Medical multi-source payment intelligent account division method and system

Abstract

The invention relates to the technical field of payment security and authorization, and discloses a medical multi-source payment intelligent account division method and system, and the method comprises the steps: obtaining the payment information and superior welfare information of a patient corresponding to medical payment, carrying out the compliance adaptation of the payment information based on the superior welfare information, and obtaining the payment information of the patient corresponding to the medical payment; the method comprises the following steps: receiving payment information sent by a server to obtain a separate account blocking instruction of the payment information, carrying out medical advice matching degree verification on the payment information based on the separate account blocking instruction to obtain payment splitting abnormal information of the payment information, and carrying out price matching degree verification on the payment information based on a preset diagnosis and treatment price library and the payment splitting abnormal information to obtain payment splitting abnormal information of the payment information. According to the method and the device, the problem of how to accurately analyze an abnormal event when a payment system finds an abnormal event can be solved by obtaining the compliance price deviation degree of the payment information and performing price overrun judgment on the payment information based on the compliance price deviation degree and the payment splitting abnormal information.

Description

Technical Field

[0001] The present invention relates to the field of payment security and authorization technology, and in particular to a medical multi-source payment intelligent account splitting method and system. Background Art

[0002] Existing payment technologies mostly rely on static rules to process patients' payment and welfare information, lack dynamic compliance adaptation and real-time verification mechanisms for multi-source payment data, and find it difficult to conduct multi-dimensional correlation analysis of patients' preferential benefits, medical prescription content, and medical treatment prices. This leads to splitting deviations or illegal over-limit payment problems during the account splitting process, and makes it impossible to accurately identify over-limit risks caused by price application or coding errors.

[0003] On the other hand, the existing account splitting system uses a single rule or simple statistical method to detect payment anomalies, and is unable to construct complex feature vectors to reveal implicit profit logic, resulting in a single risk judgment dimension, a lack of self-learning ability for historical payment data, and an inability to optimize the account splitting method through historical correlation analysis, making the strategy rigid and poorly adaptable.

[0004] Therefore, when an anomaly is discovered in the payment system, how to accurately analyze the abnormal event becomes an urgent problem to be solved. Summary of the Invention

[0005] The present invention provides a medical multi-source payment intelligent account splitting method and system, the main purpose of which is to solve the problem of how to accurately analyze abnormal events when abnormalities are found in the payment system.

[0006] To achieve the above-mentioned objectives, the present invention provides a medical multi-source payment intelligent account splitting method, comprising: S1: Obtain the payment information and preferential benefit information of the patient corresponding to the medical payment; S2: Based on the preferential benefit information, the payment information is subjected to compliance adaptation to obtain an account splitting blocking instruction for the payment information; based on the account splitting blocking instruction, the payment information is subjected to medical order matching verification to obtain payment splitting exception information for the payment information; S3: Based on a preset medical price database and the payment splitting anomaly information, the payment information is verified for price matching to obtain a compliance price deviation of the payment information. Based on the compliance price deviation and the payment splitting anomaly information, a price over-limit determination is performed on the payment information to obtain over-limit payment blocking information of the payment information. S4: Establishing a profit feature vector of the payment splitting exception information and the over-limit payment blocking information, and performing a multi-dimensional correlation analysis on the profit feature vector based on a preset profit determination model to obtain a profit determination map of the payment information; S5: performing a confidence analysis on the payment information based on the profit determination map to obtain a blocking threshold matrix for the payment information, and performing a risk classification analysis on the payment information based on the blocking threshold matrix to obtain a payment plan for the payment information; S6: Performing a historical correlation analysis on the payment plan based on the patient's historical data to obtain a billing method for the medical payment.

[0007] Optionally, the compliance adaptation of the payment information based on the preferential benefit information to obtain an account splitting blocking instruction for the payment information includes: Performing rule cross-mapping based on the preferential benefit information and the payment information to obtain a list of illegal payments of the payment information; performing dynamic payment verification based on the list of illegal payments and the payment information to obtain payment link abnormality information of the payment information; Performing a three-dimensional matching of account splitting rules on the payment information based on the payment link abnormality information and the preset blocking rules to obtain an account splitting blocking condition matrix for the payment information; A blocking instruction generation operation is performed based on the account split blocking condition matrix and the blocking level strategy in the blocking rule to obtain the account split blocking instruction of the payment information.

[0008] Optionally, performing medical order matching verification on the payment information based on the account split blocking instruction to obtain payment split exception information of the payment information includes: Performing payment-order correlation verification on the payment information based on the account split blocking instruction to obtain an abnormal payment correlation list of the payment information; Performing reverse analysis of the account splitting logic on the abnormal payment association list and the account splitting blocking instruction to obtain payment splitting violation characteristics of the payment information; Payment splitting exception information of the payment information is generated based on the payment splitting violation characteristics and a preset diagnosis and treatment price database.

[0009] Optionally, the calculation formula for the compliance price deviation is:

[0010] in: is the compliance price deviation, For the The actual payment price in the payment information described in the item, For the The actual payment price mentioned in the item corresponds to the standard price threshold in the medical price database. For the The quantitative value of the policy compliance indicator corresponding to the preferential welfare information described in the item, For the The weight of the quantitative value of the policy compliance indicator described in the item, is a time-sensitive regulatory factor. For the The three-dimensional feature values corresponding to the payment splitting abnormal information described in item 1, For the The coupling coefficient of the three-dimensional eigenvalues described in the term, For the The project life cycle decay factor, is the basic deviation coefficient, is the nonlinear deviation amplification exponent, is the total dimension of the three-dimensional eigenvalues, is the three-dimensional eigenvalue, is the total amount of the payment information, The number of the total number of payment information item, The total number of quantitative values for the policy compliance indicator. The total number of quantitative values for the policy compliance indicator item.

[0011] Optionally, the performing price-exceeding determination on the payment information based on the compliance price deviation and the payment splitting anomaly information to obtain the over-limit payment blocking information of the payment information includes: Performing feature level extraction on the payment splitting anomaly information to obtain a quantitative anomaly level code for the payment splitting anomaly information, and performing interval threshold division on the compliance price deviation to obtain a three-level warning state of the compliance price deviation; Constructing a risk strategy mapping relationship between the quantitative anomaly level code and the three-level warning state, and performing a time window compliance check on the payment information based on the risk strategy mapping relationship and the effective timetable of the preferential benefit information to obtain a time correction deviation of the payment information; performing a blocking strategy match on the payment information based on the time-corrected deviation and the quantitative anomaly level code to obtain a multi-level blocking instruction for the payment information, and performing a cross-system consistency verification operation on the payment information based on the multi-level blocking instruction and a preset system interface protocol to obtain an effective blocking status identifier for the payment information; A reverse data integrity check is performed on the payment information based on the effective blocking status identifier and the pre-acquired historical dispute item list to obtain over-limit payment blocking information of the payment information.

[0012] Optionally, the establishing of the profit feature vector of the payment splitting exception information and the over-limit payment blocking information includes: Performing payment time sequence analysis on the payment splitting exception information to obtain a time feature of the splitting behavior in the payment splitting exception information; Matching the over-limit payment blocking information with violation behaviors based on a preset payment rule library to obtain a quantitative indicator of violation characteristics in the over-limit payment blocking information; Performing spatiotemporal correlation mapping on the payment information based on the time characteristics of the splitting behavior and the quantitative indicators of the violation characteristics to obtain a spatiotemporal correlation map of abnormal payment information; Performing a rule circumvention effectiveness evaluation on the payment path of the payment information based on the time characteristics of the splitting behavior and the quantitative indicators of the violation characteristics to obtain a rule superposition circumvention strength value; The payment information is multimodal feature encoded based on the spatiotemporal association graph and the rule superposition avoidance strength value to obtain a profit feature vector of the payment information.

[0013] Optionally, the calculation formula of the preset profit determination model is:

[0014] in: To determine the profit map, is the compliance price deviation, For payment splitting abnormal information, For policy exemption matching, is the policy coverage factor, is the patient identity weight factor, is the historical correlation coefficient, is the logarithmic protection constant, is the price deviation enhancement index, is the time decay parameter, is the normalization coefficient, is the event axis influence, Denominator offset protection amount.

[0015] Optionally, performing risk classification analysis on the payment information based on the blocking threshold matrix to obtain a payment plan for the payment information includes: Performing a graded risk assessment on the payment information based on the blocking threshold matrix and the compliance price deviation to obtain a risk level distribution of the payment information; quantifying the superimposed risk of the payment information based on the risk level distribution and the payment splitting anomaly information to obtain an excess risk value of the payment information; Adapting the exemption policy of the payment information based on the excess risk value and historical data of the payment information to obtain a dynamic blocking rule for the payment information; Based on the dynamic blocking rules and the policy template library in the preferential welfare information, an account splitting path is generated for the payment information to obtain a payment plan for the payment information.

[0016] Optionally, performing a historical correlation analysis on the payment plan based on the patient's historical data to obtain a billing method for the medical payment includes: Establishing a historical-current comparison relationship between the patient's historical payment data and the payment information; Performing a historical retrospective verification operation on the payment plan based on the historical-current comparison relationship and a preset dispute payment scenario library to obtain a payment scenario compatibility value of the payment plan; The payment plan is bound with account splitting conditions based on the payment scenario compatibility value and the history-current comparison relationship to obtain the account splitting method of the medical payment.

[0017] A medical multi-source payment intelligent account splitting system, characterized in that the system includes: Information collection module: used to obtain the payment information and preferential benefit information of patients corresponding to medical payments; Anomaly analysis module: configured to perform compliance adaptation on the payment information based on the preferential benefit information to obtain an account splitting blocking instruction for the payment information, and perform medical order matching verification on the payment information based on the account splitting blocking instruction to obtain payment splitting anomaly information of the payment information; A blocking instruction generation module is configured to perform price matching verification on the payment information based on a preset medical price database and the payment splitting anomaly information to obtain a compliance price deviation of the payment information, and perform price over-limit determination on the payment information based on the compliance price deviation and the payment splitting anomaly information to obtain over-limit payment blocking information of the payment information; A graph generation module is used to establish a profit feature vector for the payment splitting exception information and the over-limit payment blocking information, and perform a multi-dimensional correlation analysis on the profit feature vector based on a preset profit determination model to obtain a profit determination graph for the payment information; Payment planning module: used to perform confidence analysis on the payment information based on the profit determination map to obtain a blocking threshold matrix for the payment information, and perform risk classification analysis on the payment information based on the blocking threshold matrix to obtain a payment plan for the payment information; The account splitting method generating module is used to perform a historical correlation analysis on the payment plan based on the patient's historical data to obtain the account splitting method of the medical payment.

[0018] Beneficial effects 1. By establishing a dynamic rule cross-mapping engine, the policy version, effective time, and exception clauses in the preferential welfare information are analyzed in real time, and multi-dimensional cross-checks are performed with the medical codes and payment channels in the payment information. Dynamic responses to policy iterations and consistency of real-time blocking strategies are maintained. Abnormal payment link information is mapped to three independent dimensions: subject qualification, payment target, and path legitimacy for risk scoring. Through a nonlinear coupling algorithm, multi-threshold account splitting and blocking instructions are generated. This architecture improves the accuracy of violation identification, especially accurately intercepting complex violation scenarios such as cross-provincial medical insurance application and split payment of high-priced consumables. At the same time, in the calculation of compliance price deviation, a sinusoidal time decay factor based on policy timeliness is introduced to automatically lower the blocking threshold in the early stage of policy implementation, improve the fault tolerance rate, and trigger strict verification in the policy maturity period. This design solves the problem of abnormal false alarms caused by frequent adjustments during the policy transition period in traditional systems, and reduces the misjudgment rate of account splitting and blocking during the policy switching period.

[0019] 2. By analyzing the temporal patterns of payment behavior and the distribution characteristics of violation characteristics, it can autonomously identify the cyclical patterns of payment splits and risk transmission paths in different scenarios, significantly improving the accuracy of capturing complex violations. At the same time, the system integrates dynamic parameters such as policy exemptions, patient identity weights, and time decay variables to automatically adjust risk assessment sensitivity for different scenarios. By introducing an exponential compensation mechanism, it overcomes the path dependence flaws of traditional linear models, strengthening routine payment verification while ensuring the smooth flow of emergency treatment channels, and achieving an adaptive balance of risk prevention and control strategies. Through the synergistic effect of dynamic weight allocation and effect decay mechanisms, this model effectively suppresses misjudgment interference and optimizes the allocation of regulatory resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flowchart of a method for intelligent bill splitting of medical multi-source payments provided by one embodiment of the present invention; Figure 2 This is a functional module diagram of a medical multi-source payment intelligent account splitting system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0022] The embodiment of the present application provides a medical multi-source payment intelligent account splitting method and system. The execution subject of the medical multi-source payment intelligent account splitting method and system includes but is not limited to at least one of the electronic devices such as the server, the terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the medical multi-source payment intelligent account splitting method and system can be executed by software or hardware installed on the terminal device or the server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0023] Reference Figure 1 FIG. 1 is a flow chart of a method for intelligently splitting accounts for multi-source medical payments according to an embodiment of the present invention. In this embodiment, the method for intelligently splitting accounts for multi-source medical payments includes: S1: Obtain the payment information and preferential benefit information of the patient corresponding to the medical payment.

[0024] Specifically, payment information refers to various types of data generated by patients during the medical payment process, which is used to record the specific circumstances of medical consumption.

[0025] For example, medical treatment costs such as registration fees, examination fees, and drug fees correspond to the charge details in the hospital's HIS system; payment methods such as medical insurance payment, self-payment, commercial insurance, etc. correspond to the card swiping and code scanning records of the payment terminal; the payment time is the specific time of the day of the consultation, which is recorded by the clock of the hospital charging system; patient identity identifiers such as ID number and medical insurance card number are used to link patient files.

[0026] The above data can be obtained through physical devices or systems such as hospital payment windows, self-service payment machines, and online payment platforms such as WeChat and Alipay medical payment.

[0027] Specifically, preferential benefit information refers to various medical preferential policies or benefits that patients can enjoy, which are used for compliance verification and account splitting rule adaptation.

[0028] For example, medical insurance policies such as reimbursement ratios and drug catalog restrictions are mapped to the real-time data interface of the medical insurance center; medical assistance subsidies, such as exemptions for low-income groups, are provided by the civil affairs department; commercial insurance terms, such as hospitalization allowances and specialty drug reimbursement scope, are sourced from the insurance company system; and hospital-specific discounts, such as discounts for chronic disease patients, are stored in the discount rule library of the hospital information system. Furthermore, the step of the acquisition operation may include: connecting with an interface of an external system through a hospital information system (HIS) to pull or receive data in real time.

[0029] Obtain the patient's medical insurance account balance and reimbursement rules through the medical insurance interface; obtain the transaction records of the third-party payment platform through the payment gateway.

[0030] After the patient completes the diagnosis and treatment, the system automatically collects payment information and benefit information during the billing process, or retrieves benefit information in advance during the pre-settlement stage for cost estimation, such as verifying medical insurance eligibility when registering for an outpatient appointment.

[0031] S2: Based on the preferential welfare information, the payment information is subjected to compliance adaptation to obtain an account splitting blocking instruction of the payment information; based on the account splitting blocking instruction, the payment information is subjected to medical order matching verification to obtain payment splitting exception information of the payment information.

[0032] In an embodiment of the present invention, rule cross-mapping is performed based on the preferential benefit information and the payment information to obtain a list of illegal payments of the payment information, and dynamic payment verification is performed based on the illegal payment list and the payment information to obtain payment link abnormality information of the payment information; Performing a three-dimensional matching of account splitting rules on the payment information based on the payment link abnormality information and the preset blocking rules to obtain an account splitting blocking condition matrix for the payment information; A blocking instruction generation operation is performed based on the account split blocking condition matrix and the blocking level strategy in the blocking rule to obtain the account split blocking instruction of the payment information.

[0033] Specifically, a blocking instruction is a control instruction used to indicate whether to block the billing of certain payment information during the billing process. For example, if the medical treatment item in the payment information is not covered by the medical insurance reimbursement catalog, a blocking instruction may be generated to prevent the medical insurance billing.

[0034] It can also be explained as follows: the account splitting blocking instruction is a control data object generated in this method. In essence, it is a set of mandatory intervention signals containing verification decision results, which is used to intercept payment account splitting requests that do not comply with the preset strategy in real time.

[0035] Among them, the account blocking instructions may include: blocking level: emergency / high / medium / low, blocking reason code: medical insurance policy conflict / C01, missing medical order / D03, arbitrage risk / R12, etc., triggered strategy source: emergency policy document number + clause index, exemption priority identifier: 0-non-exempt; 1-conditional exemption.

[0036] Furthermore, the operation process is as follows: first refer to the preferential welfare information, the applicable population is fever clinic patients, the service code = HBV-2011N, the effective time = 2023-12 / 01-12 / 31, and ordinary outpatient patients try to use this service code to pay → trigger blocking code C01 (service scope does not match). At this time, the system automatically freezes the account splitting request and generates an audit report and pushes it to the health department.

[0037] Specifically, rule cross-mapping involves comparing the medical treatment items and payment methods in the payment information with the policy rules in the preferential benefit information. For example, the drug cost in the payment information can be checked to verify whether the drug is included in the medical insurance drug catalog.

[0038] Furthermore, rule cross-mapping involves parsing the reimbursement terms, restrictions, and priority rules in the preferential benefit information and matching them item by item with the drug catalog and medical treatment items in the payment information. This identifies payment items that exceed benefit coverage (such as self-funded items and duplicate subsidy items) and generates a list of illegal payments, including the violation item code and violation type.

[0039] Specifically, the illegal payment list includes any payment information found to be inconsistent with preferential welfare policy rules during the comparison process. For example, if medical insurance is used to pay for medicines not listed in the medical insurance catalog, this expense will be included in the illegal payment list.

[0040] Specifically, dynamic payment verification involves dynamically checking the fees and related payment information in the illegal payment list to see if there are any other anomalies, such as checking whether the illegal payment involves duplicate charges.

[0041] Furthermore, dynamic payment verification involves calculating the payment amount in segments based on the item types in the illegal payment list and the requirements of preferential benefit information, such as splitting outpatient and inpatient expenses and deducting deductibles, to verify whether the actual payment ratio meets policy thresholds. If an excessive cash payment ratio or conflicting subsidy combinations is detected, the payment chain anomaly type and deviation value are flagged.

[0042] Specifically, payment link abnormality information is: through dynamic verification, find out the abnormalities in the link during the payment process, such as incomplete payment links, incorrect payment flow, etc.

[0043] Furthermore, payment link anomaly information includes: Payment link anomaly flags are structured identifiers for unusual behaviors within the payment process, such as policy violations, logical conflicts, or numerical value violations, based on the dynamic verification of payment information against preferential benefit rules. These flags accurately identify points in the payment process where policy or logic violations occur, such as excessive amounts or illegal paths. These flags trigger subsequent blocking decisions or manual review processes, preventing the non-compliant payment link from continuing, and providing a traceable chain of evidence for account blocking and risk analysis.

[0044] Furthermore, payment link anomalies are marked as a multi-dimensional label set, including anomaly types and anomaly values. The anomaly types include: rule conflicts: such as repeated enjoyment of subsidies, payment exceeding the ceiling; value exceeding the limit: such as the self-pay ratio exceeding the threshold, and the daily drug cost exceeding the warning value; path violations: such as unregistered cross-provincial settlement, and settlement by non-designated institutions.

[0045] Abnormal values include: deviation: the difference between the actual payment amount and the policy-allowed value, such as cash payment exceeding the limit; associated entries: the payment item code and name that triggered the abnormality, such as drug A-code XYZ: unit price exceeds the limit; timestamp: the payment stage where the abnormality occurred, such as the outpatient fee settlement stage and the hospitalization prepayment deduction stage; impact scope: the degree of impact of the abnormality on the overall payment chain, such as local abnormality and global abnormality.

[0046] Specifically, the three-dimensional matching of account splitting rules is to perform three-dimensional matching of abnormal marks from the subject qualification, payment target, and path legitimacy. If it is detected that a non-insured subject uses medical insurance payment (subject violation) or a beauty project is declared for medical insurance (target violation), a judgment matrix containing violation dimensions, risk levels and blocking ranges is generated.

[0047] Specifically, the account-by-account blocking condition matrix is a multi-dimensional risk assessment model used to systematically determine the type, level, and scope of risk of non-compliance in payment transactions. Essentially, it structuredly matches payment chain anomaly markers with pre-set blocking rules, forming a quantifiable and traceable basis for blocking decisions.

[0048] Furthermore, the account blocking condition matrix includes judgment dimensions, judgment parameters and dynamic weights. The judgment dimensions include: subject qualification dimension, verifying whether the payment subject has the right to use welfare benefits, such as medical insurance participation status and the validity period of military dependents' status; payment target content dimension: reviewing the matching between payment items and welfare policies, such as illegal declaration of drugs and beauty projects outside the medical insurance catalog; payment path dimension: verifying the legality of the funds flow path, such as the lack of cross-provincial settlement registration and settlement by non-designated institutions.

[0049] The judgment parameters include: risk level, which is divided into levels according to the severity of the violation, such as red / yellow warning, level one / level two blocking; blocking scope, which clearly specifies the proportion or type of funds to be blocked, such as full freeze, partial interception, and suspension of specific channels; triggering rules, which are associated with specific policy clauses or system rule codes (such as Article X of the "Medical Insurance Fund Supervision Regulations").

[0050] Dynamic weights include: time sensitivity, which automatically reduces the blocking intensity in emergency scenarios to ensure priority treatment; historical violation records, in which the number of previous violations by the subject affects the current blocking level.

[0051] Specifically, the preset blocking rules include: rule content and trigger conditions, among which the rule content includes: insurance status verification rules, which verify the validity of patient identity identifiers in payment information, such as medical insurance card numbers and military family ID numbers, to detect whether there is any invalid insurance relationship, expired ID or unregistered cross-regional use; identity superposition restriction rules, which prohibit the same patient from repeatedly enjoying multiple preferential benefits in the same payment cycle, such as using civil servant medical assistance and full compensation from commercial insurance at the same time.

[0052] The triggering conditions include: when it is detected that the patient is not insured, the certificate is invalid, or the benefits are illegally superimposed, the subject qualification dimension is blocked, for example, a red alert may be issued.

[0053] Furthermore, the preset blocking rules also include: item matching rules within the catalog, indication association rules and usage / frequency control rules, settlement method compliance rules, cross-regional settlement filing rules, and time sensitivity exemption rules.

[0054] The matching rules for items within the catalog include: verifying whether payment items such as medicines, medical services, and consumables are within the catalog covered by preferential welfare policies, such as the three major medical insurance catalogs and the list of special medicines for military families.

[0055] Indication association rules include: requiring that the diagnosis and treatment items must have a clear medical logical association with the patient's diagnosis results, such as targeted drugs that are only used by patients with malignant tumors.

[0056] Dosage / frequency control rules include: limiting the maximum single-payment dose or service frequency based on clinical guidelines and welfare policies, such as limiting CT examinations to once a month and antibiotic medication cycles to ≤14 days.

[0057] Compliance rules for settlement methods include: verifying whether the payment channel complies with policy requirements, such as major illness insurance is limited to direct payment by the hospital, and military dependents' subsidies are prohibited from being reimbursed after cash advance.

[0058] Cross-regional settlement filing rules include: checking whether out-of-town medical treatment has completed filing approval or emergency registration. If not filed, cross-provincial hospitalization expenses will only be settled at 30% of the benchmark price.

[0059] Time-sensitivity exemption rules include: relaxing the verification intensity for payment paths in special scenarios such as emergency and rescue, such as allowing registration materials to be completed afterwards.

[0060] Specifically, the blocking level strategy of the blocking rules is divided into: Level 1 blocking rules (systemic violations): involving fictitious medical facts, such as false hospitalization records, malicious withdrawal of funds, such as splitting prescriptions to circumvent the single payment limit, etc., the funds must be frozen in full immediately.

[0061] Secondary blocking rule (technical violation): If overpayment is caused by calculation error and the pooling fund is used directly without deducting the deductible, only the excess amount will be blocked.

[0062] Level 3 blocking rule (information defects): Exceptions caused by missing data or incorrect format, such as failure to fill in the diagnosis code, are allowed to be unblocked after correction within a time limit.

[0063] Specifically, the account blocking order is a risk control instruction generated during the medical payment compliance review process based on preferential benefit policies, payment information verification, and medical logic validation. Its core function is to prevent the flow of non-compliant payment funds and ensure that the medical expense account separation process complies with policies, regulations, and clinical rationale.

[0064] In an embodiment of the present invention, the payment information is verified for payment-medical order association based on the account split blocking instruction to obtain an abnormal payment association list of the payment information; Performing reverse analysis of the account splitting logic on the abnormal payment association list and the account splitting blocking instruction to obtain payment splitting violation characteristics of the payment information; Payment splitting exception information of the payment information is generated based on the payment splitting violation characteristics and a preset diagnosis and treatment price database.

[0065] Specifically, a doctor's order is a treatment plan prescribed by a doctor for a patient's condition, including diagnosis, medication, examination items, etc. For example, a doctor may prescribe a certain medication and require examination items.

[0066] Specifically, the abnormal payment association list is a list of payment information that does not match the medical order or anomalies. For example, if you pay for medicine that is not included in the medical order, it will be included in this list.

[0067] Specifically, through platforms such as hospital information systems, payment information associated with the account splitting blocking instructions is compared with the corresponding medical orders. For example, within the hospital billing system, the patient's drug payment information is compared with the doctor's prescription to verify whether the paid medication is within the prescribed scope. Any issues with the correlation between payment information and prescriptions are identified and compiled into a list of abnormal payment associations.

[0068] Specifically, payment splitting violations are characterized by analyzing and identifying irregularities in the payment splitting process, such as unreasonably splitting expenses that should be settled as a whole into multiple items.

[0069] Furthermore, within the hospital information system backend or related data analysis platform, reverse engineering analysis is performed to identify the anomalies in the abnormal payment list and the triggering cause of the account splitting block instruction. For example, if the account splitting block was caused by an abnormal payment for a particular drug, combined with the payment status of that drug in the abnormal payment list, analysis can reveal that the violation occurred by splitting the high-priced drug expense into multiple lower-priced drug expense settlements.

[0070] Specifically, the preset medical price database is a database that stores standard prices for various medical treatment items, medicines, etc. For example, the charging standards for various examination items stipulated by the local price department.

[0071] Specifically, payment splitting anomaly information includes a description of the payment splitting anomaly, determined by combining the payment splitting violation characteristics and standard price information. For example, it indicates that the total price of a certain medical treatment fee after splitting exceeds the reasonable range in the standard price database.

[0072] Furthermore, within the hospital information system, payment splitting violations are compared and analyzed against a pre-set database of medical treatment prices. For example, if a payment splitting violation is found to be the splitting of a single medical examination fee into multiple charges, the system compares the standard price of that examination in the medical treatment price database to determine whether the split fees are excessive or unreasonable. This generates payment splitting anomaly information, clearly indicating the issue with the payment splitting.

[0073] S3: Based on the preset medical price database and the payment splitting exception information, the payment information is verified for price matching to obtain the compliance price deviation of the payment information; based on the compliance price deviation and the payment splitting exception information, the payment information is judged to have exceeded the price limit to obtain the over-limit payment blocking information of the payment information.

[0074] In this embodiment of the present invention, the calculation formula for the compliance price deviation is:

[0075] in: is the compliance price deviation, For the The actual payment price in the payment information described in the item, For the The actual payment price mentioned in the item corresponds to the standard price threshold in the medical price database. For the The quantitative value of the policy compliance indicator corresponding to the preferential welfare information described in the item, For the The weight of the quantitative value of the policy compliance indicator described in the item, is a time-sensitive regulatory factor. For the The three-dimensional feature values corresponding to the payment splitting abnormal information described in item 1, For the The coupling coefficient of the three-dimensional eigenvalues described in the term, For the The project life cycle decay factor, is the basic deviation coefficient, is the nonlinear deviation amplification exponent, is the total dimension of the three-dimensional eigenvalues, is the three-dimensional eigenvalue, is the total amount of the payment information, The number of the total number of payment information item, The total number of quantitative values for the policy compliance indicator. The total number of quantitative values for the policy compliance indicator item.

[0076] Specifically, Price deviation is a quantitative indicator used to measure the degree of deviation between the actual payment price and the standard price in the payment information. The higher the deviation, the greater the difference between the actual payment price and the standard price, which may indicate unreasonable pricing.

[0077] Specifically, For the The actual payment price in the payment information, the payment flow data collected in real time by the medical institution's charging system, and the diagnosis and treatment item code in the payment information Strict binding.

[0078] For the The standard price threshold in the medical treatment price database corresponding to the actual payment price described in the item is automatically iterated by the benchmark value calibrated by policy in the preset medical treatment price database and the version number of the government guidance price document.

[0079] For the The quantitative value of the policy compliance indicator corresponding to the preferential welfare information described in the item is calculated based on the policy template library. Assign a value (0-1 range) to the satisfaction degree of the quantitative value of the policy compliance indicator.

[0080] For the The weight of the quantitative value of the policy compliance indicator is positively correlated with the effectiveness level of the policy document, for example, ministerial level = 1.0, local level = 0.6.

[0081] Specifically, is a time-sensitive adjustment factor, and its calculation formula is:

[0082] in: is a time-sensitive regulatory factor. is the policy period constant (the default is 365 days), The number of days from the current time to the policy effective date.

[0083] By periodically adjusting the policy enforcement strength through the sine function, the wave-like enforcement characteristics of government supervision are simulated. When the policy is approaching the anniversary revision ( near ), the adjustment factor automatically enhances the compliance review intensity ( peak at 1.1), and in the mid-term ( ) Appropriately relax the standards ( This mechanism accurately reflects the dynamic cycle of policy implementation from tightening to loosening and then tightening in reality.

[0084] Specifically, For the The three-dimensional characteristic values corresponding to the payment splitting abnormal information described in the item include the matching degree between the patient identity and the preferential policy, the mapping strength between the diagnosis and treatment item code and the medical insurance catalog, and the time overlap rate between the payment time and the policy effective window.

[0085] Specifically, For the The calculation formula of the project life cycle decay factor is:

[0086] in: This is the latest revision date of the project price. is the decay rate parameter (default value 0.05 / day), For the The project life cycle decay factor, is a constant, The number of days from the current time to the policy effective date.

[0087] Furthermore, this design significantly improves the temporal adaptability and policy compatibility of the medical payment supervision system, and can effectively reduce the misjudgment rate compared to the traditional fixed weight scheme.

[0088] Specifically, The basic deviation coefficient is obtained by adding 1 to the ratio of the patient's historical violation times to the total number of transactions, so that It can be automatically adjusted according to the credit rating of the medical institution.

[0089] In an embodiment of the present invention, feature level extraction is performed on the payment splitting anomaly information to obtain a quantitative anomaly level code for the payment splitting anomaly information, and interval threshold division is performed on the compliance price deviation to obtain a three-level warning state of the compliance price deviation; Constructing a risk strategy mapping relationship between the quantitative anomaly level code and the three-level warning state, and performing a time window compliance check on the payment information based on the risk strategy mapping relationship and the effective timetable of the preferential benefit information to obtain a time correction deviation of the payment information; performing a blocking strategy match on the payment information based on the time-corrected deviation and the quantitative anomaly level code to obtain a multi-level blocking instruction for the payment information, and performing a cross-system consistency verification operation on the payment information based on the multi-level blocking instruction and a preset system interface protocol to obtain an effective blocking status identifier for the payment information; A reverse data integrity check is performed on the payment information based on the effective blocking status identifier and the pre-acquired historical dispute item list to obtain over-limit payment blocking information of the payment information.

[0090] Specifically, the quantitative anomaly level code is a code representing the degree of anomaly obtained by analyzing and quantifying the characteristics of payment split anomaly information. For example, the degree of anomaly is categorized as low, medium, and high, corresponding to codes A, B, and C, respectively.

[0091] The compliance price deviation is an indicator that measures the degree of difference between the actual payment price in the payment information and the standard price.

[0092] The three-level warning status is divided into three warning levels based on the range threshold of the compliance price deviation. For example, a slight deviation is a level one warning, a moderate deviation is a level two warning, and a severe deviation is a level three warning.

[0093] The risk strategy mapping relationship is, for example, when the quantitative anomaly level code is C and the level 3 warning status is level 3 warning, it corresponds to the most stringent risk control strategy.

[0094] The effective timetable is a table that records the effective and expiration times of various preferential welfare policies, such as the time of medical insurance policy adjustment, the time of hospital preferential activities, etc.

[0095] The time-corrected deviation is the deviation obtained by adjusting the payment information in the time dimension, taking into account the risk strategy mapping relationship and the effective time of the preferential benefit information.

[0096] The list of historical disputed items is a list that records payment items that have been disputed in the past, such as fee calculation disputes, policy application disputes, etc.

[0097] Reverse data integrity check is to check whether the payment information is complete and accurate based on the effective blocking status indicator.

[0098] S4: Establishing a profit feature vector of the payment splitting exception information and the over-limit payment blocking information, and performing a multi-dimensional correlation analysis on the profit feature vector based on a preset profit determination model to obtain a profit determination map of the payment information.

[0099] In an embodiment of the present invention, a payment time sequence analysis is performed on the payment splitting exception information to obtain a time feature of the splitting behavior in the payment splitting exception information; Matching the over-limit payment blocking information with violation behaviors based on a preset payment rule library to obtain a quantitative indicator of violation characteristics in the over-limit payment blocking information; Performing spatiotemporal correlation mapping on the payment information based on the time characteristics of the splitting behavior and the quantitative indicators of the violation characteristics to obtain a spatiotemporal correlation map of abnormal payment information; Performing a rule circumvention effectiveness evaluation on the payment path of the payment information based on the time characteristics of the splitting behavior and the quantitative indicators of the violation characteristics to obtain a rule superposition circumvention strength value; The payment information is multimodal feature encoded based on the spatiotemporal association graph and the rule superposition avoidance strength value to obtain a profit feature vector of the payment information.

[0100] Specifically, the time characteristics of the splitting behavior reflect the characteristics of the abnormal payment splitting behavior in the time dimension, such as the time point, time interval, and concentrated occurrence period of the splitting behavior.

[0101] In the hospital information system or related data analysis platform, abnormal payment splitting information is sorted chronologically. For example, the timing of abnormal splitting in multiple payments for a patient can be examined to analyze whether it occurred at the beginning of the visit, during treatment, or at the time of settlement. The distribution of abnormal splitting behavior within a day or week can be analyzed to summarize the temporal characteristics of the splitting behavior.

[0102] The preset payment rule library is a pre-set database containing various payment-related rules, such as price standards, payment process specifications, fee splitting regulations, etc.

[0103] The quantitative indicators of violation characteristics are to convert the violation behaviors reflected in the over-limit payment blocking information into quantifiable indicators according to certain standards, such as the proportion of the amount involved in the violation, the number of violation items, etc.

[0104] The spatiotemporal correlation map is: , which graphically displays payment information in time and space. It can be understood as the correlation between abnormal behaviors in dimensions such as different medical treatment items and departments, and intuitively presents the distribution of abnormal payment information.

[0105] The payment path refers to the process and means by which patients pay fees, involving the order of payment links, the systems or departments passed through, etc.

[0106] Rule circumvention effectiveness assessment is to evaluate the ability and effectiveness of circumventing payment rules through various means during the payment process.

[0107] The rule superposition circumvention intensity value is a numerical value that quantifies the intensity and comprehensive effect of circumventing payment rules during the payment process.

[0108] In the embodiment of the present invention, the calculation formula of the preset profit determination model is:

[0109] in: To determine the profit map, is the compliance price deviation, For payment splitting abnormal information, For policy exemption matching, is the policy coverage factor, is the patient identity weight factor, is the historical correlation coefficient, is the logarithmic protection constant, is the price deviation enhancement index, is the time decay parameter, is the normalization coefficient, is the event axis influence, Denominator offset protection amount.

[0110] Specifically, To form a profit determination map, multiple dimensions of information are integrated through mathematical models.

[0111] It should be noted that the term “atlas” does not refer to visual graphics, but borrows the abstract meaning of “atlas” to represent the result of integrating multiple dimensional information through mathematical models.

[0112] The final calculation result of the profit determination map is a normalized value representing the comprehensive risk score of the current payment information. The range of its value is determined by the model parameters and the distribution dynamics of the input data.

[0113] It is a comprehensive risk indicator of potential violations or arbitrage behaviors in medical payment behaviors, quantified by mathematical models. The larger the value, the more likely the current payment information is to trigger overpayment blocking, such as inflated prices, abnormal account splitting or policy violations.

[0114] The goal is to dynamically determine whether the payment process needs to be intervened, such as allowing, warning or blocking, under the constraints of multiple dimensions such as price, order splitting, policy, historical behavior, identity, and time.

[0115] Specifically, To pay for abnormal splitting information, a comprehensive score can be assigned based on the number of splits, amount dispersion, and relevance of medical orders. The range can be analyzed based on historical data, for example, 0-5 points.

[0116] Specifically, It is the policy exemption matching degree, and in order to allow policy incentives to exceed the limit, the range can be divided into 0.6~1.2.

[0117] Specifically, The historical correlation coefficient is the similarity between the current payment plan and historical behavior.

[0118] Specifically, The denominator offset protection is a fixed value (such as 0.5) to prevent calculation overflow caused by sudden changes in historical data.

[0119] Specifically, It is the patient identity weight factor, which can be assigned according to the patient identity database, such as veterans =0.3, severe patients =0.7, default =1.0.

[0120] Specifically, The time decay parameter is an empirical value =0.8, reflecting the marginal diminishing effect of payment delay risk.

[0121] Specifically, The purpose is to weaken the excessive influence of privileged identities on the model, such as preventing privileged identities from shielding high-risk payments.

[0122] Specifically, is the policy coverage factor, which automatically reduces the impact of outdated policies on risk assessment. The calculation formula is:

[0123] in: is the policy coverage factor, is the expert experience coefficient.

[0124] The policy coverage factor is a key parameter extracted from a library of policy templates in government policy documents. It is used to dynamically mitigate the impact of outdated policies on payment risk assessments, avoiding misjudgments due to policy iterations or lapses in timeliness. Essentially, it represents the weighting of policy timeliness, determining the effective coverage of the current policy within the risk model.

[0125] The expert experience coefficient represents the annual decay rate of policy influence, and the default value can be 0.1.

[0126] S5: Performing a confidence analysis on the payment information based on the profit determination map to obtain a blocking threshold matrix for the payment information, and performing a risk classification analysis on the payment information based on the blocking threshold matrix to obtain a payment plan for the payment information.

[0127] In an embodiment of the present invention, a gradient risk assessment is performed on the payment information based on the blocking threshold matrix and the compliance price deviation to obtain a risk level distribution of the payment information; quantifying the superimposed risk of the payment information based on the risk level distribution and the payment splitting anomaly information to obtain an excess risk value of the payment information; Adapting the exemption policy of the payment information based on the excess risk value and historical data of the payment information to obtain a dynamic blocking rule for the payment information; Based on the dynamic blocking rules and the policy template library in the preferential welfare information, an account splitting path is generated for the payment information to obtain a payment plan for the payment information.

[0128] Specifically, the gradient risk assessment is to combine the threshold in the matrix with the price deviation range, such as a 30% overprice, to divide the risk areas into high, medium and low risk areas, and generate a grade label with tolerance.

[0129] The superimposed risk is quantified as follows: when the abnormal frequency of splitting, such as more than three split payments in a single day, exists at the same time as the high risk level, the risk value will be doubled. The excess risk value will be calculated for transactions with multiple abnormalities, and transactions with only a single risk will be treated as baseline.

[0130] Specifically, the dynamic blocking rules adjust the risk value determination criteria based on the patient's historical behavior, such as previous overpayments that are legal and policy exemptions, such as military medical subsidies.

[0131] For patients with good reputation, such as those with no violation records within three years, the risk value threshold is allowed to float up, such as from 100 to 115; for patients with a history of violations, such as false reimbursement records, the threshold is tightened to 80 and sensitive interception is implemented.

[0132] Specifically, the payment plan adopts a phased and channel-based settlement scheme. For example, in high-risk transactions, all funds will be frozen first, then transferred to manual review. Once the review is passed, the payment will be made in stages at a 50% ratio.

[0133] In low-risk transactions, real-time settlement is performed first, then 80% is deducted from the medical insurance account, and finally the self-paid portion is automatically deducted; In the exemption scenario, military patients directly prepay 90% and then submit additional materials for settlement later.

[0134] By implementing phased payments, such as releasing funds in stages after freezing high-risk transactions, we can protect the security of medical insurance funds while avoiding delays in patient diagnosis and treatment due to excessive interception. For example, for urgent treatment payments suspected of being in violation of regulations, we allow a 50% advance payment with subsequent review, preventing misuse of funds while ensuring timely treatment.

[0135] S6: Performing a historical correlation analysis on the payment plan based on the patient's historical data to obtain a billing method for the medical payment.

[0136] In an embodiment of the present invention, a historical-current comparison relationship between the patient's historical payment data and the payment information is established; Performing a historical retrospective verification operation on the payment plan based on the historical-current comparison relationship and a preset dispute payment scenario library to obtain a payment scenario compatibility value of the payment plan; The payment plan is bound with account splitting conditions based on the payment scenario compatibility value and the history-current comparison relationship to obtain the account splitting method of the medical payment.

[0137] Specifically, the historical-current comparison relationship provides a field-level mapping relationship between historical payment data and current rules, such as commercial insurance settlement cycle field mapping verification.

[0138] The dispute payment scenario library contains standardized templates for historical refunds, appeals, policy deductions and other scenarios, such as the coding of conflict scenarios for cross-year settlement of chronic disease subsidies.

[0139] Specifically, historical retrospective verification operation refers to the technical process of systematically matching and testing current payment rules with typical payment scenarios that occurred to patients in the past.

[0140] Specifically, the account splitting method is a specific payment allocation strategy that dynamically adapts to patients' payment characteristics and policy constraints after historical correlation analysis and rule modification.

[0141] For example, patient A's historical payment data shows that the medical insurance settlement delay rate is 5% (low risk), the commercial insurance rejection rate due to incomplete materials is 30% (high risk), and the proportion of out-of-pocket payments has remained stable at 20% for a long time.

[0142] The payment source priority splitting method can be used at this time: Priority rule: Medical insurance deductions are made first (accounting for 60%), followed by self-payment (20%), and finally commercial insurance deductions (20%); Dynamic adjustment: If the 20% required to be paid by commercial insurance cannot be deducted in real time due to material issues, the self-funded temporary advance payment mechanism will be immediately triggered.

[0143] For example, patient D's chronic disease subsidy did not take effect due to historical rules being delayed, resulting in overpayment out of pocket.

[0144] The account splitting steps that can be adopted at this time are the policy dynamic adaptation account splitting method: Before billing, it is mandatory to match the medical treatment items with the current policy label library, such as the chronic disease catalog version V2.3. If it is detected that the historical compliance policy is not applicable, the compensation amount will be automatically transferred from the government subsidy pool to the patient's account.

[0145] like Figure 2 FIG. 1 is a functional module diagram of a medical multi-source payment intelligent account splitting system provided by one embodiment of the present invention.

[0146] The medical multi-source payment intelligent account splitting system 100 described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the medical multi-source payment intelligent account splitting system 100 may include an information collection module 101, an abnormality analysis module 102, a blocking instruction generation module 103, a graph generation module 104, a payment planning module 105, and an account splitting method generation module 106. The modules described in the present invention, also referred to as units, refer to a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and are stored in the electronic device's memory.

[0147] In this embodiment, the functions of each module / unit are as follows: Information collection module 101: used to obtain payment information and preferential benefit information of patients corresponding to medical payment; Abnormality analysis module 102: configured to perform compliance adaptation on the payment information based on the preferential benefit information to obtain an account splitting blocking instruction for the payment information, and perform medical order matching verification on the payment information based on the account splitting blocking instruction to obtain payment splitting abnormality information for the payment information; Blocking instruction generation module 103: configured to perform price matching verification on the payment information based on a preset medical price database and the payment splitting anomaly information to obtain a compliance price deviation of the payment information, and perform price over-limit determination on the payment information based on the compliance price deviation and the payment splitting anomaly information to obtain over-limit payment blocking information for the payment information; A graph generation module 104 is configured to establish a profit feature vector for the payment splitting anomaly information and the over-limit payment blocking information, and perform a multi-dimensional correlation analysis on the profit feature vector based on a preset profit determination model to obtain a profit determination graph for the payment information; Payment planning module 105: configured to perform a confidence analysis on the payment information based on the profit determination map to obtain a blocking threshold matrix for the payment information, and perform a risk classification analysis on the payment information based on the blocking threshold matrix to obtain a payment plan for the payment information; The account splitting method generating module 106 is configured to perform a historical correlation analysis on the payment plan based on the patient's historical data to obtain the account splitting method for the medical payment.

[0148] In the several embodiments provided by the present invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0149] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0150] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0151] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0152] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A smart bill splitting method for multi-source medical payment, characterized by: The method comprises: S1: Obtain the payment information and preferential benefit information of the patient corresponding to the medical payment; S2: Based on the preferential benefit information, the payment information is subjected to compliance adaptation to obtain an account splitting blocking instruction for the payment information; based on the account splitting blocking instruction, the payment information is subjected to medical order matching verification to obtain payment splitting exception information for the payment information; S3: Based on a preset medical price database and the payment splitting anomaly information, the payment information is verified for price matching to obtain a compliance price deviation of the payment information. Based on the compliance price deviation and the payment splitting anomaly information, a price over-limit determination is performed on the payment information to obtain over-limit payment blocking information of the payment information. S4: Establishing a profit feature vector of the payment splitting exception information and the over-limit payment blocking information, and performing a multi-dimensional correlation analysis on the profit feature vector based on a preset profit determination model to obtain a profit determination map of the payment information; S5: performing a confidence analysis on the payment information based on the profit determination map to obtain a blocking threshold matrix for the payment information, and performing a risk classification analysis on the payment information based on the blocking threshold matrix to obtain a payment plan for the payment information; S6: Performing a historical correlation analysis on the payment plan based on the patient's historical data to obtain a billing method for the medical payment.

2. The intelligent account splitting method for multi-source medical payment according to claim 1, characterized in that: The step of performing compliance adaptation on the payment information based on the preferential benefit information to obtain an account splitting blocking instruction for the payment information includes: Performing rule cross-mapping based on the preferential benefit information and the payment information to obtain a list of illegal payments of the payment information; performing dynamic payment verification based on the list of illegal payments and the payment information to obtain payment link abnormality information of the payment information; Performing a three-dimensional matching of account splitting rules on the payment information based on the payment link abnormality information and the preset blocking rules to obtain an account splitting blocking condition matrix for the payment information; A blocking instruction generation operation is performed based on the account split blocking condition matrix and the blocking level strategy in the blocking rule to obtain the account split blocking instruction of the payment information.

3. The intelligent account splitting method for multi-source medical payment according to claim 1, characterized in that: The performing of medical order matching verification on the payment information based on the account split blocking instruction to obtain payment split exception information of the payment information includes: Performing payment-order correlation verification on the payment information based on the account split blocking instruction to obtain an abnormal payment correlation list of the payment information; Performing reverse analysis of the account splitting logic on the abnormal payment association list and the account splitting blocking instruction to obtain payment splitting violation characteristics of the payment information; Payment splitting exception information of the payment information is generated based on the payment splitting violation characteristics and a preset diagnosis and treatment price database.

4. The intelligent account splitting method for multi-source medical payment according to claim 3, characterized in that: The calculation formula for the compliance price deviation is: ， in: is the compliance price deviation, For the The actual payment price in the payment information described in the item, For the The actual payment price mentioned in the item corresponds to the standard price threshold in the medical price database, For the The quantitative value of the policy compliance indicator corresponding to the preferential welfare information described in the item, For the The weight of the quantitative value of the policy compliance indicator described in the item, is a time-sensitive regulatory factor. For the The three-dimensional feature values corresponding to the payment splitting abnormal information described in item 1, For the The coupling coefficient of the three-dimensional eigenvalues described in the term, For the The project life cycle decay factor, is the basic deviation coefficient, is the nonlinear deviation amplification exponent, is the total dimension of the three-dimensional eigenvalues, is the three-dimensional eigenvalue, is the total amount of the payment information, The number of the total number of payment information item, The total number of quantitative values for the policy compliance indicator. The total number of quantitative values for the policy compliance indicator item.

5. The intelligent account splitting method for multi-source medical payment according to claim 4, characterized in that: The performing price over-limit determination on the payment information based on the compliance price deviation and the payment splitting exception information to obtain over-limit payment blocking information of the payment information includes: Performing feature level extraction on the payment splitting anomaly information to obtain a quantitative anomaly level code for the payment splitting anomaly information, and performing interval threshold division on the compliance price deviation to obtain a three-level warning state of the compliance price deviation; Constructing a risk strategy mapping relationship between the quantitative anomaly level code and the three-level warning state, and performing a time window compliance check on the payment information based on the risk strategy mapping relationship and the effective timetable of the preferential benefit information to obtain a time correction deviation of the payment information; performing a blocking strategy match on the payment information based on the time-corrected deviation and the quantitative anomaly level code to obtain a multi-level blocking instruction for the payment information, and performing a cross-system consistency verification operation on the payment information based on the multi-level blocking instruction and a preset system interface protocol to obtain an effective blocking status identifier for the payment information; A reverse data integrity check is performed on the payment information based on the effective blocking status identifier and the pre-acquired historical dispute item list to obtain over-limit payment blocking information of the payment information.

6. The intelligent account splitting method for multi-source medical payment according to claim 1, characterized in that: The step of establishing a profit feature vector of the payment splitting exception information and the over-limit payment blocking information includes: Performing payment time sequence analysis on the payment splitting exception information to obtain a time feature of the splitting behavior in the payment splitting exception information; Matching the over-limit payment blocking information with violation behaviors based on a preset payment rule library to obtain a quantitative indicator of violation characteristics in the over-limit payment blocking information; Performing spatiotemporal correlation mapping on the payment information based on the time characteristics of the splitting behavior and the quantitative indicators of the violation characteristics to obtain a spatiotemporal correlation map of abnormal payment information; Performing a rule circumvention effectiveness evaluation on the payment path of the payment information based on the time characteristics of the splitting behavior and the quantitative indicators of the violation characteristics to obtain a rule superposition circumvention strength value; The payment information is multimodal feature encoded based on the spatiotemporal association graph and the rule superposition avoidance strength value to obtain a profit feature vector of the payment information.

7. The intelligent account splitting method for multi-source medical payment according to claim 1, characterized in that: The calculation formula of the preset profit determination model is: ， in: To determine the profit map, is the compliance price deviation, For payment splitting abnormal information, For policy exemption matching, is the policy coverage factor, is the patient identity weight factor, is the historical correlation coefficient, is the logarithmic protection constant, is the price deviation enhancement index, is the time decay parameter, is the normalization coefficient, is the event axis influence, Denominator offset protection amount.

8. The intelligent account splitting method for multi-source medical payment according to claim 1, characterized in that: The performing risk classification analysis on the payment information based on the blocking threshold matrix to obtain a payment plan for the payment information includes: Performing a graded risk assessment on the payment information based on the blocking threshold matrix and the compliance price deviation to obtain a risk level distribution of the payment information; quantifying the superimposed risk of the payment information based on the risk level distribution and the payment splitting anomaly information to obtain an excess risk value of the payment information; Adapting the exemption policy of the payment information based on the excess risk value and historical data of the payment information to obtain a dynamic blocking rule for the payment information; Based on the dynamic blocking rules and the policy template library in the preferential welfare information, an account splitting path is generated for the payment information to obtain a payment plan for the payment information.

9. The intelligent account splitting method for multi-source medical payment according to claim 8, characterized in that: The performing of a historical correlation analysis on the payment plan based on the patient's historical data to obtain a billing method for the medical payment includes: Establishing a historical-current comparison relationship between the patient's historical payment data and the payment information; Performing a historical retrospective verification operation on the payment plan based on the historical-current comparison relationship and a preset dispute payment scenario library to obtain a payment scenario compatibility value of the payment plan; The payment plan is bound with account splitting conditions based on the payment scenario compatibility value and the history-current comparison relationship to obtain the account splitting method of the medical payment.

10. A medical multi-source payment intelligent account splitting system, characterized by: The system comprises: Information collection module: used to obtain the payment information and preferential benefit information of patients corresponding to medical payments; Anomaly analysis module: configured to perform compliance adaptation on the payment information based on the preferential benefit information to obtain an account splitting blocking instruction for the payment information, and perform medical order matching verification on the payment information based on the account splitting blocking instruction to obtain payment splitting anomaly information of the payment information; A blocking instruction generation module is configured to perform price matching verification on the payment information based on a preset medical price database and the payment splitting anomaly information to obtain a compliance price deviation of the payment information, and perform price over-limit determination on the payment information based on the compliance price deviation and the payment splitting anomaly information to obtain over-limit payment blocking information of the payment information; A graph generation module is used to establish a profit feature vector for the payment splitting exception information and the over-limit payment blocking information, and perform a multi-dimensional correlation analysis on the profit feature vector based on a preset profit determination model to obtain a profit determination graph for the payment information; Payment planning module: used to perform confidence analysis on the payment information based on the profit determination map to obtain a blocking threshold matrix for the payment information, and perform risk classification analysis on the payment information based on the blocking threshold matrix to obtain a payment plan for the payment information; The account splitting method generating module is used to perform a historical correlation analysis on the payment plan based on the patient's historical data to obtain the account splitting method of the medical payment.

Images