TWM574295U - Claim expense auditing device - Google Patents

Abstract

The present disclosure provides a claim expense auditing device. The claim expense auditing device includes an insurance database and a processor, the processor is coupled to the insurance database. The insurance database is configured to store a past claim data, the past claim data includes a claim type and a claim expense corresponding to the claim type. The processor is configured to receive a claim request, read the past claim data in the insurance database to determine whether the claim type of the claim request exists or not, and when the claim type of the claim request exists, the processor retrieves the claim expense corresponding to the claim type.

Description

Claim review device

The present disclosure relates to an auditing device and, more particularly, to an auditing device for claims.

The quality of life of human beings is closely related to physical health. Once the body is harmed, the subsequent medical expenses often far exceed the burden of the parties. Therefore, the insurance system with mutual help concept in human society will follow. Different types of insurance products are also available based on the life and experience of each individual. Different types of goods have different types of claims systems.

When a policyholder is injured or has difficulty, he can apply for a claim through a contract with an insurance company. However, when the policyholders are most in need of help and the busiest, they are unable to receive the required compensation. Therefore, for insurance companies, the existing claims procedures are quite lengthy and there is an urgent need to propose improvements. To better play the role of insurance.

According to one embodiment of the present disclosure, a claims review apparatus is disclosed. The claims review device includes an insurance database and a processor, wherein the processor is coupled to the insurance database. The above insurance database is used to store historical claims data. This historical claim data contains the type of claim and the amount of the claim corresponding to the type of claim. The processor is configured to receive the claim request, read the historical claim data of the insurance database, to determine whether the claim request has the type of claim, and if the processor determines that the claim has the claim type, the claim corresponding to the claim type is obtained. The amount, where the claim amount is the amount of compensation received in the historical claims data.

According to another embodiment, a claim review method is disclosed for use in a claim review apparatus, wherein the claim review apparatus includes an insurance database and a processor. The historical claim data is stored in the insurance database, and the historical claims data includes the type of claim and the amount of the claim corresponding to the type of claim. The above claim review method comprises the steps of: receiving a claim request, reading a historical claim data of the insurance database, determining whether the claim request has a claim type, and, if the claim claim has a claim type, obtaining the claim corresponding to the claim The type of claim amount, where the claim amount is the amount of compensation received in the historical claim data.

The above and other objects, features, advantages and embodiments of the present disclosure will become more apparent and understood.

100‧‧‧ Claims review device

110‧‧‧ processor

120‧‧‧Insurance database

300‧‧‧blockchain database

S210~S280‧‧‧Steps

The detailed description below will be readily appreciated by reference to the accompanying drawings. It should be noted that the various features in the drawings are not necessarily drawn to scale. In fact, the dimensions of the features may be arbitrarily increased or decreased for clarity of discussion.

FIG. 1 is a block diagram showing the function of a claim review apparatus according to some embodiments of the present disclosure.

FIG. 2 is a flow chart showing the steps of a claim review method performed by the claims review apparatus according to some embodiments of the present disclosure.

The following disclosure provides many different embodiments or examples in order to implement various features of the present invention. Specific examples of components and permutations are described below to simplify the creation. Of course, the examples are merely exemplary and are not intended to be limiting. For example, forming the first feature over the second feature or the second feature in the following description may include forming the first feature and the second feature in direct contact, and may also include the first feature and the second feature Additional features are formed between the features such that the first features and features may not be in direct contact.

Please refer to FIG. 1 , which is a functional block diagram of a claim review apparatus 100 in accordance with some embodiments of the present disclosure. As shown in FIG. 1, the claims review apparatus 100 includes a processor 110 and an insurance database 120. The processor 110 is coupled to the insurance database 120 to access the data in the insurance database 120 at any time. The insurance database 120 stores all the policy information of the policyholders, such as the claims delivery information of all the policyholders that the insurance company has accepted in the past. The foregoing claims delivery information includes but is not limited to the following categories: accidental injury insurance, fire insurance, medical insurance, life insurance, and auto insurance.

The aforementioned historical claims data includes the type of claim and the amount of the claim corresponding to the type of claim. For example, the policyholder may accidentally hit the chin and cause the teeth to break. There are different claims for each injured tooth or injury type. For example, the amount of the claim for the large incisors is 4,000 yuan, and the amount of the small molars is 3,000 yuan. . In another example, the policyholder may accidentally bruise and cause a hand fracture. The amount of the claim for the fracture of the finger is 2,000 yuan, and the amount of the fracture of the elbow is 8,000 yuan. Therefore, the processor 110 is determining the claim request Whether the claim conditions of the contract terms are met, the historical claims data in the insurance database 120 is accessed, and according to the case data that has been accepted, such as the claims cases that have been accepted and the compensated claims, further automatic claims are made. Or the decision of a manual claim.

Referring to FIG. 1 , the processor 110 of the claims review apparatus 100 and the insurance database 120 are separately connected to the blockchain database 300. The blockchain database 300 can be used to share or exchange acquired databases with external agencies. The blockchain database 300 stores reference pathological data about other policyholders and a reference amount corresponding to the reference pathology data. For example, in the blockchain database 300, there are records of injuries and claims regarding the tooth parts, including the amount of the claim for the large incisors fracture being 3,500 yuan, and the amount of the claim for the small caries fracture being 2,000 yuan. The details of the claim review apparatus 100 with reference to the blockchain database 300 will be described later.

In some embodiments, the claims review apparatus 100 digitizes all relevant documents (eg, claims delivery materials, external references, etc.). For example, documents such as claims delivery data or blockchain data may be original paper documents. First, these files need to be scanned to generate digital image files, and optical characters are recognized for these images ( Optical Character Recognition (OCR) to obtain the corresponding text file. These text files are then identified by text vocabulary to segment the data fields available for the claims review device 100. During the claims review process, all claims delivery data will be stored in the insurance database 120 after digitization and data field segmentation. Each historical claim data in the insurance database 120 includes, but is not limited to, the following data fields: claim type, claim amount, claim result, and the like. among them, The historical claims data has corresponding pathological examination data, such as X-ray films, ultrasonic images, and the like. Therefore, the claim review apparatus 100 reads the historical claims data and the pathological check data in the insurance database 120 to determine whether the claims delivery data meets the claim conditions.

Please refer to FIG. 2, which is a flow chart showing the steps of the claim review method used by the claims review apparatus 100 in accordance with some embodiments of the present disclosure. In order to clarify the steps of the claim review method, please refer to Figure 1 and Figure 2 for the following instructions.

As shown in FIG. 2, in step S210, the claims review apparatus 100 receives a claim request. This claim may be sent to the claim of the aforementioned policyholder. Next, in step S220, the processor 110 determines whether it belongs to the automatic claim case. The processor 110 reads the historical claim data in the insurance database 120, wherein the historical claims data includes the claim type and the claim amount corresponding to the claim type. The historical claims data and the contents of its data fields are, for example, the following information: "Types of claims: large front teeth break, claim amount: 4000 yuan; claim result: yes". "Type of claim: small molar fracture, claim amount: 3000 yuan, claim result: yes." "Type of claim: fracture of the elbow, the amount of the claim: 8,000 yuan, the result of the claim: no."

Next, in step S230, the processor 110 determines whether the claim request has the associated claim type. In an example, the processor 110 reads the data field of the claim delivery data and obtains the medical record text of the claim request. For example, the processor 110 parses the medical record text data into a "small molar tooth break", and compares the textual content of the medical record with the historical claim data. In this example, the processor 110 is based on the "small molar fracture" of the medical text data. The insurance claim database 120 searches for the historical claim data "small caries break" that meets the claim request. Therefore, in step S240, the processor 110 obtains the claim amount corresponding to the claim type "small caries break" to "3000 yuan". In another example, if the medical record text of the claim request is “ankle sprain”, since the historical claim data about the ankle sprain is not recorded in the insurance database 120, step S250 is executed, and the processor 110 notes the corresponding claim. The claimed claim case is a non-automatic claim case. Accordingly, the claim case will be assigned to a manual review, and the claimant will later determine that the case should be a claim or a refusal.

In another embodiment of step S230, the processor 110 reads the other relevant information of the claim delivery data, and obtains the pathological image data of the claim request (not limited thereto). For example, the processor 110 determines that the accompanying pathological image data in the claim request is an X-ray image with a broken caries. The processor 110 combines the artificial intelligence algorithm with the image recognition technology to analyze and compare related images in the insurance database 120 according to the corresponding features of the small caries fracture in the pathological image data. If the insurance database 120 has claimed a claim case with an X-ray image of a small caries fracture, the injury information of the X-ray film can be obtained, and it is known that the X-ray film belongs to the claim type of the small caries fracture.

In step S240, after the processor 110 obtains the claim amount, the process proceeds to step S260, and the processor 110 determines whether the claim amount is less than a threshold. The threshold value may be a preset value. For example, the threshold value may be 5000, and the claim amount is less than 5,000 yuan, which belongs to the small automatic claim that the claim review apparatus 100 can handle. In this step, if it is determined that the claim amount is greater than the threshold value, the claims claim may involve a higher amount of claims, and the manual needs to be reviewed. Therefore, the process returns to step S250, and the processor 110 will respond to the claim. The claimed claims are noted as non-automatic claims.

In the foregoing step S260, if the claim amount is 3,000 yuan, which is less than 5000 of the threshold value, then step S270 is performed, and the processor 110 outputs the claim amount corresponding to the claim type in response to the aforementioned claim request. For example, the claim review apparatus 100 has obtained the claim for this time as "small caries break", and the amount that can be claimed is "3000 yuan". It has been confirmed that the claim for claim is in accordance with the claim condition and belongs to the automatic claim case. . Therefore, the claim review apparatus 100 can remit the claim amount to the corresponding bank account of the claim requester, so that the policyholder can directly obtain the claim.

Next, in step S280, the processor 110 stores the foregoing claim request and the corresponding claim amount in the insurance database 120, and adds the newly added historical data to the historical claim data, so that the claim review device 100 is processing This historical data will be considered for the review of the next claim. For example, the processing result of the claim request, the medical record text data related to the claim request and the pathological image data (not limited thereto) are recorded in the insurance database 120, and the claim type is automatically calculated. The number of claims is used as the basis for the next automatic claims reference of the claims review device 100.

On the other hand, after the execution of the step S240 and the acquisition of the claim amount, the claim review apparatus 100 refers to the record data of the blockchain database 300 to correct the acquired claim amount. The blockchain database 300 stores reference pathological data and a reference amount corresponding to the reference pathological data. The reference pathological data may be "large front teeth fracture" and its corresponding reference amount "3500 yuan", "small molar tooth fracture" and its corresponding reference amount "2000 yuan". The processor 110 determines that the claim request "small molar fracture" is in accordance with the reference pathological data of "small molars". "Fracture", so the corresponding reference amount is "2000 yuan". Since the small tooth decay obtained in the foregoing will pay 3,000 yuan, based on the reference data of the blockchain database 300, the processor 110 will calculate the average amount of the aforementioned claims and the reference amount obtained later to obtain the average amount. 2,500 yuan. Therefore, the processor 110 uses the average amount as the response to the claim, that is, the claimant finally obtains a claim amount of 2,500 yuan.

In summary, the claim review apparatus 100 of the present disclosure and the claim review method thereof provide an automated micro-insurance claim mechanism, and use the artificial intelligence algorithm to determine the type of claims that the claim request data conforms to, and The contents of the database to obtain the corresponding claim amount. Accordingly, the time course for the policyholder to apply for the claim can be shortened, and the claimant of the insurance company can focus on other disputed cases such as higher claims, settlements or litigation. In addition, through the records of the insurance database 120 and the blockchain database 300, it is possible to determine whether the claims are normal or abnormal, and to determine whether the claims are reasonable through historical claims data, thereby reducing the moral hazard of the claims.

The features of several embodiments are summarized above so that those skilled in the art can better understand the aspects of the present invention. Those skilled in the art will appreciate that the present invention can be readily utilized as a basis for designing or modifying other processes and structures to achieve the same objectives and/or achieve the same advantages of the embodiments described herein. It will be appreciated by those skilled in the art that such equivalent constructions are not departing from the spirit and scope of the present invention, and various changes, substitutions and alterations herein may be made without departing from the spirit and scope of the invention.

Claims (5)

A claim review apparatus includes: an insurance database for storing a historical claim data, wherein the historical claims data includes a claim type and a claim amount corresponding to one of the claim types; and a processor coupled to the insurance database The processor is configured to: receive a claim request; read the historical claim data of the insurance database to determine whether the claim request has the claim type; and if it is determined that the claim request has the claim type, Then the amount of the claim corresponding to the type of claim is obtained. The claim review device of claim 1, wherein the claim request includes a pathological image data, the processor is further configured to: read the historical claim data of the insurance database to perform a process on the pathological image data An artificial intelligence algorithm to determine whether the claim request has the claim type; when determining that the claim request has the claim type, the claim amount corresponding to the claim type is output, and the pathological image data is The claim amount corresponding to the output is stored in the insurance database; and when the claim request does not have the claim type, the note claiming one of the claim claims is a non-automatic claim case. The claim review device of claim 1, wherein the claim request includes a medical record text, the processor is further configured to: Reading the historical claim data of the insurance database to compare the medical text of the medical record with the historical claim data to determine whether the claim request has the claim type; and determining that the claim has a claim In the claim type, outputting the claim amount corresponding to the claim type, and storing the medical record text and the corresponding output of the claim amount in the insurance database; and determining that the claim request does not have the claim When type, note that one of the claim claims is a non-automatic claim case. The claims review device of claim 1, wherein the processor is communicatively coupled to a blockchain database, and the processor is further configured to: read the reference data of the blockchain database that meets the claim request To obtain a reference amount corresponding to one of the pathological materials; and calculate the amount of the claim and an average amount of the reference amount as a response to the claim. The claim review device of claim 1, wherein the processor is further configured to: when determining that the claim amount is less than a threshold, output the claim amount corresponding to the claim request; and when determining that the claim amount is greater than the threshold At the time, a claim case for a claims claim is noted as a non-automatic claim case.