Program

Abstract

The invention relates to a program. The program causes the information processing device to execute an operation including: training, by machine learning, a learning model corresponding to each store, the learning model having store information of a vehicle store and customer information of a customer in the store as inputs; a proposal information output unit that outputs proposal information of a vehicle proposal to a customer among a plurality of vehicles operated in a store; and acquiring proposal information output from the learning model by inputting customer information of a target customer, which is one or more customers satisfying a predetermined condition among the plurality of customers in the store, into the learning model.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to a program. BACKGROUND

[0002] Conventionally, a technology related to a proposal to a customer is known. For example, a business proposal system for assisting a conversation in a business activity is disclosed in Japanese Patent No. 6572354. SUMMARY

[0003] In a case where the conventional business proposal system is applied to a vehicle sale, a situation of each sales store (a vehicle and an option, etc. to be handled) is sometimes different. In a unified system, it is sometimes difficult to make a proper proposal corresponding to the situation of each sales store.

[0004] The present disclosure accomplished in view of the circumstances aims at improving the technology related to the proposal to the customer.

[0005] The program of one embodiment of the present disclosure causes an information processing apparatus to execute an action including:

[0006] training, by machine learning, a learning model corresponding to each store, the learning model taking store information of a vehicle sales store and customer information of a customer in the sales store as input and taking proposal information of a vehicle proposed to the customer among a plurality of vehicles handled in the sales store as output, and acquiring, by inputting customer information of an object customer, who is one or more customers determined from a plurality of customers in the sales store and who satisfy a predetermined condition, to the learning model, the proposal information output from the learning model.

[0007] According to one embodiment of the present disclosure, the technology related to the proposal to the customer is improved. BRIEF DESCRIPTION OF DRAWINGS

[0008] Features, advantages, and technical and industrial significance of exemplary embodiments of the present application will be described below with reference to the accompanying drawings, in which like numerals denote like elements, and wherein:

[0009] Figure 1 is a block diagram illustrating a schematic configuration of a system of one embodiment of the present disclosure; and

[0010] Figure 2 is a flowchart illustrating an action of an information processing apparatus of one embodiment of the present disclosure. DETAILED DESCRIPTION

[0011] Hereinafter, one embodiment of the present disclosure will be described. In this specification, a customer in a sales store refers to a customer who has used the sales store in the past.

[0012] Summary of Embodiment

[0013] Reference Figure 1 Here is a brief description of a system 1 according to one embodiment of the present disclosure. System 1 includes an information processing device 10 and a terminal device 20. The information processing device 10 and the terminal device 20 are connected in a communicable manner via a network 30 such as the Internet and a mobile communication network.

[0014] The information processing device 10 includes one or more computers, such as a server device, capable of communicating with each other. The information processing device 10 stores learning models.

[0015] Terminal device 20 is one or more computers such as a PC (Personal Computer), smartphone, or tablet. Terminal device 20 is used, for example, by staff at a vehicle dealership.

[0016] First, an overview of this embodiment will be given, with details to follow. The procedure of this embodiment causes the information processing device 10 to perform actions including training a learning model corresponding to each store using machine learning and acquiring proposal information output from the learning model. The learning model corresponding to each store takes the store information of the vehicle dealership and the customer information of the customers in the dealership as input, and outputs proposal information for vehicles offered to customers among the multiple vehicles sold at the dealership. The proposal information output from the learning model is acquired by inputting the customer information of one or more customers (i.e., target customers) determined from the multiple customers of the dealership and meeting predetermined conditions into the learning model.

[0017] According to this embodiment, a learning model trained using the unique store information of each retail store as input is used to generate proposal information. Therefore, appropriate proposal information can be generated based on the specific circumstances of each retail store.

[0018] Structure of Information Processing Device 10

[0019] like Figure 1 As shown, the information processing device 10 includes a control unit 100, a storage unit 102, and a communication unit 104.

[0020] The control unit 100 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processor is, for example, a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor for a specific process, but is not limited thereto. The programmable circuit is, for example, an FPGA (Field-Programmable Gate Array), but is not limited thereto. The dedicated circuit is, for example, an ASIC (Application Specific Integrated Circuit), but is not limited thereto. The control unit 100 performs various processes related to the operation of the information processing apparatus 10 and controls each unit of the information processing apparatus 10.

[0021] The storage unit 102 includes one or more memories. Each memory included in the storage unit 102 can function as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 102 stores arbitrary information for the operation of the information processing apparatus 10. For example, the storage unit 102 can store, for example, a system program, an application program, and embedded software. In the present embodiment, the storage unit 102 stores a learning model corresponding to each store. The storage unit 102 also stores a program product including the program of the present embodiment. The storage unit 102 can also store arbitrary information related to the sale of a vehicle. The information stored in the storage unit 102 can be updated, for example, based on information acquired from the network 30 via the communication unit 104.

[0022] The communication unit 104 includes at least one communication interface connected to the network 30. The communication interface corresponds to, for example, a mobile communication standard such as 4G (4th generation) or 5G (5th generation), or a wired LAN (Local Area Network) communication standard or a wireless LAN communication standard. However, the communication interface is not limited thereto and can correspond to an arbitrary communication standard.

[0023] Structure of terminal apparatus 20

[0024] As shown in FIG. 2, the terminal apparatus 20 includes a control unit 200, an input unit 202, a display unit 204, and a communication unit 206. Figure 1

[0025] ​The control section 200 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processor is, for example, a general-purpose processor such as a CPU or a GPU, or a dedicated processor for a specific processing, but is not limited thereto. The programmable circuit is, for example, an FPGA, but is not limited thereto. The dedicated circuit is, for example, an ASIC, but is not limited thereto. The control section 200 performs various processes related to the operation of the terminal device 20 and controls each section of the terminal device 20.

[0026] The input section 202 includes one or more input interfaces. The input section 202 receives an operation that inputs information for the operation of the terminal device 20. The input interface is, for example, a physical button, an electrostatic capacity button, a pointing device, a touch screen provided integrally with a display of the display section 204, or a microphone that receives a sound input. The input section 202 can be connected to the terminal device 20 as an external input device instead of being provided to the terminal device 20. As a connection method, any of a USB (Universal Serial Bus), an HDMI (registered trademark) (High-Definition Multimedia Interface), or Bluetooth (registered trademark) can be used.

[0027] The display section 204 includes one or more display interfaces. The display interface is, for example, a display that displays information as an image. The display is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display. The display section 204 displays information obtained by the operation of the terminal device 20. The display section 204 can be connected to the terminal device 20 as an external display device instead of being provided to the terminal device 20. As a connection method, any of a USB, an HDMI (registered trademark), or Bluetooth (registered trademark) can be used.

[0028] The communication section 206 includes at least one communication interface that is connected to the network 30. The communication interface corresponds to, for example, a mobile communication standard such as 4G or 5G, or a wired LAN communication standard or a wireless LAN communication standard, but is not limited thereto and can correspond to any communication standard.

[0029] Operation flow of the information processing device 10

[0030] Reference Figure 2 The operation of the information processing device 10 according to the present embodiment will be described. In the following, communication between the terminal device 20 and the information processing device 10 is performed via the communication sections 104, 206, and the network 30.

[0031] S101: The control section 100 of the information processing apparatus 10 trains a learning model corresponding to each store by machine learning. The learning model corresponding to each store takes, as input, store information of a vehicle sales store and customer information of a customer in the sales store, and takes, as output, proposal information of a vehicle proposed to the customer among a plurality of vehicles handled by the sales store. That is, a different learning model is generated for each store within the information processing apparatus 10.

[0032] The store information can also include information indicating one or more of a vehicle handled by the sales store, an option of the vehicle, and a fee plan. The store information can also further include information indicating a delivery period and an inventory status of each vehicle handled by the sales store. By machine learning that takes the delivery period and the inventory of each vehicle as input, it is possible to realize a proposal that takes into account the situation of the sales store that wants to preferentially propose a vehicle with a fast delivery period and a vehicle with a surplus in inventory. The information of the vehicle handled by the sales store can include one or more of a vehicle type, a grade, a specification, an engine displacement, a fuel consumption, a drive system (front-wheel drive, rear-wheel drive, etc.), and a residual value rate.

[0033] The customer information includes primary information and secondary information. The primary information includes present vehicle information indicating information of a vehicle currently owned by the customer, i.e., a present vehicle, and contract information at the time of purchase of the present vehicle. The present vehicle information can also include one or more of a vehicle model, a class, an equipment, a mileage, a vehicle number, a first registration year and month, a next inspection period, a next inspection scheduled date, a residual value rate, and a trade-in price. The contract information can also include one or more of a payment method of a cost of the present vehicle or a past vehicle owned by the customer in the past, a down payment, a monthly payment amount of a loan, a loan reward amount, a remaining cumulative amount, a number of times of a loan, an insurance company to join, a monthly or annual fee of insurance, a class of insurance, a name, an address, and a telephone number. The payment method of the cost of the past vehicle includes a remaining amount setting type loan, an installment, a car rental, a car subscription, a one-time payment, and the like. The "remaining amount setting type loan" refers to a payment method in which a trade-in guarantee price, which is a predetermined residual value, of a purchase price of a vehicle selected by the customer is fixed, and an installment of a remaining amount is made for a certain contract period. The secondary information includes personal information of the customer. The personal information can also include one or more of a budget, a family size, a family composition, an age of a child, a current situation of the child, a pet, an interest, a state of the customer, a plan of job change or moving, dissatisfaction or a desire for the present vehicle, a use of the present vehicle, and a purchase tendency. The current situation of the child includes birth, school entrance, an extracurricular activity, and the like. The dissatisfaction or the desire for the present vehicle includes a desire related to a load capacity, a small turning performance, a horsepower, a fuel consumption, an equipment, a loan amount, an effort required to own the present vehicle, a maintenance cost, and the like. The use of the present vehicle includes commuting, leisure, and the like. The personal information can also be a report in which matters heard from the customer by a staff in the past, for example, are summarized in a natural language. A plurality of feature amounts (budget, lifestyle, dissatisfaction for the present vehicle, and the like) associated with the secondary information in the customer information input to the learning model are extracted, for example, by natural language processing, for training of the learning model. The extracted feature amounts can also be predetermined.

[0034] The proposal information may also include information about the proposed vehicle, the cost of each payment method, the proposal category, information extracted from secondary information, and one or more recommended sentences generated through recommendation sentence generation. Information about the proposed vehicle includes model, engine type, class, performance, etc. The cost of each payment method includes monthly fees, etc. Proposal categories include vehicle size increases, etc. Information extracted from secondary information includes things like "a child was recently born," etc. Recommended sentences generated through recommendation sentence generation include things like "Because the customer's family has increased, the amount of goods has also increased, therefore a spacious ○○ vehicle is best," etc. Recommended sentences may also include articles that consider the customer's lifestyle. Recommended sentences may also include articles explaining the advantages of changing one's lifestyle by purchasing and replacing the vehicle with the proposed one (reduced costs, the whole family being able to travel, etc.). For example, the proposal information states: "• Monthly fee: Assuming the current vehicle is sold for 600,000 yen, the monthly fee remains unchanged. • Fuel consumption: For commuting, with an average monthly mileage of 2,000 km, a HEV (Hybrid Electric Vehicle) would reduce fuel costs by 00,000 yen annually, making it economical. • Maintenance: By replacing the vehicle now, there is no need to pay for tire replacements and vehicle inspections that may occur one year later, thus reducing vehicle maintenance costs."

[0035] In this embodiment, the control unit 100 trains the learning model into a learning model for each store using supervised learning. During training, supervised learning treats instances where the learning model outputs vehicle information for a successfully sold vehicle as correct, and instances where it outputs vehicle information for a vehicle that was not successfully sold as incorrect, in relation to the customer information input into the learning model. By using past sales performance as training data, vehicles with a high probability of sale can be proposed. The control unit 100 can also train the learning model using unsupervised learning.

[0036] S102: The control unit 100 identifies one or more customers who meet predetermined conditions from among multiple customers in the sales store as target customers.

[0037] The control unit 100 acquires information representing predetermined conditions input to the input unit 202 of the terminal device 20 via the communication unit 104. The control unit 100 identifies at least one customer who meets the input predetermined conditions as target customers. The predetermined conditions may also include conditions such as customers who have made an appointment to visit the dealership, customers whose remaining period before the vehicle inspection validity period is less than a threshold, and customers whose predetermined period has elapsed since their initial registration. Thus, for example, only customers who need to be dealt with in the near future can be identified as target customers, thereby improving the accessibility and convenience of information for staff.

[0038] S103: The control unit 100 obtains proposal information output from the learning model by inputting the customer information and store information of each target customer into the learning model trained for the store.

[0039] The control unit 100 acquires customer information and store information of each target customer from the input unit 202 of the terminal device 20 via the communication unit 104. The control unit 100 inputs the acquired customer information and store information into the learning model to obtain proposal information output from the learning model. The learning model may also, when generating proposal information, sequentially execute the following steps: proposal mode selection, vehicle body type selection, engine type selection, vehicle model selection, payment plan selection, amount calculation, generation of recommendation reasons for the proposed vehicle, and generation of recommendation sentences. Proposal modes include scaling up and scaling down. Vehicle body types include sedans and minivans. Engine types include HEVs and diesel engines. Payment plans include lump-sum payments and installment payments.

[0040] S104: The control unit 100 causes the display unit 204 of the terminal device 20 to display proposal information for each target customer.

[0041] S105: The control unit 100 causes the display unit 204 to display one or more user interfaces on the screen displaying proposal information.

[0042] The user interface may include, for example, buttons that accept input for causing the terminal device 20 to perform a predetermined action. The predetermined action may also include generating price information for the vehicle involved in the proposal information, printing the proposal document, and sending the proposal document to the target customer. Here, the proposal document refers to a customer-facing document created based on the proposal information.

[0043] S106: The control unit 100 causes the terminal device 20 to perform at least one of the predetermined actions based on input to one or more user interfaces.

[0044] Since actions can be performed directly from the screen displaying proposal information, there is no need to migrate to other screens, thus improving operability.

[0045] This disclosure has been described based on the accompanying drawings and embodiments, but those skilled in the art should note that various modifications and alterations can be made based on this disclosure. Therefore, it should be understood that such modifications and alterations are included within the scope of this disclosure. For example, the functions contained in each component or step can be reconfigured in a logically consistent manner, and multiple components or steps can be combined into one or divided.

[0046] For example, in the above embodiments, it is also possible to distribute the configuration and operation of the information processing device 10 and / or the terminal device 20 among multiple computers capable of communicating with each other. Furthermore, in the above embodiments, the terminal device 20 may have a storage unit for storing the learning model, or the control unit 200 of the terminal device 20 may execute the operation of the information processing device 10.

[0047] The control unit 100 can also select one or more staff members from among the various staff members at the sales store. Furthermore, the booking conditions may also include: conditions indicating that the selected staff members will each be responsible for specific customers; and conditions indicating that customers who have booked customer service within the booking period are eligible. Since only customers for whom the selected staff members are responsible and who require customer service in the near future are identified as the recipients of the proposal information, it becomes easier for the store manager or supervisor to confirm and manage staff schedules.

Claims

1. A program in which, This program causes the information processing device to perform actions including the following steps: Machine learning is used to train a learning model corresponding to each store. The learning model takes the store information of the vehicle dealership and the customer information of the customers in the dealership as input, and takes the proposal information of the customer for the vehicle among the multiple vehicles operated by the dealership as output. as well as By inputting the customer information of the target customer into the learning model, proposal information output from the learning model is obtained. The target customer is one or more customers who meet the predetermined conditions, determined from multiple customers in the sales store.

2. The procedure according to claim 1, wherein, The conditions for the reservation include at least one of the following: customers who have made an appointment to visit the dealership, customers whose remaining period before the vehicle inspection expires is less than a threshold, and customers whose reservation period has elapsed since the initial registration date.

3. The procedure according to claim 2, wherein, The action also includes selecting one or more staff members from among the multiple staff members of the sales store. The pre-determined conditions also include the condition that the selected one or more staff members are each responsible for a customer, and the condition that a customer has been pre-determined for a customer during the pre-determined period.

4. The procedure according to claim 1, wherein, The training includes training the learning model through supervised learning, where the supervised learning considers it correct if the learning model outputs vehicle information of vehicles that have been transacted with customers involved in the customer information input into the learning model, and incorrect if the learning model outputs vehicle information of vehicles that have not been transacted.

5. The procedure according to claim 1, wherein, The action also includes: The terminal device of the vehicle dealership displays the proposal information for each of the target customers. In the display unit, one or more user interfaces are displayed on the screen showing the proposal information; and Based on input to one or more user interfaces, the terminal device performs at least one of the following: generating pricing information for the vehicle involved in the proposal information, printing a customer-facing document, i.e., a proposal, based on the proposal information, and sending the proposal to the target customer.

Images