JP6980573B2 - Information processing equipment, information processing methods, and programs - Google Patents

Description

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

Conventionally, various measures for sales promotion have been proposed in consideration of the purchase situation of products and the like by customers. For example, using various information such as the sales conditions and the number of products sold, what is the status of the purchase of the product by the customer (for example, the situation of repetitive purchase, the situation of repetitive purchase). There is known a system for estimating whether or not a product is separated and no longer purchased (see, for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2010-73189

However, the conventional technology is related to the customer who visits the actual store, and the service using the network handles a huge number of products and stores, and the customer's usage environment is different from the actual store, so the conventional technology is applied. It was difficult to do.

The present invention has been made in consideration of such circumstances, and provides an information processing device, an information processing method, and a program capable of appropriately analyzing the usage status of a customer who uses a service using a network. One of the purposes is to provide.

One aspect of the present invention predetermines a user who has used a service via a network based on the relationship between the degree of use of the service and the suspension period from the last use date of the service to the present. It is an information processing apparatus including a classification unit that classifies the user types according to the classification unit and an analysis unit that analyzes the usage status of the service for each user belonging to the user type classified by the classification unit.

According to one aspect of the present invention, it is possible to appropriately analyze the usage status of a customer who uses a service using a network.

It is a schematic diagram of the information processing system 1 which concerns on embodiment. It is a block diagram of the information processing apparatus 300 which concerns on embodiment. It is a figure which shows an example of the contents of the usage status data 322 for each user. It is a figure which shows an example of the predetermined user type. It is a figure which shows an example of the contents of the user type definition information 323. It is a figure which shows an example of the content of the usage situation 324 by user type. It is a figure which shows an example of "the number of product categories per person". It is a figure which shows an example of "best store purchase ratio". It is a figure which shows an example of "purchaser ratio by product category". It is a flowchart which shows an example of the process executed in the information processing apparatus 300 which concerns on embodiment.

Hereinafter, embodiments of the information processing apparatus, information processing method, and program of the present invention will be described with reference to the drawings.

[Information processing system configuration]
FIG. 1 is a schematic diagram of an information processing system 1 according to an embodiment. The information processing system 1 includes, for example, one or more terminal devices 100, a service providing server 200, and an information processing device 300. These configurations are connected to each other by a network NW and communicate with each other via this network NW. The network NW includes, for example, a part or all of WAN (Wide Area Network), LAN (Local Area Network), the Internet, a dedicated line, a wireless base station, a provider, and the like.

The terminal device 100 is a terminal device having at least a communication function and a display function, such as a mobile phone such as a smartphone, a tablet terminal, a notebook-type or desktop-type personal computer, and a PDA (Personal Digital Assistant). The terminal device 100 is used by the user A who uses the service provided by the service providing server 200.

The service providing server 200 provides a service via the network NW. Hereinafter, an example in which the service providing server 200 provides a shopping service will be described. Further, the service providing server 200 acquires log data indicating the usage status of the shopping service by the user A and transmits the log data to the information processing apparatus 300 at a predetermined timing. This log data includes, for example, information about products (or shops) registered in favorites, information about products in a shopping cart, purchase history, browsing history, search history, member rank, and the like. The purchase history includes, for example, information on the date and time of purchase, the purchased product, the price of the product, the shop, and the like. The browsing history includes, for example, information about the browsed products, shops, and the like.

[Information processing device configuration]
Next, the configuration of the information processing apparatus 300 according to the embodiment will be described with reference to FIG. FIG. 2 is a configuration diagram of the information processing apparatus 300 according to the embodiment.

The information processing apparatus 300 includes, for example, a communication unit 310, a storage unit 320, an acquisition unit 330, a derivation unit 340, a classification unit 350, an analysis unit 360, a determination unit 370, and a distribution unit 380. The communication unit 310 includes, for example, a communication interface such as a NIC. The storage unit 320 is, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory such as an SSD, an HDD (Hard Disk Drive), or the like. In the storage unit 320, for example, log data 321 and user-specific usage status data 322, user type definition information 323, user type-specific usage status data 324, and the like are stored. The storage unit 320 may be an external storage device such as NAS (Network Attached Storage) that the information processing device 300 can access via a network.

A processor such as a CPU (Central Processing Unit) stores some or all of the acquisition unit 330, the derivation unit 340, the classification unit 350, the analysis unit 360, the determination unit 370, and the distribution unit 380 in the storage unit 320. It is realized by executing the program (software). Further, some or all of the functions of these components may be realized by hardware such as LSI, ASIC, FPGA (including circuit section: circuitry), or by cooperation between software and hardware. It may be realized.

The acquisition unit 330 transmits, for example, a log data transmission request to the service providing server 200. The acquisition unit 330 stores the log data received from the service providing server 200 in the storage unit 320 as the log data 321. Instead of this, the service providing server 200 may voluntarily transmit the log data to the information processing apparatus 300.

The derivation unit 340 derives the usage degree in the target period based on the log data 321 and stores the derived result in the storage unit 320 as a part of the user-specific usage status data 322. The target period is, for example, one year. The degree of use of the shopping service is information indicating how much the user uses the shopping service. Hereinafter, an example in which the degree of use of the shopping service is the number of purchases per year will be described. Not limited to this, the degree of use of the shopping service may be the purchase price per year, the number of views per year, the number of logins per year, the number of participation in campaigns per year, and the like. Campaigns include campaigns that increase the point award rate, campaigns that award points, and campaigns that sell a large number of sale items. Further, the degree of use of the shopping service may be a numerical value comprehensively evaluated based on this information.

Further, the derivation unit 340 derives the usage suspension period of the shopping service based on the log data 321 and stores the derived result in the storage unit 320 as a part of the user-specific usage status data 322. The period of suspension of use of the shopping service is the period from the last use date of the shopping service to the present. Hereinafter, an example in which the last usage date is the latest date included in the purchase history will be described. Not limited to this, the last usage date may be the latest date included in the browsing history, the latest date included in the search history, or the like. FIG. 3 is a diagram showing an example of the contents of the usage status data 322 for each user. The user-specific usage status data 322 is, for example, information in which a user ID is associated with a usage degree and a usage suspension period.

The classification unit 350 classifies the target user among the user A into a predetermined user type based on the relationship between the usage degree of the shopping service and the suspension period.

Here, an example of a user type will be described with reference to FIG. FIG. 4 is a diagram showing an example of a predetermined user type. FIG. 4 shows the relationship between the number of purchases per year and the purchase suspension period (the period from the last purchase date to the present). This relationship is not limited to the example of FIG. 4, and may be the relationship between the number of browsing times and the browsing suspension period, the relationship between the number of searches and the search suspension period, and the like.

In the example shown in FIG. 4, nine user types are defined according to the relationship between the number of purchases per year and the purchase suspension period. User types include, for example, a fan layer, a separation layer from a fan, a good user layer, a stable user layer, a separation fan layer, a separation layer from stability, a new layer, a separation layer from new, and a complete separation layer. Each user type is defined as shown in FIG. 4 according to the relationship between the number of purchases and the purchase suspension period. For example, the fan base is a user type having the largest number of purchases per year and the shortest purchase suspension period among the user types. The stable user group is a user type in which the number of purchases per year is an intermediate value and the purchase suspension period is also an intermediate value.

It should be noted that the ranking may be determined among a plurality of user types. For example, the nine user types mentioned above are arranged in order of proximity to the fan layer. This ranking is displayed in FIG. The distance to the fan layer is determined based on the definitions described below. For example, it is defined that the larger the number of purchases per year, the closer to the fan base, and the smaller the number of purchases per year, the farther from the fan base. It is also defined that the shorter the purchase suspension period, the closer to the fan base, and the longer the purchase suspension period, the farther from the fan base. In addition, it is defined that the longer the purchase suspension period, the stronger the tendency to separate. Further, it is defined that the user type having a large number of purchases as much as the fan group is closer to the fan group than the user type whose purchase suspension period is as short as the fan group. In addition, the number of purchases per year is an intermediate value and the period of suspension of purchase is an intermediate value, rather than the number of purchases per year or the period of suspension of purchase being less than or equal to the intermediate value. Is also defined as being close to the fan base. The classification unit 350 may determine the order of each user type by comprehensively evaluating the distance from the fan layer based on at least one of such definitions.

In FIG. 4, the layer separated from the fan, the excellent user layer, and the stable user layer are examples of user types close to the fan layer, and are hereinafter referred to as quasi-fan layers. The separation fan layer, separation layer from stability, new layer, separation layer from new, and complete separation layer are examples of user types far from the fan layer, and are hereinafter referred to as distant fan layers.

FIG. 5 is a diagram showing an example of the contents of the user type definition information 323. The user type definition information 323 is information that defines an example of the user type shown in FIG. As shown in FIG. 5, the user type definition information 323 is information in which the user type ID is associated with the number of purchases per year, the purchase suspension period, and the name of the user type. The user type ID is identification information for identifying each user type. In the user type definition information 323, the information about each user type is arranged from the top in the order of proximity to the fan layer.

The classification unit 350 refers to the user type definition information 323 and classifies the target user into a user type that matches both the usage degree of the shopping service and the suspension period based on the usage status data 322 for each user. ..

Note that the classification unit 350 may classify all users A into target users who satisfy a predetermined condition and non-target users who do not satisfy a predetermined condition before classifying them into user types. Then, the classification unit 350 classifies only the users classified as the target users into the user types. The predetermined conditions include, for example, the use of the shopping service within the target period, the fact that the customer does not fall under the category of a trader, and the like.

For example, the classification unit 350 classifies the trader users included in the user A based on the usage tendency of the shopping site by the user A, and classifies the individual users excluding the trader users from the user A into the user types. For example, when the usage status of the shopping service is far from the usage status by an individual user, the classification unit 350 classifies the user as a trader user. When the usage status of the shopping service is far from the usage status by individual users, for example, when the number of purchases in a predetermined period is equal to or greater than the threshold value, or when the number of purchases of products included in the same product category is equal to or greater than the threshold value. This includes cases where the number of purchases of products is equal to or greater than the threshold value across a plurality of product categories, and cases where the number of purchases in one purchase is equal to or greater than the threshold value. The threshold value may be determined for each product category or product.

The analysis unit 360 analyzes the usage status of the shopping service by the users belonging to the user type for each group of users belonging to the user type. When the user A is classified as either an individual user or a trader user by the classification unit 350, the analysis unit 360 analyzes the usage status of only the individual user or analyzes the usage status of only the trader user. May be good. The analysis unit 360 analyzes, for example, each predetermined item. The predetermined items include, for example, "number of product categories per person", "best store purchase ratio", "purchaser ratio by product category", "purchaser ratio by user type" and the like.

FIG. 6 is a diagram showing an example of the contents of the usage status 324 by user type. The usage status 324 for each user type is information indicating the analysis result by the analysis unit 360 for each user type. As shown in FIG. 6, the usage status 324 by user type corresponds to the number of product categories per person, the best store purchase ratio, the purchaser ratio by product category, and the purchaser ratio by user type in the user type ID. This is the attached information. The user type ID is identification information for identifying each user type.

The "number of product categories per person" is the number of product categories including products purchased by users belonging to each user type in the target period among a plurality of product categories prepared in the shopping service. The plurality of product categories are, for example, the highest category (first category) for classifying products, and include, for example, food, fashion, home appliances, sports, AV equipment, and the like. The first category includes a lower category (second category). For example, fashion includes ladies' fashion, men's fashion, watches / accessories, and the like. Hereinafter, an example in which the "number of product categories per person" is the number of the first category will be described, but the number may be the number of the second category or the number of categories lower than the second category. good.

FIG. 7 is a diagram showing an example of “the number of product categories per person”. In FIG. 7, the horizontal axis is the user type, and the vertical axis is the average value per person of the number of product categories including the products purchased within one year. For example, the analysis unit 360 obtains, as an analysis result, a tendency that the number increases as it approaches the fan layer and decreases as it moves away from the fan layer, based on the “number of product categories per person” shown in FIG. Further, the analysis unit 360 may obtain an analysis result that the stable user group does not correspond to this tendency. Further, the analysis unit 360 may obtain an analysis result that the number of product categories per person in the fan base is 8 or more on average. From these analysis results, it can be seen that the closer to the fan base, the wider the genre of products, except for the stable user base. In addition, from this analysis result, it can be seen that the fan base has a relatively strong desire to find good products and purchase products of various genres.

The "best store purchase ratio" is the ratio of the best store to all the net stores used by the users belonging to each user type. The best store is, for example, a mark given to a good shop in a shopping service. Whether or not the shop is excellent is determined based on criteria such as evaluation by user A, quality of content, and response of the shop. For example, the analysis unit 360 counts the number of best stores used by users belonging to each user type (the same shops are not duplicated) as the number of all online shops used by users belonging to each user type (same shop). Is not counted twice) to derive the best store purchase ratio.

FIG. 8 is a diagram showing an example of the “best store purchase ratio”. In FIG. 8, the horizontal axis is the user type, and the vertical axis is the best store purchase ratio. For example, the analysis unit 360 obtains, as an analysis result, a tendency that the “best store purchase ratio” shown in FIG. 8 increases as it approaches the fan layer and decreases as it moves away from the fan layer. From this analysis result, it can be seen that the fan base often shop at the best stores.

The "purchaser ratio by product category" is information showing the purchaser ratio, which indicates the ratio of the number of purchasers in each product category for each user type, by product category. The information showing the purchaser ratio by user type is the purchaser ratio by user type. The purchaser ratio is an example of usage frequency.

FIG. 9 is a diagram showing an example of “purchaser ratio by product category”. In FIG. 9, the horizontal axis is the user type and the vertical axis is the purchaser ratio. Although five product categories are illustrated in FIG. 9, the analysis unit 360 can also analyze five or more product categories. For example, the analysis unit 360 indicates that the "purchaser ratio by product category" shown in FIG. 9 is higher as it approaches the fan base in product categories (for example, AV equipment, home appliances, etc.) in which the unit price of products is often relatively high. As an analysis result, it is obtained that the product becomes lower as the distance from the fan layer increases. In addition, the analysis unit 360 indicates that the "purchaser ratio by product category" shown in FIG. 9 decreases as the product category (for example, fashion, food, etc.), in which the unit price of the product is often relatively low, approaches the fan base. Moreover, the tendency that the price increases as the distance from the fan layer increases is obtained as an analysis result. From this analysis result, the closer to the fan base, the higher the unit price of products such as AV equipment and home appliances is purchased, and the farther away from the fan base, the lower the unit price of products such as fashion and food is purchased. You can see that you are doing it. In addition, from these analysis results, it can be seen that the closer to the fan base, the higher the motivation to purchase even if there is a good product, even if it is a high-priced product.

In addition, in the purchaser ratio of "sports" shown in FIG. 9, the difference for each user type does not show a predetermined tendency. The predetermined tendency includes, for example, the above-mentioned tendency, such as a tendency that the number of purchasers increases as the distance from the fan layer increases, and a tendency that the number of purchasers increases as the distance from the fan layer increases. Of the analysis results, the analysis unit 360 may output only the analysis results in which the difference for each user type shows a predetermined tendency to the determination unit 370. By doing so, it is possible to exclude the analysis result in which the difference between the user types does not show a predetermined tendency from the target of the next step.

The decision unit 370 determines an approach for promoting the use of the shopping service based on the analysis result by the analysis unit 360. The approach includes promotions carried out in shopping services, means for notifying users of the promotions, and the like. Promotions include advertising, incentives, and sales. Advertisements include product and shop announcements. Incentives include points and discounts. The incentive may be given by limiting the target user to, for example, a person who has won a lottery, or by limiting the period.

For example, the decision unit 370 determines different approaches depending on each user type. For example, the determination unit 370 determines an approach for users belonging to the fan layer to be established in the fan layer (hereinafter referred to as a fan fixation approach). In addition, an approach for users belonging to the quasi-fan group to become a fan group (hereinafter referred to as a fan training approach) is determined. In addition, for users who belong to the distant fan group, an approach for getting them to become a quasi-fan group (hereinafter referred to as a quasi-fan training approach) is determined.

Further, the target of the fan training approach may be a part of the type included in the quasi-fan layer, and the target of the quasi-fan training approach may be a part of the type included in the distant fan layer. For example, it is assumed that the analysis unit 360 obtains the probability of shifting to another adjacent user type in FIG. 4 for each user type as an analysis result. The determination unit 370 may determine the approach for the user type with the highest probability of derivation in the quasi-fan layer (or distant fan layer) based on the derivation probability of the analysis unit 360.

[Fan retention approach]
The fan retention approach includes, for example, an approach for improving the satisfaction of the fan base, an approach for improving the purchase frequency of the fan base, and the like. Approaches to improving satisfaction include, for example, incentives, sale of bargain items (including sale items), and sale of limited items. Further, in order to further improve the satisfaction level, the announcement of the approach may be notified before the users other than the fan base. That is, the decision unit 370 may set the delivery timing of the fan retention approach to an effective timing for promoting the use of the shopping service (for example, one week before the user other than the fan base). Further, in order to further improve the satisfaction level, it is possible to notify only the fan base that measures such as giving incentives will be implemented. By doing so, it is possible to give a special feeling to the fan base and improve the satisfaction level.

Approaches for increasing the frequency of purchases by the fan base include, for example, advertisements for products belonging to product categories with a low percentage of purchasers in the fan base, and advertisements for the best stores. For example, it is assumed that the analysis unit 360 has obtained an analysis result that the number of product categories per person in the fan base is 8 or more on average, and the number of product categories is the largest among the user types. Based on this analysis result, the determination unit 370 determines an advertisement related to a product category having a low fan base purchaser ratio (for example, a ranking of intermediate or lower) among the product categories as a fan retention approach. Further, it is assumed that the analysis unit 360 has obtained the analysis result that the best store purchase ratio is the highest in the fan base. Based on this analysis result, the decision-making unit 370 decides the advertisement regarding the best store as a fan retention approach. By doing so, it is possible to satisfy the purchasing motivation of the fan base who wants to purchase even a high-priced product if there is a good product. In addition, by recommending products that belong to a product category with a low percentage of fan base purchasers, we will develop advertisements for products that the fan base has not yet purchased, satisfying the fan base's purchasing motivation as described above. Can be made to.

[Fan training approach]
The fan training approach includes, for example, an approach for getting closer to the usage status of the fan base. Approaches to get closer to the usage of the fan base include, for example, an approach to promote the lack of use in the quasi-fan layer in comparing the usage status of the fan layer with the usage status of the quasi-fan layer. .. For example, it is assumed that the analysis unit 360 has a shortage of "the number of product categories per person" of the quasi-fan layer as compared with the fan layer, and obtains the insufficient number as the analysis result. Further, it is assumed that the analysis unit 360 obtains a product category as an analysis result in which the "purchaser ratio by product category" of the quasi-fan group is lower than that of the fan group. Based on these analysis results, the decision-making unit 370 conducts a fan training approach to advertisements related to products belonging to a product category in which the "purchaser ratio by product category" of the fan group is higher than that of the quasi-fan group. To decide. Further, the determination unit 370 may determine the number of advertisements related to this product as corresponding to the number of product categories lacking a quasi-fan group as compared with the fan group.

In addition, the approach for approaching the usage status of the fan layer includes, for example, an approach related to a product or the like in which the usage frequency of the fan layer is higher than that of the quasi-fan layer. A product or the like includes at least one of a product or a store. For example, it is assumed that the analysis unit 360 has obtained an analysis result that the best store purchase ratio is the highest in the fan base. Based on the analysis result, the decision-making unit 370 decides the advertisement about the best store as a fan training approach. Further, it is assumed that the analysis unit 360 has obtained an analysis result that the ratio of purchasers of "home appliances" in the product category is the highest in the fan base. Based on this analysis result, the decision-making unit 370 decides the advertisement about the product included in the "home appliances" of the product category as a fan training approach.

[Semi-fan training approach]
The quasi-fan training approach includes, for example, an approach for approaching the usage status of the quasi-fan group. An approach to get closer to the usage status of the quasi-fan layer includes, for example, an approach to promote the insufficient utilization in the distant fan layer in comparison between the usage status of the quasi-fan layer and the usage status of the distant fan layer. included. It should be noted that this approach may be determined in the same manner as the above-mentioned approach for approaching the usage status of the fan base.

In addition, the approach for approaching the usage status of the quasi-fan layer may include an approach for improving the purchase frequency of the distant fan layer. Approaches to increasing the frequency of purchases by the far fan base include, for example, advertisements for products that belong to product categories that are easy for the far fan base to purchase, and advertisements for products in the price range that are easy for the far fan base to purchase. .. For example, it is assumed that the analysis unit 360 obtains a product category as an analysis result, which has a relatively high "purchaser ratio by product category" of a fan group far from the fan layer or the quasi-fan layer. Based on these analysis results, the decision-making unit 370 relates to products belonging to a product category in which the "purchaser ratio by product category" of the fan group far from the fan group or quasi-fan group is relatively high among the product categories. Decide on advertising as a quasi-fan training approach. Further, the decision unit 370 may decide the advertisement related to the product belonging to the product category in which the "purchaser ratio by product category" of the quasi-fan group is relatively high as compared with the fan group as the quasi-fan training approach.

Further, the determination unit 370 may determine an approach based on the analysis result for the product category in which the difference for each user type shows a predetermined tendency in the analysis result by the analysis unit 360. For example, the determination unit 370 determines the approach based on the rest of the analysis results based on the purchaser ratio of "sports" shown in FIG. 9 excluded from all the analysis results.

Further, the determination unit 370 may determine an approach to the individual user based on the usage status of only the individual user analyzed by the analysis unit 360. Further, the determination unit 370 may determine an approach to the vendor user based on the usage status of only the vendor user analyzed by the analysis unit 360. By doing so, it is possible to determine an approach suitable for each user's usage situation according to the difference between the usage situation of the individual user and the usage situation of the vendor user. For example, when the analysis result shows that the individual user has a higher purchase rate due to the point award than the trader user, the point award is given to the individual user. Further, when the analysis result shows that the trader user has a higher purchase rate due to the discount by bulk purchase than the individual user, the trader user is discounted by bulk purchase. By doing this, it is possible to approach efficiently.

Further, the determination unit 370 may determine the number of approaches according to the user type to be approached. Further, the determination unit 370 may determine the number of approaches according to the degree of use of the shopping service and the length of the suspension period. For example, when the fixation of the fan layer is emphasized, the determination unit 370 increases the number of fan fixation approaches more than other approaches.

The distribution unit 380 distributes information based on the approach determined by the determination unit 370 (hereinafter referred to as approach information) to the target of the approach among all the users A by using the communication unit 310. The approach information may be an email, content embedded in a web page, or content displayed using application software. For example, the distribution unit 380 distributes the approach information of the fan retention approach to the users belonging to the fan layer. For example, the distribution unit 380 distributes the approach information of the fan training approach to users belonging to the quasi-fan group. For example, the distribution unit 380 distributes the approach information of the quasi-fan training approach to users belonging to the distant fan group.

Further, when the determination unit 370 determines the number of approaches according to the usage degree of the shopping service, the distribution unit 380 distributes the approach information at a frequency according to the usage degree of the shopping service. When the determination unit 370 determines the number of approaches according to the length of the suspension period, the distribution unit 380 distributes the approach information at a frequency according to the length of the suspension period.

[flowchart]
Next, with reference to FIG. 10, a process executed by the information processing apparatus 300 according to the embodiment will be described. FIG. 10 is a flowchart showing an example of processing executed by the information processing apparatus 300 according to the embodiment.

First, the acquisition unit 330 stores the log data received from the service providing server 200 in the storage unit 320 as the log data 321 (S1). The derivation unit 340 derives the usage degree and the usage suspension period for each user A based on the log data 321 and stores the derived result in the storage unit 320 as a part of the usage status data 322 for each user ( S2). The classification unit 350 determines a target user among the user A (S3), and determines a target user among the user A in advance by referring to the user-specific usage status data 322 and the user type definition information 323. It is classified into the user types that have been identified (S4). The target user among the user A includes, for example, only an individual user, only a trader user, and the like.

The analysis unit 360 analyzes the usage status of the shopping service by the users belonging to the user type for each group of users belonging to the user type (S5). The decision unit 370 determines an approach for promoting the use of the shopping service based on the analysis result by the analysis unit 360 (S6). The distribution unit 380 distributes the approach information of the approach determined by the determination unit 370 to the distribution target of the approach (S7).

According to the embodiment described above, the user who has used the service via the network is determined in advance based on the relationship between the degree of use of the service and the suspension period from the last use date of the service to the present. A service using a network by providing a classification unit 350 that classifies the user types according to the classification unit 350 and an analysis unit 360 that analyzes the usage status of the service for each user belonging to the user type classified by the classification unit 350. It is possible to analyze the usage status of customers who use. As a result, when proposing various measures for promoting the sales of the service, it is possible to refer to the usage status of the customer who uses the service using the network, which is effective.

Although the embodiments for carrying out the present invention have been described above using the embodiments, the present invention is not limited to these embodiments, and various modifications and substitutions are made without departing from the gist of the present invention. Can be added.

In the present embodiment, an example in which the service providing server 200 provides a shopping service has been described, but the present invention is not limited to this. The service providing server 200 is various services provided via the network NW, for example, auction, free market, general e-commerce service (including buying and selling of stock certificates and financial products), finance (account transfer, withdrawal, etc.). ), Insurance, news sites, etc. may be provided. Further, the information processing apparatus 300 can also execute the above-mentioned processing with respect to these services, classifies users who have used any of these services into user types, and analyzes the usage status of any of these services. do.

1 ... Information processing system, 100 ... Terminal device, 200 ... Service providing server, 300 ... Information processing device, 310 ... Communication unit, 320 ... Storage unit, 330 ... Acquisition unit, 340 ... Derivation unit, 350 ... Classification unit, 360 ... Analysis unit, 370 ... decision unit, 380 ... distribution unit, 321 ... log data, 322 ... user-specific usage status data, 323 ... user type definition information, 324 ... user-specific usage status data

Claims (9)

A user who has purchased a product in an electronic commerce falls under any of the ranges in which the purchase frequency of the product and the purchase suspension period, which is the period from the last purchase date to the present, are separated by one or more threshold values. A classification unit that classifies into predetermined user types based on
Among the user types, the user belonging to the first type having the highest purchase frequency and the shortest purchase suspension period and the user belonging to the second type other than the first type user, said. An analysis unit that analyzes differences in products or stores purchased in e-commerce,
For users belonging to the second type, at least one of products or stores whose purchase frequency of the user belonging to the first type is higher than that of the user belonging to the second type is recommended or incentive. And the decision-making part that determines the approach to grant
Equipped with
The determination unit excludes products included in the product category in which the purchase frequency of the user belonging to the first type does not tend to be higher than the purchase frequency of the user belonging to the second type, and the second type is selected. Determine your approach to the users you belong to,
Information processing device. The decision unit determines the approach for improving satisfaction for users belonging to the first type.
The information processing apparatus according to claim 1. The approach to improving satisfaction includes at least one of incentives, sale of bargain items, and sale of limited items.
The information processing apparatus according to claim 2. The determination unit is for promoting the insufficient utilization of the user belonging to the second type in the comparison between the usage situation of the user belonging to the first type and the usage situation of the user belonging to the second type. Decide on an approach,
The information processing apparatus according to any one of claims 1 to 3. The user further includes a distribution unit that distributes distribution information based on the approach determined by the determination unit to the target of the approach.
The information processing apparatus according to any one of claims 1 to 4. The distribution unit distributes the distribution information at a frequency according to the degree of use of the electronic commerce or a frequency according to the length of the purchase suspension period.
The information processing apparatus according to claim 5. The classification unit classifies the trader users included in the user based on whether or not the number of purchases by the user under predetermined conditions in the electronic commerce meets the criteria, and excludes the trader user from the user. Classify users into the user types,
The information processing apparatus according to any one of claims 1 to 6. The computer
A user who has purchased a product in an electronic commerce falls under any of the ranges in which the purchase frequency of the product and the purchase suspension period, which is the period from the last purchase date to the present, are separated by one or more threshold values. Classify into predetermined user types based on
Among the user types, the user belonging to the first type having the highest purchase frequency and the shortest purchase suspension period and the user belonging to the second type other than the first type user, said. Analyze the difference between purchased products or stores in e-commerce,
For users belonging to the second type, at least one of products or stores whose purchase frequency of the user belonging to the first type is higher than that of the user belonging to the second type is recommended or incentive. Decide on an approach to grant
In the process of determining the approach, the product included in the product category in which the purchase frequency of the user belonging to the first type does not tend to be higher than the purchase frequency of the user belonging to the second type is excluded. Determine the approach to users who belong to two types,
Information processing method. On the computer
A user who has purchased a product in an electronic commerce falls under any of the ranges in which the purchase frequency of the product and the purchase suspension period, which is the period from the last purchase date to the present, are separated by one or more threshold values. Classify into predetermined user types based on
Among the user types, the user belonging to the first type having the highest purchase frequency and the shortest purchase suspension period and the user belonging to the second type other than the first type user, said. Let them analyze the differences between purchased products or stores in e-commerce,
For users belonging to the second type, at least one of products or stores whose purchase frequency of the user belonging to the first type is higher than that of the user belonging to the second type is recommended or incentive. To decide the approach to grant,
In the process of determining the approach, the product included in the product category in which the purchase frequency of the user belonging to the first type does not tend to be higher than the purchase frequency of the user belonging to the second type is excluded. Lets you decide on an approach to users who belong to two types
program.

Images