Recommendation system and product recommendation method

Abstract

To collect change of a situation of a site in real time, and to estimate a problem and a solution.SOLUTION: A recommendation system that selects a commercial material to propose for a customer, comprises: an arithmetic unit that performs a predetermined process; and a storage device that can be accessed by the arithmetic unit. The arithmetic unit has a selection unit that estimates a commercial material to be recommended to the customer, and the selection unit calculates a changing rate of specific site information of collected site information, extracts a company having a large changing rate of the specific site information as a target customer, and estimates the commercial material to be recommended to the target customer from similarity of change of the site information of the customer.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a solution recommendation system that supports the proposal of solutions to companies. [Background technology]

[0002] In B2B sales activities between companies, sales representatives may not be able to fully understand the customer's situation and issues, and may miss the optimal timing for a sales approach. In particular, the frequency of sales representatives' visits to customers has decreased in recent years, making it even more difficult to understand the customer's situation and issues. In addition, the spread of digital transformation and IoT has led to the digitization of field data such as 4M data. Furthermore, past sales data and digital customer data are not being used sufficiently in sales activities.

[0003] The following prior art is included as background technology in this technical field. Patent Document 1 (JP Patent Publication No. 2020-86954) describes an information processing system having a change rate information acquisition means for acquiring change rate information representing the change rate of the operating amount of a device, a product information storage means for storing product information, a recommended condition storage means for storing recommended conditions of a product recommended from the product information based on the change rate information, and a recommended product determination means for determining a recommended product based on the change rate information and the recommended conditions (see Abstract). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2020-86954 A Summary of the Invention [Problem to be solved by the invention]

[0005] Under the circumstances described above, in order to grasp the customer's situation in real time without sales representatives visiting the customer's site and make the necessary proposals at the optimal time, it is necessary to infer customer issues using data collected from the customer's site (factory) and infer solutions to resolve those issues.In particular, in the manufacturing industry, it is necessary to collect changes in the production situation at the site detected from 4M data such as information on equipment, human movements, and materials in real time, and infer issues and solutions from those changes.

[0006] The present invention aims to realize a solution recommendation system that collects changes in on-site situations in real time and estimates problems and solutions. [Means for solving the problem]

[0007] A representative example of the invention disclosed in the present application is as follows: A recommendation system for selecting products to be proposed to a customer includes a calculation device that executes a predetermined process and a storage device accessible by the calculation device, the calculation device has a selection unit that estimates products to be recommended to the customer, the selection unit calculates a rate of change in specific on-site information from collected on-site information, extracts companies with a large rate of change in the specific on-site information as target customers, and estimates products to be recommended to the target customers from the similarity of changes in the on-site information of the customers. Effect of the Invention

[0008] According to one aspect of the present invention, it is possible to estimate problems and solutions for customers. Problems, configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0009] [Figure 1] 1 is a block diagram showing a logical configuration of a solution recommendation system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a block diagram showing the physical configuration of the solution recommendation system of the present embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of a configuration of a company category storage unit according to the embodiment. [Figure 4] FIG. 2 is a diagram illustrating an example of the configuration of a past sales activity history information storage unit according to the present embodiment. [Diagram 5] 1 is a flowchart of a process executed by the solution recommendation system of the present embodiment. [Figure 6] 11 is a flowchart of a similar case extraction process according to the present embodiment. [Figure 7] FIG. 1 is a diagram showing changes in on-site information of a certain company. [Figure 8] 13 is a flowchart of a sales activity history registration process according to the present embodiment. [Figure 9] FIG. 13 is a diagram showing an example of a sales recommendation information display screen according to the present embodiment; [Figure 10] FIG. 13 is a diagram showing an example of a sales result registration screen in the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] FIG. 1 is a block diagram showing a logical configuration of a solution recommendation system 100 according to an embodiment of the present invention.

[0011] The solution recommendation system 100 of this embodiment has a company categorization unit 110, a sales activity history information registration unit 120, a solution selection unit 130, a control unit 140, a company category condition storage unit 141, a solution information storage unit 142, and a past sales activity history information storage unit 143.

[0012] The company categorization unit 110 has a company category determination unit 111 and a company category storage unit 112, and categorizes companies with similar business situations and manufacturing attributes. The company category determination unit 111 refers to the company category condition storage unit 141, determines the category of a company using the input company management information 161 and company manufacturing information 162, and stores it in the company category storage unit 112. The company category storage unit 112 stores information on companies whose categories have been determined by the company category determination unit 111. Details of the company category storage unit 112 will be described with reference to FIG. 3.

[0013] The sales activity history information registration unit 120 has a proposal acceptance point calculation unit 121 and a sales result registration unit 122, and registers the status achieved in the sales activity as a result of utilizing the solution recommendation system 100, the customer issues heard from the customer, and the solution the customer is looking for. The proposal acceptance point calculation unit 121 calculates the sales result points from the input sales result information 154, and calculates the proposal acceptance points of the past solution proposal cases stored in the past sales activity history information storage unit 143 using the calculated sales result points. The sales result registration unit 122 stores the results of the past sales activities in the past sales activity history information storage unit 143. The solution information storage unit 142 records the ID, name, and content of the solution, which is the product. The past sales activity history information storage unit 143 stores the results of the past sales activities. Details of the past sales activity history information storage unit 143 will be described later with reference to FIG. 4.

[0014] The solution selection unit 130 includes a past similar data pattern extraction unit 131, a similarity point calculation unit 132, and a sales recommendation information output unit 133, and estimates the customer's problem and solution from the similarity of the past 4M data changes of companies included in the same category. The past similar data pattern extraction unit 131 extracts information within the range set by the extracted data range setting information 155 (for example, sales history information registration period, operation loss time, etc.) from the past sales activity history information storage unit 143. The similarity point calculation unit 132 creates a change pattern of the extracted past sales activity history information, compares the change pattern of the past sales activity history information with the change pattern of the field information, and calculates the similarity point. The sales recommendation information output unit 133 extracts solutions of past sales activity history information with small similarity points, and generates sales recommendation information 153 to be displayed on the sales recommendation information display screen (see FIG. 9).

[0015] The control unit 140 receives input from the sales information input / output unit 164 , processes the input data using each functional unit of the solution recommendation system 100 , and outputs the results of the processing from the sales information input / output unit 164 .

[0016] The extracted data range setting information 155 is information on the range for extracting data from the past business activity history information storage unit 143 (for example, the business history information registration period, the operation loss time, etc.).

[0017] The corporate management information 161 and corporate manufacturing information 162 are information on companies that are clients receiving services from the solution recommendation system 100, and include publicly available information (registers, financial statements, etc.) and non-public information provided by each company. The corporate management information 161 is information for classifying companies mainly in terms of size, and includes basic information (company name, location, etc.) and financial information (sales, profits, etc.). The corporate manufacturing information 162 is information for classifying companies mainly in terms of products and services, and includes information such as product size, manufacturing method, and assembly accuracy.

[0018] The site information collection unit 163 is a terminal such as a sensor or a camera installed in each company, or a manufacturing management system, and collects site information (for example, so-called 4M data including Man, Machine, Method, and Material) from the manufacturing site. The sales information input / output unit 164 is a terminal device (for example, the user terminal 200 shown in FIG. 2) that provides an interface for inputting and outputting sales information to the solution recommendation system 100.

[0019] FIG. 2 is a block diagram showing the physical configuration of the solution recommendation system 100 of this embodiment.

[0020] The solution recommendation system 100 of this embodiment is configured by a computer having a processor (CPU) 1, a memory 2, an auxiliary storage device 3, and a communication interface 4. The solution recommendation system 100 may also have an input interface 5 and an output interface 8.

[0021] The processor 1 is a computing device that executes programs stored in the memory 2. The processor 1 executes various programs to realize the functions of each unit of the solution recommendation system 100 (e.g., a company categorization unit 110, a sales activity history information registration unit 120, a solution selection unit 130, a control unit 140, etc.). Note that some of the processes performed by the processor 1 by executing the programs may be executed by other computing devices (e.g., hardware such as ASIC and FPGA).

[0022] The memory 2 includes a ROM, which is a non-volatile storage element, and a RAM, which is a volatile storage element. The ROM stores unchanging programs (e.g., BIOS) and the like. The RAM is a high-speed, volatile storage element such as a DRAM (Dynamic Random Access Memory), and temporarily stores programs executed by the processor 1 and data used when the programs are executed.

[0023] The auxiliary storage device 3 is, for example, a large-capacity non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD). The auxiliary storage device 3 also stores data (for example, a company category condition storage unit 141, a solution information storage unit 142, a past sales activity history information storage unit 143, and extracted data range setting information 155) used by the processor 1 when executing the program, and the program executed by the processor 1. That is, the program is read from the auxiliary storage device 3, loaded into the memory 2, and executed by the processor 1 to realize each function of the solution recommendation system 100 (for example, a company categorization unit 110, a sales activity history information registration unit 120, a solution selection unit 130, and a control unit 140).

[0024] The communication interface 4 is a network interface device that controls communications with other devices in accordance with a predetermined protocol.

[0025] The input interface 5 is an interface to which input devices such as a keyboard 6 and a mouse 7 are connected and which receives input from a user. The output interface 8 is an interface to which output devices such as a display device 9 and a printer (not shown) are connected and which outputs the results of program execution in a format that can be viewed by the user. Note that a user terminal 200 connected to the solution recommendation system 100 via a network may provide the input device and the output device. In this case, the solution recommendation system 100 may have a web server function, and the user terminal 200 may access the solution recommendation system 100 using a predetermined protocol (e.g., http).

[0026] The program executed by the processor 1 is provided to the solution recommendation system 100 via a removable medium (such as a CD-ROM or a flash memory) or a network, and is stored in a non-volatile auxiliary storage device 3, which is a non-transitory storage medium. For this reason, the solution recommendation system 100 may have an interface for reading data from the removable medium.

[0027] The solution recommendation system 100 is a computer system configured on one physical computer, or on multiple logically or physically configured computers, and may operate on a virtual computer constructed on multiple physical computer resources. For example, the company categorization unit 110, the sales activity history information registration unit 120, the solution selection unit 130, and the control unit 140 may each operate on separate physical or logical computers, or multiple units may be combined to operate on a single physical or logical computer.

[0028] FIG. 3 is a diagram showing an example of the configuration of the company category storage unit 112. As shown in FIG.

[0029] The company category storage unit 112 is information that the company categorization unit 110 refers to in order to categorize similar companies, and stores data that characterize categories, such as industry, sales amount, number of employees, and products.

[0030] FIG. 4 is a diagram showing an example of the configuration of the past business activity history information storage unit 143. As shown in FIG.

[0031] The past sales activity history information storage unit 143 records sales-related data such as customer clusters, change rate patterns, customer issues, proposed solutions, proposal acceptance points, and average operation loss time for each customer cluster. The change patterns are categories of change rates for each item of the company's on-site information, and are represented by a string of numbers or a radar chart. For example, the change rates of waiting for work, absence of workers, shortage of workers, waiting for tools, equipment stoppage, and others may be categorized and represented on a radar chart as described below. The proposed solutions are solutions proposed to customers in the cluster, and are recorded for each customer issue. The proposal acceptance points are points that quantify the progress and results of sales activities related to the proposed solutions for multiple customers included in the customer cluster. The average operation loss time is the average value for each customer of specific on-site information (operation loss), which is an index for extracting target data for solution recommendations.

[0032] FIG. 5 is a flowchart of the process executed by the solution recommendation system 100.

[0033] First, the company category determination unit 111 acquires the company management information 161 and the company manufacturing information 162 input from the input interface 5, determines the category of the company, and outputs the company category information 151 (10). The company category information 151 is information in which the company ID is associated with the determined category.

[0034] Next, the control unit 140 collects on-site information in real time from the on-site information collection unit 163 installed in each company (11), calculates the rate of change of the collected on-site information, and extracts companies with large changes as companies to be recommended (12). The control unit 140 creates patterns of the changes in the on-site information of the extracted companies (13).

[0035] Next, the similarity point calculation unit 132 calculates the similarity of the past business activity history information of the same business category, and assigns similarity points (14).

[0036] Next, the sales recommendation information output unit 133 extracts past sales activity history information having a high similarity from the past sales activity history information storage unit 143 (15), and outputs the sales recommendation information 153 to the sales information input / output unit 164 via the control unit 140 (16).

[0037] Thereafter, the sales activity history information registration unit 120 registers the solution proposal results input to the sales information input / output unit 164.

[0038] FIG. 6 is a flowchart of the similar case extraction process, showing the details of steps 11 to 15 in FIG.

[0039] First, the control unit 140 acquires site information from the site information collection unit 163 (20).

[0040] Next, the control unit 140 extracts data in which the rate of change of specific on-site information exceeds a predetermined threshold (for example, operation loss of ±5%) as target data for solution recommendation (21).

[0041] Next, the control unit 140 calculates the rate of change of other site information and classifies it into a plurality of categories according to a predetermined threshold value (22). For example, the rate of change of waiting for work, absence of worker, shortage of worker, waiting for tool, equipment stoppage, etc. is calculated, and it is classified into five categories: 100% or more, less than 100% to 50% or more, less than 50% to -30% or more, less than -30% to -50% or more, and less than -50%.

[0042] Next, the control unit 140 creates a change pattern of the site information from the category of the change rate of the site information (23). For example, if waiting for work is category 3, absence of worker is category 3, shortage of worker is category 3, waiting for tool is category 2, equipment stoppage is category 5, and others are category 3, the change pattern becomes 333253. In other words, the change pattern is a value that aggregates the features of the site information.

[0043] Then, the control unit 140 outputs recommendation target company information 152 of the company that is the target of the solution recommendation to the past similar data pattern extraction unit 131.

[0044] Next, the past similar data pattern extraction unit 131 extracts (24) past sales activity history information that matches the company category information 151 and the recommended company information 152 from the past sales activity history information storage unit 143 within the range set in the extracted data range setting information 155. By extracting past sales activity history information from the past sales activity history information storage unit 143 within the range set in the extracted data range setting information 155, it is possible to eliminate old sales history information when, for example, a sales history information registration period is specified.

[0045] Next, the similarity point calculation unit 132 creates a change pattern of the extracted past sales activity history information, compares the change pattern of the past sales activity history information with the change pattern of the field information, and calculates the similarity points (25). For example, the similarity points are calculated by adding 1 point for every difference of 1 in each digit. With this method, the similarity points between the change pattern 333253 and the change pattern 334252 are 2 points.

[0046] Next, the sales recommendation information output unit 133 extracts solutions of past sales activity history information with small similarity points (for example, similarity points of 2 or less) and generates sales recommendation information 153 to be displayed on the sales recommendation information display screen (see FIG. 9) (26).

[0047] A specific example of the similar case extraction process will be described with reference to Fig. 7. Fig. 7 is a diagram showing changes in on-site information of a certain company, and shows the rate of change in production status as the change in on-site information.

[0048] An operating loss of ±5% is used as the rate of change of specific on-site information, which serves as an index for extracting target data for solution recommendations.

[0049] In the data shown in the figure, the operation loss time on January 15th increased by 6.6%, exceeding the ±5% threshold. Therefore, the on-site information on January 15th is used to estimate the customer issue.

[0050] First, since the total operation loss time on January 15th was 650 minutes, a change pattern in the average operation loss time within a predetermined range is extracted by referring to the past sales activity history information storage unit 143. This is because, for companies with significantly different values ​​of operation loss time, even if other on-site information is similar, the production methods and the like are not similar in the first place, and therefore the solutions they propose should also be different.

[0051] Then, from the change patterns extracted based on the total operation loss time, past cases having similar change patterns to other on-site information are preferentially extracted.

[0052] FIG. 8 is a flowchart of the sales activity history registration process.

[0053] First, when a recommendation ID is input from the sales information input / output unit 164, the sales activity history information registration unit 120 retrieves the customer name, customer category, on-site situation change date, and change rate pattern for that recommendation ID from the past sales activity history information storage unit 143, and displays them on the sales result registration screen (see Figure 10) (30).

[0054] Next, when the solution ID and acceptance status of the proposed solution are input from the sales information input / output unit 164, the sales activity history information registration unit 120 acquires the proposed solution name and acceptance points of the solution ID from the past sales activity history information storage unit 143, and displays them on the sales result registration screen (see FIG. 10). Then, the proposed solution ID and acceptance status are registered in the past sales activity history information storage unit 143, and past cases with similar customer categories, change rate patterns, and proposed solutions are extracted from the past sales activity history information storage unit 143 (31). Note that a sub-screen may be displayed that displays a list of solution IDs and solution names and allows the user to select the solution ID to be input, prompting the user to input the solution ID.

[0055] Next, the sales activity history information registration unit 120 determines whether a past case similar to the set condition exists (32). If it is not determined that a past case similar to the set condition exists, it registers it as a new pattern in the past sales activity history table (33) and proceeds to step 34. On the other hand, if it is determined that a past case similar to the set condition exists, step 33 is skipped and the process proceeds to step 34.

[0056] Next, the sales activity history information registration unit 120 sets the sales result status of the input sales result information 154 in the past sales activity history information storage unit 143, and the proposal acceptance point calculation unit 121 calculates the sales result points from the input sales result information 154 (34). The sales result points are numerical values ​​determined according to the progress from sales activities and customer consideration to receiving an order, and for example, refusing an appointment may be 0 points, holding an interview may be 20 points, a specific proposal may be 40 points, an estimate may be 60 points, customer consideration and approval may be 80 points, and receiving an order may be 100 points.

[0057] Next, the sales activity history information registration unit 120 uses the calculated sales result points to calculate the proposal acceptance points of the extracted past cases (35). The proposal acceptance points are the average value of the past sales result points.

[0058] Next, the sales activity history information registration unit 120 records the calculated new proposal acceptance points in the past sales activity history information storage unit 143 (36).

[0059] FIG. 9 is a diagram showing an example of a sales recommendation information display screen that displays the sales recommendation information 144.

[0060] The sales recommendation information 144 includes a recommendation ID that is unique identification information of the recommendation, the name of the customer and the customer category for which the solution is recommended, the date of change in the on-site information of the customer, and a change pattern of other on-site information accompanying the change in the detected on-site information. Furthermore, the sales recommendation information 144 includes a solution ID of a solution to be proposed to the customer, similar points of the solution, acceptance points, candidate customer issues, and candidate solutions.

[0061] The sales recommendation information 144 includes a recommendation ID that is unique identification information of the recommendation, the name of the customer and the customer category for which the solution is recommended, the date of change in the on-site information of the customer, and a change pattern of other on-site information accompanying the change in the detected on-site information. Furthermore, the sales recommendation information 144 includes a solution ID of a solution to be proposed to the customer, similar points of the solution, acceptance points, candidate customer issues, and candidate solutions.

[0062] FIG. 10 is a diagram showing an example of a sales result registration screen 1000. As shown in FIG.

[0063] The sales result registration screen includes a recommendation information display area and a solution information display area. The recommendation information display area includes a recommendation ID input field into which a recommendation ID is input from the sales information input / output unit 164, and the customer name, customer category, on-site situation change date, and change rate pattern corresponding to the recommendation ID. The solution information display area includes a solution ID input field, a solution name display field, an acceptance status input field, and an acceptance point display field into which information on a solution proposed to a customer is input.

[0064] As described above, the recommendation system of this embodiment can analyze customer issues from real-time on-site information (4M data) and recommend appropriate solutions to the manufacturing industry. In addition, by feeding back sales results, the accuracy of analyzing customer issues from changes in on-site information can be improved.

[0065] The present invention is not limited to the above-described embodiments, and includes various modified examples and equivalent configurations within the spirit of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the configurations described. Furthermore, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Furthermore, the configuration of another embodiment may be added to the configuration of one embodiment. Furthermore, a part of the configuration of each embodiment may be added, deleted, or replaced with another configuration.

[0066] In addition, each of the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in hardware, for example by designing some or all of them as an integrated circuit, or may be realized in software by a processor interpreting and executing a program that realizes each function.

[0067] Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC card, an SD card, or a DVD.

[0068] In addition, the control lines and information lines shown are those considered necessary for the explanation, and do not necessarily show all the control lines and information lines necessary for implementation. In reality, it can be considered that almost all components are connected to each other. [Explanation of symbols]

[0069] 1 processor 2. Memory 3 Auxiliary storage 4. Communication Interface 5 Input Interface 6 Keyboard 7. Mouse 8 Output Interface 9 Display Devices 100 Solution Recommendation System 110 Corporate Categorization Department 111 Corporate Category Judgment Department 112 Company Category Memory Section 120 Sales Activity History Information Registration Department 121 Proposal acceptance point calculation unit 122 Sales Results Registration Department 130 Solution Selection Department 131 Past Similar Data Pattern Extraction Unit 132 Similarity Points Calculation Section 133 Sales recommendation information output unit 140 Control section 141 Company Category Condition Memory Section 142 Solution information storage unit 143 Past business activity history information storage unit 144 Business Recommendation Information 151 Company Category Information 152 Recommended Company Information 153 Business Recommendation Information 154 Sales Results Information 155 Extraction data range setting information 161 Business Management Information 162 Company manufacturing information 163 Field Information Collection Division 164 Output section 200 User terminals

Claims

1. A recommendation system for selecting products to be proposed to a customer, A computing device that executes a predetermined process and a storage device that can be accessed by the computing device, The computing device has a selection unit that estimates a product to be recommended to a customer, The selection unit is Calculate the rate of change of specific on-site information among the collected on-site information, Extracting companies with a high rate of change in the specific on-site information as target customers; A recommendation system that predicts products to recommend to a target customer based on the similarity of changes in the customer's on-site information.

2. The recommendation system according to claim 1, the arithmetic unit has a categorization unit that determines a category of a customer based on similarity of attributes of the customer; The recommendation system is characterized in that the selection unit estimates the products to be recommended to a customer based on the similarity of changes in on-site information of customers in the same category.

3. The recommendation system according to claim 2, The storage device stores past sales activity history information including products proposed to customers, which is calculated based on a status reached in sales activities of the products, a change pattern showing a rate of change for each category of on-site information of the customers, and a proposal acceptance point showing a progress of sales activities regarding the products to customers in the category; The recommendation system includes a sales activity history information registration unit that updates the past sales activity history information, The selection unit refers to the past sales activity history information and the on-site information, and estimates a product of the past sales activity history information having a change pattern similar to the on-site information of the customer as a product to be recommended to the customer of the on-site information, A recommendation system characterized in that the sales activity history information registration unit updates the proposal acceptance points when sales activities carried out on a customer are input.

4. The recommendation system according to claim 3, the storage device stores extracted data range setting information that defines a range of sales activity history to be extracted from the past sales activity history information; The selection unit is extracting sales activity history from the past sales activity history information within the range defined in the extracted data range setting information; A recommendation system that estimates products to be recommended to a customer based on the extracted sales activity history.

5. The recommendation system according to claim 1, A recommendation system characterized in that the selection unit determines the similarity of changes in the customer's on-site information by taking into account the similarity of the values ​​of the specific on-site information.

6. A product recommendation method in which a recommendation system selects a product to be proposed to a customer, comprising: The recommendation system includes a computing device that executes a predetermined process and a storage device that is accessible by the computing device, The product recommendation method includes: The computing device estimates a product to be recommended to the customer, The computing device calculates a rate of change of specific on-site information among the collected on-site information, The computing device extracts companies having a large rate of change in the specific on-site information as target customers; The method for recommending a product, wherein the calculation device estimates a product to be recommended to a target customer based on similarity of changes in on-site information of the customer.

7. A product recommendation method according to claim 6, comprising: The computing device determines a customer category based on the similarity of customer attributes; The method for recommending a product, characterized in that the calculation device estimates a product to be recommended to a customer based on similarity in changes in on-site information of customers included in the same category.

8. A product recommendation method according to claim 7, comprising: The storage device stores past sales activity history information including products proposed to customers, which is calculated based on a status reached in sales activities of the products, a change pattern showing a rate of change for each category of on-site information of the customers, and a proposal acceptance point showing a progress of sales activities regarding the products to customers in the category; The product recommendation method includes: The computing device refers to the past sales activity history information and the on-site information, and estimates a product of the past sales activity history information having a change pattern similar to that of the on-site information of the customer as a product to be recommended to the customer of the on-site information, A merchandise recommendation method, characterized in that the computing device updates the proposal acceptance points when sales activities carried out with respect to a customer are input.

9. A product recommendation method according to claim 8, comprising: the storage device stores extracted data range setting information that defines a range of sales activity history to be extracted from the past sales activity history information; The product recommendation method includes: The computing device extracts sales activity history from the past sales activity history information within the range defined in the extracted data range setting information, The product recommendation method, wherein the calculation device estimates a product to be recommended to the customer based on the extracted sales activity history.

10. A product recommendation method according to claim 6, comprising: A product recommendation method, characterized in that the calculation device determines the similarity of changes in the customer's on-site information by taking into account the similarity of the values ​​of the specific on-site information.

Images