JP2020135480A - Providing device, providing method, and providing program - Google Patents

Abstract

To offer adequate information for a user.SOLUTION: A providing device includes an estimation part and a providing part. The estimation part estimates an event in which occurrence possibility satisfies a predetermined condition based on user information showing a user's information. The providing part provides a user with information regarding insurance corresponding to the event estimated by the estimation part.SELECTED DRAWING: Figure 1

Description

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

Conventionally, there has been known a technique of proposing information to a user according to various attribute information such as a user's gender and age. As an example of such a technique, there is known a technique of selecting an insurance product that can be underwritten based on the age and gender of the user and the illness affected, and recommending the selected insurance product.

Japanese Unexamined Patent Publication No. 2014-232527

However, the above-mentioned conventional technique has not always been able to propose appropriate information for the user. For example, the above-mentioned prior art merely proposes an insurance product that can be underwritten based on the age and sex of the user and the illness suffered. Therefore, in the above-mentioned conventional technology, for example, there is a risk of proposing an insurance product having contents that are not so necessary for the user.

The present application has been made in view of the above, and an object of the present application is to provide a providing device, a providing method, and a providing program that propose more appropriate information to a user.

The providing device according to the present application relates to an estimation unit that estimates an event that is likely to occur in the future and satisfies a predetermined condition based on the user information indicating the user information, and insurance corresponding to the event estimated by the estimation unit. It is characterized by having a providing unit that provides information to the user.

According to one aspect of the embodiment, information appropriate for the user can be proposed.

FIG. 1 is a diagram showing an example of a provision process according to an embodiment. FIG. 2 is a diagram showing a configuration example of the provision system according to the embodiment. FIG. 3 is a diagram showing a configuration example of the terminal device according to the embodiment. FIG. 4 is a diagram showing a configuration example of the providing device according to the embodiment. FIG. 5 is a diagram showing an example of a user information storage unit according to the embodiment. FIG. 6 is a diagram showing an example of the model information storage unit according to the embodiment. FIG. 7 is a diagram showing an example of the insurance information storage unit according to the embodiment. FIG. 8 is a flowchart showing an example of the provision process according to the embodiment. FIG. 9 is a flowchart showing an example of the provision process according to the embodiment. FIG. 10 is a hardware configuration diagram showing an example of a computer that realizes the function of the providing device.

Hereinafter, a providing device, a providing method, and a mode for carrying out the providing program (hereinafter referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. It should be noted that this embodiment does not limit the providing device, providing method, and providing program according to the present application. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

(Embodiment)
[1. An example of information processing]
First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of information processing according to an embodiment. FIG. 1 shows an example in which information processing according to an embodiment is executed by the providing device 100.

[Configuration of information processing system]
Prior to the description of FIG. 1, the configuration of the providing system 1 will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the provision system according to the embodiment. As shown in FIG. 2, the terminal device 10 and the providing device 100 are included. The terminal device 10 and the providing device 100 are communicably connected by wire or wirelessly via a predetermined network N. The providing system 1 shown in FIG. 2 may include a plurality of terminal devices 10 and a plurality of providing devices 100.

The terminal device 10 is an information processing device used by a user who is considering taking out insurance (hereinafter, appropriately referred to as a "user"). The terminal device 10 is realized by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. In the following, the terminal device 10 may be referred to as a user. That is, in the following, the user can be read as the terminal device 10.

The providing device 100 is, for example, an information processing device such as a PC or WS (Work Station), and performs processing based on information transmitted from the terminal device 10 via the network N.

Before returning to the description of FIG. 1, a comparison between the provided processing according to the embodiment and the prior art will be described. Conventionally, there has been known a technique for proposing an insurance product that can be underwritten based on the age and gender of the user and the illness affected. However, with the above-mentioned conventional technology, it is not always possible to propose appropriate information for the user because there is a risk of proposing an insurance product whose content is not so necessary for the user. To give a specific example, in the above-mentioned conventional technology, since it merely proposes insurance products that are recalled from the attributes of the user and the illness that he / she has suffered from, he has traveled a lot in Japan, but he will travel a lot overseas in the future. There was a risk of proposing a generous insurance product in Japan to users who had cancer, or of proposing cancer insurance after treatment of the onset cancer.

The providing device 100 according to the embodiment includes an estimation unit that estimates an event that is likely to occur in the future and satisfies a predetermined condition based on the user information indicating the user information, and insurance corresponding to the event estimated by the estimation unit. It is characterized by having a providing unit that provides information about the user. In this way, the providing device 100 estimates an event that is likely to occur in the future for the user and provides insurance, so that it is possible to propose appropriate information for the user.

Hereinafter, an example of the providing process will be described with reference to FIG. First, a process of estimating an event in which the providing device 100 satisfies a predetermined condition for the possibility of occurring in the future will be described. In the embodiment according to FIG. 1, the providing device 100 shows an example of estimating an event related to a disease (hereinafter, appropriately referred to as “disease”) as an example of the event. The providing device 100 generates a model based on the correlation (relationship) between the user information indicating the user information and the disease affected by the user (step S101). In other words, the providing device 100 trains the model to learn the correlation between the user information and the disease affected by the user. For example, the providing device 100 trains a model using user information predetermined as correct answer data, and generates a model that reflects the learning result.

Specifically, the providing device 100 learns the correlation between the information regarding the transition of the user's life log (hereinafter, appropriately referred to as “time series data”) and the disease affected by the user as a model. More specifically, the providing device 100 causes the model to learn the characteristics of time-series data such as the order (flow) and period of the life log and the correlation with the disease. To give a specific example, the providing device 100 learns the correlation between the life log order such as “change of job → promotion” and the disease such as “hypertension”. In addition, the providing device 100 learns the correlation between the order of life logs such as "weight gain → increase in food intake" and diseases such as "increased blood glucose level". The life log may be information on the user's lifestyle (living environment), information on the user's health, information on the user's lifestyle, and information on the user's surrounding environment.

Then, the providing device 100 uses the generated model to estimate a disease that satisfies a predetermined condition that the user to be evaluated may be affected in the future (step S102). In addition, the providing device 100 may estimate the timing at which the disease occurs. For example, the providing device 100 may estimate the timing at which the possibility of developing a disease is equal to or greater than a predetermined threshold value. Then, the providing device 100 provides information on insurance corresponding to the estimated illness to the user to be evaluated (step S103). The insurance provided may be one-to-one correspondence with the estimated illness or may include (cover) the estimated illness. To give a specific example, when the presumed disease is cancer, the providing device 100 transmits information on cancer insurance related to cancer to the terminal device 10 used by the user to be evaluated. For example, when the presumed illness is diabetes, the providing device 100 transmits information on insurance covering the diabetes to the terminal device 10 used by the user to be evaluated. For example, when the presumed illness is diabetes, the providing device 100 may transmit insurance to the terminal device 10 that covers illnesses such as cancer and cerebral infarction in addition to diabetes.

The case of user U1 in FIG. 1 shows that the providing device 100 generates model MO1 based on the correlation between the user information of user U1 and the disease affected by user U1. More specifically, in the case of the user U1, the providing device 100 is affected by the information (time series data) regarding the transition of the user's lifestyle included in the user information UINF1 which is the user information of the user UI and the user U1. It is shown that the model MO1 is generated based on the correlation with the information about the disease (for example, the disease or the timing when the disease occurs). Information about the disease affected by the user U1 may or may not be included in the user information UINF1. In other words, the information about the disease affected by the user U1 may or may not be included in the user information of the user U1. That is, the information about the event that has occurred to the user may or may not be included in the user information. In the case of the user U1, the providing device 100 learns the correlation between the time series data of the user U1 and the information about the disease of the user U1 using the correct answer data, and generates a model MO1 that reflects the learning result. Is shown. Here, the time-series data that is the correct answer data is the information before the outbreak of the disease. In the example of FIG. 1, the time-series data that are the correct answer data for the disease 11 are life # 11 and life # 12. In this case, the providing device 100 generates a model that learns the correlation between the time series data up to life # 12 and the disease 11. In other words, the providing device 100 generates a model in which the transition of “life # 11 → life # 12” and the correlation with the disease 11 are learned. The time-series data that are the correct answer data for the disease 12 are life # 11 to life # 13. In this case, the providing device 100 generates a model that learns the correlation between the time series data up to life # 13 and the disease 12. In other words, the providing device 100 generates a model that learns the correlation between the transition of “life # 11 → life # 12 → life # 13” and the disease 12. In this way, the providing device 100 generates a model that learns the correlation between the time series data before the event occurred and the event. The time series data may be information in a period considered to be short-term, information in a period considered to be medium-term, or information in a period considered to be long-term. For example, the time series data may be the information of the user in the past week, the information of the past year, or the information of the past 10 years.

The case of user U2 in FIG. 1 shows that the providing device 100 uses the model MO1 generated in the case of user U1 to estimate a disease that the user U2 is likely to suffer in the future to meet certain conditions. Specifically, in the case of the user U2, the providing device 100 inputs the user time series data included in the user information UINF2, which is the user information of the user U2, into the model MO1, and the user U2 is affected in the future. Demonstrate estimating information about fistula (eg, illness or when the illness occurs). The case of user U2 indicates that the providing device 100 provides user U2 with insurance corresponding to information about the presumed illness.

Hereinafter, the model generated by the providing device 100 will be described. The providing device 100 generates a model for operating the computer so as to output an index value indicating the possibility that an event will occur in the future for the user based on the correlation between the user information and the event. In the example of FIG. 1, when the providing device 100 inputs the time series data of the user U1 based on the correlation between the time series data of the user U1 and the disease affected by the user U1, the user U1 is affected. Generate a model to make the computer work so that it outputs an index value indicating the possibility of developing a disease. When the time series data of the user U1 is input, the providing device 100 learns the model so that the disease affected by the user U1 outputs a higher index value than the disease not affected by the user U1. I do. The providing device 100 may output an index value indicating the possibility of the disease affecting the user U1 occurring, and may output an index value indicating the possibility of the timing of the disease affecting the user U1. ..

Hereinafter, model learning will be described with reference to FIG. For example, FIG. 1 shows that illness 11 occurred in the transition from life # 12 to life # 13 of user U1 and illness 12 occurred in the transition from life # 13 to life # 14 of user U1. In this case, for example, when the providing device 100 inputs information similar to the transition from life # 12 to life # 13 of user U1, the providing device 100 inputs information not similar to the transition from life # 12 to life # 13 of user U1. The model is trained so as to output an index value of a value at which the disease 11 is more likely to occur than in the case of the above. Further, the providing device 100 outputs an index value of a value at which the disease 11 is more likely to occur than the disease 12 when the information corresponding to the transition from the life # 12 to the life # 13 of the user U1 is input. Learn the model. To give a specific example, the providing device 100 learns so that the bit indicating the correlation between the information corresponding to the transition from life # 12 to life # 13 of the user U1 and the disease 11 becomes “1”. .. Further, when the providing device 100 inputs information similar to the transition from the life # 13 to the life # 14 of the user U1, the providing device 100 inputs information not similar to the transition from the life # 13 to the life # 14 of the user U1. The model is trained so as to output an index value of a value at which the disease 12 is likely to occur. Further, the providing device 100 outputs an index value of a value at which the disease 12 is more likely to occur than the disease 11 when the information corresponding to the transition from the life # 13 to the life # 14 of the user U1 is input. Learn the model. To give a specific example, the providing device 100 learns so that the bit indicating the correlation between the information corresponding to the transition from life # 13 to life # 14 of the user U1 and the disease 12 becomes “1”. .. As described above, the providing device 100 is a model based on the correlation between the time-series data until the onset of the disease and the disease, and when the time-series data which is the correct answer data is input, the bit showing the correlation. The model is trained so that is "1".

Further, the providing device 100 may generate a model for guessing a disease which is the correct answer data by using the user's time series data as a feature. Specifically, the providing device 100 may generate a model in which what kind of information is given what kind of weight is reflexively learned from the time series data which is a feature. In other words, the providing device 100 may generate a model showing which of the time-series data acquired as the correct answer data affects the "correlation with the disease". In addition, the providing device 100 may generate a model for guessing the timing at which a disease, which is the correct answer data, occurs, using the user's time series data as a feature. Specifically, the providing device 100 generates a model showing which of the time-series data acquired as correct answer data affects the "correlation with the timing at which the disease occurs". You may.

In the above embodiment, the information regarding the transition of the user's lifestyle is used as time-series data, but any information may be used as time-series data as long as the information is related to the transition of the user's state. For example, information on the transition of the user's health may be used as time series data. Specifically, information on the user's health such as "hypertension" or "loss of appetite" may be used as time-series data. Further, in this case, the providing device 100 uses the model based on the correlation between the information indicating the user's health such as health # 11 and health # 12 and the event instead of the information such as life # 11 and life # 12. Generate. In addition, information on changes in the lifestyle of the user may be used as time-series data. Specifically, information on the user's lifestyle such as "beginning to drink coffee", "quit smoking", or "begin to exercise" may be used as time-series data. Further, in this case, the providing device 100 generates a model based on the correlation between the information indicating the user's lifestyle such as habit # 11 and habit # 12 and the event. In addition, information on changes in the user's surrounding environment may be used as time-series data. Specifically, information on the user's surrounding environment such as "the situation of the town to go to" or "the weather of the flight to be boarded" may be used as time-series data. Further, in this case, the providing device 100 generates a model based on the correlation between the event and the information indicating the user's surrounding environment such as environment # 11 and environment # 12.

Further, in the above embodiment, the providing device 100 shows an example of generating a model based on the user's time series data, but any information may be used to generate the model as long as it is user information. For example, the providing device 100 may generate a model based on information and events related to the user's health. In this case, the user information UINF1 shown in FIG. 1 includes information on the health of the user. For example, the user information UINF1 includes information on the user's answer to a question about the health condition and information on the result of the health examination. As a specific example, the providing device 100 may generate a model based on the correlation between the user's blood pressure value and diabetes. For example, the providing device 100 may generate a model trained so that the higher the blood pressure value, the higher the possibility of developing diabetes. For example, the providing device 100 may generate a model based on the correlation between the number of times a user has been bitten by a bee in the past and death. In addition, the providing device 100 may generate a model based on information and events related to the lifestyle of the user. In this case, the user information UINF1 shown in FIG. 1 includes information on the lifestyle of the user. For example, the user information UINF1 includes information on the user's answer to a question about lifestyle habits and information on the result of a lifestyle diagnosis. To give a specific example, the providing device 100 may generate a model based on the correlation between the number of times coffee is drunk per day and diabetes. Further, the providing device 100 may generate a model based on information and an event regarding the user's surrounding environment. In this case, the user information UINF1 shown in FIG. 1 includes information about the user's surrounding environment. For example, the user information UINF1 includes information about an event at a travel destination to which the user is going to travel. Specifically, the user information UINF1 contains information that many people are infected with a certain disease at the travel destination where the user travels, and that many Japanese people staying in the area are infected with a certain disease. It contains information such as being infected. As a specific example, the providing device 100 may generate a model based on the correlation between the weather of the flight and the plane crash. For example, the providing device 100 may generate a model trained so that the more rough the weather in the flight, the higher the possibility of an airplane accident.

Further, in FIG. 1, the providing device 100 shows an example of estimating an event related to a disease as an example of an event, but any event may be estimated. For example, the providing device 100 may estimate an event related to an accident. In this case, the providing device 100 generates a model showing the correlation between the user information and the event related to the accident. Further, when estimating an event related to an accident, the providing device 100 provides information on insurance corresponding to the event related to the estimated accident. For example, the providing device 100 provides information on death insurance if the presumed event is a plane crash. In addition, the providing device 100 may estimate an event related to a natural disaster. In this case, the providing device 100 generates a model showing the correlation between the user information and the event related to the natural disaster. Further, when estimating an event related to a natural disaster, the providing device 100 provides information on insurance corresponding to the estimated event related to the natural disaster. For example, the providing device 100 provides information on earthquake insurance, fire insurance, and home insurance when the estimated event is an earthquake.

In addition, the providing device 100 may estimate the schedule of admission to a cram school or a private school. In this case, the providing device 100 generates a model showing the correlation between the user information and the schedule of admission to a cram school or a private school. Then, the providing device 100 provides student insurance corresponding to the schedule of admission to a cram school or a private school. Further, the providing device 100 may estimate that the number of movements and driving by car increases. In this case, the providing device 100 generates a model showing the correlation between the user information and the increase in movement and driving by car. Then, the providing device 100 provides non-life insurance corresponding to the increase in movement and driving by car. In addition, the providing device 100 may estimate that the number of trips will increase. In this case, the providing device 100 generates a model showing the correlation between the user information and the increase in travel. Then, the providing device 100 provides travel insurance corresponding to the increase in travel.

The user information according to the above embodiment may include information indicating user attributes. For example, the user information may include information on the user's gender, age, income, occupation, and the like. In this case, the providing device 100 may generate a model using user information limited to each user attribute. For example, the providing device 100 may generate a model only for user information of a user who is similar in income to the user to be evaluated. In addition, the user information may include information on the user's family. In this case, the providing device 100 may generate a model using the information of the user's family as the user information. For example, the providing device 100 may generate a model using the husband's user information, the wife's user information, and the child's user information in a predetermined family. Further, the providing device 100 may generate a model using the husband's user information and the wife's user information as the child's user information in the predetermined family. In addition, the user information may include the user information of a colleague who works in the same workplace. In this case, the providing device 100 may generate a model using the user information of a colleague at work.

[2. Terminal device configuration]
Next, the configuration of the terminal device 10 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the terminal device 10 according to the embodiment. As shown in FIG. 3, the terminal device 10 includes a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

(Communication unit 11)
The communication unit 11 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 11 is connected to the predetermined network N by wire or wirelessly, and transmits / receives information to / from the providing device 100 via the predetermined network N.

(Input unit 12)
The input unit 12 receives various operations from the user. For example, the input unit 12 may accept various operations from the user via the display surface by the touch panel function. Further, the input unit 12 may accept various operations from the buttons provided on the terminal device 10 and the keyboard and mouse connected to the terminal device 10.

(Output unit 13)
The output unit 13 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. Further, the output unit 13 outputs the information transmitted from the providing device 100. For example, the output unit 13 outputs information about insurance transmitted from the providing device 100.

(Control unit 14)
The control unit 14 is, for example, a controller, and various programs stored in a storage device inside the terminal device 10 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like are stored in a RAM (Random Access Memory). ) Is executed as a work area. For example, the various programs include programs of applications installed in the terminal device 10. For example, the various programs include an application program that displays information transmitted from the providing device 100. Further, the control unit 14 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. 3, the control unit 14 has a transmission unit 141 and a reception unit 142, and realizes or executes the information processing operation described below.

(Transmission unit 141)
The transmission unit 141 transmits the user information to the providing device 100. For example, the transmission unit 141 transmits the user information to the providing device 100 in response to the operation of the user who uses the terminal device 10.

(Receiver 142)
The receiving unit 142 receives the information transmitted from the providing device 100. For example, the receiving unit 142 receives the insurance information transmitted from the providing device 100.

[3. Configuration of provided equipment]
Next, the configuration of the providing device 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram showing a configuration example of the providing device 100 according to the embodiment. As shown in FIG. 4, the providing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The providing device 100 has an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from the administrator of the providing device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. May be good.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC or the like. Then, the communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the terminal device 10 via the network N.

(Memory unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 4, the storage unit 120 includes a user information storage unit 121, a model information storage unit 122, and an insurance information storage unit 123.

The user information storage unit 121 stores the user information of the user. Here, FIG. 5 shows an example of the user information storage unit 121 according to the embodiment. As shown in FIG. 5, the user information storage unit 121 has items such as "user ID", "user information", and "event".

The "user ID" indicates identification information for identifying the user. "User information" indicates user information. The "user information" is not limited to information on the lifestyle of the user, but may indicate information on the health of the user, information on the lifestyle of the user, and information on the surrounding environment of the user. In the example shown in FIG. 5, it is shown that the "user information" of the user ID "U1" includes "life # 11", "life # 12", "life # 13" and the like. Here, an example in which conceptual information such as "life # 11" and "life # 12" is stored in "user information" is shown, but in reality, content data is stored. For example, "user information" stores content data related to the user's lifestyle. "Event" indicates an event that has occurred to the user. The "event" is not limited to an event related to an illness, but may indicate an event related to an accident or an event related to a natural disaster. In the example shown in FIG. 5, it is shown that the "event" of the user ID "U1" includes "disease 11", "disease 12", "disease 13" and the like. Here, an example in which conceptual information such as “disease 11” or “disease 12” is stored in the “event” is shown, but in reality, content data is stored. For example, the "event" stores content data about the disease that the user has suffered. In addition, the "event" may include information regarding the timing at which the event occurs.

Although not shown in FIG. 5, the "user information" may include items such as "user information 1", "user information 2", and "user information 3". In this case, "Life # 11" of the user ID "U1" corresponds to "User information 1", "Life # 12" corresponds to "User information 2", and "Life # 13" corresponds to "User information 3". It may correspond to. Further, although not shown in FIG. 5, the "event" may include items such as "event 1", "event 2", and "event 3". In this case, "disease 11" of the user ID "U1" may correspond to "event 1", "disease 12" may correspond to "event 2", and "disease 13" may correspond to "event 3". ..

The model information storage unit 122 stores the model generated by the providing device 100. Specifically, the model information storage unit 122 stores a model generated by using the information stored in the user information storage unit 121. Here, FIG. 6 shows an example of the model information storage unit 122 according to the embodiment. As shown in FIG. 6, the model information storage unit 122 has items such as “model ID” and “calculation formula (model)”.

The "model ID" indicates identification information for identifying the generated model. The "calculation formula (model)" indicates a calculation formula used for calculating an index value indicating the possibility of an event occurring for the user. In the example shown in FIG. 6, the item of the calculation formula (model) is shown by a concept such as "MO # 1", but in reality, the item of the calculation formula (model) is a concrete formula. Is remembered. As the calculation formula (model), any formula may be adopted as long as it is a formula for calculating an index value indicating the possibility that an event will occur using the information included in the user information. In the example shown in FIG. 1, the "calculation formula (model)" stores a specific formula for calculating an index value indicating the possibility of developing a disease affecting the user U1 using the time series data of the user U1. Will be done.

The insurance information storage unit 123 stores information related to insurance. For example, the insurance information storage unit 123 stores information such as what kind of event the insurance covers. Here, FIG. 7 shows an example of the insurance information storage unit 123 according to the embodiment. As shown in FIG. 7, the insurance information storage unit 123 has items such as “insurance ID”, “insurance”, and “event”.

“Insurance ID” indicates identification information for identifying insurance. "Insurance" indicates information about insurance. For example, "insurance" indicates the name of insurance and the type of insurance. Specifically, "cancer insurance" is stored in "insurance". “Insurance” may also indicate information about the amount covered by the insurance. Specifically, the "insurance" may store information such as "full cover" or "partial cover". “Insurance” may also indicate information about the conditions under which insurance is applied. Specifically, the "insurance" may store conditions such as "up to 60 years old" and "women only". Although an example in which conceptual information such as "XYZ1" and "XYZ2" is stored in "insurance" is shown here, content data is actually stored. “Event” refers to an event covered by insurance. The "event" is not limited to an illness, an accident or a natural disaster, and may indicate any event. Further, the "event" may indicate a plurality of events. In the example shown in FIG. 7, it is shown that the “event” of the insurance ID “H1” includes “disease X11”. Thus, an "event" may indicate an event relating to a particular disease. Further, it is shown that the "event" of the insurance ID "H2" includes "illness X21" and "illness X22". Thus, an "event" may refer to an event relating to a plurality of specific diseases. Further, it indicates that the insurance ID "H3" includes "accident Y31" and "accident Y32". Thus, the "event" may indicate an event relating to a particular accident. Further, it is shown that the insurance ID "H4" includes "illness X41", "accident Y42", and "natural disaster Z43". In this way, the "event" may indicate a plurality of different events. Although an example in which conceptual information such as "illness X11", "accident Y21", and "natural disaster Z43" is stored in "event" is shown here, content data is actually stored.

Although not shown in FIG. 7, the "event" may include items such as "event 1", "event 2", "event 3", and "event 4". In this case, the "disease X11" of the insurance ID "H1" may correspond to the "event 1". Further, the "disease X21" of the insurance ID "H2" may correspond to the "event 1", and the "disease X22" may correspond to the "event 2".

(Control unit 130)
The control unit 130 is a controller, and is realized by, for example, a CPU, an MPU, or the like executing various programs stored in a storage device inside the providing device 100 using the RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC or FPGA.

As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, a generation unit 132, an estimation unit 133, and a provision unit 134, and realizes or executes the information processing operation described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may be another configuration as long as it is a configuration for performing information processing described later.

(Acquisition unit 131)
The acquisition unit 131 acquires user information. The acquisition unit 131 acquires the user information transmitted from the terminal device 10. For example, the acquisition unit 131 acquires user information transmitted from the user's terminal device 10 which is predetermined as correct answer data. For example, the acquisition unit 131 acquires the user information transmitted from the terminal device 10 of the user to be evaluated. Further, the acquisition unit 131 stores the acquired user information in the user information storage unit 121.

For example, the acquisition unit 131 acquires information on the transition of the user's lifestyle. In this way, the acquisition unit 131 may acquire information regarding the transition of the user's state. For example, the acquisition unit 131 may acquire information on the health of the user. For example, the acquisition unit 131 may acquire information on the lifestyle of the user. For example, the acquisition unit 131 may acquire information about the user's surrounding environment.

The acquisition unit 131 acquires information about an event that has occurred to the user. The acquisition unit 131 acquires information regarding the timing of the event that has occurred. In addition, the acquisition unit 131 acquires the information about the event in association with the user information. For example, the acquisition unit 131 acquires the timing of the event that has occurred in association with the user information. In addition, the acquisition unit 131 stores information about the acquired event in the user information storage unit 121. For example, the acquisition unit 131 stores the acquired event information and the user information in the user information storage unit 121 in association with each other.

For example, the acquisition unit 131 acquires information about the disease that the user has suffered. For example, the acquisition unit 131 may acquire information about an accident suffered by the user. For example, the acquisition unit 131 may acquire information about a natural disaster involving the user.

(Generator 132)
The generation unit 132 generates a model based on the correlation between the user information and the event. For example, the generation unit 132 generates a model based on the information acquired by the acquisition unit 131. For example, the generation unit 132 generates a model based on the information stored in the user information storage unit 121. Further, the generation unit 132 stores the generated model in the model information storage unit 122.

To give a specific example, the generation unit 132 generates a model based on the correlation between the user's time series data and the disease that the user has suffered. In other words, the generation unit 132 trains the model to learn the correlation between the user's time series data and the disease affected by the user, and generates a model that reflects the learning results. In the example of FIG. 1, the generation unit 132 generates the model MO1 based on the correlation between the information on the transition of the user's lifestyle and the disease affected by the user.

Further, the generation unit 132 is a model that is generated based on the correlation between the user information and the event, and outputs a model that outputs an index value indicating the possibility that the event occurs when the user information is input. Generate. Further, the generation unit 132 is a model generated based on the correlation between the timing at which the possibility of an event occurring is equal to or higher than a predetermined threshold value and the user information, and the timing is when the user information is input. You may generate a model that outputs.

Further, when the timing at which the possibility of an event occurring is less than the first predetermined threshold value, the generation unit 132 corresponds to less than the first predetermined threshold value among the elements showing the correlation. A model trained so that the value of the weighting coefficient becomes larger as the weighting coefficient of the element to be used may be generated. For example, when an event is likely to occur in a short period of time. In this case, the generation unit 132 generates a model trained so that the weighting coefficient of the element showing the correlation, which has a stronger meaning of affecting the event in the short term, becomes large. In this case, the generation unit 132 learns the model so as to output an event that is likely to occur in a short period of time with a high index value rather than an event that is unlikely to occur in a short period of time. Do. In this case, the generation unit 132 learns so that the bit indicating the correlation between the timing at which the event below the first predetermined threshold value occurs and the short-term event becomes “1”.

In addition, when the timing at which the possibility that an event occurs is equal to or greater than the predetermined threshold value is equal to or greater than the first predetermined threshold value and less than the second predetermined threshold value, the generation unit 132 is the third element showing the correlation. A model trained so that the value of the weighting coefficient becomes larger as the weighting coefficient of the element corresponding to the predetermined threshold value of 1 or more and less than the second predetermined threshold value may be generated. For example, when an event is likely to occur during the medium period. In this case, the generation unit 132 generates a model trained so that the weighting coefficient of the element showing the correlation, which has a stronger meaning of affecting the event in the medium term, becomes large. In this case, the generation unit 132 learns the model so as to output an event that is likely to occur in the medium period with a high index value rather than an event that is unlikely to occur in the medium period. Do. In this case, the generation unit 132 sets the bit indicating the correlation between the timing at which the event that is equal to or greater than the first predetermined threshold and less than the second predetermined threshold occurs and the event in the middle period to be “1”. Do learning.

Further, when the timing at which the possibility of an event occurring is equal to or greater than a predetermined threshold value is equal to or greater than the second predetermined threshold value, the generation unit 132 corresponds to the second predetermined threshold value or more among the elements showing the correlation. A model trained so that the value of the weighting coefficient becomes larger as the weighting coefficient of the element to be used may be generated. For example, when an event is likely to occur over a long period of time. In this case, the generation unit 132 generates a model trained so that the weighting coefficient of the element showing the correlation, which has a stronger meaning of affecting the event in the long term, becomes large. In this case, the generation unit 132 learns the model so as to output an event that is likely to occur in a long period of time with a high index value rather than an event that is unlikely to occur in a long period of time. Do. In this case, the generation unit 132 learns so that the bit indicating the correlation between the timing at which the event that exceeds the second predetermined threshold value occurs and the long-term event becomes “1”.

(Estimation unit 133)
Based on the user information, the estimation unit 133 estimates an event that satisfies a predetermined condition that may occur in the future for the user. For example, the estimation unit 133 estimates an event based on information indicating a transition of the user's state. For example, the estimation unit 133 may estimate an event based on information on the health of the user. For example, the estimation unit 133 may estimate an event based on information on the lifestyle of the user. For example, the estimation unit 133 may estimate an event based on information about the user's surrounding environment.

The estimation unit 133 estimates the timing at which the event occurs. For example, the estimation unit 133 estimates the timing at which the possibility that an event will occur becomes equal to or higher than a predetermined threshold value.

The estimation unit 133 estimates the event based on the model generated by the generation unit 132. For example, the estimation unit 133 estimates an event that satisfies a predetermined condition according to an index value output when user information is input, based on the model generated by the generation unit 132.

For example, the estimation unit 133 estimates an event related to a disease. For example, an event related to an accident may be estimated. For example, events related to natural disasters and man-made disasters may be estimated.

(Providing section 134)
The provider 134 provides information about insurance. The providing unit 134 provides information on insurance stored in the insurance information storage unit 123. The providing unit 134 transmits information about insurance to the terminal device 10 of the user to be evaluated. The providing unit 134 transmits information on insurance corresponding to the event estimated by the estimation unit 133 to the terminal device 10 used by the target user. Specifically, the providing unit 134 provides information on cancer insurance when the event estimated by the estimation unit 133 is cancer. For example, the provider 134 provides information about insurance that covers diabetes if the event estimated by the estimation unit 133 is diabetes. For example, the providing unit 134 provides information on earthquake insurance, fire insurance, and home insurance when the event estimated by the estimation unit 133 is an earthquake.

The provider 134 provides information about when an event occurs. The providing unit 134 provides information regarding the timing estimated by the estimation unit 133. For example, the provider 134 may provide information that there is a high probability of developing diabetes after 3 years. For example, the providing unit 134 may provide information to the effect that the user is likely to get sick based on the user information of seniors working in the same workplace. Further, the providing unit 134 provides information on insurance when the period up to the timing estimated by the estimation unit 133 is equal to or less than a predetermined threshold value. For example, the providing unit 134 reminds the information about insurance when the period until the timing estimated by the estimation unit 133 becomes equal to or less than a predetermined threshold value.

[4. Information processing flow]
Next, the procedure of information processing by the providing system 1 according to the embodiment will be described with reference to FIGS. 8 and 9. 8 and 9 are flowcharts showing the procedure of information processing by the providing system 1 according to the embodiment.

As shown in FIG. 8, the providing device 100 acquires user information and information about an event that has occurred in the user (step S201). For example, the providing device 100 acquires user information and information about an event in a predetermined period such as a short period, a medium period, or a long period. Further, the providing device 100 determines whether the number of acquired information is equal to or greater than a predetermined threshold value (step S202). Here, when the number of acquired information is less than a predetermined threshold value (step S202; NO), the providing device 100 waits until the number of acquired information becomes equal to or more than a predetermined threshold value. Further, when the number of acquired information is equal to or greater than a predetermined threshold value (step S202; YES), the providing device 100 generates a model based on the correlation between the acquired user information and the event (step S203). Then, the providing device 100 stores the generated model in a predetermined storage unit (step S204). For example, the providing device 100 stores the generated model in the model information storage unit 122.

As shown in FIG. 9, the providing device 100 determines whether or not the user information of the user to be evaluated has been acquired (step S301). For example, the providing device 100 determines whether the user information of the user to be evaluated has been accepted via the terminal device 10. Here, when the providing device 100 has not acquired the user information of the user to be evaluated (step S301; NO), the providing device 100 waits until the user information is acquired. Further, when the providing device 100 acquires the user information of the user to be evaluated (step S301; YES), the providing device 100 satisfies a predetermined condition that it may occur in the future based on the model stored in the predetermined storage unit. Estimate the event (step S302). In addition, the providing device 100 provides information on insurance corresponding to the estimated event (step S303).

[5. effect〕
As described above, the providing device 100 according to the embodiment has an estimation unit 133 and a providing unit 134. The estimation unit 133 estimates an event that satisfies a predetermined condition that may occur in the future for the user based on the user information indicating the user information. The providing unit 134 provides the user with information on insurance corresponding to the event estimated by the estimation unit 133.

As a result, the providing device 100 according to the embodiment can propose information appropriate for the user.

In addition, the estimation unit 133 estimates the event based on the information indicating the transition of the user's state.

As a result, the providing device 100 according to the embodiment can propose appropriate information according to the transition of the user.

In addition, the estimation unit 133 estimates an event based on information on the health of the user.

Thereby, the providing device 100 according to the embodiment can propose appropriate information according to the health of the user.

In addition, the estimation unit 133 estimates an event based on information on the lifestyle of the user.

As a result, the providing device 100 according to the embodiment can propose appropriate information according to the lifestyle of the user.

In addition, the estimation unit 133 estimates the event based on the information about the user's surrounding environment.

As a result, the providing device 100 according to the embodiment can propose appropriate information according to the surrounding environment of the user.

In addition, the estimation unit 133 estimates the timing at which the possibility that an event will occur becomes equal to or higher than a predetermined threshold value. In addition, the providing unit 134 provides information regarding the timing estimated by the estimation unit 133.

As a result, the providing device 100 according to the embodiment can propose information at an appropriate timing.

Further, the providing unit 134 provides information on insurance when the period up to the timing estimated by the estimation unit 133 is equal to or less than a predetermined threshold value.

As a result, the providing device 100 according to the embodiment can improve the appealing effect of the proposed information.

Further, the providing device 100 according to the embodiment is a model generated based on the correlation between the user information and the event, and sets an index value indicating the possibility of the event occurring when the user information is input. It has a generation unit 132 that generates a model to be output. Further, the estimation unit 133 estimates the event based on the model generated by the generation unit 132.

As a result, the providing device 100 according to the embodiment can propose information appropriate for the user.

Further, the generation unit 132 is a model generated based on the correlation between the timing at which the possibility of an event occurring is equal to or higher than a predetermined threshold value and the user information, and the timing is when the user information is input. Generate a model that outputs.

As a result, the providing device 100 according to the embodiment can propose information appropriate for the user.

Further, when the timing at which the possibility of an event occurring is less than the first predetermined threshold value, the generation unit 132 corresponds to less than the first predetermined threshold value among the elements showing the correlation. A model is generated so that the value of the weighting coefficient becomes larger as the weighting coefficient of the element to be used becomes larger.

As a result, the providing device 100 according to the embodiment can propose information appropriate for the user.

In addition, when the timing at which the possibility that an event occurs is equal to or greater than the predetermined threshold value is equal to or greater than the first predetermined threshold value and less than the second predetermined threshold value, the generation unit 132 is the third element showing the correlation. A model trained so that the value of the weighting coefficient becomes larger as the weighting coefficient of the element corresponding to the predetermined threshold value of 1 or more and less than the second predetermined threshold value is generated.

As a result, the providing device 100 according to the embodiment can propose information appropriate for the user.

Further, when the timing at which the possibility of an event occurring is equal to or greater than a predetermined threshold value is equal to or greater than the second predetermined threshold value, the generation unit 132 corresponds to the second predetermined threshold value or more among the elements showing the correlation. A model is generated so that the value of the weighting coefficient becomes larger as the weighting coefficient of the element to be used becomes larger.

As a result, the providing device 100 according to the embodiment can propose information appropriate for the user.

In addition, the estimation unit 133 estimates an event related to a disease as an event.

As a result, the providing device 100 according to the embodiment can propose appropriate information according to a predetermined event.

In addition, the estimation unit 133 estimates an event related to the accident as an event.

As a result, the providing device 100 according to the embodiment can propose appropriate information according to a predetermined event.

In addition, the estimation unit 133 estimates an event related to a natural disaster as an event.

As a result, the providing device 100 according to the embodiment can propose appropriate information according to a predetermined event.

[6. Hardware configuration]
Further, the terminal device 10 and the providing device 100 according to the above-described embodiment are realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the terminal device 10 and the providing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program that depends on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via a predetermined communication network and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the predetermined communication network.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the terminal device 10 and the providing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control units 14 and 130 by executing the program loaded on the RAM 1200. .. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via a predetermined communication network.

[7. Others]
Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

In addition, the above-described embodiments can be appropriately combined as long as the processing contents do not contradict each other.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to carry out the present invention in other improved forms.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

1 Information processing system 10 Terminal device 100 Providing device 110 Communication unit 120 Storage unit 121 User information storage unit 122 Model information storage unit 123 Insurance information storage unit 130 Control unit 131 Acquisition unit 132 Generation unit 133 Estimating unit 134 Providing unit N network

Claims (17)

An estimation unit that estimates an event that satisfies a predetermined condition that may occur in the future for the user based on the user information indicating the user's information.
A provider that provides the user with information about insurance corresponding to the event estimated by the estimate unit,
A providing device characterized by being equipped with. The estimation unit
The providing device according to claim 1, wherein the event is estimated based on information indicating a transition of the state of the user. The estimation unit
The providing device according to claim 2, wherein the event is estimated based on the information on the health of the user. The estimation unit
The providing device according to claim 2 or 3, wherein the event is estimated based on information on the lifestyle of the user. The estimation unit
The providing device according to any one of claims 2 to 4, wherein the event is estimated based on information about the user's surrounding environment. The estimation unit
Estimate the timing when the possibility that the event will occur exceeds a predetermined threshold value, and
The providing part
The providing device according to any one of claims 1 to 5, wherein information about the timing estimated by the estimation unit is provided. The providing part
The providing device according to claim 6, further comprising providing information on the insurance when the period up to the timing estimated by the estimating unit falls below a predetermined threshold value. A model that is generated based on the correlation between the user information and the event, and that outputs an index value indicating the possibility that the event will occur when the user information is input is generated. Further equipped with a generator
The estimation unit
The providing device according to any one of claims 1 to 7, wherein the event is estimated based on a model generated by the generation unit. The generator
It is a model generated based on the correlation between the timing when the possibility of the event occurring is equal to or higher than a predetermined threshold value and the user information, and when the user information is input, the timing is output. The providing apparatus according to claim 8, wherein the model is generated. The generator
When the timing at which the possibility that the event occurs is equal to or higher than the predetermined threshold value is less than the first predetermined threshold value, among the elements showing the correlation, the element corresponding to the lower than the first predetermined threshold value. The providing apparatus according to claim 9, wherein a model is generated so that the value of the weighting coefficient becomes larger as the weighting coefficient becomes larger. The generator
When the timing at which the possibility that the event occurs is equal to or greater than the predetermined threshold value is equal to or greater than the first predetermined threshold value and less than the second predetermined threshold value, the first predetermined element among the elements showing the correlation The providing apparatus according to claim 9, wherein a model is generated so that the value of the weighting coefficient becomes larger as the weighting coefficient of the element corresponding to the threshold value or more and less than the second predetermined threshold value becomes larger. The generator
When the timing at which the possibility that the event occurs is equal to or greater than the predetermined threshold value is equal to or greater than the second predetermined threshold value, among the elements showing the correlation, the element corresponding to the second predetermined threshold value or more The providing apparatus according to claim 9, wherein a model is generated so that the value of the weighting coefficient becomes larger as the weighting coefficient becomes larger. The estimation unit
The providing device according to any one of claims 1 to 12, characterized in that an event related to a disease is estimated as the event. The estimation unit
The providing device according to any one of claims 1 to 12, wherein an event related to an accident is estimated as the event. The estimation unit
The providing device according to any one of claims 1 to 12, characterized in that an event related to a natural disaster is estimated as the event. A delivery method performed by a computer
An estimation process that estimates an event that is likely to occur in the future and satisfies a predetermined condition based on the user information indicating the user information.
A providing process that provides the user with information on insurance corresponding to the event estimated by the estimation process, and
Providing method characterized by including. An estimation procedure that estimates events that may meet certain conditions in the future based on user information that indicates user information, and
Providing procedure for providing the user with information on insurance corresponding to the event estimated by the estimation procedure, and
A provided program characterized by having a computer execute.

Images