Insurance policy data processing method and device, equipment, storage medium and program product

Abstract

The invention provides an insurance policy data processing method and device, equipment, a storage medium and a program product. Relates to the technical field of data processing. The method comprises the following steps: acquiring historical effective insurance policy data and a basic feature tag corresponding to a target user; calculating the accumulated insurance amount of the target user in the insurance policy coincidence time by adopting a preset insurance amount calculation model based on the historical effective insurance policy data and the basic feature tag; according to the accumulated insurance amount, generating an uncertainty type label of the target user by adopting a preset uncertainty type label generation strategy; and determining an insurance policy data processing result based on the basic feature tag corresponding to the target user and the uncertainty type tag. According to the method provided by the invention, the problem that the traditional processing method cannot reflect the short-term behavior fluctuation of the customer is solved, the missing detection condition caused by the sudden change of the customer behavior is effectively reduced, and the timeliness and accuracy of data processing are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a policy data processing method, apparatus, equipment, storage medium, and program product. Background Technology

[0002] In the process of diversification in the insurance industry, non-motor insurance has become a core engine of business growth due to its rich product offerings and broad market potential. As customer needs become increasingly personalized and risk scenarios continue to evolve, non-motor insurance is characterized by a wide variety of risks and distinct customer segmentation, placing higher demands on the precision and efficiency of uncertainty management.

[0003] Currently, the mainstream policy data processing and risk control methods in the insurance industry are mainly divided into two categories: one is the traditional model that relies on manual review, which verifies the policyholder's identity documents, financial status and other documents, and conducts background investigations and risk assessments based on human experience; the other is the automated verification model based on preset thresholds, which triggers the corresponding uncertainty review process by setting fixed thresholds such as the insured amount, the frequency of insurance, and the number of claims.

[0004] However, manual review processes are cumbersome and inefficient, and subjective judgment can easily lead to missed detections, making it difficult to cope with massive business demands; fixed threshold modes lack flexibility, are easily circumvented, and cannot adapt to complex scenarios; static data is difficult to capture the uncertainty fluctuations brought about by dynamic changes in customers' financial status, insurance behavior, etc. Summary of the Invention

[0005] The policy data processing method, apparatus, equipment, storage medium, and program products provided in this application are used to solve the technical problems of poor timeliness and accuracy in policy data processing in traditional methods.

[0006] In a first aspect, embodiments of this application provide a policy data processing method, the method comprising:

[0007] Obtain historical valid insurance policy data and basic feature tags for the target user;

[0008] The cumulative sum insured of the target user during the policy overlap period is calculated using a preset sum insured calculation model based on the historical valid policy data and basic feature tags.

[0009] Based on the cumulative insured amount, an uncertainty type label for the target user is generated using a preset uncertainty type label generation strategy;

[0010] The policy data processing result is determined based on the basic feature tags and uncertainty type tags corresponding to the target user.

[0011] In one possible implementation, the step of calculating the cumulative sum insured of the target user during the policy overlap period using a preset sum insured calculation model based on the historical valid policy data and basic feature tags includes:

[0012] Determine the set of overlapping periods between each historical policy and the current policy;

[0013] Calculate the sum insured of historical policies and current policies within the overlapping period of each policy, and multiply it by the adjustment factor corresponding to the target user to obtain the corresponding cumulative sum insured.

[0014] In one possible implementation, generating the uncertainty type label for the target user based on the accumulated insured amount using a preset uncertainty type label generation strategy includes:

[0015] If the cumulative sum insured exceeds a preset percentage of the historical average sum insured, a rapid increase in sum insured label will be generated.

[0016] If the cumulative insured amount exceeds the preset insured amount threshold corresponding to the type of the target user, an "excessively high insured amount" label is generated.

[0017] If the number of insurance applications for a target user exceeds a preset insurance application threshold within a preset time period, and the cumulative insured amount exceeds a preset insured amount threshold corresponding to the target customer type, a frequent insurance application risk label will be generated.

[0018] In one possible implementation, the basic feature tags include basic attribute tags, credit status tags, historical claims tags, and industry-related tags. Before obtaining the historical valid policy data and basic feature tags corresponding to the target user, the process further includes:

[0019] Obtain the insurance information of the target users;

[0020] Based on the insurance information, relevant attribute information is queried in a preset database, including credit information and historical claims information;

[0021] A preset basic feature label generation algorithm is used to generate corresponding feature labels based on the insurance information, credit information, and historical claims information.

[0022] In one possible implementation, determining the policy data processing result based on the basic feature tags and uncertainty type tags corresponding to the target user includes:

[0023] Based on the insurance information, determine the corresponding policy data processing strategy;

[0024] According to the preset priority order in the policy data processing strategy, the basic feature tags and uncertainty type tags are matched sequentially to obtain the matching results;

[0025] The policy data processing result is determined based on the matching result and the preset mapping relationship.

[0026] In one possible implementation, the policy data processing strategy is a multi-dimensional rule combination configuration, including a logical combination of AND / OR / NOT of basic feature labels and uncertainty type labels;

[0027] The policy data processing strategy can be added, modified, and disabled through a visual interface, and is synchronized in real time.

[0028] Secondly, embodiments of this application provide a policy data processing apparatus, comprising:

[0029] The acquisition module is used to acquire the historical valid insurance policy data and basic feature tags of the target user;

[0030] The calculation module is used to calculate the cumulative insured amount of the target user during the policy overlap period based on the historical valid policy data and basic feature tags using a preset insured amount calculation model;

[0031] The generation module is used to generate uncertainty type tags for the target user based on the cumulative insured amount and using a preset uncertainty type tag generation strategy;

[0032] The determination module is used to determine the policy data processing result based on the basic feature tags and uncertainty type tags corresponding to the target user.

[0033] Thirdly, embodiments of this application provide a policy data processing device, including: a memory and a processor;

[0034] The memory stores computer-executed instructions;

[0035] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0036] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0037] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0038] The policy data processing method, apparatus, device, storage medium, and program products provided in this application integrate historical valid policy data and basic feature tags to form a complete dataset, facilitating subsequent unified processing and analysis, improving the efficiency and accuracy of data processing, and avoiding frequent data conversion and matching between different data sources. The preset coverage calculation model has been trained and validated with a large amount of data, and can accurately calculate the cumulative coverage of a target user within the policy overlap period based on historical valid policy data and basic feature tags. The policy overlap period refers to the time when the insurance periods of different policies overlap; calculating the cumulative coverage within this period can prevent users from over-insuring. Combined with basic feature tags, the coverage calculation model can consider individual differences among users, achieving personalized coverage calculations. It adjusts the coverage calculation parameters according to the user's specific situation, improving the accuracy and rationality of the calculation results. The preset uncertainty type tag generation strategy can classify target users into different uncertainty types based on indicators such as cumulative coverage and generate corresponding tags, which can intuitively reflect the degree and characteristics of uncertainty faced by the user. By combining the basic characteristic tags and uncertainty type tags of the target users, we can comprehensively consider the individual characteristics and uncertainty of the users, provide more comprehensive and accurate decision support for policy data processing, and give accurate data processing results. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0040] Figure 1 An application scenario diagram of a policy data processing method provided in this application;

[0041] Figure 2 A flowchart illustrating a policy data processing method provided in an embodiment of this application;

[0042] Figure 3 A flowchart illustrating a policy data processing method provided in another embodiment of this application;

[0043] Figure 4 This is a schematic diagram of the structure of a policy data processing device provided in an embodiment of this application;

[0044] Figure 5 This is a schematic diagram of the structure of a policy data processing device provided in an embodiment of this application.

[0045] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0046] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0047] The collection, storage, use, processing, transmission, provision, and disclosure of financial data or user data involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0048] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0049] To clearly understand the technical solution of this application, the solutions of the prior art will be described in detail first.

[0050] In the process of diversification in the insurance industry, non-motor insurance has become a core driver of performance growth due to its rich product portfolio and broad market potential. As customer needs become increasingly personalized and various risk scenarios continue to evolve, non-motor insurance is gradually exhibiting characteristics of diversified risk types and distinct customer segmentation. This places more stringent demands on the precision and efficiency of managing uncertainties. Currently, the insurance industry mainly employs two mainstream methods in policy data processing and risk control: one is the traditional manual review model, where staff verify the insured's identity documents, financial status, and other relevant documents, and conduct background checks and risk assessments based on their experience; the other is an automated verification model based on preset thresholds, which triggers corresponding review processes for uncertainties by setting fixed standards such as insured amount, frequency of applications, and number of claims. However, existing methods have obvious shortcomings: the manual review process is complicated and inefficient, subjective judgment can easily lead to missed risks, and it is difficult to adapt to the processing needs of massive business; the fixed threshold mode lacks flexibility, is not only easy to be deliberately circumvented, but also cannot cope with complex and ever-changing risk scenarios; at the same time, relying solely on static data for risk assessment makes it difficult to accurately capture the uncertainties caused by dynamic factors such as changes in customers' financial status and adjustments to insurance behavior, which restricts the further improvement of risk control effectiveness.

[0051] Therefore, when facing technical challenges in existing technologies, to solve the data integration problem, a complete dataset is formed by acquiring historical valid policy data and basic feature tags of the target user, avoiding frequent data conversion and matching between different data sources. To address the inflexibility and susceptibility to circumvention issues of fixed threshold models, a pre-set sum assured calculation model is adopted, focusing on the core scenario of policy overlap time windows. It dynamically calculates the cumulative sum assured by integrating historical valid policy data and basic feature tags, breaking through the single limitation of fixed thresholds and achieving precise matching of sum assured assessment with the customer's actual insurance behavior and uncertainty characteristics, effectively coping with complex and ever-changing scenarios. To address the difficulty of capturing dynamic uncertainty fluctuations with static data, a pre-set uncertainty type tag generation strategy is established. This transforms the trends and scale of cumulative sum assured changes into concrete uncertainty type tags. Simultaneously, a dual analysis dimension of basic feature tags and uncertainty type tags is constructed to comprehensively characterize the customer's static risk attributes and dynamic behavioral risks. The policy data processing results are determined through tag combination matching, achieving precise control over dynamic and comprehensive risks.

[0052] Figure 1 An application scenario diagram illustrating the policy data processing method provided in this application is shown below. Figure 1 As shown in the diagram, the scenario corresponding to the policy data processing method provided in this application includes: a terminal device 101, a server 102, and a preset database 103. The policy data processing device can be integrated into the server 102.

[0053] Optionally, the policy issuance system can communicate with the policy data processing device via an interface. This interface adopts a RESTful architecture and uses the HTTP protocol for data transmission. The interface receives customer insurance information sent by the issuance system, including basic information of the policyholder, information of the insured, information of the insured product, and the insured amount. After the policy data processing device completes its processing, it returns standardized processing results and prompts through the interface. The processing results include information such as whether the risk control verification has been passed, whether supplementary information is required, and the adjusted premium rate. The prompts provide a detailed risk explanation to the issuance system based on the specific risk situation, such as "If the customer's credit rating is low, there is a certain risk; please handle with caution."

[0054] Specifically, sales personnel can initiate policy data processing requests through terminal device 101, such as sending policyholder information. Upon receiving the request, server 102 retrieves the target user's historical valid policy data and basic feature tags from the preset database 103. Then, server 102 uses a preset sum assured calculation model to calculate the target user's cumulative sum assured during the policy overlap period based on the historical valid policy data and basic feature tags. Based on the cumulative sum assured, it generates uncertainty type tags for the target user using a preset uncertainty type tag generation strategy. Finally, it determines the policy data processing result based on the target user's corresponding basic feature tags and uncertainty type tags. The processing result is then sent to terminal device 101 and displayed on a visual interface for sales personnel to view.

[0055] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0056] Figure 2 This is a flowchart illustrating a policy data processing method provided in an embodiment of this application, as shown below. Figure 2 As shown, the execution entity in this embodiment is a policy data processing device. This device can be implemented through a computer program, or through a medium storing the relevant computer program, such as a USB flash drive and / or optical disc, or through a physical device integrating or installing the relevant computer program, such as a chip or a policy data processing device. The policy data processing device can be a server, a server cluster, etc. The policy data processing method provided in this embodiment includes the following steps:

[0057] S201. Obtain the historical valid policy data and basic feature tags corresponding to the target user.

[0058] The target user refers to the natural person customer who submits the insurance application or the insured person specified in the insurance application.

[0059] Among them, historical valid policy data refers to the relevant data of the target user's previously purchased and valid policies, such as the policy purchase date, coverage period, and sum insured.

[0060] Among them, basic feature tags refer to a standardized set of tags generated based on the target user's static attributes, credit status, historical insurance behavior, and related risk information.

[0061] Specifically, upon receiving an insurance application submitted by a target user, the system automatically extracts the user's identity information, including unique identification fields such as the policyholder's or insured's name, ID number, and mobile phone number. Based on this identity, a distributed database query interface is used to traverse the stored core policy database, filtering out all historical policy records belonging to the user and currently valid. The filtered historical valid policy data is then integrated, and key fields for each policy are extracted to form a structured historical policy dataset. Finally, pre-generated and stored basic feature tags are extracted based on the user's identity information in this insurance application.

[0062] Understandably, a distributed database is a pre-configured database used to store multi-source data. First, detailed information on historical claims cases within the company is collected, including claim amounts, reasons for claims, claim dates, and policyholder information. This data is then cleaned, organized, and stored to build an internal claims information database. Industry risk information, such as industry risk indices, risk conditions in specific regions, and risk characteristics of specific population groups, is obtained through third-party database interfaces. Distributed database technologies, such as the Hadoop Distributed File System (HDFS) combined with NoSQL databases, are used to store and manage massive amounts of internal and external data. Data governance tools are used to perform data quality monitoring, data anonymization, and data backup to ensure data security and availability.

[0063] S202. Using a preset insured amount calculation model, the cumulative insured amount of the target user during the policy overlap period is calculated based on historical valid policy data and basic feature tags.

[0064] Among them, the preset coverage calculation model refers to a pre-built intelligent analysis model used to dynamically calculate the user's coverage. This model integrates historical policy data, user basic characteristics and time dimension factors, and accurately outputs the cumulative coverage within a specific time range through standardized calculation logic.

[0065] Among them, the policy overlap time refers to the period during which the coverage period of the policy corresponding to the target user's current insurance application overlaps with the coverage period of the user's historical valid policies.

[0066] The cumulative sum insured refers to the total sum insured of the target user's current policy plus the sum insured of all overlapping historical valid policies during the policy overlap period.

[0067] Specifically, the model first extracts the coverage period of the current policy, then compares it with the coverage period of each of the target user's historical valid policies to determine if there is any overlap between the two, thus forming the overlapping time period between the historical policy and the current policy. This process is repeated until the overlap time of all historical valid policies and the current policy is determined, and finally integrated to form a set of policy overlap times.

[0068] Furthermore, the model determines the adjustment factor based on the target user's basic feature tags and pre-defined rules. For each overlapping time period in the policy overlap time set, the model first calculates the total sum insured of all overlapping historical valid policies within that time period, and adds the sum insured of the current policy within that overlapping time period to obtain the total sum insured for that overlapping time period. Subsequently, this total sum insured is multiplied by the adjustment factor to obtain the cumulative sum insured corresponding to that overlapping time period.

[0069] S203. Based on the cumulative insured amount, generate uncertainty type labels for the target user using a preset uncertainty type label generation strategy.

[0070] Among them, the uncertainty type label refers to a standardized label generated based on the characteristics of the cumulative insured amount, such as its scale, growth trend, and matching degree, combined with the user's insurance behavior and risk attributes.

[0071] Among them, the preset uncertainty type label generation strategy refers to a standardized logical system that is pre-defined and includes label triggering conditions, judgment criteria, and priority rules.

[0072] Specifically, after calculating the cumulative sum insured, its features are broken down into multiple dimensions. This includes determining the typical sum insured range for the target user's group, calculating the growth rate of the cumulative sum insured compared to the target user's historical average sum insured over the same period (1-3 years), and linking the target user's insurance behavior data to extract the number of insurance applications within a preset timeframe and the changes in sum insured for each application.

[0073] For example, according to the preset rule priority in the strategy, the extracted cumulative coverage-related features are matched one by one with the triggering conditions of each tag. For example, when matching the tag of rapid coverage growth, the core judgment condition is that the cumulative coverage exceeds the preset percentage of the target user's historical average coverage, and further verification is made in combination with the time span of coverage growth. If the condition is met, the tag is triggered. When matching the tag of extremely high coverage, the preset coverage threshold corresponding to the target user's group is used as the core standard. If the cumulative coverage exceeds the threshold, the tag is triggered directly.

[0074] Optionally, after all conditions are matched, a corresponding uncertainty type label is generated based on the matching results. If only the triggering condition for a single label is met, the label is generated directly; if the triggering conditions for multiple labels are met simultaneously, such as both the excessively high coverage amount and the risk of frequent insurance purchases, the higher priority label is retained according to the preset priority, or a combined label is generated.

[0075] S204. Determine the policy data processing results based on the basic feature tags and uncertainty type tags corresponding to the target user.

[0076] Among them, the policy data processing result refers to the standardized business handling conclusion given based on the risk characteristics of the target user, combined with risk control rules and business needs, such as passing risk control verification or requiring supplementary special information.

[0077] Specifically, the basic characteristic tags of target users are fully integrated with uncertainty type tags, and a preset configurable risk control rule system is invoked. This system can be pre-configured by business personnel through a visual interface, including tag combination conditions, corresponding handling results, rule priorities, etc. The integrated tag set is matched according to the principle of prioritizing high-risk rules.

[0078] For example, single-tag triggering rule matching means that if a user only has one type of risk tag, the specific risk control rule corresponding to that tag will be matched. For instance, if only the "poor credit history" tag is present, the rule requiring supplementary financial documentation and income statements will be matched. Multi-tag combination triggering rule matching means that if a user has both basic characteristic tags and uncertainty type tags, the composite risk control rule corresponding to the tag combination will be matched. For instance, a combination of high-risk industries and frequent insurance purchases might trigger a rule to suspend policy issuance and initiate manual review.

[0079] Furthermore, based on the rule matching results, the corresponding policy data processing results are generated, along with detailed explanations. For example, when matching supplementary information rules, the types of supplementary information required are specified, such as financial proof, proof of residence, and a statement of the purpose of the insurance application, as well as the submission deadline. Finally, the processing results are packaged in a standardized format and fed back to the single system through a single service interface.

[0080] The policy data processing method provided in this application integrates historical valid policy data and basic feature tags to form a complete dataset, facilitating subsequent unified processing and analysis, improving the efficiency and accuracy of data processing, and avoiding frequent data conversion and matching between different data sources. The preset coverage calculation model has been trained and validated with a large amount of data, and can accurately calculate the cumulative coverage of a target user within the policy overlap period based on historical valid policy data and basic feature tags. The policy overlap period refers to the time when the insurance terms of different policies overlap; calculating the cumulative coverage within this period can prevent users from over-insuring. Combined with basic feature tags, the coverage calculation model can consider individual differences among users, achieving personalized coverage calculations. It adjusts the coverage calculation parameters according to the user's specific situation, improving the accuracy and rationality of the calculation results. The preset uncertainty type tag generation strategy can classify target users into different uncertainty types based on indicators such as cumulative coverage and generate corresponding tags, which can intuitively reflect the degree and characteristics of uncertainty faced by the user. By combining the target user's basic characteristic tags and uncertainty type tags, we can comprehensively consider the user's individual characteristics and uncertainty status, providing more comprehensive and accurate decision support for policy data processing and giving accurate data processing results.

[0081] As an optional implementation, based on the above embodiments, a preset sum assured calculation model is used to calculate the cumulative sum assured of the target user during any overlapping period of policies, based on historical valid policy data and basic feature tags. This includes:

[0082] Determine the set of overlapping periods between each historical policy and the current policy;

[0083] Calculate the sum insured of historical policies and current policies within the overlapping period of each policy, and multiply it by the adjustment factor corresponding to the target user to obtain the corresponding cumulative sum insured.

[0084] Among them, the policy overlap time set refers to the aggregate set of overlapping time periods formed by all historical valid policies and the current policy.

[0085] The total sum insured refers to the sum insured of all historical valid policies that overlap with the current policy within a specific overlapping time period, plus the sum insured of the current policy within that overlapping time period.

[0086] The adjustment factor refers to the risk correction coefficient determined based on the user's basic characteristic tags. It is used to adjust the sum insured calculation result in combination with the user's inherent risk level. For example, the coefficient for high-risk users is greater than 1, the coefficient for ordinary-risk users is equal to 1, and the coefficient for low-risk users is less than 1.

[0087] Specifically, the start date and end date of the current policy are extracted. Then, each of the target user's historical valid policies is retrieved one by one, and the start date and end date of the coverage for each historical policy are extracted. For each historical policy, it is determined whether there is any overlap. The overlap determination between all historical valid policies and the current policy is completed, and each determined overlap period is summarized and integrated to form a complete set of policy overlap times.

[0088] Furthermore, for each overlapping period in the set of overlapping policy periods, firstly, all overlapping historical valid policies within that period are identified, the sum assured of each historical policy is extracted and summed to obtain the subtotal of historical policy sum assured; then, the corresponding sum assured of the current policy within that overlapping period is calculated. The subtotal of historical policy sum assured is added to the converted sum assured of the current policy to obtain the total sum assured for that overlapping period.

[0089] Furthermore, adjustment factors are determined based on the target user's basic characteristic tags. For example, if a user's basic characteristic tags indicate high risk, a preset high-risk adjustment factor is activated. The sum of the insured amounts for a certain overlapping period is multiplied by the adjustment factor to obtain the cumulative insured amount for that period. If there are multiple non-contiguous overlapping periods in the policy overlap time set, the cumulative insured amount for each period is calculated separately. Finally, the cumulative insured amount for all periods is summed up, which is the target user's cumulative insured amount for any policy overlap period.

[0090] The policy data processing method provided in this application determines the set of overlapping time periods for each historical policy and the current policy, accurately identifying the overlapping portions of different policies in the time dimension. It calculates the sum insured of historical and current policies within each overlapping time period, ensuring that the sum insured of all relevant policies within the overlapping period is included in the calculation. This avoids situations where the cumulative sum insured is lowered due to the omission of certain policy sum insured, thus guaranteeing the completeness and accuracy of the cumulative sum insured calculation. Multiplying by the adjustment factor corresponding to the target user fully considers the individual characteristics and special circumstances of the target user, making the calculation of the cumulative sum insured more consistent with the actual situation of the target user, achieving personalized sum insured calculation.

[0091] As an optional implementation, based on the above embodiments, an uncertainty type tag for the target user is generated according to the cumulative insured amount using a preset uncertainty type tag generation strategy, including:

[0092] If the cumulative sum insured exceeds a preset percentage of the historical average sum insured, a "rapid increase in sum insured" label will be generated.

[0093] If the cumulative insured amount exceeds the preset insured amount threshold corresponding to the target user's type, an "excessively high insured amount" label will be generated.

[0094] If the number of insurance applications for a target user exceeds the preset insurance application threshold within a preset time period, and the cumulative insured amount exceeds the preset insured amount threshold for the target customer type, a frequent insurance application risk label will be generated.

[0095] Among them, the historical average sum insured refers to the statistical average of the cumulative sum insured of the target user's historical valid policies over the same period of time.

[0096] The preset ratio refers to a threshold ratio set in advance based on historical claims data, industry risk characteristics, and business management needs, which is used to define the standard for rapid growth of the insured amount.

[0097] Among them, target customer type refers to the group category divided according to the basic characteristic tags of target users.

[0098] Among them, the preset coverage threshold refers to the upper limit standard of coverage set for different target customer types.

[0099] The preset time refers to a pre-set time window used to monitor the frequency of user insurance purchases, such as 7 days or 30 days.

[0100] The number of insurance applications refers to the number of valid insurance applications submitted by the target user within a preset time period.

[0101] Among them, the preset insurance threshold refers to the standard set in advance to define the number of times frequent insurance is purchased, such as the threshold of 3 times for ordinary customers to purchase insurance within 30 days.

[0102] Optionally, retrieve historical valid policy data from the user's past policies that overlap with the current policy's timeframe, calculate the cumulative sum assured for the corresponding period, and then calculate the historical average sum assured using an arithmetic mean. Divide the cumulative sum assured within the current policy's overlapping timeframe by the historical average sum assured to obtain the sum assured growth rate. Compare the calculated sum assured growth rate with a preset rate. If the growth rate exceeds the preset rate, the user's sum assured growth is deemed abnormal, and a rapid sum assured growth tag is automatically generated; otherwise, the tag is not triggered.

[0103] Optionally, based on the user's basic feature tags, a corresponding target customer type is matched. Based on the determined target customer type, a preset coverage threshold corresponding to that type of customer is retrieved from a preset threshold library. The cumulative coverage within the current policy overlap period is compared with the preset coverage threshold. If the cumulative coverage exceeds the preset coverage threshold, the user's coverage is determined to be outside a reasonable range, and an excessively high coverage tag is automatically generated; otherwise, the tag is not triggered.

[0104] Optionally, a preset time parameter, such as 30 days, can be retrieved. Based on the user's identity, all valid insurance records within the preset time period are queried, and the total number of insurance applications, including this one, is calculated. The target customer type is determined based on the user's basic characteristic tags, and the preset insurance application threshold and preset coverage threshold for that customer type are retrieved. First, it is determined whether the number of insurance applications exceeds the preset insurance application threshold. Then, it is determined whether the cumulative coverage within the current policy overlap period exceeds the preset coverage threshold for that customer type. Only when both conditions are met simultaneously is the user deemed to have an abnormal risk of frequent insurance applications with excessively high coverage, and a frequent insurance application risk tag is automatically generated. If either condition is not met, the tag is not triggered.

[0105] Furthermore, after determining the trigger conditions for the three types of tags mentioned above, the results are comprehensively verified. If the trigger conditions for multiple tags are met simultaneously, then the corresponding multiple tags are generated simultaneously; if only the trigger condition for a single tag is met, then that single tag is generated; if none of the conditions are met, then no uncertain type tags are generated.

[0106] The policy data processing method provided in this application generates uncertainty type tags that quantify a user's risk level. Different types of tags correspond to different levels of risk, and users' risks can be sorted and categorized based on the type and number of tags. Based on the user's uncertainty type tags, more personalized insurance products and services can be provided.

[0107] As an optional implementation, based on the above embodiments, the basic feature tags include basic attribute tags, credit status tags, historical claims tags, and industry-related tags. Before obtaining the historical valid policy data and basic feature tags corresponding to the target user, the following steps are also included:

[0108] Obtain the insurance information of the target users;

[0109] Based on the insurance information, relevant attribute information is queried from a pre-set database. The relevant attribute information includes credit information and historical claims information.

[0110] A preset basic feature label generation algorithm is used to generate corresponding feature labels based on insurance information, credit information, and historical claims information.

[0111] Among them, basic attribute tags refer to tags generated based on users' core personal information, reflecting users' stable or unchanging attribute characteristics, such as age groups, gender, occupation type, and residential area.

[0112] Among them, credit status tags are tags generated based on user credit-related data, reflecting the user's credit level and ability to fulfill obligations, such as credit rating.

[0113] Among them, the historical claims tag refers to the tag generated based on the user's past insurance claims behavior, which reflects the user's risk-related characteristics such as the frequency and scale of claims, such as whether there are large claims records.

[0114] Among them, industry-related tags refer to tags generated based on the industry to which a user's profession belongs, reflecting the risk level of the industry in which the user works.

[0115] Among them, the insurance information refers to the relevant information filled in or provided by the target user when submitting the insurance application, including the identity information of the policyholder or insured, occupation, residential address, type of insurance product, amount of insurance, and coverage period.

[0116] The pre-built database refers to a centralized storage system that integrates multiple data sources and covers internally stored policy data, claims data, and connected credit data.

[0117] Among them, the preset basic feature label generation algorithm refers to a set of standardized label generation logic and rules that are set in advance. By analyzing, judging and classifying insurance information, credit information and historical claims information, it automatically generates corresponding basic feature labels.

[0118] Specifically, upon receiving an insurance application from a target user, the system extracts application information from the policy, such as ID number, mobile phone number, name, age, and occupation. Using core identity identifiers from the application information, such as the ID number, as search keywords, the system accesses a pre-set database for multi-dimensional information queries to obtain the target user's credit information and historical claims information. After the query is complete, the obtained credit information, historical claims information, and the current insurance application information are correlated and integrated to form a complete user risk-related dataset. A pre-set basic feature label generation algorithm is then activated to classify the integrated insurance application information, credit information, and historical claims information, generating four categories of basic feature labels.

[0119] Optionally, basic attribute tags can be generated by directly extracting relevant fields from the insurance information and assigning values.

[0120] Optionally, credit status labels can be generated by establishing a credit scoring model, standardizing the acquired credit data, inputting it into the model to calculate a credit score, and generating corresponding credit rating labels based on preset scoring ranges.

[0121] Optionally, historical claims tags can be generated: by querying and statistically analyzing historical insurance data, it can be determined whether a customer meets specific claims characteristics, thereby generating corresponding tags. For example, by counting the number of claims a customer has made in the past year, if the number of claims is more than 3, a high claims count tag can be generated.

[0122] Optionally, industry-related tags can be generated, matching the customer's industry information with industry risk data, and assigning the customer the corresponding industry risk level tag according to the industry risk level classification standard.

[0123] The policy data processing method provided in this application queries a user's credit information and generates credit status tags, which helps to understand the user's credit situation. Based on historical claims tags, the probability and level of future claims for a user can be assessed more accurately. By generating industry-related tags, the risk factors of the user's industry can be incorporated into the risk assessment system, providing a more comprehensive and accurate assessment of the user's risk status and offering a more scientific basis for insurance product pricing and risk management.

[0124] As an optional implementation, based on the above embodiments, the policy data processing result is determined based on the basic feature tags corresponding to the target user and the uncertainty type tags, including:

[0125] Determine the corresponding policy data processing strategy based on the insurance information;

[0126] According to the preset priority order in the policy data processing strategy, the basic feature tags and uncertainty type tags are matched in sequence to obtain the matching results;

[0127] The policy data processing result is determined based on the matching results and the preset mapping relationship.

[0128] Among them, the policy data processing strategy refers to a set of standardized risk control rules based on different insurance scenarios, product types, and customer groups, including matching logic, priority settings, and corresponding handling directions for various tag combinations.

[0129] The preset priority order refers to the rule matching order that is pre-set in the policy data processing strategy.

[0130] The matching result refers to the judgment conclusion obtained by comparing the target user's basic feature tags and uncertainty type tags with the rules in the policy data processing strategy, and that the user meets one or more rules.

[0131] Among them, the preset mapping relationship refers to the predefined correspondence between the matching results and the policy data processing results, which clarifies the specific business handling methods corresponding to different matching conclusions.

[0132] Specifically, core scenario identifiers, including the type of insurance product and the coverage period, are extracted from the target user's insurance information. Based on these identifiers, corresponding policy data processing strategies are matched from a pre-defined strategy library. For example, for a typical customer purchasing short-term household property insurance, a standard risk control strategy is matched. The pre-defined priority order in the strategy is read, and then, in descending order, the basic feature tags and uncertainty type tags of the target user are matched against rules one by one.

[0133] Optionally, high-risk composite label rules are prioritized for verification, such as a basic feature label of "high-risk industry" plus an uncertainty type label of "frequent insurance risk." If the label combination meets all the conditions of a high-priority rule, then that rule is directly recorded as the triggering rule. If none of the rules are met, then the conclusion that no matching rule exists is recorded.

[0134] Furthermore, the system retrieves a pre-defined mapping database. If the matching result triggers a single rule, the processing result corresponding to that rule is used as the preliminary conclusion based on the mapping relationship. For example, if a supplementary information rule is triggered, the preliminary conclusion is to request supplementary financial documentation. If the matching result triggers multiple rules, the processing result corresponding to the highest priority rule is used, or a composite processing conclusion is generated based on the combination rules in the mapping relationship. Ultimately, a clear and executable policy data processing result is generated.

[0135] Optionally, version management of policy data processing strategies can be supported, which facilitates quick version switching when business needs change, while retaining historical version records.

[0136] The policy data processing method provided in this application matches tags according to a preset policy data processing strategy and priority order, and determines the processing result based on the matching result and preset mapping relationship. This method can more accurately identify different types of customers, and then adjust the policy's coverage, premium price, or claim conditions in a timely manner based on the tag matching result to effectively deal with risks.

[0137] As an optional implementation, based on the above embodiments, the policy data processing strategy is a multi-dimensional rule combination configuration, including a logical combination of AND / OR / NOT of basic feature tags and uncertainty type tags;

[0138] Policy data processing strategies can be added, modified, and disabled through a visual interface, and are synchronized in real time.

[0139] Among them, the multi-dimensional rule combination configuration refers to the fact that the rules of the policy data processing strategy are not based on a single condition, but on two core dimensions: basic feature labels and uncertainty type labels. The rules are formed by combining logical operators to form a composite rule configuration method, which can cover complex risk scenarios.

[0140] Specifically, business personnel will determine the tag dimensions to be combined based on the risk scenarios corresponding to the current risk control needs, and select target tags from the basic feature tag library and the uncertainty type tag library. Subsequently, according to the judgment logic of the risk scenario, the corresponding logical operators are selected to combine the tags. After the combination is completed, the corresponding handling direction of the rules is clarified, forming a complete multi-dimensional combination rule, which is then entered into the policy data processing strategy library.

[0141] For example, if it is necessary to accurately identify high-risk scenarios, a combination of logic is used, such as high-risk industries, extremely high coverage, and ≥2 insurance policies in the past 30 days. All three tags must be met simultaneously to avoid misjudgment based on a single tag.

[0142] Furthermore, sales personnel log into the visual operation platform, enter the policy data processing strategy configuration module, and click the "Add Rule" button to add a new rule. When business needs change, sales personnel can query the target rule in the visual interface and click the "Modify" button to adjust it. When a rule is no longer applicable, sales personnel can find the target rule in the visual interface, click the "Disable" button, and immediately stop the use of that rule.

[0143] Optionally, a distributed message synchronization mechanism is adopted. After the visual interface completes the addition, modification, or disabling operations, the policy library updates the rule status in real time and sends a synchronization notification to the risk control engine and related business systems. After receiving the notification, the risk control engine immediately loads the updated rule set and replaces the original old rules without restarting the service. When the business system calls the risk control interface, it automatically obtains the latest policy data processing strategy to ensure that every insurance application is verified according to the currently effective rules, achieving seamless connection between strategy adjustment and business execution, and ensuring the real-time performance and accuracy of risk control.

[0144] The policy data processing method provided in this application addresses the complex scenarios and factors involved in insurance business, where different customer groups, insurance product types, and market environments require different data processing approaches. The multi-dimensional rule combination configuration flexibly combines basic feature tags and uncertainty type tags using "AND," "OR," and "NOT" logic based on specific needs. Through this multi-dimensional rule combination configuration, personalized policy data processing strategies can be developed for different customer groups.

[0145] Figure 3 A flowchart illustrating a policy data processing method provided in another embodiment of this application is shown below. Figure 3 As shown, the policy data processing method provided in this embodiment includes the following steps:

[0146] S301. Obtain the insurance information of the target user.

[0147] S302. Based on the insurance information, query relevant attribute information in the preset database. The relevant attribute information includes credit information and historical claims information.

[0148] S303. A preset basic feature label generation algorithm is used to generate corresponding feature labels based on insurance information, credit information and historical claims information.

[0149] S304. Obtain the historical valid policy data and basic feature tags corresponding to the target user.

[0150] S305. Determine the set of overlapping policy times between each historical policy and the current policy.

[0151] S306. Calculate the sum insured of historical policies and current policies within the overlapping period of each policy, and multiply it by the adjustment factor corresponding to the target user to obtain the corresponding cumulative sum insured.

[0152] S307. If the cumulative sum insured exceeds a preset percentage of the historical average sum insured, a rapid increase in sum insured label will be generated.

[0153] S308. If the cumulative insured amount exceeds the preset insured amount threshold corresponding to the target user's type, an "excessively high insured amount" label will be generated.

[0154] S309. If the number of insurance applications for a target user exceeds the preset insurance application threshold within a preset time period, and the cumulative insured amount exceeds the preset insured amount threshold corresponding to the target customer type, a frequent insurance application risk label will be generated.

[0155] S310. Determine the corresponding policy data processing strategy based on the insurance information.

[0156] S311. According to the preset priority order in the policy data processing strategy, the basic feature tags and uncertainty type tags are matched in sequence to obtain the matching results.

[0157] S312. Determine the policy data processing result based on the matching result and the preset mapping relationship.

[0158] It should be noted that the execution order of S307-S309 is not important.

[0159] In this embodiment, the implementation method and technical effect of S301-S312 are similar to those of the corresponding solutions in the above embodiments, and will not be repeated here.

[0160] Figure 4 This is a schematic diagram of the policy data processing device provided in this application, as shown below. Figure 4 As shown, the policy data processing device 40 provided in this embodiment includes: an acquisition module 41, a calculation module 42, a generation module 43, and a determination module 44.

[0161] The module 41 is used to acquire the historical valid policy data and basic feature tags of the target user; the calculation module 42 is used to calculate the cumulative sum insured of the target user during the policy overlap period based on the historical valid policy data and basic feature tags using a preset sum insured calculation model; the generation module 43 is used to generate uncertainty type tags of the target user based on the cumulative sum insured using a preset uncertainty type tag generation strategy; and the determination module 44 is used to determine the policy data processing result based on the basic feature tags and uncertainty type tags of the target user.

[0162] The policy data processing device provided in this embodiment can perform... Figure 2 The implementation principles and technical effects of the methods shown are similar, and will not be repeated here.

[0163] Optionally, the calculation module 42, when calculating the cumulative sum insured of the target user within any policy overlap period using a preset sum insured calculation model based on historical valid policy data and basic feature tags, is specifically used to: determine the set of policy overlap periods for each historical policy and the current policy; calculate the sum insured of the historical policies and the current policy within each policy overlap period, and multiply it by the adjustment factor corresponding to the target user to obtain the corresponding cumulative sum insured.

[0164] Optionally, the generation module 43, when generating uncertainty type tags for the target user based on the cumulative sum insured using a preset uncertainty type tag generation strategy, specifically generates a rapid sum insured growth tag if the cumulative sum insured exceeds a preset percentage of the historical average sum insured; generates an extremely high sum insured tag if the cumulative sum insured exceeds a preset sum insured threshold corresponding to the target user's type; and generates a frequent insurance risk tag if the number of insurance purchases by the target user within a preset time period is higher than a preset insurance purchase threshold, and the cumulative sum insured exceeds a preset sum insured threshold corresponding to the target customer type.

[0165] Optionally, the policy data processing device provided in this embodiment further includes a query module.

[0166] Accordingly, the acquisition module 41 is also used to acquire the insurance information of the target user; the query module is used to query relevant attribute information in the preset database based on the insurance information, including credit information and historical claims information; the generation module 43 is also used to generate corresponding feature tags based on the insurance information, credit information and historical claims information using a preset basic feature tag generation algorithm.

[0167] Optionally, the determining module 44, when determining the policy data processing result based on the basic feature tags and uncertainty type tags corresponding to the target user, is specifically used for: determining the corresponding policy data processing strategy based on the insurance information; matching the basic feature tags and uncertainty type tags sequentially according to the preset priority order in the policy data processing strategy to obtain the matching result; and determining the policy data processing result based on the matching result and the preset mapping relationship.

[0168] Optionally, the policy data processing device provided in this embodiment further includes a synchronization module.

[0169] Accordingly, the policy data processing strategy is configured with multi-dimensional rule combinations, including logical combinations of AND / OR / NOT between basic feature tags and uncertainty type tags; the synchronization module is used to add, modify and disable policy data processing strategies through a visual interface, and to perform real-time synchronization.

[0170] Figure 5 This is a schematic diagram of the policy data processing equipment provided in this application. Figure 5 As shown, the policy data processing device 50 provided in this embodiment includes a processor 51 and a memory 52. ​​The processor 51 and the memory 52 are connected via a bus and communicate with each other.

[0171] In the specific implementation process, the processor 51 executes the computer execution instructions stored in the memory 52, causing the processor 51 to perform the above-described method.

[0172] The specific implementation process of processor 51 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0173] In the above embodiments, it should be understood that the processor 51 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0174] The memory 52 may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0175] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0176] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0177] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0178] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0179] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0180] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0181] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0182] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0183] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0184] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0185] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for processing insurance policy data, characterized in that, The method includes: Obtain historical valid insurance policy data and basic feature tags for the target user; The cumulative sum insured of the target user during any overlapping period of policies is calculated using a preset sum insured calculation model based on the historical valid policy data and basic feature tags. Based on the cumulative insured amount, an uncertainty type label for the target user is generated using a preset uncertainty type label generation strategy; The policy data processing result is determined based on the basic feature tags and uncertainty type tags corresponding to the target user.

2. The method according to claim 1, characterized in that, The step of using a preset coverage calculation model to calculate the cumulative coverage of the target user within any overlapping policy period based on the historical valid policy data and basic feature tags includes: Determine the set of overlapping periods between each historical policy and the current policy; Calculate the sum insured of historical policies and current policies within the overlapping period of each policy, and multiply it by the adjustment factor corresponding to the target user to obtain the corresponding cumulative sum insured.

3. The method according to claim 1, characterized in that, The step of generating uncertainty type tags for the target user based on the cumulative insured amount using a preset uncertainty type tag generation strategy includes: If the cumulative sum insured exceeds a preset percentage of the historical average sum insured, a rapid increase in sum insured label will be generated. If the cumulative insured amount exceeds the preset insured amount threshold corresponding to the type of the target user, an "excessively high insured amount" label is generated. If the number of insurance applications for a target user exceeds a preset insurance application threshold within a preset time period, and the cumulative insured amount exceeds a preset insured amount threshold corresponding to the target customer type, a frequent insurance application risk label will be generated.

4. The method according to claim 1, characterized in that, The basic feature tags include basic attribute tags, credit status tags, historical claims tags, and industry-related tags. Before obtaining the historical valid policy data and basic feature tags corresponding to the target user, the process also includes: Obtain the insurance information of the target users; Based on the insurance information, relevant attribute information is queried in a preset database, including credit information and historical claims information; A preset basic feature label generation algorithm is used to generate corresponding feature labels based on the insurance information, credit information, and historical claims information.

5. The method according to claim 4, characterized in that, The process of determining the policy data processing result based on the basic feature tags and uncertainty type tags corresponding to the target user includes: Based on the insurance information, determine the corresponding policy data processing strategy; According to the preset priority order in the policy data processing strategy, the basic feature tags and uncertainty type tags are matched sequentially to obtain the matching results; The policy data processing result is determined based on the matching result and the preset mapping relationship.

6. The method according to claim 5, characterized in that, The policy data processing strategy is a multi-dimensional rule combination configuration, including logical combinations of AND / OR / NOT between basic feature tags and uncertainty type tags; The policy data processing strategy can be added, modified, and disabled through a visual interface, and is synchronized in real time.

7. A policy data processing device, characterized in that, include: The acquisition module is used to acquire the historical valid insurance policy data and basic feature tags of the target user; The calculation module is used to calculate the cumulative insured amount of the target user during the policy overlap period based on the historical valid policy data and basic feature tags using a preset insured amount calculation model; The generation module is used to generate uncertainty type tags for the target user based on the cumulative insured amount and using a preset uncertainty type tag generation strategy; The determination module is used to determine the policy data processing result based on the basic feature tags and uncertainty type tags corresponding to the target user.

8. A policy data processing device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images