Insurance policy generation method and device, computer device and storage medium

Abstract

This application provides a policy generation method and apparatus, computer equipment, and storage medium, belonging to the field of artificial intelligence technology. The method includes: acquiring and determining a predicted insurance business category based on the object's identity information and historical insurance data; outputting policy completion prompts to the target terminal where the target object is located based on the predicted insurance business category, and receiving insurance information fed back by the target terminal based on the policy completion prompts; generating a preliminary policy based on the insurance information and the predicted insurance business category; performing intelligent underwriting on the preliminary policy according to preset underwriting rules to obtain underwriting information; wherein, the underwriting information characterizes the price reasonableness, data completeness, logical accuracy, and content compliance rate of the preliminary policy; and optimizing the content of the preliminary policy based on the underwriting information to obtain a target policy. This application can be applied to business systems requiring large amounts of data, such as fintech, and can reduce manpower and error rates in the policy generation process.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and is applied to the field of financial technology, particularly to a policy generation method and apparatus, computer equipment and storage medium. Background Technology

[0002] During the policy generation process, insurance agents need to manually collect and enter the policyholder's basic information, and then confirm all policy details with the policyholder. Therefore, this process requires agents to spend a significant amount of time and effort on basic information entry and guiding policyholders through tedious form filling, which can negatively impact the policyholder's experience. Furthermore, errors in information entry are prone to occur, leading to invalid policies. Therefore, reducing manpower and error rates in the policy generation process while improving the policyholder's experience has become a pressing technical challenge. Summary of the Invention

[0003] The main objective of this application is to provide a policy generation method and apparatus, computer equipment and storage medium, which aims to reduce manpower and error rate in the policy generation process and improve the policyholder's experience during the insurance application process.

[0004] To achieve the above objectives, a first aspect of this application proposes a policy generation method, the method comprising: Obtain the target object's identity information and historical insurance data; Based on the object's identity information and the historical insurance data, the insurance business category of the target object is predicted to obtain the predicted insurance business category. Based on the predicted insurance business category, policy filling prompts are output to the target terminal where the target object is located, and the insurance information fed back by the target terminal based on the policy filling prompts is received. Based on the insurance information and the predicted insurance business category, a preliminary insurance policy is generated. The preliminary policy is intelligently underwritten according to preset underwriting rules to obtain underwriting information; wherein, the underwriting information represents the price reasonableness, data completeness, logical accuracy, and content compliance rate of the preliminary policy; The preliminary policy is optimized based on the underwriting information to obtain the target policy.

[0005] In some embodiments, the step of predicting the insurance business category of the target object based on the object's identity information and the historical insurance data to obtain the predicted insurance business category includes: A profile is constructed based on the object's identity information and the historical insurance data to obtain the object's insurance profile. The insurance application profile of the object is used to identify the business content, thereby obtaining the insurance application business content; The correlation measurement is performed based on the insurance business content and the preset candidate insurance categories to obtain correlation measurement data; The predicted insurance business category is selected from the candidate insurance categories based on the correlation measurement data.

[0006] In some embodiments, the step of constructing a profile based on the object's identity information and historical insurance data to obtain an object's insurance profile includes: Extract object attribute features from the object identity information; Extract historical insurance features from the historical insurance data; Based on the historical insurance characteristics and the object attribute characteristics, insurance category preference is predicted to obtain predicted insurance category preference information; Based on the historical insurance characteristics and the object attribute characteristics, insurance risk is predicted to obtain predicted insurance risk information; Based on the predicted insurance category preference information, the predicted insurance risk information, the object attribute characteristics, and the historical insurance characteristics, a profile is constructed to obtain the object's insurance profile.

[0007] In some embodiments, generating a preliminary policy based on the insurance information and the predicted insurance business category includes: The insurance information is processed to extract business fields, resulting in insurance business fields. Based on the predicted insurance business category, the target policy template is selected from the preset candidate policy templates; The insurance application fields are standardized based on the target policy template to obtain standardized business fields. The standardized business fields and the target policy template are integrated to obtain the preliminary policy.

[0008] In some embodiments, the underwriting rules include: a preset price range, data verification rules, logical verification rules, and compliance verification rules; the step of intelligently underwriting the preliminary policy according to the preset underwriting rules to obtain underwriting information includes: The preset price range is compared with the insurance price in the initial policy to obtain price comparison information; The preliminary policy is subjected to data integrity verification according to the data verification rules to obtain data integrity verification information; The initial policy is logically accurate according to the logical verification rules to obtain logical accuracy verification information. The initial policy is subjected to content compliance verification according to the aforementioned compliance verification rules to obtain compliance verification information; The underwriting information is obtained by concatenating the price comparison information, the data integrity verification information, the logic accuracy verification information, and the compliance verification information.

[0009] In some embodiments, the underwriting information includes content anomaly information, and the step of optimizing the preliminary policy based on the underwriting information to obtain the target policy includes: Based on the content anomaly information, content is extracted from the preliminary policy to obtain the selected policy content; In response to the target terminal's content modification operation on the selected policy content, the updated policy content is obtained; The initial policy is updated based on the updated policy information to obtain the target policy.

[0010] In some embodiments, after the underwriting information includes content anomaly information, and the preliminary policy is optimized based on the underwriting information to obtain the target policy, the method further includes: The target insurance policy is visualized to obtain a policy visualization page; The system receives policy feedback information from the target terminal on the policy visualization page, and updates the content of the target policy based on the policy feedback information to obtain an updated policy.

[0011] To achieve the above objectives, a second aspect of this application provides a policy generation apparatus, the apparatus comprising: The data acquisition module is used to acquire the target object's identity information and historical insurance data; The category prediction module is used to predict the insurance business category of the target object based on the object's identity information and the historical insurance data, and to obtain the predicted insurance business category. The output and receive module is used to output policy filling prompt information to the target terminal where the target object is located according to the predicted insurance business category, and to receive the insurance information fed back by the target terminal according to the policy filling prompt information; The policy generation module is used to generate a preliminary policy based on the insurance information and the predicted insurance business category. The underwriting module is used to intelligently underwrite the preliminary policy according to preset underwriting rules to obtain underwriting information; wherein, the underwriting information represents the price reasonableness, data completeness, logical accuracy, and content compliance rate of the preliminary policy; The content optimization module is used to optimize the content of the preliminary policy based on the underwriting information to obtain the target policy.

[0012] To achieve the above objectives, a third aspect of the present application provides a computer device, the computer device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method described in the first aspect.

[0013] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0014] The policy generation method, apparatus, computer equipment, and storage medium proposed in this application automatically collect the target object's identity information and historical insurance data, and predict the target object's current business needs category by combining the object's identity information and historical insurance data to obtain a predicted insurance business category. Personalized policy entry prompts are generated based on the predicted insurance business category to help the target object accurately input insurance information. Then, a preliminary policy is generated by combining the insurance information and the predicted insurance business category, and underwriting is performed on the preliminary policy to obtain underwriting information. The preliminary policy is then optimized based on the underwriting information to generate a target policy whose content complies with underwriting rules. Therefore, in the policy generation process, personalized entry suggestions are provided based on the target object's insurance business needs, insurance information that meets the requirements for policy generation is collected, and the policy is automatically generated. Simultaneously, the automatically generated policy is further optimized for underwriting to generate a target policy whose content complies with underwriting rules. Therefore, policy generation not only saves manpower and reduces error rates, but also improves the efficiency of policy business processing and user experience. Attached Figure Description

[0015] Figure 1 This is a flowchart of the policy generation method provided in the embodiments of this application; Figure 2 yes Figure 1 The flowchart of step S102 in the document; Figure 3 yes Figure 2 The flowchart of step S201 in the text; Figure 4 This is a schematic diagram of the insurance profile of the object in the policy generation method provided in the embodiments of this application; Figure 5 This is a schematic diagram of the policy filling prompt information in the policy generation method provided in the embodiments of this application; Figure 6 yes Figure 1 The flowchart of step S104 in the process; Figure 7 yes Figure 1 The flowchart of step S105 in the process; Figure 8 yes Figure 1 The flowchart of step S106 in the process; Figure 9 This is a flowchart of a policy generation method provided in another embodiment of this application; Figure 10 This is an overall flowchart of the policy generation method provided in the embodiments of this application; Figure 11 This is a schematic diagram of the policy generation device provided in the embodiments of this application; Figure 12 This is a schematic diagram of the hardware structure of the computer device provided in the embodiments of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0017] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0019] 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.

[0020] Natural Language Processing (NLP): NLP uses computers to process, understand, and utilize human language (such as Chinese and English). It is a branch of artificial intelligence and an interdisciplinary field combining 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.

[0021] Insurance quotation form: This is a document provided by an insurance broker when requesting a quote from a policyholder. Its main contents include the quotation period, the client's insurance conditions, and the insured amount.

[0022] User personas, also known as user roles, are an effective tool for identifying target users and aligning user needs with design direction. They are widely used across various fields. In international communication in the digital age, this technology, combined with algorithmic recommendations and semantic analysis, enables precise insights into audience needs and effective understanding of cultural differences. By constructing dynamic user personas, communication strategies can be proactively shaped. In practice, we often use the simplest and most relatable language to connect and transform user attributes, behaviors, and expectations into data.

[0023] Machine learning (ML) is a core branch of artificial intelligence. Its essence is to enable computers to automatically learn patterns from data through algorithms, rather than relying on explicit programming instructions. Compared to traditional programs, machine learning models iteratively optimize parameters through training data, ultimately gaining the ability to predict or classify unknown data. For example, a linear regression model automatically determines the optimal weight parameters by minimizing the sum of squared errors between the predicted and actual values.

[0024] Optical Character Recognition (OCR) refers to the process by which computer devices (such as scanners or digital cameras) examine characters printed on paper, determine their shapes by detecting dark and light patterns, and then translate the shapes into computer text using character recognition methods. In other words, for printed characters, optical methods are used to convert the text in paper documents into black and white dot matrix image files, and recognition software is used to convert the text in the image into text format for further editing and processing by word processing software.

[0025] Image recognition refers to the technology of using computers to process, analyze, and understand images in order to identify targets and objects of various patterns. It is a practical application of deep learning algorithms. Currently, image recognition technology is generally divided into facial recognition and product recognition. Facial recognition is mainly used in security checks, identity verification, and mobile payments.

[0026] The policy generation process requires the creation of a quote request form in advance, which is then provided to the policyholder for confirmation before the policy is generated. During quote request generation, insurance agents manually collect and input their information into the system. However, manually generating quote requests presents several problems: First, manual input is inefficient, requiring agents to spend significant time and effort on basic information entry. Second, policyholders face a tedious form-filling process under agent guidance, leading to a poor user experience. Third, manual data entry is prone to errors, resulting in rework during subsequent policy review and processing. Fourth, there is a lack of effective automated information extraction and standardized processing mechanisms. Fifth, the cumbersome business process impacts overall efficiency. Therefore, current policy generation technologies suffer from low input efficiency, poor customer experience, and high error rates. A technological solution is urgently needed to improve policy generation efficiency, enhance customer experience, and reduce policy errors.

[0027] Based on this, embodiments of this application provide a policy generation method and apparatus, computer equipment, and storage medium, aiming to automatically collect the target object's identity information and historical insurance data, and predict the target object's current business needs category by combining the object's identity information and historical insurance data to obtain a predicted insurance business category. Then, based on the predicted insurance business category, policy filling prompts are output to the target terminal where the target object is located, so that the target object can input insurance information in a targeted manner according to the policy filling prompts. Therefore, the collection of insurance information can be completed accurately and automatically, and a preliminary policy can be generated through the insurance information and the predicted insurance business category. Then, the preliminary policy is underwritten to optimize the preliminary policy based on the underwriting information, and a target policy whose content meets the needs of the target object can be constructed. Therefore, during the policy generation process, filling suggestions are provided in a targeted manner according to the target object's insurance business needs to collect insurance information that meets the requirements for policy generation and automatically generate the policy. At the same time, the automatically generated policy is further optimized through underwriting to generate a target policy whose content meets the underwriting rules. Therefore, policy generation not only saves manpower and reduces error rate, but also improves the efficiency of policy business processing and user experience.

[0028] The policy generation method, apparatus, computer equipment, and storage medium provided in this application are specifically described through the following embodiments. First, the policy generation method in this application is described.

[0029] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0030] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0031] The policy generation method provided in this application relates to the field of artificial intelligence technology and is applied in the financial technology field. The policy generation method provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the policy generation method, but is not limited to the above forms.

[0032] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer computer devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0033] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0034] Figure 1 This is an optional flowchart of the policy generation method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S106.

[0035] Step S101: Obtain the target object's identity information and historical insurance data; Step S102: Based on the object's identity information and historical insurance data, predict the insurance business category of the target object to obtain the predicted insurance business category; Step S103: Output policy filling prompts to the target terminal where the target object is located according to the predicted insurance business category, and receive the insurance information fed back by the target terminal based on the policy filling prompts; Step S104: Generate a preliminary policy based on the insurance information and the predicted insurance business category; Step S105: Perform intelligent underwriting on the preliminary policy according to the preset underwriting rules to obtain underwriting information; wherein, the underwriting information represents the price reasonableness, data completeness, logical accuracy and content compliance of the preliminary policy; Step S106: Optimize the content of the preliminary policy based on the underwriting information to obtain the target policy.

[0036] Steps S101 to S106 of this embodiment involve automatically collecting the target object's identity information and historical insurance data, and using this information to predict the target object's insurance needs and determine the predicted insurance business category. Based on the predicted insurance business category, targeted policy completion prompts are provided to the target object, enabling them to accurately generate policy information. During policy generation, a preliminary policy is first generated based on the feedback insurance information and the predicted insurance business category. Intelligent underwriting is then performed on the preliminary policy to determine underwriting information, and the preliminary policy is optimized based on this underwriting information to construct a target policy that is reasonably priced, data-complete, logically accurate, and compliant. Throughout the policy generation process, targeted completion prompts are provided for the target object's insurance needs, and insurance information sufficient to accurately construct the policy is collected. Furthermore, the automatically generated policy is underwritten during policy generation to construct an accurate target policy that meets the target object's insurance business needs. Therefore, this embodiment achieves automated and accurate policy generation, saves manpower, reduces the error rate of policy content, and improves the policyholder's experience and the efficiency of insurance business processing during the insurance application process.

[0037] In step S101 of some embodiments, the policy generation method is applied to an insurance business platform, and the target object is the policyholder on the insurance business platform. The object identity information represents the identity of the target object and includes basic object information, contact information, and object behavior data. Historical insurance data is data related to the target object's insurance business, which can reflect the target object's behavior and preferences in the insurance field. It should be noted that the object identity information can be collected on the insurance business platform or on a third-party authorized platform, and the same applies to historical insurance data, which can be collected on the insurance business platform or on a third-party authorized insurance business platform, thus expanding the collection methods for object identity information and historical insurance data.

[0038] Specifically, historical insurance data includes at least one of the following: historical policy information, historical contract documents, historical claims data, historical insurance service data, and historical insurance transaction data. Therefore, historical insurance data can be used to analyze the target audience's behavior and preferences in the insurance field, thereby revealing their insurance needs. Furthermore, combining target identity information with historical insurance data can further improve the prediction of the target audience's insurance needs.

[0039] Furthermore, in the process of collecting object identity information and historical insurance data, multimodal data can be collected from insurance business platforms and authorized third-party platforms. Specifically, this includes text, images, video, audio, and unstructured data. Using OCR recognition technology, image recognition, and natural language processing technology, key fields related to insurance business can be extracted from the multimodal data as historical insurance data, and key fields related to user identity can be extracted as object identity information. For example, natural language processing technology can identify specific entities in text, such as "Zhang San," "XX City XX District," and "XX Insurance Type," while image recognition can process non-textual information in images, such as insurance policies, ID cards, and company documents, and extract structured information from them.

[0040] In step S102 of some embodiments, the target object's insurance business needs are predicted by combining the object's identity information and historical insurance data to determine the target object's current insurance business needs and obtain the predicted insurance business category. It should be noted that the predicted insurance business category includes renewal business category, claims business category, coverage expansion business category, consultation business category, and service business category, etc. This embodiment does not limit the predicted insurance business category. The predicted insurance business category represents the target object's current business needs to generate insurance policies that meet the target object's business needs, thereby improving the target object's experience on the insurance business platform.

[0041] Please see Figure 2 In some embodiments, step S102 may include, but is not limited to, steps S201 to S204: Step S201: Construct a profile based on the object's identity information and historical insurance data to obtain the object's insurance profile; Step S202: Perform business content recognition on the insurance profile of the target to obtain the insurance business content; Step S203: Perform correlation measurement based on the content of the insurance business and the preset candidate insurance categories to obtain correlation measurement data; Step S204: Select the predicted insurance business category from the candidate insurance categories based on the correlation measurement data.

[0042] In step S201 of some embodiments, the object insurance profile represents the comprehensive insurance information of the target object in the insurance field. The characteristics of the target object in the insurance field can be determined through the object insurance profile, and the characteristics include identity attribute characteristics, insurance characteristics, insurance risk characteristics, and insurance preference characteristics, etc.

[0043] In step S202 of some embodiments, business content recognition mainly involves identifying the content related to insurance business in the object's insurance profile, and this is accomplished through a large language model to extract the insurance business content.

[0044] In step S203 of some embodiments, the candidate insurance category refers to the candidate insurance categories and insurance business status that the target object can purchase on the insurance business platform. Specifically, all insurance categories on the insurance business platform are filtered according to the target object's identity information to determine the candidate insurance categories, so as to select the insurance categories that meet the target object's insurance needs and actual situation. For example, if the target object is a patient with a chronic disease and cannot purchase ordinary medical insurance, he / she can purchase accident insurance, critical illness insurance, and car insurance, etc. Therefore, the insurance categories that the target object can purchase are used as candidate insurance categories to accurately select the insurance types that meet the target object's insurance business needs and reduce the loss ratio of the insurance business platform.

[0045] Furthermore, the correlation between insurance business content and candidate insurance categories is measured, specifically by using a large language model to calculate the correlation between candidate insurance categories, insurance business status, and insurance business content.

[0046] In step S204 of some embodiments, the candidate insurance category corresponding to the highest correlation metric data is used as the predicted insurance business category. For example, if the insurance business content is "critical illness insurance with a coverage of 1 million", the candidate insurance category with the highest correlation is determined to be critical illness insurance, and the insurance business status is determined to be insurance consultation status, so the predicted insurance business category is determined to be critical illness insurance consultation category.

[0047] In some embodiments, after constructing an object insurance profile, the object insurance profile and historical insurance data are used as two core "knowledge bases," and a large language model is used to automatically identify the target object's needs from the object insurance profile and historical insurance data. Specifically, unstructured and fragmented object identity information is intelligently transformed into accurate and actionable insurance business requirements to determine the predicted insurance business category.

[0048] In steps S201 to S204 of this embodiment, an insurance profile of the target is constructed by combining the target's identity information and historical insurance data. Then, the target's insurance profile is analyzed by machine learning algorithms to analyze the target's specific insurance business needs and determine the predicted insurance business category. This eliminates the need for insurance agents to manually inquire and analyze, automatically predicts the target's insurance business needs, saves manpower, and can accurately push insurance business.

[0049] Please see Figure 3 In some embodiments, step S201 may include, but is not limited to, steps S301 to S305: Step S301: Extract object attribute features from object identity information; Step S302: Extract historical insurance features from historical insurance data; Step S303: Based on historical insurance characteristics and object attribute characteristics, predict insurance category preferences to obtain predicted insurance category preference information; Step S304: Based on historical insurance characteristics and object attribute characteristics, predict insurance risk to obtain predicted insurance risk information; Step S305: Based on the predicted insurance category preference information, predicted insurance risk information, object attribute characteristics, and historical insurance characteristics, a profile is constructed to obtain the object's insurance profile.

[0050] In steps S301 and S302 of some embodiments, object attribute features are extracted from the object identity information. These object attribute features include the object's age, gender, medical history, occupation, city, and education level. This embodiment does not impose restrictions on the object attribute features. Historical insurance features are extracted from historical insurance data, including historical insurance type, historical insurance amount, and historical insurance frequency. This embodiment also does not impose restrictions on the historical insurance features.

[0051] In step S303 of some embodiments, insurance category preference prediction is mainly completed using a pre-trained category preference prediction model. Specifically, historical insurance features and object attribute features are input into the category preference prediction model to predict the insurance category preference information. The predicted insurance category preference information includes the preferred insurance category and the degree of preference for the preferred insurance category.

[0052] In step S304 of some embodiments, in order to construct a more comprehensive profile representing the insurance domain characteristics of the target object, insurance risk prediction is performed based on historical insurance characteristics and object attribute characteristics to obtain predicted insurance risk information. Specifically, this embodiment uses a pre-trained insurance risk prediction model to predict insurance risk based on historical insurance characteristics and object attribute characteristics to obtain predicted insurance risk information. The predicted insurance risk information includes low risk, medium risk, and high risk. By predicting insurance risk information, a more accurate target insurance policy can be generated.

[0053] In step S305 of some embodiments, object identity features are converted into object attribute tags, historical insurance features are converted into historical insurance tags, predicted insurance category preference information is converted into predicted insurance category preference tags, and predicted insurance risk information is converted into predicted insurance risk tags. Then, the object attribute tags, historical insurance tags, predicted insurance category preference tags, and predicted insurance risk are used to construct an object insurance profile for the target object. Figure 4 As shown, Figure 4This document presents an insurance profile of the target individual. This profile reveals the target individual's personal attributes, preferred insurance types, insured risks, and historical insurance patterns. Therefore, by constructing an insurance profile, the current insurance needs of the target individual can be more accurately identified.

[0054] In steps S301 to S305 of this embodiment, object attribute features are first extracted from the object's identity information, and historical insurance features are extracted from historical insurance data. Based on the object attribute features and historical insurance features, the object's insurance category preference and insurance risk are predicted. A user profile of the object's insurance application is then constructed by combining these three factors. Therefore, the user profile allows for precise identification of the target object's insurance needs, resulting in a more accurate prediction of the insurance category.

[0055] In step S103 of some embodiments, policy completion prompts are filtered from preset candidate prompts based on the predicted insurance business category, and the prompts differ for different predicted insurance business categories. Specifically, if the predicted insurance business category is a renewal business category, the policy completion prompts are used to prompt the target to provide renewal information; if the predicted insurance business category is a claims business category, the prompts are used to prompt the target to upload information related to insurance claims. Therefore, for different predicted insurance business categories, the prompts are tailored to the target to provide information that conforms to the current insurance business, reducing the probability of providing incorrect information. Specifically, after the policy completion prompts are filtered out, they are displayed in a window on the target terminal where the target is located, requiring the target to confirm. The information that the target needs to provide is also displayed on the insurance business platform, and an input example is implicitly displayed in each input box to prompt the target to complete the insurance information input. Therefore, the information entered by the target on the pop-up page serves as the insurance information.

[0056] For example, such as Figure 5 As shown, if the predicted insurance business category is insurance consultation business, and the insurance category being consulted is confirmed to be critical illness insurance, the policy filling prompt information will be related to information collection during the critical illness insurance application process, and will be based on... Figure 5 The policy entry prompts are displayed as shown. Therefore, through... Figure 5As can be seen, the policy entry prompts are displayed in various text boxes, where the target user can primarily input their company name, industry category, insured items, plan details, deductible options, and budgeted insured amount. In addition, the policy information can also be files or images uploaded by the target user, including chat logs and documents used for insurance transactions. Therefore, if the information returned by the target user on the target terminal is not text content, if it is a file, the file can be parsed to obtain key fields related to the policy as the policy information; if it is an image, OCR technology can be used to recognize the text in the image, and image recognition technology can be used to identify the content in the image to determine the policy information. Therefore, when the target user submits policy information through the target terminal, there are no restrictions on the modality of the policy information. They can directly enter text content related to insurance transactions in the text boxes, or directly upload files, images, videos, and audio related to insurance transactions, enabling multimodal data uploads and making it more convenient for the target user to handle insurance transactions.

[0057] In step S104 of some embodiments, after the insurance information collection is completed, a preliminary insurance policy is automatically generated by combining the predicted insurance business category and the insurance information, thereby realizing the intelligent generation of insurance policies and saving manpower.

[0058] Please see Figure 6 In some embodiments, step S104 may include, but is not limited to, steps S601 to S604: Step S601: Extract business fields from the insurance application information to obtain the insurance application business fields; Step S602: Select the target policy template from the preset candidate policy templates according to the predicted insurance business category; Step S603: Standardize the insurance application fields according to the target policy template to obtain standardized business fields; Step S604: Integrate the standardized business fields and the target policy template to obtain a preliminary policy.

[0059] In step S601 of some embodiments, as disclosed above, the insurance application information can be data in multiple modalities. Therefore, different intelligent recognition technologies are used to process the uploaded insurance application information for different modalities to determine the insurance content, and to extract insurance business fields related to the insurance business from the insurance content. For example, the insurance content is accurately located and all key fields related to the insurance business are extracted, such as: policyholder, insured, beneficiary information, insurance period, and insured information, etc.

[0060] In step S602 of some embodiments, a selected insurance category is selected from candidate insurance categories based on the predicted insurance business category, and a target policy template is selected from candidate policy templates based on the selected insurance category and the predicted insurance business category. For example, if the predicted insurance business category is a renewal business category, and the selected insurance category for the current renewal is determined to be medical insurance based on the renewal business category, then a target policy template for medical insurance renewal is selected from the candidate policy templates. Therefore, by selecting the corresponding target policy template for different insurance business categories and insurance categories, preliminary policies can be generated quickly, saving time and manpower in policy generation.

[0061] In step S603 of some embodiments, before standardizing the insurance application fields, the fields need to be cleaned and validated to filter out duplicate and erroneous fields, leaving only accurate target fields. Then, the target fields are standardized to convert them into standardized business fields that match the target policy template. It should be noted that the standardized formats matched to the target policy template mainly include date formats, financial formats, insurance type code formats, status code formats, and text specifications, so that the standardized business fields after format conversion can be directly input into the target policy template to construct a uniformly formatted preliminary policy, facilitating review and underwriting.

[0062] In step S604 of some embodiments, standardized business fields are structurally encapsulated to obtain structured business fields. These structured business fields are then automatically filled into the target policy template to generate a preliminary policy. For example, if the predicted insurance category is a renewal category, and the target policy template is determined to be a policy with automatically filled historical policy information for the target object, then renewal-related and new standardized business fields are automatically associated with the target policy template to generate a complete and accurate preliminary policy. Therefore, a preliminary policy is automatically constructed, saving manpower and time in policy generation and improving policy generation efficiency.

[0063] In some embodiments, the initial policy includes a selected insurance category and structured business fields. The initial policy also includes insurance recommendation information for the selected insurance category, which is determined based on the target's identity information and the selected insurance category. Specifically, this recommendation information includes a recommended coverage amount and a recommended term. For example, if the target is a long-term coronary heart disease patient who cannot purchase critical illness insurance but can only purchase special medical insurance, then special medical insurance is selected as the insurance category. Considering that the target is 60 years old, retired, and experiencing declining income, the further output insurance recommendation information will be generated based on the target's age, income, and the purchase criteria for special medical insurance. This recommendation information could suggest that the target purchase a 10-year special medical insurance policy with a low coverage amount. Therefore, an automatic policy containing an insurance category, underwriting fields, and insurance recommendations is generated, providing the target with an intelligent and precise insurance service plan.

[0064] In steps S601 to S604 of this embodiment, fields related to insurance business are extracted from the insurance application information as insurance business fields. Then, a target policy template corresponding to the predicted insurance business category is selected. The insurance business fields are converted into standardized business fields according to the target policy template, and these standardized business fields are then filled into the target policy template to generate a preliminary policy. Therefore, the policy generation process is not merely a field format conversion, but a complex engineering process integrating information processing, cleaning, verification, standardization, and structured encapsulation. It can automatically extract fields related to policy generation and automatically generate policies that match the needs of the target object, achieving automation, intelligence, and efficiency in the insurance business process.

[0065] In step S105 of some embodiments, intelligent underwriting is a process that automates risk assessment and decision-making for preliminary policies using technologies such as artificial intelligence and big data analysis. Specifically, it assesses the risk of preliminary policies in multiple aspects, including price reasonableness, data completeness, logical accuracy, and content compliance. It should be noted that the underwriting rules include preset price ranges, data verification rules, logical verification rules, and compliance verification rules. The preset price range represents the insurance price acceptable to the target audience. Data verification rules verify the accuracy and completeness of data within the preliminary policy. Logical verification rules verify whether the content of the preliminary policy conforms to product design, business processes, and business logic. Compliance verification rules verify whether the content of the preliminary policy meets insurance regulatory requirements. In addition, the underwriting rules also include system and process verification rules, which verify the consistency of data between the core business system and surrounding systems of the preliminary policy. Therefore, after generating a preliminary policy, multiple verification rules are used to verify the preliminary policy in multiple aspects, such as insurance price, data completeness, content compliance, and logical accuracy, in order to optimize the preliminary policy and generate a target policy that meets the needs of the target audience and is accurate and compliant.

[0066] Please see Figure 7 In some embodiments, step S105 may include, but is not limited to, steps S701 to S705: Step S701: Compare the preset price range with the insurance price in the initial policy to obtain price comparison information; Step S702: Perform data integrity verification on the preliminary policy according to the data verification rules to obtain data integrity verification information; Step S703: Perform logical accuracy verification on the preliminary policy according to the logical verification rules to obtain logical accuracy verification information; Step S704: Perform content compliance verification on the preliminary policy according to the compliance verification rules to obtain compliance verification information; Step S705: The price comparison information, data integrity verification information, logical accuracy verification information, and compliance verification information are concatenated to obtain the underwriting information.

[0067] In step S701 of some embodiments, a preset price range is defined as the insurance price range. The current insurance price is extracted from the preliminary policy, and the current insurance price is compared with the insurance price range to obtain price comparison information. Therefore, the price comparison information can indicate whether the current insurance price exceeds the insurance price range or is within the insurance price range. By using the price comparison information, the current insurance price of the preliminary policy can be revised to be within the insurance price range to obtain an updated insurance price, thereby establishing that the insurance price is within the price range set for the target object and increasing the probability of closing the insurance business.

[0068] In step S702 of some embodiments, the data in the preliminary policy is checked for completeness according to data verification rules. This mainly involves determining whether the required fields in the preliminary policy are empty, specifically whether the policyholder, insured, name, identification document, sum insured, and payment period are empty. The data completeness verification information is determined based on the proportion of empty fields. The preliminary policy is then optimized using this data completeness verification information. Missing fields can be identified based on this information, and filling fields can be further extracted from the policy application information, the applicant's identity information, and historical policy application data. If no filling fields can be found in the policy application information, the applicant's identity information, and historical policy application data, then field supplementation information is output to the target terminal, whereby the target applicant completes the filling of the missing fields.

[0069] In step S703 of some embodiments, the logic accuracy verification mainly involves three aspects: policy status verification of the preliminary policy, insurance product rule verification, and correlation verification. Policy status verification primarily determines whether the preliminary policy has duplicate coverage; insurance product rule verification primarily determines whether the initial policy's underwriting score exceeds the limit and whether the insurance category combination complies with the rules; and correlation verification primarily verifies whether there is a valid relationship between the policyholder and the insured in the preliminary policy. Therefore, by determining the logic accuracy verification information through logic accuracy verification, the logically invalid content in the preliminary policy can be adjusted based on the logic accuracy verification information to construct a more logically sound target policy.

[0070] In step S704 of some embodiments, the compliance verification mainly determines the authenticity of the identity within the preliminary policy and whether the policyholder and insured are on the insurance blacklist, in order to determine whether the preliminary policy contains any prohibited content. Therefore, the output compliance verification rules can instruct the content of the preliminary policy to be optimized in a compliant direction, constructing a target policy with more compliant content and reduced underwriting risk.

[0071] In step S705 of some embodiments, underwriting information is formed by combining price comparison information, data integrity verification information, logical accuracy verification information, and compliance verification information. This facilitates subsequent preliminary policy optimization, optimizing the preliminary policy from multiple aspects to output a target policy that is reasonably priced, accurate in content and logic, and compliant.

[0072] In steps S701 to S705 of this embodiment, the verification process of the preliminary policy mainly focuses on four aspects: the reasonableness of the price, the integrity of the data, the accuracy of the logic, and the compliance rate of the content. This comprehensive verification of the preliminary policy can intercept problematic preliminary policies as early as possible and provide specific optimization suggestions for the optimization of the preliminary policy, so as to optimize a more accurate and compliant target policy in the future.

[0073] In step S106 of some embodiments, the underwriting information includes content anomaly information, and the content anomaly information is content that does not comply with the underwriting rules in the preliminary policy. Therefore, the preliminary policy can be optimized in a targeted manner through the content anomaly information to build a preliminary policy with more accurate and compliant content.

[0074] Please see Figure 8 In some embodiments, step S106 includes, but is not limited to, steps S801 to S803: Step S801: Extract content from the preliminary policy based on the content anomaly information to obtain the selected policy content; Step S802: In response to the target terminal's content modification operation on the selected policy content, the updated policy content is obtained; Step S803: Update the initial policy according to the updated policy content to obtain the target policy.

[0075] In step S801 of some embodiments, as disclosed above, the content anomaly information can be price anomaly, missing fields, logical error content, and non-compliant content. Therefore, the selected policy content belongs to the problematic content in the preliminary policy.

[0076] In step S802 of some embodiments, the selected policy content is output to the target terminal. The target object then revises the preliminary policy accordingly based on the selected policy content. In response to the target object's modification operation on the target terminal, the revised content of the preliminary policy is used as the updated policy content. For example, if the abnormal information indicates that the insured amount is too high, the preliminary policy will be displayed on the insurance business platform, with the insured amount highlighted in red and in a revisable mode, requiring the target object to adjust the insured amount. If the abnormal information indicates that the policyholder is on a blacklist, the policyholder will be highlighted in red on the preliminary policy, and a notification will be displayed indicating the policyholder's abnormality, prompting the target object to re-apply for other insurance categories.

[0077] In step S803 of some embodiments, the content of the preliminary policy is updated according to the updated policy content. Specifically, the selected policy content in the preliminary policy is replaced with the updated policy content to obtain the target policy.

[0078] In steps S801 to S803 of this embodiment, during the initial policy optimization process, selected policy content is extracted based on the abnormal content of the initial policy. The selected policy content can be used to specifically prompt the target object to revise the initial policy. Then, the initial policy is updated based on the revised content to generate a standardized, compliant, and accurate target policy.

[0079] Please see Figure 9 In some embodiments, after step S106, the policy generation method may also include, but is not limited to, steps S901 to S902: Step S901: Visualize the target policy to obtain a policy visualization page; Step S902: Receive policy feedback information from the target terminal on the policy visualization page, and update the content of the target policy according to the policy feedback information to obtain an updated policy.

[0080] In step S901 of some embodiments, the target policy is a kind of inquiry form before the insurance business is processed. It needs to be further confirmed by the target object before the insurance business is completed. Therefore, the target policy needs to be converted into a policy visualization page in a visual format and displayed on the target terminal so that the target object can further confirm the policy content on the target terminal.

[0081] In step S902 of some embodiments, the target object provides feedback on the policy visualization page information on the target terminal to receive policy feedback information. The policy insurance information includes policy confirmation information and policy correction information. The target policy is determined as the final policy based on the policy confirmation information, and the content corresponding to the target policy is corrected based on the policy correction information to obtain updated policy information. It should be noted that on the policy visualization page, the target object can only adjust the policyholder's identity information and personal history; it cannot adjust insurance-related content, such as the insured amount, insurance description, and insurance standards.

[0082] In steps S901 to S902 of this embodiment, after the target policy is generated, it is first displayed on the target terminal in the form of a visual page, so that the target can further confirm the information on the target policy on the target terminal and generate a more accurate policy that conforms to the actual situation of the target.

[0083] Please refer to Figure 10The target of this application embodiment is the policyholder. The policyholder registers their information on an insurance business platform in advance to obtain their identity information. Simultaneously, the policyholder can automatically fill in their past insurance history as historical insurance data, or authorize the insurance business platform to collect historical insurance data from third-party insurance business platforms that have previously handled their insurance. It should be noted that the collected identity information and historical insurance data are uploaded in multiple modalities, including text, image, video, and unstructured data. Therefore, it is necessary to combine artificial intelligence, natural language processing, OCR, and image recognition technologies to complete the collection of identity information and historical insurance data. For example, the text uploaded by the policyholder may contain information such as "Zhang San" (name), "XX City XX District" (address), "1 million" (coverage amount), and "critical illness insurance" (type of insurance). The content of the text is used to identify historical insurance data. Then, based on the historical insurance data and the policyholder's identity information, a policyholder profile is constructed. Machine learning algorithms are then used to analyze this profile to determine the policyholder's insurance needs and predict the type of insurance business. For example, if the predicted insurance business category is determined to be a claims business category, further claims-related information needs to be collected. Therefore, a policy entry prompt corresponding to the claims business category is displayed on the policyholder's target terminal to collect the policyholder's claims-related information and obtain the insurance information. It should be noted that the insurance information can also be text content, files, or images uploaded by the policyholder to the insurance business platform, so artificial intelligence technology is still needed to extract the insurance information. Further, the insurance information is standardized. Specifically, the insurance business fields are extracted, cleaned, and validated. The validated insurance business fields are then standardized to obtain standardized business fields, which are then filled into the target policy template corresponding to the predicted insurance business category to obtain a preliminary policy. To further construct accurate, compliant, and logically correct policies, the preliminary policy needs to be underwritten. Underwriting involves price reasonableness verification, data accuracy verification, business logic accuracy verification, and content compliance verification to obtain underwriting information. Based on the underwriting information, the preliminary policy is optimized to generate a target policy that is reasonably priced, data accurate, business logic accurate, and content compliant. Finally, the target policy is displayed in a visual format on the target terminal where the policyholder is located, allowing the policyholder to further confirm and adjust it to complete the insurance transaction.

[0084] In summary, the embodiments of this application involve intelligent recognition of multiple modal data, supporting intelligent recognition of text, files, images, and other modal data, breaking through the traditional single-information input method. Simultaneously, based on the object's identity information and historical insurance data, an object's insurance profile is constructed to predict the insurance business the policyholder may need to handle, providing personalized policy filling prompts. During the policy generation process, information from different sources can be converted into a unified and standardized format to generate a uniform policy. Furthermore, a policy underwriting and optimization process is set up to construct a target policy with more accurate content and a reasonable price, while saving manpower in the policy generation process and improving the policyholder's experience during the insurance application process.

[0085] Please see Figure 11 This application also provides a policy generation device that can implement the above-described policy generation method. The device includes: Data acquisition module 1101 is used to acquire the object identity information and historical insurance data of the target object; The category prediction module 1102 is used to predict the insurance business category of the target object based on the object's identity information and historical insurance data, and obtain the predicted insurance business category. The output and receive module 1103 is used to output policy filling prompt information to the target terminal where the target object is located according to the predicted insurance business category, and to receive the insurance information fed back by the target terminal according to the policy filling prompt information; The policy generation module 1104 is used to generate a preliminary policy based on the insurance information and the predicted insurance business category. The underwriting module 1105 is used to intelligently underwrite the preliminary policy according to the preset underwriting rules and obtain underwriting information; among which, the underwriting information represents the price reasonableness, data completeness, logical accuracy and content compliance of the preliminary policy; The content optimization module 1106 is used to optimize the content of the preliminary policy based on the underwriting information to obtain the target policy.

[0086] The specific implementation of this policy generation device is basically the same as the specific implementation of the policy generation method described above, and will not be repeated here.

[0087] This application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described policy generation method. This computer device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0088] Please see Figure 12 , Figure 12 The hardware structure of a computer device according to another embodiment is illustrated. The computer device includes: The processor 1201 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 1202 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1202 can store the operating system and other applications. 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 1202 and is called and executed by the processor 1201 using the policy generation method of the embodiments of this application. The input / output interface 1203 is used to implement information input and output; The communication interface 1204 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 1205 transmits information between various components of the device (e.g., processor 1201, memory 1202, input / output interface 1203, and communication interface 1204); The processor 1201, memory 1202, input / output interface 1203 and communication interface 1204 are connected to each other within the device via bus 1205.

[0089] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described policy generation method.

[0090] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0091] The policy generation method, apparatus, computer equipment, and storage medium provided in this application automatically collect the target object's identity information and historical insurance data, and predict the target object's current business needs category by combining the object's identity information and historical insurance data to obtain a predicted insurance business category. Personalized policy entry prompts are generated based on the predicted insurance business category to help the target object accurately input insurance information. Then, a preliminary policy is generated by combining the insurance information and the predicted insurance business category, and the preliminary policy is underwritten to obtain more refined underwriting. The preliminary policy is then optimized based on the underwriting information to generate a target policy whose content conforms to the underwriting rules. Therefore, during the policy generation process, personalized entry suggestions are provided based on the target object's insurance business needs to collect insurance information that meets the requirements for policy generation and automatically generate the policy. Simultaneously, the automatically generated policy is further optimized through underwriting to generate a target policy whose content conforms to the underwriting rules. Therefore, policy generation not only saves manpower and reduces error rates but also improves the efficiency of policy business processing and user experience.

[0092] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0093] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0094] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0095] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0096] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0097] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and 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 through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0099] The units described above 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.

[0100] Furthermore, the functional units in the various embodiments of this application 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0101] If the integrated unit 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 application, in essence, or the part that contributes to the prior art, or all or 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 multiple 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 application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0102] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for generating an insurance policy, characterized in that, The method includes: Obtain the target object's identity information and historical insurance data; Based on the object's identity information and the historical insurance data, the insurance business category of the target object is predicted to obtain the predicted insurance business category. Based on the predicted insurance business category, policy filling prompts are output to the target terminal where the target object is located, and the insurance information fed back by the target terminal based on the policy filling prompts is received. Based on the insurance information and the predicted insurance business category, a preliminary insurance policy is generated. The preliminary policy is intelligently underwritten according to preset underwriting rules to obtain underwriting information; wherein, the underwriting information represents the price reasonableness, data completeness, logical accuracy, and content compliance rate of the preliminary policy; The preliminary policy is optimized based on the underwriting information to obtain the target policy.

2. The method according to claim 1, characterized in that, The step of predicting the insurance business category of the target object based on the object's identity information and the historical insurance data to obtain the predicted insurance business category includes: A profile is constructed based on the object's identity information and the historical insurance data to obtain the object's insurance profile. The insurance application profile of the object is used to identify the business content, thereby obtaining the insurance application business content; The correlation measurement is performed based on the insurance business content and the preset candidate insurance categories to obtain correlation measurement data; The predicted insurance business category is selected from the candidate insurance categories based on the correlation measurement data.

3. The method according to claim 2, characterized in that, The process of constructing a profile based on the object's identity information and historical insurance data to obtain an object's insurance profile includes: Extract object attribute features from the object identity information; Extract historical insurance features from the historical insurance data; Based on the historical insurance characteristics and the object attribute characteristics, insurance category preference is predicted to obtain predicted insurance category preference information; Based on the historical insurance characteristics and the object attribute characteristics, insurance risk is predicted to obtain predicted insurance risk information; Based on the predicted insurance category preference information, the predicted insurance risk information, the object attribute characteristics, and the historical insurance characteristics, a profile is constructed to obtain the object's insurance profile.

4. The method according to claim 1, characterized in that, The step of generating a preliminary policy based on the insurance information and the predicted insurance business category includes: The insurance information is processed to extract business fields, resulting in insurance business fields. Based on the predicted insurance business category, the target policy template is selected from the preset candidate policy templates; The insurance application fields are standardized based on the target policy template to obtain standardized business fields. The standardized business fields and the target policy template are integrated to obtain the preliminary policy.

5. The method according to any one of claims 1 to 4, characterized in that, The underwriting rules include: preset price range, data verification rules, logical verification rules, and compliance verification rules; the intelligent underwriting of the preliminary policy based on the preset underwriting rules to obtain underwriting information includes: The preset price range is compared with the insurance price in the initial policy to obtain price comparison information; The preliminary policy is subjected to data integrity verification according to the data verification rules to obtain data integrity verification information; The initial policy is logically accurate according to the logical verification rules to obtain logical accuracy verification information. The initial policy is subjected to content compliance verification according to the aforementioned compliance verification rules to obtain compliance verification information; The underwriting information is obtained by concatenating the price comparison information, the data integrity verification information, the logic accuracy verification information, and the compliance verification information.

6. The method according to any one of claims 1 to 4, characterized in that, The underwriting information includes content anomaly information. The step of optimizing the preliminary policy based on the underwriting information to obtain the target policy includes: Based on the content anomaly information, content is extracted from the preliminary policy to obtain the selected policy content; In response to the target terminal's content modification operation on the selected policy content, the updated policy content is obtained; The initial policy is updated based on the updated policy information to obtain the target policy.

7. The method according to any one of claims 1 to 4, characterized in that, After the underwriting information includes content anomaly information, and the preliminary policy is optimized based on the underwriting information to obtain the target policy, the method further includes: The target insurance policy is visualized to obtain a policy visualization page; The system receives policy feedback information from the target terminal on the policy visualization page, and updates the content of the target policy based on the policy feedback information to obtain an updated policy.

8. A policy generation device, characterized in that, The device includes: The data acquisition module is used to acquire the target object's identity information and historical insurance data; The category prediction module is used to predict the insurance business category of the target object based on the object's identity information and the historical insurance data, and to obtain the predicted insurance business category. The output and receive module is used to output policy filling prompt information to the target terminal where the target object is located according to the predicted insurance business category, and to receive the insurance information fed back by the target terminal according to the policy filling prompt information; The policy generation module is used to generate a preliminary policy based on the insurance information and the predicted insurance business category. The underwriting module is used to intelligently underwrite the preliminary policy according to preset underwriting rules to obtain underwriting information; wherein, the underwriting information represents the price reasonableness, data completeness, logical accuracy, and content compliance rate of the preliminary policy; The content optimization module is used to optimize the content of the preliminary policy based on the underwriting information to obtain the target policy.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the policy generation method according to 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 policy generation method according to any one of claims 1 to 7.

Images