Information processing device, information processing method, and program

Abstract

A customer database 100 stores each of a plurality of agencies that sell at least one insurance product among a plurality of types of insurance products to customers, and information regarding the customers of each agency, in an associated manner. A sales information database 101 stores each of the plurality of agencies, and information regarding insurance products sold to the customers by each agency, in an associated manner. A model storage unit 102 stores a learning model that has undergone machine learning so as to input information regarding the customers and information regarding the insurance products sold by the agencies with the customers, and to output one or a plurality of digital contents for the agencies with the customers. A reception unit 120 receives a designated agency, which is an agency that has been designated from among the plurality of agencies. A model application unit 121 inputs information regarding customers of the designated agency and information regarding the insurance products of the designated agency to the learning model, and outputs digital contents for the designated agency.

Description

Information processing device, information processing method, and program

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

[0002] There are many types of insurance products, and even within the same type, there are products with different contents. For this reason, many customers who wish to purchase insurance products often receive explanations face-to-face from insurance sales representatives who sell insurance products at insurance agencies, etc. Patent Document 1 discloses a technology for supporting the sales activities of insurance sales representatives who sell insurance products to customers.

[0003] Japanese Patent Application Laid-Open No. 2007-26147

[0004] The above technology is intended to support insurance sales representatives when they are actually meeting customers face-to-face. However, insurance sales representatives often take time to get customers interested and begin selling face-to-face. As such, there is room for improvement in technology to support insurance agency sales.

[0005] The present invention has been made in consideration of these points, and has as its object to provide a technique for supporting the sales of insurance agents.

[0006] A first aspect of the present invention is an information processing device comprising: a customer database that stores information relating to each of a plurality of agents selling at least one insurance product among a plurality of types of insurance products to a customer, and the customer of each agent, in association with each other; a sales information database that stores information relating to each of the plurality of agents and the insurance products sold by each agent to a customer, in association with each other; a model storage unit that stores a learning model trained by machine learning to output one or more digital contents for the agent that has the customer when information relating to a customer and information relating to the insurance products sold by the agent that has the customer are input; a reception unit that receives a designated agent that is a designated agent from among the plurality of agents; and a model application unit that inputs information relating to the customer of the designated agent, obtained by referring to the customer database, and information relating to the insurance products of the designated agent, obtained by referring to the sales information database, into the learning model, and outputs digital content for the designated agent.

[0007] The information processing device may further include a content display unit that displays the digital content output by the learning model on the website of the designated agency.

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

[0009] The multiple types of insurance products may include automobile insurance that assumes the installation of a drive recorder, and the information about the customer may include location information and acceleration information obtained by the drive recorder.

[0010] The information about the customer may include personal attributes of the customer, the browsing history of websites visited by the customer, response records to insurance products, and the customer's past contract history.

[0011] The model memory unit may store a learning model that has been machine-learned for each customer so that, when information about the customer and information about the insurance products sold by the agency that has the customer are input, one or more digital contents for the agency that has the customer are output; the reception unit may further receive customer identification information for identifying a customer of the designated agency; and the model application unit may input information about the customer identified by the customer identification information obtained by reference to the customer database and information about the insurance products of the designated agency obtained by reference to the sales information database into a learning model for the customer identified by the customer identification information, and output digital content for the customer.

[0012] A second aspect of the present invention is an information processing method, in which a processor executes the following steps: accepting a designated agent, which is an agent designated from among a plurality of agents selling at least one insurance product among a plurality of types of insurance products to a customer; acquiring information about the designated agent's customers by referencing a customer database that stores information about each of the plurality of agents associated with each agent's customers; acquiring information about the designated agent's insurance products by referencing a sales information database that stores information about each of the plurality of agents associated with each agent's insurance products sold to customers; acquiring a learning model by referencing a model storage unit that stores a learning model trained by machine learning to output one or more digital content items for the agent who has the customer when information about a customer and information about the insurance products sold by the agent who has the customer are input; and inputting the information about the designated agent's customers acquired by referencing the customer database and the information about the designated agent's insurance products acquired by referencing the sales information database into the learning model, thereby outputting digital content items for the designated agent.

[0013] A third aspect of the present invention is a program that causes a computer to implement the following functions: accepting a designated agent, which 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; acquiring information about the designated agent's customers by referencing a customer database that stores information about each of the plurality of agents associated with each agent's customers; acquiring information about the designated agent's insurance products by referencing a sales information database that stores information about each of the plurality of agents associated with each agent's insurance products sold to customers; acquiring a learning model by referencing a model storage unit that stores a learning model trained by machine learning to output one or more digital content items for an agent that has a customer when information about a customer and information about the insurance products sold by an agent that has a customer are input; and inputting the information about the designated agent's customers acquired by referencing the customer database and the information about the designated agent's insurance products acquired by referencing the sales information database into the learning model, thereby outputting digital content items for the designated agent.

[0014] In order 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 over a communication line.

[0015] Any combination of the above components, and any transformation of the present invention into a method, device, system, computer program, data structure, recording medium, etc., are also valid aspects of the present invention.

[0016] According to the present invention, a technique for supporting the sales of insurance agents can be provided.

[0017] FIG. 1 is a diagram for explaining an overview of an information processing device according to an embodiment. FIG. 2 is a diagram schematically showing a functional configuration of an information processing device according to an embodiment. FIG. 3 is a diagram schematically showing a data structure of a customer database according to an embodiment. FIG. 4 is a diagram schematically showing a data structure of a sales information database according to an embodiment. FIG. 5 is a diagram schematically showing a data structure of a merchandise database according to an embodiment. FIG. 6 is a flowchart for explaining the flow of information processing executed by an information processing device according to an embodiment.

[0018] An information processing device 1 according to an embodiment is a device for customizing and providing digital content related to insurance products for each agency that handles insurance products. The digital content presented by the information processing device 1 according to an embodiment is, for example, the design of an agency's website, content to be posted on the website, digital data of materials to be distributed to customers, etc.

[0019] Here, an insurance company is an organization whose business is to develop insurance products to compensate for losses that may arise from accidental accidents, by calculating the amount of risk based on the policyholder's assets, how they are owned, how they are used, and how they are managed, as well as the environment, social conditions, and social trends of the area in which the policyholder lives. In contrast, an insurance agency (hereinafter referred to as "agency") is an organization commissioned by an insurance company to introduce insurance products to customers on behalf of the insurance company and provide after-sales support to customers who have signed insurance contracts. To use an analogy of industrial product manufacturing and sales, an insurance company is a company that develops and manufactures products, while an agency is a brick-and-mortar store or electronic commerce site that sells the products. Generally, customer contracts for automobile insurance or fire insurance consist of a combination of the above-mentioned coverages, such as a "personal liability rider" and an "attorney's rider." Therefore, even within the same automobile insurance policy, there are some that include an attorney's rider and some that do not. In this specification, contracts consisting of a combination of these coverages are referred to as "insurance products." Therefore, even if the type of automobile insurance is the same, there may be multiple different automobile insurance policies.

[0020] Insurance companies also provide their agents with digital content to be posted on their websites and explanatory pamphlets for sales. Insurance companies also share information about the insurance products handled by each of their nationwide agents, as well as information about each agent's customers and the products they have sold. In this respect, the relationship between an insurance company and its agents differs from the relationship between a manufacturer of industrial products and its retailers.

[0021] The information processing device 1 according to the embodiment is, for example, a server under the management of an insurance company, which aggregates and manages information on insurance products handled by each agency nationwide, customer information, and product sales. The information processing device 1 according to the embodiment also maintains and manages a learning model that outputs digital content to be recommended to each agency by using a known machine learning method based on information aggregated from agencies nationwide. By utilizing this learning model, the information processing device 1 according to the embodiment realizes providing digital content related to insurance products that is customized for each agency that handles the insurance products. Note that the information processing device 1 according to the embodiment only needs to be able to manage the learning model; the execution of machine learning for model generation, re-learning, etc. may be performed by another device.

[0022] Based on the above, an overview of the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining the overview of an information processing device 1 according to the embodiment.

[0023] An information processing device 1 according to an embodiment is connected to a plurality of agents in a manner that allows mutual communication via a communication network N using the Internet or a dedicated communication line. In the example shown in Fig. 1, a first agent A1 and a second agent A2 are shown, but generally, agents exist all over Japan, and their number is on the order of several thousand to several tens of thousands.

[0024] The information processing device 1 manages multiple databases generated by acquiring various information from each agency. Specifically, the information processing device 1 manages at least a customer database 100 that stores information relating to each agency and its customers in association with each other, a sales information database 101 that stores information relating to insurance products sold by each agency to its customers, and a model storage unit 102 that stores a learning model that outputs digital content to be presented to a specified agency.

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

[0026] Generally, insurance products handled by agencies vary from agency to agency, and even insurance products of the same type may have different contents. The insurance products suitable for an agency's customers may vary depending on the customer's date of birth and family structure, as well as the climate and customs of the area where the customer lives (i.e., the area where the agency is located). The information processing device 1 according to the embodiment can provide digital content suitable for each agency by utilizing a learning model generated by a machine learning technique based on the agent's customer information and past sales performance, etc. This allows sales staff working at the agency to present information suitable for the agency's customers, increasing the likelihood of stimulating their interest.

[0027] Furthermore, by aggregating customer information and sales information from each agency located throughout the country, it can be used as a common platform, so customer behavior data can be analyzed by customer attraction method, content, insurance type, etc., and accumulated as know-how. Therefore, the information processing device 1 can share with other agencies the effectiveness and areas for improvement of each agency's customer attraction method, website design, etc.

[0028] <Functional Configuration of Information Processing Device 1 According to an Embodiment> FIG. 2 is a diagram schematically illustrating the functional configuration of an information processing device 1 according to an embodiment. The information processing device 1 includes a storage unit 10, a communication unit 11, and a control unit 12. In FIG. 2, arrows indicate main data flows, and data flows not shown in FIG. 2 may also exist. In FIG. 2, each functional block indicates a configuration in functional units, rather than a configuration in hardware (device) units. Therefore, the functional blocks shown in FIG. 2 may be implemented in a single device, or may be implemented separately in multiple devices. Data may be exchanged between functional blocks via any means, such as a data bus, a network, or a portable storage medium.

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

[0030] The communication unit 11 is a communication interface for the information processing device 1 to communicate with external devices, 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, the description of the communication unit 11 may be omitted on the assumption that communication with external devices is via the communication unit 11.

[0031] The control unit 12 is a processor such as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit) of the information processing device 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 programs stored in the memory unit 10.

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

[0033] As described above, the information processing device 1 provides digital content suitable for each agent by utilizing a learning model generated by a machine learning technique based on the agent's customer information, past sales performance, etc. For this reason, the customer database 100 stores information on 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 on the customers of each agent.

[0034] FIG. 3 is a diagram schematically illustrating the data structure of the customer database 100 according to an 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 the agency's customer, and information about each customer are linked. For example, an agency with an agency identifier AID00001 has a customer with a customer identifier UID00001. Information about the customer with the customer identifier UID00001 includes the customer's name, date of birth, gender, occupation, family structure, and the like. Note that FIG. 3 also shows that the customer with the customer identifier UID00001 is also a customer of an agency with an agency identifier AID00002. In this way, the information processing device 1 centrally manages information about each agency and its customers across the country.

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

[0036] Returning to the explanation of FIG. 2 , the model storage unit 102 stores a learning model. This learning model is machine-trained so that, when information about a customer and information about insurance products sold by an agent who has the customer are input, it outputs one or more digital contents for the agent who has the customer. Machine learning can be realized, for example, using known deep learning.

[0037] The reception unit 120 receives a designated agent, which is an agent designated from among multiple agents. For example, when the reception unit 120 receives a request for the provision of digital content from an administrator of an agent who wishes to provide digital content, the reception unit 120 accepts the agent as a designated agent. The model application unit 121 inputs information about the designated agent's customers obtained by referring to the customer database 100 and information about the designated agent's insurance products obtained by referring to the sales information database 101 into a learning model, and outputs digital content for the designated agent. This allows the information processing device 1 to provide digital content suitable for each agent.

[0038] As described above, the digital content output by the learning model may be, for example, the design of an agency's website, content to be posted on the website, or digital data of materials to be distributed to customers. If the digital content output by the model application unit 121 to the learning model is content to be posted on a website, the content display unit 122 displays the digital content output by the learning model on the designated agency's website. Specifically, the content display unit 122 connects to the designated agency's website via an API (Application Programming Interface), returns the digital content output by the learning model in response to a request from the designated agency's website, and displays it on the designated agency's website. Alternatively, the content display unit 122 is a web server that manages the designated agency's website, and displays the digital content output by the learning model on the designated agency's website via a web server built on a domain under the management of the information processing device 1. This allows the information processing device 1 to update the designated agency's website without the assistance of the designated agency's staff.

[0039] Here, each of the multiple agents handles different insurance products. Therefore, it is preferable that the digital content that the information processing device 1 shows to each agent is digital content related to the insurance products handled by the agent. For this reason, the product database 103 stores, in association with each of the multiple agents that sell at least one insurance product to customers, and the type of insurance product that each agent handles from among the multiple types of insurance products.

[0040] 5 is a diagram schematically illustrating the data structure of the product database 103 according to an embodiment. In the example of the product database 103 illustrated in FIG. 5, an agency identifier is associated with the product identifier of the insurance product handled by the agency indicated by the agency identifier, and the type of insurance product. For example, an agency with an agency identifier AID00001 handles at least three insurance products identified by product identifiers MID00001, MID00002, and MID00003. The types of insurance products identified 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 insurance products handled by the designated agency from 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. This allows the information processing device 1 to provide digital content suitable for the agency.

[0042] The above describes examples of customer information including the customer's name, date of birth, gender, occupation, family structure, etc. However, by increasing the types of training data used to train the learning model, it is possible to increase the types of customer information input into the learning model.

[0043] For example, automobile insurance, which is one type of insurance product, includes automobile insurance with a drive recorder, which is based on the premise that the vehicle is equipped with a drive recorder. The drive recorder can acquire the location coordinates of the vehicle equipped with the drive recorder based on signals transmitted by positioning satellites, and can also calculate the vehicle's speed and acceleration from changes in the location coordinates over time. For customers who purchase such automobile insurance, the above-mentioned customer information includes the location information and acceleration information acquired by the drive recorder. In this case, the learning model is trained to also use the location information and acceleration information acquired by the drive recorder as input.

[0044] Location information from the drive recorder provides information about the area where the customer drives their car, and this information reflects the car's usage patterns in the area (such as whether it is in a mountainous area, whether there is snow, whether it is in an urban area, etc.). Acceleration information also reflects the customer's driving tendencies (such as whether they accelerate or decelerate suddenly). By incorporating information obtained from the drive recorder into the learning model, the car's usage patterns in the area where the agency is located can be reflected in the digital content for car insurance.

[0045] In addition to personal customer attributes such as name, date of birth, and occupation, the customer information may also include the customer's browsing history of websites visited, response records for insurance products, and the customer's past contract history. As described above, the information processing device 1 is communicatively connected to each agency and a web server managing each agency's website via the communication network N. This allows the information processing device 1 to acquire activity histories such as website browsing history and review posts by each agency's customers. Furthermore, if information is provided by other insurance companies affiliated with the insurance company managing the information processing device 1 or companies to which the insurance company's customer acquisition operations are outsourced, the information processing device 1 may also acquire the browsing history of those insurance company's websites. Furthermore, if the insurance company managing the information processing device 1 or its agency accepts insurance product purchases and consultations over the phone, the customer information may also include data obtained by converting conversations between operators and customers into text using voice analysis technology.

[0046] A customer's website browsing history can be useful information for estimating what insurance products the customer considered before purchasing the insurance product that they ultimately purchased. Also, if a customer who has purchased an insurance product writes about their evaluation of that insurance product on a website, the content of that comment can be useful information for estimating the positive or negative reaction to the insurance product. By including customers' website browsing history, reactions to insurance products, and past contract history in the learning model, the accuracy of the digital content presented to each agent can be improved.

[0047] The above describes a 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, the model storage unit 102 stores a learning model trained by machine learning for each customer so that, when information about the customer and information about insurance products sold by the agency that owns the customer are input, one or more digital contents for the agency that owns the customer are output. More specifically, the model storage unit 102 associates the learning model with a customer identifier and stores a learning model dedicated to the customer identified by the customer identifier.

[0048] In this case, the reception unit 120 further receives customer identification information for identifying the customer of the designated agency in addition to 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 a learning model for the customer identified by the customer identification information, and outputs digital content for the customer.

[0049] For example, if a customer has multiple agents, information about the customer at each of the agent's agents is input to the customer-specific learning model. Therefore, the customer-specific learning model uses not only information about the customer at the designated agent, but also information about customers at agents other than the designated agent as input, and outputs digital content for the customer. This allows the information processing device 1 to present each agent with digital content that is appropriate for each customer of each agent.

[0050] 6 is a flowchart illustrating the flow of information processing performed by the information processing device 1 according to the embodiment. The processing in this flowchart starts, for example, when the information processing device 1 is started.

[0051] The reception unit 120 receives a designated agent, which is an agent designated from among a plurality of agents who sell at least one of a plurality of types of insurance products to a customer (S2). The model application unit 121 refers to the customer database 100, which stores information relating to each of the plurality of agents and their customers in association with each other, and acquires information relating to the designated agent's customers (S4).

[0052] The model application unit 121 obtains information about the insurance products of the designated agents by referring to the sales information database 101, which stores information linked to each of the multiple agents and information about the insurance products that each agent has sold to customers (S6).

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

[0054] The model application unit 121 inputs information about the designated agent's customers, obtained by referring to the customer database 100, and information about the designated agent's insurance products, obtained 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 content for the designated agent (S12).

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

[0056] <Effects of the information processing device 1 according to the embodiment> As described above, the information processing device 1 according to the embodiment can provide a technology for supporting the sales of insurance agents.

[0057] The present invention has been described above using embodiments, but 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 of the present invention. For example, all or part of the device can be configured by functionally or physically distributing or integrating in any unit. Furthermore, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effects of the new embodiments resulting from the combination also have the effects of the original embodiments.

[0058] <Modification> In the above, the machine learning model has been mainly described as inputting information about a customer and information about insurance products sold by an agency that has the customer. This means that information about the customer and information about insurance products sold by an agency that has the customer are used as training data for the machine learning model. However, the information used to train the machine learning model is not limited to information about the customer and information about insurance products sold by an agency that has the customer. Other information may be used instead of or in addition to this.

[0059] Other examples of information include existing contract information between the insurance company and the customer (e.g., insurance information such as type, date of enrollment, and number of years of continuation, vehicle information, property information, and insurance claim history), event information (seasonal information such as typhoons, snowfall, and travel), life events such as marriage, childbirth, home purchase, and car purchase), and agent communication (communication history such as emails and social networking services, and information provided during phone calls and interviews).

[0060] REFERENCE SIGNS LIST 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 comprising: a customer database that stores information about each of a plurality of agents that sells at least one of a plurality of types of insurance products to customers, in association with each of the agents; a sales information database that stores information about each of the plurality of agents that links with each of the agents and information about the insurance products sold to customers by each of the agents; a model memory unit that stores a learning model that has been machine-learned to output one or more digital contents for the agent that has a customer when information about a customer and information about the insurance products sold by the agent that has the customer are input; a reception unit that accepts a designated agent that is an agent designated from among the plurality of agents; and 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.

2. The information processing device according to claim 1, further comprising a content display unit that displays the digital content output by the learning model on the website of the designated agency.

3. An information processing device as described in claim 2, further comprising: a product database that stores in association with a plurality of agencies that sell at least one insurance product from a plurality of types of insurance products to customers, and the type of insurance product handled by each agency from the plurality of types of insurance products; and a selection unit that refers to the product database to select digital content related to the insurance products handled by the designated agency from the digital content output by the learning model, wherein the content display unit provides the selected digital content to the website of the designated agency.

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

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

6. The information processing device of claim 1, wherein the model memory unit stores a learning model that has been machine-learned for each customer so as to output one or more digital contents for the agency that has the customer when information about the customer and information about the insurance products sold by the agency that has the customer are input, the reception unit further receives customer identification information for identifying a customer of the designated agency, and the model application unit inputs information about the customer identified by the customer identification information obtained by reference to the customer database and information about the insurance products of the designated agency obtained by reference 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.

7. An information processing method in which a processor executes the steps of: accepting a designated agent, which is a designated agent from among a plurality of agents that sell at least one of a plurality of types of insurance products to a customer; acquiring information about the customers of the designated agent by referring to a customer database that stores information about each of the plurality of agents and their customers in association with each other; acquiring information about the insurance products of the designated agent by referring to a sales information database that stores information about each of the plurality of agents and their insurance products sold to customers in association with each other; acquiring the learning model by referring to a model memory unit that stores a learning model trained by machine learning to output one or more digital contents for the agent who has the customer when information about a customer and information about the insurance products sold by the agent who has the customer are input; and inputting the information about the customers of the designated agent acquired by referring to the customer database and the information about the insurance products of the designated agent acquired by referring to the sales information database into the learning model to output digital content for the designated agent.

8. A program that enables a computer to realize the following functions: accepting a designated agent, which is an agent designated from among a plurality of agents that sell at least one of a plurality of types of insurance products to customers; referring to a customer database that stores information about each of the plurality of agents and their customers in association with each other, to acquire information about the designated agent's customers; referring to a sales information database that stores information about each of the plurality of agents and their insurance products sold to customers in association with each other, to acquire information about the designated agent's insurance products; 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 agent who has the customer when information about a customer and information about the insurance products sold by the agent who has the customer are input, to acquire the learning model; and inputting the information about the customers of the designated agent obtained by referring to the customer database and the information about the designated agent's insurance products obtained by referring to the sales information database into the learning model, to output digital content for the designated agent.

Images