JP4171224B2 - Risk diagnosis system, risk diagnosis method and risk diagnosis program - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a system capable of diagnosing a user's risk and presenting a diagnosis result by answering a diagnosis item presented by the user.
[0002]
[Prior art]
Conventionally, an insurance system that introduces risk diagnosis and optimal insurance based on risk diagnosis is known. In this method, the user can access the insurance system via the Internet, answer the diagnostic items presented by the insurance system, perform the user's risk diagnosis, and introduce the optimum insurance.
[0003]
[Problems to be solved by the invention]
However, in order to receive introduction of insurance introduction based on appropriate risk diagnosis and diagnosis results in the conventional insurance system, it is necessary for the user to input answers to a number of diagnosis items. It was necessary. In addition, the risk changes with time, and it is desirable to be able to present a risk that is currently occurring and a risk that may occur in the future.
[0004]
An object of the present invention is to quantify user input items based on risk categories, diagnose risks, find current risks, and predict future risks.
[0005]
[Means for Solving the Problems]
An object of the present invention is a question item generation database storing various information related to a user, wherein basic information of a user and attribute information of the user associated with an ID for uniquely identifying the user are stored. Question item generation having a user database that stores and stores a response to a user's question item and a diagnosis result based on the answer, and a database for generating a question item that includes an item table that stores the question item for the user A user identification means for identifying a user based on ID included in login information from the user, and a question item for the user from the item table in response to the login from the user. Or an input item presenting means for generating a question item for the user based on the item table and presenting the item. Receive input data indicating user's responses to the selected items, classify them into preset risk categories, quantify them in relation to each risk category, and based on these values, relate to each risk category The input data processing means for calculating the risk level to be generated and generating a diagnosis result including the risk level, the current diagnosis result generated by the input data processing means, and the past regarding the user in the user database And a first risk diagnosis means for generating a first diagnosis result indicating a risk from the past to the present based on the comparison, and a risk diagnosis system comprising: Is achieved.
[0006]
According to the present invention, based on the past diagnosis result and the current diagnosis result, the risk that is considered to be present is presented. Therefore, a finer diagnosis result can be obtained. Further, by using past diagnosis results, it is possible to prevent an excessive increase in the number of items for which a user is requested to answer in diagnosis.
[0007]
In a preferred embodiment, there is further provided a second risk diagnosis means for generating a second diagnosis result indicating a future risk estimation result based on the current diagnosis result generated by the input data processing means. . As a result, not only the current risk but also a risk that may occur in the future can be presented to the user.
[0008]
In a more preferred embodiment, the first risk diagnosis means determines that the first risk category determined to have the highest risk in the previous diagnosis result and the highest risk in the current diagnosis result. Based on the determined second risk category, a first diagnosis result is generated. Further, the first risk diagnosis unit refers to a list in which the combination of the first risk category and the second risk category and one or more comment candidates are associated, and the comment associated with the combination. It is desirable to extract candidates and select an optimal candidate from the comment candidates. The selection of the optimal candidate is performed by calculating the similarity between the word included in the comment candidate and the word included in the past diagnosis result and / or the current diagnosis result, and selecting the one having the highest similarity. It is desirable to be realized.
[0009]
In another preferred embodiment, the second risk diagnosis means generates a second diagnosis result based on the second risk category determined to have the highest degree of risk in the current diagnosis result. Here again, the second risk diagnosis means refers to a list in which the second risk category and one or more case candidates are associated, and extracts case candidates associated with the first risk category. In addition, it is desirable to select an optimal candidate from the case candidates.
[0010]
In another preferred embodiment, the risk diagnosis system further includes an insurance product table storing information on insurance products, and the insurance based on the first risk diagnosis result and / or the second risk diagnosis result. Insurance diagnosis means for selecting and presenting insurance products from the product table.
[0011]
In another preferred embodiment, the system further includes a risk reduction method presenting means for presenting a method for reducing the risk indicated in the diagnosis result to the user based on at least the current diagnosis result. More preferably, the risk reduction method presenting means associates the second risk category with one or more comment candidates based on at least the second risk category determined to have the highest degree of risk in the current diagnosis result. The comment list associated with the second risk category is extracted with reference to the list, and one or more comment candidates are selected from the comment candidates.
[0012]
Another object of the present invention is a question item generation database storing various information related to a user, the user's basic information associated with an ID that uniquely identifies the user, and the attributes of the user A question having a user database storing information, a user database storing answers to the user's question items and diagnosis results based on the answers, and a question item generating database having an item table storing the question items for the user A program that accesses the item generation database, generates items for the user, and diagnoses the user's risk based on the answers to the items, based on the ID included in the login information from the user A user identification step for identifying a user and a question to the user from the item table in response to a login from the user Select an item or generate a question item for the user based on the item table, accept an item presentation step for presenting the item, and input data indicating the user's answer to the presented item, and Classify into risk categories that have been set in advance, quantify them in relation to each risk category, and calculate the risk level related to each risk category based on these values, and generate diagnostic results that include the risk level Comparing the current diagnosis result generated by the input data processing means with the past diagnosis result regarding the user in the user database, and based on the comparison, from the past to the present A first risk diagnosis step for generating a first diagnosis result indicating a risk up to Also achieved by a program to.
[0013]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. FIG. 1 is a block diagram showing a configuration of a risk diagnosis system 10 according to an embodiment of the present invention.
[0014]
As shown in FIG. 1, the risk diagnosis system 10 includes a user identification unit 12 that identifies a user based on login information such as a user ID and a password from a user, and diagnostic input items according to the number of logins by the user. It has a diagnostic input item presenting section 14 to select and present. In addition, the risk diagnosis system 10 receives user input data for the presented diagnosis input items, digitizes them according to a preset risk category, and calculates these numerical values for each risk category. The input information processing unit 16 outputs a diagnosis result by comparing with statistical materials. Furthermore, the risk diagnosis system 10 compares the diagnosis result output from the input information processing unit 16 with the previous diagnosis result stored in the user database 26 and presents a possible risk that is currently occurring. 1 risk diagnosing unit 18 and a second risk diagnosing unit 20 that estimates and presents a future risk based on the diagnosis result output from the input information processing unit 16. The risk diagnosis system 10 determines a risk category to which the highest risk belongs among the risks obtained by the first risk diagnosis unit 18 and the second risk diagnosis unit 20, and based on the determination result, the insurance product An insurance diagnosis / presentation unit 22 for selecting and presenting insurance products from the table is provided.
[0015]
Further, the risk diagnosis system 10 exchanges data between the user and the apparatus, and a database 24 storing a user database 26, a question item table 28, a comparison table 30, and an insurance product table 32, which will be described later. And an input / output unit 34. The user database 26 here functions to generate a question item for the user, and also functions as a database for storing information identifying the user such as the user ID and password. Yes.
[0016]
Next, the risk diagnosis processing procedure will be described in detail with reference to FIG.
As shown in FIG. 2, the user accesses the apparatus via the Internet using a personal computer or the like, or uses a dedicated terminal connected to the apparatus via a LAN or the like, Logging in to the risk diagnosis system 10 by entering the password.
In the present embodiment, the user needs to register a user ID and a password in advance in order to receive the service provided by the system.
[0017]
Next, based on login information such as a user ID and a password, the user specifying unit 12 of the risk diagnosis system 10 refers to the user database 26 and specifies a user (step 201).
As shown in FIG. 3, in the present embodiment, the user database 26 includes a user basic table 300 that stores various types of user information associated with user IDs. In addition, as shown in FIG. 4A, the user basic table 300 includes a user ID 401 and, for example, the user's sex, age, family structure, address, and login by the user, which are associated with the user ID 401, respectively. User basic information 402 including the number of times, etc., and user attribute information 403 including a user's hobby and personality, a user's answer to an input item to be described later, and various information on a user's risk diagnosis to be described later.
[0018]
When the user is specified by referring to the user database 26, the diagnostic input item presenting unit 14 selects a predetermined one from the conditions stored in the question item table 28 and presents it to the user (step 202). ).
In the present embodiment, as shown in FIG. 3, the question item table 28 includes a fixed condition table 301 in which question items to be presented step by step according to the number of logins of the user, and each risk category. The diagnostic condition table 302 in which the question items to be presented step by step are stored, and the life cycle in which the question items to be presented from specific events (for example, hobbies, seasonal matters) of the individual user are stored It has an information table and a life stage information table 304 in which question items to be presented from general events (for example, age and sex) of individual users are stored.
[0019]
In the present embodiment, the standard condition table 301 is for presenting basic input items according to the number of logins by the user, and more detailed input items are displayed as the number of logins increases. It has come to be presented.
As shown in FIG. 4B, in the first login, only the condition “A” and the condition “B” were obtained (see reference numeral 412). In the second login, the condition “C” "Is added (see reference numeral 413). Further, in the third login, conditions “D” and “E” are added to the above conditions “A” to “C” (see reference numeral 414). More specifically, “sex” and “age” are presented as the first login, and in the second login, in addition to the above conditions, “family structure”, “address (location)”, and “hobby” Is presented. Furthermore, “annual income” and “occupation” are added in the third login, and “history” and “personality” are added in the fourth login. Thus, it is desirable that more private items be presented as the number of logins increases. As a result, more detailed risk diagnosis is possible as the number of logins increases.
[0020]
FIG. 5 is a flowchart showing processing executed when extracting input items to be presented to the user.
As shown in FIG. 5, the diagnostic input item presenting unit 14 refers to the user ID, identifies the user basic information associated with the user ID (step 501), and is included in the identified user basic information. The number of logins is acquired (step 502). Next, the diagnostic input item presentation unit 14 refers to the fixed condition table 301 associated with the user ID, and extracts items corresponding to the acquired number of logins (step 503). Further, the diagnostic input item presentation unit 14 refers to the user basic information 402 of the user basic table 300, identifies the risk category determined to be highest last time (step 504), and an item corresponding to the number of logins Then, an item list in which items belonging to the risk category determined to be highest last time are added is generated (step 505). In this way, predetermined input items are presented to the user for each login.
[0021]
Regarding step 505, the diagnostic condition table 302 contains items to be presented in stages for each risk category, as shown in FIG. This is for presenting input items based on the user's past diagnosis results. The purpose of this table is to recognize how the risk surrounding the user has changed based on the current diagnosis result by reflecting the past diagnosis result on the current input. For example, if the previous diagnosis result is considered as the past diagnosis result, and the compensation risk is the highest, input items related to compensation risk are increased this time, and input items related to more specialized compensation risk are added. can do.
[0022]
The user inputs an answer to the item selected and presented by the diagnostic input item presenting unit 14 (step 203).
Information input by the user with respect to the input items is stored in the user basic table 300 in association with the user ID. For example, an item extracted from the standard condition table 301 is stored as user attribute information in the user basic table 300.
Next, the input information processing unit 16 acquires the information input by the user stored in the user basic table 300, and digitizes the acquired information (step 204).
[0023]
In the present embodiment, the information is classified for each preset risk category and digitized. Risk categories include "body" related to illness and injury, "compensation" related to personality, lifestyle, occupation, etc., "property" related to home, car, household property, etc., "income" related to annual income, household, salary, sports, travel, etc. “Hobby” is used. For each of these, an index indicating the degree of risk or the like is digitized.
[0024]
When the above index is digitized, the system operator can set it as desired. For example, consider “medical history” and “previous disease” which are input items of the risk category “body”. Here, even with the same medical history, the index indicating the risk varies greatly depending on the type of disease (for example, “cecalitis” and “gastric ulcer”). Therefore, the risk level can be set to “30 points” for “cecalitis”, while the risk level can be set to “70 points” for “gastric ulcer”.
[0025]
Alternatively, regarding the risk category “compensation”, a numerical value of an index indicating the degree of risk can be set according to occupation, address, personality, and the like. For example, for occupations that need to drive a car on a regular basis, a predetermined value (20 points) can be added to the values for other occupations. In addition, the amount of risk category “property” and “income” can be quantified as they are. Although property and income do not directly lead to risks, they can be used to calculate the required guarantee amount (insurance amount) in the insurance diagnosis described later. The risk categories are not limited to those described above, and can be set as desired by the operator of this system.
[0026]
The input information processing unit 16 compares each numerical value with the average value for each risk category stored in the average value / trend value table 305 of the comparison table 30 after quantification for each risk category. (Step 205).
Further, in the present embodiment, user input information for items is stored in the user basic table 300 and is extracted into the average value / trend value table 305 and processed into the average value / trend value as necessary. .
[0027]
Next, the input information processing unit 16 calculates the statistical values in the reference value table 306 (for example, compensation accident rate, average life span, disease incidence, income by age, etc.) based on the values of the above items and the values for each risk category. get. Based on the comparison and acquired information, the input information processing unit 16 makes a determination for each risk category according to the magnitude of the difference from the average value based on the comparison. This determination can be presented in the form of “plus / minus XX points” from the average value and statistical materials.
In the present embodiment, for example, as shown in FIG. 6, information in each risk category is related to each other. The operator of this system can set as desired what risk category and which risk category are linked and how they affect the quantification.
[0028]
As described above, in this embodiment, the determination is performed not only by comparing single category items and by referring to statistical values, but also by taking into account the values of items in other related categories. be able to.
When the determination regarding all risk categories is completed, the input information processing unit 16 outputs a diagnosis result (step 206).
In the present embodiment, the processing from step 204 to step 206 is executed by the input information processing unit 16 (see reference numeral 207 in FIG. 2).
[0029]
Next, risk diagnosis is performed by the first risk diagnosis unit 18 and the second risk diagnosis unit 20 based on the diagnosis result processed and output by the input information processing unit 16. Any one of the risk diagnosis units may be activated by the user's selection, and risk diagnosis may be performed, or processing by both risk diagnosis units may be executed. The first risk diagnosis unit 18 diagnoses a risk that is considered to be present (hereinafter, referred to as “risk to date” in some cases) based on the difference between the previous and current diagnosis results. In contrast, the second risk diagnosis unit 20 estimates a risk that may occur in the future.
[0030]
The first risk diagnosis unit 18 diagnoses the risk up to now based on the diagnosis result output from the input information processing unit 16 and the previous diagnosis result stored in the user basic table 300, and diagnoses A result is generated (step 208). In the present embodiment, the process of step 208 is executed by the first risk diagnosis unit 18 (see reference numeral 209 in FIG. 2).
[0031]
FIG. 7 is a flowchart showing risk diagnosis processing up to now.
As shown in FIG. 7, the first risk diagnosis unit 18 first obtains the previous diagnosis result from the user basic table 300 (step 701). Next, the first risk diagnosis unit 18 acquires the diagnosis result from the input information processing unit 16 (step 702), and the item and / or risk that has been determined to have the highest degree of risk among the previous diagnosis results. The category and the risk category to which the item and / or the item determined to be the highest in the current diagnosis result belong are extracted (step 703). In step 703, the first risk diagnosis unit 18, for example, as shown in FIG. 8A, based on the previous diagnosis result 801 and the current diagnosis result 802, of each item has the highest point. Have been extracted.
[0032]
In the example of FIG. 8A, in the previous diagnosis result, the point of “with fracture” was 40P, which was the highest value, but in this diagnosis result, “with car driving” was 50P, the most It is a high number. Therefore, the item “with fracture” is extracted from the previous diagnosis result, while the item “with vehicle driving” is extracted from the current diagnosis result.
[0033]
Next, the first risk diagnosis unit 18 refers to the previous / current comparison table 811 in FIG. 8B based on the combination of risk categories to which the item belongs, and comment candidates associated with the combination. Is selected (step 704). In the above example, the item “with fracture” is extracted with respect to the previous diagnosis result 801. Therefore, the risk category for the body was the highest risk category. On the other hand, with respect to the current diagnosis result 802, the item “with driving” is extracted. Therefore, the risk category for compensation to which this item belongs is the risk category with the highest degree of danger. Accordingly, the first risk diagnosis unit 18 refers to the previous / current comparison table 811 and selects a comment whose previous risk category is “body” and whose current risk category is “compensation”. And decide. Here, comments 814 and 815 are candidates for comments.
[0034]
The first risk diagnosis unit 18 selects the most appropriate candidate from the acquired comment candidates (step 705), generates a diagnosis result image including the selected comment, and presents it to the user (step). 706). The selection of the candidate is, for example, the word in the comment candidate, the item with the highest risk level (for example, “with fracture” or “with driving”) in the previous diagnosis result and the current diagnosis result. This can be realized by checking the relevance of and selecting the one with the highest index indicating the relevance. FIG. 9 shows an example of an image of a diagnosis result according to the present embodiment. Here, items with high risk based on the previous diagnosis result and items with high risk based on the current diagnosis result are represented in a graph (see reference numerals 901 and 902), and the selected comment is displayed. (See reference numeral 903).
[0035]
Next, the processing by the second risk diagnosis unit 20 will be described. The second risk diagnosis unit 20 generates a future risk prediction by a process to be described later based on the diagnosis result output from the input information processing unit 16 (see step 210, reference numeral 210). Second risk
FIG. 10 is a flowchart showing a future risk prediction process.
As shown in FIG. 10, the second risk diagnosis unit 20 acquires the diagnosis result from the input information processing unit 16 (step 1001), and selects the item determined to have the highest degree of risk in the current diagnosis result. Extract (step 1002). For example, for the current diagnosis result 1101 shown in FIG. 11A, the item “with driving” having the highest point is extracted as the item with the highest degree of risk.
[0036]
Next, the second risk diagnosis unit 20 identifies the risk category to which the item belongs, and based on this, refers to the future prediction table 1111 illustrated in FIG. Case candidates are selected (step 1003).
[0037]
In the example shown in FIG. 11A, regarding the current diagnosis result 1101, the item “with driving” has the highest point, and therefore the risk category of compensation to which the item “with driving” belongs is the risk level. It is the highest risk category. Therefore, the second risk diagnosis unit 20 refers to the future prediction table 1111 and makes one or more cases stored in the risk category “compensation” as candidates. As illustrated in FIG. 11B, the future prediction table 1111 stores a plurality of cases (see, for example, reference numerals 1112 and 1113) associated with each risk category.
[0038]
The second risk diagnosis unit 20 selects the most appropriate candidate from the future prediction table 1111 (step 1004), generates a diagnosis result image including the selected case, and presents it to the user (step 1005). . An optimal case can be identified by selecting the word having the highest relevance between the word in the case and the item in the diagnosis result. In the image of FIG. 9, the right side includes a case in which a future risk is estimated (see reference numeral 904).
[0039]
The insurance diagnosis / presentation unit 22 refers to the insurance product table 32 according to the diagnosis results of the first risk diagnosis unit 18 and the second risk diagnosis unit 20, and proposes insurance products to the user (step 212). ). The user can select and examine the insurance product presented by the insurance diagnosis / presentation unit 22 (step 213).
In the present embodiment, there are many similar insurance products proposed, so a plurality of insurance products may be presented (see step 214).
[0040]
According to the present embodiment, a risk that is considered to occur at the present time point is diagnosed by comparing the previous diagnosis result with the current diagnosis result, and may occur in the future based on the current diagnosis result. Estimate potential risks. Thus, the user can know both current and future risks. This also makes it possible to know insurance products that are considered necessary.
[0041]
Next, the second embodiment of the present invention will be described. In the first embodiment, the first risk diagnosis unit 18 diagnoses risks (risks to date) considered to be currently based on the past and present risks, and the second risk diagnosis. The part 20 estimates a risk that may occur in the future. In the second embodiment, in addition to this, it is possible to present a comment indicating what should be done to reduce the risk.
[0042]
Users want to pay as little as possible and are looking for a lifestyle that doesn't rely on insurance as much as possible. Therefore, the second embodiment responds to the needs of the user by presenting measures for reducing the risk.
Hereinafter, a description will be given of presentation processing of comments (risk reduction comments) including measures for reducing risk according to the second embodiment. This is preferably executed prior to step 212 (insurance diagnosis) after the processing of step 208 and step 209 (risk diagnosis) in the processing flow of FIG.
[0043]
In the second embodiment, for risk reduction comment presentation processing, a plurality of risk reduction comment candidates are associated with each risk category. The diagnosis result is referred to, and the risk category belonging to the item determined to have the highest risk in the diagnosis result is specified. Next, a plurality of risk reduction comment candidates associated with the identified risk category are found.
[0044]
From the plurality of candidates, for example, an item that is determined to have the highest degree of risk, a similar word of the item, and a word that is associated are selected. For example, if it is determined that the item “car driving” has the highest degree of danger, “seat belt wearing” or “driving when fatigued” is selected among the candidates associated with the risk category to which the item “car driving” belongs. “Sleep for the previous hour”, “airbag installed”, “air exchange in the vehicle”, etc. are selected as comments. Next, an image that includes the selected comment in the diagnosis result shown in FIG. 9 may be generated and displayed on the screen of the display device.
[0045]
According to the second embodiment, it is possible to present not only an introduction of insurance products based on risk but also a guideline for reducing the risk itself to the user.
The present invention is not limited to the above embodiments, and various modifications can be made within the scope of the invention described in the claims, and these are also included in the scope of the present invention. Needless to say.
[0046]
For example, in the above-described embodiment, the question items are presented according to the number of logins by the user. However, the present invention is not limited to this, and the system administrator may arbitrarily determine the question items.
Further, in the above embodiment, comment candidates and case candidates are extracted using the previous / current comparison table 811 and the future prediction table 1111, and the optimum one is selected from these. It is not limited. For example, the optimum candidate may be selected based on various information in the basic table of the user in addition to the diagnosis result. Alternatively, a blank is provided in a certain syntax, and an appropriate word / phrase to be given to the blank is selected according to the diagnosis result or information in the basic table, thereby creating a sentence in which the blank is filled, and this is used as a comment or case. It is also good.
[0047]
Furthermore, in the embodiment, the first risk diagnosis unit compares the previous diagnosis result with the current diagnosis result to obtain the current risk, but is not limited to the previous diagnosis result. Instead, other past diagnosis results including previous diagnosis results may be used as necessary.
[0048]
In the second embodiment, the risk reduction comment candidate is found based on the item determined to have the highest degree of risk at the current time point, but the present invention is not limited to this. You may use the table containing the risk reduction comment candidate linked | related with the combination of the fragrance judged to be the most dangerous at the past and the present time, respectively.
[0049]
Furthermore, it goes without saying that the image layout indicating the diagnosis result is not limited to the above-described embodiment. For example, in order to show a diagnostic result, while displaying an item with a graph and presenting the comment regarding a risk, you may show the present condition and the estimated symptom corresponding to a comment with animation.
In the present specification, the function of one means may be realized by two or more physical means, or the function of two or more means may be realized by one physical means.
[0050]
【The invention's effect】
According to the present invention, it is possible to quantify user input items based on risk categories, diagnose risks, find current risks, and predict future risks.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of a risk diagnosis system according to an embodiment of the present invention.
FIG. 2 is a flowchart showing a risk diagnosis processing procedure according to the present embodiment;
FIG. 3 is a diagram for explaining a database according to the present embodiment;
FIG. 4 is a diagram for explaining a table in the database according to the embodiment;
FIG. 5 is a flowchart showing a process executed when an input item according to the present embodiment is extracted.
FIG. 6 is a diagram showing an example of the correlation between risk categories according to the present embodiment.
FIG. 7 is a flowchart showing risk diagnosis processing up to now according to the present embodiment.
FIG. 8 is a diagram for explaining a comment selection method to date according to the present embodiment;
FIG. 9 is a diagram illustrating a display example of a diagnosis result using the risk diagnosis system according to the present embodiment.
FIG. 10 is a flowchart showing a future risk diagnosis process according to the present embodiment.
FIG. 11 is a diagram for explaining a future case selection method according to the present embodiment;
[Explanation of symbols]
10 Risk diagnosis system
12 User Identification Department
14 Diagnostic input item presentation section
16 Input information processor
18 First Risk Diagnosis Department
20 Second Risk Diagnosis Department
22 Insurance diagnosis / presentation department
24 database
26 User database
28 Question Item Table
30 Comparison table
32 Insurance product table

Claims (6)

A database for generating question items that stores various information related to a user, and stores basic information including a user's login count associated with an ID that uniquely identifies the user and attribute information of the user Question item having a basic table, a user database having a history table storing answers and diagnosis results for the user's question items, and a question item generating database having an item table storing question items for the user Generation database,
User identification means for identifying a user based on an ID included in login information from the user;
In response to the login information, the number of logins in the basic table associated with the user ID specified by the user specifying unit is acquired, and a new question item determined according to the number of logins is obtained. Obtained from the item table of the question item generation database, input item presenting means for presenting the question item,
The input data indicating the user's answer to the presented item is received, and the user's answer and the answer to the past question item stored in the history table are set in a predetermined risk category, and the Categorized into risk categories including “physical”, annual income, household income, “income” related to salary, “property” related to homes, cars and household goods, and “compensation” related to personality, lifestyle and occupation,
For the “income” and “property” risk categories, the amount included in the answer is quantified, and in the “body” risk category, based on the “medical history” and “previous disease” included in the answer in advance. In the risk category of “compensation”, a numerical value indicating the risk level of a specific occupation according to the “occupation” included in the answer Quantify by adding a predetermined number to a predetermined number for the occupation of
The numerical value in the reference value table storing the statistical value for each risk category is compared with the numerical value obtained by the quantification, and the numerical value in the reference value table and the numerical value obtained by the quantification are obtained for each category. An input data processing means for calculating a difference with the numerical value, generating a diagnosis result based on the difference, and storing the diagnosis result in the history table;
The current diagnosis result generated by the input data processing means is compared with the past diagnosis result related to the user stored in the history table of the user database, and the most dangerous in the previous diagnosis result Based on the first risk category determined to be and the second risk category determined to be the most dangerous in the current diagnosis result, the first diagnosis result indicating the risk from the past to the present A first risk diagnostic means to generate ,
A comment candidate associated with a combination is extracted with reference to a list in which the combination of the first risk category and the second risk category is associated with one or more comment candidates, and is included in the comment candidate A first candidate configured to calculate a similarity between a word and a word included in a past diagnosis result and / or a current diagnosis result, and to select a comment candidate having the highest similarity as an optimal candidate Risk diagnostic means ;
Based on the current diagnosis result generated by the input data processing means, a second risk estimation result based on the second risk category determined to have the highest degree of risk in the current diagnosis result A second risk diagnosis means for generating a diagnosis result ,
By referring to a list in which the second risk category and one or more case candidates are associated with each other, the case candidates associated with the second risk category are extracted, the words included in the case candidates, A second risk diagnosing means configured to calculate a similarity with a word included in the diagnosis result and to select a case candidate having the highest similarity as an optimal candidate ,
The risk diagnosis system, wherein the input item presenting means is configured to present a new question item determined according to the number of logins and a question item belonging to the first risk category. An insurance product table for storing insurance product information;
The insurance diagnosis means for selecting and presenting an insurance product from the insurance product table based on the first risk diagnosis result and / or the second risk diagnosis result. Risk diagnosis system.   A risk reduction method presentation means that presents users with risk reduction comments to reduce the risk indicated in the diagnosis results based on at least the current diagnosis results, and is judged to be the most dangerous in the current diagnosis results. Based on the second risk category, with reference to the list in which the second risk category is associated with one or more risk reduction comment candidates, the risk reduction comment candidates associated with the second risk category are selected. The risk reduction method presenting means for extracting and selecting a risk reduction comment candidate including an extracted word and an associated word after the item of the second risk category is provided. Risk diagnosis system. A database for generating question items that stores various information related to a user, and stores basic information including a user's login count associated with an ID that uniquely identifies the user and attribute information of the user Question item having a basic table, a user database having a history table storing answers and diagnosis results for the user's question items, and a question item generating database having an item table storing question items for the user A program that accesses the database for generation, generates items for users, and diagnoses user risks based on answers to the items,
A user identification step for identifying the user based on the ID included in the login information from the user;
In response to the login information, the number of logins in the basic table associated with the user ID specified by the user specifying unit is acquired, and a new question item determined according to the number of logins is obtained. Obtaining from the item table of the question item generation database, an item presentation step of presenting the question item,
The input data indicating the user's answer to the presented item is received, and the user's answer and the answer to the past question item stored in the history table are set in a predetermined risk category, and the Categorized into risk categories including “physical”, annual income, household income, “income” related to salary, “property” related to homes, cars and household goods, and “compensation” related to personality, lifestyle and occupation,
For the “income” and “property” risk categories, the amount included in the answer is quantified, and in the “body” risk category, based on the “medical history” and “previous disease” included in the answer in advance. In the risk category of “compensation”, a numerical value indicating the risk level of a specific occupation according to the “occupation” included in the answer Quantify by adding a predetermined number to a predetermined number for the occupation of
The numerical value in the reference value table storing the statistical value for each risk category is compared with the numerical value obtained by the quantification, and the numerical value in the reference value table and the numerical value obtained by the quantification are obtained for each category. An input data processing step of calculating a difference with the numerical value, generating a diagnosis result based on the difference, and storing the diagnosis result in the history table;
The current diagnosis result generated by the input data processing means is compared with the past diagnosis result related to the user stored in the history table of the user database, and the most dangerous in the previous diagnosis result Based on the first risk category determined to be and the second risk category determined to be the most dangerous in the current diagnosis result, the first diagnosis result indicating the risk from the past to the present A first risk diagnostic step to generate,
Extracting a comment candidate associated with a combination with reference to a list in which the combination of the first risk category and the second risk category is associated with one or more comment candidates; and
Calculating a similarity between a word included in the comment candidate and a word included in a past diagnosis result and / or a current diagnosis result, and selecting a comment candidate having the highest similarity as an optimal candidate A first risk diagnosis step;
Based on the current diagnosis result generated by the input data processing means, a second risk estimation result based on the second risk category determined to have the highest degree of risk in the current diagnosis result A second risk diagnostic step for generating a diagnostic result ,
Extracting a case candidate associated with the first risk category with reference to a list in which the first risk category and one or more case candidates are associated; and
A second risk diagnosing step including calculating a similarity between the word included in the case candidate and a word included in the current diagnosis result, and selecting a case candidate having the highest similarity as an optimal candidate ; To the computer,
The input item presenting step includes a step of presenting a new question item determined according to the number of logins and a question item belonging to the first risk category. And causing the computer to execute a step of selecting and presenting an insurance product from an insurance product table storing information on the insurance product based on the first risk diagnosis result and / or the second risk diagnosis result. The program according to claim 4 . A risk reduction method presentation step for presenting a risk reduction comment to a user to reduce the risk indicated in the diagnosis result based on at least the current diagnosis result,
Based on the second risk category determined to be the highest risk in the current diagnosis result, refer to the list in which the second risk category and one or more risk reduction comment candidates are associated with each other. A risk reduction method presentation step comprising: extracting risk reduction comment candidates associated with the risk category, and selecting a risk reduction comment candidate including an associated word after the item of the second risk category The program according to claim 4 or 5, wherein the program is executed by the computer.

Images