JP2023093975A - Information analysis support method, and information analysis support system - Google Patents

Abstract

To automate the maintenance of data inputted for information processing such as risk evaluation.SOLUTION: The present invention relates to an information analysis support method executed by a computer system. The method includes: a procedure of holding dictionary information for associating risk model for calculating a risk value relating to health and information regarding health with at least any one of a plurality of aggregation sections for aggregating the information regarding health and explanatory variable definition information for associating one or more combination of aggregation sections and a value of an explanatory variable of the risk model with each other to extract the information regarding health from the input information; a procedure of specifying one or more aggregation sections corresponding to the extracted information relating to health based on the dictionary information; a procedure of specifying the value of the explanatory variable corresponding to the specified combination of one or more compacted sections based on the explanatory variable definition information; and a procedure of calculating a risk value corresponding to the specified value of the explanatory variable based on the risk model.SELECTED DRAWING: Figure 1

Description

TECHNICAL FIELD The present invention relates to technology for supporting analysis of information related to health conditions.

Life insurance business operators determine the insurance claim payment risk based on the health condition of the policyholder at the time of contract, and assess underwriting. The policyholder's health condition at the time of contract is specified based on the declaration information that the policyholder submits when applying for enrollment. As a technique for assisting the input of notification information, for example, there is a technique described in Japanese Patent Application Laid-Open No. 2015-22374 (Patent Document 1). In Patent Document 1, "A computer acquires medical information corresponding to personal identification information that identifies a user, and based on the items of the medical information, the notification items in the insurance product and corresponding question text information and answers A process of selecting question text information and answer item information corresponding to the medical information from the item information, and a process of outputting input screen data of the notification items including the selected question text information and answer item information. It is stated that

JP 2015-22374 A

Information in the announcements submitted by subscribers covers a large number of items that indicate health conditions, and may include ambiguous expressions, typographical errors, or incorrect items being entered. For this reason, data is prepared manually in advance, and much time and cost are required before risk assessment can be performed. In order to perform risk assessment more accurately and simply, it is necessary to enable these processes to be performed automatically.

The above-mentioned Patent Document 1 describes a technology for assisting the entry of items to be notified by a subscriber based on a medical record, but the technology for converting the submitted information into a format suitable for risk assessment is clear. not been to.

Therefore, in order to solve the above problems, the present invention extracts and organizes information necessary for information processing such as risk assessment based on notification information about the health condition entered by the subscriber, and uses a predetermined model etc. The object is to provide a method that enables information processing.

In order to solve at least one of the above problems, a representative example of the invention disclosed in the present application is an information analysis support method executed by a computer system, wherein the computer system comprises a processor and a processor connected to the processor. a storage device comprising: a risk model for calculating a health-related risk value; and dictionary information that associates health-related information with at least one of a plurality of aggregation categories for aggregating the health-related information. and explanatory variable definition information that associates one or more combinations of the aggregated categories with the values of the explanatory variables of the risk model, and the information analysis support method includes: a first procedure for extracting health-related information; a second procedure for the processor to identify one or more of the aggregated categories corresponding to the extracted health-related information based on the dictionary information; a third procedure for identifying the values of the explanatory variables corresponding to the identified combination of the one or more aggregation categories based on the explanatory variable definition information; and a fourth step of calculating the risk value corresponding to the value of the explanatory variable.

According to one aspect of the present invention, the time and cost required for processing are reduced by automating data maintenance up to information processing such as risk assessment. Problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments.

BRIEF DESCRIPTION OF THE DRAWINGS It is a block diagram which shows an example of a structure of the information-analysis support system of Example 1 of this invention. FIG. 4 is an explanatory diagram showing an example of basic information managed by a basic information management unit according to the first embodiment of this invention; FIG. 4 is an explanatory diagram showing an example of notification information managed by a health information management unit according to Example 1 of the present invention; FIG. 4 is an explanatory diagram showing an example of health checkup information managed by a health information management unit according to the first embodiment of this invention; FIG. 4 is an explanatory diagram showing an example of disease name definition information managed by a disease name definition information management unit according to the first embodiment of this invention; FIG. 4 is an explanatory diagram showing an example of drug definition information managed by a drug definition information management unit according to Example 1 of the present invention; FIG. 4 is an explanatory diagram showing an example of surgery definition information managed by a surgery definition information management unit according to Embodiment 1 of the present invention; FIG. 4 is an explanatory diagram showing an example of hospitalization definition information managed by a hospitalization definition information management unit according to the first embodiment of this invention; FIG. 5 is an explanatory diagram showing an example of inspection result definition information managed by an inspection result definition information management unit according to the first embodiment of this invention; FIG. 4 is an explanatory diagram showing an example of explanatory variable definition information managed by an explanatory variable definition information management unit according to the first embodiment of this invention; FIG. 5 is an explanatory diagram showing an example of an intermediate table for explanatory variable generation processing managed by the explanatory variable generation result management unit according to the first embodiment of this invention; FIG. 4 is an explanatory diagram showing an example of risk calculation target information managed by a risk calculation target information management unit according to the first embodiment of this invention; FIG. 5 is an explanatory diagram showing an example of explanatory variable generation result information managed by an explanatory variable generation result management unit according to the first embodiment of this invention; FIG. 4 is an explanatory diagram showing an example of risk model information managed by a risk model information management unit according to Example 1 of this invention; FIG. 4 is an explanatory diagram showing an example of classification definition information managed by a classification definition information management unit according to the first embodiment of this invention; 5 is a flowchart showing an example of processing executed by a disease name information extraction unit according to Example 1 of the present invention; It is a flowchart which shows an example of the process which the drug information extraction part of Example 1 of this invention performs. It is a flowchart which shows an example of the process which the inspection result information extraction part of Example 1 of this invention performs. It is a flowchart which shows an example of the process which the surgery information extraction part of Example 1 of this invention performs. It is a flowchart which shows an example of the process which the hospitalization information extraction part of Example 1 of this invention performs. FIG. 5 is a flowchart showing an example of processing executed by an explanatory variable information generation unit according to Example 1 of this invention; FIG. FIG. 4 is a flowchart showing an example of processing executed by a risk calculation unit according to Example 1 of the present invention; FIG. 4 is a flowchart showing an example of processing executed by a risk determination unit according to Example 1 of the present invention; FIG. 10 is an explanatory diagram showing an example of a user interface that displays notification information in the process of generating explanatory variables by the information analysis support system according to the first embodiment of this invention; FIG. 10 is an explanatory diagram showing an example of a user interface that displays the result of aggregation processing in the processing of generating explanatory variables by the information analysis support system according to the first embodiment of this invention; FIG. 10 is an explanatory diagram showing an example of a user interface displaying a result of explanatory variable generation processing in the processing of generating explanatory variables by the information analysis support system according to the first embodiment of this invention; FIG. 4 is an explanatory diagram showing an example of a user interface displaying results of risk analysis performed by the information analysis support system according to the first embodiment of this invention; It is a block diagram which shows an example of a structure of the information-analysis support system of Example 2 of this invention. FIG. 10 is an explanatory diagram showing an example of contract information managed by a contract information management unit according to the second embodiment of this invention; FIG. 11 is an explanatory diagram showing an example of billing information managed by a billing information management unit according to the second embodiment of this invention; FIG. 10 is an explanatory diagram showing an example of payment classification definition information managed by a payment classification definition information management unit according to the second embodiment of this invention; It is explanatory drawing which shows an example of the payment determination result information which the payment determination result management part of Example 2 of this invention manages. It is a flowchart which shows an example of the process which the payment determination part of Example 2 of this invention performs. FIG. 10 is an explanatory diagram showing an example of a user interface that displays billing information in the payment determination process by the information analysis support system of Example 2 of the present invention; FIG. 11 is an explanatory diagram showing an example of a user interface on which the information analysis support system according to the second embodiment of this invention displays the result of payment determination processing;

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram showing an example of the configuration of an information analysis support system 101 according to Example 1 of the present invention.

The information analysis support system 101 is a computer system, and includes an input unit 102 such as a keyboard and a mouse, an output unit 103 representing a display for outputting display data, a CPU (Central Processing Unit) 104, a memory 105, a communication unit 108, and a storage unit. A medium 106 is provided.

The information analysis support system 101 includes a disease name information extraction unit 111, a drug information extraction unit 112, a test result information extraction unit 113, a surgery information extraction unit 114, a hospitalization information extraction unit 115, an explanatory variable information generation unit 116, a risk calculation unit 117, and It has a risk determination unit 118 . The functions of the disease name information extraction unit 111 to the risk determination unit 118 are implemented by the CPU 104 executing programs stored in the storage medium 106 . When these programs are executed by CPU 104, at least a portion of them may be copied to memory 105 as needed.

A database 107 is connected to the information analysis support system 101 . The database 107 includes a basic information management unit 121, a health information management unit 122, a disease name definition information management unit 123, a drug definition information management unit 124, a surgery definition information management unit 125, a hospitalization definition information management unit 126, and an examination result definition information management unit. 127 , explanatory variable definition information management unit 128 , explanatory variable generation result management unit 129 , risk calculation target information management unit 130 , risk model information management unit 131 and classification definition information management unit 132 .

As will be described later, the basic information management unit 121 manages basic information 200 (FIG. 2). The health information management unit 122 manages the anamnesis information 300 (Fig. 3) and the medical examination information 400 (Fig. 4). The disease name definition information management unit 123 manages disease name definition information 500 (FIG. 5). The drug definition information management unit 124 manages drug definition information 600 (FIG. 6). The surgery definition information management unit 125 manages surgery definition information 700 (FIG. 7). The hospitalization definition information management unit 126 manages hospitalization definition information 800 (FIG. 8). The inspection result definition information management unit 127 manages inspection result definition information 900 (FIG. 9). The explanatory variable definition information management unit 128 manages the explanatory variable definition information 1000 (FIG. 10). The explanatory variable generation result management unit 129 manages an intermediate table 1100 (FIG. 11) and an explanatory variable generation result 1300 (FIG. 13) of explanatory variable generation processing. The risk calculation target information management unit 130 manages risk calculation target information 1200 (FIG. 12). The risk model information management unit 131 manages risk model information 1400 (FIG. 14). The classification definition information management unit 132 manages classification definition information 1500 (FIG. 15).

The database 107 may be stored, for example, in a storage system connected to the information analysis support system 101 via a network, or may be stored in the information analysis support system 101 (for example, by being stored in the storage medium 106). good too. When the database 107 is stored in a system outside the information analysis support system 101, at least part of its contents may be copied to the storage medium 106 or memory 105 as required. Also, 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 called an information analysis support system.

Further, the information analysis support system 101 may be implemented by one computer having the configuration shown in FIG. 1, for example, or may be implemented by a plurality of computers. For example, the information held by the database 107 described above may be distributed and stored in a plurality of storage media 106 or memories 105, and the functions of the information analysis support system 101 described above may be performed by a plurality of CPUs 104 of a plurality of computers. It may be executed in a distributed manner.

FIG. 2 is an explanatory diagram showing an example of basic information 200 managed by the basic information management unit 121 according to the first embodiment of this invention.

The basic information 200 is basic information about each person who has applied for the insurance product of the insurance provider.

Specifically, the basic information 200 includes a personal ID 201 that identifies each person, a gender 202 that identifies the sex of each person, a date of birth 203 that identifies the date of birth of each person, and the number of applications received from each person. It includes an application acceptance date 204 and the like that specify the date on which the application was received. The basic information 200 described above is an example, and the basic information 200 may include various information regarding each person as necessary.

FIG. 3 is an explanatory diagram showing an example of past disease information 300 managed by the health information management unit 122 according to the first embodiment of this invention.

The pre-existing disease information 300 is information related to injury or disease (pre-existing disease) experienced by each person in the past, among information extracted from notification information submitted by each person to the insurance company for applying for insurance. The content that a person has entered in the item corresponding to the pre-existing disease in the notification information may be retained as the pre-existing disease information 300 as it is. The past disease information 300 includes an individual ID 301, a serial number 302, a disease name 303, a drug name 304, an admission date 305, a discharge date 306, an operation 307, and the like.

The personal ID 301 is information that identifies each person, and corresponds to the personal ID 201 of the basic information 200 . A serial number 302 is information that specifies each item when the contents of a plurality of items are extracted from the notification information of each person. A disease name 303, a drug name 304, an admission date 305, a discharge date 306, and an operation 307 respectively indicate contents extracted from the items of the disease name, drug name, admission date, discharge date, and operation of the notification information of each person.

The disease name 303 to surgery 307 are registered as they are by each person, so they may contain inaccurate information, ambiguous information, or may be missing. For example, the disease name 303 may include ambiguous information such as "I was told I had dyslipidemia." Alternatively, there may be cases where the disease name 303 is unknown (for example, the person does not remember it), but information on the drug name 304 or surgery 307 has been obtained.

In the example of FIG. 3 , the first and second rows of the medical history information 300 indicate that the person identified by the ID “P001” was hospitalized for hypertension from April 1, 2020 to April 5, 2020. , and indicates that the patient has submitted notification information in which he or she has been told by a doctor that he or she has dyslipidemia. The third line indicates that the person identified by the ID "P002" was prescribed drug A and underwent surgery A, although the name of the disease was unknown.

FIG. 4 is an explanatory diagram showing an example of health checkup information 400 managed by the health information management unit 122 according to the first embodiment of this invention.

The health checkup information 400 is information about the results of a health checkup (physical checkup) that each person received, and may be submitted by each person as part of the notification information for applying for insurance. Health checkup information 400 includes personal ID 401, test date 402, BMI 404, fasting blood sugar 404, HbA1c 405, interview result 406, indications 407, and the like.

The personal ID 401 is information for specifying each person, and corresponds to the personal ID 201 of the basic information 200 . The examination date 402 indicates the date on which the physical examination was performed. BMI 404, fasting blood glucose 404 and HbA1c 405 are examples of test values obtained as a result of a physical examination. The interview result 406 is the result of the interview at the time of the health checkup, and may include, for example, information indicating whether or not the person has a habit of drinking alcohol, whether or not he or she has a habit of exercising, and the like. The pointed out item 407 is information on items pointed out as a result of the medical examination.

The above information is a typical example of information obtained as a result of a health checkup, and in practice the health checkup information 400 may not include at least one of these items, or may include information on items other than these items. It's okay.

FIG. 5 is an explanatory diagram showing an example of the disease name definition information 500 managed by the disease name definition information management unit 123 according to the first embodiment of this invention.

The information about the disease name extracted from the notification information is aggregated into a plurality of predetermined categories according to the disease name definition information 500. FIG. That is, the disease name definition information 500 is dictionary information that associates descriptions of disease names included in the pre-existing disease information 300 with categories for aggregating disease names, and includes a disease name aggregation category 501, a target disease name 502, and an evaluation processing category (disease name) 503. .

The disease name aggregation classification 501 is information for identifying a classification for aggregating disease names. It may be a code or the like. This disease name aggregation category 501 is associated with an explanatory variable input to a risk model for evaluating insurance claim payment risk in a process described later.

The target disease name 502 is information that is assumed to be extracted from the disease name item of the pre-existing disease information 300 . As in the pre-existing disease information 300, the part of the notification information filled in by the insurance applicant is not necessarily filled with accurate information. Therefore, there is a possibility that the information extracted from the disease name item of the pre-existing disease information 300 is not accurate. For this reason, it is assumed that the target disease name 502 is entered in the notification information in order to correctly associate not only the correct disease name but also ambiguous or inaccurate description of the disease name with the classification for aggregating the disease names. A description of the disease name is registered.

In the example of FIG. 5, “disease name A”, “disease name B”, and “disease name C” are registered as the target disease names 502 corresponding to the value “D1” of the disease name aggregation section 501 . For example, if "D1" is a code that identifies dyslipidemia, "disease name A" is the correct disease name "dyslipidemia", and "disease name B" and "disease name C" are each ambiguous. It may be "said to be lipid abnormal" and "high lipid".

It should be noted that the description about the disease name included in the notification information may contain typographical errors (for example, typographical errors) because it is written by the person who wishes to join the insurance. Therefore, as the target disease name 502, a disease name including possible typographical errors (for example, typographical errors that frequently appeared in the past) may be registered. However, in the process of extracting information about the name of a disease from notification information, which will be described later, there are cases in which typographical errors can be corrected by syntactic analysis. Therefore, the amount of data to be held may be reduced by not registering errors that can be corrected by parsing in the target disease name 502 .

The evaluation processing category (disease name) 503 is information indicating whether or not the value of the disease name aggregation category 501 specified according to the disease name definition information 500 is to be subjected to risk assessment by the risk model. The value of the evaluation processing category (disease name) 503 “target” is subject to risk assessment processing by the model, “non-target” is not subject, “target (confirmation required)” is subject but manual confirmation indicates that the

For example, when a disease name aggregation category "D1" that identifies "dyslipidemia" is identified based on the description "I was told that I was told to have dyslipidemia", the identification accuracy is sufficiently high, and the identified disease name If a predetermined level of accuracy can be expected when risk evaluation is performed using a risk model based on the aggregated classification, “target” may be registered as the evaluation processing classification (disease name) 503 .

On the other hand, for example, the value of the target disease name 502 is only "lipid", and although it is presumed to indicate "dyslipidemia", the accuracy is low, and the risk is evaluated by the risk model based on the specified disease name aggregation category. If a predetermined accuracy cannot be expected when performing In this case, the notification information of the person corresponding to the disease name aggregate classification is excluded from the risk evaluation targets by the risk model.

In addition, if the accuracy of identification of the disease name aggregation classification is medium, and if the specific result is correct, a predetermined accuracy can be expected in the risk evaluation, the evaluation processing classification (disease name) 503 is set to "subject (confirmation required) ” may be registered. In this case, the notification information of the person corresponding to the disease name aggregation category is subject to risk evaluation by the risk model, but the result requires manual confirmation. If it is manually confirmed that the specified disease name aggregation classification is correct, the result of the risk evaluation by the risk model may be adopted, and if not, the result of the risk evaluation by the risk model may be rejected.

FIG. 6 is an explanatory diagram showing an example of drug definition information 600 managed by the drug definition information management unit 124 according to the first embodiment of this invention.

The information about drugs extracted from the notification information is aggregated into a plurality of predetermined categories according to the drug definition information 600. FIG. That is, the drug definition information 600 is dictionary information that associates descriptions of drugs included in the pre-existing disease information 300 with categories for grouping drugs, and includes drug aggregation categories 601, drug names 602, and evaluation processing categories (drugs) 603. .

The drug aggregation category 601 is information for identifying a category in which drugs are aggregated, and may be a standardized code or the like, or a code or the like uniquely used by an insurance business operator. This drug aggregation category 601 is associated with an explanatory variable input to a risk model for evaluating insurance payment risk in a process described later.

The drug name 602 is information assumed to be extracted from the drug item of the pre-existing disease information 300 . As in the case of the disease name, in order to correctly associate the drug name including ambiguity and inaccuracy described in the notification information with the category in which the drugs are aggregated, the drug name 602 contains information related to the drug name assumed in the notification information. Description is registered.

The evaluation processing category (drug) 603 is information indicating whether or not the value of the drug aggregation category 601 specified according to the drug definition information 600 is to be subject to risk evaluation by the risk model. Since this information is the same as the evaluation processing category (disease name) 503 of the disease name definition information 500, detailed description thereof will be omitted.

FIG. 7 is an explanatory diagram showing an example of surgery definition information 700 managed by the surgery definition information management unit 125 according to the first embodiment of this invention.

Information related to surgery extracted from the notification information is aggregated into a plurality of predetermined categories according to the surgery definition information 700 . That is, the surgery definition information 700 is dictionary information that associates descriptions related to surgery included in the anamnesis information 300 with categories in which surgeries are aggregated. include.

The surgery aggregation category 701 is information for identifying a category where surgery is aggregated, and may be a standardized code or the like, or a code uniquely used by an insurance business operator. This surgery aggregation category 701 is associated with an explanatory variable input to a risk model for evaluating the insurance payment risk in the process described later.

The surgery name 702 is information that is assumed to be extracted from the surgery item of the past disease information 300 . As in the case of the disease name, in order to correctly associate the operation name including ambiguity and inaccuracy described in the notification information with the classification that summarizes the operation name, the operation name 702 is the operation name assumed in the notification information. A description about is registered.

The evaluation processing category (surgery) 703 is information indicating whether or not the value of the surgery aggregate category 701 specified according to the surgery definition information 700 is to be subjected to risk evaluation by the risk model. Since this information is the same as the evaluation processing category (disease name) 503 of the disease name definition information 500, detailed description thereof will be omitted.

FIG. 8 is an explanatory diagram showing an example of hospitalization definition information 800 managed by the hospitalization definition information management unit 126 according to the first embodiment of this invention.

Information about hospitalization extracted from the notification information is aggregated into a plurality of predetermined categories according to the hospitalization definition information 800 . In other words, the hospitalization definition information 800 is dictionary information that associates descriptions related to hospitalization included in the pre-existing disease information 300 with classifications for aggregating hospitalizations. include.

The hospitalization aggregation category 801 is information for identifying a category that aggregates hospitalizations, and may be a standardized code or the like, or a code or the like uniquely used by an insurance company. This hospitalization aggregation classification 801 is associated with an explanatory variable input to a risk model for evaluating insurance payment risk in the process described later.

The number of days of hospitalization 802 is information on the number of days of hospitalization that is assumed to be extracted from the item of surgery in the medical history information 300 . For example, the hospitalization days 802 may be information indicating the range of hospitalization days.

The evaluation processing category (hospitalization) 803 is information indicating whether or not the value of the hospitalization summary category 801 specified according to the hospitalization definition information 800 is to be subject to risk evaluation by the risk model.

In this embodiment, the information on hospitalization is aggregated into a plurality of categories according to the number of days of hospitalization. In the example of FIG. 8, information indicating that the number of days of hospitalization is "0" (that is, the patient was not hospitalized) is aggregated into the hospitalization aggregation category "A1". Information on the number of days of hospitalization from "1" to "14" is aggregated into the hospitalization aggregation category "A2". Information on the number of days of hospitalization from "15" to "31" is aggregated into the hospitalization aggregation category "A3". Information on the number of days of hospitalization of "32" or more is aggregated into the hospitalization aggregation category "A4".

Furthermore, in the example of FIG. 8, the evaluation processing classification of the hospitalization aggregation classifications "A1" and "A2" is "subject", the evaluation processing classification of the hospitalization aggregation classification "A3" is "subject (confirmation required)", and the hospitalization aggregation classification is " A4” evaluation processing category becomes “non-target”. In general, the number of samples of notification information included in training data used to build a risk model tends to decrease as the number of days of hospitalization increases. For this reason, the greater the number of days of hospitalization in the notification information that is input as an explanatory variable into the constructed risk model, the lower the frequency of occurrence of the number of samples of such notification information, and the higher the accuracy of the risk value calculated by the risk model. tend to decline. For this reason, in the above example, although the hospitalization aggregation category "A3" is included in the risk calculation target using the risk model, manual confirmation is required, and the hospitalization aggregation category "A4" does not use the risk model. excluded from the risk calculation.

FIG. 9 is an explanatory diagram showing an example of inspection result definition information 900 managed by the inspection result definition information management unit 127 according to the first embodiment of this invention.

Information such as test results extracted from the health checkup information 400 submitted at the time of notification is aggregated into a plurality of predetermined categories according to the test result definition information 900 . That is, the test result definition information 900 is dictionary information that associates the test results included in the health checkup information 400 with categories for aggregating the test results. 903 included.

The inspection result aggregation category 901 is information for identifying a category in which inspection results are aggregated. This inspection result aggregation section 901 is associated with an explanatory variable input to a risk model for evaluating the insurance payment risk in the process described later.

The test results 902 are test result information that is assumed to be extracted from the health checkup information 400 . For example, the test result 902 may be information specifying a range of values of the test result.

The evaluation processing category (inspection) 903 is information indicating whether or not the value of the inspection result aggregation category 901 specified according to the inspection result definition information 900 is to be subject to risk assessment by the risk model. As with the evaluation processing category (hospitalization) 803, the test result aggregation category corresponding to the range of test result values that appear less frequently in the data used to build the risk model is evaluated as an evaluation processing category (examination) 903. "Target (confirmation required)" or "non-target" may be registered.

FIG. 10 is an explanatory diagram showing an example of explanatory variable definition information 1000 managed by the explanatory variable definition information management unit 128 according to the first embodiment of this invention.

The explanatory variable definition information 1000 is dictionary information that associates a combination of results of aggregation into categories of each item based on the notification information of each person and an explanatory variable. Specifically, the explanatory variable definition information 1000 includes an explanatory variable 1001 , a disease name aggregation category 1002 , a medicine aggregation category 1003 , an examination aggregation category 1004 , an operation aggregation category 1005 and a hospitalization aggregation category 1006 . As a result, the value of the explanatory variable 1001 and the combination of the values from the disease name aggregation category 1002 to the hospitalization aggregation category 1006 are associated.

For example, if the disease name aggregation classification based on the notification information of a certain person is "D1" and there is no corresponding value for the medicine aggregation classification to the hospitalization aggregation classification, the explanatory variable corresponding to the notification information of the person is " E101”. In addition, the disease name aggregation classification based on the notification information of another certain person is "D1", there is no corresponding value from the medicine aggregation classification to the surgery aggregation classification, and the hospitalization aggregation classification is "A1", "A2", or " A3", the explanatory variable corresponding to the notification information of the person is "E102".

FIG. 11 is an explanatory diagram showing an example of an intermediate table 1100 for explanatory variable generation processing managed by the explanatory variable generation result management unit 129 according to the first embodiment of this invention.

The intermediate table 1100 for the explanatory variable generation process stores the information extracted from the notification information of each person based on the disease name definition information 500, the drug definition information 600, the surgery definition information 700, the hospitalization definition information 800, and the test result definition information 900. It is aggregated information and is generated in the course of explanatory variable generation processing.

Specifically, the intermediate table 1100 for the explanatory variable generation processing includes an individual ID 1101, a disease name aggregation category 1102, a medicine aggregation category 1103, an examination aggregation category 1104, an operation aggregation category 1105, a hospitalization aggregation category 1106, and an evaluation processing category (disease name) 1107. , evaluation process category (medicine) 1108 , evaluation process category (examination) 1109 , evaluation process category (surgery) 1110 and evaluation process category (hospitalization) 1111 .

The personal ID 1101 is information for specifying each person, and corresponds to the personal ID 201 of the basic information 200 . Disease name aggregation category 1102, drug aggregation category 1103, examination aggregation category 1104, surgery aggregation category 1105, hospitalization aggregation category 1106, evaluation processing category (disease name) 1107, evaluation processing category (drug) 1108, evaluation processing category (examination) 1109, evaluation A processing category (surgery) 1110 and an evaluation processing category (hospitalization) 1111 indicate the result of aggregating the information of each item of the notification information of each person and the evaluation processing category of each item.

FIG. 12 is an explanatory diagram showing an example of risk calculation target information 1200 managed by the risk calculation target information management unit 130 according to the first embodiment of this invention.

The risk calculation target information 1200 is information for determining whether or not each person's notification information is to be evaluated by the risk model based on the value of the evaluation processing classification of each item of each person's notification information. include. Specifically, the risk calculation target information 1200 includes an evaluation target category 1201, an evaluation processing category (disease name) 1202, an evaluation processing category (drug) 1203, an evaluation processing category (examination) 1204, and an evaluation processing category (surgery) 1205. .

An evaluation processing category (disease name) 1202, an evaluation processing category (medicine) 1203, an evaluation processing category (examination) 1204, and an evaluation processing category (surgery) 1205 are evaluation processing categories extracted from each person's notification information. It corresponds to an evaluation processing category (disease name) 503 , an evaluation processing category (medicine) 603 , an evaluation processing category (examination) 903 and an evaluation processing category (surgery) 703 . The evaluation target category 1201 corresponds to a set of values from the evaluation processing category (disease name) 1202 to the evaluation processing category (surgery) 1205. The final evaluation target category of the notification information of each person (that is, the risk information indicating whether or not to be evaluated by the model). The value of the evaluation target category 1201 is one of “target”, “target (confirmation required)”, and “non-target”, as with the evaluation processing categories of individual items.

For example, when the evaluation processing classification of all items extracted from a certain person's notification information is "target", the person's notification information may be determined as an evaluation target by the risk model. In addition, if the evaluation processing classification of at least one item extracted from a certain person's notification information is "target (confirmation required)" and the evaluation processing classification of all remaining items is "target", the notification of the person The information is subject to evaluation by risk models, but may be determined to require manual review. Further, when the evaluation processing category of at least one item extracted from the notification information of a certain person is "non-target", it may be determined that the notification information of the person is excluded from the evaluation target of the risk model.

However, the criteria as described above are only examples, and other criteria may be applied. In addition, in this embodiment, as described above, determination is made in three stages of "target", "target (confirmation required)" and "non-target". Only two stages, or only two stages of "subject" and "not subject" may be determined.

FIG. 13 is an explanatory diagram showing an example of explanatory variable generation result information 1300 managed by the explanatory variable generation result management unit 129 according to the first embodiment of this invention.

The explanatory variable generation result information 1300 includes information on explanatory variables generated as a result of the explanatory variable generation processing. Specifically, the explanatory variable generation result information 1300 includes individual ID 1301, gender 1302, age 1303, BMI 1304, fasting blood sugar 1305, HbA1c 1306, interview result 1307, indications 1308, E101_1309, E102_1310, E103_1311, E201_1312, E202_131. 3, E203_1314 and an evaluation target category 1315 and the like.

The personal ID 1301 is information for specifying each person, and corresponds to the personal ID 201 of the basic information 200 . Gender 1302 and age 1303 correspond to each person's information extracted from basic information 200 . Indications 1308 from BMI 1304 correspond to each person's information extracted from health checkup information 400 . FIG. 13 is an example, and explanatory variable generation result information 1300 includes necessary items according to the items of basic information 200 and health checkup information 400 .

E101_1309 to E203_1314 indicate explanatory variables specified by collating the information extracted from the notification information of each person with the explanatory variable definition information 1000 from the disease name definition information 500 . For example, "1" is registered in the column corresponding to the specified explanatory variable. Although only some explanatory variables are shown in FIG. 13, all the identified explanatory variables are actually registered.

The evaluation target category 1315 indicates the evaluation target category specified by collating the information extracted from the notification information of each person from the disease name definition information 500 with the test result definition information 900 and the risk calculation target information 1200 .

In practice, there is a case where a single person submits information such as a plurality of disease names and a plurality of drugs as notification information. Therefore, a plurality of explanatory variables may be identified from the announcement information of one person. In that case, "1" is registered in each corresponding explanatory variable column among E101_1309 to E203_1314. Also, one explanatory variable may be identified multiple times from the announcement information of one person. In that case, "1" is registered in the explanatory variable column.

FIG. 14 is an explanatory diagram showing an example of risk model information 1400 managed by the risk model information management unit 131 according to the first embodiment of this invention.

The risk model information 1400 includes a model ID 1401 that identifies a model for assessing risk (risk model), a model name 1402 that indicates what kind of model each model is, and model parameters 1403 that indicate the structure and parameters of the model. including.

A plurality of risk model parameters can be registered in the risk model information 1400, and one of them can be selected and used for risk calculation as necessary.

FIG. 15 is an explanatory diagram showing an example of the classification definition information 1500 managed by the classification definition information management unit 132 according to the first embodiment of this invention.

Classification definition information 1500 is information that associates a risk value calculated by a risk model with a classification that asks whether or not insurance can be purchased, and includes a model ID 1501 , classification conditions 1502 and a classification label 1503 . The model ID 1501 is information specifying a risk model and corresponds to the model ID 1401 of the risk model information 1400 . The classification condition 1502 is a condition applied to the risk value calculated by the risk model, and may be information indicating the range of the risk value, for example. The classification label 1503 is information indicating classification such as whether or not a person who satisfies the condition indicated by the classification condition 1502 can purchase insurance.

In the example of FIG. 10, when the risk value calculated by applying the risk model identified by the model ID “1” to the notification information is 0 or more and less than 0.7, the person who submitted the notification information is the standard If the risk value is 0.7 or more and less than 0.9, the person is classified as a conditional person (that is, a person with a predetermined condition, such as an increase in health care fees). If the risk value is 0.9 or more, the person is classified as a refusal (that is, a person who cannot purchase insurance).

Although the example of FIG. 10 shows the definition of the classification corresponding to the model ID "1", if the risk model information 1400 holds a plurality of risk models, the classification definition information 1500 contains the classification for each risk model. It holds the information that defines it. This enables appropriate classification for each risk model.

FIG. 16 is a flow chart showing an example of processing executed by the disease name information extraction unit 111 according to the first embodiment of this invention.

When the process is started (step 1601), the disease name information extraction unit 111 reads notification information (step 1602). Next, the disease name information extraction unit 111 reads the disease name definition information 500 (step 1603).

Next, the disease name information extraction unit 111 extracts disease name information from the read notification information (step 1604). As a result, for example, the value of the disease name 303 of the pre-existing disease information 300 is extracted. The information about the name of the disease included in the notification information is written by the person who wishes to join the insurance, so it may contain errors. For this reason, the disease name information extraction unit 111 may perform syntactic analysis to correct typographical errors included in the information about the disease name.

Next, the disease name information extraction unit 111 identifies disease name aggregation categories based on the extracted disease name information and the disease name definition information 500 (step 1605). As a result, for example, the value of the disease name aggregation section 501 of the disease name definition information 500 corresponding to the value of the extracted disease name 303 is specified.

Next, the disease name information extraction unit 111 stores the identified disease name aggregation classification (step 1606). As a result, for example, the value of the specified disease name aggregation category 501 and the value of the corresponding evaluation processing category (disease name) 503 are changed to the disease name aggregation category 1102 and the evaluation processing category (disease name) of the intermediate table 1100 for the explanatory variable generation processing, respectively. 1107.

Thus, the processing of the disease name information extraction unit 111 is completed (step 1607).

FIG. 17 is a flow chart showing an example of processing executed by the drug information extraction unit 112 according to the first embodiment of the present invention.

When the process is started (step 1701), the drug information extraction unit 112 reads notification information (step 1702). Next, the drug information extraction unit 112 reads the drug definition information 600 (step 1703).

Next, the drug information extraction unit 112 extracts drug information from the read notification information (step 1704). As a result, for example, the value of the drug name 304 of the pre-existing disease information 300 is extracted. As in the case of the disease name information, the drug information extraction unit 112 may perform syntactic analysis to correct typographical errors included in the drug-related information.

Next, the drug information extraction unit 112 identifies drug aggregation categories based on the extracted drug information and the drug definition information 600 (step 1705). As a result, for example, the value of the drug aggregation section 601 of the drug definition information 600 corresponding to the value of the extracted drug name 304 is specified.

Next, the drug information extraction unit 112 stores the specified drug aggregation category (step 1706). As a result, for example, the value of the specified drug aggregation category 601 and the value of the corresponding evaluation processing category (drug) 603 are changed to the drug aggregation category 1103 and the evaluation processing category (drug) of the intermediate table 1100 of the explanatory variable generation processing, respectively. 1108.

Thus, the processing of the drug information extraction unit 112 is completed (step 1707).

FIG. 18 is a flow chart showing an example of processing executed by the inspection result information extraction unit 113 according to the first embodiment of this invention.

When the process is started (step 1801), the inspection result information extraction unit 113 reads notification information (step 1802). Next, the inspection result information extraction unit 113 reads the inspection result definition information 900 (step 1803).

Next, the inspection result information extraction unit 113 extracts inspection result information from the read notification information (step 1804). As a result, for example, information corresponding to the test results included in the health checkup information 400 is extracted.

Next, the inspection result information extraction unit 113 identifies inspection result aggregation categories based on the extracted inspection result information and the inspection result definition information 900 (step 1805). As a result, for example, the value of the inspection result aggregation section 901 of the inspection result definition information 900 corresponding to the extracted inspection result is specified.

Next, the inspection result information extraction unit 113 stores the specified inspection result aggregation classification (step 1806). As a result, for example, the value of the specified inspection result aggregation category 901 and the value of the corresponding evaluation processing category (inspection) 903 are changed to the inspection aggregation category 1104 and the evaluation processing category (inspection) of the intermediate table 1100 for explanatory variable generation processing, respectively. ) 1109 .

Thus, the processing of the inspection result information extraction unit 113 is completed (step 1807).

FIG. 19 is a flow chart showing an example of processing executed by the surgery information extraction unit 114 according to the first embodiment of the present invention.

When the process starts (step 1901), the surgery information extraction unit 114 reads notification information (step 1902). Next, the surgery information extraction unit 114 reads the surgery definition information 700 (step 1903).

Next, the surgery information extraction unit 114 extracts surgery information from the read notification information (step 1904). As a result, for example, the value of surgery 307 in the pre-existing disease information 300 is extracted.

Next, the surgery information extracting unit 114 identifies a combined surgery section based on the extracted surgery information and the surgery definition information 700 (step 1905). As a result, for example, the value of the surgery aggregation section 701 of the surgery definition information 700 corresponding to the value of the extracted surgery 307 is specified.

Next, the surgery information extraction unit 114 stores the identified surgery-intensive classification (step 1906). As a result, for example, the value of the identified surgery-intensive section 701 and the value of the evaluation processing section (surgery) 703 corresponding thereto are changed to the surgery-intensive section 1105 and the evaluation processing section (surgery) of the intermediate table 1100 for explanatory variable generation processing, respectively. 1110.

This completes the processing of the surgery information extraction unit 114 (step 1907).

FIG. 20 is a flow chart showing an example of processing executed by the hospitalization information extraction unit 115 according to the first embodiment of this invention.

When the process starts (step 2001), the hospitalization information extractor 115 reads notification information (step 2002). Next, the hospitalization information extraction unit 115 reads the hospitalization definition information 800 (step 2003).

Next, the hospitalization information extraction unit 115 extracts hospitalization information from the read notification information (step 2004). As a result, for example, the values of the date of admission 305 and the date of discharge 306 of the pre-existing disease information 300 are extracted.

Next, the hospitalization information extraction unit 115 identifies the hospitalization aggregation category based on the extracted hospitalization information and the hospitalization definition information 800 (step 2005). As a result, for example, the value of the hospitalization aggregation section 801 of the hospitalization definition information 800 corresponding to the number of days of hospitalization identified from the values of the extracted hospitalization date 305 and discharge date 306 is identified.

Next, the hospitalization information extraction unit 115 stores the specified hospitalization aggregation category (step 2006). As a result, for example, the value of the identified hospitalization aggregation category 801 and the value of the evaluation processing category (hospitalization) 803 corresponding thereto are changed to the hospitalization aggregation category 1106 and the evaluation processing category (hospitalization) of the intermediate table 1100 for explanatory variable generation processing, respectively. 1111.

Thus, the processing of the hospitalization information extraction unit 115 is completed (step 2007).

FIG. 21 is a flow chart showing an example of processing executed by the explanatory variable information generation unit 116 according to the first embodiment of this invention.

When the process is started (step 2101), the explanatory variable information generation unit 116 reads the aggregate classification result (step 2102). For example, the explanatory variable information generation unit 116 may read the intermediate table 1100 of the explanatory variable generation process.

Next, the explanatory variable information generating unit 116 identifies the explanatory variable by matching the explanatory variable definition information 1000 with the read intermediate table 1100 of the explanatory variable generation process (step 2103).

Next, the explanatory variable information generating unit 116 groups the information extracted from the notification information and the explanatory variables obtained as a result of matching by grouping them by the ID of each person (step 2104).

Next, the explanatory variable information generating unit 116 stores the grouped information as the explanatory variable generation result information 1300 (step 2105).

The processing of the explanatory variable information generation unit 116 is thus completed (step 2105).

FIG. 22 is a flow chart showing an example of processing executed by the risk calculation unit 117 according to the first embodiment of this invention.

When the process starts (step 2201), the risk calculator 117 sets the conditions for the risk calculation process (step 2202). The conditions set here may include, for example, specification of notification information for risk calculation, risk models to be used, data items to be aggregated, and the like.

Next, the risk calculator 117 reads explanatory variable information (step 2203). For example, the risk calculator 117 may read explanatory variable generation result information 1300 .

Next, the risk calculation unit 117 calculates the risk by inputting the explanatory variables included in the explanatory variable generation result information 1300 into the risk model (step 2204).

Next, the risk calculator 117 stores the calculated risk value in the storage medium 106 or database 107 (step 2205). The processing of the risk calculation unit 117 is thus completed (step 2206).

FIG. 23 is a flow chart showing an example of processing executed by the risk determination unit 118 according to the first embodiment of this invention.

When the process starts (step 2301), the risk determination section 118 reads the risk value calculated by the risk calculation section 117 (step 2302).

Next, the risk determination unit 118 determines whether the risk calculation result based on the risk model of each person is subject to risk determination (for example, “subject” or It is classified into those corresponding to "object (confirmation required)") and those not being object (for example, those corresponding to "non-object") (step 2303).

Next, the risk determination unit 118 matches the risk calculation result of each person who is the target of risk determination with the classification definition information 1500 corresponding to the risk model used for the risk calculation, thereby adding a classification label ( step 2304). Specifically, the value of the classification label 1503 corresponding to the value of the classification condition 1502 satisfied by the risk value calculated for each person is assigned.

Next, the risk determination unit 118 stores the assigned classification label in the storage medium 106 or database 107 (step 2305). At this time, if the risk determination unit 118 determines that it is “target (confirmation required)” based on the risk calculation target information 1200, the information indicating that fact is stored in the storage medium 106 or the database 107 together with the classification label. may be stored. Also, the risk determination unit 118 may output these pieces of information via the output unit 103 or the communication unit 108 (see FIG. 27).

The processing of the risk determination unit 118 is thus completed (step 2306).

Next, an example of a user interface provided by the information analysis support system 101 when executing the processes shown in FIGS. 16 to 23 will be described with reference to FIGS. 24 to 27. FIG.

FIG. 24 is an explanatory diagram showing an example of a user interface that displays notification information in the process of generating explanatory variables by the information analysis support system 101 according to the first embodiment of this invention.

An explanatory variable generation screen 2400 shown in FIG. 24 is an example of display data output by the information analysis support system 101. For example, an announcement information designation section 2401, an announcement information read execution button 2402, an aggregation processing target designation section 2403, an aggregation It includes a process execution button 2404 , an explanatory variable generation process execution button 2405 and an information display section 2406 .

Note that this display data may be output as an image by the output unit 103 or may be output by the communication unit 108 . In the latter case, the display data is transferred from the communication unit 108 via a network (not shown) to an external device (for example, a terminal device used by a user, not shown), and output as an image by the external device. good. In this case, information input through the screen is input using an input unit (not shown) of the external device and input to the information analysis support system 101 via the network and communication unit 108 . The same applies to other screens to be described later.

Information designating the target notification information to be read is input to the notification information specifying section 2401 . When the user inputs information designating the notification information to the notification information designating section 2401 and operates the notification information read execution button 2402, the designated notification information is read (see steps 1602, 1702, 1802, 1902 and 2002). The read notification information 2407 is displayed on the information display portion 2406 . Announcement information 2407 may be similar to preexisting disease information 300 and medical examination information 400, for example.

FIG. 25 is an explanatory diagram showing an example of a user interface that displays the result of the aggregation process in the process of generating explanatory variables by the information analysis support system 101 according to the first embodiment of this invention.

For example, after the notification information is read as shown in FIG. Item aggregation processing is performed (see steps 1605, 1705, 1805, 1905 and 2005). The information display portion 2406 displays an aggregation processing result 2501 . The aggregation processing result 2501 may be similar to the intermediate table 1100 of the explanatory variable generation processing, for example.

FIG. 26 is an explanatory diagram showing an example of a user interface that displays the results of explanatory variable generation processing in the processing of generating explanatory variables by the information analysis support system 101 according to the first embodiment of this invention.

For example, after notification information is read as shown in FIG. 24 and aggregation processing is executed as shown in FIG. 25, when the user operates an explanatory variable generation processing execution button 2405, explanatory variable generation processing is executed (see 21). An explanatory variable generation result 2601 is displayed on the information display section 2406 . The explanatory variable generation result 2601 may be similar to the explanatory variable generation result information 1300, for example.

FIG. 27 is an explanatory diagram showing an example of a user interface that displays the results of risk analysis executed by the information analysis support system 101 according to the first embodiment of this invention.

The risk analysis execution screen 2700 shown in FIG. 27 includes, for example, an explanatory variable designation section 2701, an explanatory variable read execution button 2702, a risk model designation section 2703, a classification condition designation section 2704, a risk analysis execution button 2705, and an information display section 2706. .

The explanatory variable designation unit 2701 receives input of information for designating the explanatory variable to be read. When the user inputs information for specifying an explanatory variable to the explanatory variable specifying section 2701 and operates the explanatory variable read execution button 2702, the specified explanatory variable is read (see step 2203 in FIG. 22). For example, explanatory variable generation result information 1300 may be read.

The risk model designation unit 2703 and the classification condition designation unit 2704 receive input of information designating the risk model used for calculating the risk value and information designating the classification condition based on the risk value, respectively. A risk model and a classification condition are designated according to the user's operation on the risk model designation section 2703 and the classification condition designation section 2704 . For example, one of the risk models registered in the risk model information 1400 and one of the classification definitions registered in the classification definition information 1500 may be designated.

When the user operates the risk analysis execution button 2705, risk analysis is executed based on the designated explanatory variables, the designated risk model, and the designated classification conditions (step 2204 onward in FIG. 22 and see FIG. 23). A risk analysis result 2707 is displayed in the information display section 2706 . The risk analysis result 2707 is stored in the storage medium 106 or the database 107 as a result of processing by the risk calculation unit 117 and the risk determination unit 118, and includes, for example, an individual ID 2707A, a risk value 2707B, a classification result 2707C, and confirmation necessity. 2707D included.

Personal ID 2707A is information for specifying each person, and corresponds to personal ID 201 of basic information 200 . The risk value 2707B is a risk value calculated by inputting explanatory variables generated by the risk calculation unit 117 from each person's notification information into the risk model. The classification result 2707C is the classification of each person determined by comparing the risk value calculated for each person with the classification definition information 1500 by the risk determination unit 118 .

The confirmation necessity 2707D indicates whether or not the evaluation target category of the explanatory variable generated from the notification information of each person is "target (confirmation required)". If the value of the confirmation necessity 2707D is “confirmation required”, it indicates that the evaluation target classification of the explanatory variable is “target (confirmation required)”, and if the value of the confirmation necessity 2707D is blank (“−”), If there is, it indicates that the evaluation target category of the explanatory variable is "target". Note that the explanatory variables whose evaluation target classification is "non-target" are excluded from the target of analysis by the risk model, so the result is not displayed as the risk analysis result 2707. FIG.

The user refers to the risk analysis result 2707, adopts the value of the classification result 2707C for which the value of the corresponding confirmation necessity 2707D is not "confirmation required", and adopts the value of the corresponding confirmation necessity 2707D as "confirmation required". The value of the classification result 2707C can be adopted after confirming that the aggregation at the time of explanatory variable generation was appropriate.

Note that the functions of the information analysis support system 101 of the first embodiment described above may be provided via an API (Application Programming Interface). For example, when the information analysis support system 101 receives notification information via a network (not shown) connected to the communication unit 108, it stores it in the database 107 and executes the processes shown in FIGS. 24 to 27 may be output via the network.

According to the first embodiment described above, by appropriately aggregating the values of the items of the notification information, it is possible to automate the risk evaluation based on the notification information including various expressions using the risk model. In addition, if the notification information satisfies predetermined conditions, it is excluded from the automation of risk assessment using the risk model, or risk assessment is performed using the risk model, but manual confirmation is required to ensure the accuracy of the risk assessment. can do.

Next, Example 2 of the present invention will be described. Except for the differences described below, the parts of the system of Example 2 have the same functions as the like-numbered parts of Example 1 shown in FIGS. are omitted.

FIG. 28 is a block diagram showing an example of the configuration of the information analysis support system 101 of Example 2 of the present invention.

In the information analysis support system 101 of Example 2, the storage medium 106 further has a payment determination unit 119 . The database 107 further holds a contract information management section 133 , a billing information management section 134 , a payment classification definition information management section 135 and a payment judgment result information management section 136 . Note that the function of the payment determination unit 119 is implemented by the CPU 104 executing a program stored in the storage medium 106, similarly to the functions of the other units.

FIG. 29 is an explanatory diagram showing an example of contract information 2900 managed by the contract information management unit 133 according to the second embodiment of this invention.

The contract information 2900 is basic information related to the insurance product of the insurance company contracted by each person.

Specifically, the contract information 2900 includes an individual ID 2901 that identifies each person who has subscribed to the insurance product, a gender 2902 that identifies the sex of each person, a contracted insurance product 2903 that identifies the insurance product contracted by each person, It includes a daily hospitalization amount 2904 that indicates the amount paid per day of hospitalization in each insurance product, and a surgery benefit rate 2905 that indicates the rate of payment when surgery is performed. The contract information 2900 described above is an example, and the contract information 2900 may include various information related to insurance products contracted by each person as necessary.

FIG. 30 is an explanatory diagram showing an example of billing information 3000 managed by the billing information management unit 134 according to the second embodiment of this invention.

Claim information 3000 is information extracted from claims for payment of insurance claims made by insurance subscribers to insurance companies. It may be held as billing information 3000 . Billing information 3000 includes personal ID 3001 , billing ID 3002 , billing date and time 3003 , billing details 3004 , number of hospital stays 3005 , and surgery 3006 .

The personal ID 3001 is information for specifying each person, and corresponds to the personal ID 2901 of the contract information 2900 . The billing ID 3002 is information identifying the billing from each person. The billing date and time 3003 is information specifying the date and time when the billing was made by each person.

The request content 3004 indicates the content of the request from each person. For example, the contents written by each person in the request form may be registered as the request contents 3004 as they are. Specifically, the claim content 3004 may include the event (eg, disease name, etc.) that is the reason for the claim for insurance payment.

The hospitalization days 3005 indicates the number of days when each person is hospitalized. Surgery 3006 indicates whether or not each person underwent surgery and, if so, what kind of surgery he underwent.

Although omitted in FIG. 30, the billing information 3000 may include information indicating the drug prescribed to each person and information indicating the test value of each person.

FIG. 31 is an explanatory diagram showing an example of payment category definition information 3100 managed by the payment category definition information management unit 135 according to the second embodiment of this invention.

The payment category definition information 3100 is dictionary information that associates a combination of the results of aggregation into categories of each item based on the billing information 3000 of each person and the payment category. Specifically, the payment category definition information 3100 includes a payment category 3101 , a disease name aggregation category 3102 , a medicine aggregation category 3103 , an examination aggregation category 3104 , an operation aggregation category 3105 and a hospitalization aggregation category 3106 . As a result, the value of the payment category 3101 and the combination of the values from the disease name aggregation category 3102 to the hospitalization aggregation category 3106 are associated.

For example, if the disease name aggregation classification based on the billing information 3000 of a certain person is "D1" and there is no corresponding value for the medicine aggregation classification to the hospitalization aggregation classification, the payment classification corresponding to the billing information 3000 of the person is becomes "P101". A claim payment amount can be determined based on the specified payment category.

FIG. 32 is an explanatory diagram showing an example of payment determination result information 3200 managed by the payment determination result information management unit 136 according to the second embodiment of this invention.

The payment judgment result information 3200 includes an individual ID 3201, a payment category 3202, an insurance amount paid 3203, an evaluation target category 3204, a disease name aggregation category 3205, a drug aggregation category 3206, an examination aggregation category 3207, an operation aggregation category 3208, and a hospitalization aggregation category 3209. .

The personal ID 3201 is information for specifying each person, and corresponds to the personal ID 2901 of the contract information 2900 . The payment classification 3202 indicates the payment classification determined by the processing of the payment determination unit 119, which will be described later. The insurance payment amount 3203 indicates the payment amount of the insurance money determined according to the determined payment category. The evaluation target category 3204 indicates the evaluation target category determined by the processing of the payment determination unit 119, which will be described later. This is determined in the same manner as the evaluation target classification in the first embodiment.

A disease name aggregated section 3205 to a hospitalization aggregated section 3209 respectively show the result of aggregating the information on the disease name, drug, test value, surgery, and hospitalization extracted from the contract information 2900 into predetermined categories. Aggregation into these categories is performed in the same manner as in the first embodiment. The value of the payment category 3101 corresponding to the combination of the disease name aggregation category 3102 to the hospitalization aggregation category 3106 matching the combination of the values of the disease name aggregation category 3205 to the hospitalization aggregation category 3209 is registered as the payment category 3202 .

FIG. 33 is a flow chart showing an example of processing executed by the payment determination unit 119 according to the second embodiment of this invention.

When the process is started (step 3301), the payment determination section 119 reads the billing information 3000 (step 3302). Next, the payment determination unit 119 sequentially extracts disease name information, drug information, test result information, hospitalization information, and surgery information from the billing information 3000 (steps 3303 to 3307).

Next, the payment determination unit 119 performs payment determination on the extracted information (step 3308). Specifically, the payment determination unit 119 first performs aggregation processing into predetermined categories for the extracted disease name information, drug information, test result information, surgery information, and hospitalization information. This is the same as the processing executed by the disease name information extraction unit 111, the drug information extraction unit 112, the test result information extraction unit 113, the surgery information extraction unit 114, and the hospitalization information extraction unit 115 of the first embodiment (steps 1605 and 1705). , 1805, 1905 and 2002). The categories thus aggregated are registered in the disease name aggregation category 3205, the drug aggregation category 3206, the examination aggregation category 3207, the surgery aggregation category 3208, and the hospitalization aggregation category 3209 of the payment judgment result information 3200.

Then, the payment determination unit 119 identifies a combination of the disease name aggregation categories 3102 to the hospitalization aggregation categories 3106 that match the combination of the values of the disease name aggregation categories 3205 to the hospitalization aggregation categories 3209, and determines the value of the payment category 3101 corresponding to the specified combination. is specified as the payment determination result.

Next, the payment determination unit 119 stores the identified payment determination result in the payment category 3202 of the payment determination result information 3200 (step 3309). Thus, the processing of the payment determination unit 119 is completed (step 3310).

Next, an example of a user interface provided by the information analysis support system 101 of Example 2 will be described with reference to FIGS. 34 and 35. FIG.

FIG. 34 is an explanatory diagram showing an example of a user interface that displays billing information in the payment determination process by the information analysis support system 101 according to the second embodiment of this invention.

A payment determination screen 3400 shown in FIG. 34 is an example of display data output by the information analysis support system 101, and includes, for example, a billing information designation section 3401, a billing information read execution button 3402, an aggregation processing target designation section 3403, and an aggregation processing. It includes an execution button 3404 , a payment judgment processing execution button 3405 and an information display section 3406 .

Information specifying billing information to be read is input to the billing information designation section 3401 . When the user inputs information designating billing information to the billing information designating section 3401 and operates the billing information read execution button 3402, the designated billing information is read (see step 3302). The read billing information 3407 is displayed in the information display portion 3406 . Billing information 3407 may be similar to billing information 3000, for example.

FIG. 35 is an explanatory diagram showing an example of a user interface on which the information analysis support system 101 according to the second embodiment of this invention displays the result of payment determination processing.

For example, after the billing information is read as shown in FIG. 34, when the user inputs information for designating the information items to be aggregated into the aggregation processing target designation field 3403 and operates the aggregation processing execution button 3404, the payment judgment processing is performed. In (step 3308), the aggregation processing of the specified items is executed.

Further, when the user operates the payment determination process execution button 3405, the process of specifying the payment determination result by matching the combination of the aggregated categories among the payment determination processes (step 3308) is executed. A judgment processing result 3501 is displayed on the information display portion 3406 . The determination processing result 3501 may be the same as the payment determination result information 3200, for example.

Note that the functions of the information analysis support system 101 of the second embodiment described above may be provided via an API (Application Programming Interface) as in the first embodiment. For example, when the information analysis support system 101 receives the billing information via the network connected to the communication unit 108, it stores it in the database 107, executes the processing shown in FIG. Data necessary for displaying the information shown in may be output via a network.

Further, the information analysis support system 101 shown in FIG. 28 has a function of risk analysis similar to that of the first embodiment in addition to the function of specifying the payment category based on the billing information described above. However, such a system configuration is an example, and the information analysis support system 101 of the second embodiment may not have the risk analysis function of the first embodiment.

According to the second embodiment described above, it is possible to automate the determination of insurance payment while ensuring accuracy.

Moreover, the system of the embodiment of the present invention may be configured as follows.

(1) An information analysis support method executed by a computer system (for example, information analysis support system 101), wherein the computer system includes a processor (for example, CPU 104) and a storage device (for example, storage medium 106 or database 107), and the storage device includes a risk model for calculating a health-related risk value, and dictionary information ( For example, at least one of disease name definition information 500, drug definition information 600, surgery definition information 700, hospitalization definition information 800, and test result definition information 900), a combination of one or more of the aggregation categories, and explanatory variables of the risk model and explanatory variable definition information (for example, explanatory variable definition information 1000) that associates values with values, and the information analysis support method includes a first procedure (for example, steps 1604, 1704, 1804, 1904 and/or 2004); (for example, at least one of steps 1605, 1705, 1805, 1905, and 2005); A third procedure (eg, steps 2102-2105) of identifying a value, and a fourth procedure (eg, step 2204), and

As a result, the values of the items of the notification information are appropriately aggregated, and the risk evaluation based on the notification information including various expressions can be automated using the risk model.

(2) In (1) above, the health-related information includes information describing a disease name (eg, disease name 303), information describing a drug (eg, drug name 304), and health-related test value information (eg, BMI 403 to HbA1c 405), information describing surgery (for example, surgery 307), and information describing the period of hospitalization (for example, date of admission 305 and date of discharge 306). (for example, disease name definition information 500), information that associates a plurality of descriptions of drugs with one of the aggregated categories (for example, drug definition information 600), and the range of test values related to health. information (for example, test result definition information 900) associated with the aggregation section, information (for example, surgery definition information 700) that associates a plurality of descriptions related to the surgery with one aggregation section, and the range of the length of the hospitalization period, It includes at least one of the information (for example, the hospitalization definition information 800) associated with the aggregation category.

By this, the information about health can be collected appropriately.

(3) In (2) above, the input information is information included in notification information submitted by a person who wishes to enroll in an insurance product, and the health-related risk value is insurance money in the insurance product. The storage device further holds classification definition information (for example, classification definition information 1500) for classifying the person based on the risk value, and the information analysis support method further includes a fifth procedure (eg steps 2303-2304) in which the processor classifies the person based on the calculated risk value and the classification definition information.

This allows automation of the assessment of the risk of a person wishing to enroll in an insurance product.

(4) In (3) above, the dictionary information includes, for each of the associations between the health-related information and the aggregated categories, the identified aggregated categories as targets for calculating the risk value based on the risk model. information (for example, at least one of the evaluation processing category (disease name) 503, the evaluation processing category (drug) 603, the evaluation processing category (surgery) 703, the evaluation processing category (hospitalization) 803, and the evaluation processing category (examination) 903 ), and in the second step, the processor determines whether the identified aggregated category is a target for calculating the risk value based on the risk model, and determines whether the identified aggregated category is the risk model , the explanatory variable specified based on the specified aggregation category is excluded from targets of the fourth procedure and the fifth procedure.

This ensures a certain degree of accuracy for the automated risk assessment.

(5) In (4) above, if the accuracy of association between the description regarding the disease name and the aggregated classification is lower than a predetermined standard, the dictionary information includes the accuracy of association between the description regarding the drug and the aggregated classification. is lower than a predetermined standard, or if the accuracy of the correspondence between the description about the surgery and the aggregated category is lower than a predetermined standard, the identified aggregated category calculates the risk value based on the risk model including information indicating that it is not subject to

This ensures a certain degree of accuracy for the automated risk assessment.

(6) In the above (4), the dictionary information includes the aggregation classification corresponding to the range of the health-related test values whose appearance frequency is lower than a predetermined standard, or the range of the length of the hospitalization period. Information indicating that the specified aggregated category is not subject to calculation of the risk value based on the risk model is included for the aggregated category corresponding to a range in which the appearance frequency is lower than a predetermined standard.

This ensures a certain degree of accuracy for the automated risk assessment.

(7) In (3) above, the dictionary information is information indicating whether to request confirmation of the identified aggregation classification for each of the associations between the health-related information and the aggregation classification (e.g., evaluation processing classification (disease name) 503, evaluation processing category (medicine) 603, evaluation processing category (surgery) 703, evaluation processing category (hospitalization) 803, and evaluation processing category (examination) 903), and in the second procedure, The processor determines whether confirmation of the identified aggregation classification is requested, and the information analysis support method causes the processor to display a result of classifying the person and confirm the identified aggregation classification. is requested, a sixth procedure (e.g., step 2305) of outputting information indicating that confirmation of said identified aggregated partition is requested.

This ensures a certain degree of accuracy for the automated risk assessment.

(8) In (7) above, if the accuracy of association between the description about the disease name and the aggregated classification is lower than a predetermined standard, the dictionary information includes the accuracy of association between the description about the drug and the aggregated classification. is lower than a predetermined standard, or if the accuracy of the correspondence between the description about the surgery and the aggregated section is lower than a predetermined standard, including information indicating that the identified aggregated section is requested to be confirmed .

This ensures a certain degree of accuracy for the automated risk assessment.

(9) In the above (7), the dictionary information includes the aggregation classification corresponding to the range of the health-related test values whose appearance frequency is lower than a predetermined standard, or the range of the length of the hospitalization period. It includes information indicating that confirmation of the identified aggregated category is requested for the aggregated category corresponding to a range in which the appearance frequency is lower than a predetermined standard.

This ensures a certain degree of accuracy for the automated risk assessment.

(10) An information analysis support method executed by a computer system (for example, information analysis support system 101), wherein the computer system includes a processor (for example, CPU 104) and a storage device (for example, storage medium 106 or database 107), and the storage device has dictionary information (for example, disease name definition information 500, drug definition information 600, at least one of the surgery definition information 700, the hospitalization definition information 800, and the test result definition information 900), the combination of one or more of the aggregate classifications, and the payment classification definition information (for example, the payment classification definition information 3100), and the information analysis support method includes a first procedure (for example, at least one of steps 3303 to 3307) in which the processor extracts the health-related information from the information for claiming insurance payment; , a second step (e.g., step 3308) in which the processor identifies one or more of the aggregate categories corresponding to the extracted health-related information based on the dictionary information; and a third procedure (eg, step 3308) of identifying the payment class corresponding to the identified combination of one or more aggregate classes based on.

As a result, the values of items of billing information are appropriately aggregated, and determination of payment type based on billing information including various expressions can be automated.

(11) In (10) above, the health-related information includes information describing a disease name (eg, disease name 303), information describing a drug (eg, drug name 304), and health-related test value information (eg, BMI 403 to HbA1c 405), information describing surgery (for example, surgery 307), and information describing the period of hospitalization (for example, date of admission 305 and date of discharge 306). (for example, disease name definition information 500), information that associates a plurality of descriptions of drugs with one of the aggregated categories (for example, drug definition information 600), and the range of test values related to health. information (for example, test result definition information 900) associated with the aggregation section, information (for example, surgery definition information 700) that associates a plurality of descriptions related to the surgery with one aggregation section, and the range of the length of the hospitalization period, It includes at least one of the information (for example, the hospitalization definition information 800) associated with the aggregation category.

By this, the information about health can be collected appropriately.

(12) In (11) above, the dictionary information is such that, for each of the associations between the health-related information and the aggregated categories, the specified aggregated category is a specified payment category based on the payment category definition information. Information indicating whether it is a target (for example, at least evaluation processing category (disease name) 503, evaluation processing category (drug) 603, evaluation processing category (surgery) 703, evaluation processing category (hospitalization) 803, and evaluation processing category (examination) 903 either), and in the second step, the processor determines whether the specified aggregation category is a specified target of the payment category based on the payment category definition information , if the identified aggregated classification is not a specified target of the payment classification based on the payment classification definition information, the identified aggregated classification is excluded from the target of the third procedure .

As a result, predetermined accuracy can be ensured for the automated determination of the payment category.

(13) In (11) above, the dictionary information is information indicating whether to request confirmation of the specified aggregation classification for each of the associations between the health-related information and the aggregation classification (e.g., evaluation processing classification (disease name) 503, evaluation processing category (medicine) 603, evaluation processing category (surgery) 703, evaluation processing category (hospitalization) 803, and evaluation processing category (examination) 903), and in the second procedure, The processor determines whether confirmation of the identified aggregated classification is requested, and the information analysis support method is such that the processor displays the identified payment classification and confirms the identified aggregated classification. is requested, a fourth step of outputting information indicating that confirmation of the identified aggregated partition is requested.

As a result, predetermined accuracy can be ensured for the automated determination of the payment category.

In addition, the present invention is not limited to the above-described embodiments, and includes various modifications. For example, the above embodiments have been described in detail for better understanding of the present invention, and are not necessarily limited to those having all the configurations described. Moreover, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Moreover, it is possible to add, delete, or 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, for example, by designing a part or all of them using an integrated circuit. Moreover, each of the above configurations, functions, etc. may be realized by software by a processor interpreting and executing a program for realizing each function. Information such as programs, tables, files, etc. that realize each function is stored in storage devices such as non-volatile semiconductor memories, hard disk drives, SSDs (Solid State Drives), or computer-readable non-volatile memory such as IC cards, SD cards, DVDs, etc. It can be stored on a temporary data storage medium.

Also, the control lines and information lines indicate those considered necessary for explanation, and not necessarily all the control lines and information lines are indicated on the product. In fact, it may be considered that almost all configurations are interconnected.

101 information analysis support system 102 input unit 103 output unit 104 CPU
105 memory 106 storage medium 107 database 108 communication unit 111 disease name information extraction unit 112 drug information extraction unit 113 test result information extraction unit 114 surgery information extraction unit 115 hospitalization information extraction unit 116 explanatory variable information generation unit 117 risk calculation unit 118 risk determination unit 119 Payment determination unit 121 Basic information management unit 122 Health information management unit 123 Disease name definition information management unit 124 Drug definition information management unit 125 Surgery definition information management unit 126 Hospitalization definition information management unit 127 Examination result definition information management unit 128 Explanatory variable definition information Management unit 129 Explanatory variable generation result management unit 130 Risk calculation target information management unit 131 Risk model information management unit 132 Classification definition management unit 133 Contract information management unit 134 Billing information management unit 135 Payment classification definition information management unit 136 Payment judgment result information management Department

Claims (14)

An information analysis support method executed by a computer system, comprising:
The computer system has a processor and a storage device connected to the processor,
The storage device
a risk model for calculating health-related risk values;
Dictionary information that associates health-related information with at least one of a plurality of aggregation categories for aggregating the health-related information;
holding explanatory variable definition information that associates one or more combinations of the aggregation categories with the values of the explanatory variables of the risk model;
The information analysis support method includes:
a first step in which the processor extracts the health-related information from input information;
a second step in which the processor identifies one or more of the aggregated categories corresponding to the extracted health-related information based on the dictionary information;
a third procedure in which the processor identifies the value of the explanatory variable corresponding to the identified combination of the one or more aggregation categories based on the explanatory variable definition information;
and a fourth step in which the processor calculates the risk value corresponding to the identified explanatory variable value based on the risk model. The information analysis support method according to claim 1,
The health information includes at least one of information describing disease names, information describing drugs, information about test values regarding health, information describing surgery, and information describing hospitalization periods,
The dictionary information includes information that associates multiple descriptions of the disease name with one aggregated category, information that associates multiple descriptions of the drug with one aggregated category, and information that associates the range of test values related to health with the aggregated category. An information analysis support method comprising at least one of information, information that associates a plurality of descriptions related to the surgery with one of the aggregated categories, and information that associates a range of the length of the hospital stay with the aggregated category. . The information analysis support method according to claim 2,
The input information is information included in the notification information submitted by the person who wishes to join the insurance product,
The health-related risk value is a value indicating the magnitude of the insurance claim payment risk in the insurance product,
the storage device further retains classification definition information for classifying the person based on the risk value;
The information analysis support method, wherein the processor further includes a fifth step of classifying the person based on the calculated risk value and the classification definition information. The information analysis support method according to claim 3,
The dictionary information includes information indicating whether the specified aggregated category is a target for calculating the risk value based on the risk model for each association between the health-related information and the aggregated category,
In the second step, the processor determines whether the identified aggregation category is a target for calculating the risk value based on the risk model;
If the identified aggregated category is not the target of the risk value calculation based on the risk model, the explanatory variable identified based on the identified aggregated category is the target of the fourth procedure and the fifth procedure. An information analysis support method characterized by being excluded from. The information analysis support method according to claim 4,
In the dictionary information, when the accuracy of the correspondence between the description on the disease name and the aggregated classification is lower than a predetermined standard, when the accuracy of the association between the description on the drug and the aggregated classification is lower than a predetermined standard, or and information indicating that the identified aggregated category is not subject to calculation of the risk value based on the risk model when the accuracy of the correspondence between the description about the surgery and the aggregated category is lower than a predetermined standard. An information analysis support method characterized by: The information analysis support method according to claim 4,
The dictionary information includes the aggregation classification corresponding to the range of the health-related test values in which the frequency of appearance is lower than a predetermined standard, or the range of the length of hospitalization in which the frequency of appearance is lower than the predetermined standard. An information analysis support method, wherein information indicating that the specified aggregated category is not subject to calculation of the risk value based on the risk model is included in the aggregated category corresponding to the range. The information analysis support method according to claim 3,
The dictionary information includes information indicating whether to request confirmation of the specified aggregated classification for each association between the health-related information and the aggregated classification,
In the second procedure, the processor determines whether confirmation of the identified aggregated partition is requested;
In the information analysis support method, the processor displays a result of classifying the person, and if confirmation of the specified aggregation classification is requested, confirmation of the specified aggregation classification is requested. An information analysis support method, further comprising a sixth step of outputting information indicating the. The information analysis support method according to claim 7,
In the dictionary information, when the accuracy of the correspondence between the description on the disease name and the aggregated classification is lower than a predetermined standard, when the accuracy of the association between the description on the drug and the aggregated classification is lower than a predetermined standard, or , an information analysis support method characterized by including information indicating a request for confirmation of the specified aggregated category when the accuracy of the correspondence between the description about the surgery and the aggregated category is lower than a predetermined standard. . The information analysis support method according to claim 7,
The dictionary information includes the aggregation classification corresponding to the range of the health-related test values in which the frequency of appearance is lower than a predetermined standard, or the range of the length of hospitalization in which the frequency of appearance is lower than the predetermined standard. An information analysis support method, comprising: information indicating a request for confirmation of the identified aggregated classification for the aggregated classification corresponding to the range. An information analysis support method executed by a computer system, comprising:
The computer system has a processor and a storage device connected to the processor,
The storage device
Dictionary information that associates health-related information with at least one of a plurality of aggregation categories for aggregating the health-related information;
Holds payment category definition information that associates one or more combinations of the aggregate categories with insurance claim payment categories;
The information analysis support method includes:
a first step in which the processor extracts the health-related information from claim information;
a second step in which the processor identifies one or more of the aggregated categories corresponding to the extracted health-related information based on the dictionary information;
and a third step of identifying the payment classification corresponding to the specified combination of the one or more consolidated classifications, based on the payment classification definition information. The information analysis support method according to claim 10,
The health information includes at least one of information describing disease names, information describing drugs, information about test values regarding health, information describing surgery, and information describing hospitalization periods,
The dictionary information includes information that associates multiple descriptions of the disease name with one aggregated category, information that associates multiple descriptions of the drug with one aggregated category, and information that associates the range of test values related to health with the aggregated category. An information analysis support method comprising at least one of information, information that associates a plurality of descriptions related to the surgery with one of the aggregated categories, and information that associates a range of the length of the hospital stay with the aggregated category. . The information analysis support method according to claim 11,
The dictionary information includes, for each of the associations between the health-related information and the aggregate classification, information indicating whether the specified aggregate classification is a specified target of the payment classification based on the payment classification definition information. ,
In the second step, the processor determines whether the identified aggregated classification is a specified target of the payment classification based on the payment classification definition information,
If the specified aggregation category is not a target of the specified aggregation category based on the payment category definition information, the specified aggregation category is excluded from the target of the third procedure. An information analysis support method characterized by: The information analysis support method according to claim 11,
The dictionary information includes information indicating whether to request confirmation of the specified aggregated classification for each association between the health-related information and the aggregated classification,
In the second procedure, the processor determines whether confirmation of the identified aggregated partition is requested;
In the information analysis support method, when the processor displays the specified payment classification and confirmation of the specified aggregation classification is requested, confirmation of the specified aggregation classification is requested. An information analysis support method, further comprising a fourth step of outputting information indicating the. An information analysis support system,
a processor and a storage device connected to the processor;
The storage device
a risk model for calculating health-related risk values;
Dictionary information that associates health-related information with at least one of a plurality of aggregation categories for aggregating the health-related information;
holding explanatory variable definition information that associates one or more combinations of the aggregation categories with the values of the explanatory variables of the risk model;
The processor
extracting the health-related information from the input information;
Based on the dictionary information, identify one or more aggregate categories corresponding to the extracted health-related information;
Based on the explanatory variable definition information, identify the value of the explanatory variable corresponding to the identified combination of the one or more aggregation categories;
An information analysis support system, wherein the risk value corresponding to the specified explanatory variable value is calculated based on the risk model.

Images