Insurance service method and device based on full-chain geographic position, equipment and medium

Abstract

The invention provides an insurance service method and device based on a full-chain geographic position, equipment and a medium, and relates to the field of data processing. According to the method, the insurance service request, including the service demand information, the service data and the position data, of the user is accurately obtained, and comprehensive data support is provided for processing of the insurance service. By determining the business data demand and the corresponding business model, the data can be collected and integrated in a more targeted manner, and the integrity and accuracy of the information are ensured. The application of model analysis makes the data processing more automatic and intelligent, improves the accuracy of risk assessment and fraud detection, and optimizes the claim decision process. And the output business service result is beneficial for realizing automation and intelligentization of the insurance business process, human errors are reduced, and the response speed is improved, so that the processing efficiency and quality of the whole insurance business are greatly improved, and quicker and more accurate insurance services are provided for customers.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to an insurance service method, device, equipment and medium based on full-chain geographic location. Background Art

[0002] Currently, the insurance industry has begun to use GPS and location services to optimize risk assessment and claims efficiency, but most of them focus on responding to single events and lack comprehensive management of the insurance life cycle. The application of AI and big data is mainly concentrated in risk assessment and fraud detection, while the integration of large language models is still in its infancy and is mainly used for automated customer service and document processing. It lacks complex application scenarios that are deeply integrated into accident handling and claims decision-making.

[0003] At present, the insurance industry lacks an intelligent solution that fully integrates geographic location information and covers insurance life cycle management. There are deficiencies in data collection, integration and analysis applications, which leads to information loss at user contact points and data dispersion, making the processing efficiency of insurance business inefficient.

[0004] Therefore, how to improve the business processing efficiency of insurance business has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides an insurance service method, device, equipment and medium based on full-chain geographical location, aiming to improve the business processing efficiency of insurance business.

[0006] In a first aspect, the present application provides an insurance service method based on a full-chain geographical location, and the insurance service method based on a full-chain geographical location comprises the following steps:

[0007] Acquire an insurance service request of a target user, wherein the insurance service request includes service demand information, first service data, and location data;

[0008] Based on the insurance business request, determining a business data requirement of at least one current business project and a first business model corresponding to each of the current business projects;

[0009] Based on the business data requirements of the current business project, obtaining first business data and location data;

[0010] Based on the first business model, a model analysis is performed on the first business data and the location data, and a business service result is output.

[0011] In a second aspect, the present application further provides an insurance service device based on a full-chain geographical location, the insurance service device based on a full-chain geographical location comprising:

[0012] A request acquisition module, used to acquire an insurance service request of a target user, wherein the insurance service request includes service demand information, first service data and location data;

[0013] A business demand determination module, configured to determine, based on the insurance business request, a business data demand of at least one current business project and a first business model corresponding to each of the current business projects;

[0014] A data acquisition module, used to acquire first business data and location data based on the business data requirements of the current business project;

[0015] A data analysis module is used to perform model analysis on the first business data and the location data based on the first business model, and output a business service result.

[0016] In a third aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the above-mentioned insurance service method based on the full-chain geographic location are implemented.

[0017] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the insurance service method based on the full-chain geographic location as described above are implemented.

[0018] The present application provides an insurance service method, device, computer equipment and storage medium based on the full-chain geographic location. The method of the present application includes obtaining the insurance business request of the target user, wherein the insurance business request includes service demand information, first business data and location data; based on the insurance business request, determining the business data demand of at least one current business project and the first business model corresponding to each current business project; based on the business data demand of the current business project, obtaining the first business data and location data; based on the first business model, performing model analysis on the first business data and the location data, and outputting the business service result. In the above manner, the present application provides comprehensive data support for the processing of insurance business by accurately obtaining the user's insurance business request, including service demand information, business data and location data. By determining the business data demand and the corresponding business model, data can be collected and integrated in a more targeted manner to ensure the integrity and accuracy of the information. The use of model analysis makes data processing more automated and intelligent, improves the accuracy of risk assessment and fraud detection, and optimizes the claims decision-making process. The output business service results help to realize the automation and intelligence of insurance business processes, reduce human errors and improve response speed, thereby greatly improving the processing efficiency and quality of the entire insurance business and providing customers with faster and more accurate insurance services. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A flowchart of a first embodiment of an insurance service method based on a full-chain geographical location provided by this application;

[0021] Figure 2 A schematic diagram of the structure of a smart insurance ecosystem driven by a full-chain geographic location service provided in an embodiment of the present application;

[0022] Figure 3 It is a structural schematic diagram of a first embodiment of an insurance service device based on full-chain geographical location provided by the present application;

[0023] Figure 4 It is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application.

[0024] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0027] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0028] Please refer to Figure 1 , Figure 1 A flowchart of a first embodiment of an insurance service method based on full-chain geographic location provided in this application.

[0029] like Figure 1 As shown, the insurance service method based on the entire chain geographic location includes steps S101 to S104.

[0030] S101, obtaining an insurance service request of a target user, wherein the insurance service request includes service demand information, first service data, and location data;

[0031] In one embodiment, the target user can log in to the client and initiate an insurance service request to the server through the client. The server analyzes the insurance service request to obtain the service demand, location data and service-related data of the target user.

[0032] Specifically, service demand information may include customers' specific needs for insurance services, such as insurance types (such as health insurance, life insurance, accident insurance, etc.), coverage, and premium budget, etc. The insurer displays all insurance information to consumers through the smart insurance ecosystem, remotely obtains necessary insurance information, and realizes basic functions such as confirming the location of the insured and the insured, and identifying the insured's identity.

[0033] Specifically, the first business data may include basic information of the target customer, such as name, contact information and occupation, as well as data related to the insurance product, such as the insured amount, insurance period and payment method, and may also include accident data related to insurance claims.

[0034] Specifically, in the insurance business, location data may include data such as the insured location of the policyholder and the insured, vehicle trajectory, and accident location.

[0035] In one embodiment, the present application provides a smart insurance ecosystem driven by a full-chain geographic location service, such as Figure 2 As shown, the system can include insurance business-related modules such as multi-dimensional data fusion and processing module, intelligent risk assessment and customized insurance product module, real-time risk monitoring and disaster warning module, behavior incentive and insurance preferential module, claim automation and anti-fraud module and personalized insurance product recommendation and explanation module.

[0036] S102: Based on the insurance business request, determine a business data requirement of at least one current business project and a first business model corresponding to each current business project;

[0037] In one embodiment, the current business projects may include insurance projects such as multi-dimensional data fusion, risk assessment, risk monitoring and disaster warning, behavioral incentives, insurance claims, and personalized customization of insurance products.

[0038] In one embodiment, the target user's business data needs are determined based on the insurance business needs, including insurance type, coverage, premium budget, claim settlement needs, etc. The target user's basic information, including name, contact information, and occupation, etc., may also be included.

[0039] Generally, the first business model can pre-configure insurance business-related data models and data algorithms according to actual insurance business needs, such as data fusion algorithms, deep learning models, risk assessment models, large language models, etc.

[0040] For example, Figure 2 In the smart insurance ecosystem shown, different insurance business modules use different data types and algorithm models.

[0041] Specifically, the multi-dimensional data fusion and processing module can connect with multiple data sources to provide strong data support for the smart insurance ecosystem. The multi-dimensional data fusion and processing module fuses multi-dimensional data through data fusion algorithms to establish a correlation network between user behavior and social environment.

[0042] Specifically, the intelligent risk assessment and customized insurance product module uses the LSTM (Long Short-Term Memory) network to learn the time series characteristics of the user's historical location data and combine other factors to predict the risk level. It uses collaborative filtering or content-based recommendation algorithms to recommend the most suitable insurance products to users based on risk assessment results.

[0043] Specifically, the real-time risk monitoring and disaster warning module can predict the probability of disasters based on meteorological data and disaster warning data through machine learning-based risk prediction models, such as random forest or XGBoost, combined with real-time data. The spatiotemporal prediction model, combined with spatiotemporal sequence analysis, can predict the risk status of a specific location at a certain point in the future.

[0044] Specifically, the behavioral incentive and insurance discount module identifies user behavior patterns through clustering algorithms, trains models to learn users' positive feedback, and dynamically adjusts incentive strategies to maximize user engagement and health levels.

[0045] Specifically, the claims automation and anti-fraud module uses OCR (optical character recognition) technology to automatically read the report materials and combine it with the rule engine to preliminarily determine the eligibility of claims. It also combines GPS data analysis with machine learning models such as Isolation Forest or Autoencoder to identify abnormal claims behavior.

[0046] Specifically, the personalized insurance product recommendation and explanation module combines the user's historical data, location information and behavior patterns, and uses a large language model to generate personalized insurance product introductions and recommendation reasons.

[0047] S103, acquiring first business data and location data based on the business data requirements of the current business project;

[0048] Furthermore, based on the business data requirements, target data of at least one dimension is collected from at least one data source; based on a data processing algorithm, data processing is performed on the target data of each dimension to obtain the first business data and the location data.

[0049] In one embodiment, the insurer may collect multi-dimensional target data corresponding to the business data requirements from various data sources based on the business data requirements, including but not limited to basic customer information, insurance records, and claims records. It may also include external data such as medical data, credit score data, etc. These data can help verify the information provided by the customer.

[0050] In one embodiment, the first business data may include basic user information (such as name, contact information, occupation, etc.), insurance data such as the insured amount, insurance period, payment method, claim data such as accident description, accident scene data, user health status, insurance history and other related data.

[0051] In one embodiment, the location data may include the geographic location data of the policyholder and the insured to support the remote insurance application and underwriting process. It may also include data such as the location where the accident occurred.

[0052] In one embodiment, the target data is processed by a data processing algorithm, and operation processes such as data cleaning, data integration, and real-time stream processing can be used. Among them, data cleaning can remove noise and inconsistent data and process missing values; data integration can use ETL (Extract, Transform, Load) tools to unify the format of data from different sources; real-time stream processing can use Apache Kafka or Flink to build a real-time data processing pipeline to perform real-time analysis on the data stream.

[0053] It is understandable that data processing may also include other operations, such as data integration, data transformation, data reduction, etc.

[0054] S104: Based on the first business model, perform model analysis on the first business data and the location data, and output a business service result.

[0055] In one embodiment, data processing is performed through corresponding business service modules according to different business needs, and different business service modules analyze and process the first business data and location data through the first business model according to business needs, and output the model analysis results to respond to insurance business requests.

[0056] In a specific embodiment, when the current business project is multi-dimensional data fusion and processing, the first business data may include GPS data, social media geo-tags, Internet of Things (IoT) devices, climate and environmental data, and public safety information.

[0057] Among them, GPS data includes real-time user location information and location information of accidents. Social media geo-tags include extracting location information shared by users on social media to understand their daily activity areas. Internet of Things (IoT) devices include environmental data and user behavior data provided by smart homes and wearable devices. Climate and environmental data include public weather station data and satellite data, which are used to analyze climate conditions and natural disaster risks. Public safety information includes accident reports and crime records from governments and non-governmental organizations.

[0058] Then, through the data processing algorithm, the multi-dimensional data is cleaned, integrated and analyzed in real time. Finally, through the data fusion algorithm, the graph-based data fusion method is used to establish the association network of user behavior and social environment.

[0059] Specifically, data is collected from multiple data sources, which may include social media, online transaction records, geographic location information, etc. Preprocessing steps include data cleaning, formatting, and standardization to ensure data consistency and quality. Use graph data models to represent the relationship between users and social environments. In a graph model, nodes can represent users or entities, and edges represent the relationship between them. This model can capture complex interactions and relationships and is suitable for social network analysis. Data fusion algorithms are applied to integrate information from different data sources. This may include feature-level fusion, where features extracted from various data sources are combined to form a more complete user profile. Graph analysis techniques such as community detection, path analysis, and centrality analysis are used to identify key patterns and trends in user behavior and social environments.

[0060] By integrating multi-dimensional data, this embodiment enables the insurance company to more accurately assess the risk level of the insured object and provide customers with more personalized premium pricing. It also optimizes its own risk-bearing structure and improves the accuracy of risk assessment.

[0061] In one embodiment, based on the first business data, the risk assessment data of the target user is determined; based on the first business model, feature learning is performed on the risk assessment data and the location data to generate a risk prediction level for the target user; based on the risk prediction level, target products matching the risk prediction level are screened to generate a product recommendation plan.

[0062] Specifically, when the current business project is a risk assessment business, personal data such as the user's historical claim records, health records, and vehicle maintenance records are collected, as well as historical disaster incidence, average loss and other data in the industry benchmark risk database. These data will serve as the basis for model training. In the data preprocessing stage, the data needs to be cleaned, normalized, and segmented to improve the training effect of the model.

[0063] Specifically, based on the first business data, the risk assessment data of the target user is determined. This may include the user's claim frequency, claim amount, health score, etc., which will be used to assess the user's risk level. A deep learning model, such as an LSTM network, is used to learn the time series features in the user's historical location data and predict the risk level in combination with other factors. Among them, the LSTM network is particularly suitable for processing and predicting time series data, can capture long-term dependencies, and is suitable for financial risk assessment.

[0064] Specifically, recommendation system algorithms, such as collaborative filtering or content-based recommendation algorithms, are used to recommend the most suitable insurance products to users based on risk assessment results. Collaborative filtering recommendation systems analyze the similarities between users and recommend content that similar users like; while content-based recommendation systems analyze the characteristics of the content itself and recommend content that is similar to the user's historical behavior.

[0065] This embodiment utilizes automated processing and intelligent analysis technology to reduce the need for manual review, shorten the claims cycle, speed up the claims processing process, and improve customer satisfaction. At the same time, it effectively reduces false claims and protects company assets through anti-fraud technology.

[0066] In one embodiment, based on the location data, at least one target location is determined; based on the first business data, the meteorological monitoring data corresponding to each of the target locations is determined; based on the first business model, a risk analysis is performed on the meteorological monitoring data corresponding to each of the target locations to generate a disaster risk prediction result corresponding to each of the target locations.

[0067] Specifically, meteorological monitoring data can include real-time meteorological data, earthquake monitoring network, flood warning system and other meteorological monitoring data. In addition, multi-dimensional data sources such as global marine meteorological observation data, ground meteorological data, high-altitude meteorological data, weather radar data, etc. can also be added to provide more comprehensive disaster prediction information. For example, various meteorological data provided by the National Meteorological Information Center.

[0068] Specifically, GIS technology can be used to build more detailed and dynamic risk maps by combining multi-source data, such as topography, land use, population distribution, etc. High-risk areas can be identified and visualized through spatial analysis tools.

[0069] Specifically, when developing risk prediction models based on machine learning, algorithms such as random forests, XGBoost, and LSTM neural networks can be considered. For example, the random forest model performs well in urban rainstorm waterlogging predictions, with high prediction accuracy and stability. At the same time, the long short-term memory network (LSTM) can be used to predict the time series of water depth in combination with spatiotemporal series analysis to predict the risk status of a specific location at a certain point in the future. Combined with spatiotemporal series analysis, the risk status of a specific location at a certain point in the future can be predicted. For example, the LSTM-based weather forecast model can predict future rainfall, snowfall, temperature changes and other data by learning the features and time patterns in historical meteorological data.

[0070] Specifically, a real-time monitoring system can be established to collect and analyze data source information in real time, and to update risk maps and prediction results in a timely manner. Through the early warning system, disaster warning information can be issued to users so that preventive measures can be taken, such as moving vehicles to safe areas.

[0071] This embodiment can notify insurance companies and customers of potential risks in advance through a real-time risk monitoring and disaster warning system, so that preventive measures can be taken to reduce losses caused by disasters. It reflects the shift from passive compensation to active risk management and enhances disaster prevention and loss reduction capabilities.

[0072] In one embodiment, based on a behavior pattern recognition algorithm, the behavior characteristics of the target user are extracted from the first business data and the location data to determine the user behavior pattern of the target user; based on the first business model, the user behavior pattern is evaluated to generate a behavior reward strategy.

[0073] Specifically, in the behavior pattern recognition business, the user's GPS trajectory data and health APP physiological data can be collected. Among them, GPS trajectory data can reflect driving habits, exercise volume, etc. Health App data can include health indicators such as steps and heart rate.

[0074] Specifically, clustering algorithms such as K-Means can be used to perform pattern recognition on user behaviors and classify user behaviors into different categories or patterns. This can be achieved by analyzing features such as the frequency and speed changes of users' activities within a specific time period. Deep learning methods such as convolutional neural networks (CNN), long short-term memory networks (LSTM), or graph convolutional networks (GCN) can be used to extract more complex features and improve the accuracy of behavior recognition.

[0075] Specifically, you can design channels for earning points, such as health indicators such as the number of steps and heart rate recorded by the health app, or driving habits monitored by GPS trajectory data to earn points. At the same time, set rules for earning points, such as daily check-ins, completing specific health tasks, etc. You can set channels for spending points, such as using points to redeem insurance discounts, deduct order amounts, and redeem coupons. At the same time, formulate rules for redeeming points, such as how many points can be converted into how much amount to deduct from an order. You can also set the validity period of points, and expired points will be invalidated. When consuming points, you can design the system to give priority to points that are about to expire.

[0076] Specifically, the model can be trained through reinforcement learning, learning the positive feedback of users, and dynamically adjusting the incentive strategy. This can be achieved by designing a reward function that not only reflects the ultimate goal of the task, but also should be fed back to the agent in a timely manner, balancing sparse rewards and dense rewards to avoid the emergence of pseudo-targets. Learning can be accelerated by adding additional reward signals without changing the optimal strategy. This can be done by defining a potential function that evaluates the "distance" between the current state and the target state and adjusts the reward accordingly.

[0077] This embodiment encourages users to adopt a safer and healthier lifestyle through a behavioral incentive mechanism, promoting improvements in customer behavior, which not only reduces personal risks, but also promotes the improvement of the overall welfare of society and enhances customer loyalty.

[0078] In one embodiment, based on the first business data, the accident authentication data of the claim accident is identified, including the location and time of the accident; based on the location data, the accident authentication data is verified to determine the accident verification result; when the accident verification result is passed, based on the first business model, the first business data is subjected to a claim analysis to generate an accident claim plan.

[0079] In a specific embodiment, in the claims handling business, multiple data sources and technical means are combined to improve the efficiency and accuracy of claims handling while reducing fraud.

[0080] Specifically, in addition to accident scene photos, video records and GPS track records, accident authentication data can also include the vehicle's black box data, maintenance records, medical records, police reports, etc., providing more comprehensive background information for claims.

[0081] Specifically, by comparing GPS track records with accident reports, the location and time of the accident can be verified. If the GPS data at the accident site does not match the information provided in the report, this may indicate a false claim. Based on the first business model, the claims data can be deeply analyzed in combination with machine learning algorithms to generate personalized claims solutions. For example, by analyzing historical claims data, the probability and amount of compensation for different types of accidents can be predicted, thereby providing a reference for new claims cases.

[0082] Specifically, abnormal claims behavior can be identified through spatiotemporal behavior pattern analysis. For example, if a claimant files multiple claims in a short period of time, or the location of the claim does not match their daily activity area, this may be a sign of fraud. Using intelligent claims solutions, such as the OCR technology provided by Baidu AI Open Platform, medical bills can be automatically identified to speed up the claims process.

[0083] Specifically, the accident compensation plan should include medical expenses, loss of work time, nursing fees, compensation for mental damage and subsequent treatment costs, etc., to ensure that victims receive reasonable compensation.

[0084] This embodiment uses OCR technology to read the report materials. OCR technology can also be used to identify medical documents, identity documents, etc. to automatically collect personal information required for claims. Machine learning models (such as isolation forests and autoencoders, support vector machines (SVM), random forests, gradient boosting trees, etc.) can be used to improve the accuracy of fraud detection. By analyzing the associations between claimants, potential fraud gangs can be discovered. For example, if the parties in multiple claims cases have close social connections, this may be a sign of gang fraud. Using graph databases such as NebulaGraph to store and query complex relational data can effectively identify and analyze fraud networks.

[0085] In one embodiment, based on the first business data, the historical business data and behavior pattern data of the target user are determined; based on the first business model, the historical business data, behavior pattern data and location data are analyzed to generate personalized business promotion text.

[0086] Specifically, big data technology is used to collect users' historical business data, behavior pattern data, and location data. User data is analyzed to identify users' needs and preferences, including their insurance purchase history, search habits, and mobile app usage. Based on the analysis results, a large language model is used to generate personalized insurance product introductions and recommendation reasons. Natural language generation technology can be used to provide easy-to-understand insurance product descriptions to increase transparency and trust.

[0087] Specifically, customized insurance product recommendation letters or simulated chat conversations can be generated based on user portraits, using the conversational capabilities of large language models to provide a more natural and humane interactive experience.

[0088] The location-based services in this embodiment help insurance companies allocate resources more reasonably, such as strengthening monitoring or deploying more resources in high-risk areas, achieving efficient operations, and optimizing resource allocation. Digital transformation and intelligent services have improved the market competitiveness of insurance companies, meeting the needs of different customers through customized products and services, leading the industry's innovation trends, and improving competitiveness and innovation.

[0089] This embodiment provides an insurance service method based on full-chain geographic location. The application method provides comprehensive data support for the processing of insurance business by accurately obtaining the user's insurance business request, including service demand information, business data and location data. By determining the business data requirements and the corresponding business model, data can be collected and integrated in a more targeted manner to ensure the integrity and accuracy of the information. The use of model analysis makes data processing more automated and intelligent, improves the accuracy of risk assessment and fraud detection, and optimizes the claims decision-making process. The output business service results help to realize the automation and intelligence of insurance business processes, reduce human errors and increase response speed, thereby greatly improving the processing efficiency and quality of the entire insurance business, and providing customers with faster and more accurate insurance services.

[0090] See also Figure 3 , Figure 3 It is a structural schematic diagram of the first embodiment of an insurance service device based on a full-chain geographical location provided in the present application. The insurance service device based on a full-chain geographical location is used to execute the aforementioned insurance service method based on a full-chain geographical location.

[0091] like Figure 3 As shown, the insurance service device 200 based on the entire chain geographic location includes: a request acquisition module 201, a business demand determination module 202, a data acquisition module 203 and a data analysis module 204.

[0092] A request acquisition module 201 is used to acquire an insurance service request of a target user, wherein the insurance service request includes service demand information, first service data and location data;

[0093] A business requirement determination module 202, configured to determine, based on the insurance business request, a business data requirement of at least one current business project and a first business model corresponding to each current business project;

[0094] A data acquisition module 203, configured to acquire first business data and location data based on the business data requirements of the current business project;

[0095] The data analysis module 204 is used to perform model analysis on the first business data and the location data based on the first business model, and output a business service result.

[0096] In one embodiment, the data acquisition module 203 includes:

[0097] A data collection unit, configured to collect target data of at least one dimension from at least one data source based on the business data requirement;

[0098] A data processing unit is used to perform data processing on the target data of each dimension based on a data processing algorithm to obtain the first business data and the location data.

[0099] In one embodiment, the data analysis module 204 includes:

[0100] a risk assessment data determining unit, configured to determine risk assessment data of the target user based on the first business data;

[0101] a risk prediction level generating unit, configured to perform feature learning on the risk assessment data and the location data based on the first business model to generate a risk prediction level for the target user;

[0102] The product recommendation scheme generating unit is used to screen target products matching the risk prediction level based on the risk prediction level and generate a product recommendation scheme.

[0103] In one embodiment, the data analysis module 204 includes:

[0104] a target position determination unit, configured to determine at least one target position based on the position data;

[0105] A meteorological monitoring data determining unit, configured to determine the meteorological monitoring data corresponding to each of the target locations based on the first service data;

[0106] The disaster risk prediction unit is used to perform risk analysis on the meteorological monitoring data corresponding to each of the target locations based on the first business model, and generate disaster risk prediction results corresponding to each of the target locations.

[0107] In one embodiment, the data analysis module 204 includes:

[0108] a behavior pattern analysis unit, configured to extract the behavior characteristics of the target user from the first service data and the location data based on a behavior pattern recognition algorithm, and determine a user behavior pattern of the target user;

[0109] A reward strategy generating unit is used to evaluate the user behavior pattern based on the first business model and generate a behavior reward strategy.

[0110] In one embodiment, the data analysis module 204 includes:

[0111] An accident authentication data identification unit, used to identify the accident authentication data of the claim settlement accident based on the first business data, including the location and time of the accident;

[0112] An accident verification unit, configured to verify the accident authentication data based on the location data and determine an accident verification result;

[0113] An accident claim settlement plan generating unit is used to perform a claim settlement analysis on the first business data based on the first business model to generate an accident claim settlement plan when the accident verification result is verified passed.

[0114] In one embodiment, the data analysis module 204 includes:

[0115] a data determination unit, configured to determine the historical business data and behavior pattern data of the target user based on the first business data;

[0116] A text generation unit is used to analyze the historical business data, behavior pattern data and location data based on the first business model to generate personalized business promotion text.

[0117] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned insurance service method embodiment based on the full-chain geographical location, and will not be repeated here.

[0118] The apparatus provided in the above embodiment may be implemented in the form of a computer program. The computer program may be Figure 4 Runs on the computer device shown.

[0119] See also Figure 4 , Figure 4 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0120] See also Figure 4 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0121] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any insurance service method based on the full-chain geographical location.

[0122] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0123] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any insurance service method based on the full-chain geographic location.

[0124] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0126] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0127] Acquire an insurance service request of a target user, wherein the insurance service request includes service demand information, first service data, and location data;

[0128] Based on the insurance business request, determining a business data requirement of at least one current business project and a first business model corresponding to each of the current business projects;

[0129] Based on the business data requirements of the current business project, obtaining first business data and location data;

[0130] Based on the first business model, a model analysis is performed on the first business data and the location data, and a business service result is output.

[0131] In one embodiment, when the processor implements the business data requirement based on the current business project and acquires the first business data and the location data, it is configured to implement:

[0132] Based on the business data requirement, collecting target data of at least one dimension from at least one data source;

[0133] Based on a data processing algorithm, the target data in each dimension is processed to obtain the first business data and the location data.

[0134] In one embodiment, when the processor performs model analysis on the first business data and the location data based on the first business model and outputs the business service result, it is configured to implement:

[0135] Determining risk assessment data of the target user based on the first business data;

[0136] Based on the first business model, feature learning is performed on the risk assessment data and the location data to generate a risk prediction level of the target user;

[0137] Based on the risk prediction level, target products matching the risk prediction level are screened and product recommendation plans are generated.

[0138] In one embodiment, when the processor performs model analysis on the first business data and the location data based on the first business model and outputs the business service result, it is configured to implement:

[0139] determining at least one target location based on the location data;

[0140] Based on the first business data, determining the meteorological monitoring data corresponding to each of the target locations;

[0141] Based on the first business model, risk analysis is performed on the meteorological monitoring data corresponding to each of the target locations to generate disaster risk prediction results corresponding to each of the target locations.

[0142] In one embodiment, when the processor performs model analysis on the first business data and the location data based on the first business model and outputs the business service result, it is configured to implement:

[0143] Based on a behavior pattern recognition algorithm, extracting the behavior characteristics of the target user from the first business data and the location data, and determining a user behavior pattern of the target user;

[0144] Based on the first business model, the user behavior pattern is evaluated to generate a behavior reward strategy.

[0145] In one embodiment, when the processor performs model analysis on the first business data and the location data based on the first business model and outputs the business service result, it is configured to implement:

[0146] Based on the first business data, identifying the accident authentication data of the claim settlement accident, including the location and time of the accident;

[0147] Based on the location data, verify the accident authentication data to determine an accident verification result;

[0148] When the accident verification result is passed, a claim analysis is performed on the first business data based on the first business model to generate an accident claim plan.

[0149] In one embodiment, when the processor performs model analysis on the first business data and the location data based on the first business model and outputs the business service result, it is configured to implement:

[0150] Based on the first business data, determining the historical business data and behavior pattern data of the target user;

[0151] Based on the first business model, the historical business data, behavior pattern data and location data are analyzed to generate personalized business promotion text.

[0152] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any one of the insurance service methods based on the full-chain geographic location provided in the embodiments of the present application.

[0153] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0154] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An insurance service method based on full-chain geographical location, characterized in that: The method comprises: Acquire an insurance service request of a target user, wherein the insurance service request includes service demand information, first service data, and location data; Based on the insurance business request, determining a business data requirement of at least one current business project and a first business model corresponding to each of the current business projects; Based on the business data requirements of the current business project, obtaining first business data and location data; Based on the first business model, a model analysis is performed on the first business data and the location data, and a business service result is output.

2. The insurance service method based on the full chain geographical location according to claim 1 is characterized in that: The acquiring the first business data and the location data based on the business data requirement of the current business project includes: Based on the business data requirement, collecting target data of at least one dimension from at least one data source; Based on a data processing algorithm, the target data in each dimension is processed to obtain the first business data and the location data.

3. The insurance service method based on the full chain geographical location according to claim 1 is characterized in that: The performing model analysis on the first business data and the location data based on the first business model and outputting a business service result includes: Determining risk assessment data of the target user based on the first business data; Based on the first business model, feature learning is performed on the risk assessment data and the location data to generate a risk prediction level of the target user; Based on the risk prediction level, target products matching the risk prediction level are screened and product recommendation plans are generated.

4. The insurance service method based on the full chain geographical location according to claim 1 is characterized in that: The performing model analysis on the first business data and the location data based on the first business model and outputting a business service result includes: determining at least one target location based on the location data; Based on the first business data, determining the meteorological monitoring data corresponding to each of the target locations; Based on the first business model, risk analysis is performed on the meteorological monitoring data corresponding to each of the target locations to generate disaster risk prediction results corresponding to each of the target locations.

5. The insurance service method based on the full chain geographical location according to claim 1 is characterized in that: The performing model analysis on the first business data and the location data based on the first business model and outputting a business service result includes: Based on a behavior pattern recognition algorithm, extracting the behavior characteristics of the target user from the first business data and the location data, and determining a user behavior pattern of the target user; Based on the first business model, the user behavior pattern is evaluated to generate a behavior reward strategy.

6. The insurance service method based on the full chain geographical location according to claim 1 is characterized in that: The performing model analysis on the first business data and the location data based on the first business model and outputting a business service result includes: Based on the first business data, identifying the accident authentication data of the claim settlement accident, including the location and time of the accident; Based on the location data, verify the accident authentication data to determine an accident verification result; When the accident verification result is passed, a claim analysis is performed on the first business data based on the first business model to generate an accident claim plan.

7. The insurance service method based on the full chain geographical location according to claim 1 is characterized in that: The performing model analysis on the first business data and the location data based on the first business model and outputting a business service result includes: Based on the first business data, determining the historical business data and behavior pattern data of the target user; Based on the first business model, the historical business data, behavior pattern data and location data are analyzed to generate personalized business promotion text.

8. An insurance service device based on the entire chain of geographical locations, characterized in that: The insurance service device based on the full chain geographical location includes: A request acquisition module, used to acquire an insurance service request of a target user, wherein the insurance service request includes service demand information, first service data and location data; A business demand determination module, configured to determine, based on the insurance business request, a business data demand of at least one current business project and a first business model corresponding to each of the current business projects; A data acquisition module, used to acquire first business data and location data based on the business data requirements of the current business project; A data analysis module is used to perform model analysis on the first business data and the location data based on the first business model, and output a business service result.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the insurance service method based on the full-chain geographic location 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 a computer program, wherein when the computer program is executed by a processor, the steps of the insurance service method based on the full-chain geographic location as described in any one of claims 1 to 7 are implemented.

Images