Large-model-based insurance overcompensation judgment digital system

By using a digital system based on large models during the insurance claims process, deep learning models analyze insurance information and patient situations, the problem of excessive insurance compensation is solved, the accuracy and rationality of the compensation amount is improved, and the insurance company's loss.

CN119006175APending Publication Date: 2024-11-22YINGTAI (NINGBO) INFORMATION TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411018428.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

During the insurance claim settlement process, due to false information from insured personnel and incomplete judgment of insurance staff, excessive insurance claims occur frequently, resulting in avoidable losses from the insurance company.

Method used

Using a digital system based on a large model, the patient's identity and patient situation are input through the information input module. The data processor has built-in deep learning model to analyze the insurance information and patient situation, determine whether there is an overpayment, and based on the patient's situation Adjust the amount of compensation to ensure the rationality and accuracy of the amount of compensation.

Benefits of technology

It improves the efficiency of insurance claims, reduces the situation where the compensation amount is large, ensures the rationality and accuracy of the compensation amount, avoids errors in human judgment, and provides a standard-based compensation amount decision.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119006175A_ABST
    Figure CN119006175A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of insurance claim settlement, and particularly relates to a digital system for insurance overcompensation judgment based on a large model, which comprises an information input module, a data processor and a display, the signal output end of the information input module is connected with the data processor, patient identity information input by the information input module enters the data processor, and the data processor retrieves the database based on the patient identity information. In actual use, when an insured person applies for insurance claim settlement or the amount of insurance claim payment is preliminarily determined, the system can be adopted to participate in insurance claim settlement, the efficiency is high, the situation that the amount of claim payment is large in difference is not prone to occurring in insurance claim settlement through the logic relation of multi-layer judgment, and the insurance claim settlement efficiency is improved through the multiple screening adjustment mode. The final compensation amount can be adjusted to a proper interval, and the obtained compensation amount is reasonable and accurate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of insurance claims, and in particular to a digital system for determining insurance excess compensation based on a large model. Background Art

[0002] Insurance refers to the commercial insurance behavior in which the insured pays premiums to the insurer according to the terms of the contract, and the insurer assumes the liability for paying insurance compensation for property losses caused by accidents that may occur as stipulated in the contract, or when the insured dies, becomes disabled, becomes ill, or reaches the age, term, etc. stipulated in the contract.

[0003] Insurance companies collect premiums and invest the capital from the premiums in assets such as bonds, stocks, and loans, and use the income from these assets to pay the insurance compensation determined by the policy. Through the above business, insurance companies can obtain high returns on investment and provide appropriate insurance services to customers at lower premiums, thereby making profits.

[0004] Insurance claims settlement refers to the act of an insurance company fulfilling its obligation to compensate or pay in accordance with the provisions of the contract when an insurance accident occurs to the subject matter of insurance, causing damage to the insured's property or personal life, or when other insurance accidents stipulated in the policy occur and the insurance money needs to be paid. It is a work that directly reflects the insurance function and the fulfillment of insurance responsibilities.

[0005] Simply put, insurance claims settlement is the act of the insurer handling the claim request made by the insured after a risk accident occurs to the insurance subject. In insurance operations, insurance claims settlement is the specific embodiment of the insurance compensation function.

[0006] In the actual insurance claims process, there are cases of over-payment. The reasons include false information reported by the insured person (patient), misjudgment by the insurance staff, or incomplete grasp of the insured person's information by the insurance staff, which leads to over-payment, thus causing avoidable losses to the insurance company. Summary of the invention

[0007] The purpose of the present invention is to provide a digital system for determining insurance excess compensation based on a large model, so as to solve the problem of insurance excess compensation in the actual insurance claims process proposed in the above-mentioned background technology, the reasons of which include false information reported by the insured person (patient) and misjudgment of the insurance staff or the insurance staff's incomplete grasp of the insured person's information, resulting in insurance excess compensation, which causes the insurance company to suffer avoidable losses.

[0008] To achieve the above object, the present invention provides the following technical solution: a digital system for determining insurance excess loss based on a large model, comprising:

[0009] An information input module, wherein the information input module is used to input the patient's identity information and condition;

[0010] A data processor, wherein the signal output end of the information input module is connected to the data processor, the patient identity information input by the information input module enters the data processor, the data processor searches the database based on the patient identity information, and retrieves the patient's insurance information. The data processor has a built-in deep learning model, and the deep learning model analyzes the patient's insurance information and the patient's condition. The data processor determines whether the amount of compensation actually approved for the patient is an excess compensation amount;

[0011] When the actual amount of compensation approved for the patient is an excess amount, the deep learning model will adjust the reasonable compensation amount based on the patient's condition;

[0012] When the actual amount of compensation approved for the patient is not an excess compensation amount, the deep learning model will proceed to determine whether it is an excess compensation amount next time;

[0013] A display, wherein the signal output end of the data processor is connected to the display, and the display is used to display the recognition results of the deep learning model.

[0014] Preferably, the information input module includes a touch input screen and a voice input recognition module.

[0015] Preferably, the identity information includes the patient's name, ID number, and date of birth.

[0016] Preferably, the patient's insurance information includes the type of insurance, the time of insurance, the address of insurance, the policyholder, the insured, the insurance compensation amount and the insurance compensation conditions.

[0017] Preferably, the deep learning model classifies the patient's condition into different levels, and divides the patient's condition into mild, moderate and severe conditions based on the different levels.

[0018] Preferably, when the deep learning model determines that the patient's condition is critically ill, the deep learning model continues to determine whether the patient's condition is a pre-existing disease.

[0019] Preferably, the workflow of the digital system for determining excess loss of insurance based on a large model is as follows:

[0020] S1: Retrieve patient data based on input information: When a patient applies for compensation or the approved compensation amount for the patient has been preliminarily determined, the patient's information is entered into the system through the information input module;

[0021] S2: Obtaining insurance compensation amount information based on retrieved data: The data processor searches for the patient's insurance information based on the input patient information;

[0022] S3: Obtain the actual amount of compensation approved for the patient: and compare the insurance compensation amount of the patient with the approved compensation amount:

[0023] When the insurance reimbursement amount of the patient is lower than the approved reimbursement amount, the approved reimbursement amount does not meet the insurance requirements, and the patient's reimbursement amount will be re-determined;

[0024] When the insurance reimbursement amount of the patient is higher than the approved reimbursement amount, the approved reimbursement amount is preliminarily in line with the insurance and proceeds to the next step;

[0025] S4: Further judgment based on the deep learning model: The deep learning model further analyzes the patient's condition to determine whether the patient's condition is severe:

[0026] When the patient's condition is not serious, proceed to the next step to determine the compensation amount based on the patient's actual condition;

[0027] When the patient's condition is serious, the patient's condition is judged to be a pre-existing condition. If the patient's condition is judged not to be a pre-existing condition, the compensation amount is determined according to the actual condition of the serious condition; if the patient's condition is judged to be a pre-existing condition, proceed to the next step to determine the compensation amount according to the actual condition of the patient;

[0028] S5: Adjustment of the compensation amount: Re-determine the compensation amount based on the actual condition of the patient.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] In actual use, insured persons can use this system to participate in insurance claims when applying for insurance claims or when the amount of insurance compensation is preliminarily determined. It is highly efficient and, through the logical relationship of multi-layer judgment, makes it less likely that large differences in compensation amounts will occur in insurance claims.

[0031] Through multiple screening and adjustment methods, the final compensation amount can be adjusted to an appropriate range, and the resulting compensation amount is more reasonable and accurate.

[0032] Compared with the prior art of manually judging the final compensation amount, this solution judges and determines the compensation amount based on a specific standard, which has reasons and basis, and avoids inaccurate judgments or large judgment errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a system logic block diagram of the present invention;

[0034] Figure 2 It is the work flow chart of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] In the description of the present invention, it is necessary to understand that the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0037] Embodiment 1:

[0038] See also Figure 1-2 The present invention provides a technical solution: a digital system for determining insurance excess loss based on a large model, comprising:

[0039] An information input module, wherein the information input module is used to input the patient's identity information and condition;

[0040] A data processor, wherein the signal output end of the information input module is connected to the data processor, the patient identity information input by the information input module enters the data processor, the data processor searches the database based on the patient identity information, and retrieves the patient's insurance information. The data processor has a built-in deep learning model, and the deep learning model analyzes the patient's insurance information and the patient's condition. The data processor determines whether the amount of compensation actually approved for the patient is an excess compensation amount;

[0041] Multiple cases that have passed standard assessment in the past are selected as cases for deep learning model training, and the selected cases correspond to different compensation standards, with no less than 100 cases for each compensation standard, that is, no less than 100 cases for minor illness compensation, no less than 100 cases for moderate illness compensation, and no less than 100 cases for severe illness compensation. The above cases are brought into the deep learning model for training.

[0042] There are specific medical criteria for determining mild, moderate and severe illnesses, such as the first, second and third degree disability in medicine, which will not be elaborated here. The compensation amount will be adjusted based on the criteria for determining mild, moderate and severe illnesses, combined with treatment costs and recovery time.

[0043] When the actual amount of compensation approved for the patient is an excess amount, the deep learning model will adjust the reasonable compensation amount based on the patient's condition;

[0044] When the actual amount of compensation approved for the patient is not an excess compensation amount, the deep learning model will proceed to determine whether it is an excess compensation amount next time;

[0045] That is, the amount of compensation received by the patient should not be greater than the maximum amount of compensation for the insured content. For example, if a patient participates in an insurance policy, and the maximum compensation amount for a disease under this insurance policy is n yuan, then after the patient suffers from this disease, the amount of compensation received by the patient shall not exceed n yuan.

[0046] When a patient suffers from the disease and applies for insurance compensation, the insurance company will first manually determine that the compensation amount received by the patient should not be greater than n yuan. Then, the deep learning model of this solution will compare the compensation amount with the patient's condition to determine whether the compensation amount is accurate. When there is a large gap between the manual judgment and the judgment of the deep learning model, subsequent assessment is required, such as further assessment by experienced staff within the insurance company.

[0047] A display, wherein the signal output end of the data processor is connected to the display, and the display is used to display the recognition results of the deep learning model.

[0048] Analysis of the above content: The workflow of the digital system for insurance excess compensation determination based on the big model is as follows:

[0049] S1: Retrieve patient data based on input information: When a patient applies for compensation or the approved compensation amount for the patient has been preliminarily determined, the patient's information is entered into the system through the information input module;

[0050] The system here is integrated on a computer, or the conclusions drawn from the deep learning model are uploaded to a host computer. The touch input screen and voice input recognition module are both existing technologies.

[0051] S2: Obtaining insurance compensation amount information based on retrieved data: The data processor searches for the patient's insurance information based on the input patient information;

[0052] S3: Obtain the actual amount of compensation approved for the patient: and compare the insurance compensation amount of the patient with the approved compensation amount:

[0053] When the insurance reimbursement amount of the patient is lower than the approved reimbursement amount, the approved reimbursement amount does not meet the insurance requirements, and the patient's reimbursement amount will be re-determined;

[0054] When the insurance reimbursement amount of the patient is higher than the approved reimbursement amount, the approved reimbursement amount is preliminarily in line with the insurance and proceeds to the next step;

[0055] S4: Further judgment based on the deep learning model: The deep learning model further analyzes the patient's condition to determine whether the patient's condition is severe:

[0056] When the patient's condition is not serious, proceed to the next step to determine the compensation amount based on the patient's actual condition;

[0057] When the patient's condition is serious, the patient's condition is judged to be a pre-existing condition. If the patient's condition is judged not to be a pre-existing condition, the compensation amount is determined according to the actual condition of the serious condition; if the patient's condition is judged to be a pre-existing condition, proceed to the next step to determine the compensation amount according to the actual condition of the patient;

[0058] S5: Adjustment of the compensation amount: Re-determine the compensation amount based on the actual condition of the patient.

[0059] Embodiment 2:

[0060] See also Figure 1-2 The present invention provides a technical solution based on the first embodiment: the information input module includes a touch input screen and a voice input recognition module.

[0061] Analysis of the above content: With the advancement of science and technology, touch input screens and voice input recognition modules have many advantages. Touch input screens and voice input recognition modules can be more convenient to use through touch input and voice input.

[0062] Embodiment three:

[0063] See also Figure 1-2 The present invention provides a technical solution based on Example 1: the identity information includes the patient's name, ID number, and date of birth, and the patient's insurance information includes the type of insurance, the time of insurance, the address of insurance, the insured, the insured, the insurance compensation amount, and the insurance compensation conditions.

[0064] Analysis of the above content: By understanding the patient's identity information and insurance information, we can better understand the patient's insurance information.

[0065] Embodiment 4:

[0066] See also Figure 1-2The present invention provides a technical solution based on Example 1: the deep learning model classifies the patient's condition into different levels, and classifies the patient's condition into mild, moderate and severe conditions based on the different levels. When the deep learning model determines that the patient's condition is severe, the deep learning model continues to determine whether the patient has a preexisting disease.

[0067] Analysis of the above content: First, the range of the patient's compensation amount is preliminarily limited, and the patient's condition is divided into mild, moderate and severe conditions, so as to preliminarily determine the compensation amount.

[0068] Then we check whether the patient has a pre-existing condition, which can further narrow the compensation amount and determine the exact range of the compensation amount.

[0069] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention; therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is limited by the attached claims rather than the above description. Therefore, it is intended to include all changes within the meaning and scope of the equivalent elements of the claims in the present invention, and any figure marks in the claims should not be regarded as limiting the claims involved.

[0070] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A digital system for determining excess loss of insurance based on a large model, characterized in that: include: An information input module, wherein the information input module is used to input the patient's identity information and condition; A data processor, wherein the signal output end of the information input module is connected to the data processor, the patient identity information input by the information input module enters the data processor, the data processor searches the database based on the patient identity information, and retrieves the patient's insurance information. The data processor has a built-in deep learning model, and the deep learning model analyzes the patient's insurance information and the patient's condition. The data processor determines whether the amount of compensation actually approved for the patient is an excess compensation amount; When the actual amount of compensation approved for the patient is an excess amount, the deep learning model will adjust the reasonable compensation amount based on the patient's condition; When the actual amount of compensation approved for the patient is not an excess compensation amount, the deep learning model will proceed to determine whether it is an excess compensation amount next time; A display, wherein the signal output end of the data processor is connected to the display, and the display is used to display the recognition results of the deep learning model.

2. A digital system for determining insurance excess loss based on a large model according to claim 1, characterized in that: The information input module includes a touch input screen and a voice input recognition module.

3. A digital system for determining insurance excess loss based on a large model according to claim 1, characterized in that: The identity information includes the patient's name, ID number, and date of birth.

4. A digital system for determining insurance excess loss based on a large model according to claim 1, characterized in that: The patient's insurance information includes the type of insurance, the time of insurance, the address of insurance, the policyholder, the insured, the insurance compensation amount and the insurance compensation conditions.

5. The digital system for determining insurance excess loss based on a large model according to claim 1, characterized in that: The deep learning model classifies the patient's condition into different levels, and divides the patient's condition into mild, moderate and severe conditions based on the different levels.

6. A digital system for determining excess loss of insurance based on a large model according to claim 5, characterized in that: When the deep learning model determines that the patient's illness is serious, the deep learning model continues to determine whether the patient's illness is a pre-existing disease.

7. The digital system for determining excess loss of insurance based on a large model according to claim 1, characterized in that: The workflow of the digital system for insurance excess loss determination based on the big model is as follows: S1: Retrieve patient data based on input information: When a patient applies for compensation or the approved compensation amount for the patient has been preliminarily determined, the patient's information is entered into the system through the information input module; S2: Obtaining insurance compensation amount information based on retrieved data: The data processor searches for the patient's insurance information based on the input patient information; S3: Obtain the actual amount of compensation approved for the patient: and compare the insurance compensation amount of the patient with the approved compensation amount: When the insurance reimbursement amount of the patient is lower than the approved reimbursement amount, the approved reimbursement amount does not meet the insurance requirements, and the patient's reimbursement amount will be re-determined; When the insurance reimbursement amount of the patient is higher than the approved reimbursement amount, the approved reimbursement amount is preliminarily in line with the insurance and proceeds to the next step; S4: Further judgment based on the deep learning model: The deep learning model further analyzes the patient's condition to determine whether the patient's condition is severe: When the patient's condition is not serious, proceed to the next step to determine the compensation amount based on the patient's actual condition; When the patient's condition is serious, the patient's condition is judged to be a pre-existing condition. If the patient's condition is judged not to be a pre-existing condition, the compensation amount is determined according to the actual condition of the serious condition; if the patient's condition is judged to be a pre-existing condition, proceed to the next step to determine the compensation amount according to the actual condition of the patient; S5: Adjustment of the compensation amount: Re-determine the compensation amount based on the actual condition of the patient.