Insurance claim settlement application method and device, equipment and storage medium

Abstract

The invention provides an insurance claim settlement application method and device, equipment and a storage medium, and the method comprises the steps: receiving a claim settlement material image submitted by a user; extracting structured key information related to the claim settlement application from the claim settlement material image; determining guarantee responsibility and available insurance policies of the user based on the structured key information, and generating a plurality of candidate claim settlement schemes based on the guarantee responsibility and the available insurance policies; performing compensation amount trial calculation on each candidate claim settlement scheme to obtain a pre-compensation amount, and determining an optimal claim settlement scheme based on the pre-compensation amount of each candidate claim settlement scheme; and initiating a claim settlement application process to an insurance service system based on the optimal claim settlement scheme. By adopting the method, the claim application efficiency and accuracy can be improved, and the user claim experience and the insurance service quality are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of smart insurance, and more specifically, to an insurance claim application method, apparatus, device, and storage medium. Background Technology

[0002] In the financial insurance sector, insurance claims are a core business process for protecting the rights and interests of the insured, and directly affect user satisfaction with insurance services. With the widespread use of corporate group insurance policies, insured individuals (mostly company employees) often face multiple policies with various coverages, including supplementary medical insurance and accidental medical insurance. The complexity of the claims process continues to increase, placing higher demands on the efficiency and convenience of claims services.

[0003] In existing technologies, insurance claims are mainly processed through a fully manual review process: users need to manually fill out a detailed claim application form, prepare paper claim materials such as medical invoices, medical records, and identity documents, and submit them to the insurance company; the insurance company arranges professional reviewers to verify the completeness and authenticity of the materials one by one, manually enter the key information in the materials into the system, then check the policy terms under the user's name to confirm the coverage liability, and finally calculate the compensation amount based on the details of medical expenses, and complete the review and compensation decision.

[0004] The manual review scheme has significant technical flaws: manual processing requires a large investment of manpower, and the processes of information entry, policy matching, and amount calculation rely on manual operation, which is not only inefficient and unable to meet the needs of large-scale claims, but also prone to problems such as information errors and biased liability judgments due to human negligence; at the same time, users have to bear tedious work such as material preparation and information filling, the claims cycle is long, the overall experience is poor, and it cannot meet the current demand for intelligent and efficient services. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide an insurance claim application method, device, equipment and storage medium that can improve the efficiency and accuracy of claim applications and significantly improve the user's claim experience and the quality of insurance services.

[0006] In a first aspect, embodiments of this application provide an insurance claim application method, the method comprising: Receive images of claim materials submitted by users; Extract structured key information related to the claim application from the images of the claim materials; Based on the structured key information, the user's coverage responsibilities and available policies are determined, and several candidate claim settlement plans are generated based on the coverage responsibilities and available policies. The pre-payment amount is calculated for each candidate claim plan, and the optimal claim plan is determined based on the pre-payment amount of each candidate claim plan. Based on the optimal claims settlement plan, a claims application process is initiated with the insurance business system.

[0007] Optionally, the step of extracting structured key information related to the claim application from the image of the claim materials includes: The images of the claim materials are identified by type to determine whether they belong to at least one of the following: medical invoices, expense lists, examination reports, medical records, or identity documents. Based on the identified image type, the corresponding optical character recognition model or pre-trained deep learning model is invoked to locate and extract key information fields of the preset category from the image; When the image type is a medical invoice, the extracted key information fields include at least the payer's name, the total amount of medical expenses, the time the expenses occurred, and the name of the medical institution.

[0008] Optionally, determining the user's coverage and available policies based on the structured key information includes: Obtain the user identifier from the structured key information; Based on the user identifier, access the core insurance business system and query all available insurance policies that are in a valid state associated with the user identifier; Analyze the insurance terms of each valid and usable policy to extract the specific types of coverage provided by each policy.

[0009] Optionally, the generation of several candidate claim settlement plans based on the coverage and the available policies includes: Establish a mapping relationship between types of coverage and available insurance policies; Based on the mapping relationship, generate all possible combinations of coverage liability-underwritten policy matching sequences; If the same coverage applies to multiple available policies, then an independent matching item will be generated for each policy. If multiple different coverage liabilities are involved, all permutations and combinations containing different liability claim sequences are generated, and each complete liability matching sequence with the policy constitutes a candidate claim scheme.

[0010] Optionally, the step of calculating the pre-payment amount for each candidate claim settlement plan includes: For each candidate claim plan, based on the details and amount of medical expenses in the structured key information, and in accordance with the claim order determined in the candidate claim plan, the theoretical payout amount for each coverage liability under its corresponding policy is calculated sequentially. The theoretical payout amounts for each coverage under the candidate claim plan are summarized under their corresponding policies to obtain the pre-payout amount for the candidate claim plan.

[0011] Optionally, determining the optimal claim settlement plan based on the pre-payment amount of each candidate claim settlement plan includes: Compare the pre-payment amounts of all candidate claim options; The candidate claim settlement plan with the highest pre-payment amount is determined as the optimal claim settlement plan; If multiple candidate claim settlement options have the same pre-payment amount, the option involving the fewest policies will be selected as the optimal claim settlement option.

[0012] Optionally, after determining the optimal claim settlement plan based on the trial calculation results of the compensation amount for each candidate claim settlement plan, and before initiating the claim application process to the insurance business system based on the optimal claim settlement plan, the method further includes: The optimal claims settlement plan and its corresponding pre-payment amount will be returned to the user's terminal for display. Receive user confirmation or modification instructions for the optimal claims settlement plan; If a user confirmation instruction is received, standardized claim application data is generated based on the confirmed optimal claim settlement plan and its corresponding structured key information, and an application process is initiated to the insurance business system.

[0013] Secondly, embodiments of this application provide an insurance claim application device, the device comprising: The claims document image receiving module is used to receive images of claims documents submitted by users. The structured key information extraction module is used to extract structured key information related to the claim application from the image of the claim materials; The candidate claim solution generation module is used to determine the user's coverage responsibilities and available policies based on the structured key information, and to generate several candidate claim solutions based on the coverage responsibilities and available policies. The optimal claims settlement plan determination module is used to calculate the pre-payment amount for each candidate claims settlement plan, and determine the optimal claims settlement plan based on the pre-payment amount of each candidate claims settlement plan. The claims application process initiation module is used to initiate a claims application process to the insurance business system based on the optimal claims settlement plan.

[0014] Optionally, the step of extracting structured key information related to the claim application from the image of the claim materials includes: The images of the claim materials are identified by type to determine whether they belong to at least one of the following: medical invoices, expense lists, examination reports, medical records, or identity documents. Based on the identified image type, the corresponding optical character recognition model or pre-trained deep learning model is invoked to locate and extract key information fields of the preset category from the image; When the image type is a medical invoice, the extracted key information fields include at least the payer's name, the total amount of medical expenses, the time the expenses occurred, and the name of the medical institution.

[0015] Optionally, determining the user's coverage and available policies based on the structured key information includes: Obtain the user identifier from the structured key information; Based on the user identifier, access the core insurance business system and query all available insurance policies that are in a valid state associated with the user identifier; Analyze the insurance terms of each valid and usable policy to extract the specific types of coverage provided by each policy.

[0016] Optionally, the generation of several candidate claim settlement plans based on the coverage and the available policies includes: Establish a mapping relationship between types of coverage and available insurance policies; Based on the mapping relationship, generate all possible combinations of coverage liability-underwritten policy matching sequences; If the same coverage applies to multiple available policies, then an independent matching item will be generated for each policy. If multiple different coverage liabilities are involved, all permutations and combinations containing different liability claim sequences are generated, and each complete liability matching sequence with the policy constitutes a candidate claim scheme.

[0017] Optionally, the step of calculating the pre-payment amount for each candidate claim settlement plan includes: For each candidate claim plan, based on the details and amount of medical expenses in the structured key information, and in accordance with the claim order determined in the candidate claim plan, the theoretical payout amount for each coverage liability under its corresponding policy is calculated sequentially. The theoretical payout amounts for each coverage under the candidate claim plan are summarized under their corresponding policies to obtain the pre-payout amount for the candidate claim plan.

[0018] Optionally, determining the optimal claim settlement plan based on the pre-payment amount of each candidate claim settlement plan includes: Compare the pre-payment amounts of all candidate claim options; The candidate claim settlement plan with the highest pre-payment amount is determined as the optimal claim settlement plan; If multiple candidate claim settlement options have the same pre-payment amount, the option involving the fewest policies will be selected as the optimal claim settlement option.

[0019] Optionally, the apparatus further includes an application process initiation module, used for: After determining the optimal claim settlement plan based on the trial calculation results of the compensation amount of each candidate claim settlement plan, and before initiating the claim application process to the insurance business system based on the optimal claim settlement plan, the optimal claim settlement plan and its corresponding pre-payment amount are returned to the user terminal for display. Receive user confirmation or modification instructions for the optimal claims settlement plan; If a user confirmation instruction is received, standardized claim application data is generated based on the confirmed optimal claim settlement plan and its corresponding structured key information, and an application process is initiated to the insurance business system.

[0020] Thirdly, embodiments of this application provide a computer device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the insurance claim application method described in any of the optional embodiments of the first aspect are performed.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the insurance claim application method described in any of the optional embodiments of the first aspect.

[0022] The technical solution provided in this application includes, but is not limited to, the following beneficial effects: The step of receiving images of the claims materials submitted by users eliminates the need for users to organize paper materials and submit them offline. This breaks the time and space constraints, simplifies the initial process of claims application, lowers the threshold for users to submit materials, and allows users to conveniently initiate claims applications anytime and anywhere, thus improving the convenience and timeliness of claims applications.

[0023] Extracting structured key information related to the claim application from images of claim materials eliminates the tedious manual input of information by users, avoids information errors that may occur due to manual input, and quickly transforms unstructured image information into standardized structured data, providing accurate and efficient data support for the subsequent claims process and significantly improving information processing efficiency.

[0024] Based on structured key information, the system determines the user's coverage responsibilities and available policies and generates several candidate claim solutions. This eliminates the need for users to sort out their policies and interpret their coverage responsibilities themselves, effectively solving the problem of unclear claim paths when users face multiple coverage responsibilities and multiple policies. Furthermore, the generated candidate solutions comprehensively cover potential matching situations, providing users with a diverse range of choices and reducing the difficulty of decision-making.

[0025] The compensation amount for each candidate claim plan is calculated separately and the optimal claim plan is determined. Through precise calculation, users can clearly understand the expected compensation results of different plans, ensuring that users can obtain the maximum compensation rights in accordance with the policy terms, avoiding the loss of rights due to user's own decision-making errors, while simplifying the user's decision-making process and improving the rationality of the claim plan and user acceptance.

[0026] The system initiates the claims application process to the insurance business system based on the optimal claims settlement plan, realizing the automation of claims application initiation. Users are no longer required to manually connect to the insurance business system or repeatedly submit application materials, which reduces redundant intermediate steps, lowers the risk of operational errors in the application process, ensures the standardization and efficiency of the claims application process, and further shortens the overall claims settlement cycle.

[0027] In summary, the above steps are interconnected, forming a complete claims application chain from material submission, information processing, solution generation, optimal decision-making to application initiation. The entire process focuses on user convenience and rights protection, which not only greatly simplifies the user operation process and reduces user decision-making and operation costs, but also improves the efficiency and accuracy of claims applications through standardized and automated processing. This effectively addresses the pain points of the traditional claims model and significantly improves the user claims experience and the quality of insurance services.

[0028] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 A flowchart of an insurance claim application method provided in Embodiment 1 of this application is shown; Figure 2 The flowchart of a structured key information extraction method provided in Embodiment 1 of this application is shown; Figure 3 A flowchart of a method for determining an available insurance policy provided in Embodiment 1 of this application is shown; Figure 4 A flowchart of a method for generating candidate claims schemes provided in Embodiment 1 of this application is shown; Figure 5 A flowchart of a method for calculating pre-compensation amount provided in Embodiment 1 of this application is shown; Figure 6 A flowchart of a method for determining an optimal claims settlement plan provided in Embodiment 1 of this application is shown; Figure 7 A flowchart of an application process initiation method provided in Embodiment 1 of this application is shown; Figure 8 This paper illustrates the architecture and interaction diagram of an intelligent claims system provided in Embodiment 1 of this application; Figure 9 This paper shows a schematic diagram of the structure of an insurance claim application device provided in Embodiment 2 of this application; Figure 10 A schematic diagram of the structure of a computer device provided in Embodiment 3 of this application is shown. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0032] Example 1 To facilitate understanding of this application, the following is combined with... Figure 1 The flowchart illustrating an insurance claim application method provided in Embodiment 1 of this application will be described in detail for Embodiment 1 of this application.

[0033] See Figure 1 As shown, Figure 1 A flowchart of an insurance claim application method provided in Embodiment 1 of this application is shown, wherein the method includes steps S101 to S103: S101: Receive images of claim materials submitted by the user.

[0034] Specifically, the users are mainly employees (insured persons) under corporate group insurance policies. They need to initiate a claim application and upload pictures of claim documents (such as ID card, medical invoices, etc.) through this APP.

[0035] As one of the four core components of the intelligent claims system, the claims middle platform receives images uploaded by users and saves the data using persistent storage to ensure that subsequent information retrieval, intelligent calculation and other processes can be accessed at any time. This storage mechanism provides data security for the entire process automation.

[0036] S102: Extract structured key information related to the claim application from the image of the claim materials.

[0037] Specifically, this step is completed independently by the "information extraction agent," one of the two core intelligent agents. Its core objective is to address the pain point of "cumbersome claims process" that is not covered by existing technologies, and to achieve automated operation of "submission and entry" without requiring users to manually fill in information.

[0038] The information extraction agent uses deep learning technology and is trained through data analysis of a large number of claims materials images to improve recognition accuracy. It can meet the needs of basic classification and key information extraction. Currently, it supports the recognition of common claims materials such as ID cards, medical invoices, examination records, medical documents, and identity verification documents. It can also extract information such as expense details and medical insurance settlement categories from medical invoices.

[0039] The extraction process strictly follows the logic of "classification-extraction-verification-display": first, the image type is identified, then structured information is extracted according to preset fields. After extraction, the information is verified by the system (currently based on manual verification) and returned to the claims platform. The platform assembles the data and sends it back to the claims terminal APP, where it is automatically pre-filled on the application page. Currently, users can directly modify and correct the pre-filled information. In the future, a cross-validation mechanism will be added. If the extracted information is consistent with the user's historical data or information from multiple documents, no user confirmation is required. Manual verification will only be triggered when the information is inconsistent.

[0040] S103: Based on the structured key information, determine the user's coverage responsibilities and available policies, and generate several candidate claim settlement plans based on the coverage responsibilities and available policies.

[0041] Specifically, the coverage defined in this application focuses on medical expense reimbursement scenarios, mainly including supplemental medical outpatient services, supplemental medical inpatient services, medical funds, and accidental medical expenses. These types of coverage are the core basis for interpreting policy terms and generating claims solutions.

[0042] This step is led by another core intelligent agent, the "application decision intelligent agent," which accesses the core insurance business system through user identifiers (such as ID card numbers) in structured key information to query all available insurance policies under the user's name that are in a valid state.

[0043] The generation of candidate claim solutions is based on the "liability-policy" mapping relationship, covering all possible matching combinations: when a single liability corresponds to multiple policies, an independent matching item is generated for each policy; when multiple liabilities correspond to multiple policies, all permutations and combinations containing different liability claim orders are generated to ensure that no potential optimal solution is missed.

[0044] During the process of generating candidate solutions, the system will rigorously deconstruct the liability clauses of each policy to lay the foundation for subsequent dynamic planning and trial calculations, while avoiding invalid applications for duplicate claims in advance.

[0045] S104: Perform trial calculations on the compensation amount for each candidate claim plan to obtain the pre-compensation amount, and determine the optimal claim plan based on the pre-compensation amount of each candidate claim plan.

[0046] Specifically, the trial calculation process is executed precisely in two scenarios: when a single liability corresponds to multiple policies, the system automatically performs a claim trial calculation for each relevant policy according to the terms and conditions, and directly selects the policy with the highest payout under that liability as the sub-plan; when multiple liabilities correspond to multiple policies, the system first lists the complete set of all permutations and combinations of liabilities and policies (such as liabilities A and B with policies X and Y, generating combinations such as AX→BY and AY→BX), and then iteratively calculates according to the order of liabilities.

[0047] The core logic of iterative trial calculation is: first calculate the compensation amount for the preceding liability, deduct this part to get the remaining amount to be claimed, and then continue to calculate the subsequent liability based on the remaining amount and the policy terms (such as the compensation ratio and deductible). Since the order of claims will directly affect the final compensation amount (such as the difference in compensation rules between supplementary medical and health trust fund), dynamically updating the remaining amount can ensure the accuracy of the trial calculation results.

[0048] The determination of the optimal solution strictly follows the "dual objectives": the solution with the highest pre-payment amount is selected first to ensure that the user receives the theoretical maximum payout amount limited by the policy terms; if multiple solutions have the same pre-payment amount, the solution involving the fewest policies is selected to simplify the subsequent claims process and reduce the risk of disputes.

[0049] S105: Initiate a claim application process to the insurance business system based on the optimal claim settlement plan.

[0050] Specifically, after receiving the optimal solution, the claims processing platform submits claims applications to the core insurance business system in sequence according to the liability and policy order determined in the solution, realizing an automated closed loop of "solution determination - application initiation", which significantly improves the efficiency and accuracy of claims processing.

[0051] During the application process, the system automatically integrates structured key information, details of the optimal solution, and other data to generate standardized claims application data. The format is fully compatible with the receiving requirements of the insurance business system, avoiding application rejection due to data format issues and further improving the user experience.

[0052] In an optional implementation, see Figure 2 As shown, Figure 2 The flowchart illustrates a method for extracting structured key information according to Embodiment 1 of this application, wherein the step of extracting structured key information related to the claim application from the claim material image includes steps S201-S202: S201: Perform type recognition on the image of the claim materials to determine that it belongs to at least one of the following: medical invoice, expense list, examination report, medical record document or identity document.

[0053] Specifically, the identification operation is completed by the information extraction agent through a pre-trained model. The identification result directly determines the fields and rules for subsequent information extraction. For example, if it is identified as an ID card, fields such as name and ID number are extracted; if it is identified as a medical record, diagnostic information is extracted, etc., ensuring the targeting and efficiency of the extraction process.

[0054] The identification scope covers all common material types in current claims business, and can be expanded according to business needs in the future.

[0055] S202: Based on the identified image type, call the corresponding optical character recognition model or pre-trained deep learning model to locate and extract key information fields of a preset category from the image. When the image type is a medical invoice, the extracted key information fields include at least the payer's name, the total amount of medical expenses, the time of expense occurrence, and the name of the medical institution.

[0056] Specifically, different image types correspond to specific extraction fields: ID cards require extraction of name, ID number, and validity period; medical invoices require extraction of name, payment amount, payment time, and hospital (extraction of expense details and medical insurance settlement category is not currently supported, but will be implemented in the future); examination records and medical records require extraction of name, time, and diagnosis information, ensuring that the extracted information fully covers the core needs of the claim application.

[0057] The model selection follows the principle of "on-demand use": the optical character recognition model is used to accurately extract textual information (such as invoice amount and ID number), and the pre-trained deep learning model is used to recognize complex structural information (such as diagnosis conclusions in medical records). The two models are used in conjunction to ensure the extraction accuracy.

[0058] In an optional implementation, see Figure 3 As shown, Figure 3The flowchart illustrates a method for determining available insurance policies provided in Embodiment 1 of this application, wherein determining the user's coverage and available policies based on the structured key information includes steps S301-S303: S301: Obtain the user identifier from the structured key information.

[0059] Specifically, user identifiers are primarily obtained from structured information extracted from ID card images, typically the ID card number. This identifier is the sole core basis for linking all insurance policies under a user's name, ensuring that policy searches do not result in misattribution and providing an accurate user matching foundation for subsequent liability analysis and calculations.

[0060] The extraction and verification of user identifiers is a crucial step. The system will automatically check the identifier format (such as the number of digits in the ID card number and the check code). If the extracted identifier has a format error, the system will return to the APP to prompt the user to re-upload the ID card image to ensure the smooth progress of subsequent processes.

[0061] S302: Based on the user identifier, access the core insurance business system and query all available insurance policies that are in a valid state associated with the user identifier.

[0062] Specifically, the query operation is initiated by the application decision-making intelligent agent. Through real-time interaction with the core insurance business system, it filters out policies that are "within the coverage period, not terminated, and not invalid" and excludes invalid policies that have expired or been terminated, ensuring that the subsequent claims settlement plans are all based on legal and valid coverage.

[0063] The query results will be stored synchronously in the claims platform, which will facilitate the quick access to policy terms during subsequent calculations, reduce the system load caused by repeated queries, and improve the overall process efficiency.

[0064] S303: Analyze the insurance terms of each valid and available policy and extract the specific types of coverage provided by each available policy.

[0065] Specifically, the analysis process focuses on medical expense reimbursement clauses, accurately extracting types of coverage such as supplementary outpatient medical care, supplementary inpatient medical care, medical funds, and accidental medical care.

[0066] The analysis process uses "clause deconstruction" technology to break down complex policy clauses into standardized liability labels. For example, "outpatient medical expense reimbursement ratio 80%, deductible 100 yuan" is broken down into "supplementary medical outpatient - 80% - 100 yuan", providing a standardized calculation basis for subsequent intelligent calculation.

[0067] In an optional implementation, see Figure 4 As shown, Figure 4The flowchart illustrates a method for generating candidate claim schemes according to Embodiment 1 of this application, wherein the step of generating several candidate claim schemes based on the coverage and the available policies includes steps S401 to S404: S401: Establish a mapping relationship between the types of coverage and available policies.

[0068] Specifically, the mapping relationship is established based on the coverage liability label of each policy. For example, if policy X covers "supplementary medical outpatient" and "accidental medical", then two mappings are established: "supplementary medical outpatient - policy X" and "accidental medical - policy X" to ensure that the correspondence between liability and policy is complete and error-free.

[0069] The mapping relationships will be stored in the claims platform in tabular form. The format is clear and facilitates quick querying during subsequent combination generation and trial calculation. For example, "Coverage Liability Type - Available Policies": "Supplemental Medical Outpatient - Policy X, Y", "Supplemental Medical Inpatient - Policy X", "Accidental Medical - Policy Y, Z".

[0070] S402: Based on the mapping relationship, generate all possible combinations of protection liability-underwritten policy matching sequences.

[0071] Specifically, the generation process adopts the principle of "full coverage". For example, if liability A corresponds to policies X and Y, and liability B corresponds to policies X and Z, then all single liability-policy matching items such as AX, AY, BX, and BZ are generated. At the same time, it lays the foundation for multi-liability combinations and ensures that no potential high-payout combinations are missed.

[0072] The generation of the combined sequence is completed automatically by the application decision-making agent without human intervention, thus avoiding omissions or errors that may occur during manual combination.

[0073] S403: If the same coverage corresponds to multiple available policies, then generate an independent matching item for each policy.

[0074] Specifically, for example: if the "Supplemental Medical Outpatient" liability corresponds to Policy X (reimbursement ratio 80%, deductible 100 yuan) and Policy Y (reimbursement ratio 70%, deductible 50 yuan), then two independent matching items, "Supplemental Medical Outpatient - Policy X" and "Supplemental Medical Outpatient - Policy Y", will be generated respectively. Each matching item contains the complete terms and conditions of the policy, providing a basis for subsequent separate trial calculations.

[0075] This design ensures that different policies under the same liability have a fair chance to be calculated, avoiding being overlooked due to the large number of policies, and ensuring that every potential high-payout option can be discovered, maximizing the protection of users' rights.

[0076] S404: If multiple different coverage liabilities are involved, generate all permutations and combinations containing different liability claim sequences. Each complete liability matching sequence with the policy constitutes a candidate claim scheme.

[0077] Specifically, since the order of claims directly affects the final payout amount, for example, the result of paying "accidental medical expenses" first and then "supplementary medical outpatient expenses" may be different from that of paying "supplementary medical outpatient expenses" first and then "accidental medical expenses," it is necessary to generate all possible order combinations.

[0078] For example, if two liabilities are involved, namely "Accidental Medical Treatment" (corresponding to policies Y and Z) and "Supplemental Medical Outpatient Treatment" (corresponding to policies X and Y), then the generated permutations and combinations include all complete sequences such as "Accidental Medical Treatment - Policy Y → Supplemental Medical Outpatient Treatment - Policy X", "Accidental Medical Treatment - Policy Y → Supplemental Medical Outpatient Treatment - Policy Y", "Accidental Medical Treatment - Policy Z → Supplemental Medical Outpatient Treatment - Policy Y", and "Supplemental Medical Outpatient Treatment - Policy X → Accidental Medical Treatment - Policy Y". Each sequence is an independent candidate claim solution.

[0079] In an optional implementation, see Figure 5 As shown, Figure 5 The flowchart illustrates a method for calculating the pre-payment amount provided in Embodiment 1 of this application, wherein the step of performing trial calculations on the payment amount for each candidate claim plan to obtain the pre-payment amount includes steps S501-S502: S501: For each candidate claim scheme, based on the details and amount of medical expenses in the structured key information, and in accordance with the claim order determined in the candidate claim scheme, calculate the theoretical payout amount for each coverage liability under its corresponding policy.

[0080] Specifically, the calculation is based on structured information extracted from medical invoices, including detailed data such as total payment amount, co-payment 1, co-payment 2, and out-of-pocket expenses, to ensure the accuracy of the calculation basis. For example, if the total amount of the medical invoice is 5,000 yuan, co-payment 1 is 3,000 yuan, co-payment 2 is 1,000 yuan, and out-of-pocket expenses are 1,000 yuan, the corresponding expense items need to be calculated according to the policy terms during the trial calculation.

[0081] Example of iterative calculation: The candidate solution is "Accidental Medical Treatment - Policy Y → Supplemental Medical Outpatient Treatment - Policy X". Policy Y's terms are "Accidental Medical Treatment pays 90% of the co-payment, with no deductible". Policy X's terms are "Supplemental Medical Outpatient Treatment pays 80% of the remaining co-payment, with a deductible of 100 yuan". First, calculate the payout amount for Policy Y: 3000 × 90% = 2700 yuan. The remaining co-payment is 3000 - 2700 = 300 yuan. Then, calculate the payout amount for Policy X: (300 - 100) × 80% = 160 yuan. The theoretical payout amounts for the two liabilities are 2700 yuan and 160 yuan, respectively.

[0082] S502: Summarize the theoretical payout amounts of each coverage under the candidate claim plan under its corresponding policy to obtain the pre-payout amount of the candidate claim plan.

[0083] Specifically, the aggregation process strictly follows the principle of "no double reimbursement". The same medical expense (such as 3,000 yuan for out-of-pocket expenses) will not be calculated repeatedly under multiple liabilities or policies. Only the remaining unreimbursed portion will be calculated.

[0084] Taking the above example, the total pre-payment amount for the candidate plan is 2700 + 160 = 2860 yuan. The total result directly reflects the payout strength of the plan and is the core indicator for subsequent selection of the optimal plan.

[0085] In an optional implementation, see Figure 6 As shown, Figure 6 The flowchart illustrates a method for determining an optimal claims settlement plan according to Embodiment 1 of this application, wherein determining the optimal claims settlement plan based on the pre-payment amount of each candidate claims settlement plan includes steps S601 to S603: S601: Compare the prepayment amounts of all candidate claim options.

[0086] Specifically, the comparison process uses a "precise ranking" method, which arranges the pre-payment amounts of all candidate options from high to low. For example, candidate option 1 has a pre-payment of 2,860 yuan, candidate option 2 has a pre-payment of 2,750 yuan, and candidate option 3 has a pre-payment of 2,860 yuan. After ranking, option 1 = option 3 > option 2.

[0087] The comparison process is completed automatically by the application decision-making intelligent agent, which is fast and error-free, avoiding the mistakes that may occur in manual comparison and ensuring the accuracy of the screening results.

[0088] S602: The candidate claim settlement plan with the highest pre-payment amount is determined as the optimal claim settlement plan.

[0089] Specifically, the judgment criteria use an "intelligent decision engine based on protection liability" to ensure that users obtain the maximum benefits under the policy terms. For example, in the above example, Plan 1 and Plan 3 have the highest pre-payment amount (2,860 yuan) and are initially listed as the optimal plan candidates.

[0090] S603: If multiple candidate claim settlement options have the same pre-payment amount, the option involving the fewest policies shall be selected as the optimal claim settlement option.

[0091] Specifically, taking the above example, Option 1 is "Accidental Medical Treatment - Policy Y → Supplemental Medical Outpatient Treatment - Policy X" (involving 2 policies), and Option 3 is "Accidental Medical Treatment - Policy Y → Supplemental Medical Outpatient Treatment - Policy Y" (involving 1 policy). Option 3 is ultimately selected as the optimal claim solution because it involves fewer policies, which simplifies the subsequent review process and reduces the risk of claims disputes.

[0092] This supplementary rule balances user rights and process efficiency, improves the criteria for determining the optimal solution, and makes the solution selection more practical and operable.

[0093] In an optional implementation, see Figure 7 As shown, Figure 7 The flowchart of an application process initiation method provided in Embodiment 1 of this application is shown. After determining the optimal claim settlement plan based on the trial calculation results of the compensation amount for each candidate claim settlement plan, and before initiating the claim application process to the insurance business system based on the optimal claim settlement plan, the method further includes steps S701-S703: S701: Return the optimal claim settlement plan and its corresponding pre-payment amount to the user terminal for display.

[0094] Specifically, the platform for displaying the details is a claims terminal APP, which uses a visual interface to present the plan details, including key information such as the type of coverage, the corresponding policy, the claim order, the pre-payment amount, and the calculation basis (such as the reimbursement ratio and deductible). For example, it can display "Optimal Plan: Accidental Medical Treatment - Policy Y → Supplementary Medical Outpatient Treatment - Policy Y, Pre-payment Amount 2860 Yuan (Policy Y: Accidental Medical Treatment Reimbursement 2700 Yuan, Supplementary Medical Outpatient Treatment Reimbursement 160 Yuan)", which is convenient for users to understand quickly.

[0095] The interface design is simple and clear, catering to the usage habits of enterprise employees, allowing users to understand the solution details without professional knowledge, thus increasing user acceptance of the solution.

[0096] S702: Receive the user's confirmation or modification instruction for the optimal claims settlement plan.

[0097] Specifically, users can directly approve the plan through the "Confirm" button on the APP interface, or adjust the order of responsibilities and change the corresponding policy through the "Modify" entry (such as changing "Supplemental Medical Outpatient - Policy Y" in Plan 3 to "Supplemental Medical Outpatient - Policy X"). The system receives and responds to these operation instructions in real time.

[0098] This step empowers users with the right to choose, respecting their decision-making preferences while allowing for further optimization of the plan through user modifications. This avoids unreasonable plans due to system misjudgments and improves the plan's executability.

[0099] S703: If a user confirmation instruction is received, standardized claim application data is generated based on the confirmed optimal claim settlement plan and its corresponding structured key information, and an application process is initiated to the insurance business system.

[0100] Specifically, the standardized claims application data integrates core information such as user information (name, ID number), policy information (policy number, liability type), claim amount (total prepayment amount, itemized amount), and material information (extracted structured key information), and the format fully complies with the receiving requirements of the insurance business system.

[0101] After an application is submitted, the claims processing platform will track the application progress in real time and synchronize the progress to the APP, allowing users to check at any time, further improving the user experience and completing a fully intelligent service from "uploading materials - confirming the plan - submitting the application - tracking the progress".

[0102] To better explain the insurance claim application method provided in this application, please refer to [link / reference]. Figure 8 As shown, Figure 8 The diagram illustrates the architecture and interaction of an intelligent claims system provided in Embodiment 1 of this application. The diagram shows the core components involved in the intelligent claims process, and the two-way interaction relationship between the components is shown by arrows: the "claims terminal APP" and the "claims middle platform" can interact in two directions, and the "claims middle platform" can interact in two directions with the "core system", "application decision intelligent agent" and "information extraction intelligent agent" respectively, which intuitively reflects the collaborative relationship of each module in the intelligent claims process.

[0103] To better illustrate the insurance claim application method provided in this application, the following specific examples are also provided: Suppose that Mr. Zhang is an employee of Company A and is married. Company A has taken out policy Y for him (covering accidental medical expenses, with 90% reimbursement for out-of-pocket expenses and no deductible; it also covers supplementary outpatient medical expenses, with 80% reimbursement for the remaining out-of-pocket expenses and a deductible of 100 yuan). His spouse has taken out policy X (covering supplementary outpatient medical expenses, with 75% reimbursement for out-of-pocket expenses and no deductible) and policy Z (covering accidental medical expenses, with 85% reimbursement for out-of-pocket expenses and a deductible of 200 yuan) for him. In addition, Mr. Zhang can also enjoy the unified protection policy W (medical fund, which fully reimburses the expenses including out-of-pocket expenses and self-paid expenses, with a single reimbursement limit of 2,000 yuan).

[0104] After receiving medical treatment due to an accident, Mr. Zhang uploaded the medical invoice through the group's corporate portal APP. The information extraction AI extracted key information: the total amount was 5000 yuan, including 3000 yuan for out-of-pocket expenses, 1000 yuan for out-of-pocket expenses, and 1000 yuan for out-of-pocket expenses. The decision-making AI then retrieved four valid insurance policies under Mr. Zhang's name and identified the available policies for each coverage: accidental medical expenses correspond to policies Y and Z; supplementary outpatient medical expenses correspond to policies Y and X; and medical fund expenses correspond to policy W.

[0105] Based on the above correspondence, the system generates multiple candidate claim schemes, the core of which include: Accidental Medical Treatment - Policy Y → Supplemental Medical Outpatient Treatment - Policy X → Medical Fund - Policy W, Accidental Medical Treatment - Policy Z → Supplemental Medical Outpatient Treatment - Policy Y → Medical Fund - Policy W, Medical Fund - Policy W → Accidental Medical Treatment - Policy Y → Supplemental Medical Outpatient Treatment - Policy X, etc.

[0106] Based on the calculation of compensation amounts, the total pre-compensation amount for Plan 1 (Accidental Medical Insurance Y compensation of 2700 yuan, Supplementary Medical Insurance X compensation of 225 yuan, and Medical Fund W compensation of 2000 yuan) and Plan 3 (Medical Fund W compensation of 2000 yuan, Accidental Medical Insurance Y compensation of 2700 yuan, and Supplementary Medical Insurance X compensation of 225 yuan) is 4925 yuan, which is the highest amount; Plan 2 has a total pre-compensation of 4796 yuan, which is lower than the former two.

[0107] Ultimately, Option 1 was determined to be the optimal claim settlement option. After the APP showed the details to Mr. Zhang, he confirmed that everything was correct. The system then initiated the claim application in the order of "Accidental Medical Treatment Y → Supplementary Medical Treatment X → Medical Fund W", completing the entire intelligent claim settlement process.

[0108] Example 2 See Figure 9 As shown, Figure 9 This illustration shows a structural schematic diagram of an insurance claim application device provided in Embodiment 2 of this application, wherein the device includes: The claims material image receiving module 901 is used to receive images of claims materials submitted by the user; The structured key information extraction module 902 is used to extract structured key information related to the claim application from the image of the claim materials; The candidate claim solution generation module 903 is used to determine the user's coverage responsibilities and available policies based on the structured key information, and generate several candidate claim solutions based on the coverage responsibilities and available policies. The optimal claims settlement plan determination module 904 is used to perform trial calculations of the compensation amount for each candidate claims settlement plan to obtain the pre-compensation amount, and to determine the optimal claims settlement plan based on the pre-compensation amount of each candidate claims settlement plan; The claims application process initiation module 905 is used to initiate a claims application process to the insurance business system based on the optimal claims settlement plan.

[0109] In an optional implementation, the extraction of structured key information related to the claim application from the claim material image includes: The images of the claim materials are identified by type to determine whether they belong to at least one of the following: medical invoices, expense lists, examination reports, medical records, or identity documents. Based on the identified image type, the corresponding optical character recognition model or pre-trained deep learning model is invoked to locate and extract key information fields of the preset category from the image; When the image type is a medical invoice, the extracted key information fields include at least the payer's name, the total amount of medical expenses, the time the expenses occurred, and the name of the medical institution.

[0110] In an optional implementation, determining the user's coverage and available policies based on the structured key information includes: Obtain the user identifier from the structured key information; Based on the user identifier, access the core insurance business system and query all available insurance policies that are in a valid state associated with the user identifier; Analyze the insurance terms of each valid and usable policy to extract the specific types of coverage provided by each policy.

[0111] In an optional implementation, the generation of several candidate claim settlement plans based on the coverage and the available policies includes: Establish a mapping relationship between types of coverage and available insurance policies; Based on the mapping relationship, generate all possible combinations of coverage liability-underwritten policy matching sequences; If the same coverage applies to multiple available policies, then an independent matching item will be generated for each policy. If multiple different coverage liabilities are involved, all permutations and combinations containing different liability claim sequences are generated, and each complete liability matching sequence with the policy constitutes a candidate claim scheme.

[0112] In an optional implementation, the step of calculating the pre-payment amount for each candidate claim settlement plan includes: For each candidate claim plan, based on the details and amount of medical expenses in the structured key information, and in accordance with the claim order determined in the candidate claim plan, the theoretical payout amount for each coverage liability under its corresponding policy is calculated sequentially. The theoretical payout amounts for each coverage under the candidate claim plan are summarized under their corresponding policies to obtain the pre-payout amount for the candidate claim plan.

[0113] In an optional implementation, determining the optimal claim settlement plan based on the pre-payment amount of each candidate claim settlement plan includes: Compare the pre-payment amounts of all candidate claim options; The candidate claim settlement plan with the highest pre-payment amount is determined as the optimal claim settlement plan; If multiple candidate claim settlement options have the same pre-payment amount, the option involving the fewest policies will be selected as the optimal claim settlement option.

[0114] In an optional implementation, the apparatus further includes an application process initiation module for: After determining the optimal claim settlement plan based on the trial calculation results of the compensation amount of each candidate claim settlement plan, and before initiating the claim application process to the insurance business system based on the optimal claim settlement plan, the optimal claim settlement plan and its corresponding pre-payment amount are returned to the user terminal for display. Receive user confirmation or modification instructions for the optimal claims settlement plan; If a user confirmation instruction is received, standardized claim application data is generated based on the confirmed optimal claim settlement plan and its corresponding structured key information, and an application process is initiated to the insurance business system.

[0115] Example 3 Based on the same application concept, see [link / reference] Figure 10 As shown, Figure 10 This illustration shows a structural schematic diagram of a computer device provided in Embodiment 3 of this application, wherein, as shown... Figure 10 As shown, the computer device 1000 provided in Embodiment 3 of this application includes: The computer device 1000 includes a processor 1001, a memory 1002, and a bus 1003. The memory 1002 stores machine-readable instructions that can be executed by the processor 1001. When the computer device 1000 is running, the processor 1001 and the memory 1002 communicate through the bus 1003. When the machine-readable instructions are executed by the processor 1001, they perform the steps of the insurance claim application method shown in Embodiment 1 above.

[0116] Example 4 Based on the same concept, this application also provides a computer-readable storage medium storing a computer program, which, when run by a processor, performs the steps of the insurance claim application method described in any of the above embodiments.

[0117] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0118] The computer program product for making insurance claims provided in this application includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0119] The insurance claim application device provided in this application embodiment can be specific hardware on a device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0120] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0121] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] In addition, the functional units in the embodiments provided in 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.

[0123] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they 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 a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0124] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0125] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, 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. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for filing an insurance claim, characterized in that, The method includes: Receive images of claim materials submitted by users; Extract structured key information related to the claim application from the images of the claim materials; Based on the structured key information, the user's coverage responsibilities and available policies are determined, and several candidate claim settlement plans are generated based on the coverage responsibilities and available policies. The pre-payment amount is calculated for each candidate claim plan, and the optimal claim plan is determined based on the pre-payment amount of each candidate claim plan. Based on the optimal claims settlement plan, a claims application process is initiated with the insurance business system.

2. The method according to claim 1, characterized in that, The extraction of structured key information related to the claim application from the image of the claim materials includes: The images of the claim materials are identified by type to determine whether they belong to at least one of the following: medical invoices, expense lists, examination reports, medical records, or identity documents. Based on the identified image type, the corresponding optical character recognition model or pre-trained deep learning model is invoked to locate and extract key information fields of the preset category from the image; When the image type is a medical invoice, the extracted key information fields include at least the payer's name, the total amount of medical expenses, the time the expenses occurred, and the name of the medical institution.

3. The method according to claim 1, characterized in that, The process of determining the user's coverage and available policies based on the structured key information includes: Obtain the user identifier from the structured key information; Based on the user identifier, access the core insurance business system and query all available insurance policies that are in a valid state associated with the user identifier; Analyze the insurance terms of each valid and usable policy to extract the specific types of coverage provided by each policy.

4. The method according to claim 1, characterized in that, The generation of several candidate claim settlement plans based on the coverage and available policies includes: Establish a mapping relationship between types of coverage and available insurance policies; Based on the mapping relationship, generate all possible combinations of coverage liability-underwritten policy matching sequences; If the same coverage applies to multiple available policies, then an independent matching item will be generated for each policy. If multiple different coverage liabilities are involved, all permutations and combinations containing different liability claim sequences are generated, and each complete liability matching sequence with the policy constitutes a candidate claim scheme.

5. The method according to claim 1, characterized in that, The preliminary compensation amount is obtained by performing trial calculations on the compensation amount for each candidate compensation plan, including: For each candidate claim plan, based on the details and amount of medical expenses in the structured key information, and in accordance with the claim order determined in the candidate claim plan, the theoretical payout amount for each coverage liability under its corresponding policy is calculated sequentially. The theoretical payout amounts for each coverage under the candidate claim plan are summarized under their corresponding policies to obtain the pre-payout amount for the candidate claim plan.

6. The method according to claim 1, characterized in that, The process of determining the optimal claim settlement plan based on the pre-payment amount of each candidate claim settlement plan includes: Compare the pre-payment amounts of all candidate claim options; The candidate claim settlement plan with the highest pre-payment amount is determined as the optimal claim settlement plan; If multiple candidate claim settlement options have the same pre-payment amount, the option involving the fewest policies will be selected as the optimal claim settlement option.

7. The method according to claim 1, characterized in that, After determining the optimal claim settlement plan based on the trial calculation results of the compensation amount for each candidate claim settlement plan, and before initiating the claim application process to the insurance business system based on the optimal claim settlement plan, the method further includes: The optimal claims settlement plan and its corresponding pre-payment amount will be returned to the user's terminal for display. Receive user confirmation or modification instructions for the optimal claims settlement plan; If a user confirmation instruction is received, standardized claim application data is generated based on the confirmed optimal claim settlement plan and its corresponding structured key information, and an application process is initiated to the insurance business system.

8. An insurance claim application device, characterized in that, The device includes: The claims document image receiving module is used to receive images of claims documents submitted by users. The structured key information extraction module is used to extract structured key information related to the claim application from the image of the claim materials; The candidate claim solution generation module is used to determine the user's coverage responsibilities and available policies based on the structured key information, and to generate several candidate claim solutions based on the coverage responsibilities and available policies. The optimal claims settlement plan determination module is used to calculate the pre-payment amount for each candidate claims settlement plan and determine the optimal claims settlement plan based on the pre-payment amount of each candidate claims settlement plan. The claims application process initiation module is used to initiate a claims application process to the insurance business system based on the optimal claims settlement plan.

9. A computer device, characterized in that, include: The computer device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the insurance claim application method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the insurance claim application method as described in any one of claims 1 to 7.

Images