Sales promotion proposal device

Abstract

You can accurately obtain specific sales promotion measures that are suited to the products you want to sell, the sales area, the weather, the target customer base, and the events you are holding, allowing you to efficiently increase sales. [Solution] The system comprises a means for generating a machine learning model that has been trained on successfully sold products, sales regions, weather, target customer segments, events held, and specific promotional measures taken when the products are sold; a means for inputting a dataset of a product to be sold, the sales region, weather, target customer segments, and events held into the machine learning model and generating specific promotional measures; a means for calculating sales or sales numbers for a product for which the generated specific promotional measures have been implemented; a means for determining whether the sales or sales numbers are below a specified target value; a means for causing the machine learning model to perform additional learning; and, if it is determined that the sales or sales numbers are below the specified target value, a means for inputting the previous dataset into the machine learning model after the additional learning, and regenerating other specific promotional measures.

Description

[Technical field]

[0001] This relates to a technique for proposing specific measures for product sales promotion. [Background technology]

[0002] In selling products (including services), the skill of customer service can result in products that would normally sell not selling, or conversely, products that would be difficult to sell selling easily.

[0003] Furthermore, Patent Document 1 proposes a system that supports store clerks in providing appropriate customer service and an environment that is easy to shop in by suggesting customer service methods that are tailored to customers and setting notification destinations according to the nature of the clerk's work. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2016-153935 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the above-mentioned conventional technology has a problem in that, when a business sells a desired product to a consumer, it is not possible to obtain a specific measure for increasing the probability of concluding a sale of the product.

[0006] In view of the above problems, the present invention aims to provide a sales promotion proposal device that can accurately obtain specific sales promotion measures suitable for the product to be sold, the sales area, the weather in the sales area, the target customer base, and events being held in the sales area, thereby efficiently increasing sales. [Means for solving the problem]

[0007] One embodiment of the sales promotion proposal device disclosed includes a model generation means for generating a machine learning model that learns a data set of a sales region, weather in the sales region, purchasing customer demographics, events held in the sales region, and specific measures related to sales promotion when sales are determined to be good in purchase data for each product type, and outputs the specific measures by inputting a product type to be sold, the sales region, weather in the sales region, target customer demographics, and events held in the sales region; a model storage means for storing parameters that specify input / output characteristics of the machine learning model that outputs the specific measures in response to input of the product type to be sold, the sales region, weather in the sales region, target customer demographics, and events held in the sales region; the sales promotion policy generating means inputting a dataset of events held in a sales area into the machine learning model to generate one of the specific policies; a sales promotion implementation means performing processing to implement the one specific policy at the sales site; a verification information calculation means calculating sales related to a product for which the one specific policy has been implemented; a goal achievement determination means determining whether the sales are below a predetermined target value; additional learning means causing the machine learning model to perform additional learning; and, if the goal achievement determination means determines that the sales are below a predetermined target value, a sales promotion policy regeneration means inputting a dataset of the one product type to be sold, the sales area, the weather in the sales area, the target customer demographic, and events held in the sales area into the machine learning model after the additional learning, and regenerating another of the specific policies.

[0008] Furthermore, one embodiment of the sales promotion proposal device disclosed includes a model generation means for generating a machine learning model that learns a data set of a sales region, weather in the sales region, purchasing customer demographics, events held in the sales region, and specific measures related to sales promotion when sales volume is determined to be good in purchase data for each product type, and outputs the specific measures by inputting a product type to be sold, the sales region, weather in the sales region, target customer demographics, and events held in the sales region; a model storage means for storing parameters that specify input / output characteristics of the machine learning model that outputs the specific measures in response to input of the product type to be sold, the sales region, weather in the sales region, target customer demographics, and events held in the sales region; The system is characterized by having a promotional measure generation means for inputting a dataset of events held in a region into the machine learning model and generating one of the specific measures, a promotional implementation means for performing processing to implement the one specific measure at the sales site, a verification information calculation means for calculating sales figures for a product for which the one specific measure has been implemented, a goal achievement determination means for determining whether the sales figure is below a predetermined target value, additional learning means for causing the machine learning model to perform additional learning, and, if the goal achievement determination means determines that the sales figure is below a predetermined target value, a promotional measure regeneration means for inputting a dataset of the one product type to be sold, the sales region, the weather in the sales region, the target customer demographic, and events held in the sales region into the machine learning model after the additional learning, and regenerating another of the specific measures. Effect of the Invention

[0009] The disclosed sales promotion proposal device can accurately obtain specific sales promotion measures suited to the product to be sold, the sales area, the weather in the sales area, the target customer base, and events being held in the sales area, thereby efficiently increasing sales. [Brief description of the drawings]

[0010] [Figure 1] 1 is a diagram showing an overview of a sales promotion proposal device according to an embodiment of the present invention; [Diagram 2] 1 is a functional block diagram of a sales promotion proposal device according to an embodiment of the present invention. [Diagram 3] 1 is a diagram illustrating an example of a hardware configuration of a sales promotion proposal device according to an embodiment of the present invention. [Figure 4] 10 is a flowchart showing a flow of an example of processing performed by the sales promotion proposal device according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS With reference to the drawings, an embodiment of the present invention will be described. (Operation principle of the sales promotion proposal device according to the present embodiment)

[0012] The operation principle of a sales promotion proposal device (hereinafter simply referred to as "the device") 100 according to the present embodiment will be described with reference to Figures 1 and 2. Figure 1 is a diagram showing the connection relationship between the device 100 and other devices, and Figure 2 is a functional block diagram of the device 100.

[0013] 1, the present device 100 is connected to a store terminal 350 via a communication network 360. The communication network 360 may be either wired or wireless. The store terminal 350 is a device that notifies the present device 100 of the sales status and inventory status of products sold in a store (including a virtual store), and may be, for example, a POS (Point Of Sales) system.

[0014] 2, the present device 100 has learning data storage means 110, model storage means 120, model generation means 130, measure generation means 140, measure implementation means 150, verification information calculation means 160, goal achievement determination means 170, additional learning means 180, and measure regeneration means 190. Note that the storage means 110 and 120 do not necessarily have to be provided in the present device 100, and the present device 100 may use the storage means 110 and 120 provided in an external device.

[0015] The learning data storage means 110 stores, for each product type 210, a learning data set 270 of a sales region 220, weather 230 in the sales region 220, purchasing customer demographics 240, events 250 held in the sales region 220, and specific measures (including images) 260 related to sales promotion when sales are determined to be good in the purchase data. The learning data set 270 is added and updated over time. The specific measures 260 include, for example, a commercial message (CM), sales promotion materials, sales talk, advertisements to be displayed on a display (digital signage), coupons, live commerce, and the like, and may also be a combination of these. The model storage means 120 stores parameters that define the input / output characteristics of the machine learning model 340 described below.

[0016] The model generation means 130 trains the machine learning model 340 on the learning dataset 270, and generates the machine learning model 340 that outputs specific measures 330 for sales promotion by inputting the product type 280 to be sold, the sales area 290, the weather 300 in the sales area 290, the target customer group 310, and the events 320 held in the sales area 290. The learning algorithm is not particularly limited.

[0017] The measure generation means 140 inputs a data set of a type of product 280 to be sold, a sales area 290, weather 300 in the sales area 290, a target customer group 310, and events 320 held in the sales area 290 into a machine learning model 340, and generates a specific measure 330. The specific measure 330 includes, for example, a commercial, a sales promotion material, a sales talk, an advertisement to be displayed on a display (digital signage), a coupon, live commerce, etc., and may also be a combination of these.

[0018] The measure implementation means 150 performs processing to implement specific measures 330 at the sales site of the product 280 to be sold. The customer service implementation means 150 performs processing to implement, for example, broadcasting commercials, producing and distributing promotional materials, live commerce, and the like.

[0019] The verification information calculation means 160 calculates the sales or sales volume of the product 280 to be sold. The verification information calculation means 160 acquires information on the sales or sales volume of the product 280 to be sold from the store terminal 350 and performs an operation of tallying up the information.

[0020] The target achievement determination means 170 determines whether or not the sales or sales volume of the product 280 calculated by the verification information calculation means 160 is below a predetermined target value. The target value can be set as appropriate.

[0021] The additional learning means 180 causes the machine learning model 340 to perform additional learning using the added / updated learning dataset 270. Note that, before and after the additional learning, the input / output characteristics of the machine learning model 340 generally change. Furthermore, when processing is performed by the additional learning means 180, the information stored in the model storage means 120 is also updated.

[0022] When the goal achievement determination means 170 determines that the target is “below the target”, the measure regeneration means 190 inputs a data set of a product type 280 to be sold, a sales area 290, weather 300 in the sales area 290, a target customer demographic 310, and events 320 held in the sales area 290 into the machine learning model 340 after additional learning, and regenerates another specific measure 330.

[0023] Based on the above operating principle, the device 100 can accurately obtain specific sales promotion measures 330 suited to the product 280 to be sold, the sales area 290, the weather 300 in the sales area, the target customer group 310, and the events 320 being held in the sales area 290, thereby efficiently increasing sales. (Hardware configuration of the sales promotion proposal device according to this embodiment)

[0024] An example of the hardware configuration of the present device 100 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the hardware configuration of the present device 100. As shown in Fig. 3, the present device 100 has a CPU (Central Processing Unit) 510, a ROM (Read-Only Memory) 520, a RAM (Random Access Memory) 530, an auxiliary storage device 540, a communication I / F 550, an input device 560, a display device 570, and a storage medium I / F 580.

[0025] CPU 510 is a device that executes a program stored in ROM 520, performs arithmetic processing on data expanded (loaded) into RAM 530 in accordance with instructions from the program, and controls the entire device 100. ROM 520 stores programs and data to be executed by CPU 510. When CPU 510 executes a program stored in ROM 520, the program and data to be executed are expanded (loaded) into RAM 530, and RAM 530 temporarily holds the arithmetic data during calculation.

[0026] The auxiliary storage device 540 is a device that stores the OS (Operating System) which is basic software, the application program according to the present embodiment, and the like together with related data, and may include, for example, the learning data storage means 110 and the model storage means 120. The auxiliary storage device 540 is, for example, a HDD (Hard Disk Drive) or a flash memory.

[0027] The communication I / F 550 is an interface for connecting to a communication network 360 such as a wired or wireless LAN (Local Area Network) or the Internet, and for transmitting and receiving data to and from another device (such as a POS system) 350 that provides a communication function.

[0028] The input device 560 is a device such as a keyboard for inputting data to the present device 100. The display device (output device) 570 is a device constituted by an LCD (Liquid Crystal Display) or the like, and functions as a user interface when the user utilizes the functions of the present device 100 or when performing various settings. The storage medium I / F 580 is an interface for transmitting and receiving data to and from a storage medium 590 such as a CD-ROM, DVD-ROM, or USB memory.

[0029] Each of the means of the present device 100 may be realized by CPU 510 executing a program corresponding to each of the means stored in ROM 520 or auxiliary storage device 540. Each of the means of the present device 100 may be realized by hardware that performs processing related to each of the means. Alternatively, the present device 100 may be caused to read the program according to the present invention from an external server device via communication I / F 550, or to read the program according to the present invention from storage medium 590 via storage medium I / F 580, and cause the present device 100 to execute the program. (Example of processing by the sales promotion proposal device according to the present embodiment) An example of processing by the present device 100 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the flow of an example of processing by the present device 100.

[0030] In S10, the model generation means 130 trains the machine learning model 340 on the learning dataset 270, and generates the machine learning model 340 that outputs specific measures 330 for sales promotion by inputting the product type 280 to be sold, the sales region 290, the weather 300 in the sales region 290, the target customer demographic 310, and the events 320 held in the sales region 290. The learning algorithm is not particularly limited. Furthermore, parameters defining the input / output characteristics of the machine learning model 340 generated by the process in S10 are stored in the model storage means 120.

[0031] In S20, the measure generation means 140 inputs a data set of a type of product 280 to be sold, a sales area 290, weather 300 in the sales area 290, a target customer group 310, and events 320 held in the sales area 290 into the machine learning model 340, and generates a specific measure 330. The specific measure 330 includes, for example, a commercial, a sales promotion material, a sales talk, an advertisement to be displayed on a display (digital signage), a coupon, live commerce, etc., and may also be a combination of these.

[0032] Then, in S20, the measure implementation means 150 performs processing to implement specific measures 330 at the sales site of the product 280 to be sold. The customer service implementation means 150 performs processing to implement, for example, broadcasting commercials, producing and distributing promotional materials, live commerce, and the like.

[0033] Furthermore, after the processing of S20, the additional learning means 180 performs processing to cause the machine learning model 340 to perform additional learning using the added / updated learning dataset 270. Note that, before and after the additional learning, the input / output characteristics of the machine learning model 340 generally change. Furthermore, when the processing is performed by the additional learning means 180, the information stored in the model storage means 120 is also updated.

[0034] In S30, the verification information calculation means 160 calculates the sales or sales volume of the product 280 to be sold. The verification information calculation means 160 obtains information on the sales or sales volume of the product 280 to be sold from the store terminal 350 and performs a calculation operation.

[0035] Then, in S30, the target achievement determination means 170 determines whether or not the sales or sales volume of the product 280 calculated in S30 is below a predetermined target value. The target value can be set as appropriate.

[0036] If it is determined in S30 that the target value is “below the target value”, in S40 the measure regeneration means 190 inputs a data set of the type of product 280 to be sold, the sales area 290, the weather 300 in the sales area 290, the target customer demographic 310, and the events 320 held in the sales area 290 into the machine learning model 340 after additional learning, and regenerates other specific measures 330.

[0037] By carrying out the above-mentioned processing, the device 100 can accurately obtain specific sales promotion measures 330 suited to the product 280 to be sold, the sales area 290, the weather 300 in the sales area, the target customer group 310, and the events 320 being held in the sales area 290, thereby efficiently increasing sales.

[0038] Although the embodiment of the present invention has been described in detail above, the present invention is not limited to such specific embodiment, and various modifications and variations are possible within the scope of the gist of the present invention described in the claims. [Explanation of symbols]

[0039] 100 Sales promotion proposal device 110 Learning data storage means 120 Model storage means 130 Model Generation Method 140 Measure generation means 150 Measures for implementing policies 160 Verification information calculation means 170 Goal achievement determination means 180 Additional Learning Resources 190 Measures regeneration means 210 Successfully Sold Products 220 Sales area (of successfully sold products) 230 Weather in the sales area (of the product successfully sold) 240 Customer base (of products successfully sold) 250 Events held in the sales area (of the product that was successfully sold) 260 Specific measures for sales promotion (for products that have been successfully sold) 270 training data sets 280 Products for sale 290 Sales area (of the product you want to sell) 300 Weather in the area where you want to sell the product 310 Target customer base (of the product you want to sell) 320 Events held in the sales area (of the product you want to sell) 330 Specific measures for sales promotion generated by machine learning models 340 Machine Learning Models 350 Store terminals (POS systems) 360 Communication Network 510 CPU 520 ROM 530 RAM 540 Auxiliary storage 550 Communication Interface 560 Input Device 570 Output Device 580 Storage Media Interface 590 Storage medium

Claims

1. a model generation means for generating a machine learning model that learns a data set of a sales region, weather in the sales region, target customer segments, events held in the sales region, and specific measures related to sales promotion when sales are determined to be good in the purchase data for each product type, and outputs the specific measures by inputting the product type to be sold, the sales region, weather in the sales region, target customer segments, and events held in the sales region; A model storage means for storing parameters that define input / output characteristics of a machine learning model that outputs the specific measures in response to inputs of the type of product to be sold, the sales area, the weather in the sales area, the target customer group, and events held in the sales area; and A measure generating means for inputting a data set of the type of product to be sold, a sales area, the weather in the sales area, a target customer demographic, and events held in the sales area into the machine learning model, and generating the specific measure; A policy implementation means for carrying out a process to implement the one specific policy at a sales site; A verification information calculation means for calculating sales of a product for which the one specific measure has been implemented; a target achievement determination means for determining whether the sales amount is below a predetermined target value; An additional learning means for performing additional learning on the machine learning model; and a measure regeneration means for inputting a data set of the type of product to be sold, the sales area, the weather in the sales area, the target customer demographic, and events held in the sales area into the machine learning model after the additional learning, when the target achievement determination means determines that the target achievement is below the target, and regenerating other specific measures.

2. a model generation means for generating a machine learning model that learns a data set of a sales region, weather in the sales region, target customer segments, events held in the sales region, and specific measures for sales promotion when sales volume is determined to be good in the purchase data for each product type, and outputs the specific measures by inputting the product type to be sold, the sales region, weather in the sales region, target customer segments, and events held in the sales region; A model storage means for storing parameters that define input / output characteristics of a machine learning model that outputs the specific measures in response to inputs of the type of product to be sold, the sales area, the weather in the sales area, the target customer group, and events held in the sales area; and A measure generating means for inputting a data set of the type of product to be sold, a sales area, the weather in the sales area, a target customer demographic, and events held in the sales area into the machine learning model, and generating the specific measure; A policy implementation means for carrying out a process to implement the one specific policy at a sales site; A verification information calculation means for calculating the sales volume of the product for which the one specific measure has been implemented; a target achievement determination means for determining whether the sales volume is below a predetermined target value; An additional learning means for performing additional learning on the machine learning model; and a measure regeneration means for inputting a data set of the type of product to be sold, the sales area, the weather in the sales area, the target customer demographic, and events held in the sales area into the machine learning model after the additional learning, when the target achievement determination means determines that the target achievement is below the target, and regenerating other specific measures.

3. A computer having a model storage means for storing parameters that define input / output characteristics of a machine learning model that performs machine learning on a data set of a sales region, weather in the sales region, target customer demographics, events held in the sales region, and specific measures for sales promotion when sales are determined to be good in purchase data for each product type, and outputs the specific measures by inputting a product type to be sold, the sales region, weather in the sales region, target customer demographics, and events held in the sales region, a model generation means for generating the machine learning model that learns a data set of a sales region, a weather in the sales region, a purchasing customer base, events held in the sales region, and specific measures related to sales promotion when sales are determined to be good in the purchase data for each of the product types, and outputs the specific measures by inputting the product type to be sold, the sales region, the weather in the sales region, the target customer base, and events held in the sales region; A step in which a measure generating means inputs a data set of one of the types of products to be sold, a sales region, the weather in the sales region, a target customer demographic, and events held in the sales region into the machine learning model, and generates one of the specific measures; A step in which a policy implementation means executes a process for implementing the one specific policy at a sales site; A step of calculating sales of a product for which the one specific measure has been implemented by a verification information calculation means; A step of determining whether or not the sales amount is below a predetermined target value by a target achievement determination means; An additional learning step of causing the machine learning model to perform additional learning; and if the target achievement determination means determines that the target achievement is below the target, inputting a data set of the type of product to be sold, the sales area, the weather in the sales area, the target customer demographic, and events held in the sales area into the machine learning model after the additional learning, and regenerating other specific measures.

4. A computer having a model storage means for storing parameters that define input / output characteristics of a machine learning model that performs machine learning on a data set of a sales region, weather in the sales region, target customer demographics, events held in the sales region, and specific measures for sales promotion when sales volume is determined to be good for each product type in purchase data, and outputs the specific measures by inputting the type of product to be sold, the sales region, weather in the sales region, target customer demographics, and events held in the sales region, a model generation means for generating the machine learning model that learns a data set of a sales region, a weather in the sales region, a purchasing customer base, events held in the sales region, and specific measures related to sales promotion when sales volume is determined to be good in the purchase data for each of the product types, and outputs the specific measures by inputting the product type to be sold, the sales region, the weather in the sales region, the target customer base, and events held in the sales region; A step in which a measure generating means inputs a data set of one of the types of products to be sold, a sales region, the weather in the sales region, a target customer demographic, and events held in the sales region into the machine learning model, and generates one of the specific measures; A step in which a policy implementation means executes a process for implementing the one specific policy at a sales site; A step of calculating a sales volume of a product for which the specific measure has been implemented by a verification information calculation means; A step of determining whether or not the sales volume is below a predetermined target value by a target achievement determination means; An additional learning step of causing the machine learning model to perform additional learning; and if the target achievement determination means determines that the target achievement is below the target, inputting a data set of the type of product to be sold, the sales area, the weather in the sales area, the target customer demographic, and events held in the sales area into the machine learning model after the additional learning, and regenerating other specific measures.

5. A sales promotion suggestion program for causing a computer to execute the method according to claim 3 or 4.

Images