TWM627725U - Claims Fraud Detection and Prevention System - Google Patents

Abstract

A claims fraud detection and prevention system is disclosed herein, the system includes electrically coupled to each other A connected processing module, an associated network module, an expert rule module and a risk assessment module. The system uses the processing module to cooperate with each module, and uses the expert rule module and the associated network module to detect the associated groups for the target claim case information, and analyzes whether the associated groups are abnormal, and calculates and analyzes the abnormal risk. A percentile rating to assess whether the underlying claim information is a high-risk fraud case.

Description

Claims Fraud Detection and Prevention System

The new model belongs to the field of insurance claim settlement, in particular to a system capable of implementing a method for detecting and preventing insurance claim settlement fraud.

In the field of insurance business, in addition to insurance and underwriting, insurance claims settlement is one of the main businesses. Although the field is currently committed to the systematization of the traditional claim settlement process, there is still no effective detection and prevention of fraud cases that may exist in insurance claims. The management unit will eventually send a special person to conduct cross-examination and collect details related to claims cases. This method requires long-term human experience, lacks systematic management, and lacks a risk classification system.

There are a large number of insurance claims cases, and there is currently no relevant tool or system in the prior art that can effectively detect and prevent insurance claims fraud. In view of this, there is an urgent need in the art for a novel claim settlement fraud detection and prevention system to improve the deficiencies of the prior art.

The novel content is intended to provide a simplified summary of the disclosure to give the reader a basic understanding of the disclosure. This summary is not an exhaustive overview of the disclosure and is not intended to identify important or critical elements of the novel embodiments or to delineate the scope of the novel.

The new system relates to a claim settlement fraud detection and prevention system and a method for using the claim settlement fraud detection and prevention system to assess the risk of insurance claim fraud. In addition to the effective detection and prevention of fraud risks in the method analysis, the claim settlement fraud detection and prevention system also has various functions of the graphical user interface. The settings of the function page allow users to quickly detect possible fraud risks in the process of claim settlement.

A new aspect of the present invention relates to a method for assessing the risk of insurance claim fraud by using a claim fraud detection and prevention system. Specifically, the claim settlement and fraud detection and prevention system includes a processing module, an associated network module, an expert rule module and a risk assessment module coupled to each other. Furthermore, the method for insurance claim fraud risk includes the following steps: (a) using the processing module to obtain information on a target claim case, and using an expert rule module to determine whether the target claim case information is abnormal, if so; , to obtain the abnormal information of a target claim settlement case; (b) use the associated network module to obtain at least one associated claim settlement case information corresponding to the abnormal information of the target claim settlement case; (c) use the expert rule module to determine the at least one related claim settlement case information; Whether the related claims case information is abnormal, if so, obtain at least one related claim case abnormal information; (d) use the risk assessment module to obtain a group of cases based on the subject claim case information and the at least one related claim case information (e) use the risk assessment module to obtain the group compensation amount corresponding to the number of cases in the group, and refer to the group abnormality ratio to obtain a group of abnormal risk values; and (f) repeating the steps (a)-(e) to obtain a plurality of group abnormal risk values, and use the risk assessment module to classify the plurality of group abnormal risk values according to the size Sorting to obtain an abnormal risk percentage level corresponding to the abnormal risk values of these groups, wherein when the abnormal risk percentage level reaches a set risk threshold, the abnormal risk The information of the subject claim settlement corresponding to the risk percentage level is regarded as a fraudulent high-risk case.

In an optional embodiment, the expert rule module includes a plurality of expert rule information, which are selected from the group consisting of: the number of times of payment, the number of times of trips, abnormal trips, short-term trips, frequent trips, and insurance Multiple insurance types, major notification records, special data file records and over-insurance.

In other embodiments, the association network module includes analyzing a plurality of node information corresponding to the subject claim case information, wherein the node information is selected from the group consisting of: the total number of nodes, the total number of associations, Number of reporting nodes, number of license plate nodes and number of personnel nodes.

According to a further embodiment of the present invention, in the step (b), the associated network module generates a corresponding associated network diagram according to the at least one associated claim settlement case information. Furthermore, the association network graph is presented according to the node information, and is composed of a plurality of nodes and association lines, and one side of any node displays a statistical data corresponding to the expert rule information.

In an embodiment of the present invention, the method further includes generating a claim management screen by using the processing module, wherein the claims management screen includes a case management list, wherein the case management list is used to display the information of the target claim case.

In other embodiments of the present invention, a warning graphic may be generated on the claims management screen, and the warning graphic may be displayed on the case management list.

In yet another embodiment of the present invention, the case management list further includes an anomaly check page for checking a claim data corresponding to the target claim case information. Specifically, the exception checking page further includes a case related information and a case checking rule list.

In an optional embodiment, the case-related information includes a number of nodes, a number of associations, a number of cases, a number of license plates, a number of persons, or a combination thereof.

According to an embodiment of the present invention, the method further includes using the risk assessment module to perform a group pattern analysis according to at least one related claim settlement case information of the related network module and at least one related claim settlement case abnormal information of the expert rule module, and obtains: Results of a population-like analysis.

Another aspect of the present invention relates to a claim settlement fraud detection and prevention system, which operates in a computer host, and the system includes a processing module, an associated network module, an expert rule module and A risk assessment module. The claim settlement fraud detection and prevention system is used to execute the method described in any one of the above embodiments.

After referring to the following embodiments, those with ordinary knowledge in the technical field to which the present invention pertains can easily understand the basic spirit and other new purposes of the present invention, as well as the technical means and implementation aspects of the present invention.

The main component symbols of this new model are listed as follows:

10: Hardware equipment

11: Storage device

12: Processor

13: Communication components

14: Input device

15: Display

100: Claims Fraud Detection and Prevention System

110: Processing modules

120: Associated Network Modules

130: Expert Rules Module

140: Risk Assessment Module

301, 303, 305, 307, 309, 311: Steps

400: Claims management screen

410: Case Management List

412: Warning Graphics

414: Case information sub-page

416: Exception check paging

422: Claims Case Information

424: Case related information

426: Group Information

428: Case Review Information

432: Warning reminder picture

500: Associated Network Graph

510: Node

520: Associated Line

In order to make the above and other objects, features, advantages and embodiments of the present invention more clearly understood, the accompanying drawings are described as follows: Figure 1 shows the hardware for running the new system according to an embodiment of the present invention. A schematic diagram of the device 10; FIG. 2 is a schematic diagram of a new claim settlement fraud detection and prevention system 100 according to an embodiment of the present invention; FIG. 3 is a new claim settlement fraud detection and prevention method according to an embodiment of the present disclosure. flow chart; 4A to 4D are schematic diagrams of a claims management screen 400 according to an embodiment of the present disclosure; and FIG. 5 is a schematic diagram of an associated network diagram 500 according to another embodiment of the present disclosure.

In accordance with common practice, the various features and elements in the drawings are not drawn to scale, but are drawn in order to best represent specific features and elements relevant to the present invention. Furthermore, the same or similar reference numerals are used to refer to similar elements/components among the different drawings.

In order to make the description of the present disclosure more detailed and complete, the following provides an illustrative description for the implementation aspects and specific embodiments of the present invention; but this is not the only form of implementing or using the specific embodiments of the present invention. The features of various specific embodiments as well as method steps and sequences for constructing and operating these specific embodiments are encompassed in the detailed description. However, other embodiments may also be utilized to achieve the same or equivalent function and sequence of steps.

Unless otherwise defined in this specification, the scientific and technical terms used herein have the same meanings as understood and commonly used by those of ordinary skill in the art to which the present invention belongs. In addition, unless contradicting the context, the singular noun used in this specification covers the plural form of the noun; and the plural noun used also covers the singular form of the noun.

In order to solve the defects existing in the prior art, the present invention provides a novel claim settlement fraud detection and prevention method and system, which can display abnormal claim settlement cases in real time, integrate multiple information of claim settlement cases, and enable users to Quickly and comprehensively review abnormal claims cases, thereby reducing the risk of insurance fraud and optimizing the claims mode.

FIG. 1 shows a hardware device 10 for running the system of the present invention according to an embodiment of the present invention. Structurally, the hardware device 10 includes, but is not limited to, a storage device 11 , a processor 12 , a communication element 13 , an input device 14 and a display 15 that are electrically and/or communicatively coupled to each other. The hardware device 10 is a computer device, such as a computer host.

Examples of the processor 12 include, but are not limited to, a central processing unit (CPU), or other programmable general-purpose or special-purpose microprocessors (Microprocessors), digital signal processors (Digital Signal Processors) Processor, DSP), programmable controller, Application Specific Integrated Circuit (ASIC), or other similar components or combinations of the above components, the present disclosure is not limited thereto.

The storage device 11 is used to store the novel system, and includes necessary data and program codes required by the processor 12 to run. The storage device 11 can be any type of fixed or removable random access memory (Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), flash memory (flash memory), hard disk (Hard Disk Drive, HDD), Solid State Drive (Solid State Drive, SSD) or similar components or a combination of the above components.

The input device 14 is used for providing the user to input various types of information, data and instructions to the processor 12 . In particular, the input device 14 can receive voice commands and target capture commands from the user. Examples of the input device 14 include, but are not limited to, a controller for operating a video recording device, a microphone, a keyboard, a mouse, a touch screen, a pedal, a human machine interface, or other communication interfaces that allow the user to Input data by connecting to other electronic devices (for example, connecting to a mobile phone through a Bluetooth interface, and then inputting data through a mobile phone). The human-machine interface can be, but is not limited to, a mouse, a switch, or other electromechanical devices for control. The present disclosure is not limited by the implementation of the input device 14 .

Examples of the communication element 13 include, but are not limited to, support for Global System for Mobile communication (GSM), Personal Handy-phone System (PHS), Code Division Multiple Access (Code Division Multiple Access) , CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, Long Term Evolution (LTE) system, Worldwide interoperability for Microwave Access (WiMAX) system, wireless security True (Wireless Fidelity, Wi-Fi) system or Bluetooth signal transmission components.

FIG. 2 is a schematic diagram of a new claim settlement fraud detection and prevention system 100 according to an embodiment of the present invention. The claim settlement fraud detection and prevention system 100 includes a processing module 110 , an associated network module 120 , an expert rule module 130 and a risk assessment module 140 that are electrically coupled to each other. The associated processing module 110 is electrically coupled to each of the modules, and is used for cooperating with each of the modules to process and calculate the information in the novel method, so as to complete the insurance claim fraud detection and prevention method of the present invention.

Please also refer to FIG. 3. FIG. 3 is a flowchart of an insurance claim fraud detection and prevention method according to an embodiment of the present invention. In the process of insurance claims, first, the processing module 110 is used to obtain the information of a target claim case, and the expert rule module is used to judge whether the information of the target claim case is abnormal, and if so, obtain the abnormal information of the target claim case (step 1). 301).

In an optional embodiment, the expert rule module includes a plurality of expert rule information, including but not limited to the number of payments, the number of trips, abnormal trips, short-term trips, frequent trips, multi-insurance types, and major notification records , special profile records and over-insurance. The setting of the expert rule can adjust the threshold of each rule parameter according to the actual usage. For example, if the number of rule items set by the expert rule is violated, it can be determined that the information of the target claim settlement case is abnormal.

Next, use the associated network module 120 to obtain at least one associated claim case information corresponding to the abnormal information of the target claim case, so as to grasp the associated claim case information related to the abnormal information of the target claim case (step 303 ), and to further understand related claims The number of groups associated with case information.

In addition, in other embodiments, in step 303, the association network module 120 generates a corresponding association network graph according to at least one associated claim settlement case information, which is composed of a plurality of nodes and association lines, and any one One side of the node displays a statistic corresponding to the expert rule information. Specifically, the association network module 120 includes analyzing a plurality of node information corresponding to the target claim settlement case information, wherein the node information includes, but is not limited to, the total number of nodes, the total number of associations, the number of reporting nodes, the number of license plate nodes, and the number of personnel. number of nodes. Furthermore, in addition to passing through the nodes, the association network module can also further analyze the associations of the nodes and classify the associations. Taking auto insurance as an example, it includes, but is not limited to, the underwriting relationship, the accident-causing relationship, the driving relationship, etc. . In addition, the relevant statistical data may be insurance premiums, claims settlement costs, personnel information or subject information, etc.

Furthermore, the expert rule module 130 determines whether the information of the at least one related claim settlement case is abnormal, and if so, obtains at least one related claim settlement case abnormal information (step 305 ). Next, the risk assessment module 140 is used to calculate and obtain the number of group cases and a number of abnormal cases corresponding to the number of group cases according to the target claim case information and at least one related claim case information to obtain a group abnormal ratio (step 307 ). Specifically, the group abnormality ratio is the percentage of the number of abnormal cases in the number of group cases.

Next, the risk assessment module 140 also calculates a group abnormal risk value according to the group compensation amount corresponding to the number of group cases and with reference to the group abnormality ratio (step 309 ).

Repeat steps 301-309 to obtain a plurality of group abnormal risk values, and use the risk assessment module 140 to sort the plurality of group abnormal risk values according to size, and obtain an abnormal risk percentage level corresponding to the abnormal risk values of these groups, wherein when When the abnormal risk percentage level reaches a certain set risk threshold, the information of the subject claim settlement corresponding to the abnormal risk percentage level is regarded as a high-risk fraud case (step 311 ).

It can be seen from the above-mentioned contents of this new model that, through the multi-layer structure, the new model analyzes the scale and shape of the related groups related to the target claim settlement case, and analyzes whether there are abnormal behaviors and corresponding abnormal risks, and can timely screen out insurance. High-risk cases of fraudulent claims.

4A to 4D are claims management screens 400 provided by the method of the present invention according to an embodiment of the present invention. The claims management screen 400 of the present invention transmits image information to the display 15 through the processing module 110 . Referring to FIG. 4A, the claims management screen 400 includes a case management list 410 for displaying at least one target claim case information. The claim settlement case information may include case number, type, case note, due date, case status, investigation schedule, etc. The relevant information displayed on the case management list 410 may be modified according to the actual needs of the user. The claim settlement case management screen 400 may include a case information sub-page 414 for displaying detailed information of the subject claim settlement case information.

Furthermore, the claim settlement management screen 400 of the present invention further includes a warning image 412 to mark high-risk fraud cases, and is displayed on the side of the case number in the subject claim settlement information of the case management list 410 . The warning image 412 can also be a hyperlink, which the user can click to bring to the anomaly check page 416 (FIG. 4C).

The abnormality check page 416 is used to display claim settlement case information 422 , case related information 424 , group information 426 and case check information 428 . A warning reminder graphic 432 is provided on one side of the case related information 424 and the case verification information 428 to show whether abnormal. Furthermore, it should be noted that the anomaly check page 416 of the present invention is specially configured to display group information 426, which covers group size and group form, wherein the group size is used to view the related claims related to the subject claim information. The number of nodes and correlations of case information, and the group pattern is used to check the type of abnormal pattern of the group. In an optional embodiment, the case-related information includes, but is not limited to, the number of nodes, the number of associations, the number of cases, the number of license plates, the number of personnel, or a combination thereof.

In addition, the case checking information 428 is a case checking rule list. For example, the description includes, but is not limited to, the short time for two claims settlement time and the recent multiple claims settlement records.

According to an embodiment of the present invention, the method of the present invention may further include using the risk assessment module 140 to perform group pattern analysis according to the related claim settlement case information of the related network module 120 and the related claim settlement case abnormal information of the expert rule module 130, Obtain a group of morphological analysis results. For example, the group profile may be the related records that the group includes 60% of the personnel in different cases.

FIG. 5 is an associated network diagram 500 according to an embodiment of the present invention. The associated network graph 500 can also be configured to display a graphical associated network graph 500 by clicking an option on the claims management screen 400 . The association network graph 500 is presented according to node information, and is composed of a plurality of nodes 510 and association lines 520 . The relevant statistical data can be insurance premiums, claim amounts, personnel information or subject information, etc.

In Figure 5, the auto insurance case is taken as an example. The figure shows the information of multiple nodes, including the insured, the owner, the case, etc., and also shows the correlation of each node, such as underwriting relationship, accident relationship, driving relationship, etc. It should be noted that the graphical association network diagram 500 can indicate the number of groups formed by the relevant cases related to the target claims case and the possible group appearance. The analysis results displayed in this two-dimensional format can improve the ability of practitioners to inspect abnormal cases. Alertness and immediacy.

Based on the above, the claim fraud detection and prevention system proposed by the present invention and the method for evaluating the risk of insurance claim fraud by using the system can systematically detect and prevent claims fraud cases through the cooperation of various modules, and adopt active detection and real-time protection. It can effectively and accurately carry out risk classification, quantify the security control mechanism, and improve the efficiency and accuracy of insurance claims fraud detection and prevention.

100: Claims Fraud Detection and Prevention System

110: Processing modules

120: Associated Network Modules

130: Expert Rules Module

140: Risk Assessment Module

Claims (11)

A claim settlement fraud detection and prevention system operates in a computer host, the system includes a processing module, an associated network module, an expert rule module and a risk assessment module electrically coupled to each other, wherein: (a) use the processing module to obtain the information of a target claim case, and use an expert rule module to judge whether the target claim case information is abnormal, if so, obtain the abnormal information of a target claim case; (b) use the correlation The network module obtains at least one related claim case information corresponding to the abnormal information of the target claim case; (c) judges whether the at least one related claim case information is abnormal by the expert rule module, and if so, obtains at least one related claim case information; (d) Using the risk assessment module to obtain the number of cases of a group and the number of abnormal cases corresponding to the number of cases of the group based on the information of the target claim case and the information of the at least one related claim case , obtain a group of abnormal proportions; (e) use the risk assessment module to obtain the group compensation amount corresponding to the number of cases in the group, and refer to the group abnormal proportion to obtain a group of abnormal risk values; and (f) repeat the Steps (a)-(e), obtaining a plurality of group abnormal risk values, and using the risk assessment module to sort the plurality of group abnormal risk values according to size, to obtain an abnormal risk corresponding to the group abnormal risk values respectively Percentage level, wherein when the abnormal risk percentile level reaches a set risk threshold, the information of the target claim settlement corresponding to the abnormal risk percentile level is regarded as a fraudulent high-risk case. The system according to claim 1, wherein the expert rule module includes a plurality of expert rule information, which are selected from the following groups: the number of times of payment, the number of trips, abnormal trips, short-term trips, frequent trips, and insurance Multiple insurance types, major notification records, special data file records and over-insurance. The system of claim 1, wherein the associated network module includes analyzing a plurality of node information corresponding to the subject claim case information, wherein the node information is selected from the group consisting of: the total number of nodes , the total number of associations, the number of reporting nodes, the number of license plate nodes, and the number of personnel nodes. The system of claim 3, wherein in the step (b), the associated network module generates a corresponding associated network graph according to the at least one associated claim settlement case information. The system of claim 4, wherein the association network graph is presented according to the node information, and is composed of a plurality of nodes and association lines, and one side of any of the nodes displays an image corresponding to the expert rule information. Statistical data. The system of claim 1, further comprising: using the processing module to generate a claims management screen, wherein the claims management screen includes a case management list, wherein the case management list is used to display the target claim case information. The system according to claim 6, further comprising: if the target claim settlement case information is a fraud high-risk case, displaying a warning image on the case management list. The system according to claim 7, wherein the case management list further includes an abnormality check page for checking a claim data corresponding to the target claim settlement information. The system of claim 8, wherein the exception checking page further includes a case related information and a case checking rule list. The system of claim 9, wherein the case-related information includes a number of nodes, a number of associations, a number of cases, a number of license plates, a number of personnel, or a combination thereof. The system according to claim 1, further comprising using the risk assessment module to perform a group pattern analysis according to at least one related claim settlement case information of the related network module and at least one related claim settlement case exception information of the expert rule module , to obtain a group of morphological analysis results.

Images