk prediction set; Specifically, S310 includes the following sub-steps: Respectively obtain a first dynamic weight value of the health status label, a second dynamic weight value of the behavior preference label, and a third dynamic weight value of the risk level label; Multiply each dynamic weight value by its corresponding preset risk coefficient, where the preset risk coefficients include the health risk coefficient α, the behavior risk coefficient β and the risk event coefficient γ, which take the preset values ​​of 0.1, 5.0 and 3.0 respectively; The result of multiplying each dynamic weight value by its corresponding preset risk factor is added together to generate a comprehensive risk score for the customer; In this embodiment, the customer's comprehensive risk score = first dynamic weight value × 0.1 + second dynamic weight value × 5.0 + third dynamic weight value × 3.0 = 1.877; Specifically, S320 includes the following sub-steps: Preset risk level threshold table to define the comprehensive risk score intervals corresponding to low risk, medium risk, and high risk; The risk level threshold table is shown in Table 1; Table 1 Preset risk level thresholds Risk Level Comprehensive risk score range Low risk [0, 1.2) Medium risk [1.2, 2.5) High risk [2.5, +∞) Match the customer's comprehensive risk score with the risk level threshold table to determine the customer's risk level; In this example, the customer's comprehensive risk score of 1.877 is medium risk; A list of events associated with risk levels is extracted from the preset risk event library to generate an initial risk prediction set; wherein, the initial risk prediction set includes event name, event probability, impact coefficient and priority score; wherein, the priority score is calculated based on the weighted sum of event probability and impact coefficient, specifically, the weight ratio is 60% for probability value and 40% for impact coefficient.

[0033] Specifically, in S320, conflict detection is performed on the multi-dimensional label set of the same customer. If the logical relationship between the health status label and the risk level label is inconsistent, a manual review process is triggered; wherein the logical relationship contradiction is defined as: the health status label indicates low risk and the risk level label indicates high risk, or the health status label indicates high risk and the risk level label is not adjusted synchronously.

[0034] In this example, a customer's health label shows "normal BMI (first dynamic weight value is 2.1)", but the risk label is "high risk (third dynamic weight value is 0.4)". When the management platform detects that the first dynamic weight value is lower than the preset health risk safety threshold (3.0) and the third dynamic weight value is higher than the preset risk level warning threshold (0.3), the conflict rule is triggered and a review work order is generated and sent to the underwriting department. Manual verification found that the customer was engaged in high-altitude work, and the third dynamic weight value was recalculated to 0.35 after manually adding the "occupational risk" label.

[0035] Specifically, generating a dynamic adjustment signal in S400 includes: S410, setting a trigger rule base; The trigger rules in the trigger rule library include: If the health monitoring data exceeds the threshold range for N consecutive days, a health risk warning is triggered; preferably, N is set to 3; If the economic volatility index in the external environment data exceeds the volatility threshold, it triggers a reassessment of economic risks; preferably, the volatility threshold is set at 3%; If the customer fails to complete the policy renewal operation within the preset time, the churn risk mark will be triggered; S420, monitoring customer behavior events and external environment data streams in real time through an event-driven architecture; S430: When it is detected that a behavior event matches a trigger rule, a dynamic adjustment signal including an event type, a timestamp, and an impact range is generated.

[0036] Specifically, in S500, risk reassessment is performed based on the dynamic adjustment signal and the updated risk prediction set, including: S510, receiving a dynamic adjustment signal and parsing event type, timestamp and impact range parameters, extracting an abnormal feature vector associated with a customer tag set; wherein the abnormal feature vector includes health monitoring deviation, economic fluctuation sensitivity and policy renewal hysteresis period; S520, constructing a risk transmission model based on the Bayesian network, performing joint probability distribution calculation on the abnormal feature vector and the probability of occurrence of events in the initial risk prediction set, and generating a dynamic correction coefficient; S530, iteratively correcting the first dynamic weight value, the second dynamic weight value, and the third dynamic weight value in the customer portrait data set based on the dynamic adjustment signal; S540, generating an updated risk prediction set based on the revised first dynamic weight value, the second dynamic weight value, and the third dynamic weight value, and updating the customer risk level; S550, generating differentiated insurance strategies; S560. Write the updated risk prediction set and differentiated insurance strategies into the customer portrait data set, overwriting the original dynamic weight values ​​and risk prediction results.

[0037] Specifically, the process of generating the dynamic correction coefficient in S520 includes: S520.1. According to the event type in the dynamic adjustment signal, the corresponding weight matrix is ​​matched from the preset conduction path weight matrix library; wherein the conduction path weight matrix is ​​a three-dimensional tensor structure, and the dimensions include event type dimension, abnormal feature vector dimension and risk event dimension, and the matrix element value is the conditional probability weight obtained by historical data training, and the matrix element value is calculated by counting the conditional probability of each event type and abnormal feature vector triggering a risk event in the historical data; S520.2. Input the abnormal feature vector into the pre-trained random forest model, and output the probability of the risk transmission intensity of the abnormal feature to the risk event; wherein the random forest model uses health monitoring deviation, economic fluctuation sensitivity and policy renewal hysteresis period as input features, and the probability of risk transmission intensity as output target, and the random forest model is trained offline through the dynamic weight value of the historical claims records and customer label set in the risk event library; S520.3. Extract the current timestamp and the reference timestamp of the probability of occurrence of the corresponding event in the initial risk prediction set, and calculate the time difference between the two; substitute the time difference and the preset decay period parameter into the decay function to generate the time decay coefficient, and the decay period parameter is dynamically set according to the event type defined in the trigger rule library in S410; In this embodiment, specifically: Health risk warning: Use logarithmic decay function, the expression is D=log(1+Δt / T 1 ), where D is the time attenuation coefficient, Δt is the time difference, T1 is the preset cycle parameter, the value is 7; Economic risk reassessment: using a linear attenuation function, expressed as D = Δt / T 2 , where D is the time attenuation coefficient, Δt is the time difference, T 2 is the preset cycle parameter, the value is 3; Loss risk marker: Use exponential decay function, the expression is D=exp(Δt / T 3 )−1, where D is the time attenuation coefficient, Δt is the time difference, and T 3 It is the preset period parameter, and its value is 15.

[0038] S520.4. Weighted fusion of the matching weight values ​​in the conduction path weight matrix, the risk conduction intensity probability and the time attenuation coefficient output by the random forest model to generate a dynamic correction coefficient; In this embodiment, the specific formula is: C=W ij ⋅P / (1+D); Where C represents the dynamic correction coefficient, W ij It represents the matching weight value in the conduction path weight matrix, P represents the risk conduction intensity probability, and D represents the time attenuation coefficient.

[0039] S520.5. Normalize the dynamic correction coefficient so that it is mapped to the interval [0,1].

[0040] Specifically, the process of iteratively correcting the first dynamic weight value, the second dynamic weight value, and the third dynamic weight value in the customer portrait data set based on the dynamic adjustment signal in S530 is: S530.1. If the dynamic adjustment signal is a health risk warning, perform the following steps: Based on the standard deviation ratio of the health monitoring deviation and the mean of the health monitoring data calculated in S220, combined with the dynamic correction coefficient, a weighted linear interpolation method is used to update the first dynamic weight value corresponding to the health status label; Triggering the Monte Carlo simulation recalculation of the risk level label, using the updated first dynamic weight value and the dynamic correction coefficient as input parameters, and regenerating the third dynamic weight value; If the difference between the regenerated third dynamic weight value and the original value exceeds a preset threshold value, which is set to 10%, a secondary correction of the cross-label association influence matrix is ​​triggered until the weight value change converges within the threshold value; S530.2. If the dynamic adjustment signal is an economic risk reassessment, perform the following steps: Extract the sensitivity of economic fluctuations, calculate the deviation coefficient between the economic fluctuation index and the preset industry benchmark, add the product of the deviation coefficient and the dynamic correction coefficient to the risk adjustment factor corresponding to the third dynamic weight value of the risk level label, and generate the corrected third dynamic weight value; S530.3. If the dynamic adjustment signal is a loss risk marker, perform the following steps: A negative correlation function is constructed based on the inverse of the policy renewal lag period, and the second dynamic weight value of the behavior preference label and the weighted value of the dynamic correction coefficient are substituted into the function to recalculate the behavior risk coefficient; Next, a revised second dynamic weight value is generated based on the updated behavior risk coefficient.

[0041] Specifically, in S540, an updated risk prediction set is generated based on the revised first dynamic weight value, the second dynamic weight value, and the third dynamic weight value, and the process of updating the customer risk level is as follows: S540.1. Re-input the revised first dynamic weight value, second dynamic weight value, and third dynamic weight value into S310 to calculate the comprehensive risk score, and then perform weighted correction on the event occurrence probability in combination with the dynamic correction coefficient to obtain a revised comprehensive risk score; S540.2. Update the customer risk level based on the matching result between the revised comprehensive risk score and the risk level threshold table in S310; S540.3. Extract the implicit relationship between the health status label and the risk level label through the association analysis algorithm to generate a cross-label association influence matrix; S540.4. Generate an updated risk prediction set based on the updated customer risk level, the cross-tag association impact matrix, and the event list associated with the risk level in the risk event library in S320.

[0042] Specifically, the process of generating a differentiated insurance policy in S550 is as follows: S550.1. Matching a benchmark insurance plan from a preset strategy library based on the updated customer risk level, dynamic weight value distribution characteristics and dynamic correction coefficient; S550.2. Optimize the parameters of the benchmark insurance plan through genetic algorithms to generate differentiated insurance strategies; the optimization parameters include the premium floating range, the elastic threshold of the coverage, and the claim response priority.

[0043] S550.3. Perform logical conflict detection on the optimized differentiated insurance strategy: If it is detected that the premium floating interval has an opposite trend to the first dynamic weight value of the health status tag, and the dynamic correction coefficient is lower than the preset threshold, which is set to 0.5, and there is no external environmental data to support the reverse adjustment, the strategy backtracking mechanism is triggered to readjust the preset risk factor weight ratio in S310; If no logical conflict is detected, the differentiated insurance policy is confirmed as the final output policy.

[0044] In this embodiment, the preset strategy library in S550.1 matches the benchmark insurance plan "whole life insurance + critical illness supplementary insurance" for medium-risk male customers aged 50; the parameter optimization in S550.2 corresponds to premium-to-benefit ratio = expected claim amount / (premium*discount rate); after 100 generations of evolution, the output is "term life insurance to 70 years old + cancer special insurance", which reflects the generation logic of "differentiated insurance strategy".

[0045] In S550.3, the management platform suggested increasing the premium by 10% for a "health improvement" customer (the first dynamic weight value dropped from 0.4 to 0.2). It was detected that the trend of the first dynamic weight value change was inconsistent with the premium adjustment direction. Retrospective analysis revealed that a new record of "frequent beneficiary changes" was added to the behavior label; the revised strategy was "premium remains unchanged but beneficiary change restriction clauses are added".

[0046] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

Claims

1. A data tracking, analysis and management platform based on digital life insurance companies, characterized in that: Including a management platform, the operation process of the management platform specifically includes the following steps: S100, obtaining multi-source customer data; wherein the multi-source customer data includes basic customer information, insurance policy records, health monitoring data, consumer behavior data and claims records; S200, performing structured processing on multi-source customer data to generate a customer portrait data set; wherein the customer portrait data set includes at least one customer tag set, and the customer tag set includes a risk level tag, a behavior preference tag, a health status tag, and the dynamic weight values ​​corresponding to each of them; S300, generating an initial risk prediction set based on the customer tag set; S400, real-time monitoring of customer behavior events and external environment data, and generating dynamic adjustment signals according to preset trigger rules; S500, re-evaluating the risk based on the dynamic adjustment signal and the initial risk prediction set to generate an updated risk prediction set; wherein the updated risk prediction set is used to correct the dynamic weight value in the customer portrait data set and generate a differentiated insurance strategy; S600. Generate a visual analysis report based on the customer portrait data set.

2. A data tracking, analysis and management platform based on digital life insurance companies according to claim 1, characterized in that: Structural processing of multi-source customer data in S200 includes: S210, associating and mapping the basic customer information with the insurance policy record through the unique customer identification code to generate a basic customer file; S220, using a K-means clustering algorithm to classify the health monitoring data, generate health status labels, and calculate a first dynamic weight value corresponding to each health status label based on a time series analysis method; wherein the calculation process of the first dynamic weight value is: according to the ratio of the mean of the health monitoring data within a preset time window to the standard deviation of the health monitoring data, multiplied by a preset normalization coefficient, to obtain a weight value of the health status label; S230, performing sentiment polarity analysis on text information in the consumer behavior data through natural language processing technology, generating behavior preference labels, and calculating a second dynamic weight value of each behavior preference label based on a TF-IDF algorithm; wherein the second dynamic weight value is calculated by extracting a weight value of a keyword through a TF-IDF algorithm, and then multiplying the weight value by a preset behavior influence factor to generate a weight value of the behavior preference label; S240, matching the historical claims records with the preset risk event library, marking the risk level labels, and simulating the probability of occurrence and impact intensity of the risk events through the Monte Carlo simulation algorithm, and calculating the third dynamic weight value of each risk level label; wherein the third dynamic weight value is calculated by: multiplying the simulated probability of occurrence of the event by the impact coefficient, and then multiplying by the preset risk adjustment factor to generate the weight value of the risk level label; S250. Integrate the health status label and its first dynamic weight value, the behavior preference label and its second dynamic weight value, the risk level label and its third dynamic weight value to generate a customer label set, and aggregate all customer label sets into a customer portrait data set; wherein, the customer portrait data set is stored in a distributed database, supporting real-time query and batch update.

3. A data tracking, analysis and management platform based on digital life insurance companies according to claim 2, characterized in that: Generating an initial risk prediction set in S300 includes: S310, calculating a comprehensive risk score of the customer based on the first dynamic weight value, the second dynamic weight value, and the third dynamic weight value in the customer tag set; S320, dividing the risk level according to the comprehensive risk score and generating an initial risk prediction set; wherein, S310 specifically includes the following sub-steps: Respectively obtain a first dynamic weight value of the health status label, a second dynamic weight value of the behavior preference label, and a third dynamic weight value of the risk level label; Multiply each dynamic weight value by its corresponding preset risk factor, where the preset risk factor includes a health risk factor, a behavioral risk factor, and a risk event factor; The result of multiplying each dynamic weight value by its corresponding preset risk factor is added together to generate a comprehensive risk score for the customer; S320 specifically includes the following sub-steps: Preset risk level threshold table to define the comprehensive risk score intervals corresponding to low risk, medium risk, and high risk; Match the customer's comprehensive risk score with the risk level threshold table to determine the customer's risk level; A list of events associated with risk levels is extracted from a preset risk event library to generate an initial risk prediction set; wherein the initial risk prediction set includes event name, event probability, impact coefficient and priority score; wherein the priority score is calculated based on the weighted sum of the event probability and the impact coefficient.

4. A data tracking, analysis and management platform based on digital life insurance companies according to claim 3, characterized in that: In S320, conflict detection is performed on the multi-dimensional label set of the same customer. If the logical relationship between the health status label and the risk level label is inconsistent, a manual review process is triggered; wherein the logical relationship contradiction is defined as: the health status label indicates low risk and the risk level label indicates high risk, or the health status label indicates high risk and the risk level label is not adjusted synchronously.

5. A data tracking, analysis and management platform based on digital life insurance companies according to claim 1, characterized in that: Generating a dynamic adjustment signal in S400 includes: S410, setting a trigger rule base; The trigger rules in the trigger rule library include: If the health monitoring data exceeds the threshold range for N consecutive days, a health risk warning will be triggered; If the economic volatility index in the external environment data exceeds the volatility threshold, it will trigger a reassessment of economic risks; If the customer fails to complete the policy renewal operation within the preset time, the churn risk mark will be triggered; S420, monitoring customer behavior events and external environment data streams in real time through an event-driven architecture; S430: When it is detected that a behavior event matches a trigger rule, a dynamic adjustment signal including an event type, a timestamp, and an impact range is generated.

6. A data tracking, analysis and management platform based on digital life insurance companies according to claim 5, characterized in that: S500 performs risk reassessment based on the dynamic adjustment signal and the updated risk prediction set, including: S510, receiving a dynamic adjustment signal and parsing event type, timestamp and impact range parameters, extracting an abnormal feature vector associated with a customer tag set; wherein the abnormal feature vector includes health monitoring deviation, economic fluctuation sensitivity and policy renewal hysteresis period; S520, constructing a risk transmission model based on the Bayesian network, performing joint probability distribution calculation on the abnormal feature vector and the probability of occurrence of events in the initial risk prediction set, and generating a dynamic correction coefficient; S530, iteratively correcting the first dynamic weight value, the second dynamic weight value, and the third dynamic weight value in the customer portrait data set based on the dynamic adjustment signal; S540, generating an updated risk prediction set based on the revised first dynamic weight value, the second dynamic weight value, and the third dynamic weight value, and updating the customer risk level; S550, generating differentiated insurance strategies; S560. Write the updated risk prediction set and differentiated insurance strategies into the customer portrait data set, overwriting the original dynamic weight values ​​and risk prediction results.

7. A data tracking, analysis and management platform based on digital life insurance companies according to claim 6, characterized in that: The process of generating the dynamic correction coefficient in S520 includes: S520.

1. According to the event type in the dynamic adjustment signal, the corresponding weight matrix is ​​matched from the preset conduction path weight matrix library; wherein the conduction path weight matrix is ​​a three-dimensional tensor structure, the dimensions of which include event type dimension, abnormal feature vector dimension and risk event dimension, and the matrix element value is the conditional probability weight obtained by historical data training; S520.

2. Input the abnormal feature vector into the pre-trained random forest model, and output the probability of the risk transmission intensity of the abnormal feature to the risk event; wherein the random forest model uses health monitoring deviation, economic fluctuation sensitivity and policy renewal hysteresis period as input features, and the probability of risk transmission intensity as output target, and the random forest model is trained offline through the dynamic weight value of the historical claims records and customer label set in the risk event library; S520.

3. Extract the current timestamp and the reference timestamp of the probability of occurrence of the corresponding event in the initial risk prediction set, and calculate the time difference between the two; substitute the time difference and the preset decay period parameter into the decay function to generate the time decay coefficient, and the decay period parameter is dynamically set according to the event type defined in the trigger rule library in S410; S520.

4. Weighted fusion of the matching weight values ​​in the conduction path weight matrix, the risk conduction intensity probability and the time attenuation coefficient output by the random forest model to generate a dynamic correction coefficient; S520.

5. Normalize the dynamic correction coefficient.

8. A data tracking, analysis and management platform based on digital life insurance companies according to claim 6, characterized in that: The process of iteratively correcting the first dynamic weight value, the second dynamic weight value, and the third dynamic weight value in the customer portrait data set based on the dynamic adjustment signal in S530 is as follows: S530.

1. If the dynamic adjustment signal is a health risk warning, perform the following steps: Based on the standard deviation ratio of the health monitoring deviation and the mean of the health monitoring data calculated in S220, combined with the dynamic correction coefficient, a weighted linear interpolation method is used to update the first dynamic weight value corresponding to the health status label; Triggering the Monte Carlo simulation recalculation of the risk level label, using the updated first dynamic weight value and the dynamic correction coefficient as input parameters, and regenerating the third dynamic weight value; If the difference between the regenerated third dynamic weight value and the original value exceeds a preset threshold, a secondary correction of the cross-label association influence matrix is ​​triggered until the weight value change converges within the threshold; S530.

2. If the dynamic adjustment signal is an economic risk reassessment, perform the following steps: Extract the sensitivity of economic fluctuations, calculate the deviation coefficient between the economic fluctuation index and the preset industry benchmark, add the product of the deviation coefficient and the dynamic correction coefficient to the risk adjustment factor corresponding to the third dynamic weight value of the risk level label, and generate the corrected third dynamic weight value; S530.

3. If the dynamic adjustment signal is a loss risk marker, perform the following steps: A negative correlation function is constructed based on the inverse of the policy renewal lag period, and the second dynamic weight value of the behavior preference label and the weighted value of the dynamic correction coefficient are substituted into the function to recalculate the behavior risk coefficient; Next, a revised second dynamic weight value is generated based on the updated behavior risk coefficient.

9. A data tracking, analysis and management platform based on digital life insurance companies according to claim 6, characterized in that: In S540, an updated risk prediction set is generated based on the revised first dynamic weight value, the second dynamic weight value, and the third dynamic weight value, and the process of updating the customer risk level is as follows: S540.

1. Re-input the revised first dynamic weight value, second dynamic weight value, and third dynamic weight value into S310 to calculate the comprehensive risk score, and then perform weighted correction on the event occurrence probability in combination with the dynamic correction coefficient to obtain a revised comprehensive risk score; S540.

2. Update the customer risk level based on the matching result between the revised comprehensive risk score and the risk level threshold table in S310; S540.

3. Extract the implicit relationship between the health status label and the risk level label through the association analysis algorithm to generate a cross-label association influence matrix; S540.

4. Generate an updated risk prediction set based on the updated customer risk level, the cross-tag association impact matrix, and the event list associated with the risk level in the risk event library in S320.

10. A data tracking, analysis and management platform based on digital life insurance companies according to claim 6, characterized in that: The process of generating a differentiated insurance policy in S550 is as follows: S550.

1. Matching a benchmark insurance plan from a preset strategy library based on the updated customer risk level, dynamic weight value distribution characteristics and dynamic correction coefficient; S550.

2. Optimize the parameters of the benchmark insurance scheme through genetic algorithms to generate differentiated insurance strategies; S550.

3. Perform logical conflict detection on the optimized differentiated insurance strategy: If it is detected that the premium floating interval has an opposite trend to the first dynamic weight value of the health status tag, and the dynamic correction coefficient is lower than the preset threshold, and there is no external environmental data to support the reverse adjustment, the strategy backtracking mechanism is triggered to readjust the preset risk factor weight ratio in S310; If no logical conflict is detected, the differentiated insurance policy is confirmed as the final output policy.

Images