JP7407519B2 - Decision device, decision method, and decision program - Google Patents

Description

The present invention relates to a determination device, a determination method, and a determination program.

2. Description of the Related Art Conventionally, services have been known that aim to optimize information provided to users based on information about the users. As an example of such a technology, a technology is known that proposes an optimized lifestyle, such as the optimal insurance amount and savings amount, based on information input by the user for lifestyle diagnosis.

Japanese Patent Application Publication No. 2002-140527

However, with the above-mentioned conventional technology, it may not be possible to propose the optimal insurance form to the user.

For example, in the above-mentioned conventional technology, the guarantee fee to be paid to guarantee the optimal required pension insurance premium for the user is calculated, and the user is provided with the calculated guarantee fee and a method for paying the guarantee fee. I'm just making a suggestion. For this reason, the above-mentioned conventional technology cannot be said to appropriately suggest insurance aspects such as what kind of insurance is suitable for the user and how much guarantee fee should be paid.

This application was made in view of the above, and aims to propose a more appropriate insurance form to users.

The determination device according to the present application includes an acquisition unit that acquires user information related to a user, an insurance-related product selected by the user from among a plurality of insurance-related products related to insurance, and user information of the user. and a determining unit that determines a combination of insurance-related products to be proposed to the user from the user information acquired by the acquiring unit using a model that has learned the relationship between shall be.

According to one aspect of the embodiment, an appropriate insurance form can be proposed to a user.

FIG. 1 is a diagram illustrating an example of an information providing apparatus according to an embodiment. FIG. 2 is a diagram illustrating a configuration example of an information providing apparatus according to an embodiment. FIG. 3 is a diagram illustrating an example of a user information database according to the embodiment. FIG. 4 is a diagram illustrating an example of a user attribute database according to the embodiment. FIG. 5 is a diagram illustrating an example of an insurance-related product database according to the embodiment. FIG. 6 is a flowchart illustrating an example of the flow of determination processing according to the embodiment. FIG. 7 is a diagram showing an example of the hardware configuration.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Below, a determination device, a determination method, and a mode for implementing a determination program (hereinafter referred to as an "embodiment") according to the present application will be described in detail with reference to the drawings. Note that the determination device, determination method, and determination program according to the present application are not limited to this embodiment. Further, in each of the embodiments below, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[1. Example of information providing device]
First, an example of an information providing device 10, which is an example of a determining device according to an embodiment, will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of an information providing apparatus according to an embodiment. In FIG. 1, an example of a process for determining a combination of insurance-related products to be proposed to a user will be described as an example of a determination process executed by an information providing apparatus 10, which is an example of a determination apparatus.

In addition, the insurance-related products explained below are products related to various types of insurance, and once a predetermined insurance premium is collected from a user, if a predetermined event occurs within a predetermined period, A person who pays a specified amount to a person. In addition, if an insurance-related product is related to various types of insurance, it includes details of events covered by insurance, type of insurance, insurance premiums, insurance premium payment conditions, special contracts, etc. It's okay.

The information providing device 10 shown in FIG. 1 is an information processing device that performs decision processing, and is realized by, for example, a server device, a cloud system, or the like. For example, the information providing device 10 can communicate with a user terminal 100 used by a user via a network N such as the Internet (see, for example, FIG. 2). Note that the information providing device 10 may be able to communicate with any number of user terminals 100 used by any number of users.

Note that the information providing device 10 may be able to communicate with various arbitrary server devices via the Internet. For example, the information providing device 10 is a server that maintains a log of arbitrary content (hereinafter collectively referred to as "posted information") such as information and images posted by users, such as SNS (Social Networking Service) and microblogs. It is assumed that the device is capable of communicating with a server device, etc. that maintains the history of search queries entered by the user. It is also assumed that the information providing device 10 is capable of communicating with a server device that specifies or estimates demographic attributes and psychographic attributes of users.

The user terminal 100 is an information processing terminal such as a PC (Personal Computer) or a smartphone used by the user U. For example, the user terminal 100 can communicate with the information providing device 10 via a network N such as the Internet (see, for example, FIG. 2). Although not shown in FIG. 1, the information providing device 10 may be able to communicate with any number of user terminals 100.

[1-1. Overview of decision processing]
Here, the above-mentioned conventional technology merely proposes to the user a method for paying the guarantee fee, but cannot present to the user what type of insurance is recommended. Can not. For this reason, we provide users with insurance portfolios, such as deciding how much to spend on what type of insurance and how to combine the types of insurance. I can't say that.

Therefore, the information providing device 10 executes the following determination process. First, the information providing device 10 acquires user information related to the user. Then, the information providing device 10 determines a combination of insurance-related products to be proposed to the user from a plurality of insurance-related products related to insurance, based on the user information.

For example, the information providing device 10 acquires behavior information indicating a user's behavior on the Internet as the user information. To give a more specific example, the information providing device 10 stores search history that is a history of search queries input by users, posting history that is a history of information posted by users on SNS, microblogs, etc., and information provided by users. A location history that is a history of the location of a user, a browsing history that is a history of web contents viewed by the user, a purchase history that is a history of products purchased by the user on an online shopping mall, etc. are acquired. Further, the information providing device 10 may acquire information about the user as user information, which is information registered in advance on the web by the user.

For example, the information providing device 10 may acquire the search history from the search server or the user terminal 100. Further, the information providing device 10 may acquire posting history from an SNS server or the like that provides an SNS service. Further, the information providing device 10 may acquire location information obtained by the user terminal 100 using GPS (Global Positioning System) etc. as a location history, and a history of base stations that have communicated with the user terminal 100. Alternatively, the history of access points to which the user terminal 100 has connected, the history of beacons, etc. may be acquired as the location history. Further, the information providing device 10 may acquire the history of web content viewed by the user from a browser application installed on the user terminal 100. Further, the information providing device 10 may acquire the history of products purchased by the user as a purchase history from a server device that provides services related to the online shopping mall.

Here, the various user information mentioned above, statistical attributes (i.e., demographic attributes) such as the user's age and gender, and psychological attributes (i.e., psychosocial attributes) such as the user's hobbies and preferences are used. graphic attributes). These user attributes include information useful for selecting insurance-related products, such as what kind of lifestyle the user has and what kind of guarantee he or she would require in the event of an unexpected event. It can be.

Therefore, the information providing device 10 estimates the user's attributes from the acquired user information, and determines the combination of insurance-related products to be proposed to the user based on the estimated user's attributes. For example, the information providing device 10 may determine a combination of insurance-related products of different types as the combination of insurance-related products. Further, for example, the information providing device 10 may determine a combination of insurance-related products including at least one of life insurance, non-life insurance, accident insurance, disease insurance, personal pension insurance, or nursing care insurance. Further, the information providing device 10 may determine a combination of insurance-related products provided by different vendors.

That is, the information providing device 10 regards the user's attributes as the user's persona, and determines the optimal combination of insurance-related products for the persona. As a result, the information providing device 10 can provide the user with an appropriate combination of insurance-related products.

Here, the information providing device 10 may determine the combination of insurance-related products to be proposed to the user according to the combination of demographic attributes and psychographic attributes. For example, assume that the information providing device 10 estimates information such as "30s" and "male" as the user's demographic attributes, and information such as "I like motorcycles" as the psychographic attribute. In this way, in the case of a man in his 30s who loves motorcycles, liability insurance and vehicle insurance to compensate for injuries caused to the other party in a traffic accident are more important than personal pension insurance. , or it would be better to allocate priority expenses to life insurance. Furthermore, for example, if the user is married, it may be better to allocate more expenses to life insurance and accident insurance than to vehicle insurance.

Therefore, the information providing device 10 determines the allocation of costs to a plurality of insurance-related products of different types based on the user's attributes, and selects insurance-related products of each type based on the determined cost allocation. do. For example, the information providing device 10 estimates the probability that an event that is related to the estimated user attribute and guaranteed by each insurance-related product will occur.

For example, the information providing device 10 may determine, based on psychographic attributes indicating the user's hobbies such as "I like motorcycles", "Motorcycle accident", "Death accident", "Incurrence of compensation for damages", "Occurrence of after-effects", " Estimating events such as "loss of motorcycle". Such estimation of events related to user attributes may be estimated based on a preset rule-based table, for example, and the estimated psychographic attributes of the user may be estimated using an associative memory model. It may be estimated from For example, the information providing device 10 holds in advance a list of events guaranteed by insurance-related products to be combined. Then, the information providing device 10 selects an event whose degree of association with the user's attribute exceeds a predetermined threshold value from among the held events.

For example, people in cold regions are more likely to suffer from serious illnesses such as heart attacks and cerebral hemorrhages than in warm regions. Furthermore, if the user is a woman, there is a high possibility that she will suffer from diseases unique to women, such as breast cancer. Therefore, the information providing device 10 selects, as an event, a disease for which the possibility of separation of the user is higher than a predetermined threshold value from the estimated demographic attributes of the user. Furthermore, the information providing device 10 selects other events associated with the estimated disease (for example, the type of disorder that may occur, the occurrence of hospitalization costs, etc.).

Here, even among users who like motorcycles, for example, a woman in her 30s or a man in his 60s will drive faster than a man in his 30s. As a result, the probability of fatal accidents, the probability of aftereffects, and the amount of compensation for damages are thought to be lower. Furthermore, the possibility that a user will contract a disease and the severity of the disease may vary depending on the region where the user resides and the age of the user. Therefore, the information providing device 10 estimates the probability that each estimated event will occur based on the user's demographic attributes and psychographic attributes. Here, the probability that each event will occur is a concept that indicates not only the probability of whether or not each event will actually occur, but also the severity that will occur when the event actually occurs. That is, the information providing device 10 estimates events that may occur to the user based on the user's attributes, and further estimates the impact that each event may have on the user based on the user's attributes. Estimate the degree of accuracy.

Note that the information providing device 10 scores all events according to the user's attributes, that is, scores that have the attributes, without selecting events from among the events guaranteed by the insurance-related products to be combined. A score indicating the degree of influence each event has on the user may be assigned. Note that such score calculation may be performed, for example, on a rule basis, or may be realized using various models. For example, the information providing device 10 maintains a score table in which points are assigned to each combination of an event and a user's attribute. When calculating a score for a certain event, the information providing device 10 calculates the sum of points previously given to the pair of the event and the estimated user attribute as the score for the event. May be adopted.

The information providing device 10 then determines the combination of insurance-related products to be provided to the user based on the score assigned to each event. For example, the information providing device 10 selects an event whose score value exceeds a predetermined threshold, and selects an insurance-related product of a type that guarantees the selected event. The information providing device 10 then combines the insurance-related products so that the cost is allocated more to insurance-related products of the type that guarantees an event with a higher score than other events than to other types of insurance-related products. Determine. Further, the information providing device 10 selects insurance-related products so that all the selected events are guaranteed.

For example, the information providing device 10 selects events such as "death accident," "occurrence of compensation for damages," and "loss of motorcycle" as events whose score value exceeds a predetermined threshold value from among each event. . In such a case, the information providing device 10 provides "life insurance" that guarantees "death accident", "liability insurance" that guarantees "occurrence of compensation for damages", and "vehicle insurance" that covers "loss of motorcycle". Identify. Then, the information providing device 10 selects insurance-related products from among the insurance-related products to be combined so that at least "life insurance," "liability insurance," and "vehicle insurance" are included.

Here, for example, if the score of "death accident" is higher than "occurrence of compensation for damages" or "loss of motorcycle", the information providing device 10 determines the ratio of the cost to "life insurance" that guarantees "death accident". Insurance-related products are selected in such a way that the For example, the information providing device 10 calculates the ratio of the score of "death accident", the score of "occurrence of compensation for damages", and the score of "loss of motorcycle" to the cost of "life insurance" and the score of "compensation for damages". ” and the cost of “vehicle insurance.” Then, the information providing device 10 calculates the amount of cost to be allocated to each insurance based on the preset total cost (for example, the total cost set in advance by the user) and the cost ratio for each insurance. Then, select "life insurance," "liability insurance," and "vehicle insurance" so that the insurance premium falls within the calculated amount. Note that the information providing device 10 may determine a plurality of combinations of insurance-related products that satisfy these conditions.

The information providing device 10 then provides the selected combinations of insurance-related products to the user. As a result, the information providing device 10 can propose appropriate insurance types to the user.

[1-2. Regarding an example of decision processing]
Next, an example of a process executed by the information providing device 10 will be described using FIG. 1. First, the information providing device 10 collects user information of users who use the user terminal 100 (step S1). For example, the information providing device 10 stores the user's search history "motorcycle", "travel", posting history "touring!", location history "location #1", "location #2", browsing history "site #1", "Site #2", purchase history "Product #1", registered information "Registered information #1", etc. are collected.

Then, the information providing device 10 estimates the user's attributes based on the user information (step S2). For example, the information providing device 10 estimates the user's demographic attributes “30s” and “male” based on the user's search history, purchase history, registered information, and the like. For example, in the example shown in FIG. 1, the user's search history includes "motorcycle" and "travel," and the posting history includes "touring!" Therefore, the information providing device 10 estimates information such as "I like motorcycles" as the user's psychographic attribute. Note that any estimation technique can be adopted for estimating such attributes.

Furthermore, the information providing device 10 estimates the probability that an event covered by each insurance will occur based on the estimated attributes of the user (step S3). For example, the information providing device 10 calculates a probability of "80" for the event "traffic accident" based on the user's demographic attributes "30s", "male", psychographic attributes "I like motorcycles", etc. Calculate the accuracy of "death accident" of "70".

Furthermore, the information providing device 10 determines the allocation ratio of expenses for various types of insurance based on the estimated accuracy (step S4). For example, when a traffic accident or a fatal accident occurs, the information providing device 10 provides insurance such as "life insurance," "non-life insurance," "accident insurance," "disease insurance," etc. Select. Then, the information providing device 10 calculates the cost allocation ratio for each type of each selected insurance-related product based on the probability calculated for each event in step S3. For example, the information providing device 10 determines that the cost ratio for "life insurance" is "0.3", the cost ratio for "non-life insurance" is "0.5", the cost ratio for "disability insurance" is "0.1", Calculate the cost ratio "0.1" to "illness insurance".

Then, the information providing device 10 determines a combination of insurance-related products to be proposed to the user based on the determined cost allocation ratio (step S5). For example, the information providing device 10 determines the combination of insurance-related products to be proposed to the user by combining various types of insurance-related products so as to satisfy the cost allocation ratio calculated in step S4. . For example, the information providing device 10 may provide combinations of insurance-related products whose insurance IDs (Identifiers) for identifying insurance-related products are "Insurance #1," "Insurance #3," "Insurance #5," and "Insurance #8." Determine.

The information providing device 10 then provides the determined combination of insurance-related products to the user (step S6). As a result, the information providing device 10 can propose an appropriate combination of insurance-related products according to various attributes such as the user's gender, age, hobbies, etc.

[1-3. About determining the combination]
Here, the information providing device 10 may learn a model that generates a combination of insurance-related products from user attributes, and use the model to determine a combination of insurance-related products to be proposed to the user. good. For example, the information providing device 10 may employ various neural networks such as DNN (Deep Neural Network) or SVM (Support Vector Machine) as a model.

For example, the information providing device 10 acquires, as learning data, attribute information indicating a user's attribute and combination information indicating a combination of insurance-related products to be proposed to a user having the attribute. Such learning data may be created manually in advance based on rules. Then, the information providing device 10 performs model learning so as to generate corresponding combination information when attribute information is input. In other words, the information providing device 10 uses a model to learn the relationship between the characteristics of a user's attributes and the characteristics of a combination of insurance-related products that it would like to propose to a user whose attributes have such characteristics. let

Furthermore, the information providing device 10 generates a combination of insurance-related products to be proposed to the user based on the user's attributes using the model learned by the above-described learning process, and generates a combination of insurance-related products to be proposed to the user. provide a combination of Here, the information providing device 10 receives information from the user who provided the combination of insurance-related products, including the degree of satisfaction with the content of the proposal, the percentage of customers who actually purchased the proposed insurance-related products (i.e., conversion rate), etc., as correction information. get. The information providing device 10 may then modify the model based on the acquired modification information.

For example, the information providing device 10 proposes a combination of "life insurance," "personal pension," and "liability insurance" to a user with a certain attribute, but the user Even if you modify the model to output a combination of "life insurance" and "casualty insurance" when you enter the user's attributes if you have only entered into a contract with "casualty insurance". good. Furthermore, the information providing device 10 may modify the model based on whether an event guaranteed by the insurance product proposed to the user actually occurs within a predetermined period.

[1-4. others〕
Note that the information providing device 10 may perform any process as long as it determines the combination of insurance-related products to be proposed to the user based on the user information. For example, the information providing device 10 uses a model to learn the relationship between a feature of user information and a feature of a combination of insurance-related products that is predicted to be appropriate for the user indicated by the user information of the feature. let By inputting the acquired user information into the model, the information providing device 10 may determine the combination of insurance-related products without estimating the user's persona or calculating the score of each event.

Note that any insurance-related product can be adopted as each insurance-related product. For example, the information providing device 10 may determine a combination of insurance-related products provided by different businesses. Further, the information providing device 10 may be combined with whole life insurance, insurance that guarantees for one year, or the like. For example, the information providing device 10 may determine a combination of insurance-related products that is estimated to be appropriate for the user within a predetermined period (for example, a combination of insurance-related products that are guaranteed for the most recent year).

Further, the information providing device 10 may estimate the user's future persona based on the user information, and determine a combination of insurance-related products that guarantee the future based on the estimated persona. For example, the information providing device 10 may reduce the ratio for disease insurance if the possibility that the user will suffer from a specific disease in the future is low.

Further, if the user has a spouse, the information providing device 10 may determine a combination of insurance-related products appropriate for the user based on the spouse's persona. For example, if the user has a spouse, the information providing device 10 may select an insurance-related product with a higher guaranteed amount at the time of death.

Further, depending on the insurance-related product, the user may be subject to mental and physical or economic enrollment conditions when enrolling in the insurance. Therefore, the information providing device 10 determines whether each insurance-related product is available for use by the user based on the user information, and selects a combination of insurance-related products that are determined to be available for use by the user. may be determined. For example, the information providing device 10 can determine, from user information, psychological tendencies of the user, diseases that the user has suffered from in the past, diseases that the user is likely to suffer from, probability of suffering from a predetermined disease, and whether or not the user is a smoker. , estimate various information related to membership conditions, such as whether or not any family member has contracted a certain disease, occupation, income, etc. The information providing device 10 then compares the estimation results with the participation conditions of each insurance-related product, identifies insurance-related products available to the user, and selects user information from among the identified insurance-related products. Based on this, a combination of insurance-related products that is appropriate for the user may be determined.

Further, the information providing device 10 may determine the combination of insurance-related products by considering special contracts for insurance-related products. For example, the information providing device 10 selects a combination of life insurance that provides death protection and accident insurance for a certain user, but the disability insurance includes death protection in the event of the user's death as a special provision. You may exclude life insurance from the proposal if the

[2. Configuration of information providing device]
An example of the functional configuration of the information providing device 10 described above will be described below. FIG. 2 is a diagram illustrating a configuration example of an information providing apparatus according to an embodiment. As shown in FIG. 2, the information providing device 10 includes a communication section 20, a storage section 30, and a control section 40.

The communication unit 20 is realized by, for example, a NIC (Network Interface Card). The communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 100.

The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 30 also stores a user information database 31, a user attribute database, an insurance-related product database 33, and a model database 34 (hereinafter sometimes collectively referred to as "databases 31 to 34").

An example of information registered in each of the databases 31 to 34 will be described below with reference to FIGS. 3 to 5. User information is registered in the user information database 31. For example, FIG. 3 is a diagram illustrating an example of the user information database according to the embodiment. In the example shown in FIG. 3, the user information database 31 includes "user ID," "search history," "posting history," "location history," "browsing history," "purchase history," and "registration information." ” etc. are registered in association with each other. Note that in addition to the information shown in FIG. 3, the user information database 31 may also register any information related to users.

Here, the "user ID" is an identifier that identifies a user. Moreover, the "search history" is the history of search queries input by the user identified by the associated "user ID". Moreover, the "posting history" is the history of posted information posted by the user identified by the associated "user ID". Further, the “location history” is the history of the location of the user identified by the associated “user ID”, and is, for example, the history of the location of the user terminal 100. Moreover, the "browsing history" is the history of web content viewed by the user identified by the associated "user ID". Further, the "purchase history" is information indicating the history of products, services, etc. purchased at the online shopping mall by the user identified by the associated "user ID." Moreover, "registration information" is information of a user registered in advance by the user identified by the associated "user ID".

For example, in the example shown in FIG. #1,” a browsing history “browsing history #1,” a purchasing history “purchasing history #1,” and registered information “registered information #1” are registered in association with each other. Such information is such that the search history of the user indicated by the user ID "User #1" is "Search history #1", the posting history is "Posting history #1", and the location history is "Location history". #1", the browsing history is "browsing history #1", the purchase history is "purchase history #1", and the registered information is "registered information #1".

In the example shown in FIG. 3, "Search history #1", "Post history #1", "Location history #1", "Browsing history #1", "Purchase history #1", "Registered information #1" Although we have described conceptual values such as search query strings and images, posted information, latitude and longitude information obtained by GPS etc., URL (Uniform Resource Locator) of web content, usage Numerical values, character strings, etc. indicating the famous place of transaction that the person purchased, the seller, the price, the date and time of purchase, and the gender of the user will be registered.

Information indicating attributes of users (hereinafter sometimes referred to as "attribute information") is registered in the user attribute database 32. For example, FIG. 4 is a diagram illustrating an example of a user attribute database according to the embodiment. In the example shown in FIG. 4, in the user attribute database 32, "user ID", "demographic attribute", and "psychographic attribute" are registered in association with each other. In addition, "demographic attributes" include items such as "age," "gender," "address," "annual income," and "marriage," and "psychographic attributes" include "hobbies," "purchasing tendencies," and so on. Includes items such as ``. Note that, in addition to the information shown in FIG. 4, arbitrary information regarding usage attributes may be registered in the user attribute database 32.

Here, "demographic attributes" is information indicating statistical attributes of users, as shown in each item. Furthermore, "psychographic attributes" are information indicating the psychological attributes of the user, as shown in each item. For example, in the example shown in Figure 4, for the user ID "User #1", age is "30s", gender is "male", address is "address #1", annual income is "annual income #1", and marriage is "single". , hobby ``motorcycle touring,'' and purchasing tendency ``cautious'' are registered in association with each other. Such information indicates that the user indicated by the user ID "User #1" is a man in his 30s, lives at the residence indicated by "Address #1", and has an annual income of "Annual Income #1". Yes, indicating that the person is unmarried. Further, such information indicates that the user indicated by the user ID "User #1" has a hobby of touring by motorcycle and tends to carefully select transaction items before purchasing.

In addition, in the example shown in Figure 4, conceptual values such as "address #1" and "annual income #1" are described, but in reality, character strings and numerical values indicating addresses, numerical values indicating annual income, etc. are registered. Ru.

Information regarding insurance-related products is registered in the insurance-related product database 33. For example, FIG. 5 is a diagram illustrating an example of the insurance-related product database according to the embodiment. In the example shown in FIG. 5, the insurance-related product database 33 has registered information such as "insurance-related product ID", "type", "insurance premium", "participation conditions", "maturity period", "special contract information", etc. has been done. In addition to the information shown in FIG. 5, various types of information regarding insurance-related products may be registered in the insurance-related product database 33.

Here, the "insurance-related product ID" is an identifier that identifies an insurance-related product. Further, the "type" is information indicating the type of insurance-related product (for example, whether it is life insurance or accident insurance). Furthermore, “insurance premium” is the fee for insurance-related products. Furthermore, "participation conditions" are conditions imposed on users when using insurance-related products. Further, the "maturity period" is information indicating a period during which insurance provides compensation for a predetermined event. Further, "special contract information" is information indicating a so-called special contract.

For example, in the example shown in FIG. 5, the insurance-related product database 33 includes the insurance-related product ID "Insurance #1", the type "Life", the insurance premium "Insurance premium #1", the participation condition "Condition #1", and the maturity date. The term "lifetime" and special contract information "special contract #1" are registered in association with each other. Such information indicates that the insurance-related product indicated by the insurance-related product ID "Insurance #1" is whole life insurance, the insurance premium is "Insurance premium #1", and the participation condition is "Condition #1". , indicates that the special agreement is “special agreement #1”.

In the example shown in Figure 5, conceptual values such as "insurance #1", "insurance premium #1", "condition #1", and "special contract #1" are described, but in reality, insurance-related products Numerical values and character strings identifying insurance premiums, numerical values and character strings representing insurance premiums, numerical values and character strings representing participation conditions, and numerical and character strings representing special contracts are registered.

Returning to FIG. 2, the explanation will be continued. Learned models are registered in the model database 34. For example, the model database 34 includes an input layer into which input information that is input to the model is input, a plurality of intermediate layers that sequentially perform predetermined processing on the input information input into the input layer, and a plurality of intermediate layers that sequentially perform predetermined processing on the input information input to the input layer. Data of a model having an output layer that generates output information corresponding to input information based on the output of the intermediate layer that performs processing last among the intermediate layers is registered. More specifically, the model database 34 registers data indicating connection relationships between nodes and connection coefficients between nodes.

Here, the value of the model is calculated based on the first element that belongs to any layer from the input layer to the output layer but other than the output layer, and the first element and the weight of the first element. By performing calculations based on the first element and the weight of the first element, with each element belonging to each layer other than the output layer as the first element, on the information input to the input layer, including the second element, The computer functions to output information from the output layer that corresponds to information input to the input layer. Note that the model may be one that is assumed to be used as a program module that is part of artificial intelligence software.

In such a model, when at least one of a user's user information and user attribute information is input to the input layer, the user information corresponding to the user information and attribute information is input from the output layer. The computer is operated to output information indicating a combination of insurance-related products to be proposed to the customer. For example, the model is used in a computer that includes a CPU and memory. Specifically, the CPU of a computer applies learned weighting coefficients in a neural network to user information and attribute information input to the input layer of the model, according to instructions from a trained model stored in memory. It performs calculations based on the response function and the like, and operates to output information indicating the combination of user information and insurance-related products proposed to the corresponding user from the output layer.

Here, when the model is realized by a neural network having one or more intermediate layers, such as a DNN, the first element included in each model is considered to be any node included in the input layer or the intermediate layer. The second element corresponds to the node to which the value is transmitted from the node corresponding to the first element, that is, the next node, and the weight of the first element corresponds to the node corresponding to the first element. is the weight considered for the value transmitted from to the node corresponding to the second element, ie, the connection coefficient.

Here, the information providing device 10 generates a model for predicting the destination of the epidemic by using information registered in the user information database 31, user attribute database 32, and insurance-related product database 33 as learning data. do. That is, the information registered in the user information database 31, user attribute database 32, and insurance-related product database 33 is stored in the input layer where demand information is input, the output layer, and any one from the input layer to the output layer. The input user information or attribute information includes a first element that belongs to a layer other than the output layer, and a second element whose value is calculated based on the first element and the weight of the first element. By performing calculations based on weights that reflect the characteristics of the user, information corresponding to the input user information or attribute information is proposed to the user who corresponds to the input user information or attribute information. This data is used to cause a computer to output information indicating combinations of insurance-related products from the output layer.

The control unit 40 is, for example, a controller, and uses a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc. to process various programs (an example of a notification program) stored in a storage device inside the information providing device 10. (equivalent to ) is realized by executing the RAM as a work area. Further, the control unit 40 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 40 includes an acquisition unit 41, an estimation unit 42, a determination unit 43, a provision unit 44, and a learning unit 45. The acquisition unit 41 acquires user information related to the user. For example, the acquisition unit 41 acquires behavior information indicating a user's behavior on the Internet as the user information. For example, the acquisition unit 41 acquires information about the user that can be acquired via the Internet, such as search history, posting history, location history, viewing history, purchase history, and registration information. The acquisition unit 41 then registers the acquired information in the user information database 31 as user information.

The estimation unit 42 estimates the user's attributes based on the acquired user information. For example, the estimation unit 42 estimates the user's demographic attributes and psychographic attributes as the user's attributes. For example, the estimation unit 42 estimates the user's gender, age, address, hobbies, etc. based on information registered in the user information database 31. Note that the estimation unit 42 may estimate the user's attribute information using, for example, a predetermined estimation model that estimates the user's attribute information from the user information. The estimation unit 42 then registers the estimated user attribute information in the user attribute database 32.

The determining unit 43 determines a combination of insurance-related products to be proposed to the user from among a plurality of insurance-related products related to insurance, based on the user information. For example, the determining unit 43 determines a combination of insurance-related products of different types as the combination of insurance-related products. Further, the determining unit 43 determines, for example, a combination of insurance-related products including at least one of life insurance, non-life insurance, accident insurance, disease insurance, personal pension insurance, or nursing care insurance. Further, the determining unit 43 may determine a combination of insurance-related products provided by different companies.

For example, when executing a process using a model, the determining unit 43 reads the model registered in the model database 34, and reads out the model registered in the model database 34 and the user information registered in the user information database 31 and the user attribute database 32. input the attribute information into the model. The determining unit 43 then obtains the combination of insurance-related products output by the model.

On the other hand, for example, when executing processing based on rules, the determining unit 43 generates a combination of insurance-related products registered in the insurance-related product database 33 based on user information and attribute information. Note that the determining unit 43 may determine the combination of insurance-related products to be proposed to the user based only on the attribute information estimated by the estimating unit 42.

For example, the determining unit 43 may determine the combination of insurance-related products to be proposed to the user according to the combination of the estimated demographic attributes and psychographic attributes. Further, for example, the determining unit 43 may determine the combination of insurance-related products depending on the probability that an event related to the estimated user attributes and guaranteed by the insurance-related product will occur. . Further, the determining unit 43 determines the allocation of costs to a plurality of insurance-related products of different types based on the user information, and selects insurance-related products of each type based on the determined cost allocation. Good too. Further, the determining unit 43 may allocate costs to insurance-related products that have a higher probability of causing a guaranteed event than other types of insurance-related products than to other types of insurance-related products. good.

The providing unit 44 provides the combination of insurance-related products determined by the determining unit 43 to the user. For example, the providing unit 44 reads information on insurance-related products included in the combination of insurance-related products determined by the determining unit 43 from the insurance-related product database 33. The providing unit 44 then transmits the read information to the user terminal 100.

The learning unit 45 performs model learning. For example, when the user information and attribute information of a certain user are input into a model, the learning unit 45 determines the combination of insurance-related products proposed to that user based on a rule base. The model is trained using a learning method such as backpropagation to output information indicating the combination of insurance-related products. In addition, for example, when a combination of insurance-related products is proposed to a certain user, the learning unit 45 may select the insurance-related products that are highly rated by the user among the insurance-related products included in the combination, or Identify the insurance-related products that the person actually subscribed to. Then, when the user information and attribute information of the user are input into the model, the learning unit 43 identifies insurance-related products that are highly rated by the user and insurance-related products that the user has actually subscribed to. The model is trained to output information indicating product combinations.

[3. Processing procedure]
Next, the procedure of the determination process by the information providing apparatus 10 according to the embodiment will be described using FIG. 6. FIG. 6 is a flowchart illustrating an example of the flow of determination processing according to the embodiment. As shown in FIG. 6, the information providing device 10 acquires user information (step S101), and estimates the user's attributes from the user information (step S102). In such a case, the information providing device 10 estimates the probability that an event guaranteed by each insurance-related product will occur based on the estimated attributes (step S103). Then, the information providing device 10 determines the proportion of expenses to be allocated to each type of insurance-related product based on the estimated accuracy (step S104), and based on the determination result, the insurance-related product to be proposed to the user. A combination of the following is determined (step S105). Thereafter, the information providing device 10 provides the determined combination of insurance-related products (step S106), and ends the process.

[4. Modified example]
The information providing device 10 described above may be implemented in various different forms other than the embodiments described above. Therefore, other embodiments of the information providing device 10 will be described below.

[4-1. About the information providing device]
For example, the information providing device 10 may implement the above-described processing by an acquisition device that obtains user information and a decision device that executes the above-described decision processing working together. In such a case, the acquisition device will have the acquisition section 41 shown in FIG. 2, and the determination device will have the estimation section 42 and the determination section 43. Furthermore, each of the databases 31 to 34 registered in the storage unit 30 may be managed by, for example, an external storage server or the like.

[4-2. others〕
Further, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, and conversely, the processes described as being performed manually can be performed manually. All or part of this can also be performed automatically using known methods. In addition, information including the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured.

Furthermore, the embodiments described above can be combined as appropriate within a range that does not conflict with the processing contents.

[4-3. program〕
Further, the information providing apparatus 10 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in FIG. 7, for example. FIG. 7 is a diagram showing an example of the hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 connected by a bus 1090. has.

The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and performs various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic unit 1030 for various calculations. Further, the secondary storage device 1050 is a storage device in which data used by the arithmetic unit 1030 for various calculations and various databases are registered, and includes ROM (Read Only Memory), HDD (Hard Disk Drive), flash memory, etc. This is realized by

The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various information such as a monitor or a printer, and is, for example, a USB (Universal Serial Bus), a DVI (Digital Visual Interface), This is realized using a connector compliant with standards such as HDMI (registered trademark) (High Definition Multimedia Interface). Further, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, and a scanner, and is realized by, for example, a USB or the like.

Note that the input device 1020 is, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), or a tape. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Furthermore, the input device 1020 may be an external storage medium such as a USB memory.

Network IF 1080 receives data from other devices via network N and sends it to computing device 1030, and also sends data generated by computing device 1030 to other devices via network N.

Arithmetic device 1030 controls output device 1010 and input device 1020 via output IF 1060 and input IF 1070. For example, the arithmetic device 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040, and executes the loaded program.

For example, when the computer 1000 functions as the information providing device 10, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 40 by executing a program loaded onto the primary storage device 1040.

[5. effect〕
As described above, the information providing device 10 acquires user information related to the user. Then, the information providing device 10 determines a combination of insurance-related products to be proposed to the user from a plurality of insurance-related products related to insurance, based on the user information. Therefore, the information providing device 10 can show the combination of a plurality of insurance-related products that are estimated to be appropriate for the user, and can therefore suggest an appropriate insurance form.

Furthermore, the information providing device 10 determines a combination of insurance-related products of different types as a combination of insurance-related products. Furthermore, the information providing device 10 determines a combination of insurance-related products including at least one of life insurance, non-life insurance, accident insurance, disease insurance, personal pension insurance, or nursing care insurance. The information providing device 10 also determines combinations of insurance-related products provided by different vendors. Therefore, the information providing device 10 can propose appropriate insurance types.

Furthermore, the information providing device 10 estimates the user's attributes based on the user information, and determines a combination of insurance-related products to be proposed to the user according to the estimation result. In this way, the information providing device 10 estimates the user's persona based on the user information and determines the combination of insurance-related products according to the estimated persona, so that the information providing device 10 can provide appropriate insurance according to the user's persona. Aspects can be proposed.

Furthermore, the information providing device 10 estimates the user's demographic attributes and psychographic attributes as the user's attributes, and responds to the user according to the combination of the estimated demographic attributes and psychographic attributes. and determine the combination of insurance-related products to be proposed. Therefore, for example, the information providing device 10 can propose a combination of life insurance and liability insurance to a man in his 30s who likes motorcycles, that is, a user who is likely to cause motorcycle accidents.

The information providing device 10 determines a combination of insurance-related products according to the probability that an event related to the estimated user attribute and guaranteed by the insurance-related product will occur. Therefore, the information providing device 10 can propose insurance-related products that guarantee against events that are more likely to occur.

Furthermore, the information providing device 10 determines cost allocation for a plurality of insurance-related products of different types based on the user information, and selects each type of insurance-related product based on the determined cost allocation. . For example, among insurance-related products, the information providing device 10 allocates costs to insurance-related products of a type that guarantees an event that has a higher probability of occurring than other events guaranteed by the insurance-related product, compared to other types of insurance-related products. of insurance-related products. Therefore, the information providing device 10 can propose combinations that place emphasis on insurance-related products that guarantee events that are more likely to occur.

Further, the information providing device 10 acquires, as user information, behavior information indicating the user's behavior on the Internet. Therefore, the information providing device 10 can suggest appropriate insurance types to the user without requiring the user to input various information in order to obtain a combination of insurance-related products.

Although the embodiments of the present application have been described above in detail based on the drawings, this is merely an example, and various modifications and improvements can be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to implement the invention in other forms.

Further, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc. For example, the estimating section can be replaced with estimating means or estimating circuit.

10 information providing device 20 communication unit 30 storage unit 31 user information database 32 user attribute database 33 insurance-related product database 34 model database 40 control unit 41 acquisition unit 42 estimation unit 43 determination unit 44 provision unit 45 learning unit 100 user terminal

Claims (7)

an acquisition unit that acquires user information related to the user;
From the user information acquired by the acquisition unit using a model trained to estimate the probability of an event guaranteed by an insurance-related product related to insurance occurring from the user information of the user, Estimate the probability that the event will occur, determine the cost allocation for each type of insurance-related product corresponding to each different event based on the estimated probability, and based on the determined cost allocation for each type , A determining device comprising: a determining unit that determines a combination of insurance-related products to be proposed to a user. The determining device according to claim 1, wherein the determining unit determines a combination of insurance-related products of different types as the combination of insurance-related products. Claim 1 or claim 1, wherein the determining unit determines a combination of insurance-related products including at least one of life insurance, non-life insurance, accident insurance, disease insurance, personal pension insurance, or nursing care insurance. 2. The determination device according to 2. The determining device according to any one of claims 1 to 3, wherein the determining unit determines a combination of insurance-related products provided by different companies. an estimation unit that estimates demographic attributes and psychographic attributes of the user as attributes of the user;
The determining unit uses, as the model, a model trained to estimate the probability that the event occurs from a combination of demographic attributes and psychographic attributes, and determines the demographic attributes estimated by the estimating unit. and psychographic attributes, to estimate the probability that the event will occur in the user, and to determine a combination of insurance-related products to be proposed to the user based on the estimated probability. The determining device according to claim 4. A determination method performed by a determination device, comprising:
an acquisition step of acquiring user information related to the user;
Using a model trained to estimate the probability of an event guaranteed by an insurance-related product related to insurance occurring from the user information of the user, from the user information acquired in the acquisition step, Estimate the probability that the event will occur, determine the cost allocation for each type of insurance-related product corresponding to each different event based on the estimated probability, and based on the determined cost allocation for each type , A determining method comprising: determining a combination of insurance-related products to be proposed to a user. an acquisition procedure for acquiring user information related to the user;
Using a model trained to estimate the probability of occurrence of an event guaranteed by an insurance-related product related to insurance from the user information of the user, from the user information acquired by the acquisition procedure, Estimate the probability that the event will occur, determine the cost allocation for each type of insurance-related product corresponding to each different event based on the estimated probability, and based on the determined cost allocation for each type , A determination program for causing a computer to execute a determination procedure for determining a combination of insurance-related products to be proposed to a user.

Images