Digital fund backflow prevention control method and system for mass health industry

Abstract

The invention relates to the technical field of fund management in the massive health industry, in particular to a digital fund backflow prevention control method and system for the massive health industry. The method comprises the following steps: acquiring and integrating multi-source data of the large health industry, and extracting fund backflow risk features; a multi-dimensional index early warning system is constructed, the current fund flow direction is monitored in real time, the abnormity of the current fund flow direction is identified, and risk level early warning is sent out; setting a differentiated disposal strategy according to the risk level, taking grading measures, continuously tracking the disposal effect and dynamically adjusting the disposal strategy; the system comprises a data acquisition and analysis module, a risk early warning and fund flow direction detection module and a risk dynamic disposal module. Through the above mode, multi-source data fusion analysis, real-time risk monitoring and graded dynamic disposal are realized, so that the accuracy and timeliness of fund backflow risk prevention and control are improved, and the compliance and safety of fund flow in the large health industry are guaranteed.

Description

Technical Field

[0001] This invention relates to the field of fund management technology in the big health industry, and in particular to a digital method and system for preventing fund backflow control in the big health industry. Background Technology

[0002] With the deepening of medical reform and the integration of digital technology, the big health industry has formed a complex industrial chain covering multiple links such as pharmaceutical research and development, production, distribution, medical services, medical insurance settlement, and health management. The flow of funds is characterized by many participating entities, long circulation paths, and complex transaction scenarios.

[0003] Currently, the healthcare industry's methods for preventing the repatriation of funds still primarily rely on manual verification and post-event audits. This involves staff meticulously comparing transaction contracts, fund flows, and business vouchers, consuming significant manpower and limited by their efficiency and experience. This approach struggles to cover the entire industry chain's fund flow scenarios and cannot capture cross-stage, highly concealed fund repatriation risks in real time. Furthermore, the existing prevention and control system lacks standardized risk warning mechanisms and dynamic handling procedures. On one hand, different companies or regulatory departments have varying definitions of "abnormal fund flows," leading to a lack of consistency and authority in risk warnings. On the other hand, when faced with risk warnings, a "one-size-fits-all" approach is often adopted, failing to develop differentiated measures based on the severity of the risk. This can result in either excessive control impacting normal business operations or insufficient handling leading to the spread of risk. In summary, the current big health industry faces problems such as low risk identification efficiency and an incomplete early warning mechanism in the prevention and control of fund repatriation. Therefore, there is an urgent need for a control method that can achieve multi-source data fusion analysis, real-time risk monitoring, and hierarchical dynamic handling to improve the accuracy and timeliness of fund repatriation risk prevention and control, and ensure the compliance and security of fund flow in the big health industry. Summary of the Invention

[0004] The purpose of this invention is to provide a digital method and system for preventing the return of funds in the big health industry, aiming to solve the problems of low risk identification efficiency and inadequate early warning mechanism in the prevention and control of fund return in the existing technology.

[0005] To achieve the above objectives, this invention employs a digital anti-fund reflux control method for the big health industry, comprising the following steps: Acquire and integrate multi-source data from the big health industry to extract risk characteristics of fund repatriation; Construct a multi-dimensional indicator early warning system to monitor the current flow of funds in real time, identify abnormalities in the current flow of funds, and issue risk level warnings. Differentiated response strategies are set according to risk levels, tiered measures are adopted, and the effectiveness of the response is continuously tracked and the response strategies are dynamically adjusted.

[0006] Among the steps involved in acquiring and integrating multi-source data from the healthcare industry and extracting risk characteristics of fund repatriation: We collect raw data from the big health industry through multiple channels and clean and process the collected multi-source data. Extract abnormal feature variables; among which abnormal feature variables include abnormal transaction frequency, closed-loop fund flow, and high proportion of transactions by related entities.

[0007] Among the steps involved in collecting raw data from the big health industry through multiple channels and cleaning and processing the collected multi-source data: Remove duplicate, erroneous, and incomplete data, standardize data formats and standards, and form a standardized dataset.

[0008] After extracting anomalous characteristic variables, including abnormal transaction frequency, closed-loop fund flows, and a high proportion of transactions involving related entities: By filtering and optimizing abnormal characteristic variables, core risk characteristics are obtained, and a risk characteristic database of fund repatriation is constructed.

[0009] Among the steps involved in building a multi-dimensional indicator early warning system, monitoring current fund flows in real time, identifying anomalies in current fund flows, and issuing risk level warnings: A multi-level early warning indicator system is constructed by selecting key indicators from the dimensions of the relevance of the transaction entities, the timeliness of fund flows, and the reasonableness of amount fluctuations; among which the key indicators include the overlap of transaction counterparties, the fund turnover cycle, and the deviation of a single transaction; It connects to various data sources in real time and dynamically tracks the flow and status of funds in multiple stages; The real-time monitoring data is compared and analyzed with the early warning indicator system.

[0010] Before the step of real-time connection to various data sources and dynamic tracking of the flow and status of funds across multiple stages: The threshold range of the early warning indicators is dynamically adjusted, and they are divided into three risk levels: high, medium, and low.

[0011] Among the steps involved in comparing and analyzing real-time monitoring data with the early warning indicator system: When an indicator exceeds the corresponding threshold, a risk warning signal sending request is triggered.

[0012] Among the steps are: setting differentiated treatment strategies based on risk levels, adopting tiered measures, continuously tracking the treatment effects, and dynamically adjusting the treatment strategies; In response to high-risk warnings, a primary strategy will be implemented. In response to the medium-risk warning, a secondary strategy will be implemented. For low-risk warnings, a three-tiered strategy will be implemented.

[0013] Among the steps are: setting differentiated treatment strategies based on risk levels, adopting tiered measures, continuously tracking the treatment effects, and dynamically adjusting the treatment strategies; Establish a mechanism to track the effectiveness of the response, adjust the response strategy according to the changing trends of risks, and form a closed-loop management system.

[0014] This invention also provides a digital anti-funds-backflow control system for the big health industry, including a data acquisition and analysis module, a risk warning and funds flow detection module, and a dynamic risk management module; wherein: The data acquisition and analysis module is used to acquire and integrate multi-source data from the big health industry and extract risk characteristics of capital repatriation. The risk warning and fund flow detection module is used to build a multi-dimensional indicator warning system, monitor the current fund flow in real time, identify abnormal fund flows, and issue risk level warnings. The risk dynamic management module is used to set differentiated management strategies based on risk levels, take tiered measures, continuously track the management effect, and dynamically adjust the management strategies.

[0015] This invention discloses a digital method and system for preventing the backflow of funds in the health industry. The system comprises a data acquisition and analysis module, a risk warning and fund flow detection module, and a dynamic risk management module, which perform the following steps: acquiring and integrating multi-source data from the health industry to extract risk characteristics of fund backflow; constructing a multi-dimensional indicator early warning system to monitor current fund flows in real time, identify anomalies in current fund flows, and issue risk level warnings; setting differentiated management strategies based on risk levels, implementing tiered measures, continuously tracking management effectiveness, and dynamically adjusting management strategies; through the above methods, multi-source data fusion analysis, real-time risk monitoring, and tiered dynamic management are achieved to improve the accuracy and timeliness of fund backflow risk prevention and control, and to ensure the compliance and security of fund flows in the health industry. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the steps of the digital anti-fund backflow control method for the big health industry of the present invention.

[0018] Figure 2 This is a flowchart of steps S100 of the present invention.

[0019] Figure 3 This is a flowchart of steps S200 of the present invention.

[0020] Figure 4 This is a flowchart of steps S300 of the present invention.

[0021] Figure 5 This is a schematic diagram of the structure of the digital anti-fund backflow control system for the big health industry of the present invention.

[0022] Figure 6 This is a schematic diagram of the electronic device of the present invention.

[0023] 401 - Data Acquisition and Analysis Module, 402 - Risk Warning and Fund Flow Detection Module, 403 - Dynamic Risk Management Module. Detailed Implementation

[0024] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0025] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0026] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0027] Please see Figures 1-4 This invention provides a digital method for preventing the return of funds in the big health industry, comprising the following steps: S100: Acquire and integrate multi-source data from the big health industry to extract risk characteristics of fund repatriation.

[0028] In this implementation, multi-source data from the big health industry is acquired and integrated to extract characteristics of fund repatriation risk. The specific process is as follows: S101: Collect raw data from the big health industry from multiple channels, clean and process the collected multi-source data, remove duplicate, erroneous and incomplete data, unify data format and standards, and form a standardized dataset; S102: Extract anomalous feature variables from the normalized dataset; among which anomalous feature variables include abnormal transaction frequency, closed-loop fund flow, and high proportion of transactions by related entities; S103: Filter and optimize from abnormal feature variables to obtain core risk features and build a fund return risk feature library.

[0029] In the aforementioned process, raw data is collected from multiple channels, including the HIS (Hospital Information System) and LIS (Laboratory Information System) systems of medical institutions, reimbursement records and payment flows from medical insurance settlement platforms, outbound ledgers and distributor agreements of pharmaceutical manufacturers, transaction orders and payment records from pharmaceutical e-commerce platforms, and corporate / private fund transfer details from financial institutions. This data covers transaction entities (such as hospitals, pharmaceutical companies, patients, and distributors), business information (such as drug names, treatment items, and service types), and financial data (such as transaction amounts, payment times, and settlement methods). The collected multi-source data is cleaned, duplicate records are removed through field matching, errors are corrected based on business rules (such as abnormal amounts and logically contradictory transaction times), incomplete data (such as missing counterparty information) is supplemented through interpolation or correlation, and the data format is standardized to ultimately form a structured and standardized dataset. The standardized data format includes, for example: The date format should be standardized to YYYY-MM-DD, and the monetary unit should be standardized to yuan.

[0030] Based on typical patterns of capital repatriation in the healthcare industry (such as closed-loop circulation of "pharmaceutical company → distributor → hospital → pharmaceutical company" and high-frequency, small-amount transactions between related companies), three types of anomalous feature variables are extracted from the standardized dataset: Abnormal transaction frequency: The number of transactions between the same entity in a short period of time is significantly higher than the industry average (e.g., the number of monthly transactions between a pharmaceutical company and a hospital is more than 5 times that of similar collaborations). Closed-loop fund flow: After flowing through three or more related entities, the funds eventually flow back to the initial payer (e.g., the patient's medical insurance reimbursement funds flow back to the pharmaceutical company after passing through pharmacies and distributors). High proportion of transactions with related entities: The transaction amount between a certain entity and its related enterprises (such as upstream and downstream companies controlled by the same legal person) accounts for more than 60% of its total transaction amount.

[0031] By assessing the importance of features (such as retrospective analysis based on historical risk cases), the core features that contribute the most to the identification of fund repatriation risk are selected (such as the combination of "closed-loop fund flow + related entity transaction ratio > 80%)", and redundant or low-discrimination features (such as occasional single large transactions) are eliminated. The selected core features are classified and stored according to risk type (such as medical insurance fraud and inflated costs) to build a dynamically updated fund repatriation risk feature library.

[0032] S200: Construct a multi-dimensional indicator early warning system to monitor the current flow of funds in real time, identify abnormalities in the current flow of funds, and issue risk level warnings.

[0033] In this implementation, a multi-dimensional indicator early warning system is constructed to monitor the current flow of funds in real time, identify anomalies in the current fund flow, and issue risk level warnings. The specific process is as follows: S201: Select key indicators from the dimensions of transaction entity relevance, timeliness of fund flow, and reasonableness of amount fluctuations to construct a multi-level early warning indicator system; among which key indicators include counterparty overlap, fund turnover cycle, and deviation of single transaction; S202: Dynamically adjust the threshold range of early warning indicators and classify them into three risk levels: high, medium, and low. S203: Real-time connection to various data sources, dynamically tracking the flow path and status of funds in multiple stages; S204: Compare and analyze real-time monitoring data with the early warning indicator system. When an indicator exceeds the corresponding threshold, trigger a risk warning signal sending request.

[0034] In the above process, key indicators are selected from three dimensions to construct a multi-level early warning system consisting of basic indicators, composite indicators, and risk labels: Dimensions of transaction entity relevance: Select the degree of overlap of counterparties (the proportion of common transaction objects between a certain entity and another entity) and the proportion of equity related transactions (the proportion of transaction amount with related enterprises). Timeliness of cash flow: Select cash turnover cycle (the interval between the outflow and return of the same cash) and cross-stage payment delay (such as the deviation between the time from drug delivery to hospital payment and the industry average). Reasonableness of amount fluctuations: Select the deviation of a single transaction (the ratio of the difference between the amount of a single transaction and the average amount of this type of business) and the volatility of monthly transaction amount (the fluctuation range of the monthly transaction amount compared with the average of the past 6 months).

[0035] Based on the statistical distribution (mean, standard deviation) of normal industry transaction data over the past three years and the threshold characteristics of historical risk cases, initial normal ranges for each indicator are set (e.g., "capital turnover cycle < 90 days" and "single transaction deviation < 30%"). Each quarter, based on newly added normal transaction data and risk events, the thresholds are dynamically adjusted using machine learning models (e.g., lowering the threshold when the overall capital turnover cycle of similar companies shortens). Risk levels are then categorized according to the severity of indicators exceeding the thresholds. High risk: Three or more core indicators exceed the threshold, or one indicator exceeds the threshold by more than twice (e.g., deviation of a single transaction > 60%). Medium risk: 1-2 core indicators exceed the threshold, and the exceedance is between 1 and 2 times; Low risk: A single non-core indicator exceeds the threshold, or the magnitude of the exceedance is less than 1.

[0036] By connecting to data sources such as medical institutions, medical insurance platforms, and financial institutions in real time through API interfaces, and using stream processing technology (such as Kafka) to receive real-time transaction data, and combining blockchain technology to record key nodes of fund flow (such as payment initiation, intermediate transfer, and final receipt), a fund flow graph is dynamically generated to intuitively display the path and status of funds in pharmaceutical production, distribution, consumption, and medical insurance reimbursement (such as stagnation, acceleration, and abnormal jumps).

[0037] The system compares real-time monitored fund flow data with the early warning indicator system and triggers verification logic through the rule engine (e.g., when the overlap of counterparties is greater than 70% and the fund turnover cycle is less than 30 days, the related transaction risk verification is triggered). If the indicator exceeds the threshold of the corresponding risk level, the system automatically generates an early warning report containing the risk subject, abnormal indicators, and fund path, and pushes it to risk control management personnel through SMS, system pop-ups, etc., while marking the relevant transactions as "pending verification".

[0038] S300: Set differentiated handling strategies based on risk levels, adopt tiered measures, continuously track the handling effects, and dynamically adjust the handling strategies.

[0039] In this implementation, differentiated treatment strategies are set according to risk levels, tiered measures are adopted, and the treatment effects are continuously tracked and the treatment strategies are dynamically adjusted. The specific process is as follows: S301: Implement Level 1 strategies in response to high-risk warnings; S302: Implement secondary strategies in response to medium-risk warnings; S303: Implement a three-tiered strategy for low-risk early warnings; S304: Establish a mechanism for tracking the effectiveness of disposal, adjust disposal strategies according to the trend of risk changes, and form a closed-loop management.

[0040] In the aforementioned process, in response to high-risk warnings, a Level 1 response strategy is implemented: immediately freeze the fund accounts involved in abnormal transactions (such as suspending medical insurance fund payments to a hospital), suspend the business permissions of relevant entities (such as prohibiting a pharmaceutical company from participating in drug bidding); at the same time, a special investigation team is launched to collect transaction contracts, logistics vouchers, personnel relationship certificates, and other materials to verify whether there are any illegal acts such as fictitious business or forged documents; if violations are confirmed, the case is transferred to the regulatory authorities for handling, and the relevant entities are added to the industry blacklist.

[0041] In response to medium-risk warnings, a level-two response strategy is implemented: suspend the approval process for related businesses (such as temporarily suspending the medical insurance designation qualification review of a certain pharmacy), send a "Risk Warning Letter" to the transaction entity, requiring it to provide supplementary proof of the transaction's rationality within 3 working days (such as genuine drug warehousing records and patient medical records); arrange for risk control personnel to conduct face-to-face interviews with the transaction entity to verify the transaction background; if the supporting materials cannot explain the anomalies, the response is upgraded to high-risk.

[0042] For low-risk warnings, a three-tiered response strategy is implemented: a risk alert is sent to the trading entity, prompting it to self-check the compliance of its transactions (such as verifying whether there are any discrepancies in the amount due to operational errors); the monitoring frequency of the entity's transactions in the following three months is increased (such as from once a day to once an hour), and its transaction behavior is recorded to see if it continues to be abnormal; if three consecutive low-risk warnings occur, the response is upgraded to medium-risk.

[0043] Establish a mechanism to track the effectiveness of risk mitigation and set risk mitigation assessment indicators (such as the termination rate of abnormal transactions and the time it takes for fund flows to return to normal). Review the risk events that have been handled every two weeks and analyze the actual effect of the handling measures on risk mitigation (such as whether abnormal fund flows stop after freezing accounts in high-risk events). Adjust the handling strategy based on the review results (for example, if a certain type of medium-risk event can be resolved by supplementing materials, shorten the material review cycle), and update the adjusted strategy to the system rule base to form a closed-loop management of "early warning-handling-assessment-optimization".

[0044] This invention first acquires and integrates multi-source data from the healthcare industry to extract risk characteristics of fund repatriation; then, it constructs a multi-dimensional indicator early warning system to monitor the current fund flow in real time, identify anomalies in the current fund flow, and issue risk level warnings; finally, it sets differentiated disposal strategies based on risk levels, adopts tiered measures, continuously tracks the disposal effects, and dynamically adjusts the disposal strategies; through the above methods, it achieves multi-source data fusion analysis, real-time risk monitoring, and tiered dynamic disposal, thereby improving the accuracy and timeliness of fund repatriation risk prevention and control, and ensuring the compliance and security of fund flows in the healthcare industry.

[0045] Corresponding to the aforementioned embodiments of the digital anti-fund backflow control method in the big health industry, this application also provides embodiments of the digital anti-fund backflow control system in the big health industry.

[0046] Figure 5 This is a block diagram illustrating a digital anti-cash-flow control system for the big health industry, according to an exemplary embodiment. (Refer to...) Figure 5 The system may include: a data acquisition and analysis module 401, a risk warning and fund flow detection module 402, and a dynamic risk management module 403; wherein: The data acquisition and analysis module 401 is used to acquire and integrate multi-source data from the big health industry and extract risk characteristics of capital repatriation. The risk warning and fund flow detection module 402 is used to construct a multi-dimensional indicator warning system, monitor the current fund flow in real time, identify abnormalities in the current fund flow and issue risk level warnings. The risk dynamic handling module 403 is used to set differentiated handling strategies according to the risk level, take graded measures, continuously track the handling effect, and dynamically adjust the handling strategy.

[0047] In this embodiment, the data acquisition and analysis module 401 acquires and integrates multi-source data from the big health industry, extracting risk characteristics of fund repatriation; the risk warning and fund flow detection module 402 constructs a multi-dimensional indicator warning system, monitors the current fund flow in real time, identifies abnormal fund flows, and issues risk level warnings; the risk dynamic handling module 403 sets differentiated handling strategies according to the risk level, adopts tiered measures, continuously tracks the handling effect, and dynamically adjusts the handling strategies; through the above methods, multi-source data fusion analysis, real-time risk monitoring, and tiered dynamic handling are achieved to improve the accuracy and timeliness of fund repatriation risk prevention and control, and ensure the compliance and security of fund flows in the big health industry.

[0048] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0049] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0050] Accordingly, this application also provides an electronic device, including: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the digital anti-fund reflux control method for the big health industry described above. Figure 6 The diagram shown is a hardware structure diagram of any device with data processing capabilities, used in a digital anti-fund reflux control system for the big health industry provided by an embodiment of the present invention. (Except for...) Figure 6 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0051] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the aforementioned digital anti-fund reflux control method in the big health industry. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.

[0052] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0053] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A digital anti-money laundering control method for the wellness industry, characterized by, The method comprises the following steps: acquiring and integrating multi-source data of the health industry, extracting fund return risk characteristics; constructing a multi-dimensional index early warning system, monitoring the current fund flow in real time, identifying the abnormal current fund flow and issuing a risk level warning; setting a differentiated disposal strategy according to the risk level, taking graded measures, continuously tracking the disposal effect and dynamically adjusting the disposal strategy.

2. The digital anti-money laundering control method for the wellness industry of claim 1, wherein, In the step of acquiring and integrating multi-source data of the health industry, extracting fund return risk characteristics: collecting original data of the health industry from multiple channels, and cleaning the collected multi-source data; extracting abnormal characteristic variables; wherein the abnormal characteristic variables include transaction frequency abnormality, fund closed-loop flow and high proportion of associated subject transaction.

3. The digital anti-money laundering control method for the wellness industry of claim 2, wherein, In the step of collecting original data of the health industry from multiple channels and cleaning the collected multi-source data: eliminate repeated, incorrect and incomplete data, unify data format and standard, and form a standardized data set.

4. The digital anti-money laundering control method for the wellness industry of claim 2, wherein, After the step of extracting abnormal characteristic variables, wherein the abnormal characteristic variables include transaction frequency abnormality, fund closed-loop flow and high proportion of associated subject transaction: screening and optimizing from the abnormal characteristic variables, obtaining core risk characteristics, and constructing a fund return risk characteristic library.

5. The digital anti-money laundering control method for the wellness industry of claim 1, wherein, In the step of constructing a multi-dimensional index early warning system, monitoring the current fund flow in real time, identifying the abnormal current fund flow and issuing a risk level warning: selecting key indicators from the dimensions of transaction subject correlation, fund flow timeliness and amount fluctuation rationality, and constructing a multi-level early warning index system; wherein the key indicators include transaction counterparty overlap, fund turnover period and single transaction deviation; real-time interfacing with each data source, dynamically tracking the flow path and state of the fund in multiple links; comparing and analyzing the real-time monitoring data with the early warning index system.

6. The digital anti-money laundering control method for the wellness industry of claim 5, wherein, Before the step of real-time interfacing with each data source, dynamically tracking the flow path and state of the fund in multiple links: dynamically adjusting the threshold range of the early warning index, and dividing into high, medium and low three risk levels.

7. The digital anti-money laundering control method for the wellness industry of claim 6, wherein, In the step of comparing and analyzing the real-time monitoring data with the early warning index system: when the index exceeds the corresponding threshold, trigger a risk warning signal sending request.

8. The digital anti-money laundering control method for the wellness industry of claim 1, wherein, In the step of setting a differentiated disposal strategy according to the risk level, taking graded measures, continuously tracking the disposal effect and dynamically adjusting the disposal strategy: for high-risk warning, implement a first-level strategy; for medium-risk warning, implement a second-level strategy; for low-risk warning, implement a third-level strategy.

9. The digital anti-money laundering control method for the wellness industry of claim 8, wherein, In the step of setting a differentiated disposal strategy according to the risk level, taking graded measures, continuously tracking the disposal effect and dynamically adjusting the disposal strategy: establish a disposal effect tracking mechanism, adjust the disposal strategy according to the risk change trend, and form a closed-loop management.

10. A digital anti-money laundering control system for the health industry, which adopts the digital anti-money laundering control method for the health industry according to claim 1, characterized in that, It comprises a data collection and analysis module, a risk early warning and fund flow detection module, and a risk dynamic disposal module; wherein: the data collection and analysis module is used to acquire and integrate multi-source data of the health industry, and extract fund return risk characteristics; the risk early warning and fund flow detection module is used to construct a multi-dimensional index early warning system, monitor the current fund flow in real time, identify the abnormal current fund flow and issue a risk level warning; The risk dynamic treatment module is used for setting a differentiated treatment strategy according to a risk level difference, taking hierarchical measures, continuously tracking treatment effects and dynamically adjusting the treatment strategy.

Images