Industrial injury medical fee fraud prevention system and method based on data screening and remote authentication

Abstract

The invention provides an industrial injury medical fee anti-fraud system and method based on data screening and remote authentication, and relates to the technical field of industrial injury medical informatization and intelligent monitoring. An intelligent screening module carries out abnormal behavior detection on an industrial injury medical process through a machine learning algorithm based on related data multi-dimensional information, and sends an abnormal behavior detection result to a remote authentication module; outputting a list of mechanisms and personnel with suspected fraudulent behaviors; the risk assessment sub-module identifies an abnormal mode and a potential risk assessment result for the mechanism and personnel list of the suspected fraudulent behavior by using machine learning and data analysis technologies; the risk evaluation module generates a risk score for each organization and personnel according to an evaluation result, and marks key supervision objects; the random spot check and task issuing module issues a ward round task to a related mechanism according to the key supervision object list, and verifies staff information and ward round requirements; and after receiving the task, the personnel performs field inspection, so that the timeliness and accuracy of supervision are improved, and the workload and cost of manual inspection are reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of industrial injury medical informationization and intelligent monitoring technology, and in particular to an industrial injury medical expense fraud prevention system and method based on data screening and remote authentication. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] In the treatment of work-related injuries, there are some cases of hanging beds in hospitals and false hospitalizations, which occupy medical resources and attempt to embezzle work-related injury medical expenses, seriously damaging the security and fairness of social security funds. The existing monitoring methods for work-related injury medical treatment are online or manual random inspections in hospitals, which have certain limitations in the timeliness and accuracy of supervision, and the workload and cost of inspections are also relatively high. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes an anti-fraud system and method for work-related medical expenses based on data screening and remote authentication, which integrates application algorithm models, identity authentication, robotics technology and communication methods to achieve accurate monitoring of relevant processes of work-related medical treatment.

[0005] According to some embodiments, the present disclosure adopts the following technical solutions:

[0006] The work-related injury medical expense anti-fraud system based on data screening and remote authentication includes:

[0007] The data collection submodule is configured to: obtain relevant data from relevant institution systems;

[0008] An intelligent screening module is configured to: detect abnormal behavior in the work-related injury medical process based on multi-dimensional information of relevant data through machine learning algorithms, and output a list of institutions and personnel suspected of fraud;

[0009] The risk assessment submodule is configured to: use machine learning and data analysis technology to identify abnormal patterns and potential risks for a list of institutions and personnel suspected of fraudulent behavior and obtain assessment results;

[0010] The risk scoring submodule is configured to: generate a risk score for each institution and person based on the assessment results, and mark key supervision objects;

[0011] The random inspection and task assignment module is configured to: assign the list of key supervision targets to the relevant agencies for round-up tasks, verify the specific employee information and round-up requirements;

[0012] The information collection and authentication module is configured to: after receiving the task, the personnel conduct on-site verification;

[0013] The data upload and review module is configured to transmit the authentication data to the background work injury review system through the network.

[0014] According to some embodiments, the present disclosure adopts the following technical solutions:

[0015] The anti-fraud method for work-related injury medical expenses based on data screening and remote authentication includes:

[0016] Obtain data and information related to work-related injury medical expenses and perform pre-processing;

[0017] Extract key features from structured data, use statistical methods and machine learning algorithms to detect anomalies in key features, intelligently generate risk scores based on the test results and historical records, and classify them into low risk, medium risk, and high risk according to the scores to form preliminary review data;

[0018] Use random sampling algorithms to randomly generate supplementary data, and combine the random sampling data generated by the preliminary review data to form the final sampling inspection list;

[0019] Issue ward rounds to the work-related injury medical institution or department, log in through face recognition authentication, and perform remote identification and authentication; upload authentication data for review to verify the actual hospitalization status of employees receiving work-related injury treatment, and adjust the work-related injury medical expenses based on the review results, and make necessary deductions.

[0020] According to some embodiments, the present disclosure adopts the following technical solutions:

[0021] A non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method of the work-related injury medical expense anti-fraud system based on data screening and remote authentication is implemented.

[0022] According to some embodiments, the present disclosure adopts the following technical solutions:

[0023] An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the method of implementing the work-related injury medical expense anti-fraud system based on data screening and remote authentication.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] The disclosed work-related injury medical expense anti-fraud system based on data screening and remote authentication can effectively identify and prevent fraudulent behaviors such as "hanging beds". "Hanging beds for hospitalization" is also called "fake hospitalization", which is mainly for the purpose of defrauding work-related injury medical expenses, registering for hospitalization, but not actually being hospitalized. The disclosed system issues ward rounds through text messages, phone calls, and other means. The staff of work-related injury medical institutions collect information on workers who seek medical treatment for work-related injuries and conduct real-person authentication through mobile devices or ward robots. The authentication data is automatically transmitted to the work-related injury review system, which improves the timeliness and accuracy of supervision and reduces the workload and cost of manual inspections, so as to improve the transparency and fairness of work-related injury medical management and ensure the rational use of work-related injury medical expenses and the safety of funds.

[0026] The disclosed industrial injury medical expense anti-fraud system based on data screening and remote authentication includes an intelligent screening module, which is based on industrial injury medical data, industrial injury insurance identification data, historical data and other multi-dimensional information, and through machine learning algorithm training, realizes abnormal detection of industrial injury medical institutions, departments and industrial injury medical workers, and outputs a list of industrial injury medical institutions, departments and industrial injury medical workers suspected of fraudulent behavior; a random inspection and task issuance module, based on the suspected fraud list output by the algorithm model, combined with the random inspection mechanism, intelligently screens out the list that needs to be supervised, and issues ward rounds to relevant industrial injury medical institutions through SMS, phone or internal channels. The task content clearly indicates the specific industrial injury medical worker information and ward rounds requirements that need to be verified; an information collection and authentication module, after receiving the task, the staff of the industrial injury medical institution goes to the ward for on-site verification; a data upload and review module, the authentication data (including face recognition results, industrial injury medical worker action video, location information, industrial injury information, etc.) is automatically transmitted to the background industrial injury review system through the network. Social security staff will review the uploaded data in the system and, after confirming that it is correct, deduct or adjust the relevant work-related injury medical expenses based on the review results to ensure the safety of the fund. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0028] Figure 1 This is an architecture diagram of the anti-fraud system according to an embodiment of the present disclosure;

[0029] Figure 2 The present invention is a flowchart of the anti-fraud method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0031] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0032] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0033] Example 1

[0034] In one embodiment of the present disclosure, a work-related injury medical expense anti-fraud system based on data screening and remote authentication is provided, comprising:

[0035] The data collection submodule is configured to: obtain relevant data from relevant institution systems;

[0036] An intelligent screening module is configured to: detect abnormal behavior in the work-related injury medical process based on multi-dimensional information of relevant data through machine learning algorithms, and output a list of institutions and personnel suspected of fraud;

[0037] The risk assessment submodule is configured to: use machine learning and data analysis technology to identify abnormal patterns and potential risks for a list of institutions and personnel suspected of fraudulent behavior and obtain assessment results;

[0038] The risk scoring submodule is configured to: generate a risk score for each institution and person based on the assessment results, and mark key supervision objects;

[0039] The random inspection and task assignment module is configured to: assign the list of key supervision targets to the relevant agencies for round-up tasks, verify the specific employee information and round-up requirements;

[0040] The information collection and authentication module is configured to: after receiving the task, the personnel conduct on-site verification;

[0041] The data upload and review module is configured to transmit the authentication data to the background work injury review system through the network.

[0042] As an embodiment, the work-related injury medical expense anti-fraud system based on data screening and remote authentication disclosed herein includes a data collection submodule, an intelligent screening module, a risk assessment submodule, a risk scoring submodule, a random inspection and task assignment module, an information collection and authentication module, and a data upload and review module;

[0043] Among them, the data collection submodule collects data information related to work-related medical expenses from various work-related medical institutions, social security institutions and other data sources, covering data on injured workers, work-related medical institutions, departments, etc. Among them, the data on injured workers include the basic information of injured workers, work units, social security payment records, medical treatment records, work-related injury identification information, expense reimbursement records, hospitalization records, etc.; the data on work-related medical institutions include hospitalization records, expense reimbursement records, medical treatment records, historical violation records, etc. of injured workers; the data on departments include hospitalization records, expense data, medical treatment records, medication lists, etc. of departments. The collected data are cleaned, deduplicated, formatted and other pre-processing operations are performed to ensure the accuracy and consistency of the data, and the data are factorized and labeled to form a structured data set;

[0044] The intelligent screening module is based on multi-dimensional information such as work-related medical data, work-related injury insurance recognition data, historical data, etc., and is trained through machine learning algorithms. It adopts a typical machine learning workflow, including data preprocessing (to implement operations such as data cleaning and integration), feature engineering, model selection (selecting machine learning algorithms (random forests)), model training and evaluation, anomaly detection and result output, to achieve anomaly detection of work-related medical institutions, departments, and behaviors of employees seeking medical treatment for work-related injuries, and output a list of work-related medical institutions, departments, and employees seeking medical treatment for work-related injuries that are suspected of fraud.

[0045] The risk assessment submodule uses machine learning and data analysis technology to analyze the historical data of workers, departments, and medical institutions for work-related injuries, identify abnormal patterns and potential risks, and obtain assessment results. The main algorithms include anomaly detection and cluster analysis.

[0046] The risk scoring submodule then generates risk scores for each institution and individual based on the assessment results, marking key regulatory targets;

[0047] Specifically, it includes:

[0048] Intelligent screening of risky medical institutions for work-related injuries. Extract key features such as average length of stay, total cost, and cost distribution by structuring data sets related to medical institutions for work-related injuries; use statistical methods and machine learning algorithms to detect anomalies in expense reimbursement records and hospitalization data of medical institutions for work-related injuries, with rules including abnormal expense reimbursement and excessive length of stay; intelligently generate risk scores for medical institutions for work-related injuries based on test results and historical records, and classify them into low risk, medium risk, and high risk according to the scores.

[0049] Intelligent screening of risky department lists. Extract key features from structured department-related data sets, such as department cost distribution, average length of stay, diagnosis and treatment patterns, etc.; use statistical methods and machine learning algorithms to detect anomalies in department cost distribution, diagnosis and treatment patterns, and length of stay, including abnormal cost fluctuations, excessive length of stay, etc.; intelligently generate department risk scores based on test results and historical records, and classify them into low risk, medium risk, and high risk according to the scores.

[0050] Intelligent screening of the medical list of workers with work-related injuries. Extract key features through structured data sets related to workers with work-related injuries, such as the number of annual work-related injuries, total work-related injury expenses, and number of days of hospitalization for work-related injuries; use statistical methods and machine learning algorithms to detect anomalies in the medical expense reimbursement records and hospitalization days of workers with work-related injuries, with rules including abnormal expenses, excessive hospitalization time, etc.; intelligently generate risk scores for workers with work-related injuries based on the test results and historical records, and classify them into low risk, medium risk, and high risk according to the scores.

[0051] Back-end social security staff conduct a preliminary review of the suspicious data in the intelligent screening module, including the risk scores and related records of work-related injury medical institutions, departments, and employees receiving medical treatment for work-related injuries, and mark out abnormal data that requires further verification.

[0052] Use the suspicious data that has passed the preliminary review as the main data source, and use a random sampling algorithm to randomly generate supplementary data. Combine the preliminary review data and the random sampling data generated by the algorithm to form the final sampling inspection list to ensure the representativeness and comprehensiveness of the sampling inspection.

[0053] According to the sampling inspection list, issue ward rounds to the work-related injury medical institutions or departments through SMS, phone calls or internal channels, and specify the workers who need to be verified. Ensure that the work-related injury medical institutions or departments confirm receipt of the task notification and arrange relevant personnel to perform the task.

[0054] The random inspection and task assignment module issues round-up tasks to the relevant agencies from the list of key supervision targets, verifies specific employee information and round-up requirements; in the information collection and certification module, after the personnel receive the task, they conduct on-site inspection and certification;

[0055] Specifically, it includes: 1) mobile device authentication. The medical institution for work-related injuries receives the task notification and arranges relevant staff to carry mobile devices for ward rounds. After the injured workers log in through facial recognition authentication, the social security staff uses the 5G remote video capability to connect directly "face to face" with the injured workers to ensure the authenticity of the hospitalization information.

[0056] 2) Ward robot authentication: The ward robot automatically arrives at the designated bed, gives voice reminders and guides injured workers to perform real-person authentication operations. The device uses a high-definition camera and a face recognition algorithm to capture and identify the facial features of injured workers in real time to ensure the authenticity of hospitalization information.

[0057] The data upload and review module transmits the certification data to the background work injury review system through the network. The certification data is automatically uploaded to the work injury review system, and the social security staff reviews the uploaded certification data to verify the actual hospitalization of the workers who received medical treatment for work injuries, and adjusts the medical expenses for work injuries based on the review results and makes necessary deductions.

[0058] Example 2

[0059] In one embodiment of the present disclosure, a system for preventing work-related injury medical expenses from being fraudulent is provided based on data screening and remote authentication. Figure 1 As shown, the intelligent screening module 101 is based on multi-dimensional information such as work-related medical data, work-related injury insurance recognition data, historical data, etc., and is trained through machine learning algorithms to achieve abnormal detection of work-related medical institutions, departments, and the behaviors of employees seeking medical treatment for work-related injuries, and outputs a list of work-related medical institutions, departments, and employees seeking medical treatment for work-related injuries that are suspected of fraudulent behavior.

[0060] The data collection submodule 1011 obtains relevant data from the work-related injury medical service institutions and social security institutions, including work-related injury employee information, insurance information, medical treatment records, expense reimbursement records, etc.

[0061] The risk assessment submodule 1012 uses machine learning and data analysis technology to analyze the historical data of workers, departments, and medical institutions for work-related injuries to identify abnormal patterns and potential risks. The main algorithms include anomaly detection, cluster analysis, etc.

[0062] The risk scoring submodule 1013 generates a risk score for each work-related injury medical institution, department, and employee receiving medical treatment for work-related injuries based on the evaluation results, and marks objects with higher risks as those requiring key supervision.

[0063] The random inspection and task assignment module 102 intelligently selects the list of suspected fraudsters output by the algorithm model and combines it with the random inspection mechanism to issue round-up tasks to relevant work-related injury medical institutions through text messages, phone calls or internal channels. The task content clearly indicates the specific work-related injury medical treatment information that needs to be verified and the round-up requirements.

[0064] After receiving the task, the staff of the work-related injury medical institution 103 will go to the ward for on-site verification. There are two ways to collect information: one is to use mobile devices such as mobile phones to guide workers who are injured in the work to perform face recognition and designated actions to ensure that the workers are actually in the hospital and meet the conditions for hospitalization; the other is to use ward robots to automatically reach the designated bed and remind workers who are injured in the work to perform face recognition, information verification and other operations to further improve the efficiency and accuracy of verification.

[0065] The data upload and review module 104 authenticates the data (including face recognition results, action videos of workers receiving medical treatment for work-related injuries, location information, work-related injury information, etc.) and automatically transmits them to the back-end work-related injury review system through the network. Social security staff will review the uploaded data in the system and, after confirming that they are correct, deduct or adjust the relevant work-related injury medical expenses based on the review results to ensure the safety of the fund.

[0066] Example 3

[0067] In one embodiment of the present disclosure, a method for preventing fraud in work-related injury medical expenses based on data screening and remote authentication is provided, comprising:

[0068] Obtain data and information related to work-related injury medical expenses and perform pre-processing;

[0069] Extract key features from structured data, use statistical methods and machine learning algorithms to detect anomalies in key features, intelligently generate risk scores based on the test results and historical records, and classify them into low risk, medium risk, and high risk according to the scores to form preliminary review data;

[0070] Use random sampling algorithms to randomly generate supplementary data, and combine the random sampling data generated by the preliminary review data to form the final sampling inspection list;

[0071] Issue ward rounds to the work-related injury medical institution or department, log in through face recognition authentication, and perform remote identification and authentication; upload authentication data for review to verify the actual hospitalization status of employees receiving work-related injury treatment, and adjust the work-related injury medical expenses based on the review results, and make necessary deductions.

[0072] As an embodiment, the method for preventing fraud of work-related injury medical expenses based on data screening and remote authentication specifically includes:

[0073] S101: Data and information related to work-related injury medical expenses are collected from various work-related injury medical institutions, social security institutions and other data sources, covering data on injured employees, work-related injury medical institutions, departments, etc. Among them, the data on injured employees include the basic information of injured employees, work units, social security payment records, medical treatment records, work-related injury recognition information, expense reimbursement records, hospitalization records, etc.; the data on work-related injury medical institutions include the hospitalization records of injured employees, expense reimbursement records, medical treatment records, historical violation records, etc.; the data on departments include the hospitalization records, expense data, medical treatment records, medication lists, etc. of the department.

[0074] S102: Perform pre-processing operations such as cleaning, deduplication, and formatting on the collected data to ensure the accuracy and consistency of the data, and factorize and label the data to form a structured data set.

[0075] S103: Intelligent screening of risky medical institutions for work-related injuries. Extract key features such as average length of stay, total cost, and cost distribution through structured data sets related to medical institutions for work-related injuries; use statistical methods and machine learning algorithms to detect anomalies in expense reimbursement records and hospitalization data of medical institutions for work-related injuries, with rules including abnormal expense reimbursement and excessive length of stay; intelligently generate risk scores for medical institutions for work-related injuries based on test results and historical records, and classify them into low risk, medium risk, and high risk according to the scores.

[0076] S104: Intelligent screening of risky department lists. Extract key features from structured department-related data sets, such as department cost distribution, average length of stay, diagnosis and treatment patterns, etc.; use statistical methods and machine learning algorithms to detect anomalies in department cost distribution, diagnosis and treatment patterns, and length of stay, with rules including abnormal cost fluctuations, excessive length of stay, etc.; intelligently generate department risk scores based on test results and historical records, and classify them into low risk, medium risk, and high risk according to the scores.

[0077] S105: Intelligent screening of the medical treatment list for workers with work-related injuries. Extract key features through structured data sets related to workers with work-related injuries, such as the number of annual work-related injuries, total work-related injury expenses, and number of days of hospitalization for work-related injuries; use statistical methods and machine learning algorithms to detect anomalies in the medical expense reimbursement records and hospitalization days of workers with work-related injuries, with rules including abnormal expenses, excessive hospitalization time, etc.; intelligently generate risk scores for workers with work-related injuries based on the test results and historical records, and classify them into low risk, medium risk, and high risk according to the scores.

[0078] S106: Backstage social security staff conducts a preliminary review of the suspicious data in the intelligent screening module, including the risk scores and related records of work-related injury medical institutions, departments and workers receiving medical treatment for work-related injuries, and marks abnormal data that require further verification.

[0079] S107: Use the suspicious data that have passed the preliminary review as the main data source, and use the random sampling algorithm to randomly generate supplementary data. Combine the preliminary review data and the random sampling data generated by the algorithm to form the final sampling inspection list to ensure the representativeness and comprehensiveness of the sampling inspection.

[0080] S108: Based on the sampling inspection list, issue ward rounds to the work-related injury medical institutions or departments through SMS, phone calls or internal channels, and specify the workers who need to be verified. Ensure that the work-related injury medical institutions or departments confirm receipt of the task notification and arrange relevant personnel to perform the task.

[0081] S109: Mobile device authentication. The work-related injury medical institution receives the task notification and arranges relevant staff to carry mobile devices for ward rounds. After the injured employee logs in through face recognition authentication, the social security staff uses the 5G remote video capability to connect directly "face to face" with the injured employee to ensure the authenticity of the hospitalization information.

[0082] S1010: Ward robot authentication. The ward robot automatically arrives at the designated bed, gives voice reminders and guides injured workers to perform real-person authentication operations. The device uses a high-definition camera and a face recognition algorithm to capture and identify the facial features of injured workers in real time to ensure the authenticity of hospitalization information.

[0083] S1011: The certification data is automatically uploaded to the work-related injury review system. Social security staff will review the uploaded certification data to verify the actual hospitalization status of employees who have received work-related injuries. Based on the review results, they will adjust the work-related injury medical expenses and make necessary deductions.

[0084] Example 4

[0085] In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, a method of implementing an anti-fraud system for work-related injury medical expenses based on data screening and remote authentication is implemented.

[0086] Example 5

[0087] In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the method of implementing the work-related injury medical expense anti-fraud system based on data screening and remote authentication.

[0088] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0090] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. The work-related injury medical expense anti-fraud system based on data screening and remote authentication is characterized by: include: The data collection submodule is configured to: obtain relevant data from relevant institution systems; An intelligent screening module is configured to: detect abnormal behavior in the work-related injury medical process based on multi-dimensional information of relevant data through machine learning algorithms, and output a list of institutions and personnel suspected of fraud; The risk assessment submodule is configured to: use machine learning and data analysis technology to identify abnormal patterns and potential risks for a list of institutions and personnel suspected of fraudulent behavior and obtain assessment results; The risk scoring submodule is configured to: generate a risk score for each institution and person based on the assessment results, and mark key supervision objects; The random inspection and task assignment module is configured to: assign the list of key supervision targets to the relevant agencies for round-up tasks, verify the specific employee information and round-up requirements; The information collection and authentication module is configured to: after receiving the task, the personnel conduct on-site verification; The data upload and review module is configured to transmit the authentication data to the background work injury review system through the network.

2. The work-related injury medical expense anti-fraud system based on data screening and remote authentication as claimed in claim 1, characterized in that: Relevant data are obtained from the systems of relevant institutions, including: information on injured employees, insurance information, medical treatment records, and expense reimbursement records; based on the information on injured employees, insurance information, and multi-dimensional information of historical data, machine learning algorithms are used to detect anomalies in the behaviors of injured medical institutions, departments, and injured employees, and output a list of injured medical institutions, departments, and injured employees suspected of fraud.

3. The work-related injury medical expense anti-fraud system based on data screening and remote authentication as claimed in claim 1, characterized in that: Using machine learning and data analysis technology, anomaly detection and cluster analysis are performed on the historical data of work-related injury medical treatment workers, departments, and work-related injury medical treatment institutions in the list of work-related injury medical treatment institutions, departments, and work-related injury medical treatment workers suspected of fraud, to identify abnormal patterns and potential risks and conduct assessments.

4. The work-related injury medical expense anti-fraud system based on data screening and remote authentication as claimed in claim 1, characterized in that: Based on the assessment results, a risk score will be generated for each work-related injury medical institution, department and employee receiving medical treatment for work-related injuries, and high-risk objects will be marked as those requiring key supervision. Combined with the random inspection mechanism, a list of objects requiring supervision will be intelligently screened out, and ward rounds will be assigned to relevant work-related injury medical institutions via text messages, phone calls or internal channels. The task content clearly indicates the specific information of employees receiving medical treatment for work-related injuries that needs to be verified and the ward rounds requirements.

5. The work-related injury medical expense anti-fraud system based on data screening and remote authentication as claimed in claim 1, characterized in that: In the information collection and authentication module, the information collection methods include: first, through mobile devices, guiding employees who receive medical treatment for work-related injuries to perform facial recognition and designated action operations to ensure that the employees who receive medical treatment for work-related injuries are actually in the hospital and meet the conditions for hospitalization for work-related injuries; second, using ward robots to automatically reach designated beds to perform facial recognition and information verification operations on employees who receive medical treatment for work-related injuries.

6. The work-related injury medical expense anti-fraud system based on data screening and remote authentication as claimed in claim 1, characterized in that: The authentication data includes facial recognition results, action videos of workers seeking medical treatment for work-related injuries, location information, and work-related injury information.

7. The work-related injury medical expense anti-fraud system based on data screening and remote authentication as claimed in claim 1, characterized in that: The list of institutions and personnel suspected of fraudulent behavior that are intelligently screened includes: extracting key features from the structured data of work-related injury medical institutions, using statistical methods and machine learning algorithms to detect anomalies in the expense reimbursement records and hospitalization data of work-related injury medical institutions. The rules include abnormal expense reimbursement and excessive hospitalization days. Based on the test results and historical records, risk scores for work-related injury medical institutions, departments, and employees are intelligently generated and classified into low risk, medium risk, and high risk according to the scores.

8. A method for preventing fraud in work-related medical expenses based on data screening and remote authentication according to any one of claims 1 to 7, characterized in that: include: Obtain data and information related to work-related injury medical expenses and perform pre-processing; Extract key features from structured data, use statistical methods and machine learning algorithms to detect anomalies in key features, intelligently generate risk scores based on the test results and historical records, and classify them into low risk, medium risk, and high risk according to the scores to form preliminary review data; Use random sampling algorithms to randomly generate supplementary data, and combine the random sampling data generated by the preliminary review data to form the final sampling inspection list; Issue ward rounds to the work-related injury medical institution or department, log in through face recognition authentication, and perform remote identification and authentication; upload authentication data for review to verify the actual hospitalization status of employees receiving work-related injury treatment, and adjust the work-related injury medical expenses based on the review results, and make necessary deductions.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the method of the work-related injury medical expense anti-fraud system based on data screening and remote authentication as described in claim 8 is implemented.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the method of implementing the work-related injury medical expense anti-fraud system based on data screening and remote authentication as described in any one of claim 8.

Images