Information processing system

Abstract

To accurately classify customer loyalty by product brand and easily visualize their characteristics. [Solution] The information processing system comprises a control unit. The control unit acquires purchase history information, including the number of purchases and the number of units purchased for each brand of a predetermined category of products for multiple customers over a predetermined period. Based on the number of purchases for each brand and the ratio of the number of units purchased for each brand to the total number of units purchased for all brands, the control unit determines the loyalty classification of each customer for each brand from at least a first customer classification, a second customer classification lower than the first customer classification, and a third customer classification lower than the second customer classification. In response to the brand selection by the user terminal, the control unit outputs a predetermined statistical chart to the user terminal based on the number of units purchased for each determined loyalty classification of that brand.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, and a program for processing information related to customer purchasing activities.

Background Art

[0002] Conventionally, there has been a technique for classifying customers based on customer purchase data.

[0003] For example, in Patent Document 1 below, a first classification step of classifying customers into a plurality of hierarchies according to the purchase quantity of products in a specific market for each customer based on customer purchase data for a predetermined period, and based on the customer purchase data for the same predetermined period as the first classification step, a second classification step of classifying customers into a plurality of hierarchies according to the concentration degree of purchase of a specific product among the products in a specific market for each customer according to the concentration degree of the purchased product types, and a two-dimensional display step of dividing a two-dimensional display screen constituted by a first coordinate axis of a plurality of hierarchies by the classification of the first classification step and a second coordinate axis of a plurality of hierarchies by the classification of the second classification step into cells of all combinations of each hierarchy and displaying them on a display unit are disclosed.

[0004] Also, in Patent Document 2 below, questionnaire information including the results of answering questionnaires regarding brand recognition, usage experience, and usage frequency and the attributes of questionnaire respondents is obtained, and based on the answering results, the respondents are assigned to any one of a plurality of preset segments, and for each of the plurality of segments, based on the number of respondents assigned to the corresponding segment, the number of demanders and the ratio of the number of demanders to the total number of segments are estimated, and information regarding measures for demanders in each of the plurality of segments and the costs for the measures is displayed so as to be compared between different segments. A marketing support system is disclosed.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

[0006] However, the technology described in Patent Document 1 does not use the frequency of customer purchases over a predetermined period to classify customers. Therefore, for example, a customer who purchased a product only once over a predetermined period and then stopped purchasing it may be classified into the same loyalty category as a customer who made multiple purchases in a continuous cycle.

[0007] Furthermore, although the technology described in Patent Document 2 above classifies consumers based on their frequency of brand use, this frequency is based solely on the results of consumer surveys, and these survey results do not include information on the number of products purchased. Therefore, the accuracy of the classification may still be low.

[0008] The present invention relates to an information processing system, information processing method, and program that can accurately classify the loyalty of purchasing customers for each product brand and easily visualize their characteristics. [Means for solving the problem]

[0009] An information processing system according to one embodiment of the present invention comprises a control unit. The control unit acquires purchase history information, including the number of purchases and the number of units purchased for each brand of a predetermined category of products for a predetermined period of time for a plurality of customers. Based on the number of purchases for each brand and the ratio of the number of units purchased for each brand to the total number of units purchased for all brands for each customer, the control unit determines the customer loyalty classification for each brand for each customer from at least a first customer classification, a second customer classification lower than the first customer classification, and a third customer classification lower than the second customer classification. The control unit generates a predetermined statistical chart based on the number of units purchased for each determined loyalty classification of the brand and outputs it to the user terminal. [Effects of the Invention]

[0010] According to one embodiment of the present invention, an information processing system can accurately classify the loyalty of purchasing customers for each product brand and easily visualize their characteristics. However, this effect is not limited to the present invention. [Brief explanation of the drawing]

[0011] [Figure 1] This diagram shows the configuration of a customer analysis system related to one embodiment of the present invention. [Figure 2] This diagram shows the hardware configuration of a customer analysis server according to one embodiment of the present invention. [Figure 3] This diagram shows the configuration of the database of a customer analysis server according to one embodiment of the present invention. [Figure 4] This diagram illustrates the customer loyalty classification determined by a customer analysis server according to one embodiment of the present invention. [Figure 5] This flowchart shows the flow of customer purchase information analysis processing by a customer analysis server according to one embodiment of the present invention. [Figure 6] This figure shows the relationship between the number of items purchased for a target brand and the total number of items purchased for all brands, used by a customer analysis server according to one embodiment of the present invention to determine customer loyalty classification. [Figure 7] This flowchart shows the flow of customer analysis information provision processing by a customer analysis server according to one embodiment of the present invention. [Figure 8] This figure shows an example of a statistical chart generated by a customer analysis server related to one embodiment of the present invention. [Figure 9] This figure shows another example of a statistical chart generated by a customer analysis server according to one embodiment of the present invention. [Figure 10] This figure shows another example of a statistical chart generated by a customer analysis server according to one embodiment of the present invention. [Modes for carrying out the invention]

[0012] Hereinafter, embodiments of the present invention will be described while referring to the drawings.

[0013] [Configuration of the System] As shown in FIG. 1, this system includes a customer analysis server 100 on the Internet 50 and a plurality of user terminals 200.

[0014] The customer analysis server 100 is a server (information processing device) that executes a service for analyzing purchase data of products by customers and providing the analysis information to users. The customer analysis server 100 is connected to a plurality of user terminals 200 via the Internet 50.

[0015] The products include products of multiple brands in multiple categories such as, for example, household goods (consumables such as laundry detergents, fabric softeners, diapers, etc.), cosmetics, clothing, food, etc. The analysis information includes customer loyalty classification information for each category and each brand of customers who purchased the products.

[0016] The customer analysis server 100 receives a customer analysis information providing request from the user terminal 200 together with the user's selection information regarding the product category and brand, and transmits the customer analysis information in the category and brand to the user terminal 200.

[0017] The user terminal 200 (200A, 200B, 200C...) is a terminal used by the user, such as a smartphone, mobile phone, tablet PC (Personal Computer), notebook PC, desktop PC, etc. The user is, for example, a marketing staff or product development staff of a company (manufacturer). Note that the customer analysis server 100 may be a server operated by the company for the company's staff. In this case, the customer analysis server 100 may be connected to an intranet within the company instead of the Internet 50.

[0018] The user terminal 200 accesses the customer analysis server 100, receives a web page containing the customer analysis information, etc., and displays it on the screen using a browser or similar. Alternatively, the user terminal 200 may have an application installed that supports the customer analysis information provision service, and the user terminal 200 may access the customer analysis server 100 and display the customer analysis information using that application.

[0019] [Hardware configuration of the customer analysis server] As shown in Figure 2, the customer analysis server 100 includes a CPU (Central Processing Unit) 11, ROM (Read Only Memory) 12, RAM (Random Access Memory) 13, an input / output interface 15, and a bus 14 that connects these components to each other.

[0020] The CPU 11 accesses RAM 13 and other memory as needed, performing various calculations and comprehensively controlling each block of the customer analysis server 100. Multiple CPUs 11 may be provided depending on the processing. ROM 12 is a non-volatile memory in which the OS, programs, and firmware such as various parameters to be executed by the CPU 11 are permanently stored. RAM 13 is used as a working area for the CPU 11 and temporarily holds the OS, various running applications, and various data being processed.

[0021] The input / output interface 15 is connected to a display unit 16, an operation reception unit 17, a storage unit 18, a communication unit 19, and the like.

[0022] The display unit 16 is a display device that uses, for example, an LCD (Liquid Crystal Display), an OLED (Organic ElectroLuminescence Display), or a CRT (Cathode Ray Tube).

[0023] The operation reception unit 17 is, for example, a pointing device such as a mouse, a keyboard, a touch panel, or other input device. If the operation reception unit 17 is a touch panel, the touch panel may be integrated with the display unit 16.

[0024] The storage unit 18 is a non-volatile memory such as an HDD (Hard Disk Drive), flash memory (SSD; Solid State Drive), or other solid-state memory. The OS, various applications, and various data are stored in this storage unit 18.

[0025] As will be described later, in this embodiment in particular, the storage unit 18 has a customer information database, a purchase information database, and a customer analysis information database, in addition to programs such as applications necessary for the customer analysis information provision process described later.

[0026] The communication unit 19 consists of various modules for wireless communication, such as a NIC (Network Interface Card) for Ethernet or a wireless LAN, and is responsible for communication processing with the user terminal 200.

[0027] Although not shown in the diagram, the basic hardware configuration of the user terminal 200 is substantially the same as that of the customer analysis server 100.

[0028] [Database configuration of the customer analysis server]

[0029] As shown in Figure 3, the customer analysis server 100 has a customer information database 31, a purchase information database 32, and a customer analysis information database 33 in its storage unit 18. Note that these databases may also be stored in external storage devices or servers connected to the customer analysis server 100, rather than in the storage unit 18.

[0030] The customer information database 31 stores attribute information for each customer that is the target of customer analysis by the customer analysis server 100. Customer attribute information includes general information such as customer ID, age (age group), occupation, address (residential area), and gender to identify the customer, as well as information on favorite product categories and brands, and information indicating customer loyalty classification, which will be described later.

[0031] The purchase information database 32 stores purchase history information such as the category, brand, price, quantity, purchase date and time, and purchase store (purchase channel) of the products purchased by the customer, categorized and brand by category.

[0032] The customer analysis information database 33 stores information generated by the customer analysis server 100 based on the information stored in the purchase information database 32. Specifically, the customer analysis information database 33 stores data such as customer loyalty classifications, which classify customers according to their purchase frequency and quantity for each category and brand, as well as statistical graphs that visualize the customer structure based on these customer loyalty classifications, such as graphs showing the trends in the number of customers and purchase amounts for each customer loyalty classification for each brand.

[0033] These databases are referenced and used as needed in the customer purchase information analysis processing and customer analysis information provision processing performed by the customer analysis server 100, which will be described later.

[0034] [Customer Loyalty Classification] Figure 4 shows the customer loyalty classifications and their definitions determined by the customer analysis server 100 for each category and brand in this embodiment. As shown in the figure, the customer analysis server 100 classifies customers into five loyalty classifications for each product category and brand: loyal customers, repeat customers, trial customers, churned customers, and non-purchasing customers.

[0035] The analysis period is defined as follows: T1 is the most recent 12 months, T2 is the 12 months prior to T1, and T3 is the period of T1 + T2. Here, periods T1 and T2 can be set according to the average purchase interval for each target product. For products with shorter purchase intervals, T1 and T2 may be set to, for example, 6 months, 3 months, or 1 month, depending on the interval, while for products with longer purchase intervals, they may be set to 24 months, 36 months, or similar, depending on the interval. The customer analysis server 100 may calculate and update the average purchase interval from the purchase history data of each customer in the purchase information database 32.

[0036] By default, the number of purchases is counted by the number of purchases made on each day. For example, if purchases are made on different days, it will be counted as multiple purchases. If you want to count purchases on a daily basis, such as counting two purchases on the same day as one, the counting period is set to one day, but you can also set the counting period to three days, one week, etc. This allows you to exclude customers who only purchase during sale periods from being loyal customers.

[0037] A loyal customer is a customer who has purchased products from the target brand two or more times during period T1, and whose purchase ratio of the number of products from that brand to the total number of products from all purchased brands within the target category is above a predetermined threshold (%). The threshold may be, for example, 70% or 80%, but is not limited to these.

[0038] Repeat customers are defined as customers who have purchased products of the target brand two or more times during period T1, and whose percentage within the target category is below the threshold (%).

[0039] A trial customer is a customer who purchased a product of the target brand only once during period T1.

[0040] A churned customer is a customer who purchased a product of the target brand at least once during period T2, but did not purchase any products of the target brand during period T1.

[0041] Non-purchasing customers are those who have not purchased any products from the target brand during period T3.

[0042] [Customer analysis server operation] Next, the operation of the customer analysis server 100 configured as described above will be explained. This operation is performed through the cooperation of the hardware of the customer analysis server 100, such as the CPU 11 and communication unit 19, and the software stored in the storage unit 18. For convenience, in the following explanation, the CPU 11 will be considered the main operator.

[0043] (Customer purchase information analysis processing by customer analysis server) Figure 5 is a flowchart showing the flow of customer purchase information analysis processing (customer loyalty classification determination processing) by the customer analysis server 100.

[0044] As shown in the figure, first the CPU 11 obtains purchase data for the target category of the customer being analyzed from the purchase information database 32 (step 51).

[0045] Next, CPU11 extracts the number of purchases of the target brand in the most recent 12 months (period T1 above) from the purchase data (step 52).

[0046] Next, CPU 11 determines whether the number of purchases mentioned above is two or more (step 53).

[0047] If it is determined that the above purchase count is two or more (Yes in step 53), CPU 11 extracts A) the number of target brand products purchased in the most recent 12 months and B) the number of products purchased from all brands within the target category from the above purchase data (step 54).

[0048] Next, the CPU 11 determines whether the ratio of A) to B) is equal to or greater than the threshold (%) (step 55).

[0049] If the CPU determines that the above ratio is above the threshold (Yes in step 55), it classifies the customer as a loyal customer (step 56). On the other hand, if the CPU determines that the above ratio is below the threshold (No in step 55), it classifies the customer as a repeat customer (step 57).

[0050] Furthermore, if in step 53 it is determined that the number of purchases is less than two (No. in step 53), the CPU 11 determines whether the number of purchases is one or not (step 58).

[0051] If it is determined that the number of purchases is one (Yes in step 58), CPU 11 classifies the customer as a trial customer (step 59).

[0052] On the other hand, if it is determined that the number of purchases is 0 (No. in step 58), CPU 11 determines whether the customer has purchased any products of the target brand in the 12 months prior to the most recent 12 months (T1) (T2 above) (step 60).

[0053] If CPU 11 determines that the customer purchased the target brand's products during period T2 (Yes in step 60), it classifies the customer as a churned customer (step 61). On the other hand, if CPU 11 determines that the customer did not purchase the products during period T2 (No in step 60), it classifies the customer as a non-purchasing customer (step 62).

[0054] The information used to determine the loyalty classification is stored in the customer analysis information database 33, categorized and brand by brand.

[0055] Furthermore, the customer analysis server 100 may, in order to determine the risk of customer churn early on for the above-mentioned loyal customers, repeat customers, and trial customers, and to enhance the effectiveness of repeat purchase promotion measures, identify customers who have not made a repeat purchase for three months since their last purchase as "potential churners" within each customer loyalty classification, and store this information in the above-mentioned customer information database 31 or customer analysis information database 33.

[0056] Figure 6 is a table showing the relationship between the number of items purchased for a target brand (row) and the total number of items purchased for all brands (column), which the customer analysis server 100 uses to determine the above customer loyalty classification.

[0057] As described above, customers who have purchased products from the target brand zero times are classified as either churned customers or non-purchasing customers, while customers who have purchased products once are classified as trial customers, regardless of the number of purchases or items purchased from other brands.

[0058] Customers who have purchased products from the target brand two or more times are classified as either loyal customers or repeat customers, as shown in the diagram, according to the ratio of the number of items purchased from that brand to the total number of items purchased from all brands in the category.

[0059] (Customer purchase information analysis processing by customer analysis server) Figure 7 is a flowchart showing the flow of customer analysis information provision processing using the customer loyalty classification described above by the customer analysis server 100.

[0060] As shown in the figure, the CPU 11 first determines whether or not it has received a customer analysis information request from the user terminal 200 (step 71). In response to this customer analysis information request, the user selects the category and brand for which information is requested on the user terminal 200, and this selection information is sent to the customer analysis server 100.

[0061] If the CPU determines that it has received a customer analysis information request (Yes in step 71), the CPU 11 retrieves the target category information and target brand information included in the request (step 72).

[0062] Next, CPU 11 retrieves customer loyalty classification information for the target brand in the target category from the customer analysis information database 33 (step 73).

[0063] Next, CPU 11 generates various statistical graphs from the acquired customer loyalty classification information (step 74).

[0064] Next, the CPU 11 sends the generated statistical graphs to the user terminal 200 (step 75).

[0065] Next, the CPU 11 determines whether or not it has received a customer analysis information request from the user terminal 200 for a different category or brand (step 76).

[0066] If the CPU determines that it has received a customer analytics information request for a different category or brand (Yes in step 76), the CPU 11 returns to step 72 and repeats the subsequent processing.

[0067] On the other hand, if it is determined that no different request has been received (No in step 76), the CPU 11 determines whether or not the user terminal 200 has instructed it to terminate processing (step 77).

[0068] Then, if it determines that the process has been instructed to end (Yes in step 77), the CPU 11 terminates the process. If it determines that the process has not been instructed to end (No in step 77), it continues to display various statistical graphs until it is instructed to end the process.

[0069] Figures 8, 9, and 10 show examples of statistical charts generated by the customer analysis server 100. These statistical charts may be displayed simultaneously on a single screen on the user terminal 200, allowing scrolling vertically or horizontally, or they may be switchable by clicking or other operations.

[0070] Figure 8 is a table showing the number of customers in each customer loyalty category (loyal / repeat / trial) for the target brand over one month, the difference from the previous month, the difference from the same month of the previous year, their population composition ratio and sales composition ratio, as well as the average purchase quantity, purchase amount, and average unit price per customer for each customer loyalty category. The target brand and the month to be displayed can be arbitrarily set and switched by the user.

[0071] Figure 9(A) is a graph showing the trend in the number of customers for each customer loyalty category of the target brand over a two-year period. This allows the customer analysis server 100 to visualize and present to the user the changes in the number of customers for each loyalty category over time.

[0072] As shown in Figure (B), the graph in Figure (A) visually indicates, for example, by different colors, where the increase in the number of customers for each customer loyalty category shows a divergent trend (Figure (B1)), where the increase in the number of customers shows a stable trend (Figure (B2)), and where the increase in the number of customers shows a convergent trend over two consecutive periods (months).

[0073] Specifically, for example, data markers showing a divergent trend are shown in black, data markers showing a maintenance trend are shown in dark gray, and data markers showing a convergence trend are shown in light gray. In this way, the customer analysis server 100 determines and visualizes the growth patterns from the changes in the number of customers for each customer loyalty category, allowing users to recognize market changes early and speed up the next action.

[0074] Figure 10 is a graph showing the two-year trend of purchase amounts for each customer loyalty category of the target brand. This allows the customer analysis server 100 to visualize and present to the user the changes in the sales contribution of customers in each loyalty category over time. The purchase amount is calculated from the number of purchases and the average purchase price for each customer stored in the purchase information database 32.

[0075] The customer analysis server 100 may provide a user interface in these statistical charts for narrowing down customers in each loyalty category by, for example, gender, age, or purchase channel, and enable in-depth searches with a click operation by the user. The display period in the statistical charts may also be switchable as desired.

[0076] Furthermore, the customer analysis server 100 may be provided with a function to export each statistical chart in a predetermined format. Each statistical chart will be provided with a predetermined user interface for such export. This will allow users to easily export analysis content and data as needed, such as for meeting reports.

[0077] Furthermore, when sending a customer analysis information request to the customer analysis server 100, users can specify search criteria for target categories and brands with just a few clicks (selections) using a mouse, allowing anyone to easily operate and utilize customer analysis information regardless of their search skills.

[0078] As described above, according to this embodiment, the customer analysis server 100 can accurately classify the loyalty of purchasing customers for each product brand and easily visualize their characteristics.

[0079] [Differentiation] Although embodiments of the present invention have been described above, the present invention is not limited to the embodiments described above, and various modifications can be made without departing from the spirit of the present invention.

[0080] In the embodiments described above, five customer loyalty classifications were shown, but customer loyalty classifications are not limited to these five. For example, customers may be classified into only three categories: loyal customers, repeat customers, and trial customers.

[0081] The statistical charts shown in the embodiments described above are not limited to these, and various other statistical charts can be created and provided to users using the above customer loyalty classification. For example, for multiple brands, a table comparing the number of loyal customers for each brand, or the percentage of loyal customers for each brand, or a graph plotting the trend over time can be used to compare brands.

[0082] In the embodiment described above, only one customer analysis server 100 is shown, but the processing performed by the customer analysis server 100 may be distributed and executed across multiple servers. For example, the customer loyalty classification process and the process of providing customer analysis information (statistical charts) using the customer loyalty classification may be performed on separate servers.

[0083] Of the inventions described in the claims of this application, the invention described as "information processing method" is one in which each step is performed automatically by at least one device such as a computer through information processing by software, and not by a human using a computer or other device. In other words, the "information processing method" is an information processing method using computer software, and not a method in which a human operates a computer as a calculating tool. [Explanation of Symbols]

[0084] 11…CPU 18...Storage section 19… Communications Department 31…Customer Information Database 32…Purchase Information Database 33…Customer Analysis Information Database 100... Customer analysis server 200... User terminals

Claims

1. We obtain purchase history information including the number of purchases and the number of items purchased for each brand of multiple products in a specified category over a specified period for multiple customers. Based on the number of purchases per brand by each customer and the ratio of the number of purchases per brand to the total number of purchases of all brands, the loyalty classification of each customer for each brand is determined from at least a first customer classification, a second customer classification lower than the first customer classification, and a third customer classification lower than the second customer classification. The system generates a predetermined statistical chart based on the number of purchases for each loyalty category determined for the aforementioned brand and outputs it to the user terminal. control unit An information processing system equipped with the following features.

2. The control unit receives selection information from the user terminal to select one of the multiple brands, and generates the statistical chart for the selected brand. The information processing system according to claim 1.

3. The control unit determines that the loyalty classification of customers who have made purchases of each brand less than a predetermined number of times is the third customer classification, and determines whether the loyalty classification is the first customer classification or the second customer classification based on the ratio of the number of items purchased by customers who have made purchases of the predetermined number of times or more. The information processing system according to claim 1 or 2.

4. The control unit sets the predetermined period according to the average purchase interval of the product. The information processing system according to claim 1 or 2.

5. The control unit, Obtain information regarding the purchase price of the aforementioned product, As the aforementioned statistical graphs, for each brand, a first statistical chart showing the trend in the number of customers for each determined loyalty category, and a second statistical chart showing the trend in the purchase amount calculated from the purchase price for each determined loyalty category, are output simultaneously or by switching between them. The information processing system according to claim 1 or 2.

6. The control unit outputs the trend in the number of customers for each determined loyalty classification for each brand as a statistical chart, and outputs on the statistical chart in a way that makes it visible where the increase in the number of customers shows a divergence trend and where it shows a convergence trend. The information processing system according to claim 1 or 2.

7. We obtain purchase history information including the number of purchases and the number of items purchased for each brand of multiple products in a specified category over a specified period for multiple customers. Based on the number of purchases for each brand by each customer and the ratio of the number of purchases for each brand to the total number of purchases for all brands, the customer loyalty classification for each brand of each customer is determined from at least a first customer classification, a second customer classification lower than the first customer classification, and a third customer classification lower than the second customer classification. A predetermined statistical chart is generated based on the number of units purchased for each loyalty category determined for the aforementioned brand, and output to the user terminal. Information processing methods.

8. In an information processing device, A step of obtaining purchase history information including the number of purchases and the number of items purchased for each brand of multiple products in a predetermined category over a predetermined period for multiple customers, Based on the number of purchases for each brand by each customer and the ratio of the number of purchases for each brand to the total number of purchases for all brands, the customer loyalty classification for each brand of each customer is determined from at least a first customer classification, a second customer classification lower than the first customer classification, and a third customer classification lower than the second customer classification. The steps include generating a predetermined statistical chart based on the number of purchases for each determined loyalty category of the brand and outputting it to the user terminal. A program that executes the command.

Images