JP7553122B2 - Product proposal system - Google Patents

Description

The present invention relates to a product suggestion system that can suggest products and services that are likely to be sold (provided) to a larger number of customers for each product introducer who introduces the products and services.

Currently, a wide variety of products are sold via the Internet. In order to increase sales to each customer, a product suggestion system has been proposed that suggests products suited to each customer based on their attributes.

For example, Patent Document 1 discloses a product suggestion system that suggests appropriate products according to attributes possessed by individual customers, comprising: a product selection means that refers to a product database that stores correlations between individual products and one or more attributes and selects multiple products that are correlated with the attributes possessed by the customer; a display mode selection means that determines a display mode for a group of products consisting of multiple products selected by the product selection means so that products that have a large number of attributes that match the attributes possessed by the customer among the correlated attributes are preferentially displayed; and an interest level determination means that determines the customer's level of interest in each product displayed in the display mode determined by the display mode selection means based on one or more elements of the time, number of times, and content of the customer's operation on the display area of the product, and the display mode selection means is characterized in that it changes the display mode so that products with a high level of interest are preferentially displayed after the interest level determination means has determined the interest level, and it is possible to suggest appropriate products according to the attributes possessed by each individual customer.

On the other hand, there is influencer marketing (social network marketing), in which influencers, people who have a great influence over consumers, promote products online. It is said that influencer marketing can increase awareness of products and services among consumers and encourage them to purchase them by having influencers introduce the products and services.

JP 2022-64035 A

However, there is a problem with influencer marketing in that it is unclear what kind of product or service each influencer should introduce to consumers in order to increase awareness of that product or service and to encourage consumers to purchase that product or receive that service.

And these problems cannot be solved by the conventional product recommendation systems described above.

In consideration of the above-mentioned circumstances, the present invention aims to provide a product/service suggestion system that can suggest products/services that are likely to be sold (provided) to a greater number of customers for each product/service introducer who introduces the product/service.

As a result of extensive research into the problems mentioned above, the inventors of the present invention have come up with the following groundbreaking product suggestion system.

The first aspect of the present invention for solving the above problem is a product suggestion system that proposes to a plurality of product introducers who introduce products and services, among unintroduced products that have not been introduced by the product introducer in the past, which are likely to be sold or provided to many customers if introduced by the product introducer, and includes a sales quantity database that stores product data on products and services and sales quantity data indicating the number of products sold or the number of services provided for each product or service that the product introducer has introduced in the past, and based on the sales quantity data of the product introducer and the sales quantity data of other product introducers other than the product introducer, a sales quantity database that calculates the sales quantity data between the product introducer and the other product introducers for each other product introducer. The product suggestion system has a correlation coefficient calculation unit that calculates a sales quantity correlation coefficient for each of the product introducers, a target product introducer selection unit that selects other product introducers whose sales quantity correlation coefficient is higher than a predetermined value from among the other product introducers as target product introducers, a predicted sales quantity calculation unit that calculates predicted sales quantity data for each unintroduced product based on the sales quantity data of the target product introducer and the sales quantity correlation coefficient of the target product introducer for the product introducer, and an unhandled product extraction unit that selects unintroduced products related to a predetermined number of predicted sales quantity data from the predicted sales quantity data of unintroduced products in descending order of the highest predicted sales quantity data, and extracts product data related to unintroduced products from the sales quantity database.

According to the first aspect, it is possible to provide a product etc. proposal system that can propose products and services that are likely to be sold (provided) to more customers for each product etc. introducer who introduces a product or service.

A second aspect of the present invention is the product recommendation system described in the first aspect, characterized in that the sales volume correlation coefficient is Pearson's product moment correlation coefficient.

According to the second aspect, the sales volume correlation coefficient can be easily calculated.

FIG. 1 is a schematic conceptual diagram of a product recommendation system according to the first embodiment. FIG. 2 is a schematic diagram of an information terminal according to the first embodiment. FIG. 3 is a schematic conceptual diagram of the product suggestion server according to the first embodiment. FIG. 4 is a table showing an example of sales amount data according to the first embodiment. FIG. 5 is a table showing an example of calculation of the Pearson product-moment correlation coefficient according to the first embodiment. FIG. 6 is a table showing forecast sales and other quantity data of influencer 1 according to the first embodiment. FIG. 7 is a flowchart showing the operation of the product recommendation system according to the first embodiment.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of a product recommendation system according to the present invention will be described with reference to the accompanying drawings. Note that the present invention is not limited to the following embodiment.
(Embodiment 1)

In the embodiment described below, we will explain a product suggestion system that can suggest to product introducers products that have not been introduced before and that have a high possibility of being sold to more customers.

FIG. 1 is a schematic conceptual diagram of a product proposal system according to this embodiment. As shown in this diagram, the product proposal system 1 is composed of multiple information terminals 10 and a product proposal server 20 connected via a network 30. Note that in this embodiment, the product proposal system 1 is composed of multiple information terminals 10 and one product proposal server, but it goes without saying that the product proposal system may also be composed of multiple information terminals and multiple product proposal servers.

First, the information terminal 10 will be described. As shown in FIG. 2, the information terminal 10 is used by a product introducer who introduces products and services to customers, and is not particularly limited as long as it has an input unit 11 for inputting information about the product introducer (the person) as described below, and a display unit 12 for displaying product data 211 relating to the product.

Here, the product data 211 is not particularly limited as long as it is information related to the target product. Examples of the product data include an overview of the product, the selling (offering) price, etc.

The input unit 11 is not particularly limited as long as it can input information about the product introducer, and examples of such include a keyboard, a voice input system, and a touch panel. The display unit 12 is also not particularly limited as long as it can display the product data 211 described below, and examples of such include a liquid crystal panel and an organic EL panel. Examples of the information terminal 10 include a smartphone, a tablet personal computer, and a personal computer.

Here, the term "customer" is not particularly limited as long as it is a person who purchases a product or is thinking of purchasing a product. The "product introducer" is also not particularly limited, but is preferably someone who has a significant influence on the customer's decision to purchase a product or not.

Next, the product etc. proposal server 20 will be described. As shown in FIG. 3, the product etc. proposal server 20 has a sales etc. quantity database (sales etc. quantity DB) 21, a correlation coefficient calculation unit 22, a target product etc. introducer selection unit 23, a predicted sales etc. quantity calculation unit 24, an unhandled product etc. extraction unit 25, and a data transmission unit 26.

The sales etc. quantity DB21 is not particularly limited as long as it can store product etc. data 211 and sales etc. quantity data 212. Examples of the sales etc. quantity DB21 include commercially available relational database software.

The sales etc. quantity data 212 is not particularly limited as long as it is information indicating the number of sales of a product that a product introducer has previously introduced. Examples of the sales etc. quantity data 212 include data such as that shown in FIG. 4. In this figure, for example, the number "5" written in the "Product A" column for "Influencer 1" who is a product introducer indicates the number of sales of Product A that was sold as a result of Influencer 1 introducing Product A. Also, the letter "null" written in the "Product E" and "Product F" columns for "Influencer 1" indicates that these are unintroduced products that have not yet been introduced by Influencer 1. In other words, to Influencer 1, "Product E" and "Product F" are unintroduced products.

The correlation coefficient calculation unit 22 is not particularly limited as long as it can calculate the sales quantity correlation coefficient between the sales quantity data 212 of the product introducer and other product introducers for each other product introducer based on the sales quantity data 212 of the product introducer and the sales quantity data 212 of other product introducers other than that product introducer.

Here, the sales etc. quantity correlation coefficient is not particularly limited as long as it is a correlation coefficient between the sales etc. quantity data 212 of the product introducer and the sales etc. quantity data 212 of other product introducers. Examples of sales etc. quantity correlation coefficients include Pearson's product moment correlation coefficient, Spearman's rank correlation coefficient, and Kendall's rank correlation coefficient, but the Pearson's product moment correlation coefficient shown in the following formula is preferred because it can be easily calculated.

In this formula, ρ _az indicates the Pearson product moment correlation coefficient between product introducer a and product introducer z, r _ay indicates the sales volume of the product introduced by product introducer a, and Y _az indicates the set of products introduced by both product introducer a and product introducer z.

The correlation coefficient calculation unit 22 may be, for example, a program that operates as follows. First, in FIG. 4, the product introducer is influencer 1, and the other product introducers are influencers 2 to 5. In such a case, by substituting the sales quantity data 212 of influencer 1 and the sales quantity data 212 of each of influencers 2 to 5 into the above formulas (1) and (2), respectively, the Pearson product moment correlation coefficients of each of influencers 2 to 5 with influencer 1 can be calculated, as shown in FIG. 5. Note that the Pearson product moment correlation coefficient of influencer 1 with influencer 1 is naturally 1, since it is a correlation coefficient with itself. Then, this calculation is performed for each of influencers 2 to 5. In this way, the sales quantity correlation coefficient (Pearson product moment correlation coefficient) for the sales quantity data 212 between the product introducer and the other product introducers can be calculated. Needless to say, when proposing a product that is likely to be sold (provided) to a larger number of customers only to a specific product introducer, it is sufficient to calculate the sales quantity correlation coefficient for the sales quantity data 212 between that product introducer and other product introducers.

The target product etc. introducer selection unit 23 is not particularly limited as long as it can select (extract) from other product etc. introducers as target product etc. introducers other product etc. introducers whose sales etc. quantity correlation coefficient is higher than a predetermined value.

The "predetermined value" here can be set arbitrarily. When using Pearson's product moment correlation coefficient as the sales quantity correlation coefficient, examples of the predetermined value include "0", "0.3", "0.5", etc. For example, if the product introducer is influencer 1 and the predetermined value is set to "0", in FIG. 4, the Pearson product moment correlation coefficients of influencers 2, 4, and 5 with influencer 1 are all greater than 0, so influencers 2, 4, and 5 will be selected as the target product introducers.

On the other hand, since the Pearson product moment correlation coefficient of influencer 3 with influencer 1 is less than or equal to 0, influencer 3 will not be selected as an introducer of the target product, etc. It goes without saying that a single introducer of the target product, etc. may be selected, or multiple introducers of the target product, etc. may be selected. An example of the introducer selection unit 23 for the target product, etc. may be a program having such a function.

The predicted sales etc. quantity calculation unit 24 is not particularly limited as long as it can calculate predicted sales etc. quantity data for each unintroduced product etc. based on the sales etc. quantity data 212 of the introducer of the target product etc. and the sales etc. quantity correlation coefficient of the introducer of the target product etc. to the product etc. introducer.

Here, the predicted sales volume refers to the predicted (assumed) sales volume that can be sold if the product introducer introduces the product.

The forecast sales etc. quantity calculation unit 24 can calculate forecast sales etc. quantity data r'ay of the unintroduced product etc. a by, for example, substituting the Pearson's product moment correlation coefficient calculated by the correlation coefficient calculation unit ₂₂ into the following equation.

Specifically, for example, as described above, products E and F are unintroduced products, etc., for influencer 1 in FIG. 1. Therefore, by substituting the data shown in FIG. 4 and FIG. 5 into the above formula (3) and performing calculations for products E and F of influencer 1, respectively, it is possible to calculate predicted sales, etc. quantity data for products E and F, which are unintroduced products, etc., for influencer 1, as shown in FIG. 6.

The predicted sales etc. quantity calculation unit 24 may be, for example, a program that can calculate predicted sales etc. quantity data using the above-mentioned formula.

The unintroduced products etc. extraction unit 25 is not particularly limited as long as it can select a predetermined number of unintroduced products etc. in order from the predicted sales etc. quantity data of unintroduced products etc., starting with the highest value, and extract product etc. data 211 relating to the unintroduced products etc. from the sales etc. quantity database 21.

Specifically, when the predetermined number is "1", only the product data 211 for "Product F" with the largest predicted sales quantity data value among the unintroduced products shown in FIG. 6 is extracted, and when the predetermined number is "2", the product data 211 for "Product F" with the largest predicted sales quantity data value and "Product E" with the second largest predicted sales quantity data value among the unintroduced products shown in FIG. 6 are extracted from the sales quantity database 21.

Here, the "predetermined number" is not particularly limited, and examples include "3," "5," "10," etc. Note that the unhandled product etc. extraction unit 25 may be, for example, a program having such a function.

The data transmission unit 26 is not particularly limited as long as it is capable of transmitting product data 211, such as unintroduced products, extracted by the unhandled product extraction unit 25, to the information terminal 10.

Specifically, for example, when the predetermined number is "1" and the unhandled product etc. extraction unit 25 extracts the product etc. data 211 of "product E" shown in FIG. 6, the data transmission unit 26 transmits the product etc. data 211 relating to "product E" to the information terminal 10. Note that the data transmission unit 26 may be, for example, a program having such a function.

Next, the operation of the product suggestion system 1 will be described. FIG. 7 is a flowchart showing the operation of the product suggestion system. As shown in this figure, when the product suggestion system 1 is operated (S1), information on the product introducer is input from the information terminal 10 (for example, the name of the influencer 1 is specified) (S2). Then, the correlation coefficient calculation unit 22 calculates the sales quantity correlation coefficient for the sales quantity data 212 between the product introducer and other product introducers for each product introducer (S3). Then, this calculation is repeated until all sales quantity correlation coefficients are calculated (S4). Here, as described above, when proposing a product that is likely to be sold (provided) to more customers only to a specific product introducer, it is only necessary to calculate the sales quantity correlation coefficient for the sales quantity data 212 between the product introducer and other product introducers.

Next, the target product introducer selection unit 23 selects other product introducers whose sales quantity correlation coefficients are higher than a predetermined value as target product introducers (S5). After that, the predicted sales quantity calculation unit 24 calculates predicted sales quantity data for each unintroduced product (S6).

Then, the unhandled product etc. extraction unit 25 selects a predetermined number of unintroduced products etc. related to the predicted sales etc. quantity data, starting from the highest numerical value, and extracts product etc. data 211 relating to the unintroduced products etc. from the sales etc. quantity database 21 (S7). The product etc. data 211 relating to the unintroduced products etc. is then transmitted to the information terminal 10 by the data transmission unit 26. The product etc. data 211 is then displayed on the display unit 12 of the information terminal 10 (S8), and the operation of the product etc. proposal system 1 ends (S9).

In this way, the product etc. proposal system 1 can propose products and services that are likely to be sold (provided) to more customers for each product etc. introducer who introduces the product or service.

(Other Aspects)
In the above-described embodiment, a product suggestion system has been described that can suggest to a product introducer products that have not been introduced before and that have a high possibility of being sold to more customers, but the present invention is not limited to this.

For example, the product suggestion system may be configured to suggest to the product introducer services that have not been introduced before and that are likely to be accepted by more customers. Such a product suggestion system may be configured in the same manner as that according to the first embodiment.

REFERENCE SIGNS LIST 1 Product etc. proposal system 10 Information terminal 11 Input unit 12 Display unit 20 Product etc. proposal server 21 Sales etc. quantity database 211 Product etc. data 212 Sales etc. quantity data 22 Correlation coefficient calculation unit 23 Target product etc. introducer selection unit 24 Predicted sales etc. quantity calculation unit 25 Unhandled product etc. extraction unit 26 Data transmission unit 30 Network

Claims (2)

A product suggestion system that proposes to a plurality of product introducers who introduce products and services, among unintroduced products that have not been introduced by the product introducers in the past, the unintroduced products are likely to be sold or provided to many customers by the product introducers,
a sales quantity database storing product data relating to the products and services and sales quantity data indicating the number of products sold or the number of services provided for each of the products or services previously introduced by the product introducer;
a correlation coefficient calculation unit that calculates a sales quantity correlation coefficient between the sales quantity data of the product introducer and the other product introducers for each of the other product introducers based on the sales quantity data of the product introducer and the sales quantity data of other product introducers other than the product introducer;
a target product introducer selection unit that selects, as a target product introducer, the other product introducer having a sales quantity correlation coefficient higher than a predetermined value from the other product introducers;
a predicted sales amount calculation unit that calculates predicted sales amount data indicating a predicted sales amount for each of the unintroduced products when the product introducer introduces the product, etc., based on the sales amount data of the target product, etc. introducer and a sales amount correlation coefficient of the target product, etc. introducer to the product, etc. introducer ;
an unintroduced product etc. extraction unit that selects a predetermined number of unintroduced products related to the predicted sales etc. volume data of the unintroduced products in order from the highest predicted sales etc. volume data, and extracts the product etc. data related to the unintroduced products from the sales etc. volume database;
A product suggestion system comprising: The product recommendation system according to claim 1, characterized in that the sales volume correlation coefficient is Pearson's product moment correlation coefficient.