Scheme generation method and device, equipment and medium

Abstract

The invention belongs to the field of artificial intelligence, and relates to a scheme generation method, comprising: receiving payment request data of a target object transmitted by a medical institution, the payment request data comprising diagnosis and treatment data, insurance data and staging intention data; based on the diagnosis and treatment data and the insurance data, determining a target cost and an insurance direct payment amount of the target object; obtaining user information of the target object, and determining a risk score of the target object and an optimization parameter of a payment combination based on the user information and the staging intention data; according to the risk score and the optimization parameter, adopting a multi-target constraint optimization algorithm to generate a payment combination scheme of the target object; judging whether the payment combination scheme accords with a preset payment capability threshold value of the target object or not; and if yes, outputting a payment combination scheme to a medical institution. The invention further provides a device, equipment and a medium. The method can be applied to the business fields of financial insurance, medical treatment and the like, and efficient medical payment processing can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and is applied to online processing business scenarios such as finance and insurance, medical treatment, and the like, and in particular relates to a scheme generation method and device, equipment and a medium. BACKGROUND

[0002] In the current medical payment system, there are many technical pain points that need to be solved, which seriously affect the efficiency and user experience of medical payment.

[0003] First, at the process and data level, there is a clear split and island phenomenon. When making a large medical payment, the patient needs to face two independent processes of applying for installment loans (or using credit cards) by financial institutions and submitting claim materials by insurance companies. Due to the lack of data interconnection between hospitals, insurance companies and financial institutions, the patient has to repeatedly submit a series of materials such as ID cards, medical records, insurance policies, income certificates, etc., which is cumbersome and prone to errors. The insurance company adopts a post-reimbursement mode, and the patient needs to pay the full medical expenses in advance and then go through a long audit process of several days to several weeks, which is a huge financial pressure, especially for low-income or people with sudden serious illness. Due to the lack of real-time and accurate medical scene data, the financial institution mainly relies on traditional credit investigation and income proof for risk control, and it is difficult to dynamically assess the rationality of medical expenses and the relevance to the user's repayment ability, resulting in overly conservative approval or high risk.

[0004] Secondly, there is a serious lack of timeliness and user experience. High medical expenses require patients to pre-fund, which may delay treatment opportunities. Installment approval and insurance claim are independent, which takes a long time, making it difficult for users to turn over funds. At the same time, users need to communicate and coordinate with hospitals, insurance companies and financial institutions, which is costly.

[0005] In addition, the existing "direct payment" service has obvious limitations. Some high-end insurance or specific scenarios (such as dentistry and physical examination) have direct payment services, but they are limited to insurance coverage and do not integrate installment functions. Patients still need to fund themselves for amounts exceeding the insurance coverage, deductibles or non-covered items. The existing direct payment system is mostly point-to-point connection between insurance companies and a single or small number of hospitals, which has a narrow coverage and poor scalability, making it difficult to support complex "insurance + installment" combined payment, and lacking a unified platform and deep collaboration mechanism, which cannot realize one-stop and real-time processing of insurance liability, user installment willingness, financial institution risk control and hospital settlement demand. SUMMARY

[0006] The purpose of the embodiments of the present application is to propose a scheme generation method, device, computer equipment and storage medium to solve the problems of process fragmentation, data island and poor timeliness in the existing medical payment system.

[0007] In a first aspect, a scheme generation method is provided, which adopts the following technical solution:

[0008] The payment request data of the target object transmitted by the medical institution is received, the payment request data including diagnosis and treatment data, insurance data, and installment intention data; the target fee and the insurance direct payment amount of the target object are determined based on the diagnosis and treatment data and the insurance data; the user information of the target object is obtained, and the risk score and the optimization parameter of the payment combination of the target object are determined based on the user information and the installment intention data; the payment combination scheme of the target object is generated by using a preset multi-objective constraint optimization algorithm according to the risk score and the optimization parameter; it is judged whether the payment combination scheme meets the preset payment ability threshold of the target object; if the payment combination scheme meets the preset payment ability threshold of the target object, the payment combination scheme is output to the medical institution.

[0009] In a second aspect, a scheme generation device is provided, which adopts the following technical solution:

[0010] The receiving module is configured to receive payment request data of a target object transmitted by a medical institution, the payment request data including diagnosis and treatment data, insurance data, and installment intention data;

[0011] The first determining module is configured to determine the target fee and the insurance direct payment amount of the target object based on the diagnosis and treatment data and the insurance data;

[0012] The second determining module is configured to obtain user information of the target object, and determine the risk score and the optimization parameter of the payment combination of the target object based on the user information and the installment intention data;

[0013] The generating module is configured to generate the payment combination scheme of the target object by using a preset multi-objective constraint optimization algorithm according to the risk score and the optimization parameter;

[0014] The judging module is configured to judge whether the payment combination scheme meets the preset payment ability threshold of the target object;

[0015] The output module is configured to output the payment combination scheme to the medical institution if the payment combination scheme meets the preset payment ability threshold of the target object.

[0016] In a third aspect, a computer device is provided, which adopts the following technical solution:

[0017] The payment request data of the target object transmitted by the medical institution is received, the payment request data including diagnosis and treatment data, insurance data and installment intention data; the target fee and the insurance direct payment amount of the target object are determined based on the diagnosis and treatment data and the insurance data; the user information of the target object is acquired, and the risk score and the optimization parameter of the payment combination of the target object are determined based on the user information and the installment intention data; the payment combination scheme of the target object is generated by using a preset multi-objective constraint optimization algorithm according to the risk score and the optimization parameter; whether the payment combination scheme meets the preset payment ability threshold of the target object is judged; and if the payment combination scheme meets the preset payment ability threshold of the target object, the payment combination scheme is output to the medical institution.

[0018] In a fourth aspect, a computer-readable storage medium is provided, and the following technical solutions are adopted:

[0019] The payment request data of the target object transmitted by the medical institution is received, the payment request data including diagnosis and treatment data, insurance data and installment intention data; the target fee and the insurance direct payment amount of the target object are determined based on the diagnosis and treatment data and the insurance data; the user information of the target object is acquired, and the risk score and the optimization parameter of the payment combination of the target object are determined based on the user information and the installment intention data; the payment combination scheme of the target object is generated by using a preset multi-objective constraint optimization algorithm according to the risk score and the optimization parameter; whether the payment combination scheme meets the preset payment ability threshold of the target object is judged; and if the payment combination scheme meets the preset payment ability threshold of the target object, the payment combination scheme is output to the medical institution.

[0020] Compared with the prior art, the embodiments of the present application have the following beneficial effects: by receiving the payment request containing diagnosis and treatment, insurance and installment intention data, breaking the data island, realizing data integration and avoiding the target object repeatedly submitting materials. The target fee and the direct payment amount are determined based on the diagnosis and treatment and the insurance data, the risk score and the optimization parameter are determined in combination with the user information and the installment intention, and the multi-objective constraint optimization algorithm is used to generate the payment combination scheme, which changes the mode of traditional financial institutions relying on limited data for risk control and approval. The rationality of the medical expenses and the user's repayment ability can be dynamically evaluated, the risk is reduced, and the approval is more reasonable. Whether the scheme meets the preset payment ability threshold is judged and output, which can one-stop real-time process the needs of insurance liability, user installment intention and the like, shorten the installment approval and insurance claim time, reduce the patient's pre-funding pressure, reduce the communication cost, improve the settlement efficiency, realize one-stop, real-time and efficient medical payment processing. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the scheme in the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is an exemplary system architecture diagram to which the present application can be applied;

[0023] Figure 2 Flow chart of an embodiment of the scheme generation method according to the present application;

[0024] Figure 3 is a structural schematic diagram of an embodiment of the scheme generation device according to the present application;

[0025] Figure 4 is a structural schematic diagram of an embodiment of the computer device according to the present application. DETAILED DESCRIPTION

[0026] 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 the present application belongs; the terms used herein in the specification and claims of the present application and the above description of drawings are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "comprise" and "have" and any variations thereof in the specification and claims of the present application and the above description of drawings are intended to cover non-exclusive inclusion. The terms "first", "second" and the like in the specification and claims of the present application and the above description of drawings are used to distinguish different objects, not to describe a specific order.

[0027] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily mutually exclusive of other embodiments. It is explicitly and implicitly understood that the embodiments described herein can be combined with other embodiments.

[0028] In order to enable those skilled in the art to better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings.

[0029] As Figure 1As shown, the system architecture 100 can include a terminal device 101, a network 102 and a server 103. The terminal device 101 can be a notebook computer 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103. The network 102 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0030] A user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0031] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing, in addition to the notebook computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer and a desktop computer, etc.

[0032] The server 103 can be a server providing various services, such as a background server supporting a page displayed on the terminal device 101.

[0033] It should be noted that the scheme generation method provided by the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the scheme generation apparatus is generally provided in a server / terminal device.

[0034] It should be understood that Figure 1 The number of terminal devices, networks and servers in

[0035] With reference to Figure 2 , a flowchart of one embodiment of the scheme generation method according to the present application is shown. The scheme generation method includes the following steps:

[0036] Step S201, receiving payment request data of a target object transmitted by a medical institution, the payment request data including diagnosis and treatment data, insurance data and installment intention data.

[0037] The medical institution refers to an institution with professional medical qualifications that can provide various medical services for patients, covering disease diagnosis, treatment, nursing, etc. Such as hospitals, clinics, etc. For generating and transmitting data related to patient diagnosis and treatment.

[0038] The target object refers to a patient individual who receives medical services and generates medical payment needs. For the object around which the payment process is clear.

[0039] The payment request data is transmitted by the medical institution, and contains a set of data that contains the key information required by the target object in the medical payment process. For triggering subsequent payment processing steps.

[0040] The diagnosis and treatment data is part of the payment request data, which records the detailed information of the target object during the diagnosis and treatment in the medical institution. For accurate calculation of target cost. For example, patient medical records, test reports, prescription information, etc. are all diagnosis and treatment data.

[0041] The insurance data is also a component of the payment request data, which contains information related to the insurance purchased by the target object. For determining the insurance direct payment amount. Through insurance data, you can know the coverage, amount, deductible, etc. of the insurance. For example, patient insurance information, insurance claim records, etc. are insurance data.

[0042] The installment intention data is information in the payment request data that reflects the target object's willingness and demand for installment payment of medical expenses. It represents the target object's selection tendency in payment methods, and is used to determine the risk score and optimization parameters of the payment combination in combination with user information.

[0043] Step S202, based on the diagnosis and treatment data and the insurance data, determine the target cost and the insurance direct payment amount of the target object.

[0044] The target cost is the total medical cost that the target object needs to pay based on the diagnosis and treatment data and the insurance data. It represents the amount of fees that the target object needs to bear finally after considering insurance reimbursement, and is used to generate a payment combination scheme subsequently.

[0045] The insurance direct payment amount is the amount of fees that the target object needs to pay directly to the medical institution by the insurance company in the medical payment process according to the insurance data. It represents the part of the cost that the insurance company bears in the medical payment process, and is used to clarify the amount of money that the patient does not need to pay by himself but is directly settled by the insurance.

[0046] Step S203, obtain the user information of the target object, and determine the risk score of the target object and the optimization parameters of the payment combination based on the user information and the installment intention data.

[0047] The user information is personal information about the target object, including but not limited to identity information, credit information, income situation, etc., and the source is the information provided by the patient, recorded by the medical institution, and obtained through legal channels. It represents the personal characteristics and credit status of the target object, and is used to determine the risk score and optimize the parameters of the payment combination in combination with the installment intention data.

[0048] The risk score is a numerical value reflecting the risk level of the target object in medical expense installment payment, calculated based on user information and installment intention data through a specific evaluation model.

[0049] The payment combination refers to a set of schemes provided for the target object, including multiple payment methods and payment arrangements. It represents different payment options that meet the medical payment needs of the target object, and is used for the target object to choose the appropriate payment method according to their own situation.

[0050] The optimization parameter is a parameter used to adjust and optimize the payment combination scheme in the process of determining the payment combination. It represents the key factors that affect the generation and adjustment of the payment combination scheme, and is used to make the generated payment combination scheme more in line with the needs and actual situation of the target object.

[0051] Step S204, according to the risk score and optimization parameter, a preset multi-objective constraint optimization algorithm is used to generate the payment combination scheme of the target object.

[0052] The multi-objective constraint optimization algorithm is a mathematical algorithm used to find the optimal solution under multiple objectives and constraints. It represents a method that can consider the payment ability of the target object, the risk control of the financial institution, the settlement needs of the hospital, and other multiple objectives, and generate the optimal payment combination scheme under certain constraints.

[0053] The payment combination scheme is a specific payment arrangement generated according to the risk score and optimization parameter using the multi-objective constraint optimization algorithm. It represents a medical expense payment plan tailored for the target object, and is used to guide the target object to make medical payments. The payment combination scheme specifies detailed information such as payment method, payment amount, and payment time.

[0054] Step S205, determine whether the payment combination scheme meets the preset payment ability threshold of the target object.

[0055] The preset payment ability threshold is a standard value preset to measure whether the payment ability of the target object can withstand the payment combination scheme. It can be determined according to the user information, income situation, and general payment ability evaluation rules of the target object. It represents an important basis for determining whether the payment combination scheme is suitable for the target object, and is used to ensure that the generated payment combination scheme does not bring excessive payment pressure to the target object.

[0056] In step S206, if the payment combination scheme meets the preset payment ability threshold of the target object, the payment combination scheme is output to the medical institution.

[0057] In an example, the following is described in detail taking a patient with heart disease who needs to undergo a heart stent implantation surgery as an example. After the medical institution receives the patient, the patient is taken as a target object, and payment request data is transmitted. Among them, the diagnosis and treatment data shows that the surgery cost is 80,000 yuan, including stent cost, surgery operation cost, etc. The insurance data shows that the patient has purchased commercial medical insurance, with a coverage of 60,000 yuan and a deductible of 10,000 yuan. The installment intention data shows that the patient hopes to make installment payment. Based on the diagnosis and treatment data and the insurance data, the system determines that the target cost is 80,000 yuan, and the insurance direct payment amount is 50,000 yuan (60,000 yuan coverage minus 10,000 yuan deductible). Then the user information of the target object is obtained, the patient has a monthly income of 8,000 yuan and a good credit record. In combination with the installment intention data, the system determines the risk score. Considering that the patient's income is stable and the credit is good, the risk score is low. At the same time, the optimization parameters of the payment combination are determined, such as setting the installment handling fee rate to a low level, and setting the repayment period range to 6-24 months. According to the risk score and the optimization parameters, a payment combination scheme is generated by using a preset multi-objective constraint optimization algorithm. Scheme one is that the patient pays 30,000 yuan (80,000 target cost-50,000 insurance direct payment amount) first, and the remaining 30,000 yuan is divided into 12 installments, with a monthly repayment of 2,500 yuan; scheme two is to pay 20,000 yuan first, and the remaining 40,000 yuan is divided into 18 installments, with a monthly repayment of about 2,222 yuan. It is judged whether the two payment combination schemes meet the patient's preset payment ability threshold. Assuming that the patient presets that the monthly repayment does not exceed 30% of the income, that is, 2,400 yuan. The monthly repayment of scheme one is 2,500 yuan, which exceeds the threshold, and scheme two meets the threshold. Therefore, the system outputs scheme two to the medical institution, and the medical institution can settle the cost and payment arrangement with the patient according to the scheme, realizing one-stop, real-time processing of insurance liability, user installment intention, financial institution risk control, and hospital settlement demand.

[0058] The embodiments of the present application can break the data island by receiving payment requests containing diagnosis and treatment, insurance and installment intention data, realize data integration, and avoid the target object from repeatedly submitting materials. The target cost and direct payment amount are determined based on the diagnosis and treatment and insurance data, the risk score and optimization parameters are determined in combination with the user information and installment intention, and the payment combination scheme is generated by using a multi-objective constraint optimization algorithm, which changes the traditional mode of financial institutions relying on limited data for risk control and approval. The rationality of medical expenses and the user's repayment ability can be dynamically evaluated, the risk is reduced, and the approval is more reasonable. The scheme is judged whether it meets the preset payment ability threshold and is output, which can one-stop real-time process the insurance liability, user installment intention and other demands, shorten the installment approval and insurance claim time, reduce the patient's pre-funding pressure, reduce the communication cost, improve the settlement efficiency, and realize one-stop, real-time and efficient medical payment processing.

[0059] In some optional implementations of the embodiment, step 202 of determining the target fee and the insurance direct payment amount of the target object based on the diagnosis and treatment data and the insurance data specifically includes the following steps:

[0060] Using a preset fee verification model, the diagnosis and treatment data and the insurance data are subjected to fee verification to determine the target medical fee of the target object; using a preset insurance liability matching model, the target medical fee is analyzed to screen out the medical fee part covered by the insurance and determine the insurance direct payment amount.

[0061] The fee verification model is a mathematical or logical model based on preset rules and algorithms, used for verifying the accuracy and reasonableness of medical payment related fee data. It is used to ensure the accuracy of the calculation of the target medical fee of the target object. For example, if the diagnosis and treatment data shows that the cost of a certain examination item is significantly higher than the average standard cost of the same item in the region, the fee verification model will mark this anomaly and further verify it to ensure that the final determined target medical fee is true and reliable.

[0062] The fee verification refers to the process of checking, comparing and verifying the diagnosis and treatment data and the insurance data transmitted by the medical institution using the fee verification model. It represents the evaluation behavior of the accuracy and reasonableness of the medical fee data, and is used to determine the target medical fee of the target object.

[0063] The insurance liability matching model is a specially designed model used to match and correspond the target medical fee with the liability clauses in the insurance contract. It is used to screen out the medical fee part covered by the insurance and determine the insurance direct payment amount.

[0064] The analysis refers to the process of in-depth research, disassembly and judgment of the target medical fee using the insurance liability matching model. It represents the detailed exploration behavior of the relationship between the medical fee and the insurance liability, and is used to screen out the medical fee part covered by the insurance.

[0065] The medical fee part refers to the specific fee categories of the target medical fee divided according to different attributes or bearing subjects. It represents the subdivision of the target medical fee, and is used to clarify the attribution and payment method of each item of fee.

[0066] In an example, a patient who has purchased high-end commercial medical insurance and needs to undergo a heart bypass surgery is taken as an example. The medical institution transmits the payment request data of the patient to the system, wherein the diagnosis and treatment data shows that the total cost of the surgery is 250,000 yuan, including surgery cost, equipment cost, drug cost, etc. The insurance data shows that the insurance amount is 200,000 yuan, with a 10,000 yuan deductible, and part of the imported equipment is not within the scope of reimbursement. The system uses a preset cost verification model to compare each cost in the diagnosis and treatment data with the local medical charging standard and the historical cost of the same type of surgery in the hospital, and combines the reimbursement rules in the insurance data to verify the reasonableness of the cost. After verification, it is determined that the target medical cost is 250,000 yuan. Then, a preset insurance liability matching model is used to analyze the target medical cost. According to the insurance contract terms, the model identifies that the imported equipment cost of 50,000 yuan is not within the insurance coverage, and after deducting the deductible of 10,000 yuan, it selects the medical cost covered by the insurance of 140,000 yuan, and determines the insurance direct payment amount of 140,000 yuan. In the traditional mode, the patient needs to pay 250,000 yuan in full, and then submit materials to the insurance company for claim, which is a long process and has a large financial pressure. The scheme of the present application quickly and accurately determines the insurance direct payment amount through the cost verification model and the insurance liability matching model, so that the patient only needs to pay the remaining 110,000 yuan, reduces the financial pressure, avoids the problem of repeated submission of materials due to the lack of data interconnection, and improves the payment efficiency.

[0067] The embodiments of the present application can verify the diagnosis and treatment data and the insurance data through the cost verification model, accurately determine the target medical cost, effectively solve the problem that the financial institution is difficult to verify the authenticity of the medical behavior and the reasonableness of the cost due to information asymmetry, and avoid fraud risks such as false medical treatment, excessive medical treatment and fund extraction. At the same time, the traditional risk control relying on static data is changed, and dynamic evaluation is realized according to real-time diagnosis and treatment data. The insurance liability matching model analyzes the target medical cost, quickly selects the insurance coverage part and determines the direct payment amount, improves the insurance company's audit efficiency, can intercept suspicious claims in real time, and reduces the insurance fraud risk. In addition, the two models work together to avoid the complex financial reconciliation of the hospital settlement with the patient and the insurance company, shorten the collection cycle, reduce the dependence of inter-institution settlement on manual reconciliation and traditional payment channels, reduce costs, improve speed and reduce error rate, and greatly optimize the medical payment process.

[0068] In some optional implementation manners, step S203 comprises the following steps of:

[0069] Based on the user information and the installment intention data, a preset credit evaluation model is used to evaluate the credit of the target object, to obtain the credit score and installment amount of the target object; based on the credit score, installment amount and insurance direct payment amount, a preset risk evaluation model is used to analyze the relevance between the diagnosis and treatment data, insurance data and installment intention data, to determine the risk score of the target object and the optimization parameters of the payment combination.

[0070] The credit evaluation model is a mathematical model for quantitatively evaluating the credit status of the target object based on a large amount of historical data and advanced algorithms. The model represents the likelihood of the target object fulfilling the repayment obligation on time in financial transactions, and reflects the credit level by comprehensively considering various factors.

[0071] The credit evaluation refers to the process of using a specific credit evaluation model to comprehensively analyze and evaluate the credit-related information of the target object. It represents the comprehensive judgment of the credit reliability and debt repayment ability of the target object, and through quantitative analysis of various credit indicators, an evaluation result reflecting the credit status is obtained.

[0072] The credit score is a quantitative value obtained in the credit evaluation process, which is used to intuitively represent the credit level of the target object.

[0073] The installment amount refers to the maximum amount of installment consumption or payment within a certain period approved by the financial institution based on the credit evaluation result of the target object.

[0074] The risk evaluation model is a tool specifically used to analyze and evaluate the risk degree and type that the target object may face in a specific business scenario. It represents the comprehensive influence degree of various risk factors in the business operation process of the target object, and can quantify the risk size and identify the main risk points.

[0075] The relevance refers to the mutual connection and influence relationship between the diagnosis and treatment data, insurance data and installment intention data. It is used for the risk evaluation model to analyze the complex relationship between the data, so as to determine the risk score of the target object and the optimization parameters of the payment combination.

[0076] In an example, a patient needs to undergo a heart stent implantation surgery due to heart disease. The medical institution transmits the payment request data of the patient to the system, wherein the diagnosis and treatment data shows that the total cost of the surgery is 80,000 yuan, the insurance data shows that the patient's purchased insurance can cover 50,000 yuan of medical expenses, that is, the insurance direct payment amount is 50,000 yuan, and the patient expresses the intention to pay the remaining 30,000 yuan by installment. The system obtains the user information of the patient, including age 45, monthly income 12,000 yuan, no bad credit record, etc. Based on these user information and installment intention data, a preset credit evaluation model is used for credit evaluation. The model considers factors such as income stability and credit history, and obtains a credit score of 750 points (out of 900 points) for the patient. According to the rules set in the model, the patient is given a installment limit of 40,000 yuan. Then, based on the credit score of 750 points, the installment limit of 40,000 yuan, and the insurance direct payment amount of 50,000 yuan, a preset risk assessment model is used to analyze the relevance between the diagnosis and treatment data, the insurance data, and the installment intention data. Considering that the cost of heart surgery is high and there may be subsequent rehabilitation costs, combined with the patient's income, it is analyzed that the patient has certain repayment ability, but there is a certain risk of fund turnover. After model calculation, it is determined that the risk score of the patient is medium, and the optimization parameter of the payment combination is to divide 30,000 yuan into 12 installments, with a repayment of 2,500 yuan per installment. This payment combination takes into account the patient's repayment ability, combined with the characteristics of medical expenses and insurance coverage, and achieves a reasonable balance between risk and payment, and finally outputs the payment combination scheme to the medical institution.

[0077] The embodiments of the present application can use a preset credit evaluation model to evaluate credit based on user information and installment intention data, which can comprehensively consider various aspects of the user and accurately obtain a credit score and installment limit. This enables financial institutions to break free from the limitations of traditional credit investigation and income proof, and more dynamically and comprehensively assess user credit. Then, based on the credit score, installment limit, and insurance direct payment amount, a preset risk assessment model is used to analyze the relevance between diagnosis and treatment, insurance data, and installment intention data, which can deeply understand the risk status of the user in the entire medical payment scenario. Not only can the risk score be determined, but also the optimization parameter of the payment combination can be obtained, effectively solving the problem that financial institutions cannot accurately assess risks due to the lack of real-time medical scenario data.

[0078] In some optional implementations, the step of "based on the credit score, the installment limit, and the insurance direct payment amount, using a preset risk assessment model to analyze the relevance between the diagnosis and treatment data, the insurance data, and the installment intention data, and determining the risk score of the target object and the optimization parameter of the payment combination" specifically includes the following steps:

[0079] extracting a cost structure feature in the diagnosis and treatment data, a liability coverage feature in the insurance data, and a repayment ability feature in the installment intention data; inputting the cost structure feature, the liability coverage feature, the repayment ability feature, a credit score, an installment limit, and an insurance direct payment amount into a preset risk assessment model to generate a multi-dimensional risk assessment matrix; calculating a risk score of the target object according to the multi-dimensional risk assessment matrix, and determining an optimization parameter of a payment combination in combination with the risk score.

[0080] The cost structure feature is extracted from the diagnosis and treatment data, which represents the distribution and composition of the medical expenses of the target object in different items. Through detailed analysis of each item of expenses in the diagnosis and treatment data, such as drug expenses, examination expenses, surgery expenses, and bed expenses, a series of data indicators are obtained by summarizing according to the dimensions of expense types and proportions.

[0081] The liability coverage feature is derived from the insurance data, which represents the coverage range and degree of insurance for the medical expenses of the target object. Through analysis and extraction of key information such as insurance contract terms, guarantee items, deductible, and reimbursement ratio, a data set is formed that can reflect the specific coverage of insurance liability.

[0082] The repayment ability feature is extracted from the installment intention data, which represents the ability of the target object to repay installment payments on time in the medical expense installment payment scenario. Through comprehensive analysis and quantitative evaluation of relevant information such as the income level, income stability, debt situation, and asset condition of the target object, a series of indicators are obtained.

[0083] The multi-dimensional risk assessment matrix is a comprehensive data structure generated by inputting various data such as the cost structure feature, the liability coverage feature, the repayment ability feature, the credit score, the installment limit, and the insurance direct payment amount into a preset risk assessment model.

[0084] In an example, a patient needs surgery for a fracture. The medical institution transmits payment request data of the patient to the system, wherein the diagnosis and treatment data shows that the total surgery cost is 20,000 yuan, including surgery cost 12,000 yuan, drug cost 5,000 yuan, and examination cost 3,000 yuan, from which the cost structure feature is extracted, such as surgery cost proportion 60%, drug cost proportion 25%, and examination cost proportion 15%. The insurance data shows that the patient's purchased insurance reimburses 80% of the surgery cost, fully reimburses the drug cost, and reimburses 50% of the examination cost, and the liability coverage feature is extracted. The patient's installment intention data shows that his monthly income is 8,000 yuan, and his monthly fixed debt is 2,000 yuan, from which the repayment ability feature is extracted. The system has obtained the patient's credit score of 700 points (based on user information and installment intention data through a credit assessment model), an installment limit of 30,000 yuan, and an insurance direct payment amount of 13,100 yuan (surgery cost 12,000 yuan x 80% + drug cost 5,000 yuan + examination cost 3,000 yuan

[0085] These features, scores, limits and amounts are input into a preset risk assessment model to generate a multi-dimensional risk assessment matrix covering multiple risk dimensions such as expense reasonableness, insurance coverage sufficiency, and repayment ability stability. According to the matrix calculation, the patient risk score is medium. In combination with the score, the payment combination optimization parameters are determined as repaying the remaining 69,000 yuan in 6 installments of 1150 yuan each. This scheme takes into account the patient's repayment ability and combines the insurance coverage, achieving a reasonable balance between risk and payment.

[0086] The present application can accurately grasp the medical expense composition by extracting the expense structure features in the diagnosis and treatment data, and clearly define the expense distribution and reasonableness. The insurance data responsibility coverage features can clearly define the insurance payment range and degree. The repayment ability features in the installment intention data can assess the patient's repayment strength. Inputting these features, credit scores, installment limits, and insurance direct payment amounts into a risk assessment model generates a multi-dimensional risk assessment matrix, which can comprehensively and deeply assess risks from multiple dimensions. Based on this matrix, risk scores are calculated and payment combination optimization parameters are determined, which can consider various factors to make the payment combination more in line with the actual situation of the patient, effectively reduce payment risks, and improve the scientificity and feasibility of medical payment schemes.

[0087] In some optional implementations, the step of "calculating the risk score of the target object according to the multi-dimensional risk assessment matrix, and determining the optimization parameters of the payment combination in combination with the risk score" specifically includes the following steps:

[0088] Assigning weights to each dimension of the multi-dimensional risk assessment matrix, based on the weights, performing weighted summation on each element in the multi-dimensional risk assessment matrix to obtain a comprehensive risk value; obtaining a preset risk score strategy to determine the risk score corresponding to the comprehensive risk value; determining the repayment ability coefficient of the target object based on the repayment ability features and the credit score; generating a plurality of candidate payment schemes according to the installment limit, the insurance direct payment amount, and the repayment ability coefficient; obtaining business constraint conditions, determining a target candidate payment scheme from the plurality of candidate payment schemes based on the business constraint conditions, and taking the target payment scheme as the payment combination of the target object; extracting the optimization parameters from the payment combination.

[0089] The weights represent the importance of each dimension of the multi-dimensional risk assessment matrix to the overall risk assessment.

[0090] Each element refers to a specific data value at the intersection of each dimension in the multi-dimensional risk assessment matrix.

[0091] The comprehensive risk value is a value obtained by performing weighted summation on each element in the multi-dimensional risk assessment matrix based on assigning weights to each dimension of the matrix.

[0092] The risk score strategy represents the corresponding relationship rule between the comprehensive risk value and the risk score. The strategy is used to convert the calculated comprehensive risk value into an intuitive risk score, so as to more clearly evaluate the risk level of the target object.

[0093] The risk score is obtained by matching the calculated comprehensive risk value according to the preset risk score strategy.

[0094] The repayment ability coefficient is a parameter calculated based on the repayment ability feature and the credit score through a specific algorithm and model. It represents the strength of the target object's ability to repay medical expenses installment on time.

[0095] The candidate payment scheme is a set of possible payment schemes generated according to the installment amount, insurance direct payment amount, and repayment ability coefficient through a preset algorithm and rules.

[0096] The business constraint condition is a restriction condition summarized from the actual operation rules of medical payment business, laws and regulations, and risk management requirements, etc. It represents various provisions and restrictions that need to be followed when generating and selecting payment combination schemes.

[0097] In an example, taking the case of patient Li who needs to undergo a heart stent implantation surgery due to heart disease. The system receives the payment request data transmitted by the medical institution, and after processing, obtains a multi-dimensional risk assessment matrix, which contains dimensions such as cost structure (surgery cost, material cost proportion, etc.), responsibility coverage (insurance reimbursement ratio for each cost), and repayment ability. Assign weights to each dimension, such as setting the cost structure dimension weight to 0.4, the responsibility coverage dimension weight to 0.3, and the repayment ability dimension weight to 0.3. Weighted sum of matrix elements, the comprehensive risk value is 65. According to the preset risk score strategy, 60-70 points correspond to risk score level 3 (medium risk). Combined with Li's repayment ability feature (monthly income 10000 yuan, debt 2000 yuan) and credit score 750 points, the repayment ability coefficient is determined to be 0.7. Given the installment amount of 50000 yuan and the insurance direct payment amount of 20000 yuan, candidate payment schemes are generated, such as scheme A: 12 installments, each installment of 2500 yuan; scheme B: 24 installments, each installment of 1250 yuan. The business constraint condition stipulates that the installment period is no more than 24 periods, and the installment amount per period is no less than 1000 yuan. According to this, schemes A and B both meet the requirements, and scheme B is selected as the target payment scheme after comprehensive consideration. From scheme B, optimization parameters such as installment period 24 periods and installment amount per period 1250 yuan are extracted, which provide the basis for generating the final payment combination scheme.

[0098] The embodiments of the present application can obtain a comprehensive risk value by assigning weights to each dimension of the multi-dimensional risk assessment matrix and weighted summation, can comprehensively and accurately consider the influence degree of different risk factors on the overall risk, and make the risk assessment more scientific and reasonable. According to the risk scoring strategy, the risk score is determined, the complex risk condition is converted into a direct numerical value, and the risk level is quickly judged. The repayment ability coefficient is determined in combination with the repayment ability characteristics and the credit score, which can accurately measure the repayment strength of the target object. Based on this, a plurality of candidate payment schemes are generated, and the target payment combination is selected according to the business constraint condition, which can provide a compliant scheme with strong adaptability, and finally the optimization parameters are extracted, which lays a foundation for generating a scheme that finally meets the payment ability of the target object.

[0099] In some optional implementations, step S205, determining whether the payment combination scheme meets the preset payment ability threshold of the target object, specifically includes the following steps:

[0100] The insurance direct payment amount, the installment plan and the self-payment amount in the payment combination scheme are extracted; the insurance direct payment amount, the installment plan and the self-payment amount are compared with the preset payment ability threshold to obtain a comparison result, and based on the comparison result, it is determined whether the payment combination scheme meets the preset payment ability threshold of the target object.

[0101] The installment plan represents the specific arrangement of the target object for installment payment of medical expenses, covering key information such as the number of installments, the amount to be repaid each installment, and the time interval of repayment.

[0102] The self-payment amount is calculated after determining the target fee, the insurance direct payment amount and the installment plan of the target object. It is the amount of fees that the target object needs to bear by himself after deducting the insurance direct payment amount and the part of the fees covered by the installment plan from the target fee.

[0103] The comparison result is the conclusion obtained by comprehensively comparing the insurance direct payment amount, the installment plan and the self-payment amount in the payment combination scheme with the preset payment ability threshold.

[0104] In an example, taking the fracture treatment of a patient Zhang as an example. After the system receives the payment request data transmitted by the medical institution, a payment combination scheme is generated through processing, in which the insurance direct payment amount is 80,000 yuan, the installment plan is to repay for 24 periods, each period of 3,000 yuan, and the self-payment amount is 20,000 yuan. The preset payment ability threshold is set to be that the total amount of monthly repayment and self-payment does not exceed 5,000 yuan. Comparing the insurance direct payment amount, the installment plan and the self-payment amount with the preset threshold, the total monthly expenditure is first calculated, the self-payment amount is allocated to about 833 yuan per month, plus 3,000 yuan per period of installment, a total of 3,833 yuan per month. Since 3,833 yuan is less than the preset threshold of 5,000 yuan, the comparison result is that it meets the requirements. Based on this comparison result, it is determined that the payment combination scheme meets the preset payment ability threshold of Zhang. The system then outputs this payment combination scheme to the medical institution, so that Zhang can complete the fracture treatment in a suitable payment manner, while ensuring that the medical institution can smoothly receive the payment, realizing the rationality and efficiency of the medical payment link.

[0105] The embodiments of the present application can extract the insurance direct payment amount, the installment plan and the self-payment amount in the payment combination scheme, so as to clearly and explicitly show the fund composition of the target object in the medical payment. Comparing these amounts with the preset payment ability threshold can accurately quantify the matching degree of the payment combination scheme and the economic affordability of the target object. Determining whether the scheme meets the threshold through the comparison result can effectively avoid generating a scheme that exceeds the payment ability of the target object, protect the economic interests of the target object, and ensure that the medical institution can smoothly receive the payment.

[0106] In some optional implementation manners, after determining whether the payment combination scheme meets the preset payment ability threshold of the target object in step S205, the following steps are further included:

[0107] If the payment combination scheme does not meet the preset payment ability threshold of the target object, the installment plan and the self-payment amount are adjusted, and a new payment combination scheme is generated by using the multi-objective constraint optimization algorithm again until the preset payment ability threshold is met.

[0108] In an example, taking the heart valve replacement surgery of Ms. Li as an example. The system first generates an initial payment combination scheme, in which the insurance direct payment amount is 150,000 yuan, the initial installment scheme is to repay in 18 installments, each installment is 5,000 yuan, and the self-payment amount is 30,000 yuan. Li's preset payment ability threshold is that the total amount of monthly repayments and self-payments does not exceed 4,500 yuan. Obviously, the initial scheme does not meet the requirements. At this time, the system automatically adjusts the installment scheme and the self-payment amount. The installment period is extended to 24 installments, and the repayment amount of each installment is adjusted to 3,500 yuan, and the self-payment amount is recalculated to 24,000 yuan, which is about 1,000 yuan per month. Then, a new payment combination scheme is generated by using a multi-objective constraint optimization algorithm, considering factors such as cost, risk, and Li's repayment ability. Again, the insurance direct payment amount, the adjusted installment scheme (24 installments, 3,500 yuan per installment), and the self-payment amount (about 1,000 yuan per month) in the new scheme are compared with the preset payment ability threshold. At this time, the total monthly payment is about 4,500 yuan, which meets the threshold requirement. Through this continuous adjustment and optimization process, the generated payment combination scheme can not only meet the medical institution's collection needs, but also adapt to Li's economic bearing capacity, ensuring the smooth progress of the medical payment process and improving the patient's medical experience and payment rationality.

[0109] The embodiments of the present application adjust the installment scheme and the self-payment amount when the payment combination scheme does not meet the target object's preset payment ability threshold, and generate a new scheme by using a multi-objective constraint optimization algorithm again until the threshold is met. This process has significant advantages. It can dynamically optimize payment arrangements based on the actual payment ability of the target object, avoiding excessive economic pressure on the target object due to unreasonable initial schemes. Through continuous adjustment, the medical institution's collection needs and the target object's bearing capacity can be precisely balanced, ensuring that the payment scheme meets the medical expense settlement and does not cause excessive burden to the target object, improving the scientificity, rationality and feasibility of the medical payment scheme, and ensuring the smooth progress of the medical payment process.

[0110] It should be emphasized that, in order to further ensure the privacy and security of the above-mentioned diagnosis and treatment data, insurance data, installment intention data, risk score, optimization parameter, and payment combination scheme, the above-mentioned diagnosis and treatment data, insurance data, installment intention data, risk score, optimization parameter, and payment combination scheme can also be stored in a node of a block chain.

[0111] The blockchain referred to in the present application is a new application mode of distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm and other computer technologies. The blockchain is essentially a decentralized database, which is a series of data blocks associated using cryptographic methods, each data block containing information of a batch of network transactions, used to verify the validity (anti-fake) of the information and generate the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer.

[0112] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Artificial intelligence (AI) is the use of digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0113] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The software technology of artificial intelligence mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0114] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by computer readable instructions instructing related hardware, and the computer readable instructions can be stored in a computer readable storage medium. The program can include the processes of the above-mentioned embodiments when executed, wherein the storage medium can be a non-volatile storage medium such as a magnetic disc, an optical disc, a read-only memory (ROM), or a random access memory (RAM).

[0115] It should be understood that although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other orders. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0116] Further reference is made to Figure 3, as an implementation of the method shown in the above Figure 2 The present application provides an embodiment of a scheme generation device, which corresponds to the method embodiment shown in the above Figure 2 The device embodiment can be applied in various electronic devices.

[0117] As shown in the above Figure 3 The scheme generation device 400 of the present embodiment comprises a receiving module 401, a first determining module 402, a second determining module 403, a generating module 404, a judging module 405 and an output module 406. Wherein:

[0118] The receiving module 401 is configured to receive the payment request data of the target object transmitted by the medical institution, wherein the payment request data comprises diagnosis and treatment data, insurance data and installment intention data;

[0119] The first determining module 402 is configured to determine the target fee and the insurance direct payment amount of the target object based on the diagnosis and treatment data and the insurance data;

[0120] The second determining module 403 is configured to obtain the user information of the target object, and determine the risk score of the target object and the optimization parameter of the payment combination based on the user information and the installment intention data;

[0121] The generating module 404 is configured to generate the payment combination scheme of the target object by using a preset multi-objective constraint optimization algorithm according to the risk score and the optimization parameter;

[0122] The judging module 405 is configured to judge whether the payment combination scheme meets the preset payment ability threshold of the target object;

[0123] The output module 406 is configured to output the payment combination scheme to the medical institution if the payment combination scheme meets the preset payment ability threshold of the target object.

[0124] In the present embodiment, the payment request containing diagnosis and treatment, insurance and installment intention data is received to break the data island, realize data integration and avoid repeated submission of materials by the target object. The target fee and the direct payment amount are determined based on the diagnosis and treatment and insurance data, the risk score and the optimization parameter are determined in combination with the user information and the installment intention, and the multi-objective constraint optimization algorithm is used to generate the payment combination scheme, which changes the mode of relying on limited data for risk control and approval by traditional financial institutions, dynamically evaluates the rationality of medical expenses and the repayment ability of the user, reduces the risk and makes the approval more reasonable. The scheme is judged whether it meets the preset payment ability threshold and is output, which can process the insurance liability, the installment intention of the user and other needs in one station and in real time, shorten the installment approval and insurance claim time, reduce the pre-funding pressure of the patient, reduce the communication cost, improve the settlement efficiency, realize one-stop, real-time and efficient medical payment processing.

[0125] In an embodiment, the first determining module 402 comprises:

[0126] The verification submodule is configured to adopt a preset expense verification model to verify the diagnosis and treatment data and the insurance data, and determine the target medical expense of the target object.

[0127] The screening submodule is configured to adopt a preset insurance liability matching model to analyze the target medical expense, screen out a medical expense part covered by the insurance, and determine the insurance direct payment amount.

[0128] The embodiments of the present application can verify the diagnosis and treatment data and the insurance data through the expense verification model, accurately determine the target medical expense, effectively solve the problem that the financial institutions are difficult to verify the authenticity of medical behavior and the reasonableness of expense due to information asymmetry, and avoid fraud risks such as false medical treatment, excessive medical treatment and fund extraction. At the same time, the embodiments change the situation that the traditional risk control relies on static data and is difficult to accurately evaluate, and realize dynamic evaluation according to real-time diagnosis and treatment data. The insurance liability matching model analyzes the target medical expense, can quickly screen out the insurance covered part and determine the direct payment amount, improves the insurance company's auditing efficiency, can intercept suspicious claims in real time, and reduces the insurance fraud risk. In addition, the two models work together to avoid the complex financial reconciliation of hospitals settling with patients and insurance companies, shorten the repayment cycle, reduce the dependence of inter-institution settlement on manual reconciliation and traditional payment channels, reduce costs, improve speed and reduce error rate, and greatly optimize the medical payment process.

[0129] In an embodiment, the second determining module 403 comprises:

[0130] The evaluation submodule is configured to adopt a preset credit evaluation model to evaluate the credit of the target object based on the user information and the installment intention data, and obtain the credit score and the installment amount of the target object.

[0131] The determination submodule is configured to adopt a preset risk evaluation model to analyze the relevance between the diagnosis and treatment data, the insurance data and the installment intention data based on the credit score, the installment amount and the insurance direct payment amount, and determine the risk score of the target object and the optimization parameter of the payment combination.

[0132] The embodiment of the application can perform credit evaluation based on user information and installment intention data by using a preset credit evaluation model, can comprehensively consider the user's multiple aspects, and accurately obtain credit score and installment amount. This makes the financial institutions get rid of the limitation of relying only on traditional credit investigation and income proof, and can more dynamically and comprehensively evaluate the user's credit. Then, based on the credit score, installment amount and insurance direct payment amount, the correlation of diagnosis and treatment, insurance data and installment intention data is analyzed by using a preset risk evaluation model, which can deeply understand the risk status of the user in the whole medical payment scene. Not only the risk score can be determined, but also the optimization parameters of the payment combination can be obtained, effectively solving the problem that the financial institutions are difficult to accurately evaluate the risk due to the lack of real-time medical scene data.

[0133] In an embodiment, the determining sub-module is further configured to extract a fee structure feature in the diagnosis and treatment data, a liability coverage feature in the insurance data, and a repayment ability feature in the installment intention data; input the fee structure feature, the liability coverage feature, the repayment ability feature, the credit score, the installment amount, and the insurance direct payment amount into a preset risk evaluation model to generate a multi-dimensional risk evaluation matrix; calculate a risk score of the target object according to the multi-dimensional risk evaluation matrix, and determine the optimization parameters of the payment combination in combination with the risk score.

[0134] The embodiment of the application can accurately grasp the medical expense structure by extracting the fee structure feature in the diagnosis and treatment data, and can clearly define the insurance payment range and degree by the liability coverage feature in the insurance data. The repayment ability feature in the installment intention data can evaluate the repayment strength of the patient. Inputting these features, the credit score, the installment amount, and the insurance direct payment amount into the risk evaluation model to generate a multi-dimensional risk evaluation matrix can comprehensively and deeply evaluate the risk from multiple dimensions. Based on the matrix, the risk score is calculated and the optimization parameters of the payment combination are determined, which can consider various factors, make the payment combination more suitable for the actual situation of the patient, effectively reduce the payment risk, and improve the scientificity and feasibility of the medical payment scheme.

[0135] In an embodiment, the determining sub-module is further configured to assign a weight to each dimension of the multi-dimensional risk evaluation matrix, perform weighted summation on each element in the multi-dimensional risk evaluation matrix based on the weight to obtain a comprehensive risk value; obtain a preset risk score strategy to determine a risk score corresponding to the comprehensive risk value; determine a repayment ability coefficient of the target object based on the repayment ability feature and the credit score; generate a plurality of candidate payment schemes based on the installment amount, the insurance direct payment amount, and the repayment ability coefficient; obtain a business constraint condition, determine a target candidate payment scheme from the plurality of candidate payment schemes based on the business constraint condition, and take the target payment scheme as the payment combination of the target object; and extract the optimization parameters from the payment combination.

[0136] The embodiment of the application can obtain a comprehensive risk value by assigning weights to each dimension of a multi-dimensional risk assessment matrix and weighted summation, can comprehensively and accurately consider the influence degree of different risk factors on the overall risk, and makes the risk assessment more scientific and reasonable. According to the risk scoring strategy, the risk score is determined, the complex risk condition is converted into a direct numerical value, and the risk level is quickly judged. The repayment ability coefficient is determined in combination with the repayment ability characteristics and the credit score, and the repayment strength of the target object can be accurately measured. Based on this, a plurality of candidate payment schemes are generated, and the target payment combination is screened according to the business constraint condition, a scheme with strong adaptability and compliance can be provided, and finally the optimization parameters are extracted, which lays a foundation for generating a scheme that finally meets the payment ability of the target object.

[0137] In an embodiment, the determining module 405 comprises:

[0138] The extraction sub-module is configured to extract the insurance direct payment amount, the installment plan, and the self-payment amount in the payment combination scheme.

[0139] The comparison sub-module is configured to compare the insurance direct payment amount, the installment plan, and the self-payment amount with the preset payment ability threshold to obtain a comparison result, and determine whether the payment combination scheme meets the preset payment ability threshold of the target object based on the comparison result.

[0140] The embodiment of the application can extract the insurance direct payment amount, the installment plan, and the self-payment amount in the payment combination scheme, and can clearly and explicitly show the fund composition of the target object in the medical payment. Comparing these amounts with the preset payment ability threshold can accurately quantify the matching degree of the payment combination scheme and the economic affordability of the target object. By determining whether the scheme meets the threshold through the comparison result, it can effectively avoid generating a scheme that exceeds the payment ability of the target object, protect the economic interests of the target object, and ensure that the medical institution can smoothly receive the payment.

[0141] In an embodiment, the scheme generation device 400 further comprises:

[0142] The adjustment module is configured to adjust the installment plan and the self-payment amount if the payment combination scheme does not meet the preset payment ability threshold of the target object, and to generate a new payment combination scheme by using the multi-objective constraint optimization algorithm again until the preset payment ability threshold is met.

[0143] The embodiment of the application adjusts the installment scheme and the self-payment amount when the payment combination scheme does not meet the preset payment ability threshold of the target object, and generates a new scheme by using the multi-objective constraint optimization algorithm again until the threshold is met. This process has obvious advantages. It can dynamically optimize the payment arrangement according to the actual payment ability of the target object, and avoid the situation that the target object bears too much economic pressure due to the unreasonable initial scheme. Through continuous adjustment, the payment demand of the medical institution and the bearing capacity of the target object can be accurately balanced, so that the payment scheme can meet the medical expense settlement and will not cause too heavy burden to the target object, and the scientificity, rationality and feasibility of the medical payment scheme are improved, and the smooth progress of the medical payment process is ensured.

[0144] To solve the above technical problems, the embodiment of the application further provides a computer device. For details, please refer to Figure 4 , Figure 4 The basic structure block diagram of the computer device of the embodiment is shown in the figure.

[0145] The computer device 6 includes a memory 61, a processor 62 and a network interface 63 which are connected to each other through a system bus. It should be pointed out that only the computer device 6 with the memory 61, the processor 62 and the network interface 63 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented. Among them, those skilled in the art can understand that the computer device here is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0146] The computer device can be a desktop computer, a notebook computer, a palm computer and a cloud server, etc. The computer device can interact with the user through a keyboard, a mouse, a remote controller, a touchpad or a sound control device, etc.

[0147] The memory 61 includes at least one type of readable storage medium, including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 6. Of course, the memory 61 can include both an internal storage unit and an external storage device of the computer device 6. In the present embodiment, the memory 61 is generally used to store an operating system and various application software installed on the computer device 6, such as computer readable instructions of the scheme generation method, etc. In addition, the memory 61 can also be used to temporarily store various data that have been output or will be output.

[0148] The processor 62 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In the present embodiment, the processor 62 is used to run computer readable instructions or process data stored in the memory 61, such as computer readable instructions of the scheme generation method.

[0149] The network interface 63 can include a wireless network interface or a wired network interface, and is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0150] The embodiment of the application can break data islands, realize data integration, and avoid repeated submission of materials by the target object by receiving a payment request containing diagnosis and treatment, insurance, and installment intention data. The target fee and direct payment amount are determined based on diagnosis and treatment and insurance data, the risk score and optimization parameters are determined in combination with user information and installment intention, and a payment combination scheme is generated by using a multi-objective constraint optimization algorithm. The mode of relying on limited data for risk control and approval by traditional financial institutions is changed, the rationality of medical expenses and the repayment ability of the user can be dynamically evaluated, the risk is reduced, and the approval is more reasonable. Whether the scheme meets the preset payment ability threshold is judged and output, which can one-stop real-time process the needs of insurance liability, user installment intention, etc., shorten the installment approval and insurance claim time, reduce the pre-funding pressure of patients, reduce the communication cost, improve the settlement efficiency, and realize one-stop, real-time, and efficient medical payment processing.

[0151] The application also provides another implementation, that is, a computer readable storage medium storing computer readable instructions, which can be executed by at least one processor to make the at least one processor execute the steps of the scheme generation method as described above.

[0152] The embodiment of the application can break data islands, realize data integration, and avoid repeated submission of materials by the target object by receiving a payment request containing diagnosis and treatment, insurance, and installment intention data. The target fee and direct payment amount are determined based on diagnosis and treatment and insurance data, the risk score and optimization parameters are determined in combination with user information and installment intention, and a payment combination scheme is generated by using a multi-objective constraint optimization algorithm. The mode of relying on limited data for risk control and approval by traditional financial institutions is changed, the rationality of medical expenses and the repayment ability of the user can be dynamically evaluated, the risk is reduced, and the approval is more reasonable. Whether the scheme meets the preset payment ability threshold is judged and output, which can one-stop real-time process the needs of insurance liability, user installment intention, etc., shorten the installment approval and insurance claim time, reduce the pre-funding pressure of patients, reduce the communication cost, improve the settlement efficiency, and realize one-stop, real-time, and efficient medical payment processing.

[0153] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and a general hardware platform as required, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) execute the method of each embodiment of the application.

[0154] Obviously, the above-described embodiments are only some embodiments but not all embodiments of the present application, and the preferred embodiments of the present application are shown in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing specific embodiments or equivalently replace some technical features thereof. Any equivalent structure made by using the content of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the patent protection scope of the present application.

[0155] The non-company software tools or components appearing in the embodiments of the present application are only illustrative and do not represent actual use.

Claims

1. A scheme generation method, characterized in that, include: Receive payment request data from medical institutions for target individuals, the payment request data including medical data, insurance data, and installment payment intention data; Based on the medical data and the insurance data, the target cost and direct insurance payment amount for the target individual are determined; Obtain user information of the target object, and based on the user information and the installment intention data, determine the risk score and optimization parameters of the payment combination for the target object; Based on the risk score and the optimization parameters, a pre-defined multi-objective constraint optimization algorithm is used to generate a payment combination scheme for the target object; Determine whether the payment combination scheme meets the preset payment capacity threshold of the target object; If the payment combination scheme meets the preset payment capacity threshold of the target object, then the payment combination scheme is output to the medical institution.

2. The method according to claim 1, characterized in that, The step of determining the target cost and direct insurance payment amount for the target individual based on the medical data and the insurance data specifically includes: A preset cost verification model is used to verify the costs of the medical data and the insurance data to determine the target medical costs for the target object. Using a pre-defined insurance liability matching model, the target medical expenses are analyzed to identify the portion of medical expenses covered by insurance and determine the direct payment amount from the insurance company.

3. The method according to claim 1, characterized in that, The step of determining the risk score and optimization parameters of the payment combination for the target object based on the user information and the installment intention data specifically includes: Based on the user information and the installment intention data, a preset credit assessment model is used to conduct a credit assessment on the target object to obtain the target object's credit score and installment limit; Based on the credit score, the installment amount, and the direct insurance payment amount, a preset risk assessment model is used to analyze the correlation between the medical data, the insurance data, and the installment intention data, and to determine the optimized parameters of the risk score and payment combination for the target object.

4. The method according to claim 3, characterized in that, The step of analyzing the correlation between the medical data, insurance data, and installment intention data based on the credit score, the installment amount, and the direct insurance payment amount, using a preset risk assessment model, to determine the optimized parameters of the target object's risk score and payment combination, specifically includes: Extract the cost structure features from the medical data, the liability coverage features from the insurance data, and the repayment ability features from the installment intention data; The cost structure characteristics, liability coverage characteristics, repayment ability characteristics, credit score, installment amount, and direct insurance payment amount are input into a preset risk assessment model to generate a multi-dimensional risk assessment matrix. Based on the multidimensional risk assessment matrix, the risk score of the target object is calculated, and the optimization parameters of the payment combination are determined in combination with the risk score.

5. The method according to claim 4, characterized in that, The step of calculating the risk score of the target object based on the multidimensional risk assessment matrix, and determining the optimization parameters of the payment portfolio in conjunction with the risk score, specifically includes: Weights are assigned to each dimension of the multidimensional risk assessment matrix, and based on the weights, each element in the multidimensional risk assessment matrix is ​​summed in a weighted manner to obtain a comprehensive risk value. Obtain a preset risk scoring strategy and determine the risk score corresponding to the comprehensive risk value; Based on the repayment ability characteristics and the credit score, the repayment ability coefficient of the target object is determined; Based on the installment amount, the direct insurance payment amount, and the repayment ability coefficient, multiple candidate payment schemes are generated; Obtain business constraints, determine a target candidate payment scheme from the plurality of candidate payment schemes based on the business constraints, and use the target payment scheme as the payment combination for the target object; Extract optimization parameters from the payment combination.

6. The method according to claim 1, characterized in that, The step of determining whether the payment combination scheme meets the preset payment capability threshold of the target object specifically includes: Extract the direct insurance payment amount, installment plan, and out-of-pocket payment amount from the payment combination scheme; The direct insurance payment amount, the installment plan, and the out-of-pocket payment amount are compared with a preset payment capacity threshold to obtain a comparison result. Based on the comparison result, it is determined whether the payment combination plan meets the preset payment capacity threshold of the target object.

7. The method according to claim 6, characterized in that, After the step of determining whether the payment combination scheme meets the preset payment capacity threshold of the target object, the method further includes: If the payment combination scheme does not meet the preset payment capacity threshold of the target object, the installment plan and the self-payment amount are adjusted, and the multi-objective constraint optimization algorithm is re-applied to generate a new payment combination scheme until it meets the preset payment capacity threshold.

8. A speech generation device, characterized in that, include: The receiving module is used to receive payment request data of the target object transmitted by the medical institution. The payment request data includes medical data, insurance data, and installment intention data. The first determining module is used to determine the target cost and direct insurance payment amount for the target object based on the medical data and the insurance data. The second determining module is used to obtain user information of the target object, and based on the user information and the installment intention data, determine the risk score and optimization parameters of the payment combination of the target object; The generation module is used to generate a payment combination scheme for the target object based on the risk score and the optimization parameters, using a preset multi-objective constraint optimization algorithm. The judgment module is used to determine whether the payment combination scheme meets the preset payment capability threshold of the target object; The output module is used to output the payment combination scheme to the medical institution if the payment combination scheme meets the preset payment capacity threshold of the target object.

9. A computer device, characterized in that, The method includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the scheme generation 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 computer-readable instructions, which, when executed by a processor, implement the steps of the scheme generation method as described in any one of claims 1 to 7.

Images