Digitization system for previous insurance symptom judgment based on large model
By adopting a digital system based on large models in insurance companies, combining deep learning models and hospital-side data analysis, the inaccurate information caused by manual inquiries by insurance companies is solved, and the accurate judgment of policyholders' past problems is achieved, and disputes are reduced. Improved efficiency.
Patent Information
- Application Number
- CN202411018432.5
- 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
When determining whether the insured has previous symptoms, existing insurance companies mainly rely on manual inquiries, which leads to inaccurate information and leads to conflicts and disputes.
A digital system based on a large model is adopted, user information is input through the information input module, and the data processor integrates a deep learning model to establish a communication connection with the hospital side, analyze user case information, and determine whether the user's condition is a previous disease.
It realizes accurate judgment of the policyholder's past symptoms, reduces subsequent disputes, and improves judgment efficiency and accuracy.
Smart Images

Figure CN119006176A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of insurance pre-existing condition identification, and specifically to a digital system for insurance pre-existing condition determination 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] Pre-existing conditions refer to diseases or health abnormalities that the insured has had before taking out the insurance. If there is a pre-existing condition, the insured must inform the insurance company in detail when taking out the insurance. If there is intentional concealment or negligent omission, or false information that is sufficient to change or reduce the insurer's assessment of the risk, the insurer may terminate the contract.
[0005] At present, the judgment of whether the insured has a pre-existing disease mainly relies on the insurance company staff's questioning of the insured person. This way of questioning often contains a lot of inaccurate information, leading to subsequent conflicts and disputes. Summary of the invention
[0006] The purpose of the present invention is to provide a digital system for determining insurance pre-existing conditions based on a large model, so as to solve the problem raised in the above background technology that the current judgment on whether the insured has a pre-existing condition mainly relies on the insurance company staff's questioning of the insured person. This way of questioning often contains a lot of inaccurate information, leading to subsequent conflicts and disputes.
[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a digital system for determining insurance pre-existing conditions based on a large model, comprising:
[0008] An information input module, wherein the information input module is used to input user information;
[0009] A data processor, wherein the output end of the information input module is connected to the data processor, and the data processor is integrated with a deep learning model;
[0010] A display, the signal output terminal of the data processor is connected to the display, and the display is used to display the result of the data processor processing;
[0011] The user case acquisition unit, the hospital side and the user side, the data processor establishes a communication connection with the user case acquisition unit, the data processor outputs the input user information to the user case acquisition unit, the user case acquisition unit applies for the user case to the hospital side based on the user information, the hospital side sends an information reminder to the user side based on the application of the user case acquisition unit, the user side determines whether to output the user's case information based on the information reminder feedback, after the user's information is output, the user's case information is analyzed by an integrated deep learning model to determine the time when the user discovered the disease, and based on the time when the user discovered the disease, determine whether the user's disease is a pre-existing disease.
[0012] Preferably, the information input module includes at least one of a touch input screen, a mouse, and a keyboard.
[0013] Preferably, the information input module is a voice recognition input module.
[0014] Preferably, the deep learning model determines the time when the user's illness is discovered based on a convolutional neural network.
[0015] Preferably, it further comprises a communication module, wherein the communication module is connected to the data processor, and the data processor is connected to the user case acquisition unit via the communication module.
[0016] Preferably, the hospital end is a smart device with a communication platform, and the user end is an APP integrated on the user's smartphone.
[0017] Preferably, the communication module is a wireless communication module or a wired communication module.
[0018] Preferably, the case information includes the user's identity information, the time when the user's query results are displayed, the time when the user discovers symptoms, the user's medical history, personal history, and family history.
[0019] Preferably, the method for using the digital system for determining insurance pre-existing conditions based on the large model is as follows:
[0020] S1: Input patient information: This digital system has a pre-established network connection and has passed the hospital security certification. The staff inputs the patient's identity information, i.e. user information, based on the information input module;
[0021] S2: Sending a request to the hospital: The data processor receives the patient's identity information and sends a request to the hospital to obtain the patient's medical records based on the patient's identity information;
[0022] S3: The hospital asks the patient whether he agrees to the information output: The hospital sends the request to the user:
[0023] When the user disagrees with the output of the case information, the process returns to step S2;
[0024] When the user agrees to output the case information, proceed to the next step;
[0025] S4: Analysis of patient information: After the user agrees, the data processor analyzes the user's case information time and compares and determines the relationship between the user's disease diagnosis time and insurance enrollment time:
[0026] S5: Determine whether the patient's condition is a pre-existing disease: When the user's disease diagnosis time is earlier than the insurance enrollment time, the patient's condition is considered to be a pre-existing disease;
[0027] When the user's illness is diagnosed later than the time of insurance participation, the patient's condition is deemed not to be a pre-existing condition.
[0028] Compared with the prior art, the present invention has the following beneficial effects:
[0029] Based on big data, when the insured person (user, patient) participates in the insurance, a communication connection is established with the hospital's data, and the insured person's medical condition can be obtained from the hospital, thereby obtaining the insured person's health status before the insurance, and based on the diagnosis time of the patient's corresponding condition, it is determined whether the insured person's corresponding condition is a pre-existing condition.
[0030] This approach can promptly and accurately determine the situation of insured persons and reduce subsequent disputes. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 is a system logic block diagram of the present invention;
[0032] Figure 2 The present invention is used as a flow chart. DETAILED DESCRIPTION
[0033] 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.
[0034] 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.
[0035] Embodiment 1:
[0036] See also Figure 1-2 ,The present invention provides a technical solution: a digital system for determining insurance pre-existing conditions based on a large model, comprising: an information input module, a data processor, a display, a user case acquisition unit, a hospital end, and a user end;
[0037] The information input module is used to input user information, the output end of the information input module is connected to the data processor, the data processor has a deep learning model integrated therein, the signal output end of the data processor is connected to a display, the display is used to display the results of processing by the data processor, the data processor establishes a communication connection with a user case acquisition unit, the data processor outputs the input user information to the user case acquisition unit, the user case acquisition unit applies for the user case to the hospital based on the user information, the hospital sends an information reminder to the user based on the application of the user case acquisition unit, the user decides whether to output the user's case information based on the information reminder feedback, after the user's information is output, the integrated deep learning model analyzes the user's case information, determines the time when the user discovered the disease, and determines whether the user's disease is a pre-existing disease based on the time when the user discovered the disease.
[0038] Select multiple cases that have been evaluated as standards in the past as cases for deep learning model training. The judgment here is relatively easy, that is, obtain the time when the patient was first found to have the disease and the time when the patient participated in insurance, obtain these two time points, and compare the two time points. There are three situations:
[0039] 1. If the earliest time a patient was found to have the disease is earlier than the time when the patient joined the insurance, the patient's disease can be regarded as a pre-existing disease;
[0040] 2. If the time when the patient was first diagnosed with the disease and the time when the patient joined the insurance are in the same period, the patient's condition can be considered not to be a pre-existing disease;
[0041] 3. If the earliest time the patient was found to have the disease is later than the time the patient participated in insurance, it can be deemed that the patient’s condition is not a pre-existing condition.
[0042] The cases are screened to the cases of pre-existing medical conditions that have been handled by the insurance company in the past.
[0043] The specific performance evaluation method for the deep learning model is as follows: randomly simulate the input of the patient's insurance enrollment time and the time when the disease was discovered, and use the deep learning model to determine whether the patient's illness is a pre-existing condition. The number of evaluations is no less than 100,000 times, and the number of incorrect judgments by the deep learning model does not exceed 1, then the deep learning model is considered to have an accurate judgment.
[0044] The method for determining the time when the patient's condition was discovered is to establish a communication connection with the hospital's data, obtain the time when the patient discovered the condition based on the patient's medical records stored in the hospital.
[0045] Insurance company staff asks insured persons about the time when the illness was discovered. In order to protect their own interests, insured persons often conceal some real situations. This solution establishes a communication connection with the hospital's data and does not need to consult the insured persons. The data obtained in this way is more accurate and improves work efficiency.
[0046] Without the permission of the insured person, the insurance company cannot obtain the patient's medical records from the hospital. At the same time, the insurance company will not pay the insured amount to the patient without knowing the time when the patient discovered the illness. Regarding the confidentiality of the patient's medical records, the existing electronic information field has been sufficient to ensure this, so I will not elaborate on it here.
[0047] Pre-existing conditions refer to any illness or health abnormality that the insured has had before taking out the insurance.
[0048] Previous medical conditions include hypertension, diabetes, coronary heart disease and other diseases, and they are treated accordingly.
[0049] 1. Hypertension: Hypertension is generally caused by genetics or bad habits. If the patient's family has a history of hypertension, hypertension will carry the gene to the next generation, thus causing symptoms of hypertension. If the patient consumes too much salt or drinks too much alcohol for a long time, it will also cause blood pressure to rise.
[0050] 2. Diabetes: If patients consume high-calorie and high-sugar foods for a long time, they may experience high blood sugar and develop diabetes.
[0051] 3. Coronary heart disease: Coronary heart disease is generally caused by changes in the coronary veins and damage to the cells inside the blood vessels, which leads to symptoms of coronary heart disease.
[0052] In addition to the above, past medical history also included myocardial infarction.
[0053] Analysis of the above content: When a user applies for an insurance claim, the insurance company staff obtains the user's identity information (including name, date of birth, and ID card information). The insurance company staff confirms with the user in person or by phone that they will apply to the hospital for the user's medical record information. Based on the medical record information, the deep learning model obtains the time point of the user's illness diagnosis from the obtained medical record information. Based on the comparison between the time point and the insurance enrollment time, if the user's illness diagnosis time is earlier than the insurance enrollment time, the patient's condition is considered to be a pre-existing condition.
[0054] When the user's illness is diagnosed later than the time of insurance participation, the patient's condition is deemed not to be a pre-existing condition.
[0055] In the training process of deep learning models, data preprocessing is a very important step. First, the raw data needs to be cleaned and denoised to remove outliers and noise data to ensure the quality of the input data. Secondly, the data needs to be normalized to have the same scale and distribution to improve the convergence and generalization ability of the model. Thirdly, attention should be paid to data privacy and security; when processing sensitive data (such as personal identity information), measures need to be taken to protect data privacy, such as desensitization, using differential privacy technology, or generating synthetic data sets without revealing the details of the original data.
[0056] When performing data preprocessing, you can also use data enhancement methods to generate more samples by rotating, translating, scaling, and other operations on the original data, thereby increasing the diversity of training data and improving the robustness and generalization ability of the model.
[0057] Embodiment 2:
[0058] See also Figure 1-2 The present invention provides a technical solution based on the first embodiment: the information input module includes at least one of a touch input screen, a mouse, and a keyboard.
[0059] According to the use requirements and corresponding supporting equipment, the information input module includes at least one of a touch input screen, a mouse, and a keyboard, or a combination of at least two of the touch input screen, a mouse, and a keyboard.
[0060] Embodiment three:
[0061] See also Figure 1-2 , the present invention provides a technical solution based on embodiment 1: the information input module is a speech recognition input module.
[0062] Analysis of the above content: the information input module can also be a voice recognition input module. The voice recognition input module directly recognizes the input information by recognizing voice. The existing voice recognition input module can be used here.
[0063] Embodiment 4:
[0064] See also Figure 1-2 The present invention provides a technical solution based on Example 1: the deep learning model determines the time when the user discovers the disease based on a convolutional neural network.
[0065] Embodiment five:
[0066] See also Figure 1-2 The present invention provides a technical solution based on the first embodiment: further comprising a communication module, the communication module is connected to the data processor, and the data processor is connected to the user case acquisition unit through the communication module. The communication module is a wireless communication module or a wired communication module.
[0067] Embodiment six:
[0068] See also Figure 1-2 The present invention provides a technical solution based on the first embodiment: the hospital end is a smart device with a communication platform, and the user end is an APP integrated on the user's smart phone. The case information includes the user's identity information, the time when the user's query result is displayed, the time when the user discovered the symptoms, the user's medical history, personal history, and family history.
[0069] Embodiment seven:
[0070] See also Figure 1-2 The present invention provides a technical solution based on the first embodiment: the method for using the digital system for determining insurance pre-existing conditions based on a large model is as follows:
[0071] S1: Input patient information: This digital system has a pre-established network connection and has passed the hospital security certification. The staff inputs the patient's identity information, i.e. user information, based on the information input module;
[0072] S2: Sending a request to the hospital: The data processor receives the patient's identity information and sends a request to the hospital to obtain the patient's medical records based on the patient's identity information;
[0073] S3: The hospital asks the patient whether he agrees to the information output: The hospital sends the request to the user:
[0074] When the user disagrees with the output of the case information, the process returns to step S2;
[0075] When the user agrees to output the case information, proceed to the next step;
[0076] S4: Analysis of patient information: After the user agrees, the data processor analyzes the user's case information time and compares and determines the relationship between the user's disease diagnosis time and insurance enrollment time:
[0077] S5: Determine whether the patient's condition is a pre-existing disease: When the user's disease diagnosis time is earlier than the insurance enrollment time, the patient's condition is considered to be a pre-existing disease;
[0078] When the user's illness is diagnosed later than the time of insurance participation, the patient's condition is deemed not to be a pre-existing condition.
[0079] 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.
[0080] 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 insurance pre-existing conditions based on a large model, It is characterized in that include: An information input module, wherein the information input module is used to input user information; A data processor, wherein the output end of the information input module is connected to the data processor, and the data processor is integrated with a deep learning model; A display, the signal output terminal of the data processor is connected to the display, and the display is used to display the result of the data processor processing; The user case acquisition unit, the hospital side and the user side, the data processor establishes a communication connection with the user case acquisition unit, the data processor outputs the input user information to the user case acquisition unit, the user case acquisition unit applies for the user case to the hospital side based on the user information, the hospital side sends an information reminder to the user side based on the application of the user case acquisition unit, the user side determines whether to output the user's case information based on the information reminder feedback, after the user's information is output, the user's case information is analyzed by an integrated deep learning model to determine the time when the user discovered the disease, and based on the time when the user discovered the disease, determine whether the user's disease is a pre-existing disease.
2. A digital system for determining insurance pre-existing conditions based on a large model according to claim 1, Features: The information input module includes at least one of a touch input screen, a mouse, and a keyboard.
3. A digital system for determining insurance pre-existing conditions based on a large model according to claim 1, Features: The information input module is a voice recognition input module.
4. A digital system for determining insurance pre-existing conditions based on a large model according to claim 1, Features: The deep learning model determines the time when the user's condition is discovered based on a convolutional neural network.
5. A digital system for determining insurance pre-existing conditions based on a large model according to claim 1, Features: It also includes a communication module, which is connected to the data processor, and the data processor is connected to the user case acquisition unit through the communication module.
6. A digital system for determining insurance pre-existing conditions based on a large model according to claim 1, Features: The hospital end is a smart device with a communication platform, and the user end is an APP integrated on the user's smartphone.
7. A digital system for determining insurance pre-existing conditions based on a large model according to claim 5, Features: The communication module is a wireless communication module or a wired communication module.
8. A digital system for determining insurance pre-existing conditions based on a large model according to claim 1, Features: The case information includes the user's identity information, the time when the user's query results are displayed, the time when the user discovered symptoms, the user's medical history, personal history, and family history.
9. A digital system for determining insurance pre-existing conditions based on a large model according to claim 1, Features: The specific method of using the digital system for determining insurance pre-existing conditions based on the big model is as follows: S1: Input patient information: This digital system has a pre-established network connection and has passed the hospital security certification. The staff inputs the patient's identity information, i.e. user information, based on the information input module; S2: Sending a request to the hospital: The data processor receives the patient's identity information and sends a request to the hospital to obtain the patient's medical records based on the patient's identity information; S3: The hospital asks the patient whether he agrees to the information output: The hospital sends the request to the user: When the user disagrees with the output of the case information, the process returns to step S2; When the user agrees to output the case information, proceed to the next step; S4: Analysis of patient information: After the user agrees, the data processor analyzes the user's case information time and compares and determines the relationship between the user's disease diagnosis time and insurance enrollment time: S5: Determine whether the patient's condition is a pre-existing disease: When the user's disease diagnosis time is earlier than the insurance enrollment time, the patient's condition is considered to be a pre-existing disease; When the user's illness is diagnosed later than the time of insurance participation, the patient's condition is deemed not to be a pre-existing condition.
