Information processing device, information processing method, and program

Abstract

To support the business of an insurance agency.SOLUTION: A customer database 100 associates each of multiple agencies to sell at least one of insurance products among multiple types of insurance products to customers, with information about the customers of each agency and stores them. A sales information database 101 associates each of multiple agencies with information about the insurance products sold to the customers by each agency and stores them. A model storage unit 102 inputs information about the customers and the information about the insurance products sold by the agency having the customers and stores the learning model machine-learned to output one or multiple digital contents for the agency with the customer. A reception unit 120 accepts the designated agency which is the agency designated from the multiple agencies. A model application unit 121 inputs information about the designated agency customer and information about the insurance products of the designated agency into a learning model and outputs the digital contents for the designated agency.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] There are many types of insurance products, and even those of the same type may have different contents. For this reason, many customers who wish to purchase insurance products often receive explanations in person from insurance sales staff who sell insurance products at insurance agencies or the like. Patent Document 1 discloses a technique for supporting the sales activities of insurance sales staff who sell insurance products to customers.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The above technique assumes support at the time when insurance sales staff are actually conducting business face-to-face with customers. On the other hand, it often takes time for insurance sales staff to get the customer interested and start business face-to-face. Thus, it is considered that there is room for improvement in the technique for supporting the business of insurance agencies.

[0005] The present invention has been made in view of these points, and an object thereof is to provide a technique for supporting the business of insurance agencies.

Means for Solving the Problems

[0006] A first aspect of the present invention is an information processing apparatus. This apparatus includes a customer database that stores, in association with each of a plurality of agencies that sell at least one type of insurance product out of a plurality of types of insurance products to customers, information about the customers of each agency; a sales information database that stores, in association with each of the plurality of agencies, information about the insurance products sold by each agency to customers; a model storage unit that stores a learning model that has been machine-learned to output one or more digital contents for the agency that has a customer when information about the customer and information about the insurance products sold by the agency that has the customer are input; a reception unit that receives a designated agency that is a designated agency selected from among the plurality of agencies; and a model application unit that inputs the information about the customers of the designated agency obtained by referring to the customer database and the information about the insurance products of the designated agency obtained by referring to the sales information database into the learning model to output digital contents for the designated agency.

[0007] The information processing apparatus may further include a content display unit that causes the digital contents output by the learning model to be displayed on the website of the designated agency.

[0008] The information processing apparatus may further include a product database that stores, in association with each of a plurality of agencies that sell at least one type of insurance product out of a plurality of types of insurance products to customers, the types of insurance products handled by each agency; and a selection unit that refers to the product database and selects, from among the digital contents output by the learning model, the digital contents related to the insurance products handled by the designated agency. The content display unit may provide the selected digital contents to the website of the designated agency.

[0009] The plurality of types of insurance products may include automobile insurance premised on the installation of a drive recorder, and the information about the customer may include position information and acceleration information obtained by the drive recorder.

[0010] The information about the customer may include the attributes of the individual customer, the browsing history of the websites browsed by the customer, the response records of insurance materials, and the past contract history of the customer.

[0011] The model storage unit may store a learning model that is machine-learned for each customer so as to output one or more digital contents for the agency having the customer when information about the customer and information about the insurance materials sold by the agency having the customer are input. The reception unit may further receive customer identification information for identifying the customers of the designated agency. The model application unit may input information about the customer identified by the customer identification information obtained by referring to the customer database and information about the insurance materials of the designated agency obtained by referring to the sales information database into the learning model for the customer identified by the customer identification information, and output digital contents for the customer.

[0012] A second aspect of the present invention is an information processing method. In this method, a processor receives a designated agency, which is a designated agency selected from among a plurality of agencies that sell at least one type of insurance merchant material to customers, and refers to a customer database that stores each of the plurality of agencies in association with information about the customers of each agency, to obtain information about the customers of the designated agency. The processor also refers to a sales information database that stores each of the plurality of agencies in association with information about the insurance merchant materials sold by each agency to customers, to obtain information about the insurance merchant materials of the designated agency. The processor refers to a model storage unit that stores a learning model that has been machine-learned to output one or more digital contents for the agency that has the customer when information about the customer and information about the insurance merchant materials sold by the agency that has the customer are input, to obtain the learning model. Then, the processor inputs the information about the customers of the designated agency obtained by referring to the customer database and the information about the insurance merchant materials of the designated agency obtained by referring to the sales information database into the learning model, to cause the learning model to output digital contents for the designated agency.

[0013] A third aspect of the present invention is a program. This program causes a computer to have a function of accepting a designated agency, which is a designated agency selected from among a plurality of agencies that sell at least one type of insurance merchant material to customers, a function of referring to a customer database that stores and associates each of the plurality of agencies with information about the customers of each agency, and acquiring information about the customers of the designated agency, a function of referring to a sales information database that stores and associates each of the plurality of agencies with information about the insurance merchant materials sold by each agency to customers, and acquiring information about the insurance merchant materials of the designated agency, a function of referring to a model storage unit that stores a learning model that has been machine-learned to output one or more digital contents for the agency that has the customer when information about the customer and information about the insurance merchant materials sold by the agency that has the customer are input, and acquiring the learning model, and a function of inputting the information about the customers of the designated agency acquired by referring to the customer database and the information about the insurance merchant materials of the designated agency acquired by referring to the sales information database into the learning model, and causing the learning model to output digital contents for the designated agency.

[0014] To provide this program or to update a part of the program, a computer-readable recording medium on which this program is recorded may be provided, or this program may be transmitted via a communication line.

[0015] Note that any combination of the above-described components and a conversion of the expression of the present invention among a method, an apparatus, a system, a computer program, a data structure, a recording medium, etc. are also effective as aspects of the present invention.

Effects of the Invention

[0016] According to the present invention, it is possible to provide a technology for supporting the business of insurance agencies.

Brief Description of the Drawings

[0017]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Mode for Carrying Out the Invention

[0018] <Summary of the Embodiment> The information processing apparatus 1 according to the embodiment is an apparatus for customizing and providing digital content related to insurance merchandise for each agency handling the insurance merchandise. The digital content presented by the information processing apparatus 1 according to the embodiment is, for example, the design of the agency's website, the content posted on the website, the digital data of the materials distributed to customers, and the like.

[0019] Here, an insurance company is an organization that calculates the amount of risk based on the policyholder's owned property, the way it is owned, used, and managed, the environmental and social situation of the area where the policyholder lives, social trends, etc., and conducts as its business the development of insurance products to compensate for damages that may occur due to accidental accidents. On the other hand, an agency (insurance agency) is an organization that undertakes the work of being entrusted by an insurance company and guiding insurance products to customers on behalf of the insurance company, or providing after-follow-up services to customers who have contracted insurance products. If we were to draw an analogy to the manufacturing and sales of industrial products, the insurance company is the company that develops and manufactures products, and the agency corresponds to a physical store or an EC (electronic commerce) site that sells products. Generally, the objects that customers contract, such as auto insurance and fire insurance, are composed of the above-mentioned compensations, for example, combinations such as "personal injury liability endorsement" and "lawyer endorsement". For this reason, even for the same auto insurance, there will be auto insurance that includes a lawyer endorsement and auto insurance that does not. In this specification, the contract object composed of these multiple combinations of compensations is described as an "insurance product". Therefore, even if they are of the same type of auto insurance, there are multiple different auto insurances.

[0020] The insurance company also provides each agency with digital content to be posted on the agency's website for selling the company's insurance products, as well as sales brochures. In addition, the insurance company shares the information on the insurance products handled by each agency across the country, as well as the customer information and product sales information of each agency. In this regard, the relationship between the insurance company and its agencies is different from the relationship between a company that manufactures industrial products and a store that sells those industrial products.

[0021] The information processing apparatus 1 according to the embodiment is, for example, a server under the management of an insurance company, and aggregates and manages insurance sales materials, customer information, and information on sold products handled by each agency nationwide. The information processing apparatus 1 according to the embodiment also maintains and manages a learning model that outputs digital content for recommendation to each agency by using a known machine learning method based on the information aggregated from agencies nationwide. By using this learning model, the information processing apparatus 1 according to the embodiment realizes the customization and provision of digital content related to insurance sales materials for each agency handling the insurance sales materials. Note that the information processing apparatus 1 according to the embodiment only needs to be able to manage the learning model, and other apparatuses may execute machine learning for model generation, re-learning execution, and the like.

[0022] Based on the above, the outline of the embodiment will be described with reference to FIG. 1. FIG. 1 is a diagram for explaining the outline of the information processing apparatus 1 according to the embodiment.

[0023] The information processing apparatus 1 according to the embodiment is connected in a mode capable of mutually communicating with a plurality of agencies via a communication network N using the Internet or a dedicated communication line. In the example shown in FIG. 1, the first agency A1 and the second agency A2 are shown, but generally, agencies exist throughout Japan, and the number is on the order of thousands to tens of thousands.

[0024] The information processing apparatus 1 manages a plurality of databases generated by acquiring various information from each agency. Specifically, the information processing apparatus 1 manages at least a customer database 100 that stores by associating each agency with information regarding the customers of each agency, a sales information database 101 that stores information regarding insurance sales materials sold by each agency to customers, and a model storage unit 102 that stores a learning model that outputs digital content for presentation to a designated agency.

[0025] Here, the learning model stored in the model memory unit 102 is learned to output digital content suitable for the agency when at least information about the customers of the agency and information about the insurance products sold by the agency to the customers are input.

[0026] Generally, the insurance products handled by agencies vary from agency to agency, and even for the same type of insurance product, the content is different. And the insurance products suitable for the customers of an agency also vary depending on the customer's date of birth, family composition, and may also vary depending on the climate and habits of the region where the customer lives (i.e., the region where the agency is located). The information processing apparatus 1 according to the embodiment can provide digital content suitable for each agency by using a learning model generated by a machine learning method based on the customer information of the agency and past sales results, etc. Thereby, the sales staff working at the agency can present information suitable for the customers of that agency to the customers, and can increase the possibility of arousing the customers' interest.

[0027] Furthermore, since the customer information and sales information of each agency existing nationwide can be aggregated and used as a common base, it is possible to analyze the national core behavior data from perspectives such as different customer acquisition means, different types of content, and different insurance categories, and accumulate it as know-how. For this reason, the information processing apparatus 1 can expand the effects and improvement points such as the customer acquisition methods and the design of the website of each agency to other agencies as findings.

[0028] <Functional Configuration of Information Processing Apparatus 1 According to the Embodiment> FIG. 2 is a diagram schematically showing the functional configuration of the information processing apparatus 1 according to the embodiment. The information processing apparatus 1 includes a storage unit 10, a communication unit 11, and a control unit 12. In FIG. 2, the arrows indicate the main data flow, and there may be a data flow not shown in FIG. 2. In FIG. 2, each functional block shows a configuration in terms of function units, not in terms of hardware (device) units. Therefore, the functional blocks shown in FIG. 2 may be implemented in a single device, or may be divided and implemented in a plurality of devices. The exchange of data between the functional blocks may be performed via any means such as a data bus, a network, a portable storage medium, etc.

[0029] The storage unit 10 is a large-capacity storage device such as a ROM (Read Only Memory) that stores the BIOS (Basic Input Output System) of a computer that realizes the information processing apparatus 1, a RAM (Random Access Memory) that serves as a work area of the information processing apparatus 1, an OS (Operating System), an application program, a customer database 100, a sales information database 101, a model storage unit 102, a merchandise database 103, etc. that are referred to when the application program is executed, and an HDD (Hard Disk Drive), an SSD (Solid State Drive), etc.

[0030] The communication unit 11 is a communication interface for the information processing apparatus 1 to communicate with an external device, and is realized by a known communication module such as a LAN (Local Area Network) module or a Wi-Fi (registered trademark) module. Hereinafter, in this specification, when communicating with an external device, the description of the communication unit 11 may be omitted on the premise that it is via the communication unit 11.

[0031] The control unit 12 is a processor such as the CPU (Central Processing Unit) or GPU (Graphics Processing Unit) of the information processing apparatus 1, and functions as a reception unit 120, a model application unit 121, a content display unit 122, and a selection unit 123 by executing the program stored in the storage unit 10.

[0032] Note that FIG. 2 shows an example in the case where the information processing apparatus 1 is configured by a single device. However, the information processing apparatus 1 may be realized by computing resources such as a plurality of processors and memories, such as a cloud computing system. In this case, each unit constituting the control unit 12 is realized by at least one of the plurality of different processors executing a program.

[0033] As described above, the information processing apparatus 1 provides digital content suitable for each agency by using a learning model generated by a machine learning method based on the customer information of the agency and past sales results. For this reason, the customer database 100 stores, in association with each other, a plurality of agencies that sell at least one insurance product among a plurality of types of insurance products to customers, and information on the customers of each agency.

[0034] FIG. 3 is a diagram schematically showing the data structure of the customer database 100 according to the embodiment. In the example of the customer database 100 shown in FIG. 3, an agency identifier for identifying an agency, a customer identifier for identifying a customer of the agency, and information regarding each customer are associated. For example, in an agency with agency identifier AID00001, there is a customer with customer identifier UID00001. Further, as information regarding the customer with customer identifier UID00001, the customer's name, date of birth, gender, occupation, family composition, etc. are stored. Note that FIG. 3 shows that the customer with customer identifier UID00001 is also a customer of the agency with agency identifier AID00002. In this way, the information processing apparatus 1 centrally manages information regarding each agency existing nationwide and information regarding customers of the agencies.

[0035] FIG. 4 is a diagram schematically showing the data structure of the sales information database 101 according to the embodiment. The sales information database 101 stores, in association with each of a plurality of agencies, information regarding insurance products sold by the agencies to customers. In the example of the sales information database 101 shown in FIG. 4, for each agency identifier, a product identifier for identifying an insurance product handled by the agency, the type of the insurance product, a customer identifier indicating a customer who purchased the insurance product, etc. are associated as information regarding the insurance product. For example, an agency with agency identifier AID00001 handles an insurance product with product identifier MID0001. The type of the insurance product with product identifier MID0001 is automobile insurance, and at least customers with customer identifiers UID00001 and UID00002 have purchased it.

[0036] Returning to the description of FIG. 2, the model storage unit 102 stores a learning model. This learning model is a learning model that has been machine-learned to output one or more digital contents for an agency having a customer when information regarding the customer and information regarding an insurance product sold by the agency having the customer are input. Machine learning can be realized using, for example, known deep learning.

[0037] The reception unit 120 receives a designated agency, which is an agency designated from among a plurality of agencies. For example, when the reception unit 120 receives a request for providing digital content from the administrator of an agency that wishes to provide digital content, it receives that agency as the designated agency. The model application unit 121 inputs the information regarding the customers of the designated agency obtained by referring to the customer database 100 and the information regarding the insurance merchant materials of the designated agency obtained by referring to the sales information database 101 into the learning model, and causes the learning model to output digital content for the designated agency. Thereby, the information processing apparatus 1 can provide digital content suitable for each agency to that agency.

[0038] As described above, the digital content output by the learning model is, for example, the design of the agency's website, the content posted on the website, the digital data of the materials distributed to customers, and the like. When the digital content output by the model application unit 121 to the learning model is the content posted on the website, the content display unit 122 causes the digital content output by the learning model to be displayed on the website of the designated agency. Specifically, the content display unit 122 connects to the website of the designated agency via an API (Application Programming Interface), returns the digital content output by the learning model in response to a request from the designated agency website, and renders it on the designated agency website. Alternatively, the content display unit 122 is a web server that manages the website of the designated agency and is constructed on a domain under the management of the information processing apparatus 1, and causes the digital content output by the learning model to be displayed on the website of the designated agency via this web server. Thereby, the information processing apparatus 1 can update the website of the designated agency without relying on the staff of the designated agency.

[0039] Here, the insurance products handled by each of the multiple agencies are different. Therefore, it is preferable that the digital content shown by the information processing apparatus 1 to each agency is digital content related to the insurance products handled by the agency. For this reason, the product database 103 stores in association a plurality of agencies that sell at least one of a plurality of types of insurance products to customers, and the types of insurance products handled by each agency among the plurality of types of insurance products.

[0040] FIG. 5 is a diagram schematically showing the data structure of the product database 103 according to the embodiment. In the example of the product database 103 shown in FIG. 5, an agency identifier, a product identifier of the insurance product handled by the agency indicated by the agency identifier, and the type of the insurance product are associated. For example, an agency with an agency identifier of AID00001 handles at least three insurance products specified by product identifiers MID00001, MID00002, and MID00003. The types of insurance products specified by product identifiers MID00001, MID00002, and MID00003 are automobile insurance, earthquake insurance, and life insurance, respectively.

[0041] The selection unit 123 refers to the product database 103 and selects digital content related to the insurance products handled by the designated agency from among the digital content output by the learning model. The content display unit 122 provides the digital content selected by the selection unit 123 to the website of the designated agency. Thereby, the information processing apparatus 1 can provide digital content suitable for the agency.

[0042] As described above, as an example of information about a customer, the case where the customer's name, date of birth, gender, occupation, family composition, etc. are included has been described. However, by increasing the types of teacher data used for training the learning model, the types of information about the customer input to the learning model can be increased.

[0043] For example, among automobile insurance, which is one of multiple types of insurance products, there is automobile insurance with a drive recorder that assumes the installation of a drive recorder. The drive recorder can obtain the position coordinates of the automobile on which it is installed based on the signals transmitted by positioning satellites, and can also calculate the speed and acceleration of the automobile from the time change of the position coordinates. For customers who have purchased such automobile insurance, the position information and acceleration information obtained by the drive recorder are included as the information about the customers described above. In this case, the learning model is trained to take the position information and acceleration information obtained by the drive recorder as inputs.

[0044] From the position information of the drive recorder, information about the area where the customer uses the automobile can be obtained, and this information reflects the usage pattern of automobiles in the area (such as usage in mountainous areas, presence or absence of snow accumulation, whether it is an urban area or not, etc.). Also, from the acceleration information, the driving tendency of the customer (such as whether to make sudden accelerations or decelerations) is reflected. By including the information obtained from the drive recorder in the training of the learning model, the usage pattern of automobiles in the area where the agency is located can be reflected in the digital content for automobile insurance.

[0045] In addition to information about customers, such as their names, dates of birth, occupations, etc., the information about customers may also include the browsing history of the websites visited by the customers, the response records of insurance brochures, and the past contract history of the customers. As described above, the information processing device 1 is connected in a communicable manner to a web server that manages each agency and the websites of each agency via the communication network N. Therefore, the information processing device 1 can obtain the history of activities such as the browsing history of websites by the customers of each agency and the writing of evaluations. In addition to the agencies, if there is an offer from another insurance company that the insurance company managing the information processing device 1 is affiliated with or from a company that has entrusted the customer acquisition business, the browsing history of the website of that insurance company may be obtained. Furthermore, when the insurance company managing the information processing device 1 or its agency accepts purchases or consultations of insurance brochures by phone, data obtained by converting the conversation between the operator and the customer into a character string by voice analysis technology may also be included as information about the customer.

[0046] The browsing history of websites by customers can be powerful information for estimating what insurance brochures the customers were considering before finally purchasing the insurance brochures they purchased. Also, if a customer who has purchased an insurance brochure writes an evaluation on the website regarding that insurance brochure, the content can be powerful information for estimating the quality of the response regarding the insurance brochure. By including the browsing history of websites by customers, the response of insurance brochures, and the past contract history in the learning of the learning model, the accuracy of the digital content presented to each agency can be improved.

[0047] The above has described the case where the digital content output by the learning model is digital content suitable for each agency. Alternatively, the learning model may output digital content suitable for each customer. Specifically, when the model storage unit 102 inputs information about a customer and information about insurance products sold by the agency that has that customer, it stores a learning model that has been machine-learned for each customer to output one or more digital contents for the agency that has that customer. More specifically, the model storage unit 102 stores a learning model dedicated to the customer identified by the customer identifier, in association with the customer identifier.

[0048] In this case, in addition to the designated agency, the reception unit 120 further receives customer identification information for identifying the customers of the designated agency. The model application unit 121 inputs information about the customer identified by the customer identification information obtained by referring to the customer database 100 and information about the insurance products of the designated agency obtained by referring to the sales information database 101 into the learning model for the customer identified by the customer identification information, and outputs digital content for the customer.

[0049] For the learning model dedicated to the customer, for example, when the customer is a customer who spans multiple agencies, information about the customer at each agency of that customer is input. Therefore, the learning model dedicated to the customer outputs digital content for that customer using not only the information about the customer at the designated agency but also the information about the customer at other agencies other than the designated agency. Thereby, the information processing apparatus 1 can present digital content suitable for each customer of each agency to each agency.

[0050] <Processing flow of the information processing method executed by the information processing apparatus 1> FIG. 6 is a flowchart for explaining the flow of information processing executed by the information processing apparatus 1 according to the embodiment. The processing in this flowchart starts, for example, when the information processing apparatus 1 is activated.

[0051] The reception unit 120 receives a designated agency, which is an agency designated from among a plurality of agencies that sell at least one type of insurance product to customers (S2). The model application unit 121 refers to the customer database 100 that stores by associating each of the plurality of agencies with information about the customers of each agency, and acquires information about the customers of the designated agency (S4).

[0052] The model application unit 121 refers to the sales information database 101 that stores by associating each of the plurality of agencies with information about the insurance products sold by each agency to customers, and acquires information about the insurance products of the designated agency (S6).

[0053] The model application unit 121 refers to the model storage unit 102 that stores a learning model that has been machine-learned to output one or more digital contents for an agency having a customer when information about the customer and information about the insurance products sold by the agency having the customer are input, and acquires the learning model (S8).

[0054] The model application unit 121 inputs the information about the customers of the designated agency acquired by referring to the customer database 100 and the information about the insurance products of the designated agency acquired by referring to the sales information database 101 into the learning model (S10). As a result, the model application unit 121 causes the learning model to output digital contents for the designated agency (S12).

[0055] When the model application unit 121 causes the learning model to output digital contents, the processing in this flowchart ends.

[0056] <Effects achieved by the information processing apparatus 1 according to the embodiment> As described above, according to the information processing apparatus 1 according to the embodiment, it is possible to provide a technology for supporting the business of insurance agencies.

[0057] As described above, the present invention has been explained using embodiments. However, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist. For example, all or part of the device can be configured by functionally or physically dispersing and integrating it in any unit. Also, new embodiments resulting from any combination of multiple embodiments are included in the embodiments of the present invention. The effects of the new embodiments resulting from the combination have the effects of the original embodiments combined.

[0058] <Modification Example> Above, the case where the machine learning model inputs information about a customer and information about insurance products sold by an agency having the customer has been mainly described. This means using information about a customer and information about insurance products sold by an agency having the customer as teacher data for the machine learning model. However, the information used for learning the machine learning model is not limited to information about a customer and information about insurance products sold by an agency having the customer. Instead of these, or in addition to these, other information may be used.

[0059] As an example of other information, existing contract information between an insurance company and a customer (for example, insurance information such as item, enrollment date, number of continuous years, vehicle information, property information, health claim history), event information (seasonal information such as typhoons, snowfall, travel), life events such as marriage, childbirth, house purchase, car purchase, etc., and recruiter communication (communication history such as emails and social networking services, guidance content during phone calls and interviews) can be mentioned.

Explanation of Reference Numerals

[0060] 1 Information processing device 10 Storage unit 100 Customer database 101 Sales information database 102 Model storage unit 103 Product database 11 Communication unit 12 Control unit 120 Reception unit 121 Model Application Unit 122 Content Display Unit 123 Selection Unit N Communication Network

Claims

1. An information processing device, a customer database that stores information relating to each of a plurality of agents that sell at least one insurance product among a plurality of types of insurance products to a customer, in association with information relating to the customer of each agent; a sales information database that stores information relating to each of the plurality of agents and the insurance products sold by each agent to customers in association with each other; a model storage unit that stores a learning model that has been machine-learned to output one or more digital contents for an agent who has a customer when information about the customer and information about the insurance product sold by the agent who has the customer are input; a reception unit that receives a designated agent that is an agent designated from among the plurality of agents; a model application unit that inputs information about the designated agent's customers, obtained by referring to the customer database, and information about the designated agent's insurance products, obtained by referring to the sales information database, into the learning model, and outputs digital content for the designated agent; and a content display unit that displays the digital content output by the learning model on the website of the designated agent via a web server constructed on a domain under the management of the information processing device. Information processing device.

2. a product database that stores, in association with each other, a plurality of agents that sell at least one insurance product among a plurality of types of insurance products to customers and the type of insurance product that each agent handles among the plurality of types of insurance products; a selection unit that refers to the product database and selects digital content related to insurance products handled by the designated agency from the digital content output by the learning model; the content display unit provides the selected digital content to the registered agent's website; The information processing device according to claim 1 .

3. The plurality of types of insurance products include automobile insurance that assumes the installation of a drive recorder, The information about the customer includes location information and acceleration information acquired by the drive recorder. The information processing device according to claim 1 .

4. The information about the customer includes the customer's personal attributes, the browsing history of websites visited by the customer, response records to insurance products, and the customer's past contract history. The information processing device according to claim 1 .

5. the model storage unit stores a learning model that has been machine-learned for each customer so as to output one or more digital contents for the agent who has the customer when information about the customer and information about the insurance product sold by the agent who has the customer are input; the reception unit further receives customer identification information for identifying a customer of the designated agent; the model application unit inputs information about the customer identified by the customer identification information obtained by referring to the customer database and information about the insurance products of the designated agent obtained by referring to the sales information database into a learning model for the customer identified by the customer identification information, and outputs digital content for the customer. The information processing device according to claim 1 .

6. A processor of an information processing device, A step of accepting a designated agent that is a designated agent from among a plurality of agents that sell at least one insurance product among a plurality of types of insurance products to a customer; a step of obtaining information about the designated agent's customers by referring to a customer database that stores information about each of the plurality of agents and their customers in association with each other; a step of acquiring information about the insurance products of the designated agency by referring to a sales information database that stores information about each of the plurality of agencies and the insurance products sold to customers by each agency in association with each other; a step of acquiring a learning model by referring to a model storage unit that stores a learning model that has been machine-trained to output one or more digital contents for an agent who has a customer when information about the customer and information about the insurance product sold by the agent who has the customer are input; a step of inputting information about the designated agent's customers, obtained by referring to the customer database, and information about the designated agent's insurance products, obtained by referring to the sales information database, into the learning model, and outputting digital content for the designated agent; and displaying the digital content output by the learning model on the website of the designated agent via a web server established on a domain under the management of the information processing device. Information processing methods.

7. On the computer, A function of accepting a designated agent that is an agent designated from among a plurality of agents that sell at least one insurance product among a plurality of types of insurance products to a customer; a function of acquiring information about the designated agent's customers by referencing a customer database that stores information about each of the plurality of agents and their customers in association with each other; A function of acquiring information about the insurance products of the designated agency by referring to a sales information database that stores information about each of the plurality of agencies and the insurance products sold to customers by each agency in association with each other; a function of acquiring a learning model by referring to a model storage unit that stores a learning model that has been machine-trained to output one or more digital contents for an agent who has a customer when information about the customer and information about the insurance product sold by the agent who has the customer are input; and a function of inputting information about the designated agent's customers, obtained by referring to the customer database, and information about the designated agent's insurance products, obtained by referring to the sales information database, into the learning model, and outputting digital content for the designated agent; and realizing a function of displaying the digital content output by the learning model on the website of the designated agent via a web server constructed on a domain under the control of the computer. program.

Images