Hospital internal control risk data processing method, system, equipment and medium

Abstract

The invention discloses a hospital internal control risk data processing method, system and device and a medium, and the method comprises the steps: determining a plurality of corresponding risk management nodes according to an internal control risk management strategy of a hospital information business system and a risk management process of each related business node, and enabling the plurality of risk management nodes to form a risk data management network structure; extracting risk feature data from the hospital information service system based on the risk data management network structure and a preset risk data extraction rule; respectively obtaining an internal control guiding risk detection result and a numerical risk detection result; based on the internal control guiding risk detection result and the numerical value risk detection result, obtaining a simulation optimization feedback result; analyzing, simulating and optimizing a feedback result according to preset risk data hierarchy classification to obtain a multi-level risk index; performing risk detection based on the multi-level risk indexes to obtain a final risk detection result; the accuracy of internal control risk management is improved, and the real-time performance and effectiveness of risk prevention and control are enhanced.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, system, device and medium for processing hospital internal control risk data. Background Art

[0002] With the rapid development of the medical industry and the continuous improvement of the level of informatization, hospitals are facing increasingly complex internal management and external regulatory challenges. In order to ensure the quality and safety of medical services, hospitals need to establish a sound internal control system to effectively manage and prevent various potential risks. However, there are still some shortcomings in the internal control risk management of hospitals.

[0003] Many hospitals still rely on manual recording and management of risk data, which is not only time-consuming and labor-intensive, but also prone to human errors, resulting in the inability to guarantee the accuracy and completeness of the data. Existing risk detection methods often only focus on a specific aspect, such as financial risk or medical risk, and lack comprehensiveness and systematicness.

[0004] Some hospitals have begun to use information technology tools to collect and report risk data, but these tools usually have simple functions and are unable to conduct in-depth data analysis and risk assessment; although some information technology tools have certain risk warning functions, due to the single data source and simple algorithm, the accuracy and timeliness of the warning still need to be improved.

[0005] Therefore, there is an urgent need for a hospital internal control risk data processing technology that can improve the accuracy of internal control risk management and enhance the real-time and effectiveness of risk prevention and control. Summary of the invention

[0006] In order to improve the accuracy of internal control risk management and enhance the real-time and effectiveness of risk prevention and control, the present application provides a hospital internal control risk data processing method, system, equipment and medium.

[0007] In the first aspect, the invention objective of the present application is achieved by adopting the following technical solutions: A method for processing hospital internal control risk data, comprising: According to the internal control risk management strategy of the hospital information business system and the risk management process of each relevant business node, multiple corresponding risk management nodes are determined, and multiple risk management nodes form a risk data management network structure; Extracting risk feature data from the hospital information service system based on the risk data management network structure and preset risk data extraction rules; Performing an internal control-oriented initial risk detection and a numerical initial risk detection on the risk characteristic data to obtain an internal control-oriented risk detection result and a numerical risk detection result respectively; Based on the internal control-oriented risk detection result and the numerical risk detection result, obtaining a simulation optimization feedback result; Analyze the simulation optimization feedback results by using a preset risk data hierarchy classification to obtain multi-level risk indicators; Risk detection is performed based on the multi-level risk indicators to obtain a final risk detection result.

[0008] By adopting the above technical scheme, the internal control-oriented initial risk detection conducts risk detection from the perspective of the hospital's internal control needs to ensure that risk management meets the actual needs of the hospital. The numerical initial risk detection conducts risk detection from the perspective of data performance to ensure the accuracy and reliability of the data. The accuracy of risk detection is improved by combining the internal control-oriented risk detection results and the numerical risk detection results. This application constructs multiple risk management nodes to form a risk data management network structure corresponding to the hospital information business system, which can comprehensively cover various business nodes of the hospital and ensure the comprehensiveness and systematicness of risk management. At the same time, based on the preset risk data extraction rules, risk feature data is automatically extracted from the hospital information business system, which reduces manual intervention and improves the efficiency and accuracy of data extraction. Through simulation optimization The feedback results are used to conduct multi-level risk indicator gaps, which can quickly locate and identify potential risk points. The risk prevention and control method combined with internal control guidance and numerical detection can monitor the risk changes in hospital business and information management processes in real time, and promptly report and deal with potential risks to effectively prevent the expansion of risks. The multi-level risk indicators provide detailed risk data support for the hospital management, helping the management to make more scientific and reasonable decisions. The present invention constructs a multi-dimensional risk management node and a multi-level risk indicator system, combines internal control guidance and numerical detection methods, and realizes efficient and accurate processing of the hospital's internal risk data, which not only improves the real-time and effectiveness of risk prevention and control, but also enhances the transparency and compliance of hospital management, which is conducive to promoting the improvement and development of the hospital's internal control system.

[0009] In a preferred example of the present application, the internal control-oriented initial risk detection and the numerical initial risk detection are performed on the risk feature data to obtain the internal control-oriented risk detection result and the numerical risk detection result, respectively, specifically including: Acquire the hospital's internal control demand information, perform internal control-oriented coupling on the risk characteristic data, and obtain internal control-oriented risk characteristic data; An internal control-oriented initial risk detection is performed on the internal control-oriented risk characteristic data to obtain an internal control-oriented risk detection result; and a numerical initial risk detection is performed on the risk characteristic data to obtain a numerical risk detection result.

[0010] By adopting the above technical solutions, the hospital's internal control demand information is obtained to ensure that the hospital's actual needs and management goals are fully considered during the risk detection process, making risk detection more targeted and practical. The risk characteristic data is coupled with the internal control orientation so that the risk characteristic data is closely integrated with the hospital's internal control needs. Through coupling, the risk points related to internal control can be more accurately identified. Initial risk detection is performed based on internal control-oriented risk characteristic data, which can comprehensively assess risks from the perspective of hospital internal control, ensuring that the risk detection results can reflect the actual needs and management goals of the hospital's internal control. Through the combination of internal control-oriented initial risk detection and numerical initial risk detection, a comprehensive assessment of risks from multiple dimensions is achieved, which can discover and deal with risks more comprehensively and timely, and improve the real-time and effectiveness of risk prevention and control.

[0011] In a preferred example of the present application: the simulation optimization feedback result is obtained based on the internal control-oriented risk detection result and the numerical risk detection result, specifically including: Based on the internal control-oriented risk detection result and the numerical risk detection result, simulation optimization is performed to obtain internal control-oriented simulation optimization data and numerical simulation optimization data, respectively. The simulation optimization refers to simulating and generating optimized data of the same type generated by hospital management behaviors corresponding to the risk data represented by the internal control-oriented risk detection result and the numerical risk detection result; Performing an internal control-oriented initial risk detection based on the internal control-oriented simulation optimization data to obtain an internal control-oriented simulation optimization feedback result; Numerical initial risk detection is performed based on the numerical simulation optimization data to obtain numerical simulation optimization feedback results, wherein the simulation optimization feedback results include internal control-oriented simulation optimization feedback results and numerical simulation optimization feedback results.

[0012] By adopting the above technical solutions, simulation optimization is performed based on the internal control-oriented risk detection results and the numerical risk detection results respectively, so that risk data can be evaluated and optimized from multiple dimensions, which not only takes into account the needs of hospital internal control, but also takes into account the actual situation of data performance, ensuring the comprehensiveness and accuracy of risk assessment; the simulation optimization process generates the same type of data generated by the optimized hospital management behavior, so that the simulated optimization data is closer to the actual business scenario, more realistically reflects potential risks, and improves the accuracy of risk assessment. Based on the internal control-oriented simulation optimization data, the internal hole-oriented initial risk detection is performed, and the internal control-oriented simulation optimization feedback results can be obtained, which ensures the effectiveness and feasibility of the optimized management behavior under the internal control framework, and helps to timely discover and correct potential internal control defects. Based on the numerical simulation optimization data, numerical initial risk detection is performed, and numerical simulation optimization feedback results can be obtained. The actual effect of the optimized management behavior is verified by numerical methods to ensure that the optimization measures can effectively reduce risks.

[0013] In a preferred example of the present application, the simulation optimization feedback results are analyzed by classifying the preset risk data levels to obtain multi-level risk indicators, specifically including: Based on the preset risk data hierarchical classification, the risk data represented by the simulation optimization feedback results corresponding to the internal control-oriented initial risk detection and the numerical initial risk detection are respectively combined and associated, and the risk data after the combination and association are analyzed to obtain an indicator for evaluating whether the data is risky, that is, a multi-level risk indicator. The preset risk data hierarchical classification refers to the information after all risk data types are classified in different dimensions; The multi-level risk indicators include individual risk indicators, associated risk indicators and comprehensive risk indicators. The individual risk indicators refer to indicators for evaluating the risk level of individual data, the associated risk indicators refer to indicators for evaluating the risk relationship between two directly related data, and the comprehensive risk indicators refer to indicators for evaluating the overall risk status of multiple data.

[0014] By adopting the above technical solutions, multi-level risk indicator analysis evaluates risk data from three dimensions: individual, correlation and comprehensive, ensuring the comprehensiveness and accuracy of risk assessment. By combining and correlating the simulation optimization feedback results corresponding to the internal control-oriented initial risk detection and the numerical initial risk detection, it is possible to comprehensively evaluate risk data from multiple angles and levels to ensure the comprehensiveness and accuracy of risk assessment. Multi-level risk indicators provide detailed risk data support for hospital management, helping management to scientifically evaluate and manage risks. Through multi-level risk indicator analysis, hospitals can take more effective management measures and optimize resource allocation.

[0015] In a preferred example of the present application, the risk feature data is extracted from the hospital information service system based on the risk data management network structure and the preset risk data extraction rules, specifically including: Determine the key business processes and data sources of each risk management node according to the risk data management network structure; Based on the key business processes and data sources, preset risk data extraction rules are defined, and the preset risk data extraction rules include the time interval for data extraction, the frequency of data extraction, the conditions for data extraction and the specific fields for data extraction; according to the preset risk data extraction rules, risk feature data is extracted from the hospital information business system.

[0016] By adopting the above technical solutions, the key business processes and data sources of each risk management node are determined according to the risk data management network structure, ensuring the targeted data extraction; by defining preset risk data extraction rules, including the time interval for data extraction, the frequency of data extraction, the conditions for data extraction and the specific fields for data extraction, the normalization and standardization of data extraction are ensured, while reducing manual intervention and improving the efficiency of data extraction; by determining the key business processes and data sources of each risk management node, the source of data is ensured to be clear and traceable, and the focus and key links of the hospital's internal control management are clarified, providing a basis for subsequent risk audits and tracking.

[0017] In a preferred example of the present application, the risk detection is performed based on the multi-level risk indicators to obtain the final risk detection result, including: Calculate the individual risk index R based on formula (1) i , R i Indicates the risk level of a single data point: R i =ω 1 ×F 1 +ω 2 ×F 2 +…+ω n ×F n (1) In the formula, F 1 , F 2 , …, F n is the value of each factor that affects individual risk; ω 1 ,ω 2 ,…,ω n is the weight of each factor, and Based on formula (2), the correlation risk index R is calculated ij : In the formula, R iWith R j are the individual risk indicators of two associated data points, ρ ij is the correlation coefficient between two data points, and its value range is [-1, 1]; Calculate the comprehensive risk index R based on formula (3) total : R k is the individual risk indicator or associated risk indicator of the kth data point, ω k is the weight of the kth data point, and

[0018] By adopting the above technical solutions, the calculation of multi-level risk indicators conducts a comprehensive assessment of risk data from three dimensions: individual, correlation and comprehensive. This not only improves the accuracy and real-time nature of risk assessment, but also enhances the effectiveness of risk prevention and control and the efficiency and reliability of data processing.

[0019] In the second aspect, the invention objective of the present application is achieved by adopting the following technical solutions: A hospital internal control risk data processing system, used to execute the hospital internal control risk data processing method as described above, the system comprising: The risk management node determination module is used to determine the corresponding multiple risk management nodes according to the internal control risk management strategy of the hospital information business system and the risk management process of each relevant business node. The multiple risk management nodes form a risk data management network structure; A risk data extraction module, used to extract risk feature data from the hospital information business system based on the risk data management network structure and preset risk data extraction rules; A risk detection module, used to perform internal control-oriented initial risk detection and numerical initial risk detection on the risk feature data, and obtain internal control-oriented risk detection results and numerical risk detection results respectively; A simulation optimization module, used to obtain simulation optimization feedback results based on the internal control-oriented risk detection results and the numerical risk detection results; A multi-level risk indicator analysis module is used to classify and analyze the simulation optimization feedback results according to a preset risk data hierarchy to obtain multi-level risk indicators; The final risk detection module is used to perform risk detection based on the multi-level risk indicators to obtain the final risk detection result.

[0020] In the third aspect, the invention objective of the present application is achieved by adopting the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned hospital internal control risk data processing method when executing the computer program.

[0021] In a fourth aspect, the invention objective of the present application is achieved by adopting the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned hospital internal control risk data processing method.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application forms a risk data management network structure corresponding to the hospital information business system by constructing multiple risk management nodes, which can fully cover various business nodes of the hospital and ensure the comprehensiveness and systematicness of risk management. At the same time, based on the preset risk data extraction rules, risk feature data is automatically extracted from the hospital information business system, which reduces manual intervention and improves the efficiency and accuracy of data extraction. By performing multi-level risk indicator gaps on the simulation optimization feedback results, potential risk points can be quickly located and identified. The risk prevention and control method combined with internal control guidance and numerical detection can monitor the risk changes in hospital business and information management in real time, timely report and handle potential risks, and effectively prevent the expansion of risks. The multi-level risk indicators provide detailed risk data support for the hospital management, helping the management to make more scientific and reasonable decisions. The present invention realizes efficient and accurate processing of hospital internal risk data by constructing multi-dimensional risk management nodes and multi-level risk indicator systems, combined with internal control guidance and numerical detection methods; 2. Determine the key business processes and data sources of each risk management node based on the risk data management network structure to ensure the targeted data extraction; by defining preset risk data extraction rules, including the time interval for data extraction, the frequency of data extraction, the conditions for data extraction and the specific fields for data extraction, ensure the normalization and standardization of data extraction, and improve the efficiency of data extraction while reducing manual intervention; by determining the key business processes and data sources of each risk management node, ensure that the source of data is clear and traceable, clarify the focus and key links of the hospital's internal control management, and provide a basis for subsequent risk audits and tracking. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a method for processing hospital internal control risk data in one embodiment of the present application; Figure 2 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a method for processing hospital internal control risk data, which specifically includes the following steps: S1: According to the internal control risk management strategy of the hospital information business system and the risk management process of each relevant business node, the corresponding multiple risk management nodes are determined, and the multiple risk management nodes form a risk data management network structure.

[0026] In this embodiment, the internal control risk management strategy refers to the overall strategy of internal control and risk management formulated by the hospital. The business nodes are various business process nodes within the hospital, such as registration, medical treatment, drug management, financial settlement, contract review, etc. The risk management node refers to the risk management node established at each business node to monitor and manage specific risks.

[0027] Specifically, the hospital formulates an internal risk management strategy, sorts out the various business processes within the hospital, determines the key risk points of each business node, sets up risk management nodes at each business node, ensures the comprehensive collection of risk data, and connects various risk management nodes to form a risk data management network structure. For example, the financial settlement node monitors the flow of funds during the financial settlement process, and the drug management node monitors the drug procurement, storage and distribution process to prevent drug expiration, loss and abuse.

[0028] S2: Based on the risk data management network structure and preset risk data extraction rules, risk feature data is extracted from the hospital information business system.

[0029] In this embodiment, the risk data extraction rules include the time interval for data extraction, the frequency of data extraction, the conditions for data extraction and the specific fields for data extraction; the risk characteristic data refers to the data related to risk management extracted from the hospital information business system.

[0030] Specifically, after extracting risk feature data from the hospital information business system, the extracted risk feature data is preprocessed, including data cleaning, data conversion and data standardization, to ensure the integrity and consistency of the data. For example: Registration system: extract registration records, monitor registration anomalies, and prevent scalper registration and false registration; Drug management system: extract drug procurement records and monitor drug procurement anomalies.

[0031] S3: Perform internal control-oriented initial risk detection and numerical initial risk detection on the risk characteristic data to obtain internal control-oriented risk detection results and numerical risk detection results respectively.

[0032] In this embodiment, the internal control-oriented initial risk detection is to perform risk detection from the perspective of the hospital's internal control needs; the numerical initial risk detection is to perform risk detection from the perspective of data performance.

[0033] Specifically, in step S3, internal control-oriented initial risk detection and numerical initial risk detection are performed on the risk feature data to obtain internal control-oriented risk detection results and numerical risk detection results, respectively, which specifically include: S31: Obtain the hospital's internal control demand information, perform internal control-oriented coupling on the risk characteristic data, and obtain internal control-oriented risk characteristic data.

[0034] In this embodiment, internal control demand information refers to the internal control demand formulated by the hospital, including the objectives, policies and specific requirements of internal control; internal control-oriented coupling refers to combining risk characteristic data with the internal control demand information of the hospital to generate internal control-oriented risk characteristic data. For example, internal control-oriented coupling is to map internal control demand information with risk characteristic data to determine which risk characteristic data are related to which internal control demands; for example: if one of the internal control demands is to prevent financial fraud, then the relevant risk characteristic data may include financial transaction records, account balance changes, etc. By defining specific mapping rules (such as data screening conditions, data processing methods), it is clear how to combine the internal control demand information with the risk characteristic data, and then according to the defined mapping rules, the internal control demand information is coupled with the risk characteristic data. Through the coupling process, internal control-oriented risk characteristic data is generated, and these data contain the specific requirements of the internal control demand.

[0035] Specifically, when implementing data mapping rules through data screening conditions, you can define which data points are related to internal control requirements; for example, if the internal control requirement is to prevent drugs from expiration, then the relevant data points may include the drug's production date, expiration date, and storage location. When implementing through data processing methods, define how to process these data points, such as calculating the remaining days of the drug's expiration date, checking whether the drug's storage location complies with regulations, etc.

[0036] S32: Perform internal control-oriented initial risk detection on the internal control-oriented risk characteristic data to obtain the internal control-oriented risk detection result.

[0037] In this embodiment, a risk detection method suitable for internal control needs is selected, such as threshold detection, historical value detection, and model detection, to perform risk assessment on internal control-oriented risk feature data and identify potential risk points. For example: Financial settlement system: Use the threshold detection method to check whether the financial data exceeds the set threshold, generate internal control-oriented risk detection results, and discover potential abnormalities in capital flows; Drug management system: Use the historical value detection method to check whether the drug procurement data is significantly different from the historical data, generate internal control-oriented risk detection results, and discover potential procurement anomalies.

[0038] S33: Performing a numerical initial risk detection on the risk characteristic data to obtain a numerical risk detection result.

[0039] In this embodiment, the numerical risk detection result refers to the detection result reflecting the potential risk in the risk characteristic data; a risk detection method suitable for the data representation is selected, such as statistical analysis, machine learning model, etc.

[0040] S4: Based on the internal control-oriented risk detection results and numerical risk detection results, obtain simulation optimization feedback results.

[0041] In this embodiment, step S4 specifically includes: S41: Perform simulation optimization based on the internal control-oriented risk detection results and the numerical risk detection results to obtain internal control-oriented simulation optimization data and numerical simulation optimization data respectively. Simulation optimization refers to the risk data represented by the internal control-oriented risk detection results and the numerical risk detection results, and simulates the same type of data generated by the hospital management behavior that generates the corresponding risk data after optimization.

[0042] In this embodiment, simulation optimization refers to the same type of data generated by simulating optimized management behaviors through risk detection results; internal control-oriented simulation optimization data refers to optimized data generated based on internal control-oriented risk detection results; numerical simulation optimization data refers to optimized data generated based on numerical risk detection results. The simulation optimization method can select simulation modeling or machine learning model.

[0043] S42: Perform internal control-oriented initial risk detection based on the internal control-oriented simulation optimization data to obtain internal control-oriented simulation optimization feedback results.

[0044] In this embodiment, the internal control-oriented initial risk detection refers to risk detection of the internal control-oriented simulation optimization data from the perspective of internal control needs; the internal control-oriented simulation optimization feedback results are used to reflect the detection results of potential risks in the internal control-oriented simulation optimization data.

[0045] S43: Performing numerical initial risk detection based on numerical simulation optimization data to obtain numerical simulation optimization feedback results, wherein the simulation optimization feedback results include internal control-oriented simulation optimization feedback results and numerical simulation optimization feedback results.

[0046] In this embodiment, the numerical initial risk detection refers to risk detection of numerical simulation optimization data from the perspective of data performance; the numerical simulation optimization feedback result reflects the detection result of potential risks in the numerical simulation optimization data.

[0047] For example: Use statistical analysis methods to check the distribution and trend of optimized financial data, generate numerical simulation optimization feedback results, and discover potential cash flow anomalies; use machine learning models to check abnormal patterns of optimized drug procurement and inventory data, generate numerical simulation optimization feedback results, and discover potential procurement and inventory anomalies.

[0048] S5: Analyze the simulation optimization feedback results based on the preset risk data hierarchy classification to obtain multi-level risk indicators.

[0049] Specifically, risk data hierarchical classification refers to the information after all risk data types are classified in different dimensions. Multi-level risk indicators include individual risk indicators, associated risk indicators and comprehensive risk indicators, among which individual risk indicators refer to indicators that evaluate the risk level of individual data, associated risk indicators refer to indicators that evaluate the risk relationship between two directly related data, and comprehensive risk indicators refer to indicators that evaluate the overall risk status of multiple data.

[0050] In this embodiment, in step S5, the preset risk data hierarchical classification analysis simulation optimization feedback results are used to obtain multi-level risk indicators, specifically including: S51: Based on the preset risk data hierarchical classification, the risk data represented by the simulation optimization feedback results corresponding to the internal control-oriented initial risk detection and the numerical initial risk detection are combined and associated, and the risk data after the combination and association are analyzed to obtain indicators for evaluating whether the data is risky, that is, multi-level risk indicators. The preset risk data hierarchical classification refers to the information after all risk data types are classified in different dimensions.

[0051] In this embodiment, the multi-level risk index refers to information after all risk data types are classified in different dimensions, such as by business process, by data type, by time period, etc.

[0052] Specifically, the implementation steps of the preset risk data hierarchy classification include: 1. First define the classification standards: Business process dimension: classify according to the various business process nodes within the hospital, such as registration, medical treatment, drug management, financial settlement, etc.; Data type dimension: classify according to the type of data, such as financial data, drug data, patient data, etc.; Time period dimension: classify according to the time period of the data, such as daily data, weekly data, monthly data, etc.

[0053] 2. Combine and associate risk data: Business process dimension: Combine and associate risk data on the same business process node. For example, associate risk data in the registration process with risk data in the medical treatment process; Data type dimension: Combine and associate data of the same type; for example, associate income data with expenditure data in financial data; Time period dimension: Combine and associate risk data within the same time period; for example, associate daily financial data with weekly financial data; Use data association algorithms (such as association rule mining, cluster analysis, etc.) to combine and associate risk data.

[0054] 3. Multi-level risk indicator analysis: Calculate the individual risk index R based on formula (1) i , R i Indicates the risk level of a single data point: R i =ω 1 ×F 1 +ω 2 ×F 2 +…+ω n ×F n (1) In the formula, F 1 , F 2 , …, F n is the value of each factor that affects individual risk; ω 1 ,ω 2 ,…,ω n is the weight of each factor, and Based on formula (2), the correlation risk index R is calculated ij : In the formula, R i With R j are the individual risk indicators of two associated data points, ρ ij is the correlation coefficient between two data points, and its value range is [-1, 1]; Calculate the comprehensive risk index R based on formula (3) total : R kis the individual risk indicator or associated risk indicator of the kth data point, ω k is the weight of the kth data point, and

[0055] In this embodiment, the individual factor values ​​in the financial settlement system include transaction amount, transaction frequency, transaction time, transaction counterparty, account balance, and transaction type; the individual factor values ​​in the patient management system include patient age, patient medical history, patient medication record, patient hospitalization time, patient expenses, patient diagnosis results, etc. Assume that the factor values ​​of the financial settlement system are prepared as transaction amount 1,000 yuan, transaction frequency 5 times a day, transaction time 10 pm, transaction counterparty supplier A, account balance 50,000 yuan, transaction type expenditure, and then the weights are determined in order: transaction amount 80, transaction frequency 70, transaction time 90, transaction counterparty 60, account balance 50, transaction type 70, and then the individual risk index R is calculated by formula (1). i .

[0056] Similarly, when calculating the associated risk index, the associated data points are first determined, such as the income and expenditure data in the financial settlement system, the purchase and inventory data in the drug management system, etc. After the individual risk index is calculated, the correlation coefficient calculation method of the Pearson correlation coefficient (suitable for the evaluation of linear relationships) or the Spearman rank correlation coefficient (suitable for the evaluation of nonlinear relationships) is used to calculate the correlation relationship ρ between two associated data points. ij , and then use formula (2) to calculate the associated risk index R ij .

[0057] S6: Perform risk detection based on multi-level risk indicators to obtain the final risk detection results.

[0058] In this embodiment, a random forest model is used to train a risk detection model, individual risk indicators and associated risk indicators are input, and risk assessment results are output.

[0059] In one embodiment, in step S2, based on the risk data management network structure and the preset risk data extraction rules, risk feature data is extracted from the hospital information service system, specifically including: S21: Determine the key business processes and data sources of each risk management node based on the risk data management network structure.

[0060] In this embodiment, the risk data management network structure includes various risk management nodes and their connection relationships; key business processes refer to the key business processes involved in each risk management node, such as registration, medical treatment, drug management, financial settlement, contract approval, etc.; data source refers to the data source involved in each key business process, such as information systems, paper records, external data, etc.

[0061] S22: Based on key business processes and data sources, define preset risk data extraction rules, where the preset risk data extraction rules include the time interval for data extraction, the frequency of data extraction, the conditions for data extraction, and the specific fields for data extraction.

[0062] In this embodiment, the time interval for data extraction refers to the time interval between each data extraction, such as daily, weekly, monthly, etc.; the frequency of data extraction refers to the frequency of each data extraction, such as once a day, once a week, etc.; the condition for data extraction refers to the trigger condition for data extraction, such as the occurrence of a specific event, the arrival of a specific time point, etc.; the specific field for data extraction refers to the specific data field that needs to be extracted, such as patient name, drug name, transaction amount, etc.

[0063] S23: Extract risk feature data from the hospital information business system according to preset risk data extraction rules.

[0064] In this embodiment, for example, SQL queries are used to extract daily revenue data from a database, and an API interface is used to extract drug inventory data from an external system; the extracted risk feature data is preprocessed, including data cleaning, data conversion, and data standardization, and the extracted risk feature data is stored in a designated data warehouse or data lake, for example, daily revenue data is stored in a MySQL database, and drug inventory data is stored in a Hadoop data lake, to ensure data security and accessibility.

[0065] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0066] In one embodiment, a hospital internal control risk data processing system is provided, and the hospital internal control risk data processing system corresponds to the hospital internal control risk data processing method in the above embodiment.

[0067] A hospital internal control risk data processing system includes a risk management node determination module, a risk data extraction module, a risk detection module, a simulation optimization module, a multi-level risk indicator analysis module and a final risk detection module. The detailed description of each functional module is as follows: The risk management node determination module is used to determine the corresponding multiple risk management nodes according to the internal control risk management strategy of the hospital information business system and the risk management process of each relevant business node. The multiple risk management nodes form a risk data management network structure; A risk data extraction module is used to extract risk characteristic data from the hospital information business system based on the risk data management network structure and preset risk data extraction rules; The risk detection module is used to perform internal control-oriented initial risk detection and numerical initial risk detection on the risk feature data, and obtain internal control-oriented risk detection results and numerical risk detection results respectively; A simulation optimization module is used to obtain simulation optimization feedback results based on internal control-oriented risk detection results and numerical risk detection results; The multi-level risk indicator analysis module is used to classify and analyze the simulated optimization feedback results based on the preset risk data level to obtain multi-level risk indicators; The final risk detection module is used to perform risk detection based on multi-level risk indicators and obtain the final risk detection results.

[0068] For the specific limitations of the hospital internal control risk data processing system, please refer to the limitations of the hospital internal control risk data processing method in the above text, which will not be repeated here; the various modules in the above-mentioned hospital internal control risk data processing system can be implemented in whole or in part through software, hardware and their combination; the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0069] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 2 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store risk data management network structure, internal control-oriented risk detection results and numerical risk detection results, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a hospital internal control risk data processing method is implemented.

[0070] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: S1: According to the internal control risk management strategy of the hospital information business system and the risk management process of each relevant business node, multiple corresponding risk management nodes are determined, and multiple risk management nodes form a risk data management network structure; S2: Extract risk feature data from the hospital information business system based on the risk data management network structure and preset risk data extraction rules; S3: Performing internal control-oriented initial risk detection and numerical initial risk detection on the risk feature data to obtain internal control-oriented risk detection results and numerical risk detection results respectively; S4: Based on the internal control-oriented risk detection results and the numerical risk detection results, obtain the simulation optimization feedback results; S5: Classify and analyze the simulation optimization feedback results based on the preset risk data hierarchy to obtain multi-level risk indicators; S6: Perform risk detection based on multi-level risk indicators to obtain the final risk detection results.

[0071] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: S1: According to the internal control risk management strategy of the hospital information business system and the risk management process of each relevant business node, multiple corresponding risk management nodes are determined, and multiple risk management nodes form a risk data management network structure; S2: Extract risk feature data from the hospital information business system based on the risk data management network structure and preset risk data extraction rules; S3: Performing internal control-oriented initial risk detection and numerical initial risk detection on the risk feature data to obtain internal control-oriented risk detection results and numerical risk detection results respectively; S4: Based on the internal control-oriented risk detection results and the numerical risk detection results, obtain the simulation optimization feedback results; S5: Classify and analyze the simulation optimization feedback results based on the preset risk data hierarchy to obtain multi-level risk indicators; S6: Perform risk detection based on multi-level risk indicators to obtain the final risk detection results.

[0072] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0073] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0074] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the features thereof may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for processing hospital internal control risk data, characterized in that: include: According to the internal control risk management strategy of the hospital information business system and the risk management process of each relevant business node, multiple corresponding risk management nodes are determined, and multiple risk management nodes form a risk data management network structure; Extracting risk feature data from the hospital information service system based on the risk data management network structure and preset risk data extraction rules; Performing an internal control-oriented initial risk detection and a numerical initial risk detection on the risk characteristic data to obtain an internal control-oriented risk detection result and a numerical risk detection result respectively; Based on the internal control-oriented risk detection result and the numerical risk detection result, obtaining a simulation optimization feedback result; Analyze the simulation optimization feedback results by using a preset risk data hierarchy classification to obtain multi-level risk indicators; Risk detection is performed based on the multi-level risk indicators to obtain a final risk detection result.

2. A hospital internal control risk data processing method according to claim 1, characterized in that: The performing of internal control-oriented initial risk detection and numerical initial risk detection on the risk feature data to obtain internal control-oriented risk detection results and numerical risk detection results respectively specifically includes: Acquire the hospital's internal control demand information, perform internal control-oriented coupling on the risk characteristic data, and obtain internal control-oriented risk characteristic data; An internal control-oriented initial risk detection is performed on the internal control-oriented risk characteristic data to obtain an internal control-oriented risk detection result; and a numerical initial risk detection is performed on the risk characteristic data to obtain a numerical risk detection result.

3. A hospital internal control risk data processing method according to claim 1, characterized in that: The obtaining of simulation optimization feedback results based on the internal control-oriented risk detection results and the numerical risk detection results specifically includes: Based on the internal control-oriented risk detection result and the numerical risk detection result, simulation optimization is performed to obtain internal control-oriented simulation optimization data and numerical simulation optimization data, respectively. The simulation optimization refers to simulating and generating optimized data of the same type generated by hospital management behaviors corresponding to the risk data represented by the internal control-oriented risk detection result and the numerical risk detection result; Performing an internal control-oriented initial risk detection based on the internal control-oriented simulation optimization data to obtain an internal control-oriented simulation optimization feedback result; Numerical initial risk detection is performed based on the numerical simulation optimization data to obtain numerical simulation optimization feedback results, wherein the simulation optimization feedback results include internal control-oriented simulation optimization feedback results and numerical simulation optimization feedback results.

4. A hospital internal control risk data processing method according to claim 1, characterized in that: The simulation optimization feedback results are analyzed by classifying them according to the preset risk data hierarchy to obtain multi-level risk indicators, specifically including: Based on the preset risk data hierarchical classification, the risk data represented by the simulation optimization feedback results corresponding to the internal control-oriented initial risk detection and the numerical initial risk detection are respectively combined and associated, and the risk data after the combination and association are analyzed to obtain an indicator for evaluating whether the data is risky, that is, a multi-level risk indicator. The preset risk data hierarchical classification refers to the information after all risk data types are classified in different dimensions; The multi-level risk indicators include individual risk indicators, associated risk indicators and comprehensive risk indicators. The individual risk indicators refer to indicators for evaluating the risk level of individual data, the associated risk indicators refer to indicators for evaluating the risk relationship between two directly related data, and the comprehensive risk indicators refer to indicators for evaluating the overall risk status of multiple data.

5. A hospital internal control risk data processing method according to claim 1, characterized in that: The extracting risk feature data from the hospital information service system based on the risk data management network structure and the preset risk data extraction rules specifically includes: Determine the key business processes and data sources of each risk management node according to the risk data management network structure; Based on the key business processes and data sources, define preset risk data extraction rules, wherein the preset risk data extraction rules include a time interval for data extraction, a frequency for data extraction, a condition for data extraction, and specific fields for data extraction; According to the preset risk data extraction rules, risk feature data is extracted from the hospital information service system.

6. A hospital internal control risk data processing method according to claim 4, characterized in that: The risk detection is performed based on the multi-level risk indicators to obtain the final risk detection result, including: Calculate the individual risk index R based on formula (1) i , R i Indicates the risk level of a single data point: R i =ω1×F1+ω2×F2+…+ω n ×F n (1) Where F1, F2, …, F n are the values ​​of various factors that affect individual risk; ω1, ω2, …, ω n is the weight of each factor, and Based on formula (2), the correlation risk index R is calculated ij : In the formula, R i With R j are the individual risk indicators of two associated data points, ρ ij is the correlation coefficient between two data points, and its value range is [-1, 1]; Calculate the comprehensive risk index R based on formula (3) total : R k is the individual risk indicator or associated risk indicator of the kth data point, ω k is the weight of the kth data point, and 7. A hospital internal control risk data processing system, characterized in that: A method for processing hospital internal control risk data according to any one of claims 1 to 6, the system comprising: The risk management node determination module is used to determine the corresponding multiple risk management nodes according to the internal control risk management strategy of the hospital information business system and the risk management process of each relevant business node. The multiple risk management nodes form a risk data management network structure; A risk data extraction module, used to extract risk feature data from the hospital information business system based on the risk data management network structure and preset risk data extraction rules; A risk detection module, used to perform internal control-oriented initial risk detection and numerical initial risk detection on the risk feature data, and obtain internal control-oriented risk detection results and numerical risk detection results respectively; A simulation optimization module, used to obtain simulation optimization feedback results based on the internal control-oriented risk detection results and the numerical risk detection results; A multi-level risk indicator analysis module is used to classify and analyze the simulation optimization feedback results according to a preset risk data hierarchy to obtain multi-level risk indicators; The final risk detection module is used to perform risk detection based on the multi-level risk indicators to obtain the final risk detection result.

8. A hospital internal control risk data processing system according to claim 7, characterized in that: The risk detection module specifically includes: An internal control demand information acquisition unit is used to acquire the hospital's internal control demand information, perform internal control-oriented coupling on the risk characteristic data, and obtain internal control-oriented risk characteristic data; An internal control-oriented initial risk detection unit, used to perform an internal control-oriented initial risk detection on the internal control-oriented risk feature data to obtain an internal control-oriented risk detection result; The numerical initial risk detection unit is used to perform a numerical initial risk detection on the risk characteristic data to obtain a numerical risk detection result.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a hospital internal control risk data processing method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a hospital internal control risk data processing method as described in any one of claims 1 to 6 are implemented.

Images