Group insurance policy generation method and device, computer equipment and storage medium
By parsing and filling in insurance form templates, and combining user information and claims records to predict premiums, the problem of low efficiency in generating group insurance policies has been solved, achieving efficient and accurate policy generation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- PING AN HEALTH INSURANCE CO LTD
- Filing Date
- 2026-04-28
- Publication Date
- 2026-07-24
AI Technical Summary
The group insurance policy generation process is slow because sales personnel cannot process it in a timely manner while conducting business outside the office.
By receiving the original personnel list file sent by the mobile application, parsing and populating the insurance form template, obtaining user information and claims records, predicting premiums, generating and sending the target insurance form.
This improves the efficiency and accuracy of group insurance policy generation, ensuring complete and accurate information and timely feedback to the target group.
Smart Images
Figure CN122453532A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of artificial intelligence technology, and is applicable to the financial insurance field, particularly to a method, apparatus, computer equipment, and storage medium for generating group insurance policies. Background Technology
[0002] Group insurance policy generation refers to the technical means by which insurance companies, based on the unified insurance needs of a group of clients, generate insurance policies in batches for members of the group through a systematic process. The group insurance policy generation method generates a master policy containing the coverage information of all members after risk assessment, based on members' basic information (such as name, age, occupation, etc.) and a predetermined insurance plan.
[0003] The generation of group insurance policies primarily relies on sales personnel. From business development to policy creation, sales personnel must be involved throughout the entire process. However, in real-world business scenarios, sales personnel often need to travel to conduct business. For group insurance-related policy generation tasks, such as verifying and uploading personnel lists, they must return to the company before proceeding. This slows down the policy generation process and, to some extent, affects the efficiency of group insurance policy generation. Summary of the Invention
[0004] This application provides a method, apparatus, computer equipment, and storage medium for generating group insurance policies, in order to solve the technical problem that the slow progress of the policy generation process and the impact on the efficiency of group insurance policy generation are caused by the inability of business personnel to handle group insurance policy generation matters in a timely manner when they are conducting business outside.
[0005] Firstly, a method for generating group insurance policies is provided, applicable to an enterprise's internal backend, including: Receive an original personnel list file of a target group sent by a mobile application; wherein the target group includes multiple target objects; The original personnel list file is parsed to obtain the original list fields; Based on the original list fields and the original personnel list file, the fields are filled in the preset insurance form template to obtain the original insurance form for the target group; Based on the original insurance form, obtain the original user information and historical claims records of each target object; based on the original user information and the historical claims records, perform premium prediction to obtain the target premium data for each target object; Based on the target premium data and the original insurance form for each target object, a target insurance form for the target group is generated, and the target insurance form is sent to the mobile application so that the target insurance form can be sent to the target group through the mobile application.
[0006] Secondly, a group insurance policy generation device is provided for use in an enterprise's internal backend, including: The manifest file acquisition module is used to receive the original personnel manifest file of the target group sent by the mobile application; wherein, the target group includes multiple target objects; The file parsing module is used to parse the original personnel list file to obtain the original list fields; The field filling module is used to fill in the fields in the preset insurance form template based on the original list fields and the original personnel list file to obtain the original insurance form for the target group; The user data acquisition module is used to acquire the original user information and historical claims records of each target object based on the original insurance form. The premium calculation module is used to predict premiums based on the original user information and the historical claims records, and to obtain target premium data for each target object. The target policy generation module is used to generate a target insurance form for the target group based on the target premium data of each target object and the original insurance form, and send the target insurance form to the mobile application so that the target insurance form can be sent to the target group through the mobile application.
[0007] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described group insurance policy generation method.
[0008] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the aforementioned group insurance policy generation method.
[0009] In the aforementioned scheme implementing the group insurance policy generation method, device, computer equipment, and storage medium, the policy generation process for group insurance products under insurance business firstly involves receiving an original personnel list file of the target group sent by a mobile application; the target group includes multiple target objects, clearly defining the basic information of the objects. Next, the original personnel list file is parsed to obtain the original list fields, accurately extracting key data to ensure accurate information identification. After obtaining the original list fields, fields are filled into a preset insurance form template based on the original list fields and the original personnel list file, quickly generating a standardized original insurance form for the target group, improving form creation efficiency and standardization. Furthermore, based on the original insurance form, the original user information and historical claims records of each target object are obtained; premium prediction is performed based on the original user information and historical claims records, and the target premium data for each target object is calculated by combining the actual situation of each target object. Finally, based on the target premium data and original insurance forms for each target individual, a target insurance form for the target group is generated and sent to a mobile application. This ensures the completeness and accuracy of the form information and provides timely feedback to the target group, facilitating their understanding of the insurance details. The overall process improves the efficiency and accuracy of group insurance policy generation, resolving the technical issue of slow policy generation due to sales personnel being unable to handle group insurance policy generation in a timely manner while conducting business outside the office. Attached Figure Description
[0010] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0011] Figure 1 This is a schematic diagram of an application environment for a group insurance policy generation method in one embodiment of this application; Figure 2 This is a flowchart illustrating a group insurance policy generation method in one embodiment of this application; Figure 3 yes Figure 2 A schematic diagram of a specific implementation method for step S20; Figure 4 yes Figure 2 A schematic diagram of a specific implementation method for step S30; Figure 5 yes Figure 2A schematic diagram of a specific implementation method for step S50; Figure 6 yes Figure 5 A flowchart illustrating a specific implementation of step S53; Figure 7 This is a schematic diagram of a group insurance policy generation device in one embodiment of this application; Figure 8 This is a schematic diagram of the structure of a computer device according to one embodiment of this application. Detailed Implementation
[0012] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0013] First, let's analyze some of the terms used in this application: Artificial intelligence (AI) is a new branch of computer science that studies, develops, and applies theories, methods, technologies, and systems to simulate, extend, and expand human intelligence. It aims to understand the essence of intelligence and produce intelligent machines that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thought. Furthermore, AI utilizes digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to achieve optimal results.
[0014] Natural Language Processing (NLP): NLP uses computers to process, understand, and utilize human language (such as Chinese and English). NLP is a branch of artificial intelligence and an interdisciplinary field of computer science and linguistics, often referred to as computational linguistics. NLP includes syntactic analysis, semantic analysis, and discourse understanding. It is commonly used in machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, intent recognition, information extraction and filtering, text classification and clustering, sentiment analysis, and opinion mining. It involves data mining, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computation.
[0015] Information extraction is a text processing technique that extracts factual information such as entities, relationships, and events from natural language text and outputs it as structured data. Information extraction is a technique for extracting specific information from text data. Text data is composed of specific units, such as sentences, paragraphs, and chapters. Text information is composed of smaller, specific units, such as characters, words, phrases, sentences, paragraphs, or combinations of these units. Extracting noun phrases, names of people, and place names from text data is an example of text information extraction. Of course, text information extraction techniques can extract information of various types.
[0016] Group insurance is a form of commercial insurance where a group is the policyholder and its members are the insured, providing risk protection for all members under a single master policy. Group insurance is typically purchased by organizations such as businesses, government agencies, and schools for their employees or members, covering multiple types of insurance including life, health, and accident insurance. Compared to individual insurance, group insurance is characterized by lower costs, broader coverage, and simpler procedures, and can leverage the group's negotiating power to obtain more favorable rates. Furthermore, group insurance can be customized to the group's needs, effectively transferring the risks faced by the group, enhancing members' sense of belonging and security, and is an important way for groups to provide benefits and improve their protection system.
[0017] Group insurance policy generation refers to the technical means by which insurance companies, based on the unified insurance needs of a group of clients, generate insurance policies in batches for members of the group through a systematic process. The group insurance policy generation method generates a master policy containing the coverage information of all members after risk assessment, based on members' basic information (such as name, age, occupation, etc.) and a predetermined insurance plan.
[0018] The generation of group insurance policies primarily relies on sales personnel. From business development to policy creation, sales personnel must be involved throughout the entire process. However, in real-world business scenarios, sales personnel often need to travel to conduct business. For group insurance-related policy generation tasks, such as verifying and uploading personnel lists, they must return to the company before proceeding. This slows down the policy generation process and, to some extent, affects the efficiency of group insurance policy generation.
[0019] Based on this, this application provides a method, apparatus, computer equipment, and storage medium for generating group insurance policies, in order to solve the technical problem that the slow progress of the policy generation process and the impact on the efficiency of group insurance policy generation are caused by the inability of business personnel to handle group insurance policy generation matters in a timely manner when they are conducting business outside.
[0020] The group insurance policy generation method, apparatus, electronic device, and storage medium provided in this application are specifically described through the following embodiments. First, the group insurance policy generation method in this application embodiment is described.
[0021] The group insurance policy generation method provided in this application embodiment can be applied to, for example, Figure 1 In this application environment, the client communicates with the server via a network. The server has an internal backend that receives a raw personnel list file of a target group sent by a mobile application on the client. The target group includes multiple target objects. The raw personnel list file is parsed to obtain raw list fields. Based on the raw list fields and the raw personnel list file, fields are filled into a preset insurance form template to obtain the raw insurance form for the target group. Based on the raw insurance form, the original user information and historical claims records of each target object are obtained. Based on the original user information and historical claims records, premium prediction is performed to obtain the target premium data for each target object. Based on the target premium data for each target object and the raw insurance form, a target insurance form for the target group is generated and fed back to the client's mobile application, allowing the mobile application to send the target insurance form to the target group.
[0022] In this application, regarding the policy generation process for group insurance products under insurance business, firstly, the system receives an original personnel list file of the target group sent by a mobile application; the target group includes multiple target objects, clearly defining the basic information of the objects. Next, the original personnel list file is parsed to obtain the original list fields, accurately extracting key data to ensure accurate information identification. After obtaining the original list fields, the system fills in the fields in a preset insurance form template based on the original list fields and the original personnel list file, quickly generating a standardized original insurance form for the target group, improving form creation efficiency and standardization. Furthermore, based on the original insurance form, the system obtains the original user information and historical claims records of each target object; based on the original user information and historical claims records, premium prediction is performed, and the target premium data for each target object is calculated by combining the actual situation of each target object. Finally, based on the target premium data and original insurance forms for each target individual, a target insurance form for the target group is generated and sent to a mobile application. This ensures the completeness and accuracy of the form information and provides timely feedback to the target group, facilitating their understanding of the insurance details. The overall process improves the efficiency and accuracy of group insurance policy generation, resolving the technical issue of slow policy generation due to sales personnel being unable to handle group insurance policy generation in a timely manner while conducting business outside the office.
[0023] The client can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and other devices used by the business entity, and this client has a mobile application installed. The server is a device with an internal enterprise backend, and the backend processing system of this server can be implemented using a dedicated server or a server cluster consisting of multiple servers. The following detailed description of specific embodiments further illustrates this application.
[0024] Please see Figure 2 As shown, Figure 2 A flowchart illustrating the group insurance policy generation method provided in this application embodiment includes the following steps: S10. Receive the original personnel list file of the target group sent by the mobile application; wherein the target group includes multiple target objects; It should be noted that mobile applications are communication software used by business entities to communicate with customers when conducting business or following up on insurance policies. Compared to the internal backend of an enterprise, mobile applications are considered external applications. Furthermore, the security of mobile applications is significantly weaker than that of the internal backend. Therefore, original personnel list files cannot be processed in mobile applications; they must be sent to the internal backend for processing.
[0025] In the context of insurance, the target group refers to the collective that needs to purchase group insurance, such as businesses, schools, and community organizations. For example, if a company, as a whole, purchases group insurance for its employees, that company is the target group.
[0026] The target group refers to the individual members within the target group. In the context of corporate group insurance, the target group consists of the company's employees. For example, in a company with 100 employees, these 100 employees are the target group.
[0027] The original personnel list file is a document that records relevant information about all target individuals within the target group. It typically includes basic data such as name, age, gender, ID number, and job title. For example, an Excel spreadsheet provided by the company lists the above information for each employee in detail.
[0028] It should be noted that the original personnel list file of the target group is sent by the person in charge of the target group (such as the person in charge of the enterprise) to the business object (the agent of the insurance company), and then the business object sends it to the enterprise's internal backend on the server side through the client's mobile application. Therefore, the enterprise's internal backend on the server side is one of the ends that receives the original personnel list file of the target group.
[0029] Next, the enterprise's internal backend processes the original personnel list file of the target group to obtain the target insurance form, and sends it to the client's mobile application through the enterprise's internal backend, so that the client can send the target insurance form to the target group through the mobile application.
[0030] S20. Parse the original personnel list file to obtain the original list fields; It's important to understand that "parsing" here refers to splitting, identifying, and extracting the data from the original personnel list file, transforming it into a field format that matches the fields used by the insurance company. For example, identifying each column of data in an Excel spreadsheet as a different field, and extracting the data from the "Name" column in the original personnel list file into the "Name" field.
[0031] Among them, such as Figure 3 As shown, step S20, which involves parsing the original personnel list file to obtain the original list fields, includes the following steps: S21. Recognize the format of the original personnel list file to obtain the list file format; S22. Select a preset field parsing model based on the manifest file format; S23. Parse the original personnel list file using the field parsing model to obtain the original list fields.
[0032] For steps S21 to S23, the original personnel list file is formatted to identify its specific format type, thus obtaining the list file format. Next, a corresponding preset field parsing model is selected based on the identified list file format to ensure targeted parsing. For example, an Excel file uses a field parsing model specifically for Excel files, and a TXT file uses a field parsing model specifically for TXT files. Finally, the original personnel list file is parsed using the field parsing model to obtain the original list fields. This method accurately and efficiently obtains the original list fields, avoiding parsing errors caused by format mismatches and improving parsing efficiency and accuracy.
[0033] Specifically, the characteristics of the original personnel list file are analyzed to determine its text format. For example, this involves checking for specific identifiers at the beginning of the file and the type of delimiters used between data. The list file format refers to the specific file format used in the original personnel list file; common formats include CSV (comma-separated values), Excel (.xlsx or .xls), and TXT (plain text).
[0034] It's understandable that different formats differ in how they store, display, and read data. Different file formats require different parsing methods. Only by correctly identifying the format can the appropriate field parsing model be selected for subsequent operations, avoiding parsing failures or data errors due to incorrect formatting. For example, if a CSV file is mistakenly identified as an Excel file and processed using an Excel parsing tool, it may result in data misalignment or inability to be read.
[0035] It should be noted that a field parsing model is a pre-designed set of rules and algorithms used to extract the required field information from files of a specific format. Different file formats correspond to different field parsing models, which are optimized for the characteristics of their respective formats and can parse data efficiently and accurately.
[0036] After defining the format of the original personnel list file, a matching model is selected from multiple preset field parsing models based on this format. Choosing an appropriate field parsing model can significantly improve the efficiency and accuracy of data parsing and reduce the occurrence of parsing errors.
[0037] For example, if the manifest file format is CSV, select a field parsing model specifically designed for parsing CSV files. If the manifest file format is Excel, select a field parsing model specifically designed for parsing Excel files. If the manifest file format is TXT, select a field parsing model specifically designed for parsing TXT files.
[0038] After determining the field parsing model, the selected model is used to analyze and process the data in the original personnel list file line by line and column by column, according to the rules and algorithms defined in the model, to extract the required field information. For example, for a CSV file, the parsing model will split the data in each row into different fields based on comma delimiters. Through field parsing, structured and standardized data can be extracted from the original file, facilitating subsequent policy generation processing.
[0039] It should be noted that the original list fields are specific information items extracted from the original personnel list file, such as the target object's name, age, gender, and ID number mentioned above. These fields are the core data for insurance business processing.
[0040] In some embodiments, after step S23, that is, after parsing the original personnel list file to obtain the original list fields, the following steps are included: The preset form fields of the preset insurance form template are matched with the fields of the original list to obtain field matching data; the field matching data is used to indicate whether there are any missing fields in the original list. If the field matching data indicates that there are missing fields in the original list, field missing information is generated based on the missing fields and sent to the mobile application so that the field missing information can be sent to the target group through the mobile application.
[0041] Specifically, the preset form fields are first matched with the parsed original list fields to determine if the original list fields are complete. By comparing the results, missing fields can be quickly located, and matching data is obtained, which forms the basis for subsequent judgments. If the matching data indicates that there are missing fields in the original list, missing field information is generated based on these missing fields. This clearly reflects the specific missing content, facilitating timely supplementation and improvement, preventing missing fields from affecting subsequent insurance business processing, and ensuring the accurate and efficient progress of business operations.
[0042] It should be noted that the preset insurance form templates are standard insurance form formats pre-designed by insurance companies for specific insurance products. They include various information fields that need to be filled in, such as policyholder information, insured information, insurance items, and insured amount. For example, a group accident insurance form template includes fields for company name, employee names, and insured amount.
[0043] The insurance form template includes pre-defined form fields. These pre-defined form fields are a set of information fields that must be filled in within the template. For example, in a group accident insurance application form, pre-defined form fields might include the insured's name, ID number, age, occupation, contact information, type of accident insurance, and coverage amount. These fields serve as the basis for the insurance company's policy generation, subsequent underwriting / claims processing, and other business operations, ensuring the integrity and standardization of business data.
[0044] Specifically, the preset form fields and the original list fields are compared one by one. For example, a traversal approach can be used to check whether each field in the original list exists in the preset form fields. If it exists, the field matching data indicates that the original list field does not have a missing field; if it does not exist, the field matching data indicates that the original list field has a missing field, and lists which fields in the preset form fields do not have corresponding content in the original list fields.
[0045] For example, a company purchases group health insurance for its employees and submits an Excel file containing employee information as the initial personnel list to the insurance company. The insurance company's system has pre-defined form fields including employee name, ID number, gender, age, medical history, type of health insurance, and coverage amount. The system matches these pre-defined form fields with the fields in the initial list parsed from the Excel file. It finds that the initial list lacks the "medical history" field, and the field matching data will then record the missing "medical history" field.
[0046] When the field matching data indicates that there are missing fields in the original list, field missing information is generated based on the missing fields. Field missing information is a detailed description and prompt information of the missing fields in the original list. It usually clearly indicates the name of the missing field and may also include some related suggestions or explanations so that the enterprise or relevant personnel can understand and supplement the missing fields in a timely manner. For example, field missing information could be "The 'Past Medical History' field is missing from the original list. Please supplement this field information."
[0047] After receiving the missing field information, the server-side internal backend automatically sends the missing field information to the client's mobile application. This allows the client to send the missing field information to the target group via the mobile application, reminding the target group to supplement the corresponding information and prompting them to fill in the missing fields as soon as possible to ensure the normal operation of the insurance business.
[0048] S30. Based on the original list fields and the original personnel list file, fill in the fields in the preset insurance form template to obtain the original insurance form for the target group; It's important to understand that "field filling" here refers to taking the parsed raw list fields, one by one, and filling them into the corresponding fields according to the requirements of the preset insurance form template to complete the initial filling of the entire form. For example, the company name is filled into the policyholder information field, and the employee's name, age, etc., are filled into the insured information field.
[0049] Among them, such as Figure 4 As shown, step S30, which involves filling in the fields in the preset insurance form template based on the original list fields and the original personnel list file to obtain the original insurance form for the target group, includes the following steps: S31. Extract candidate field information from the original personnel list file based on the original list fields; S32. Standardize the candidate field information to obtain standardized field information; S33. Map the preset form fields and the original list fields to obtain the field mapping relationship; S34. Based on the field mapping relationship, fill the standardized field information into the insurance form template to obtain the original insurance form for the target group.
[0050] For steps S31 to S34, firstly, candidate field information is extracted from the original personnel list file based on the original list fields. This allows for precise location of the required data and avoids interference from irrelevant information. Next, the candidate field information is standardized to obtain standardized field information, unifying the data format, eliminating errors caused by format differences, and improving data quality. Further, a mapping is established between preset form fields and original list fields to obtain field mapping relationships, clarifying the data filling direction. Finally, based on the field mapping relationships, the standardized field information is filled into the insurance form template. This allows for the rapid and accurate generation of the original insurance form for the target group, improving form generation efficiency and accuracy, and reducing human error.
[0051] It is important to understand that field extraction here refers to accurately locating and retrieving the data under the corresponding fields in the original personnel list file, based on the guidance of each row / column.
[0052] The original list fields are specific field names predefined in the original personnel list file. For example, in a group insurance scenario, they may include "name", "age", "gender", "ID number", "occupation category", etc. These fields are key information required for generating insurance forms later.
[0053] Understandably, the field names in the original personnel list file may differ from those required by the insurance company. For example, the ID description in the original personnel list file might be id_no, while the insurance company's standard format is identity_no. Therefore, standardizing the candidate field information based on these predefined field name definitions can eliminate problems caused by inconsistent data formats, improve data accuracy and consistency, and ensure the correctness of the generated insurance forms.
[0054] Specifically, standardization includes, but is not limited to, operations such as format conversion and encoding standardization. Standardized field information is field information that has undergone standardization, possessing a unified format and expression method, facilitating subsequent data processing and form filling.
[0055] Furthermore, establishing a mapping here refers to analyzing the meaning and purpose of the preset form fields and the original list fields, determining their correspondence, and recording it. The field mapping relationship is used to characterize the correspondence between the preset form fields and the original list fields, indicating which field's data from the original list should be filled into which field of the insurance form template. For example, determining that "Insured's Name" in the insurance form template corresponds to the "Name" field in the original list. By clarifying the direction and rules of data filling through the field mapping relationship, subsequent field filling operations can be performed accurately and orderly, avoiding data filling errors.
[0056] After obtaining the field mapping relationship, the standardized field information is filled into the corresponding field positions in the insurance form template according to the format and requirements of the insurance form template, so as to obtain the original insurance form of the target group. This quickly and accurately generates the original insurance form of the target group, improving the efficiency of insurance business processing.
[0057] In some embodiments, if the insurance form template requires the gender and birthdate information of the target object, but the original list fields do not contain gender and birthdate fields, but instead contain an ID card field, the ID card field can be parsed to obtain the gender and birthdate information, and this parsed information can be filled into the insurance form template. Similarly, if the field matching data indicates that the original list fields lack gender and birthdate fields, but the field contains an ID card field, the gender and birthdate fields can be parsed from the ID card field, thus preventing the generation of field missing information for the missing gender and birthdate fields in the original list fields.
[0058] It should be noted that the original insurance form is an insurance form with complete insurance information after the fields have been filled in, but subsequent processing such as premium calculation has not yet been performed.
[0059] S40. Obtain the original user information and historical claims records for each target individual based on the original insurance form. It's important to understand that the original user information here refers to the basic personal information provided by the target individual when applying for insurance, such as age, gender, and occupation. By obtaining this original user information, the insurance company can grasp the basic characteristics and risk profile of the target individual, providing foundational data for accurate premium calculation. For example, in group health insurance, employees of different age groups have different disease risks, making age a crucial piece of original user information; different occupations also face different health risks, such as the different occupational risks of office workers and construction workers, and occupational information affects premium calculation.
[0060] The historical claims record here refers to the relevant records of claims filed by the target individual during previous insurance periods. The historical claims record reflects the target individual's past risk occurrences. If an employee has a high number of claims and large claim amounts, it indicates a relatively high risk, and the premium can be appropriately increased when calculating the insurance premium to reasonably distribute the risk. For example, if an employee filed a medical expense claim due to accidental injury during a group accident insurance policy purchased a year ago, the amount, time, and cause of injury of this claim constitute that employee's historical claims record.
[0061] S50. Based on the original user information and historical claims records, predict the premium to obtain the target premium data for each target object.
[0062] It's important to understand that premium prediction here refers to calculating the insurance premium payable by each insured person based on factors such as the insurance product's rate rules, the insured's (target's) original user information and historical claims records, and the insured amount. For example, group accident insurance calculates premiums according to the corresponding rate based on the employee's occupation category and the selected coverage amount.
[0063] Specifically, the insurance company's underwriting system or specialized premium calculation program obtains the corresponding original user information and historical claims records from the insured information recorded in the original insurance form, as well as the insurance product rules, and uses the corresponding algorithms and rate tables to calculate the premium for each target individual. For example, for a 30-year-old office worker who chooses an accidental death benefit of 500,000 yuan, the premium calculated according to the group accident insurance rate rules would be 200 yuan.
[0064] Among them, such as Figure 5 As shown, step S50, which involves predicting premiums based on original user information and historical claims records to obtain target premium data for each target object, includes the following steps: S51. For each target object, perform feature processing on the original user information to obtain user feature data; S52. Extract features from historical claims records to obtain claims record features; It's important to understand that feature processing in step S51 refers to using data cleaning, transformation, and encoding techniques to process raw user information and obtain user feature data. This user feature data is representative and valuable for analysis, obtained after processing the raw user information. For example, age is converted into age ranges (20-30 years old), and occupations are categorized according to risk level (programmers belong to a low-risk occupation category). For health status information, textual descriptions are converted into numerical ratings. For gender information, males are coded as 1, and females as 0. By extracting user feature data, key features can be extracted, retaining features relevant to insurance risk while ignoring irrelevant information.
[0065] Step S52, feature extraction, refers to using data mining and analysis techniques to identify valuable features from historical claims records, resulting in claims record features. These features are key information extracted from historical claims records that reflects the target entity's claims risk. Examples include claims frequency (number of claims per year) and average claim amount. Extracting claims record features provides a deeper understanding of the target entity's past claims history, offering a basis for assessing future claims risk. For instance, employees with high claims frequency are more likely to make claims again in the future.
[0066] S53. Based on user characteristic data and claims record characteristics, predict premiums to obtain target premium data for each target object.
[0067] It's important to understand that premium prediction here refers to a preliminary calculation of the premium payable by the target group based on certain premium calculation rules and models, combined with user characteristic data and claims history characteristics. In group insurance, different insurance products have different premium calculation rules. For example, group accident insurance may determine the basic premium based on factors such as occupational risk level and age, and then adjust it based on historical claims data.
[0068] Among them, such as Figure 6 As shown, step S53, which involves predicting premiums based on user characteristic data and claims record characteristics to obtain target premium data for each target object, includes the following steps: S531. Based on user characteristic data and claims record characteristics, feature combinations are performed to obtain claims risk characteristics; S532. Perform risk calculations on the characteristics of claims risk to obtain underwriting risk factors; S533, Obtain the benchmark premium data for the target group's target insured products; S534. Based on the underwriting risk factors and benchmark premium data, perform aggregate calculations to obtain the target premium data for the target object.
[0069] For steps S531 to S534, firstly, feature combinations are performed based on user characteristic data and claims record characteristics to obtain claims risk characteristics, comprehensively reflecting the risk situation. Further, risk calculations are performed on the claims risk characteristics to obtain underwriting risk factors, quantifying the magnitude of the insured risk. Finally, benchmark premium data for the target group's target insured products is obtained, and aggregated calculations are performed based on the underwriting risk factors and benchmark premium data to obtain target premium data for the target group. This makes premium pricing more aligned with the actual risk of the target group, ensuring reasonable profits for the insurance company while avoiding excessive charges for low-risk customers, achieving fair and reasonable pricing, and enhancing market competitiveness and customer satisfaction.
[0070] After obtaining user characteristic data and claims record characteristics, these data are integrated according to certain rules or models. For example, user characteristic data and claims record characteristics can be concatenated into a new feature vector, thereby comprehensively considering multiple factors and more accurately assessing the claims risk of the target individual. For instance, older employees with high occupational risk and high claims frequency show higher claims risk characteristics.
[0071] For example: Suppose the user characteristics of a target group are: 20-25 years old, low-risk occupation, and claims record characteristics of 2 times / year and 1750 yuan. Then the claims risk characteristics obtained after combination can be expressed as (20-25 years old, low risk, 2 times / year, 1750 yuan).
[0072] Furthermore, after obtaining the claims risk characteristics, specific risk assessment models or algorithms are used to process and calculate these characteristics, transforming complex claims risk features into intuitive numerical values. This facilitates risk assessment and decision-making for insurance companies and provides an important basis for premium pricing, ensuring that premiums match risk. Targets with higher risk have higher underwriting risk factors, resulting in correspondingly higher premiums. For example, a logistic regression model can be used, with claims risk characteristics as input variables, to calculate the underwriting risk factor.
[0073] It should be noted that the target insured product is the insurance product that the target group intends to purchase. The base premium for the target insured product is a basic premium amount pre-set by the insurance company based on factors such as the overall market situation and the type of insurance product. For example, the base premium for group accident insurance is 500 yuan per person per year.
[0074] After determining the benchmark premium data for the target insured product, for each target individual, the underwriting risk factor of that individual is aggregated with the benchmark premium data of the target insured product to obtain the target premium data. For example, target premium = benchmark premium data × underwriting risk factor. Assuming the benchmark premium data for the target insured product is 500 yuan / year, and the underwriting risk factor of a certain target individual is 0.6, the target premium data for that employee is calculated to be 500 × 0.6 = 300 yuan.
[0075] It should be noted that, in addition to multiplication, aggregate calculation can also be based on the actual operating conditions of insurance companies, and no restrictions are imposed here.
[0076] Understandably, by calculating the target premium data for each individual, personalized premium pricing can be achieved, making the premium more reasonably reflect the risk profile of the target individual. Higher-risk individuals pay higher premiums, while lower-risk individuals pay lower premiums.
[0077] In some embodiments, if the underwriting risk factor of a target individual exceeds a preset threshold, the insurance application for that target individual may be rejected. The underwriting risk factor is determined based on the actual underwriting situation of the insurance company and is not limited here.
[0078] S60. Generate a target insurance form for the target group based on the target premium data and original insurance form for each target object, and send the target insurance form to the mobile application so that the target insurance form can be sent to the target group through the mobile application.
[0079] Specifically, after clarifying the target premium data for each target object, the target premium data for each target object is added to the corresponding position in the original insurance form to generate the final target insurance form. The target insurance form is a complete insurance form formed by adding the target premium data for each target object to the original insurance form, and includes all necessary information such as the policyholder, the insured, the insurance items, the insured amount, and the premium.
[0080] Furthermore, after obtaining the target insurance form, the server-side internal backend sends the form to the client's mobile application. This allows the client to forward the form to the target group via the mobile application for confirmation. The target group can then confirm the coverage details, premium amount, and other information based on the form, deciding whether to purchase the insurance or make necessary adjustments. This process also fulfills the obligation to inform the insurance company and protects the rights of both parties.
[0081] It should be noted that since the target group has not confirmed and paid, the current status of the target insurance form is uninsured, the insurance combination has not taken effect, and the target group's target individuals cannot enjoy insurance coverage.
[0082] In some embodiments, after step S60, that is, after generating a target insurance form for a target group based on the target premium data and the original insurance form for each target object, and sending the target insurance form to the target group, the group insurance policy generation method further includes the following steps: Receive confirmation and payment instructions for the target insurance form; wherein, the confirmation and payment instructions are triggered by the target group; In response to confirmation and payment instructions, the status of the target insurance form is adjusted to underwritten status.
[0083] Upon receiving a confirmation and payment instruction triggered by the target group, this instruction is issued by the target group on the online insurance application system after verifying the accuracy of the insurance application form. It indicates that the target group acknowledges the contents of the form and agrees to pay the premium. The confirmation and payment instruction is a clear operational signal, which may be triggered by clicking a button on the online insurance application system, signing a written confirmation, or making payment.
[0084] Upon receiving confirmation and payment instructions, the insurance company's backend processing system automatically marks the target insurance form's status in the system as "underwritten," signifying that the insurance contract has officially taken effect. Simultaneously, it may update relevant database information, recording important details such as the insurance effective date and policy number. For example, upon receiving a company's payment instruction, the insurance company's system immediately changes the status of the company's group insurance form to "underwritten" and generates a unique policy number. Understandably, an underwritten status indicates that the insurance contract has officially taken effect, the insurance company begins to assume insurance liability, the target group becomes the insured, and can enjoy insurance coverage if the terms of the insurance policy are met.
[0085] As can be seen, in the above solution, regarding the policy generation process for group insurance products under the insurance business, firstly, the system receives the original personnel list file of the target group sent by the mobile application; the target group includes multiple target objects, clearly defining the basic information of the objects. Next, the original personnel list file is parsed to obtain the original list fields, accurately extracting key data to ensure accurate information identification. After obtaining the original list fields, the system fills in the fields in a preset insurance form template based on the original list fields and the original personnel list file, quickly generating a standardized original insurance form for the target group, improving form creation efficiency and standardization. Furthermore, based on the original insurance form, the system obtains the original user information and historical claims records of each target object; based on the original user information and historical claims records, premium prediction is performed, and the target premium data for each target object is calculated by combining the actual situation of each target object. Finally, based on the target premium data and original insurance forms for each target individual, a target insurance form for the target group is generated and sent to a mobile application. This ensures the completeness and accuracy of the form information and provides timely feedback to the target group, facilitating their understanding of the insurance details. The overall process improves the efficiency and accuracy of group insurance policy generation, resolving the technical issue of slow policy generation due to sales personnel being unable to handle group insurance policy generation in a timely manner while conducting business outside the office.
[0086] It is understood that the group insurance policy generation method provided in this application embodiment can improve the automation of the policy generation process, reduce reliance on manual intervention, realize full-link automated closed loop, and improve the real-time performance of information transmission. The server can notify the progress in real time without relying on manual queries, and can handle customer requests even when the business is on the way to conduct business.
[0087] In addition, the isolation between the external network and the internal network is broken down through the mobile application on the client side and the internal backend on the server side. The internal backend also performs a complete security check on the files forwarded by the mobile application to prevent illegal or malicious files from entering the internal network.
[0088] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0089] In one embodiment, a group insurance policy generation device is provided, applied to an enterprise's internal backend. This group insurance policy generation device corresponds one-to-one with the group insurance policy generation method described in the above embodiments. For example... Figure 7 As shown, the group insurance policy generation device includes a list file acquisition module 101, a file parsing module 102, a field filling module 103, a user data acquisition module 104, a premium calculation module 105, and a target policy generation module 106. Detailed descriptions of each functional module are as follows: The manifest file acquisition module 101 is used to receive the original personnel manifest file of the target group sent by the mobile application; wherein the target group includes multiple target objects; The file parsing module 102 is used to parse the original personnel list file to obtain the original list fields; The field filling module 103 is used to fill in the fields in the preset insurance form template based on the original list fields and the original personnel list file to obtain the original insurance form of the target group. User data acquisition module 104 is used to acquire the original user information and historical claims records of each target object based on the original insurance form; The premium calculation module 105 is used to predict premiums based on original user information and historical claims records, and to obtain target premium data for each target object. The target policy generation module 106 is used to generate a target insurance form for the target group based on the target premium data and the original insurance form for each target object, and send the target insurance form to the mobile application so that the target insurance form can be sent to the target group through the mobile application.
[0090] In one embodiment, the file parsing module 102 is specifically used for: The original personnel list file is formatted to obtain the list file format. Select a preset field parsing model based on the list file format; The original personnel list file is parsed using a field parsing model to obtain the original list fields.
[0091] In one embodiment, the file parsing module 102 is specifically used for: The preset form fields and the original list fields are matched to obtain field matching data; the field matching data is used to indicate whether there are any missing fields in the original list. If the field matching data indicates that there are missing fields in the original list, field missing information is generated based on the missing fields and sent to the mobile application so that the field missing information can be sent to the target group through the mobile application.
[0092] In one embodiment, the insurance form template includes preset form fields, and the field filling module 103 is specifically used for: Based on the original list fields, extract fields from the original personnel list file to obtain candidate field information; The candidate field information is standardized to obtain standardized field information; The field mapping relationship is obtained by mapping the preset form fields and the original list fields; Based on the field mapping relationship, standardized field information is filled into the insurance form template to obtain the original insurance form for the target group.
[0093] In one embodiment, the premium calculation module 105 is specifically used for: For each target object, the original user information is processed to obtain user feature data; Feature extraction is performed on historical claims records to obtain claims record features; based on user feature data and claims record features, premium prediction is performed to obtain target premium data for each target object.
[0094] In one embodiment, the premium calculation module 105 is specifically used for: Based on the combination of user characteristic data and claims record characteristics, claims risk characteristics are obtained; Risk calculations are performed on the characteristics of claims risk to obtain underwriting risk factors; Obtain benchmark premium data for the target group's target insured products; The target premium data for the target object is obtained by aggregating and calculating based on underwriting risk factors and benchmark premium data.
[0095] In one embodiment, the group insurance policy generation device further includes: The payment information confirmation module 107 is used to receive confirmation and payment instructions from the target insurance form; wherein, the confirmation and payment instructions are triggered by the target group. The policy status adjustment module 108 is used to adjust the status of the target insurance form to the underwritten status in response to confirmation and payment instructions.
[0096] This application provides a group insurance policy generation device. For the policy generation process of group insurance products under insurance business, firstly, it receives an original personnel list file of the target group sent by a mobile application; wherein the target group includes multiple target objects, and the basic information of the objects is clearly processed. Next, the original personnel list file is parsed to obtain the original list fields, accurately extracting key data to ensure accurate information identification. After obtaining the original list fields, based on the original list fields and the original personnel list file, fields are filled in a preset insurance form template to quickly generate a standardized original insurance form for the target group, improving form production efficiency and standardization. Further, based on the original insurance form, the original user information and historical claims records of each target object are obtained; based on the original user information and historical claims records, premium prediction is performed, and the target premium data for each target object is calculated by combining the actual situation of each target object. Finally, based on the target premium data and original insurance forms for each target individual, a target insurance form for the target group is generated and sent to a mobile application. This ensures the completeness and accuracy of the form information and provides timely feedback to the target group, facilitating their understanding of the insurance details. The overall process improves the efficiency and accuracy of group insurance policy generation, resolving the technical issue of slow policy generation due to sales personnel being unable to handle group insurance policy generation in a timely manner while conducting business outside the office.
[0097] Specific limitations regarding the group insurance policy generation device can be found in the limitations of the group insurance policy generation method described above, and will not be repeated here. Each module in the aforementioned group insurance policy generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.
[0098] Please see Figure 8 , Figure 8 The hardware structure of a computer device according to another embodiment is illustrated. The computer device includes: The processor 801 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 802 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 802 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and is called and executed by the processor 801 to execute the group insurance policy generation method of the embodiments of this application, including: Receive the original personnel list file of the target group sent by the mobile application; wherein the target group includes multiple target objects; Parse the original personnel list file to obtain the original list fields; Based on the original list fields and the original personnel list file, the fields are filled in the preset insurance form template to obtain the original insurance form for the target group; The original user information and historical claims records of each target object are obtained based on the original insurance form; the premium is predicted based on the original user information and historical claims records to obtain the target premium data for each target object; Based on the target premium data and original insurance forms for each target object, a target insurance form for the target group is generated, and the target insurance form is sent to the mobile application so that the target insurance form can be sent to the target group through the mobile application.
[0099] The 803 input / output interface is used to implement information input and output. The communication interface 804 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 805 transmits information between various components of the device (e.g., processor 801, memory 802, input / output interface 803, and communication interface 804); The processor 801, memory 802, input / output interface 803, and communication interface 804 are connected to each other within the device via bus 805.
[0100] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Receive the original personnel list file of the target group sent by the mobile application; wherein the target group includes multiple target objects; Parse the original personnel list file to obtain the original list fields; Based on the original list fields and the original personnel list file, the fields are filled in the preset insurance form template to obtain the original insurance form for the target group; The original user information and historical claims records of each target object are obtained based on the original insurance form; the premium is predicted based on the original user information and historical claims records to obtain the target premium data for each target object; Based on the target premium data and original insurance forms for each target object, a target insurance form for the target group is generated, and the target insurance form is sent to the mobile application so that the target insurance form can be sent to the target group through the mobile application.
[0101] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.
[0102] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0103] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0104] It should be noted that any AI models, software tools, or components not belonging to this company appearing in the embodiments of this application are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this application has been authorized (with the knowledge and consent) by the relevant parties or has been fully authorized by all parties, and the executing entity may obtain it through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.
[0105] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for generating group insurance policies, characterized in that, Applied to an enterprise's internal backend, the method includes: Receive an original personnel list file of a target group sent by a mobile application; wherein the target group includes multiple target objects; The original personnel list file is parsed to obtain the original list fields; Based on the original list fields and the original personnel list file, the fields are filled in the preset insurance form template to obtain the original insurance form for the target group; Based on the original insurance form, obtain the original user information and historical claims records of each target object; based on the original user information and the historical claims records, perform premium prediction to obtain the target premium data for each target object; Based on the target premium data and the original insurance form for each target object, a target insurance form for the target group is generated, and the target insurance form is sent to the mobile application so that the target insurance form can be sent to the target group through the mobile application.
2. The group insurance policy generation method as described in claim 1, characterized in that, The insurance form template includes preset form fields; the process of filling in the fields in the preset insurance form template based on the original list fields and the original personnel list file to obtain the original insurance form for the target group includes: Based on the original list fields, field extraction is performed from the original personnel list file to obtain candidate field information; The candidate field information is standardized to obtain standardized field information; Based on the mapping between the preset form fields and the original list fields, a field mapping relationship is obtained; Based on the field mapping relationship, the standardized field information is filled into the insurance form template to obtain the original insurance form for the target group.
3. The group insurance policy generation method as described in claim 2, characterized in that, The process of parsing the original personnel list file to obtain the original list fields includes: The original personnel list file is formatted to obtain the list file format; Select a preset field parsing model based on the aforementioned list file format; The original personnel list file is parsed using the field parsing model to obtain the original list fields.
4. The group insurance policy generation method as described in claim 3, characterized in that, After parsing the original personnel list file using the field parsing model to obtain the original list fields, the method further includes: The preset form fields and the original list fields are matched to obtain field matching data; wherein, the field matching data is used to indicate whether there are any missing fields in the original list fields; If the field matching data indicates that there is a missing field in the original list, field missing information is generated based on the missing field, and the field missing information is sent to the mobile application so that the field missing information can be sent to the target group through the mobile application.
5. The group insurance policy generation method as described in claim 1, characterized in that, The premium prediction based on the original user information and the historical claims records, to obtain target premium data for each target object, includes: For each target object, feature processing is performed on the original user information to obtain user feature data; Feature extraction is performed on the historical claims records to obtain claims record features; based on the user feature data and the claims record features, premium prediction is performed to obtain the target premium data for each target object.
6. The group insurance policy generation method as described in claim 5, characterized in that, The premium prediction based on the user feature data and the claims record features, to obtain the target premium data for each target object, includes: Based on the user characteristic data and the claims record characteristics, feature combinations are performed to obtain claims risk characteristics; Risk calculations are performed on the aforementioned claims risk characteristics to obtain the underwriting risk factor; Obtain the benchmark premium data for the target insured products of the target group; The target premium data for the target object is obtained by performing aggregate calculations based on the underwriting risk factors and the benchmark premium data.
7. The method for generating a group insurance policy as described in any one of claims 1 to 6, characterized in that, After generating the target insurance form for the target group based on the target premium data and the original insurance form for each target object, and sending the target insurance form to the target group, the method further includes: Receive confirmation and payment instructions from the target insurance form; wherein, the confirmation and payment instructions are triggered by the target group; In response to the confirmation and payment instructions, the status of the target insurance form is adjusted to the underwritten status.
8. A group insurance policy generation device, characterized in that, The device, used in the internal backend of an enterprise, includes: The manifest file acquisition module is used to receive the original personnel manifest file of the target group sent by the mobile application; wherein, the target group includes multiple target objects; The file parsing module is used to parse the original personnel list file to obtain the original list fields; The field filling module is used to fill in the fields in the preset insurance form template based on the original list fields and the original personnel list file to obtain the original insurance form for the target group; The user data acquisition module is used to acquire the original user information and historical claims records of each target object based on the original insurance form. The premium calculation module is used to predict premiums based on the original user information and the historical claims records, and to obtain target premium data for each target object. The target policy generation module is used to generate a target insurance form for the target group based on the target premium data of each target object and the original insurance form, and send the target insurance form to the mobile application so that the target insurance form can be sent to the target group through the mobile application.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the group insurance policy generation method as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the group insurance policy generation method as described in any one of claims 1 to 7.