JP6932570B2 - Insurance design support system and insurance design support method - Google Patents

Description

The present invention relates to a product design technique in insurance product development.

Conventionally, the payment terms and amounts of medical insurance have been calculated based on official statistical data such as life tables and the occurrence status of past insurance contracts (referred to as experience data). Since empirical data is limited to cases of products launched in the past, it is difficult to correctly calculate future risks when developing insurance products with inexperienced new payment terms. For example, Japanese Patent Application Laid-Open No. 8-335235 (Patent Document 1) discloses a method of simulating future income and expenditure based on a profit rate and an occurrence rate preset by a user, but mentions insurance design. Not.

Japanese Unexamined Patent Publication No. 8-335235

In the income and expenditure analysis based on the information set by the user as in the method described in Patent Document 1, it is difficult to perform an accurate analysis in medical insurance affected by complicated background factors.

In addition, analysis based on the experience data of insurance companies cannot accurately estimate the degree of impact when inexperienced payment terms are set. If the insurance amount can be estimated based on medical consultation information such as medical receipts, the effect of setting an inexperienced payment reason can be analyzed. Furthermore, since it is possible to calculate the medical expenses actually borne by the policyholder at the same time, it is possible to search for the conditions of insurance claims products with high utility value for the policyholder. Therefore, the present invention estimates the insurance money that can be received if the patient has medical insurance and calculates the medical expenses to be paid to the medical institution from the past medical consultation information represented by the receipt, and optimally designs the medical insurance. The purpose is to provide a system to support.

In order to solve the above problems, the present invention is an insurance design support system including a processor and a storage device connected to the processor, wherein the storage device provides information on actual medical fees for a plurality of persons. The medical receipt information including the medical receipt information, the disease causal structure information indicating the relationship between the diseases, and the payment conditions of the insurance money designed in the insurance are retained, and the processor obtains the disease from the disease extracted from the medical receipt information. Based on the causal structure information, the causal disease identification procedure for identifying the causative disease and the medical treatment performed for the extracted disease when the identified causative disease corresponds to the payment conditions are described from the receipt information. Based on the insurance claim estimation procedure for estimating the insurance amount to be paid to the plurality of persons based on the extracted medical practice and the payment conditions corresponding to the causative disease, and the receipt information. It is characterized in that the medical expenses of the plurality of persons are calculated, and the insurance design evaluation procedure for evaluating the insurance design based on the calculated medical expenses and the estimated insurance amount is executed.

According to one embodiment of the present invention, by estimating the insurance amount by simulation based on medical consultation information such as medical receipts, it is possible to analyze the effect of setting a payment reason that is not included in the empirical data. As a result, accurate risk assessment can be automatically executed in the payment condition design of medical insurance, and operations can be refined and streamlined. Issues, configurations and effects other than those mentioned above will be clarified by the description of the following examples.

It is a block diagram which shows an example of the structure of the insurance design support system of Example 1 of this invention. It is explanatory drawing which shows an example of the receipt basic information managed by the receipt information management part of Example 1 of this invention. It is explanatory drawing which shows an example of the injury and illness name information managed by the receipt information management part of Example 1 of this invention. It is explanatory drawing which shows an example of the medical practice information which is managed by the receipt information management part of Example 1 of this invention. It is explanatory drawing which shows an example of the medical examination information managed by the medical examination information management part of Example 1 of this invention. It is explanatory drawing which shows an example of the health insurance subscriber information managed by the health insurance subscriber information management department of Example 1 of this invention. It is explanatory drawing which shows an example of the disease causal structure information managed by the disease causal structure management part of Example 1 of this invention. It is explanatory drawing which shows an example of the hospitalization benefit condition information managed by the payment condition management department of Example 1 of this invention. It is explanatory drawing which shows an example of the surgical benefit condition information managed by the payment condition management department of Example 1 of this invention. It is explanatory drawing which shows an example of the subscription condition information managed by the subscription condition management part of Example 1 of this invention. It is explanatory drawing which shows an example of the causal disease record information managed by the receipt information management part of Example 1 of this invention. FIG. 5 is a flow chart showing a procedure for constructing a disease causal structure by the insurance design support system according to the first embodiment of the present invention. FIG. 5 is a flow chart showing a procedure for identifying a causative disease from receipt information in the insurance design support system according to the first embodiment of the present invention. FIG. 5 is a flow chart showing a procedure in which the insurance design support system of the first embodiment of the present invention determines whether or not the disease is a payment target disease based on the causative disease identified from the medical receipt and calculates the benefit. It is a flow chart which showed the procedure which the insurance design support system of Example 1 of this invention generates information corresponding to a notification from a medical examination and a medical receipt. The insurance design support system of Example 1 of the present invention shows a procedure for calculating an insurance claim from a medical receipt according to a predetermined payment condition and optimizing the payment condition for eliminating the imbalance between the benefit amount and the medical expense. It is a flow chart. It is explanatory drawing which showed an example of the disease causal structure construction screen output by the insurance design support system of Example 1 of this invention. It is explanatory drawing which showed an example of the insurance money simulation screen output by the insurance design support system of Example 1 of this invention. It is explanatory drawing which showed an example of the insurance design simulation screen output by the insurance design support system of Example 1 of this invention. It is a block diagram which shows an example of the structure of the insurance design support system of Example 2 of this invention. It is explanatory drawing which shows an example of the subscriber information by product managed by the subscriber information management department by product of Example 2 of this invention. The procedure for the insurance design support system 101 of the second embodiment of the present invention to extract a group having the same statistical characteristics as the policyholders who are enrolled in the actual insurance product from the data of the receipt and the medical examination result. It is a flow diagram shown. It is explanatory drawing which showed an example of the subscriber group selection screen which is output at the time of the process of selecting a subscriber group by the insurance design support system of Example 2 of this invention.

Hereinafter, as Example 1 of the present invention, a method of executing from estimation of insurance amount to design of insurance product using a medical receipt (statement of medical fee) will be described with reference to the drawings.

FIG. 1 is a block diagram showing an example of the configuration of the insurance design support system 101 according to the first embodiment of the present invention.

The insurance design support system 101 is a computer system, and includes, for example, an input unit 102 such as a keyboard and a mouse, an output unit 103 representing a display, a CPU (Central Processing Unit) 104, a memory 105, and a storage medium 106. The insurance design support system 101 includes a causal disease identification unit 111, an insurance money determination unit 112, an insurance design evaluation unit 113, a notification information generation unit 114, and a subscription condition determination unit 115. Each unit of the cause disease identification unit 111 to the subscription condition determination unit 115 is realized by the CPU 104 executing the program stored in the storage medium 106. When these programs are executed by the CPU 104, at least some of them may be copied to memory 105 as needed. In the following description, the processing executed by each of the above parts is actually executed by the CPU 104 according to the instructions described in the above program.

A database 107 is connected to the insurance design support system 101. The database 107 includes a receipt information management unit 120, a medical examination information management unit 121, a health insurance subscriber information management unit 122, a disease causal structure management unit 123, a payment condition management unit 124, and a subscription condition management unit 125. The database 107 may be stored, for example, in a storage system connected to the insurance design support system 101 via a network, or may be stored in the insurance design support system 101 (for example, by being stored in the storage medium 106). May be good. When the database 107 is stored in a system external to the insurance design support system 101, at least a part of its contents may be copied to the storage medium 106 or the memory 105 as needed. Further, the entire system including the computer having the input unit 102, the output unit 103, the CPU 104, the memory 105 and the storage medium 106, and the database 107 may be referred to as an insurance design support system.

FIG. 2 is an explanatory diagram showing an example of the basic receipt information 200 managed by the receipt information management unit 120 of the first embodiment of the present invention.

The basic receipt information 200 is basic information about each receipt, and includes a health insurance member ID 201 that identifies a member of health insurance (health insurance), a search number 202 for identifying the receipt, and the month in which the receipt was issued. The date of medical treatment shown 203, the total score 204 indicating the information on medical expenses written on the receipt, the receipt type 205 indicating information such as whether the receipt is inpatient or outpatient, and the number of days required for medical treatment. Includes 206 consultation days. This information has the effect of being able to aggregate and analyze each receipt.

FIG. 3 is an explanatory diagram showing an example of injury / illness name information 300 managed by the receipt information management unit 120 of the first embodiment of the present invention.

The injury / illness name information 300 is information about the injury / illness extracted from each receipt, the search number 202 for identifying the receipt, the injury / illness name 302 indicating the injury / illness to be treated, and the injury / illness name code 303 corresponding to the injury / illness name. , And the main injury / illness flag 304 given to the disease that has invested the most medical resources among the plurality of diseases. For example, when one patient receives medical treatment for a plurality of illnesses in one month, a plurality of sets of the injury / illness name 302, the injury / illness name code 303, and the main injury / illness flag 304 are associated with the same search number 202. This information has the effect of making it possible to analyze by injury or illness.

FIG. 4 is an explanatory diagram showing an example of medical practice information 400 managed by the receipt information management unit 120 of the first embodiment of the present invention.

The medical treatment information 400 is information on the medical treatment performed on the patient in the month corresponding to each receipt, which is extracted from each receipt, and is a search number 202 for identifying the receipt, for the patient. Medical practice name 402 indicating the medical practice performed, medical practice code 403 corresponding to the medical practice, medical practice score 404 determined for each medical practice, daily information 405 to 31 indicating the date when the medical practice was performed Includes day information 408. The daily information 405 to 31st information 408 indicating the day when the medical treatment was performed indicates whether or not the medical treatment indicated by the medical treatment name 402 was performed on each day from the 1st to the 31st of the month. This is information indicating. FIG. 4 shows 1st information 405, 2nd day information 406, 3rd day information 407, and 31st day information 408 as examples, but actually includes information on the 4th day to 30th day. This information has the effect of making it possible to analyze by medical practice.

The receipt information management unit 120 may collectively manage the receipt basic information 200, the injury / illness name information 300, and the medical practice information 400 shown in FIGS. 2 to 4 as the receipt information.

FIG. 5 is an explanatory diagram showing an example of the medical examination information 500 managed by the medical examination information management unit 121 of the first embodiment of the present invention.

The medical examination information 500 is information on the result of the medical examination (medical examination) received by the health insurance member, and is the health insurance member ID 201, the medical examination examination year 502 indicating the year when the medical examination was received, and the BMI (Body Mass Index). 503, systolic blood pressure 504, triglyceride 505, fasting blood glucose 506, interview result 507 and the like are included. The interview result 507 may include, for example, information indicating whether or not there is a drinking habit, whether or not there is an exercise habit, and the like. This information has the effect of making it possible to select a simulation target group according to the health condition.

FIG. 6 is an explanatory diagram showing an example of the health insurance subscriber information 600 managed by the health insurance subscriber information management unit 122 of the first embodiment of the present invention.

The health insurance member information 600 is information on the attributes of each health insurance member, and indicates the health insurance member ID 201, whether each health insurance member is the insured person or a dependent, and if the person is a dependent, the relationship with the insured person. Relationship category 602, gender 603, date of birth 604, industry category 605 indicating the type of business at work, occupation 606, date of joining 607 indicating the date of joining the health insurance, and information on the date of withdrawal from the health insurance. Includes the indicated withdrawal date 608. This information has the effect of enabling analysis according to relationship, age, gender, industry, traceable years, and the like.

FIG. 7 is an explanatory diagram showing an example of the disease causal structure information 700 managed by the disease causal structure management unit 123 of the first embodiment of the present invention.

The disease causal structure information 700 includes a disease-related ID 701 that identifies related information between diseases, a causal point injury or illness 702 that indicates an injury or illness that is the origin of the disease causal structure, a causal terminal injury or illness 703 that terminates with respect to the causal point injury or illness 702, and medicine. The medical relevance degree 704, which indicates the degree of relevance between diseases calculated based on the actual knowledge, the actual condition relevance degree 705, which indicates the relevance between diseases calculated from the data, and the medical relevance degree 704 and the actual condition relevance degree 705 are fused. Includes the disease-related degree 706 calculated in This information has the effect of enabling analysis based on the association of diseases based on medical knowledge and actual conditions.

FIG. 8 is an explanatory diagram showing an example of hospitalization benefit condition information 800 managed by the payment condition management unit 124 of the first embodiment of the present invention.

The hospitalization benefit condition information 800 specifies the hospitalization benefit target condition ID 801 for specifying the target conditions for the hospitalization benefit (that is, payment of insurance money for hospitalization), the payment target injury / illness 802 indicating the payment target injury / illness, and the target insurance product. Includes insurance product ID 803. This information has the effect of making it possible to set the target disease for each insurance product.

FIG. 9 is an explanatory diagram showing an example of the surgical benefit condition information 900 managed by the payment condition management unit 124 of the first embodiment of the present invention.

The surgical benefit condition information 900 specifies the surgical benefit target condition ID 901 that specifies the target condition of the surgical benefit (that is, the payment of insurance money for the surgery), the payable medical practice 902 that indicates the surgical procedure to be paid, and the target insurance product. Includes insurance product ID 803 and benefit multiplier setting 903, which indicates the multiplier of benefits for the subject treatment. This information has the effect of making it possible to set the target surgical benefit conditions for each insurance product.

FIG. 10 is an explanatory diagram showing an example of subscription condition information 1000 managed by the subscription condition management unit 125 of the first embodiment of the present invention.

The enrollment condition information 1000 manages the enrollment condition ID 1001 that specifies the enrollment condition, the age condition 1002 that indicates the age enrollment condition, the gender condition 1003 that indicates the gender enrollment condition, and the health condition condition 1004 that indicates the health condition enrollment condition. doing. This information has the effect of making it possible to create a group of subscribers that take into account age, gender, and health status for each insurance product.

FIG. 11 is an explanatory diagram showing an example of the causative disease record information 1100 managed by the receipt information management unit 120 of the first embodiment of the present invention.

The receipt information management unit 120 identifies the disease considered to be the cause of the injury / illness name according to the injury / illness name recorded in each receipt based on the disease causal structure, and manages it as the causal disease 1101. The search number 202 of the causative disease record information 1100 is information that identifies each receipt, and the causative disease 1101 is a disease that is identified as the cause of the injury or illness recorded in each receipt. This information has the effect of making it possible to determine whether or not the insurance money will be paid to the patient corresponding to each receipt.

Next, the procedure for constructing the causal structure of the disease will be described with reference to the figures.

FIG. 12 is a flow chart showing a procedure in which the insurance design support system 101 of the first embodiment of the present invention constructs a disease-causal structure.

Here, the disease-related information based on the medical knowledge managed by the disease-causal structure management unit 123 is fused with the related information calculated based on the actual data such as medical receipts. First, the causal disease identification unit 111 starts the procedure for constructing the disease causal structure in the start step, and then sets the conditions for constructing the disease causal structure in the construction condition setting step 1202. Specifically, the causal disease identification unit 111 has, as a method of fusing the degree of relevance based on medical knowledge and the degree of relevance based on data, for example, a method of calculating the sum of the two, a method of calculating the product of the two, or a method of calculating the product of the two. Specify any other calculation method.

Next, the causative disease identification unit 111 reads the receipt information from the receipt information management unit 120 in the receipt information reading step 1203. Next, the causative disease identification unit 111 extracts the receipt to be analyzed in the analysis target receipt extraction step 1204 from the receipt information. For example, when targeting an inpatient receipt, the causative disease identification unit 111 refers to the receipt type 205 and extracts a receipt (that is, an inpatient receipt) whose value is a value indicating hospitalization.

Next, the causal disease identification unit 111 constructs a causal structure for the occurrence of injury or illness in the disease causal structure construction step 1205. Specifically, the causal disease identification unit 111 refers to the information of the medical treatment date 203 and the injury / illness name 302 of the hospitalization receipt, and based on the disease and its occurrence order, the causal effect shown in the disease causal structure information 700 of FIG. The origin injury and illness 702 and the causal injury and illness 703 are extracted, and the degree of relevance thereof is determined.

For example, in a patient, if lung cancer is mentioned in the name of the injury or illness of the first hospitalization receipt, the causal origin injury or illness 702 becomes lung cancer, and if the injury or illness name of the receipt issued the following month is described as pneumonia, then the cause or effect. The origin injury 702 is lung cancer and the causal termination injury 703 is pneumonia. The causative disease identification unit 111 executes such an extraction for each patient included in the target population, and calculates the actual degree of association between lung cancer and pneumonia 705.

'When, P' the actual relevance 705 P, for example, be calculated hospitalization generation toll of lung cancer N _A, after lung cancer the number of patients that hospitalized with pneumonia occurs as N _AB according to Equation 1 below can.

However, even for patients hospitalized for pneumonia after lung cancer, the length of the period from the occurrence of lung cancer hospitalization to the occurrence of pneumonia hospitalization does not meet the prescribed conditions (for example, from the prescribed period). long) for patients, may not be included that number to N _AB. In this way, in each patient, the degree of relevance indicating the strength of the causal relationship between the two is calculated based on the relationship between the time when the medical treatment for the two diseases was performed (that is, the context and the time distance between the two). NS.

The causative disease identification unit 111 carries out these treatments for all combinations of diseases and constructs a disease causal structure based on the data. Next, in the medical causal structure fusion step 1206, the causal disease identification unit 111 is based on medical knowledge regarding the causal structure and the actual condition relevance of the disease 705 based on the data obtained in the disease causal structure construction step 1205. Make corrections to. Specifically, for example, the degree of medical relevance 704 between major diseases is 1 when there is almost certainly a causal relationship, 0 when no causal relationship is found, and a weak causal relationship. If there is, enter the degree of relevance according to the evidence level in advance, such as 0.5. Next, the causative disease identification unit 111 calculates the sum of the values of the medical relevance degree 704 and the actual condition relevance degree 705 as the disease relevance degree 706. Here, in order to calculate the disease-related degree 706, in addition to calculating the sum, the product is calculated, or both are calculated using any other method (for example, weighting and calculating the sum or product). It may be synthesized.

This completes the procedure for constructing the disease-causal structure (end step 1207).

Next, the procedure for identifying the causative disease will be described with reference to the drawings.

FIG. 13 is a flow chart showing a procedure in which the insurance design support system 101 of the first embodiment of the present invention identifies a causative disease from receipt information.

When the causative disease identification unit 111 starts the procedure for identifying the causative disease from the receipt information in the start step 1301, the causative disease candidate to be the target of the preset processing is read in the target disease definition reading step 1302. .. For example, lung cancer is set when performing an analysis of diseases associated with lung cancer.

Next, the causative disease identification unit 111 sets a threshold value for the disease-related degree 706, which is a determination standard used when identifying the causative disease, in the causative disease identification condition setting step 1303. Next, the causal disease identification unit 111 reads the disease-causal structure (for example, the disease-causal structure information 700 shown in FIG. 7) constructed in advance in the disease-causal structure reading step 1304. Next, the causative disease identification unit 111 reads the receipt to be analyzed in the receipt information reading step 1305.

Next, the causative disease identification unit 111 extracts the injury / illness name 302 together with the medical treatment date of the read receipt in the injury / illness name extraction step 1306. Here, the causative disease identification unit 111 may specify the medical treatment date based on, for example, the medical treatment date 203 of each medical receipt and the daily information 405 to the 31st information 408 of the medical treatment information 400. The injuries and illnesses specified by the injuries and illnesses extracted here are also described as "disease of interest" in the subsequent treatment.

Next, the causative disease identification unit 111 determines whether or not the causative disease corresponding to the target disease definition acquired in the target disease definition reading step 1302 exists in the injury / disease name extracted in the causal disease identification step 1307. In the causal disease determination step 1308, if there is no corresponding causative disease, the process is terminated, and if the corresponding causative disease exists, the process proceeds to the next threshold value determination step 1309. In the threshold value determination step 1309, the causative disease identification unit 111 determines that the degree of disease relevance between the corresponding causative disease and the disease indicated by the injury / disease name extracted in step 1306 is the threshold value set in the causative disease identification condition setting step 1303. Determine if it meets the requirements. When the threshold value is satisfied, the causative disease identification unit 111 records the causative disease for the extracted injury / illness name in the causal disease record information 1100 of the receipt information management unit 120 in the next causal disease information recording step 1310.

For example, if "lung cancer" is set in step 1302 and "pneumonia" is extracted in step 1306, the disease causal structure information 700 is referred to in step 1307. Here, assuming that "disease C" in the disease causal structure information 700 of FIG. 7 is pneumonia, in step 1307, the name of the injury or disease extracted from the receipt based on the disease association identified by the ID "2". "Disease B", which is the cause of "pneumonia" (that is, the starting point corresponding to the terminal "pneumonia") is identified. If this "disease B" is lung cancer, it is determined in step 1307 that the causative disease is present. In the example of FIG. 7, since these disease-related degrees are "1.2", if the threshold value of the disease-related degree set in step 1303 is smaller than 1.2, the causative disease 1101 corresponding to the read receipt is ". "Lung cancer" is recorded.

On the other hand, if "disease B" is not lung cancer, the cause of disease B is further searched. In the example of FIG. 7, “disease A”, which is the cause of “disease B” (that is, the starting point corresponding to the terminal “disease B”), is identified based on the disease association identified by the ID “1”. .. If this "disease A" is lung cancer, it is determined in step 1307 that the causative disease is present. In the example of FIG. 7, the degree of disease association between "disease B" and "disease C" is "1.2", and the degree of disease association between "disease A" and "disease B" is "1.7". Based on these, the degree of disease association between "disease A" (that is, lung cancer) and "disease C" (that is, pneumonia) is calculated. For example, the smallest of these (ie, "1.2") may be the disease association between "lung cancer" and "pneumonia", or may be calculated by other methods. If the disease relevance calculated in this way is greater than the threshold set in step 1303, "lung cancer" is recorded as the causative disease 1101 corresponding to the read receipt.

If the disease set in step 1302 and the disease extracted from the receipt in step 1306 are the same, the disease extracted from the receipt in step 1306 is the receipt without reference to FIG. 7. Is recorded as the causative disease 1101 corresponding to.

This completes the procedure for identifying the causative disease from the receipt information (end step 1311).

Next, the procedure for calculating the insurance money will be described with reference to the figure.

FIG. 14 shows that the insurance design support system 101 of Example 1 of the present invention determines whether or not the causative disease is a disease to be paid based on the causative disease identified from the disease extracted from the medical receipt, and the causative disease is determined. It is a flow chart which showed the procedure of estimating the benefit based on the medical practice about the illness extracted from the medical receipt in the case of the illness to be paid. Here, not only the hospitalization benefit but also the surgery benefit is determined whether or not it is eligible for payment, and the benefit is calculated.

When the insurance money determination unit 112 starts the procedure of determining the disease to be paid and calculating the benefit in the start step 1401, the insurance money determination unit 112 reads the cause disease record information 1100 in the cause disease record information reading step 1402. Next, the insurance claim determination unit 112 reads the hospitalization benefit condition information 800 and the surgery benefit condition information 900 in the insurance product payment condition reading step 1403.

Next, the insurance claim determination unit 112 determines whether or not the identified causative disease is subject to the hospitalization benefit in the hospitalization benefit condition determination step 1404. Specifically, the insurance claim determination unit 112 refers to the causative illness 1101 corresponding to the receipt from which the illness has been extracted, and if there is an injury or illness described in the hospitalization benefit condition information 800, it is specified. It is determined that the causative illness (in other words, the hospitalization stated in the receipt) is covered by the hospitalization benefit. In this case, the insurance claim determination unit 112 calculates the hospitalization benefit in the hospitalization benefit insurance claim calculation step 1405. In general medical insurance products, a predetermined benefit stipulated in the payment conditions is paid for each day of hospitalization. Therefore, the hospitalization benefit can be calculated by multiplying the number of medical treatment days 206 (in the case of a hospitalization receipt, which represents the number of hospitalization days) of the basic medical receipt information by a predetermined insurance amount. On the other hand, if it is determined in the hospitalization benefit condition determination step 1404 that the identified causative disease is not subject to the hospitalization benefit, step 1405 is not executed.

Next, the insurance claim determination unit 112 determines in the operation benefit condition determination step 1406 whether or not the operation to be benefited is performed. Specifically, the insurance claim determination unit 112 performs the operation subject to the benefit when the medical practice name 402 of the medical practice information 400 of the receipt information management unit 120 corresponds to the medical practice 902 to be paid of the surgery benefit condition information 900. Judge that it is done. In that case, the insurance claim determination unit 112 calculates the surgical benefit in the surgical benefit insurance claim calculation step 1407. Specifically, the insurance claim determination unit 112 refers to the benefit multiple setting 903 of the surgical benefit condition information 900, and calculates the surgical benefit by multiplying the predetermined daily benefit amount for hospitalization by the multiple. When performing multiple operations in one hospitalization, the medical practice with the highest magnification is calculated only once. However, this does not apply depending on the contract terms of insurance products. On the other hand, if it is determined in the surgery benefit condition determination step 1406 that the operation to be benefited has not been performed, step 1407 is not executed.

Finally, the insurance claim determination unit 112 calculates the total benefit by adding up the hospitalization benefit and the surgery benefit in the total insurance claim calculation step 1408. This completes the procedure for determining whether the causative disease is a disease to be paid and calculating the benefit (end step 1409).

Next, the procedure for generating information corresponding to the notification used for the medical insurance enrollment examination from the medical examination or medical receipt will be described with reference to the figure.

FIG. 15 is a flow chart showing a procedure in which the insurance design support system 101 of the first embodiment of the present invention generates information corresponding to a notification from a medical examination and a medical receipt.

When the notification information generation unit 114 starts the procedure for generating information corresponding to the notification in the start step 1501, the notification information generation unit 114 sets the notification items to be created in the notification creation condition setting flow 1502. For example, in addition to basic items such as height and weight, the notification items to be generated include past medical history, surgical history within the past 5 years, hospitalization, current medication status, lifestyle-related diseases such as diabetes, and pregnancy. Whether or not there is an abnormality in the inspection value, the type of industry and occupation, etc.

Next, the notification information generation unit 114 receives the receipt information possessed by the receipt information management unit 120 in the subscriber information / receipt / medical examination information reading step 1503, the medical examination information 500 possessed by the medical examination information management unit 121, and the medical examination information 500. The health insurance subscriber information 600 held by the health insurance subscriber information management unit 122 is read. Next, in the health state determination step 1504, the notification information generation unit 114 determines from the medical examination information 500 whether or not there is an abnormality in the test value. For example, the notification information generation unit 114 determines that there is a blood glucose abnormality when the fasting blood glucose is equal to or higher than a predetermined value. Regarding other items such as blood pressure and triglyceride, the notification information generation unit 114 determines that there is an abnormality when the values deviate from the predetermined values.

Next, the notification information generation unit 114 generates notification equivalent information based on the interview items in the lifestyle-related determination step 1505. For example, smoking, drinking, and other physical information contained in the interview are extracted. Next, the notification information generation unit 114 extracts information such as the history of surgery and the presence or absence of hospitalization history based on the medical receipt in the medical consultation status determination step 1506. Specifically, the notification information generation unit 114 refers to the medical practice information 400 of the medical receipt and determines whether or not there is a record of surgery within the past five years, for example. Similarly, the notification information generation unit 114 determines whether or not a receipt for hospitalization exists. In this way, information on surgical history and hospitalization history is created.

Next, in the notification equivalent information creation step 1507, the notification information generation unit 114 creates notification equivalent information by integrating the determination result of the health condition, the determination result of the lifestyle, and the determination result of the medical consultation status. This completes the procedure for generating information corresponding to the notification (end step 1508).

In FIG. 16, the insurance design support system 101 of the first embodiment of the present invention calculates the insurance money from the receipt according to the predetermined payment conditions, and optimizes the payment conditions for eliminating the imbalance between the benefit amount and the medical expenses. It is a flow chart which showed the procedure to perform.

When the procedure of calculating insurance claims and optimizing payment conditions is started in the start step 1601, the subscription condition determination unit 115 separately creates the notification equivalent information created by the notification information generation unit 114 in the evaluation target group extraction step 1602. Based on the above, the conditions for enrollment will be examined, and persons in good health who can enroll in medical insurance will be selected. The procedure after step 1604 described later is executed for the receipt of the person extracted here. By narrowing down the target here and excluding those who cannot join, the insurance design can be evaluated more accurately.

Next, the insurance design evaluation unit 113 sets an evaluation index and its target value for evaluating whether or not the payment conditions are optimal in the evaluation condition setting step 1603. For example, it is calculated for each subscriber whether or not the insurance money is sufficient for the burden (expenditure) of medical expenses paid by the subscriber, and the sufficiency rate, which is the ratio of those who are satisfied, is used as a target index. You may use it. Specifically, for example, the ratio of the number of subscribers whose estimated insurance money is equal to or greater than the burden of the medical expenses to the number of subscribers who have incurred medical expenses may be calculated as the sufficiency rate. In that case, a predetermined sufficiency rate value (for example, 90%) is set as a target value of the evaluation index. The sufficiency rate is an example of an index that can accurately evaluate whether or not the insurance design (specifically, payment terms) is appropriate, and other indexes may be adopted.

Next, the insurance design evaluation unit 113 calculates the medical expenses based on the medical fee points described in the medical receipt in the medical expenses calculation step 1604. Medical expenses can be calculated with 30% of the medical fee points as the counter burden. Next, the insurance claim determination unit 112 calculates the insurance amount according to the insurance claim calculation flow shown in FIG. 14 in the insurance amount calculation step 1605.

Next, the insurance design evaluation unit 113 calculates an evaluation index in the evaluation index calculation step 1606 based on the insurance amount and medical expenses calculated in step 1605. The evaluation index calculated here is the one set in the evaluation condition setting step 1603. For example, when the ratio of persons whose insurance money satisfies the medical expenses (that is, the sufficiency rate) is set as the evaluation index, the insurance design evaluation unit 113 calculates the sufficiency rate as the value of the evaluation index. Next, the insurance design evaluation unit 113 determines in the target value determination step 1607 whether or not the value of the calculated evaluation index satisfies the target value. If the calculated value of the evaluation index does not satisfy the target value, the insurance design evaluation unit 113 searches for the factor in the next excess / deficiency factor search step 1608.

For example, a specific process will be described by taking a case where the sufficiency rate is less than the target value as an example. First, the insurance design evaluation unit 113 calculates the difference between medical expenses and insurance claims for each subscriber. By setting the top of the calculated difference (for example, the top 5%) to 1 and the others to 0, the difference is indexed and the magnitude of the difference is identified. Next, the insurance design evaluation unit 113 uses the past record of medical practice for each subscriber, information on the presence or absence of hospitalization, etc. as explanatory variables, and combines the data with the objective variable (that is, the difference indexed as described above). Create a set.

Further, the insurance design evaluation unit 113 extracts explanatory variables that contribute to the difference between medical expenses and insurance claims, which are objective variables, from the created data set. Any method such as a decision tree or a regression model can be applied as the method of analysis. For example, when the decision tree model is adopted, it is possible to extract the objective variable, that is, the factor (explanatory variable) that has a large influence on the difference between medical expenses and insurance money.

In order to optimize the insurance design with respect to the set target value, the insurance design evaluation unit 113 extracts the items that are the payment conditions of the insurance money from the extracted factors, and in the payment condition change step 1609, Change the payment terms. For example, if the item extracted as a factor having a large influence on the difference is the number of operations, the upper limit of the number of operations in the payment condition is changed. For example, if the upper limit of the number of operations is one, the amount of insurance payment will increase by making the benefit up to two times, and if the insurance money is insufficient, the effect of reducing the difference will be effective. be.

Next, the insurance design evaluation unit 113 recalculates the insurance amount in the insurance amount calculation step 1605, and performs a process (step 1606, step 1607) of determining whether or not the evaluation index satisfies the target value. The optimization process is executed by repeating until it reaches. When the result satisfying the target value is obtained (that is, when it is determined in the target value determination step 1607 that the value of the evaluation index satisfies the target value), the insurance design evaluation unit 113 determines the updated payment condition output step 1610. Outputs the payment terms of the above processing result. This completes the procedure for calculating insurance claims and optimizing payment conditions.

Next, the procedure for constructing the disease causal structure will be described using a screen example.

FIG. 17 is an explanatory diagram showing an example of the disease causal structure construction screen 1701 output by the insurance design support system 101 of the first embodiment of the present invention.

For example, a user of this system refers to the disease causal structure construction screen 1701 displayed by the output unit 103, operates the input unit 102 to input the disease to be paid into the cause disease input 1702, and examines the relationship. Input the disease of interest to the input disease of interest 1703, and input the threshold value as a criterion for recognizing the relationship between the causative disease and the disease of interest in the association determination threshold input 1704. When the user operates the input unit 102 and presses the calculation execution button 1705, the causal disease identification unit 111 constructs the disease causal structure by executing the process shown in FIG.

Disease causal structure display 1708 based on medical findings shows a diagram connecting the causative disease and other diseases by the degree of relevance based on medical findings. Medical relevance 704 from disease A to disease B and P _AB, medical relevance from illness B to diseases C P _BC, the relevance of the diseases B to disease D and P _BD representation, line thickness Sa expresses the strength of relevance. Disease causal structure display 1709 based on the data is obtained by calculating the relevance between the disease from the data represents the actual relevance 705, respectively P _'AB, P' _BC, as P _'BD.

Next, in the fusion method selection 1706, the user selects a method of fusing the disease causal structure based on medical knowledge and the disease causal structure based on data. FIG. 17 shows an example of fusion by sum. The calculation result is displayed on the causal structure display 1710 corrected by data. This corresponds to the disease-related degree 706.

In the example of FIG. 17, the route from disease A (for example, lung cancer) to disease C (for example, pneumonia) via disease B is shown. In determining the relationship between lung pneumonia and disease A disease C is focused disease, determines that there is relevant when both paths of _{P AB +} P _'AB and _{P BC +} P' _BC is equal to or greater than the threshold, the determination The result is displayed on the result display 1711. Here, the above example is given for the sake of explanation, but the method for determining the association is not limited to the above, and any method can be used.

In addition, this process can be executed internally and can be executed without the need for on-screen operations. For example, instead of the user designating the causative disease and the disease of interest, the causative disease identification unit 111 generates all (or the required number) combinations of the causative disease and the disease of interest and constructs a disease causal structure for them. You may. In that case, the insurance design support system 101 does not have to output the disease causal structure construction screen 1701.

Next, the procedure for executing the insurance amount estimation and referring to the result will be described using a screen example.

FIG. 18 is an explanatory diagram showing an example of the insurance money simulation screen 1801 output by the insurance design support system 101 of the first embodiment of the present invention.

There is a setting panel 1802 in the insurance money simulation screen 1801 displayed by the output unit 103, and for example, the user operates the estimation target insurance product selection 1803 via the input unit 102 to select and desire the estimation target insurance product. Specify the payment terms of. Further, the user specifies the extraction condition of the target subscriber group in the subscriber condition selection 1804, specifies the estimation target period of the receipt in the target period selection 1805, and in the hospitalization daily amount selection 1806. Set the daily hospitalization amount to be used when calculating insurance claims. When the user operates the input unit 102 and presses the estimation execution button 1807, the insurance claim determination unit 112 executes various calculations according to the procedure shown in FIG. 14, and the calculation result is displayed on the result display 1808.

The results of insurance claims estimation are displayed in the estimation result table 1809. For example, the average amount of insurance claims for each causative disease is displayed. From the calculation results, not only the average but also the standard deviation or any other statistic can be calculated and displayed. The insurance claim estimation result graph display 1810 displays the estimation results selected in the estimation result table 1809 as a graph. From this graph display, more detailed information such as the distribution of insurance amount estimation results can be obtained.

Next, the procedure for designing the optimum payment terms by estimating insurance claims will be described using a screen example.

FIG. 19 is an explanatory diagram showing an example of the insurance design simulation screen 1901 output by the insurance design support system 101 of the first embodiment of the present invention.

There is a setting panel 1802 in the insurance design simulation screen 1901 displayed by the output unit 103. For example, when the user operates the input unit 102, the target benefit sufficiency rate is input to the target benefit sufficiency rate setting 1902 in the setting panel 1802. .. This target benefit sufficiency rate corresponds to the target value set in step 1603 of FIG. When the user presses the optimization execution button 1903, the insurance design evaluation unit 113 and the like execute the optimum payment condition search according to the procedure shown in FIG.

The calculation result is displayed on the aggregation result display 1904, the pre-optimization result display 1905, and the post-optimization result display 1906. In the aggregated result display 1904, the estimated amount of insurance money and medical expenses calculated according to the payment conditions of the insurance product set in the insurance product selection 1803 are statistical values such as an average, and the insurance money is sufficient for the medical expenses. The percentage of people and the percentage of people who are in short supply are displayed. In the example of FIG. 19, the aggregated result display 1904 shows the average medical expenses out-of-pocket, average insurance amount, and sufficiency rate before and after optimization when lung cancer is selected as the causative disease. .. Here, the optimization means repeating steps 1605 to 1609 until it is determined in step 1607 of FIG. 16 that the target value is satisfied. In the column after optimization, the estimated amount of insurance money as a result of changing the contents displayed in the payment condition change contents display 1907 is displayed.

For example, the payment condition change content 1907 displays the condition change content such as adding a disease that was previously excluded from the payment condition to the target, or increasing or decreasing the benefit amount related to a specific surgical procedure. The pre-optimization result display 1905 displays a graph of the sufficiency ratio before the optimization process is executed, and the post-optimization result display 1906 displays the sufficiency ratio after the optimization process is executed. This screen example shows an example for explanation, and any setting item and display method may be used.

According to the above-mentioned Example 1, by carrying out insurance claim estimation using information such as medical receipts and medical examinations, virtual payment terms that have not actually been set and virtual payments that have not actually been subscribed yet. It is possible to evaluate the impact of adding a typical subscriber. Furthermore, since it is possible to calculate the medical expenses borne by the policyholder at the same time, it is possible to search for the conditions of insurance claims products with high utility value for the policyholder. This has the effect of automatically executing accurate risk assessment in the payment condition design of medical insurance and greatly improving the efficiency of design work related to product design.

Example 2 of the present invention will be described in detail with reference to the drawings. Here, statistics are based on the receipt data, health examination results, and attribute data based on basic attribute data such as the age and gender of the health status of the actual (that is, already sold) insurance product subscribers. An insurance design support system that selects virtual subscribers with the same characteristics will be described. Except for the differences described below, each part of the system of Example 2 has the same function as each part of Example 1 shown in FIGS. 1 to 19 having the same reference numerals. Is omitted.

FIG. 20 is a block diagram showing an example of the configuration of the insurance design support system 101 according to the second embodiment of the present invention.

In the second embodiment, the storage medium 106 of the insurance design support system 101 has an insurance subscriber feature extraction unit 116. In addition, the database 107 has a product-specific subscriber information management unit 126 that manages information on basic attribute data such as the health status, age, and gender of the actual insurance product subscriber group.

FIG. 21 is an explanatory diagram showing an example of the product-specific subscriber information 2100 managed by the product-specific subscriber information management unit 126 of the second embodiment of the present invention.

The product-specific subscriber information 2100 includes an insurance policyholder ID 2101 that identifies an insurance policyholder, an insurance product ID 803 that identifies an insurance product, an insurance product name 2102 that indicates the name of an insurance product, a gender of the insured person 603, and an insured person. Date of birth 604, industry category 2103 indicating the insured's industry, occupation category 2104 indicating the insured's occupation, date of joining the insurance product 2105, date of withdrawal from the insurance product 2106, and notification Information 2017 is managed. This information has the effect of extracting the characteristics of subscribers by product and selecting a group having the same statistical characteristics from the receipt and medical examination result information.

In FIG. 22, the insurance design support system 101 of the second embodiment of the present invention extracts a group having the same statistical characteristics as the policyholders who are enrolled in the actual insurance product from the data of the receipt and the medical examination result. It is a flow chart which showed the procedure for this.

First, the insured person feature extraction unit 116 sets at least one item (covariate) for background adjustment in order to extract statistically the same group in the adjustment variable setting step 2202. For example, if you want to adjust the age and gender composition, set the age and gender. In addition, if you want to make adjustments including your health condition, set various test values. In addition to the above, necessary items can be arbitrarily set for the covariate. Next, the insurance subscriber feature extraction unit 116 reads the product-specific subscriber information 2100 in the product-specific subscriber information reading step 2203.

Next, the insurance subscriber feature extraction unit 116 reads the receipt data, the medical examination result, and the attribute data in the health insurance subscriber information reading step 2204. Next, the insurance subscriber feature extraction unit 116 generates notification information from the receipt data, the medical examination result, and the attribute data in the notification information generation step 2205. Next, the insurance subscriber feature extraction unit 116 selects a group that can subscribe to the target insurance product from the group of health insurance subscribers in the subscription condition determination step 2206. Next, the insurance subscriber feature extraction unit 116 adjusts the covariate of the insurance product subscriber group and the covariate of the health insurance subscriber in the background adjustment step 2207. Next, in the background-adjusted selection group extraction step 2208, the insurance subscriber feature extraction unit 116 selects a group of the health insurance subscriber group that is not statistically significantly different from the covariate of the target insurance product subscriber group. Select from among. In the following description, the fact that there is no statistically significant difference is described as the same. That is, the same here includes not only the exact same but also sufficiently similar. The insurance design support system 101 of the second embodiment estimates the insurance money based on the group extracted by the insurance member feature extraction unit 116.

Next, the procedure for extracting a group having the same statistical characteristics as the actual insurance product subscriber group from the data of the receipt and the medical examination result will be described using a screen example.

FIG. 23 is an explanatory diagram showing an example of a subscriber group selection screen 2301 output when the insurance design support system 101 of the second embodiment of the present invention outputs a subscriber group selection process.

The subscriber group selection screen 2301 displayed by the output unit 103 includes a setting panel 2302. The setting panel 2302 has an adjustment variable designation 2303, a product-specific subscriber information 2304, a medical examination / receipt information 2305, a notification information generation execution button 2306, a subscription condition determination execution button 2307, and a selection execution button 2308.

For example, when the user operates the input unit 102, the variable to be adjusted is input to the adjustment variable specification 2303, the subscriber group of the product to be analyzed is specified in the product-specific subscriber information 2304, and the medical examination is performed. -In the receipt information 2305, the data set of the target group to be selected by adjusting the background is specified. Then, when the user presses the notification information generation execution button 2306, the notification information generation unit 114 generates notification information from the set medical examination / receipt information. Next, when the user presses the subscription condition determination execution button 2307, the subscription condition determination unit 115 determines whether or not to subscribe from the generated notification information and medical examination information. The output unit 103 displays, for example, information on the determination result of whether or not to subscribe on the subscription condition determination result display 2309 in the subscriber group selection screen 2301.

Next, when the user presses the selection execution button 2308, the insurance subscriber feature extraction unit 116 selects a group having the same statistical characteristics as the actual insurance product subscriber group from the group satisfying the subscription conditions. Extract. On the selection result display 2310 in the subscriber group selection screen 2301, for example, the adjusted variable, the average of the actual subscriber group and the average of the selected group related to the variable, the test result of the difference, etc. are displayed. .. By selecting subjects so that there is no significant difference between the two groups for each adjustment variable, groups with statistically the same characteristics can be extracted.

According to the second embodiment, it is possible to estimate the insurance amount based on the group having the same characteristics as the insurance member group, and it is possible to carry out a more detailed insurance design evaluation.

The present invention is not limited to the above-described examples, and includes various modifications. For example, the above-mentioned examples have been described in detail for a better understanding of the present invention, and are not necessarily limited to those having all the configurations of the description. Further, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add / delete / replace a part of the configuration of each embodiment with another configuration.

Further, each of the above configurations, functions, processing units, processing means and the like may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. Further, each of the above configurations, functions, and the like may be realized by software by the processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be stored in non-volatile semiconductor memories, hard disk drives, storage devices such as SSDs (Solid State Drives), or computers such as IC cards, SD cards, and DVDs that are not readable. It can be stored in a temporary data storage medium.

In addition, the control lines and information lines are shown as necessary for explanation, and not all control lines and information lines are necessarily shown in the product. In practice, it can be considered that almost all configurations are interconnected.

101 Insurance design support system 102 Input unit 103 Output unit 104 CPU
105 Memory 106 Storage medium 111 Cause Disease identification unit 112 Insurance claim judgment unit 113 Insurance design evaluation department 114 Notification information generation unit 115 Subscription condition judgment unit 116 Insurance subscriber feature extraction unit 120 Receipt information management department 121 Medical examination information management department 122 Health insurance Subscriber Information Management Department 123 Disease Causal Structure Management Department 124 Payment Conditions Management Department 125 Subscription Conditions Management Department 126 Product-Specific Subscriber Information Management Department

Claims (14)

An insurance design support system having a processor and a storage device connected to the processor.
The storage device holds medical receipt information including information on actual medical fees for a plurality of persons, disease causal structure information indicating a relationship between diseases, and insurance payment conditions designed in insurance.
The processor
From the diseases extracted from the medical receipt information, the causal disease identification procedure for identifying the causal disease based on the disease causal structure information, and
When the specified causative disease corresponds to the payment conditions, the medical treatment performed on the extracted disease is extracted from the receipt information, and the extracted medical treatment and the medical treatment corresponding to the causative disease are described. An insurance claim estimation procedure for estimating the insurance amount to be paid to the plurality of persons based on the payment terms and conditions, and
The medical expenses of the plurality of persons are calculated based on the receipt information, and the insurance design evaluation procedure for evaluating the insurance design based on the calculated medical expenses and the estimated insurance amount is executed. An insurance design support system characterized by this. The insurance design support system according to claim 1.
In the insurance design evaluation procedure, the processor is based on the attribute information of the plurality of persons, the medical examination information including the results of the medical examinations received by the plurality of persons, the receipt information, and the insurance enrollment conditions. Multiple persons who meet the above insurance coverage conditions are extracted as evaluation targets, and
In the insurance claim estimation procedure, the processor is an insurance design support system that estimates the insurance amount to be paid to a plurality of persons extracted as the evaluation target. The insurance design support system according to claim 2.
In the insurance design evaluation procedure, the processor
Based on the receipt information, the medical expenses of a plurality of persons extracted as the evaluation target are calculated, and the medical expenses are calculated.
Based on the medical expenses and the insurance amount, the evaluation index of the insurance design is calculated.
If the evaluation index does not reach the predetermined target value, the payment terms are changed.
An insurance design support system characterized in that when the evaluation index reaches a predetermined target value as a result of changing the payment conditions, the changed payment conditions are output. The insurance design support system according to claim 3.
The evaluation index is a sufficiency rate that is the ratio of the number of persons whose insurance amount is equal to or greater than the burden amount of the medical expenses to the number of persons who have incurred the medical expenses among the persons extracted as the evaluation target. An insurance design support system characterized by being present. The insurance design support system according to claim 1.
In the causative disease identification procedure, based on the receipt information, the processor determines when one of the two diseases is treated and when the other is treated for each combination of the two diseases. It is characterized in that it identifies, calculates the degree of relevance indicating the strength of the relationship between the two diseases based on the relationship of the specified time, and generates the disease causal structure information based on the degree of relevance. Insurance design support system. The insurance design support system according to claim 5.
In the causative disease identification procedure, the processor synthesizes a relevance indicating the strength of the relationship between the two diseases generated based on medical knowledge and a relevance calculated based on the receipt information. An insurance design support system characterized in that the disease causal structure information is generated based on the degree of relevance generated by the operation. The insurance design support system according to claim 1.
The processor is based on the attribute information of the plurality of persons, the medical examination information including the results of the medical examinations received by the plurality of persons, and the receipt information, and the attribute information, the medical examination information, and the receipt information. An insurer who extracts from the plurality of persons a group in which the statistical characteristics of one or more items are similar to the statistical characteristics of the one or more items of the subscribers of the actual insurance product already sold. Perform further feature extraction procedures and
In the insurance claim estimation procedure, the processor is an insurance design support system that estimates the insurance amount to be paid to a plurality of persons included in the extracted group. It is an insurance design support method executed by a computer system.
The computer system includes a processor and a storage device connected to the processor.
The storage device holds medical receipt information including information on actual medical fees for a plurality of persons, disease causal structure information indicating a relationship between diseases, and insurance payment conditions designed in insurance.
The insurance design support method is
A causal disease identification procedure for the processor to identify a causal disease from a disease extracted from the receipt information based on the disease causal structure information.
When the identified causative disease corresponds to the payment terms, the processor extracts the medical treatment performed on the extracted disease from the receipt information, and the extracted medical treatment and the causative disease. An insurance claim estimation procedure for estimating the insurance amount to be paid to the plurality of persons based on the payment terms corresponding to the above.
An insurance design evaluation procedure in which the processor calculates medical expenses for the plurality of persons based on the receipt information and evaluates the insurance design based on the calculated medical expenses and the estimated insurance amount. An insurance design support method characterized by including,. The insurance design support method according to claim 8.
The insurance design evaluation procedure is based on the attribute information of the plurality of persons, the medical examination information including the results of the medical examinations received by the plurality of persons, the receipt information, and the insurance enrollment conditions by the processor. Including the procedure of extracting a plurality of persons who meet the insurance enrollment conditions as evaluation targets.
The insurance claim estimation procedure is an insurance design support method including a procedure in which the processor estimates the insurance amount to be paid to a plurality of persons extracted as the evaluation target. The insurance design support method according to claim 9.
The insurance design evaluation procedure is
A procedure in which the processor calculates medical expenses for a plurality of persons extracted as evaluation targets based on the receipt information, and
A procedure in which the processor calculates an evaluation index of the insurance design based on the medical expenses and the insurance amount.
A procedure for the processor to change the payment terms when the evaluation index does not reach a predetermined target value.
An insurance design support method comprising a procedure in which the processor outputs the changed payment terms when the evaluation index reaches a predetermined target value as a result of changing the payment terms. The insurance design support method according to claim 10.
The evaluation index is a sufficiency rate that is the ratio of the number of persons whose insurance amount is equal to or greater than the burden of the medical expenses to the number of persons who have incurred the medical expenses among the persons extracted as the evaluation target. An insurance design support method characterized by being present. The insurance design support method according to claim 8.
In the causative disease identification procedure, based on the receipt information, the processor determines the time when one of the two diseases is treated and the time when the other is performed for each combination of the two diseases. Including a procedure of identifying, calculating the degree of relevance indicating the strength of the relationship between the two diseases based on the relationship of the specified time, and generating the disease causal structure information based on the degree of relevance. A characteristic insurance design support method. The insurance design support method according to claim 12.
In the causative disease identification procedure, the processor synthesizes a degree of relevance indicating the strength of the relationship between the two diseases generated based on medical knowledge and a degree of relevance calculated based on the receipt information. An insurance design support method comprising a procedure for generating the disease-causal structure information based on the degree of relevance generated by the operation. The insurance design support method according to claim 8.
Based on the attribute information of the plurality of persons, the medical examination information including the results of the medical examinations received by the plurality of persons, and the receipt information, the processor may obtain the attribute information, the medical examination information, and the receipt information. An insurer who extracts from the plurality of persons a group in which the statistical characteristics of one or more items are similar to the statistical characteristics of the one or more items of the subscribers of the actual insurance product already sold. Including further feature extraction procedure
The insurance claim estimation procedure is an insurance design support method, characterized in that the processor includes a procedure for estimating an insurance amount to be paid to a plurality of persons included in the extracted group.

Images