Customer service proposal device

Abstract

[Problem] To efficiently increase sales by accurately obtaining a specific customer service method suitable for a product to be sold, with reference to purchased products in a purchase history. [Solution] The present invention includes: a means for generating a machine learning model that learns a dataset of a product that has been successfully sold, a purchase history before the product was sold, and a customer service method used when selling the product, takes a product to be sold and a purchase history as input, and outputs a customer service method; a generating means for inputting one dataset including the product to be sold and the purchase history to the machine learning model, and generating the customer service method; a means for calculating sales or a number of units sold relating to the product for which the generated customer service method has been implemented; a means for determining whether the sales or the number of units sold is lower than a predetermined target value; a means for making the machine learning model perform additional learning; and a means for inputting one dataset including the product to be sold and the purchase history to the machine learning model after the additional learning, and re-generating a customer service method when determining that the sales or the number of units sold is lower than the predetermined target value.

Description

Customer service proposal device

[0007] ,

[0001] It relates to a technology for proposing a customer service method when selling products.

[0002] In the scenario of selling products (including services), depending on the skill of the customer service method, products that should originally sell may not sell, or conversely, products that should be difficult to sell may sell easily.

[0003] Also, in Patent Document 1, a system is proposed that supports providing an appropriate customer service and an easy shopping environment by presenting a customer service method tailored to the customers who visit the store to the store employees and setting the notification destination according to the business content of the store employees.

[0004] Japanese Patent Laid-Open No. 2016-153935

[0005] However, the above prior art has a problem that when a business operator sells a product that a consumer wishes to buy, a specific countermeasure for increasing the contract conclusion probability related to the sale of the product cannot be obtained.

[0006] Therefore, in view of the above problems, an object of the present invention is to provide a customer service proposal device that can accurately obtain a specific customer service method suitable for the product to be sold by referring to the purchased products in the purchase history and can efficiently expand sales.

[0007] One form of the customer service suggestion device disclosed is characterized by comprising: a model generation means that generates a machine learning model that outputs a specific customer service method by being trained on a dataset of products that have been successfully sold, the purchase history of the product before it was sold, and the specific customer service method used when the product was sold, and by being input with the product to be sold and the purchase history; a model storage means that stores parameters that define the input and output characteristics of the machine learning model that outputs a specific customer service method in response to the input of the product to be sold and the purchase history; a customer service method generation means that inputs one dataset of the product to be sold and the purchase history to the machine learning model and generates one of the specific customer service methods; a customer service implementation means that performs processing to implement the one specific customer service method at the sales site; a verification information calculation means that calculates the sales of the product on which the one specific customer service method was implemented; a target achievement determination means that determines whether the sales are below a predetermined target value; an additional learning means that causes the machine learning model to perform additional learning; and a customer service method regeneration means that, if it is determined by the target achievement determination means that the sales are below a predetermined target value, inputs one dataset of the product to be sold and the purchase history to the machine learning model after the additional learning and regenerates another specific customer service method.

[0008] Furthermore, other forms of the customer service suggestion device disclosed include: a model generation means that generates a machine learning model that outputs a specific customer service method by inputting a product to be sold and the purchase history, after training it with a dataset of products that have been successfully sold, the purchase history of the product before it was sold, and the specific customer service method used when the product was sold; a model storage means that stores parameters that define the input / output characteristics of the machine learning model that outputs a specific customer service method in response to the input of the product to be sold and the purchase history; a customer service method generation means that inputs one dataset of the product to be sold and the purchase history into the machine learning model and generates one specific customer service method; a customer service implementation means that performs processing to implement the one specific customer service method at the sales site; a verification information calculation means that calculates the number of sales for the product on which the one specific customer service method was implemented; a target achievement determination means that determines whether the number of sales is below a predetermined target value; an additional learning means that causes the machine learning model to perform additional learning; and a customer service method regeneration means that, if it is determined by the target achievement determination means that it is below the target, inputs one dataset of the product to be sold and the purchase history into the machine learning model after the additional learning and regenerates another specific customer service method.

[0009] The customer service suggestion system, which is being disclosed, uses the purchased items in the purchase history as a reference to accurately obtain specific customer service methods suitable for the products to be sold, thereby enabling efficient sales expansion.

[0010] This figure shows an overview of the customer service suggestion device according to this embodiment. This is a functional block diagram of the customer service suggestion device according to this embodiment. This figure shows an example of a training dataset according to this embodiment. This figure shows an example of the hardware configuration of the customer service suggestion device according to this embodiment. This flowchart shows an example of the processing flow by the customer service suggestion device according to this embodiment.

[0011] The embodiments for carrying out the present invention will be described with reference to the drawings. (Operating principle of the customer service suggestion device according to this embodiment)

[0012] The operating principle of the customer service suggestion device (hereinafter simply referred to as "this device") 100 according to this embodiment will be explained using Figures 1 and 2. Figure 1 is a diagram showing the connection relationship between this device 100 and other devices, and Figure 2 is a functional block diagram of this device 100.

[0013] As shown in Figure 1, the device 100 is connected to the store terminal 290 via a communication network 300. The communication network 300 may be either wired or wireless. The store terminal 290 is a device that informs the device 100 of the sales status and inventory status of products sold in the store (including a virtual store), and may be, for example, a POS (Point of Sales) system.

[0014] As shown in Figure 2, the device 100 includes a learning data storage means 110, a model storage means 120, a model generation means 130, a customer service method generation means 140, a customer service implementation means 150, a verification information calculation means 160, a goal achievement determination means 170, an additional learning means 180, and a customer service method regeneration means 190. Note that the storage means 110 and 120 do not necessarily have to be provided by the device 100; the device 100 may utilize storage means 110 and 120 provided by an external device.

[0015] The learning data storage means 110 stores a learning dataset 240 containing successful sales of products 210, purchase history (and purchased products) 220 prior to the sale of product 210, and specific customer service methods 230 used when selling product 210. The learning dataset 240 is added to and updated over time. The specific customer service methods 230 include sales talk to customers, advertisements displayed on a display (digital signage), coupons, etc., and may also be a combination of these.

[0016] Figure 3 shows an example of the learning data storage means 110. As shown in Figure 3, the learning data storage means 110 stores, for example, product 210: instant miso soup, purchase history 220: a group of products that are effective for the liver, and customer service method 230: it works for hangovers! The learning data storage means 110 also stores, for example, product 210: cosmetics, purchase history 220: none, and customer service method 230: even famous actresses continue to use it! The information stored in the learning data storage means 110 is not limited to these. The model storage means 120 stores parameters that define the input / output characteristics of the machine learning model 280, which will be described later.

[0017] The model generation means 130 uses the training dataset 240 to train the machine learning model 280, and by inputting the products to be sold 250 and the purchase history 260 of the target customers, it generates a machine learning model 280 that outputs specific customer service methods 270. The learning algorithm is not particularly limited.

[0018] The customer service method generation means 140 inputs a dataset of a product to be sold 250 and the purchase history 260 of a target customer into a machine learning model 280 and generates a specific customer service method 270. The specific customer service method 270 may include sales talk to the customer, advertisements displayed on a display (digital signage), coupons, etc., or a combination of these.

[0019] The customer service implementation means 150 performs the process of implementing specific customer service methods 270 at the sales site of the product 250 to be sold. For example, the customer service implementation means 150 displays the specific customer service methods 270 on an employee terminal or on an in-store display.

[0020] The verification information calculation means 160 calculates the sales or number of units sold for the product 250 that the store wants to sell. The verification information calculation means 160 obtains information regarding the sales or number of units sold for the product 250 that the store wants to sell from the store terminal 290 and performs the task of aggregating the information.

[0021] The target achievement determination means 170 determines whether the sales or number of units sold for product 250, calculated by the verification information calculation means 160, falls below a predetermined target value. The target value can be set as appropriate.

[0022] The additional learning means 180 causes the machine learning model 280 to perform additional training using the additional and updated training dataset 240. Generally, the input / output characteristics of the machine learning model 280 change before and after the additional training. Also, when processing is performed by the additional learning means 180, the information stored in the model storage means 120 is updated.

[0023] If the customer service method regeneration means 190 determines that the goal achievement determination means 170 has "fallen short," it inputs a dataset of a product to be sold 250 and the purchase history 260 of the target customer into the machine learning model 280 after additional training, and regenerates other specific customer service methods 270.

[0024] Based on the above operating principle, this device 100 can accurately obtain specific customer service methods 270 suitable for the desired product 250 by referring to the purchased products 260 in the purchase history, thereby efficiently expanding sales. (Hardware configuration of the customer service suggestion device according to this embodiment)

[0025] An example of the hardware configuration of the device 100 will be explained using Figure 4. Figure 4 is a diagram showing an example of the hardware configuration of the device 100. As shown in Figure 4, the device 100 has a CPU (Central Processing Unit) 510, ROM (Read-Only Memory) 520, RAM (Random Access Memory) 530, auxiliary storage device 540, communication I / F 550, input device 560, display device 570, and storage medium I / F 580.

[0026] The CPU 510 is a device that executes programs stored in the ROM 520. It processes data loaded into the RAM 530 according to program instructions and controls the entire device 100. The ROM 520 stores programs and data that the CPU 510 will execute. When the CPU 510 executes a program stored in the ROM 520, the RAM 530 loads the program and data to be executed and temporarily holds the calculation data during the calculation.

[0027] The auxiliary storage device 540 is a device that stores the operating system (OS), which is the basic software, and the application programs according to this embodiment, along with related data. For example, it may include a learning data storage means 110 and a model storage means 120. The auxiliary storage device 540 is, for example, an HDD (Hard Disk Drive) or flash memory.

[0028] The communication interface 550 is an interface for exchanging data with other devices (such as POS systems) 290 that connect to a communication network 300, such as a wired or wireless LAN (Local Area Network) or the Internet, and provide communication functions.

[0029] The input device 560 is a device for inputting data into the main device 100, such as a keyboard. The display device (output device) 570 is a device consisting of an LCD (Liquid Crystal Display) or the like, and functions as a user interface when the user uses the functions of the main device 100 or makes various settings. The storage medium I / F 580 is an interface for sending and receiving data with storage media 590 such as CD-ROMs, DVD-ROMs, and USB memory.

[0030] Each of the means of this device 100 may be realized by the CPU 510 executing a program corresponding to each means stored in the ROM 520 or auxiliary storage device 540. Alternatively, each of the means of this device 100 may be realized by the processing related to each means being implemented as hardware. Alternatively, the program according to the present invention may be read from an external server device via a communication I / F 550, or read from a storage medium 590 via a storage medium I / F 580, and the device 100 may execute the program. (Processing example by the customer service suggestion device according to this embodiment) An example of processing by this device 100 will be explained using Figure 5. Figure 5 is a flowchart showing the flow of the processing example by this device 100.

[0031] In S10, the model generation means 130 trains the machine learning model 280 on the training dataset 240 to generate a machine learning model 280 that outputs specific customer service methods 270 by inputting the desired products for sale 250 and the purchase history (purchased products) of the target customer 260. The learning algorithm of the machine learning model 280 is not particularly limited. In addition, the parameters that define the input / output characteristics of the machine learning model 280 generated by the processing in S10 are stored in the model storage means 120.

[0032] In S20, the customer service method generation means 140 inputs a dataset of a product to be sold 250 and the purchase history 260 of the target customer into the machine learning model 280 and generates a specific customer service method 270. The specific customer service method 270 includes sales talk to the customer, advertisements displayed on a display (digital signage), coupons, etc., and may also be a combination of these.

[0033] Then, in S20, the customer service implementation means 150 performs a process to implement the specific customer service method 270 at the sales site. For example, the customer service implementation means 150 displays the specific customer service method 270 on an employee terminal or on an in-store display.

[0034] Furthermore, after the processing in S20, the additional learning means 180 performs additional learning on the machine learning model 280 using the additional and updated training dataset 240. Generally, the input / output characteristics of the machine learning model 280 change before and after the additional learning. Also, when the processing by the additional learning means 180 is performed, the information stored in the model storage means 120 is updated.

[0035] In S30, the verification information calculation means 160 calculates the sales or number of units sold for the product 250 that the system wants to sell. The verification information calculation means 160 obtains and aggregates information regarding the sales or number of units sold for the product 250 that the system wants to sell from the store terminal 290.

[0036] Then, in S30, the target achievement determination means 170 determines whether the sales or number of products sold for the product 250 calculated in S30 is below a predetermined target value. The target value can be set as appropriate.

[0037] If it is determined in S30 that the result is "below," in S40 the customer service method regeneration means 190 inputs a dataset of one product to be sold 250 and the purchase history 260 of the target customer into the machine learning model 280 after additional training, and regenerates other specific customer service methods 270.

[0038] By performing the above-described process, the device 100 can accurately obtain specific customer service methods 270 suitable for the desired product 250 by referring to the purchased products 260 in the purchase history, thereby efficiently expanding sales.

[0039] Although embodiments of the present invention have been described in detail above, the present invention is not limited to these specific embodiments, and various modifications and changes are possible within the scope of the gist of the present invention as described in the claims.

[0040] 100 Customer service suggestion device 110 Learning data storage means 120 Model storage means 130 Model generation means 140 Customer service method generation means 150 Customer service implementation means 160 Verification information calculation means 170 Goal achievement determination means 180 Additional learning means 190 Customer service method regeneration means 210 Products successfully sold 220 Purchase history of products sold before the sale of the product (products purchased in that history) 230 Specific customer service method when the product was sold 240 Learning dataset 250 Products to be sold 260 Purchase history of target customers (products purchased in that history) 270 Specific customer service method generated by the machine learning model 280 Machine learning model 290 Store terminal (POS system) 300 Communication network 510 CPU 520 ROM 530 RAM 540 Auxiliary storage device 550 Communication interface 560 Input device 570 Output device 580 Storage medium interface 590 Storage medium

Claims

1. A customer service suggestion device comprising: a model generation means that generates a machine learning model that outputs a specific customer service method by being trained on a dataset of products that have been successfully sold, the purchase history of the product before it was sold, and the specific customer service method used when the product was sold, and by being input with a product to be sold and the purchase history; a model storage means that stores parameters that define the input and output characteristics of the machine learning model that outputs a specific customer service method in response to the input of the product to be sold and the purchase history; a customer service method generation means that inputs one dataset of the product to be sold and the purchase history to the machine learning model and generates one of the specific customer service methods; a customer service implementation means that performs processing to implement the one specific customer service method at the sales site; a verification information calculation means that calculates the sales of the product on which the one specific customer service method was implemented; a target achievement determination means that determines whether the sales are below a predetermined target value; an additional learning means that causes the machine learning model to perform additional learning; and a customer service method regeneration means that, if it is determined by the target achievement determination means that the sales are below a predetermined target value, inputs one dataset of the product to be sold and the purchase history to the machine learning model after the additional learning and regenerates another specific customer service method.

2. A customer service suggestion device characterized by comprising: a model generation means that generates a machine learning model that outputs a specific customer service method by being trained on a dataset of products that have been successfully sold, the purchase history of the products before they were sold, and the specific customer service methods used when the products were sold, and by being input with a product to be sold and the purchase history; a model storage means that stores parameters that define the input and output characteristics of the machine learning model that outputs a specific customer service method in response to the input of a product to be sold and the purchase history; a customer service method generation means that inputs one dataset of the product to be sold and the purchase history to the machine learning model and generates one of the specific customer service methods; a customer service implementation means that performs processing to implement the one specific customer service method at the sales site; a verification information calculation means that calculates the number of sales for the product on which the one specific customer service method was implemented; a target achievement determination means that determines whether the number of sales is below a predetermined target value; an additional learning means that causes the machine learning model to perform additional learning; and a customer service method regeneration means that, if it is determined by the target achievement determination means that it is below the target, inputs one dataset of the product to be sold and the purchase history to the machine learning model after the additional learning and regenerates another specific customer service method.

3. A computer equipped with a model storage means that stores parameters defining the input / output characteristics of a machine learning model that outputs a specific customer service method by inputting a product to be sold and the purchase history, which is trained on a dataset of successfully sold products, purchase history before the sale of the product, and specific customer service methods used when the product was sold, wherein the model generation means generates the machine learning model that outputs a specific customer service method by inputting the product to be sold and the purchase history, which is trained on a dataset of successfully sold products, purchase history before the sale of the product, and specific customer service methods used when the product was sold, which is then trained on the product to be sold and the purchase history A customer service suggestion method that includes the step of, if the customer service method regeneration means is determined to be below the target achievement determination means, inputting a dataset of the product to be sold and purchase history into the machine learning model after additional training, and regenerating another specific customer service method.

4. A computer equipped with a model storage means that stores parameters defining the input / output characteristics of a machine learning model that outputs a specific customer service method by inputting a product to be sold and the purchase history, which is trained on a dataset of successfully sold products, purchase history before the sale of the product, and specific customer service methods used when the product was sold, wherein the model generation means generates the machine learning model that outputs a specific customer service method by inputting the product to be sold and the purchase history, which is trained on a dataset of successfully sold products, purchase history before the sale of the product, and specific customer service methods used when the product was sold, which is trained on. A customer service suggestion method that includes the step of, if the customer service method regeneration means is determined to be below the target achievement determination means, inputting a dataset of the product to be sold and purchase history into the machine learning model after additional training, and regenerating another specific customer service method.

5. A customer service suggestion program for causing a computer to perform the method described in claim 3 or 4.

Images