Information processing device and information processing method

Abstract

An information processing device according to one embodiment of the present invention includes: an acquisition unit that acquires measurement data indicating results of purchase behavior of customers in each of a first store that implemented an advertisement measure at a physical store and a second store that is similar to the first store and did not implement the advertisement measure; and an output unit that outputs an estimation result obtained by estimating an effect of the advertisement measure on the basis of the measurement data of the first store and the second store without using information on status of customers' participation in the advertisement measure.

Description

Information processing device and information processing method

[0001] This invention relates to a technique for estimating the effectiveness of advertising measures in stores.

[0002] Techniques for estimating the effectiveness of measures are known. For example, Patent Document 1 discloses an invention of a machine learning model that outputs predictive data for what would have happened if the measures had not been implemented, based on the actual performance data of stores where the measures were implemented.

[0003] Japanese Patent Publication No. 2022-149951

[0004] The invention described in Patent Document 1 was a method of estimating the effectiveness of a measure based on a simulation prediction of what would happen if the measure were not implemented.

[0005] In contrast, the present invention provides an improved technique for estimating the effectiveness of advertising measures in stores.

[0006] An information processing device according to one aspect of the present disclosure includes an acquisition unit that acquires measurement data showing the results of customer purchasing behavior at a first store where an advertising measure was implemented, and a second store similar to the first store but where the advertising measure was not implemented, and an output unit that outputs an estimation result that estimates the effect of the advertising measure without information on the customer's participation in the advertising measure, based on the measurement data of the first store and the second store.

[0007] An information processing method relating to another aspect of the present disclosure includes the steps of: a computer acquiring measurement data showing the results of customer purchasing behavior at a first store where an in-store advertising measure was implemented, and a second store similar to the first store but where the advertising measure was not implemented; and outputting an estimation result that estimates the effect of the advertising measure without information on the customer's participation in the advertising measure, based on the measurement data of the first store and the second store.

[0008] According to the present invention, an improved technique for estimating the effectiveness of advertising measures in stores can be provided.

[0009] A diagram illustrating the system configuration of an information processing system 1 according to one embodiment. A diagram illustrating the functional configuration of the information processing system 1. A diagram illustrating the hardware configuration of the information processing device 10. A sequence chart illustrating a method for measuring the effectiveness of a measure at the first store. A diagram illustrating a store database 1000. A diagram illustrating a sales trend 2000. A flowchart illustrating a method for identifying the second store by the information processing system 1. A diagram illustrating a trade area map 3000. A diagram illustrating a measure effectiveness list 4000.

[0010] 1. Diagram 1 illustrates the system configuration of an information processing system 1 according to one embodiment. In this example, the information processing system 1 (or simply referred to as the system) is a system for estimating the effectiveness of advertising measures in stores. In this example, stores are physical stores and include, for example, retail stores such as bookstores, service stores such as cafes (or other restaurants), convenience stores, tenants in commercial facilities, or other specialty stores. Advertising measures (or in-store measures) are commercial measures implemented at each store and include, for example, measures that use advertisements that can be viewed and confirmed by customers who actually visit the store (hereinafter referred to as "users"), such as POP advertisements or signage advertisements. Such advertising measures are implemented with the aim of promoting the purchasing and consumption activities of users at the store, and the effectiveness of the advertising measures is measured and evaluated based on various methods.

[0011] In related technologies, to estimate the effectiveness of advertising campaigns, techniques such as installing cameras around advertisements to detect the gaze of customers are used to determine which users actually viewed the advertisements. However, such approaches raise concerns about privacy as individual users may be identified by the cameras. Furthermore, there is a need for improved methods of estimating the effectiveness of campaigns from the perspectives of installation costs including cameras, aggregation time for processing acquired image data, and reliability of the estimation of campaign effectiveness. Therefore, this invention proposes a technology that estimates advertising effectiveness by comparing stores that implemented in-store campaigns with similar stores that did not. In particular, given the nature of in-store advertising campaigns, not all customers who visit the store will necessarily see the advertisements, so it is practical to estimate the effectiveness of campaigns while taking into account that some users do not see them. Therefore, the inventors focused on estimating the effectiveness of campaigns using Fuzzy DiD. An overview of Fuzzy DiD is disclosed, for example, in the following paper.

[0012] Clement de Chaisemartin, Xavier D'Haultfoeuille, &Yannick Guyonvarch, Fuzzy differences-in-differences with stata. The Stata Journal (2019), 19, Number 2, pp. 435-458

[0013] Generally, Fuzzy DiD (Fuzzy Differences-in-Differences) is a method for measuring and evaluating the effect of a specific intervention element on a subject based on the difference (i.e., DID) between the intervention group and a control group that did not receive the intervention. Fuzzy DiD is a method that is expected to be applied in various fields, such as education, healthcare, and economic policy. A key feature of Fuzzy DiD is that it can estimate the effect with high accuracy even when the implementation rate (or intervention rate) of the intervention is uncertain and ambiguous (i.e., fuzzy), such as when the intervention is not carried out at all, is limited to a part of the intervention, or the intensity of the intervention varies individually. This allows for the evaluation of advertising measures with relatively reliable estimated effects, even in realistic scenarios such as some people seeing in-store advertising measures while others do not, with minimal cost (or while protecting user privacy). Therefore, the present invention provides the following system to offer an improved technology for estimating the effect of advertising measures implemented in stores.

[0014] The information processing system 1 includes an information processing device 10, store terminals 20 (for example, store terminals 21, 22, or 23), and a management server 30. In this example, each component of the system is connected via a network 9 as shown in Figure 1. In this example, the network 9 is a computer network such as the Internet or a mobile network.

[0015] The information processing device 10 is an information processing device or server device in the information processing system 1. In this example, the information processing device 10 acquires sales data (hereinafter referred to as "sales data") from a first store that implemented an advertising campaign and a second store that did not implement an advertising campaign, and estimates the effectiveness of the advertising campaign based on this sales data. The first store is the store that actually implemented the advertising campaign and is the store for which the effectiveness of the campaign is measured. The second store is another store similar to the first store. The second store is a comparison store for measuring the effectiveness of the advertising campaign implemented at the first store. The sales data (an example of measurement data) is data that shows the results of the purchasing behavior of users who visited each store, and includes, for example, the amount of sales for each store according to a specific period (for example, the period during which the campaign was implemented). The information processing device 10 estimates the effectiveness of the advertising campaign based on the sales data acquired from each store.

[0016] In this example, the information processing device 10 does not acquire information on the user's participation in the advertising campaign. Participation information is information that indicates whether an individual user has been involved with the advertisement targeted by the campaign (for example, seen, heard, or was influenced by it), and includes, for example, indirect information captured and analyzed by store cameras, and survey information directly obtained from the user's terminal.

[0017] The store terminal 20 is a terminal installed in each store and includes, for example, a personal computer. In this example, the store terminal 20 is a terminal that records customer purchasing behavior in each store and implements functions to record, for example, POS (Point of Sale) data and point history such as point programs, and periodically outputs various data as sales data to the management server 30. The store terminal 20 includes a terminal that cooperates with a QR code (registered trademark) payment service provider's server or the QR code (registered trademark) payment service provider's server itself. In this example, when a consumer reads a POP with an embedded QR code (registered trademark) using a user terminal not shown, such as a smartphone, the consumer's purchasing data is stored in the QR code (registered trademark) payment service provider's server. Details of the sales data will be described later. When distinguishing between multiple store terminals 20, they are referred to as store terminal 21, store terminal 22, ..., and so on. In Figure 1, for example, the store terminal 21 corresponding to store S21 is connected to the management server 30 (or information processing device 10) via the network 9. In this example, store S21 corresponds to the first store where the advertising campaign targeted for effect estimation was implemented. Users who visited store S21 can be broadly divided into those who viewed the advertising campaign and those who did not. Hereafter, when classifying these users, the former will be referred to as participants in the campaign, and the latter as non-participants. Stores S22 and S23 correspond to the second store (or other stores) where the target advertising campaign was not implemented.

[0018] The management server 30 is a server device that manages information about each store. In this example, the management server 30 appropriately acquires information such as store sales, business type, size, location, area, and policies from the store terminals 20. This information is stored as data in the management server 30's database and shared with the information processing device 10 via the network 9. The various types of data managed by the management server 30 will be described later.

[0019] Figure 2 is a diagram illustrating the functional configuration of the information processing system 1. In this embodiment, the information processing device 10 has functional blocks (or components) including an acquisition unit 11, an output unit 12, an estimation unit 13, a determination unit 14, a trade area identification unit 15, a store identification unit 16, a storage unit 191, and a control unit 192. In this example, the storage unit 191 stores various data, programs, and software, including a database. In this example, the control unit 192 performs various controls.

[0020] The acquisition unit 11 acquires measurement data showing the results of customer purchasing behavior at the first store where the advertising campaign was implemented, and at the second store, which is similar to the first store but did not implement the advertising campaign. In this example, the measurement data includes, for example, sales for each store. That is, the sales of the first store include the results of purchasing behavior of users affected by the campaign (for example, people who saw the advertisement). Conversely, the sales of the second store include the results of purchasing behavior as a comparison, unrelated to the campaign (it is also possible to exclude the results of purchasing behavior of people who saw the advertisement). The acquisition unit 11 acquires measurement data from the management server 30, which manages various data at the store terminal 20.

[0021] The output unit 12 outputs an estimated result that estimates the effectiveness of the advertising campaign based on measurement data from the first and second stores, without any information on customer participation in the advertising campaign. Regarding the effectiveness of this advertising campaign (hereinafter referred to as "campaign effect"), the output unit 12 outputs, for example, the difference in sales between the first and second stores over a specific period as the estimated result. In this example, the output unit 12 outputs the result obtained from the estimation unit 13 as the estimated result.

[0022] The estimation unit 13 estimates the effectiveness of advertising measures based on measurement data from the first and second stores, without requiring information on customer participation in the advertising measures. In this example, the estimation unit 13 acquires measurement data from the acquisition unit 11. For example, the estimation unit 13 performs estimation using Fuzzy DiD. Details of the estimation method will be described later.

[0023] The determination unit 14 determines whether the similarity between the first store and the second store satisfies predetermined conditions that define the second store as similar. In this example, the similarity is, for example, an index based on sales information. The similarity is used to select the second store as a comparison target for the first store, which implemented the advertising measures, and for the first store, which did not implement the advertising measures. For example, the determination unit 14 determines whether there are stores that are similar to the first store in terms of sales trends (i.e., trends over time) before the measures were implemented. The determination unit 14 identifies the stores with similar trends as the second store. In this example, the estimation unit 13 estimates the effect of the advertising measures only if it is determined that the second store satisfies the predetermined conditions. This allows the estimation unit 13 to measure the effect of the measures while excluding factors other than whether or not the advertising measures were implemented.

[0024] Let's further explain similarity here. When estimating the effectiveness of advertising measures as described above, selecting a second store that is more similar to the first store tends to improve the accuracy of the estimation results compared to selecting a store that is not similar. To explain using the sales mentioned above as an example, if the first and second stores have shown similar sales trends in the past (for example, recently), it is likely that they will follow a similar sales trend in the future. Therefore, if only the first store implements advertising measures, the comparison of sales between the first and second stores during the period in which the advertising measures were implemented can be approximated as a pure comparison where only the effect of the advertising measures contributes. Based on this perspective, in order to estimate the effectiveness of advertising measures with high accuracy, it is sufficient to identify a store that does not implement advertising measures (an example of the second store) that is similar to the store that implements advertising measures (an example of the first store). Therefore, the information processing device 10 has the following functional elements.

[0025] The trade area identification unit 15 identifies the trade area for the first store. In this example, the trade area is the area around the first store that is the target area for attracting customers, and refers to an area that includes locations related to users who use the first store (i.e., a geographical area). Locations related to users include, for example, the customer's residential area or workplace or other base area. Geographically, the trade area is the area from the first store to a predetermined distance away, or an area defined as including (or not including) the first store. Based on these areas, the trade area identification unit 15 identifies the trade area for the first store. The trade area identification unit 15 also identifies the trade area according to the scale of the advertising campaign.

[0026] The store identification unit 16 identifies a second store that is similar to the first store and belongs to a different area (hereinafter referred to as the "similar area") from the first store's trading area. In this example, the similar area, in a broad sense, is an area with similar characteristics to the area to which the first store belongs. For example, if the first store belongs to an area based on Tokyo, the similar area would be an area with a similar role as a central urban area, such as Osaka Prefecture. In a narrower sense, the similar area includes spatially adjacent areas, for example, an area based on the station next to the nearest station to the first store. The store identification unit 16 also identifies the second store using information about the chain. The store identification unit 16 identifies the second store using information about the type of business. The store identification unit 16 identifies the second store using information about the scale of operations. In this example, the store identification unit 16 identifies the trading area of ​​the first store and then identifies and extracts a similar second store (for example, a store of the same chain, the same type of business, or a company of the same size) that is located in a similar area outside of that trading area.

[0027] Regarding the trading area, for example, when the information processing device 10 identifies comparison stores for effect estimation, it is highly likely that a store in the vicinity and belonging to the same chain, or a store in a similar business format, will be extracted as a second store similar to the first store. However, depending on the content of the measure, if customers benefit from visiting the first store (for example, they can purchase the same product at a lower price at the first store), nearby stores may experience a decrease in customers due to the impact of the measure, or nearby stores, including the first store, may end up competing for customers. In such cases, factors other than whether or not an advertising measure is implemented can reduce the accuracy of the effect estimation. Therefore, in this invention, by adopting the above configuration and identifying a similar second store that does not share a trading area with the first store but is located in a similar area, a purer inter-store comparison focused solely on whether or not an advertising measure is implemented is achieved.

[0028] Figure 3 illustrates the hardware configuration of the information processing device 10. Physically, the information processing device 10 is configured as a computer including a processor 101, memory 102, storage 103, communication device 104, input device (optional), display device (optional), and a bus connecting these. Each of these devices operates on power supplied from a battery (not shown). In the following description, the term "device" can be read as a circuit, device, unit, etc. The hardware configuration of the information processing device 10 may include one or more of the devices shown in Figure 3, or it may be configured without some of the devices. Alternatively, multiple devices with different enclosures may be connected via communication to constitute the information processing device 10.

[0029] Each function in the information processing device 10 is realized by loading predetermined software (programs) onto hardware such as the processor 101 and memory 102, which allows the processor 101 to perform calculations, control communication by the communication device 104, and control at least one of the reading and writing of data in the memory 102 and storage 103.

[0030] The processor 101 controls the entire computer, for example, by running the operating system. The processor 101 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. Also, for example, a baseband signal processing unit or a call processing unit may be implemented by the processor 101.

[0031] The processor 101 reads programs (program code), software modules, data, etc., from at least one of the storage 103 and the communication device 104 into the memory 102 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described later. Functional blocks of the information processing device 10 may be stored in the memory 102 and implemented by control programs that run on the processor 101. Various processes may be executed by one processor 101, or they may be executed simultaneously or sequentially by two or more processors 101. The processor 101 may be implemented by one or more chips. The program may also be transmitted to the information processing device 10 via a telecommunications line.

[0032] Memory 102 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory 102 may also be called a register, cache, main memory, etc. Memory 102 can store executable programs (program code), software modules, etc., for carrying out the method according to this embodiment.

[0033] Storage 103 is a computer-readable recording medium, and may be composed of, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital versatile disc, a Blu-ray (registered trademark) disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 103 may also be referred to as an auxiliary storage device.

[0034] Communication device 104 is hardware (a transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc.

[0035] Each device such as processor 101 and memory 102 is connected by a bus for communicating information. The bus may be configured using a single bus, or may be configured using different buses for each device.

[0036] Information processing device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP: Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), an FPGA (Field Programmable Gate Array), etc., and some or all of each functional block may be realized by the hardware. For example, processor 101 may be implemented using at least one of these hardware.

[0037] In this example, the program stored in the storage 103 includes a program (hereinafter referred to as the "server program") for causing the computer to function as a server in the information processing system 1. When the processor 101 is executing the server program, the processor 101, the memory 102, the storage 103, and the communication device 104 are an example of functional blocks for operating the information processing device 10. The processor 101 is an example of the estimation unit 13, the determination unit 14, the business area identification unit 15, the store identification unit 16, and the control unit 192. At least one of the memory 102 and the storage 103 is an example of the storage unit 191. The communication device 104 is an example of the acquisition unit 11 and the output unit 12.

[0038] Although detailed description is omitted, the store terminal 20 is a computer having a processor, a memory, a storage, a communication device, a display device, an input device, and an output device, specifically, for example, a smartphone, a tablet terminal, or a personal computer. In this example, the program stored in the storage of the store terminal 20 includes a program (hereinafter referred to as the "client program") for causing the computer to function as a client in the information processing system 1.

[0039] The management server 30 is a computer having a processor, a memory, a storage, and a communication device. In this example, the program stored in the storage of the management server 30 includes a program (hereinafter referred to as the "management server program") for causing the computer to function as a management server in the information processing system 1. The configuration of the information processing system 1 has been described so far. Next, the operation of the information processing system 1 will be described.

[0040] 2. Operation 2-1. Method for Estimating the Effect of Measures in the First Store FIG. 4 is a sequence chart illustrating a method for measuring the effect of measures in the first store. Here, an operation example of the method for estimating the effect in the first store where the information processing system 1 implements the target measure (hereinafter referred to as the "target measure") will be described. First, a method for the management server 30 to collect sales data for each store terminal 20 will be described.

[0041] In step S101, the management server 30 requests data from the store terminal 20. This process is performed periodically; for example, sales data requests are made at predetermined intervals for sales over a target period, such as daily, weekly, monthly, or yearly.

[0042] In step S102, the management server 30 acquires sales data from the store terminal 20. In this example, the store terminal 20 has a POS function in a physical store and records and manages accounting information such as the timestamp and payment amount (or the amount of points awarded corresponding to the payment) when a consumer (an example of a user) purchases goods. The store terminal 20 outputs the sales data recorded as POS in response to a request from the management server 30.

[0043] In step S103, the management server 30 records sales data for each store in the database. The database related to the stores will now be described.

[0044] Figure 5 illustrates a store database 1000. In this example, the store database 1000 includes multiple records related to stores and sales data. Each record corresponds to information specific to each store. Each record includes a store ID, store name, sales information, store information, and policy information. The store ID is unique identification information for each store. The store name is a unique registered name for each store, including names such as Bookstore A, Cafe B, Bookstore C, ~Station Front Store, or ~Branch. The sales information is information about sales for each store. In the figure, sales for each store S are simply represented as, for example, Sales E1 for store S21, Sales E2 for store S22, and so on. The specific aggregation process for sales information will be described later. The store information is existing information about the store, including, for example, business type, size, and location. The business type is an item that represents the type or segment of business for each store, including, for example, bookstore, cafe, or convenience store. Scale is an item that represents an indicator related to the scale of operations or physical size, and includes, for example, the number of employees, the number of customers, or the site area. Location is an item that represents the actual location of the store, and includes, for example, the store's address. This store information is compiled in advance for each store and registered in the database of the management server 30. Policy information is information related to a policy, and includes, for example, the policy ID, policy content, and implementation period. The policy ID is ID information assigned to each policy. Policy content is information that represents the content of the advertising policy, and includes the type of policy, such as POP advertising or signage. The implementation period is the period (number of days, weeks, or months, etc.) during which the store implemented the target policy, and includes, for example, period T1 (e.g., one month) that shows the period during which store S21 implemented POP advertising for policy P1 in the store. The implementation period may be the period during which the policy was actually implemented or the period during which it is planned to be implemented. Note that policy information may also be registered by the manager of each store or by a company that operates multiple stores via various terminals. When the management server 30 obtains sales data from the store terminal 20, it records and stores it in the store database 1000.

[0045] Return to Figure 4. Subsequent processing begins when the information processing device 10 receives a request for effect estimation of the target measure. This request may include, for example, instructions for effect estimation of the target measure from the manager of each store, the operating company of multiple stores, or the system administrator. In step S104, the information processing device 10 cooperates with the database of the management server 30 and acquires various data.

[0046] In step S105, the information processing device 10 identifies the first store. In this example, the information processing device 10 identifies the first store (for example, store S21) from the store database 1000 according to the designation of the target measure or target store. Once the first store is identified, the information processing device 10 performs aggregation processing on the sales data of the first store. This processing includes, for example, aggregation processing on past sales trends (for example, a time-change graph showing the trend of sales) including the period during which the target measure is being implemented (for example, period T1). At this time, if the target measure is implemented, for example, from September 1 to September 30, 2024, the information processing device 10 records this one-month (or 30-day) period as period T1 (i.e., one unit) in the database.

[0047] It should be noted that a one-month period can vary; some months, like September, have 30 days, while others have 28 or 31 days. In principle, it is desirable for the information processing device 10 to determine the period before the implementation of the measure (for example, August 2nd to August 31st, 2024) and the period after the implementation of the measure (for example, October 1st to October 30th, 2024) based on the number of days in period T1 (i.e., 30 days). The purpose of setting period T as described above is to unify the temporal factors when making sales comparisons. Therefore, if the actual number of business days, holidays, or business hours differ even with the same number of days, the information processing device 10 may adjust period T0 or period T2, which are other periods, based on period T1.

[0048] In step S106, the information processing device 10 identifies the second store. In this example, the information processing device 10 performs aggregation processing on past sales data for the same period as aggregated at the first store for stores where advertising measures were not implemented (for example, store S23). Specifically, the information processing device 10 generates a graph showing the sales trend of store S23, etc., as described above. The information processing device 10 then identifies and extracts as the second store stores among the stores where advertising measures were not implemented, stores whose sales trend before the implementation of the measures is similar to that of the first store. Now, let's explain the sales trend.

[0049] Figure 6 is an example of sales trend 2000. Figure 6 shows the sales trends for each store, including the first and second stores, i.e., the change in sales over time. In Figure 6, the horizontal axis represents time, and the vertical axis represents sales. In this example, sales trend 2000 is a graph showing the sales for each store over specific consecutive periods. Period T is a period corresponding to each unit (i.e., every month) based on period T1, in which the target measure was implemented. Periods T-5 to T0 represent the periods before the implementation of the measure, and periods T2 to T6 represent the periods after the implementation of the measure. In this example, the length of each period T (T0, T2, T3, etc.) is the same as the length of period T1 (e.g., 30 days). In sales trend 2000, sales for each period T (e.g., in thousands of yen) are plotted. In this example, the sales trends plotted with black circles are the trends for store S21 (an example of the first store). Similarly, the trends plotted with various markers are examples of sales data aggregated for each store S (e.g., store S23, store S25) (only a selection of stores are shown in the figure).

[0050] The information processing device 10 identifies stores that did not implement advertising measures during period T1 as the second store if their sales trend in the period prior to the implementation of the measures (for example, period T0 immediately preceding period T1) is similar to that of the first store. In this example, the plot of store S23 during period T0 shows a sales trend similar to that of the first store, store S21. Therefore, the information processing device 10 can identify store S23 as the second store. On the other hand, the trend of store S25 shows a lower numerical trend compared to the sales of store S21 during the same period. Therefore, the information processing device 10 does not identify such a store as a similar store and excludes it from the comparison stores in the effect estimation. Note that the past trends used to identify similar stores are not limited to period T0, but the results of past trends going back to any point in time may also be used.

[0051] When identifying the second store, the conditions for matching the stores that implemented the advertising campaign and those that did not are basically that the sales data trends before the campaign period are the same, and conditions regarding store size, product range, or customer base do not necessarily have to be the same. Also, although sales amount was used as an example in the explanation, any method can be used to identify the second store. The information processing device 10 may define predetermined conditions (e.g., thresholds) for similarity that include various requirements, and identify stores with a similarity of a certain level or higher as the second store.

[0052] Now, with respect to step S106, we will explain in detail how to identify a second store that is similar to the first store in order to perform a more accurate effect estimation.

[0053] Figure 7 is a flowchart illustrating the method by which the information processing system 1 identifies the second store. This flowchart corresponds to the operation related to the process in step S106 described above. The information processing device 10 starts the following process upon identifying the first store. In step S201, the information processing device 10 acquires the store information of the first store. In this example, the information processing device 10 refers to the store database 1000 and identifies the location of the first store based on the store information.

[0054] In step S202, the information processing device 10 identifies the trading area of ​​the first store (hereinafter referred to as the "first trading area"). In this example, the trading area represents a geographical area, such as on a map. Therefore, the information processing device 10 identifies the first trading area based on location information, such as the address of the first store. The method for identifying the first trading area will now be explained.

[0055] The information processing device 10 works in conjunction with an information collection server (not shown) to identify the first trade area based on the area where the first store's users (an example of a user) reside, the area where they work or otherwise serve as a base, and the area including the address of the first store. In this example, the information collection server is a server for collecting end-user location information. For example, the information collection server collects end-user terminal location information based on base station information from a telecommunications carrier or the like. The information processing device 10 performs analysis (or obtains the analysis results themselves) based on the data acquired from the information collection server to identify the first trade area. The trade area may also be identified based on distance to the target store, topography, or means of transportation. The identified first trade area is then plotted, for example, on a map showing the location of the first store. Here, a map in which the trade area is visually plotted is called a trade area map.

[0056] Figure 8 is an example of a trade area map 3000. Figure 8 is an example of a map that depicts the trade area of ​​the first store according to geographical information. In this example, the trade area map 3000 represents a simplified blank map of a specific area. Trade area C21 is an example of the first trade area of ​​the first store (e.g., store S21). Point X21 is a point indicating the location of store S21. In this example, point X21 is illustrated on the trade area map 3000 using, for example, a simple marker. Point x is a point indicating the location of the end user's residence or base of operations. Regarding the method described above, the information processing device 10 identifies trade area C21 based on an area that includes multiple points x. Alternatively, an area that includes a certain percentage (e.g., 90% or more) of the multiple points x may be identified as trade area C. Note that trade area C may be identified and drawn on the map in any way. For example, the information processing device 10 may identify the first trade area according to the scale of the advertising campaign. In this example, trade area C is defined as the area inside a boundary line (i.e., a circle) at a certain distance from a reference point (point X21, Y23, Z24, etc.). However, the boundary line of trade area C could be a road or a river, for example. Alternatively, the trade areas for stores nationwide could be defined on the map from the outset, for example, by divisions such as city or town names.

[0057] Returning to Figure 7, in step S203, the information processing device 10 identifies stores belonging to similar areas. In this example, similar areas include other areas with similar characteristics to the area where the first store is located, or spatially adjacent areas. The information processing device 10 identifies these similar areas using various methods, such as a histogram distribution that reflects resident attributes. Specifically, the information processing device 10 acquires data in which attributes related to the trade area (for example, age distribution, gender distribution, occupation distribution, or income distribution of residents) are pre-mapped on a map. The information processing device 10 identifies candidate trade areas that are similar to the first trade area. This includes, for example, identifying trade areas centered on points that are a predetermined distance from the center of the first trade area in the east, west, north, and south directions, or the trade area of ​​the next station. Based on the candidate trade areas and the histogram distribution of resident attributes related to those candidate trade areas, the information processing device 10 identifies the trade area (or the area containing that trade area) with resident attributes that are most similar to the first trade area as a similar area. The information processing device 10 identifies stores belonging to similar areas as candidates for the second store (hereinafter referred to as "candidate second store").

[0058] In step S204, the information processing device 10 identifies the trading area of ​​the second store candidate (hereinafter referred to as the "second trading area"). In this example, the information processing device 10 identifies the second trading area using the same method as the method used to identify the first trading area.

[0059] Referring again to Figure 8, the trade area map 3000 represents a map that includes the area where the first store is located and similar areas (for example, up to the area around the next station). In this example, trade areas C23 and C24 are examples of the second trade area. Points Y23 and Z24 represent the respective locations of stores S23 and S24, which have been identified as candidates for the second store. Here, if there is an overlap between the trade area of ​​the first store (for example, trade area C21) and the trade area of ​​the candidate for the second store (for example, trade area C24) in the trade area map 3000, the information processing device 10 excludes the candidate for the second store (for example, store S24) that has that overlapping trade area. This process may also be performed, for example, by excluding candidate for the second store that has an overlapping distribution with the distribution of the first store based on the distribution of store users using the Huff model. In this way, the information processing system 1 can exclude stores from the candidates that may be affected by the measures (or compete for users) with neighboring stores. Furthermore, the Huff model may be used in combination with the concept of market area.

[0060] In step S205, the information processing device 10 identifies a second store based on the trade area map. In this example, if there are multiple similar areas, the information processing device 10 identifies stores belonging to those similar areas that do not overlap with the first trade area as the second store. The information processing device 10 may also calculate the similarity of each identified second store and further narrow down the second stores according to the similarity. In this example, the information processing device 10 may refer to the store database 1000 and calculate the similarity of stores using information such as business type, size (e.g., scale of operations), or chain. The information processing device 10 may identify a second store depending on whether the calculated similarity is above a threshold value. This process may be executed in combination with the process in step S106 described in Figure 4. The information processing device 10 outputs information about the identified second store when performing effect estimation.

[0061] Based on the above, the information processing system 1 can identify the second store. Furthermore, by using information on the trading area, the information processing system 1 can select a second store that is more similar to the first store. This allows the information processing system 1 to calculate the effectiveness of advertising measures with greater accuracy.

[0062] Returning to Figure 4, in step S107, the information processing device 10 performs an effect estimation for the target measure. In this example, the information processing device 10 estimates the effect based on, for example, the sales trend 2000. Here, the information processing device 10 calculates the effect of the advertising measure using a predetermined calculation method known as Fuzzy DiD. For example, the following equation (1) is used to calculate an index that quantifies the effect of the measure (hereinafter referred to as "effectiveness W").

[0063] In this example, the effectiveness level W represents the effectiveness level of the target measure. E " is the difference in sales (for example, in yen) between the first store where the target measure P1 was implemented and the second store where it was not implemented. D " is the intervention rate, a variable that represents the proportion of people who were intervened by the in-store advertisement, that is, the proportion of customers who actually saw the in-store advertisement. The intervention rate is determined, for example, as follows. In one example, the information processing device 10 determines the intervention rate according to the following equation (2) using the user's location information.

[0064] Here, Ns represents the number of consumers who made the target payment. Nv represents the number of visitors identified based on location information. Location information is obtained, for example, from a device owned by the user. As another example, known information such as the percentage of visitors who see in-store advertisements, based on prior market research (or academic research), may be introduced. As long as it is defined in this way, the specific method for identifying the intervention rate is not limited to the above and may be any other method.

[0065] In equation (1), "DID Eis calculated based on a well-known method (or definition formula) known as DID. For example, "DID" is calculated by the following formula (3). E is calculated.

[0066] In this example, "E S1T1 - E S1T0 " represents, for example, the difference between the sales in period T1 and the sales in period T0 of the first store S1 where the target measure P1 was implemented. On the other hand, "E S2T1 - E S2T0 " represents, for example, the difference between the sales in period T1 and the sales in period T0 of the second store S2 where the target measure P1 was not implemented. Furthermore, when calculating "DID D ", in addition to the method described above, it is also possible to apply a mathematical formula similar to formula (3). For example, "DID D " is calculated by the following formula (4).

[0067] In this example, "D S1T1 (or D S1T0 )" is defined as, for example, (the number of seats with in-store advertising) / (the total number of seats) in the case of in-store advertising placed on the tables in a restaurant. On the other hand, regarding "D S2T1 (or D S2T0 )", in the second store that has not introduced in-store advertising at all, every customer who visits the store sits at a table where there is no in-store advertising (that is, it is considered that they do not view the advertisement), so it becomes 0. Thus, "DID D " can be estimated from the content of the in-store advertising measure. Note that either formula (2) or formula (4) may be used for calculating the intervention rate DID D . Which formula to use is determined by, for example, the manager of the information processing device 10.

[0068] Furthermore, the specific method for calculating the effectiveness of the measures is not limited to the methods described above; any method or formula based on Fuzzy DID may be used. In this example, the degree of effectiveness may be the difference in sales between the first and second stores during a different period other than the measure implementation period T1 (for example, the period T2 after the measure period). The different period other than period T1 may be sales data obtained by taking the average of two or more periods. This makes it possible to estimate the effectiveness of the measures after the advertising measures have ended. Next, we will explain the estimated effectiveness of the measures.

[0069] Figure 9 is an example of the policy effectiveness list 4000. Figure 9 is an example of a list summarizing the policy effects calculated based on the formula (1) described above. In this example, the policy effectiveness list 4000 includes multiple records related to policy effects. Each record corresponds to information for each target policy. Each record includes the target policy ID, the first store ID, similar stores (or second stores), the target period, the effectiveness level W, and the similarity score. The target policy ID, the first store ID, and similar stores (items including the second store ID and store name) are identification information managed with identifiers common to the store database 1000. The target period is the period defined in formula (1) as the target for calculating the effectiveness level. The effectiveness level W is calculated in formula (1). The similarity score is a numerical value calculated as an indicator of how similar the second store is to the first store. The higher this value, the closer it can approximate the effect when comparing only the presence or absence of the advertising policy as the intervention element.

[0070] Here, the estimation of effectiveness is corrected using a probability value that indicates the extent to which errors may occur in the calculation result. This probability value may be defined based on so-called domain knowledge (generally, statistical knowledge about how often in-store advertisements are seen), or it may be a value estimated using a predetermined machine learning model. The information processing device 10 may determine whether or not there is an effect using a predetermined threshold for the estimated effectiveness. Alternatively, the information processing device 10 may estimate the effectiveness and determine whether or not there is an effect based on the perspective of statistical significance obtained by hypothesis testing (i.e., whether or not the result is due to chance). Or, the information processing device 10 may estimate the effectiveness and determine whether or not there is an effect using ROI (Return on Investment) that takes into account the cost of implementing the advertising measures.

[0071] As described above, the information processing device 10 can estimate the effectiveness of advertising measures in stores. Based on sales data from the first and second stores, the information processing device 10 can estimate the effectiveness of advertising measures without information on end-user participation in advertising measures. This allows the information processing system 1 to obtain highly reliable estimated effectiveness and evaluate advertising measures while protecting user privacy.

[0072] 3. Modifications The present invention is not limited to the embodiments described above, and various modifications are possible. Several modifications are described below. Two or more of the matters described below may be combined and applied.

[0073] (1) Information Processing System 1 The hardware configuration and network configuration in the information processing system 1 are not limited to those illustrated in the embodiments. The information processing system 1 may have any hardware configuration and network configuration as long as it can realize the required functions. For example, multiple physical devices may cooperate to function as the information processing system 1. For example, at least a part of the functions of the information processing device 10 may be implemented in the management server 30. For example, the management server 30 may have a function of calculating and managing the trade area for each store among the functions related to the information processing device 10.

[0074] (2) Information Processing Device 10 Some of the functions of the information processing device 10 may be implemented on other servers. These servers may be, for example, physical servers or virtual servers (including so-called clouds). Furthermore, the correspondence between functional elements and hardware is not limited to those illustrated in the embodiments. For example, at least some of the functions described in the embodiments as being implemented on the information processing device 10 may be implemented on other devices or systems, or conversely, at least some of the functions described as being implemented on other devices or systems may be implemented on the information processing device 10. In this example, at least some of the information processing device 10 may be implemented on the store terminal 20 or the management server 30. For example, the store terminal 20 may request the information processing device 10 to estimate the effectiveness of an advertising campaign. The management server 30 may also have a function to aggregate and process sales data for the first and second stores in the target campaign.

[0075] (3) Store terminal 20 and management server 30 The store terminal 20 and management server 30 are not limited to those illustrated in the embodiment. The store terminal 20 and management server 30 may perform the above-described processing using any display screen, input device, external device, or various UI. The store terminal 20 may implement any functions necessary for outputting measurement data for each store to the management server 30. In this example, the store terminal 20 may implement a function to calculate aggregated sales data according to the target measure. The management server 30 may implement any functions necessary for recording and managing information related to stores or measures. In this example, the management server 30 may have a function to manage identifiers common to multiple stores, such as chain stores.

[0076] (4) Method for estimating the effectiveness of the measures at the first store The sequence chart shown in Figure 4 is merely an example of operation, and the operation of the information processing system 1 is not limited thereto. Some of the illustrated operations may be changed or omitted, the order may be changed, or new operations may be added. In step S104, the information processing device 10 may automatically perform a process to aggregate sales for each store when the target measures have been completed. In this example, the information processing device 10 may have previously received a request from the system administrator or user to estimate the effectiveness of the target measures. The estimation of the effectiveness of the target measures may be performed at any time. In steps S105 and S106, the information processing device 10 may calculate the sales trend by any method. In this example, elements such as graphs, periods, indicators, or units included in the sales trend may be defined in any way. The second store identified in step S106 is not limited to stores that did not implement advertising measures in period T1, but may also be stores that did not implement advertising measures in a predetermined period prior to period T1. In step S107, the information processing device 10 may perform the effectiveness estimation using any method. In this example, the information processing device 10 may perform estimation using DID, which does not include the intervention rate, instead of Fuzzy DiD, assuming that all users, i.e., all users who visit the store, see the in-store advertising measures. Also, equation (1) may be modified in any way depending on the probability values, etc.

[0077] (5) Method for Identifying the Second Store The flowchart shown in Figure 7 is merely an example of the operation, and the operation of the information processing system 1 is not limited thereto. Some of the illustrated operations may be changed or omitted, the order may be changed, or new operations may be added. In step S202, the first trade area may be identified in any way. In this example, the geographical range of the first trade area may be changed each time depending on the target measure. In step S203, the information processing device 10 may identify similar areas in any way. Similar areas may be set in advance according to the target first store, or they may be changed according to the target measure, etc. In steps S204 and S205, the information processing device 10 may identify the second store in any way. The second store may be identified based on a combination of the trade area map and the similarity of sales trends. Note that the information collection server does not necessarily have to be included in the information processing system 1. From the perspective of protecting privacy, the information processing device 10 may identify the second store without using information about the store's users. Alternatively, the information processing device 10 may perform the above-mentioned processing without partially using methods to identify individual end users.

[0078] (6) Database (Data) The database (or the data itself) of the information processing system 1 shown in Figures 5-6, 8, and 9 is not limited to those illustrated in the embodiment. Any data may be registered in the database in this example. Any data may be recorded in the store database 1000. For example, tags, keywords, labels, or various metadata may be attached to store information or policy information. Any data may be recorded in the database, for example, text, images, graphs, or lists. The sales trend 2000 may be recorded in the database for each target policy. The trade area map 3000 may be data using any type of map. The policy effectiveness list 4000 may be output via the network 9 to various terminals held by the system administrator or users.

[0079] (7) Other programs executed by the processor 101 may be provided by downloading them via a network such as the Internet, or they may be provided recorded on a computer-readable non-temporary recording medium such as a DVD-ROM. Each processor may be, for example, a CPU, an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit).

[0080] The block diagrams used in the description of the above embodiments show functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining software with the one or more of the above devices.

[0081] Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmission unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0082] For example, the information processing device 10 in one embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure.

[0083] Each aspect or embodiment described in this disclosure may be applied to at least one of the following: LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA®, GSM®, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth®, and other appropriate systems, as well as next-generation systems extended based thereon. Furthermore, multiple systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A with 5G).

[0084] The processing procedures, sequences, flowcharts, etc., of each aspect or embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements in an exemplary order and are not limited to the specific order presented.

[0085] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be sent to other devices.

[0086] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0087] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0088] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name. Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0089] The information, signals, etc., described herein may be represented using any of the following different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be referred to throughout the above description, may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof. Terms used herein and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meaning.

[0090] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0091] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0092] Any reference to elements using the designations “First,” “Second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the First and Second elements do not imply that only two elements may be employed, or that the First element must precede the Second element in any way.

[0093] In the above-described configuration of each device, the term "part" may be replaced with "means," "circuit," "device," etc.

[0094] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0095] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0096] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0097] 1... Information processing system, 10... Information processing device, 20, 21, 22, 23... Store terminals, 30... Management server, 9... Network, 11... Acquisition unit, 12... Output unit, 13... Estimation unit, 14... Judgment unit, 15... Trade area identification unit, 16... Store identification unit, 191... Memory unit, 192... Control unit, 101... Processor, 102... Memory, 103... Storage, 104... Communication device, 1000... Store database, 2000... Sales trend, 3000... Trade area map, 4000... Policy effectiveness list

Claims

1. An information processing device comprising: an acquisition unit that acquires measurement data showing the results of customer purchasing behavior at a first store where an in-store advertising measure was implemented, and a second store similar to the first store but where the advertising measure was not implemented; and an output unit that outputs an estimation result that estimates the effect of the advertising measure without information on the customer's participation in the advertising measure, based on the measurement data of the first and second stores.

2. The information processing apparatus according to claim 1, comprising an estimation unit that estimates the effectiveness of the advertising measures based on the measurement data of the first store and the second store without information on the customers' participation in the advertising measures, and the output unit outputs the result obtained from the estimation unit as the estimation result.

3. The information processing apparatus according to claim 2, wherein the estimation unit performs estimation using Fuzzy DiD.

4. The information processing device according to claim 2, comprising a determination unit that determines whether the degree of similarity between the first store and the second store satisfies predetermined conditions defining that the second store is similar, wherein the estimation unit estimates the effect of the advertising measure only when it is determined that the second store satisfies the predetermined conditions.

5. The information processing device according to any one of claims 1 to 4, further comprising: a trade area identification unit for identifying a trade area for the first store; and a store identification unit for identifying a second store that belongs to an area different from the trade area and is similar to the first store.

6. The information processing device according to claim 5, wherein the market area identification unit identifies the market area according to the scale of the advertising measures.

7. The information processing device according to claim 5, wherein the store identification unit identifies the second store using information about the chain.

8. The information processing device according to claim 5, wherein the store identification unit identifies the second store using information about the type of business.

9. The information processing device according to claim 5, wherein the store identification unit identifies the second store using information regarding the scale of operations.

10. An information processing method comprising the steps of: a computer acquiring measurement data showing the results of customer purchasing behavior at a first store where an in-store advertising measure was implemented, and a second store similar to the first store but where the advertising measure was not implemented; and outputting an estimation result that estimates the effectiveness of the advertising measure without information on the customer's participation in the advertising measure, based on the measurement data of the first and second stores.

Images