WO2023033003A1

WO2023033003A1 - Information processing system, information processing method, and program

Info

Publication number: WO2023033003A1
Application number: PCT/JP2022/032662
Authority: WO
Inventors: 智小松▲崎▼
Original assignee: 株式会社マーケティング・フォワード
Priority date: 2021-08-30
Filing date: 2022-08-30
Publication date: 2023-03-09
Also published as: JPWO2023033003A1

Abstract

The present invention addresses the problem of visualizing a result of a marketing analysis based on a flow of people within a prescribed range in which an actual world shop exists, and providing a user with the visualized result.　A data management unit 32 associates people flow data DJ, shop purchase history data DR, online purchase history data DN, public statistical data DC, and research data DL with each other, stores the associated data in a marketing DB 71, and manages the associated data. A data analysis unit 41 acquires data to be analyzed from the data stored in the marketing DB 71, and executes a prescribed analysis on the basis of the data to be analyzed. A visualization information generation unit 441 generates visualization information including the analyzed result through the data analysis unit 41, and presents the visualized information to a user terminal 3. Accordingly, the problem is resolved.

Description

Information processing system, information processing method, and program

The present invention relates to an information processing system, an information processing method, and a program.

Conventionally, there are systems that analyze the marketing of stores that exist in the real world (see Patent Document 1, for example).

JP 2014-048780 A

However, there is a demand for realizing a service that visualizes the results of marketing analysis based on the flow of people in a predetermined range where stores in the real world exist and provides them to users. We are unable to meet this request.

The present invention has been made in view of this situation, and aims to realize a service that visualizes the results of marketing analysis based on the flow of people in a predetermined range where stores exist in the real world and provides them to users. With the goal.

In order to achieve the above object, an information processing system that is one aspect of the present invention includes:
People flow data acquisition means for acquiring, as people flow data, one or more data groups indicating people staying and moving within a predetermined range in the real world on a predetermined date and time;
store purchase history acquisition means for acquiring, as store purchase history data, one or more data groups indicating that a person purchased a predetermined product on a predetermined date and time at a predetermined store in the real world;
data management means for storing and managing the people flow data and the shop purchase history data in association with each other in a predetermined database;
analysis means for executing a predetermined analysis using the flow of people within a certain range including the store, based on the people flow data and the store purchase history data stored in the predetermined database;
Visualization information generating means for generating visualization information including analysis results by the analysis means;
Prepare.

The information processing method and program of one aspect of the present invention are the information processing method and program corresponding to the information processing system of one aspect of the present invention described above.

According to the present invention, it is possible to realize a service that visualizes the results of marketing analysis based on the flow of people in a predetermined range where stores exist in the real world and provides them to users.

1 is an image diagram showing an outline of this service that can be realized by various processes executed by an embodiment of an information processing system of the present invention; FIG. FIG. 2 is an image diagram showing an outline of this service in FIG. 1; 1 is a diagram showing a configuration example of an information processing system applied to the present service of FIGS. 1 and 2, that is, an embodiment of an information processing system of the present invention; FIG. 2 is a diagram showing the configuration of an information processing system including the server of FIG. 1; FIG. 4 is a block diagram showing the hardware configuration of a data server in the information processing system of FIG. 3; FIG. 4 is a functional block diagram showing an overview of the functional configuration of the information processing system of FIG. 3; FIG. FIG. 6 is a functional block diagram showing an example of functional configurations of a data server and an analysis server of FIGS. 2 and 5; FIG. It is a figure which shows an example of correspondence of the various data stored in marketing DB of FIG. 7 is a diagram showing a structural example of store purchase history data stored in the marketing DB of FIG. 6; FIG. FIG. 7 is a diagram showing a data structure example when a national census is adopted as official statistical data stored in the marketing DB of FIG. 6 ; 7 is a diagram showing a structure example of research data stored in the marketing DB of FIG. 6; FIG. 7 is a diagram showing a structural example of net purchase history data stored in the marketing DB of FIG. 6; FIG. 7 is a diagram showing a structure example of people flow data stored in the marketing DB of FIG. 6; FIG. FIG. 7 is a diagram showing a specific example of visualization information indicating a result of analysis using data stored in the marketing DB of FIG. 6; FIG. 14 is a specific example of visualization information showing a result of analysis using the data stored in the marketing DB of FIG. 6, and is a diagram showing an example different from FIG. 13; FIG. 15 is a diagram showing a screen example of visualization information displayed on the user terminal for the specific example of FIG. 14 ; FIG. 16 is a diagram showing a specific example of visualization information indicating a result of analysis using the data stored in the marketing DB of FIG. 6 and showing an example different from FIGS. 13 to 15; FIG. 17 is a diagram showing a screen example of visualization information displayed on a user terminal for the specific example of FIG. 16; FIG. 18 is a diagram showing a specific example of visualization information indicating a result of analysis using the data stored in the marketing DB of FIG. 6 and showing an example different from FIGS. 13 to 17;

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is an image diagram showing an outline of this service that can be realized by various processes executed by one embodiment of the information processing system of the present invention.

As shown in Figure 1, this service is a marketing analysis based on the flow of people (including customers and potential customers) in a predetermined range (for example, a commercial area) where stores in the real world (hereinafter also referred to as "real") exist. It is a marketing service that visualizes the results of the above and provides them to users (for example, people related to stores).
In particular, this service can visualize and present to the user in real time the flow of people in a predetermined range where stores in the real world exist, from beginning to end.

A provider of this service (hereinafter referred to as "service provider") manages a marketing DB 71 shown in FIG. 1 on the cloud in order to provide this service.
Although the details will be described later, the marketing DB 71 is API-linked with the user DB 72, and associates people flow data DJ, store purchase history data DR, online purchase history data DN, official statistical data DC, and research data DL. stored as
The user can access the marketing DB 71 from anywhere using his own terminal (for example, the user terminal 3 in FIG. 3 described later), and uses the analysis results based on the data stored in the marketing DB 71, as shown in FIG. It is possible to realize various things such as
For example, users can pre-understand store customers, prospects, and people flows. That is, the user can specifically grasp the size, age, day of the week, time zone, seasonal fluctuations, etc. of customers or prospective customers in the trade area.
Further, for example, the user can run a one-to-one campaign to encourage customers to visit the store.
Also, for example, the user can cooperate with additional sales promotion tools in the store to increase sales.
In addition, for example, the user can measure the effectiveness of the campaign and listen to the WHY, which will be useful next time. Specifically, for example, the user can grasp what hooked the visitors to the store where the campaign was implemented, and conversely, the reasons why the visitors did not visit.

FIG. 2 is an image diagram showing an overview of this service in FIG.
The diagram on the left side of FIG. 2 shows the positioning of data stored in the marketing DB 71 .
Of the horizontal axis, the left side indicates real (real world) data, and the right side indicates data in the digital world. In the vertical axis, the upper part indicates macro data, and the lower part indicates micro data.
The people flow data DJ is a group of one or more data indicating people staying and moving within a predetermined range (position) in the real world on a predetermined date and time. People flow data DJ is real data and micro data, but since personal information is obtained from the information provider after anonymous data processing, personal information such as name etc. cannot be identified at all. It is That is, the people flow data DJ is collated using identifiers given according to a predetermined rule, not personal information. A server (for example, the data server 1 in FIG. 3) regards them as a group and reads information from a more macroscopic point of view.
The store purchase history data DR is a group of one or more data indicating that a person purchased a predetermined product at a predetermined real (real world) store (mainly a user's store) at a predetermined date and time. The store purchase history data DR is real data, and although it is micro data, personal information is obtained from the information provider after anonymous data processing, so individuals such as names cannot be identified at all. It is made like this. That is, the store purchase history data DR is collated using not personal information but identifiers given according to a predetermined rule. A server (for example, the data server 1 in FIG. 3) regards them as a group and reads information from a more macroscopic point of view.
The online purchase history data DN is a kind of access log data, and is a group of one or more data indicating that a person has purchased a predetermined product at an Internet store. The net purchase history data DN is digital data, and is micro data (data more macro than research data DL).
The official statistical data DC is data indicating the results of statistics on a predetermined target provided by a predetermined agency of the country or locality itself. In this embodiment, data provided by the Statistics Bureau of the Ministry of Internal Affairs and Communications of Japan is adopted as the official statistical data DC. Specifically, for example, data from national census, various surveys on household finances (household survey, household consumption survey, national household structure survey, national consumption survey, national price statistics survey, etc.) are used as an example of official statistical data DC. Employed in embodiments. In addition, survey data such as low and high taxes on corporate activities may also be employed as the official statistical data DC as necessary. The official statistical data DC are real data and macro data.
Research data is data indicating the results of research on a predetermined target provided by a predetermined research agency. An example of research data, which is real data and micro data, is qualitative survey data, specifically, for example, depth interviews. On the other hand, an example of research data, which is digital data and is micro data, is quantitative survey data, specifically, for example, a web panel survey.
It should be noted that online action data (search trends), which is digital data and macro data, can also be stored in the marketing DB 71 as necessary.

Based on the data stored in the marketing DB 71, the service provider (analysis server 2 in FIG. 3 described later) determines the flow of people (customers of the store and (including customer candidates) can be performed.

Here, as shown in FIG. 1, in such an analysis, the people flow data DJ is used to grasp the real time people flow. The store purchase history data DR is used to grasp the purchase history of real stores. The online purchase history data is used to grasp the purchase history of Internet (digital) stores.
Here, in such analysis, single data (raw data) may be used, but in order to perform more public analysis, the following clustering data can be used in this embodiment. That is, the service provider makes full use of statistical analysis using a plurality of source data including people flow data DJ, store purchase history data DR, online purchase history data DN, official statistical data DC, and research data DL. , Service providers independently cluster groups of consumers based on their consumption habits and lifestyle patterns, such as "luxury product purchase type", "holiday spending type", "completely frugal type", etc. , can generate meaningful value data (information). Such "meaningful value data (information)" is clustering data. Clustering data should be easily reproducible. It is obtained as a result of classifying the data into groups for each index. Therefore, such clustering data, as shown on the right side of the official statistical data DC in FIG. Used.
The research data DL is used to understand human psychology.

In summary, the data stored in the marketing DB 71 are, as shown on the left side of FIG. 2, various types of data belonging to on (real), off (digital), macro, and micro. In particular, in conventional marketing analysis, only people flow data provided by one predetermined company was used. On the other hand, the people flow data DJ of this service is obtained by integrating the people flow data of a plurality of companies. Furthermore, in this service, not only the people flow data DJ, but also store purchase history data DR, internet purchase history data DN, etc. are connected with a sense of scale and then analyzed.
That is, this service collects and collates various data belonging to each of on (real), off (digital), macro, and micro stored in the marketing DB 71 and performs analysis. As a result, the user appropriately executes PDCA such as "prediction"->"execution"->"feedback"->"prediction" . . . as shown on the right side of FIG. be able to.
Here, in the "prediction" (near future) of PDCA, the user can easily grasp who, when, how, what to buy, or what the EC and occasion are about his/her own store.
In the "execution" of PDCA, the user can concisely formulate a scenario of action.
PDCA "Feedback" allows the user to receive feedback on whether the execution worked.
Thus, in this service, the appropriate analysis results using the marketing DB 71 are provided to the user. As a result, it is possible to achieve the effect of realizing high-speed PDCA with high accuracy.
In other words, this service is mainly based on people flow data DJ (not just one company, but integrated people flow data provided by multiple companies), and various other data such as store purchase history data DR. It is a service that does not exist at all in the past, such as providing analysis results that match various information. It is precisely because of this service that the above effects can be achieved.

The services shown in FIGS. 1 and 2 can be summarized as follows.
That is, in the past, there was a problem that only a very small number of people could read past data and transfer it to execution. Therefore, in order to solve this problem, this service aims to simplify data utilization.
In addition, in the past, the data necessary for the implementation of measures were scattered all over the world, but there was a problem that there was no way to use the scattered information in an integrated manner. Therefore, in this service, in order to solve the problem, the marketing DB 71 integrates a plurality of data including the people flow data DJ and the store purchase history data DR.
In addition, in the past, data was collected and countermeasures (execution measures for measures) were created from analysis (analysis), but the countermeasures became meaningless because too much time had passed before creation. There was a problem that there were many things to put away. Therefore, in order to solve this problem, this service speeds up the analysis (analysis) and speeds up the execution of countermeasures.
In this way, the present service is a service that enables a bird's-eye view of the data of a predetermined store and is linked to an immediate action.

In other words, the following problems existed in the past when marketing one or more stores.
That is, from the viewpoint of data integration, there are the following first to fourth problems.
The first issue is that there are no companies that utilize people flow data to make decisions. In other words, although there are various companies that handle people flow data, the data volume of each company alone is insufficient for decision making. This is because the people flow data of each company is for expanded estimation.
The second issue is the low possibility of collaboration (horizontal collaboration) between companies that provide people flow data. .
The third problem is that even if people flow data and retail purchase data are interlocked, the sense of scale that is grasped in the past is extremely small.
The fourth issue is the update frequency of people flow data. That is, the conventional update of people flow data is usually done on a monthly basis, and since it is done on a daily basis at the earliest, the fourth problem is that the data cannot be used as data for dealing with current problems for users. .
In addition, as a fifth problem from the user's point of view, there is a problem that, from the first to fourth problems described above, there has been no service that allows users to utilize people flow data.

This service is a service capable of solving the first to fifth problems.
In other words, this service is a service that can build a non-competitive position for a company that has people flow data, and can update the data in units of one hour at the latest.
Therefore, this service integrates the store purchase history data DR and other data based on the people flow data DJ. That is, the service integrates data of various companies.
In addition, this service charges users who use the data and shares the data with the company that provided the data.
In other words, this service is a service that realizes something that could not be achieved by a single company holding conventional data. It is a service that makes it possible to monetize by outputting the amount of data).
From the user's point of view, it is a service that can provide an interface that makes it easy to grasp information visually and take the next step for users who are not good at using data, such as data utilization being a list of numbers and requiring interpretation by themselves. is this service. As an image, a service that presents something like a fish finder to the user and allows them to take action (execute a measure) to drop a string because there are many fish (there are many people around the store). , is this service.

Next, the configuration of the information processing system applied to the present service shown in FIGS. 1 and 2 will be described.
FIG. 3 is a diagram showing a configuration example of an information processing system applied to the present service of FIGS. 1 and 2, that is, an embodiment of the information processing system of the present invention.

In the information processing system shown in FIG. 3, a data server 1, an analysis server 2, and user terminals 3-1 to 3-n (where n is an integer value of 1 or more) are interconnected via a predetermined network such as the Internet. It is configured by being connected to

The data server 1 and the analysis server 2 in this embodiment are servers managed by a service provider.
Each of the user terminals 3-1 to 3-n is composed of a personal computer, a smart phone, a tablet terminal, etc. managed by each of the n users.
In the following description, the user terminals 3-1 to 3-n are collectively referred to as "user terminals 3" when there is no need to distinguish them individually.

FIG. 4 is a block diagram showing the hardware configuration of the data server in the information processing system of FIG.

The data server 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input/output interface 15, an input section 16, and an output section 17. , a storage unit 18 , a communication unit 19 , and a drive 20 .

The CPU 11 executes various processes according to programs recorded in the ROM 12 or programs loaded from the storage unit 18 to the RAM 13 .
The RAM 13 also stores data necessary for the CPU 11 to execute various processes.

The CPU 11, ROM 12 and RAM 13 are interconnected via a bus 14. An input/output interface 15 is also connected to this bus 14 . An input unit 16 , an output unit 17 , a storage unit 18 , a communication unit 19 and a drive 20 are connected to the input/output interface 15 .

The input unit 16 is composed of various hardware lead and the like, and inputs various information.
The output unit 17 is composed of various liquid crystal displays and the like, and outputs various information.
The storage unit 18 is composed of a DRAM (Dynamic Random Access Memory) or the like, and stores various data.
The communication unit 19 controls communication with other devices (for example, the analysis server 2 and user terminals 3-1 to 3-n in FIG. 3) via a network including the Internet.

The drive 20 is provided as required. A removable medium 21 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory is mounted in the drive 20 as appropriate. A program read from the removable medium 21 by the drive 20 is installed in the storage section 18 as necessary. The removable medium 21 can also store various data stored in the storage section 18 in the same manner as the storage section 18 .

Although not shown, the analysis server 2 and the user terminal 3 also have the hardware configuration shown in FIG.

FIG. 5 is a block diagram showing an overview of the functional configuration of the information processing system of FIG.

The data server 1 is managed by the service provider SS and has a function of storing and managing data in the marketing DB 71 .
The data server 1 has an API Gateway 31 to acquire data stored in the marketing DB 71 . The API Gateway 31 has a function of acquiring online purchase history data DN, store purchase history data DR, and research data DL from the user U side (for example, the user DB 72 of the user U) and storing them in the marketing DB 71 . On the other hand, the API Gateway 31 receives people flow data DJ and public statistical data from various other information processing devices not shown in FIG. DC is acquired and stored in marketing DB71.
The data management unit 32 manages data stored in the marketing DB 71 .
The Data I/F API 33 has a function of sending and receiving data between the data server 1 and the analysis server 2 .

The analysis server 2 is managed by the service provider SS and has a function of executing a predetermined analysis based on data from the data server 1 (data stored in the marketing DB 71).
The analysis server 2 has a data analysis section 41 , a data extraction section 42 , an API Gateway 43 and an application section 44 .

The data analysis unit 41 acquires data to be analyzed (data stored in the marketing DB 71) from the data server 1, and performs a predetermined analysis based on the data to be analyzed.
Here, the predetermined analysis includes generation of clustering data as described above. When clustering data is generated by the data analysis unit 41 , it is transmitted to the data server 1 and stored in the marketing DB 71 as appropriate.
The data extraction unit 42 appropriately extracts data for analysis, data indicating analysis results, and the like from the data analysis unit 41 .
The API Gateway 43 has a function of exchanging data between the data analysis section 41 and the data extraction section 42 and the application section 44 .
The application unit 44 communicates with the user terminal 3 (user terminals 3-1 to 3-n in the example of FIG. 5) via a network such as the Internet, and receives a request from the user (for example, a request for analysis execution, request for presentation of analysis results, etc.) and responds to the request.
For example, in the case of a request to perform a predetermined analysis, the application unit 44 instructs the data analysis unit 41 to execute the predetermined analysis via the API Gateway 43 .
For example, in the case of a request to present the result of the predetermined analysis, the application unit 44 acquires the result of the analysis from the data extraction unit 42 via the API Gateway 43 and presents it to the user terminal 3 . Examples of various types of information presented to the user terminal 3 by the application unit 44 will be described later with reference to FIGS. 13 to 18. FIG.

In summary, the data server 1 allows this service to cooperate with the user's core system data (net purchase history data DN, store purchase history data DR, and research data DL). As a result, the analysis result (analysis output) of the analysis server 2, that is, the added value for the user can be enhanced.
In addition, this service can increase the update frequency of data (not only the data in the marketing DB 71 but also the data of the analysis result in the data analysis unit 41, etc.). For example, it is possible to increase the update frequency to the hourly level, which has not been possible in the past. As a result, the user can utilize data in near real time.

FIG. 6 is a functional block diagram showing an example of the functional configuration of the data server and analysis server of FIGS. 2 and 5. FIG.
Since the hardware configuration of the data server 1 and the analysis server 2 can both take the configuration shown in FIG. 4, the data server 1 is denoted by D, and the analysis server 12 is denoted by K, respectively. Specifically, for example, the CPU 11 of the data server 1 is described as CPU11D, while the CPU 11 of the analysis server 2 is described as CPU11K.

As shown in FIG. 6, in the CPU 11D of the data server 1, a people flow data acquisition unit 151, a store purchase history acquisition unit 152, an online purchase history acquisition unit 153, a public statistical data acquisition unit 154, and a research data acquisition unit 154. The unit 155 and the data management unit 32 function.
A marketing DB 71 is provided in the storage unit 18D of the data server 1 .
In the CPU 11K of the analysis server 2, a data analysis section 41, a data extraction section 42, and an application section 44 function.

The people flow data acquisition unit 151 acquires, as people flow data DJ, one or more data groups indicating people staying and moving within a predetermined range in the real world on a predetermined date and time. A specific example of the people flow data DJ will be described later with reference to FIG.
The store purchase history acquisition unit 152 acquires, as store purchase history data DR, one or more data groups indicating that a person purchased a predetermined product on a predetermined date and time at a predetermined store (for example, the user's store) in the real world. . A specific example of the store purchase history data DR will be described later with reference to FIG.
The net purchase history acquisition unit 153 acquires, as net purchase history data DN, one or more data groups indicating that a person has purchased a predetermined product at an Internet store. A specific example of the net purchase history data DN will be described later with reference to FIG.
The official statistical data acquisition unit 154 acquires, as official statistical data DC, data indicating statistical results for a predetermined target provided by a predetermined organization of the country or locality itself. A specific example of the official statistical data DC will be described later with reference to FIG.
The research data acquisition unit 155 acquires research data DL, which is data indicating the results of research on a predetermined target provided by a predetermined research organization. A specific example of the research data DL will be described later with reference to FIG.

Although not shown in FIG. 6, a people flow data acquisition unit 151, a store purchase history acquisition unit 152, an online purchase history acquisition unit 153, a public statistical data acquisition unit 154, a research data acquisition unit 155, The communication unit 19D exhibits functions such as data transmission/reception via the API gateway 31 of FIG.
That is, the API Gateway 31 includes a people flow data acquisition unit 151, a store purchase history acquisition unit 152, an online purchase history acquisition unit 153, a public statistical data acquisition unit 154, a research data acquisition unit 155, and a communication unit in the CPU 11D. 19D.

As described above with reference to FIG. 5, the data management unit 32 associates the people flow data DJ, the store purchase history data DR, the online purchase history data DN, the official statistics data DC, and the research data DL, and stores them in the marketing DB 71. Store and manage.
A specific example of association (linking) of the people flow data DJ, the store purchase history data DR, the online purchase history data DN, the official statistical data DC, and the research data DL will be described later with reference to FIG.

Although not shown in FIG. 6, the data managed by the data management unit 32, that is, the data stored in the marketing DB 71 is transmitted to and from the analysis server 2 via the Data I/F API 33. be given and received.
That is, from the viewpoint of another information processing apparatus using the API, the Data I/F API 33 is understood to be composed of one or more functional blocks not shown in FIG. can.

Of the functional blocks of the analysis server 2, descriptions of the functional blocks described above with reference to FIG. 5 will be omitted.
Although not shown in FIG. 6 for convenience of explanation, the API Gateway 43 of FIG. Demonstrate.

A visualization information generation unit 441 is provided in the application unit 44 .
The visualization information generation unit 441 generates visualization information including the analysis result of the data analysis unit 41 . A specific example of the visualization information will be described later with reference to FIGS. 13 to 18. FIG.

Next, specific examples of data stored in the marketing DB 71 shown in FIG. 6 and the like will be described with reference to FIGS. 7 to 12. FIG.

FIG. 7 is a diagram showing an example of the association of various data stored in the marketing DB of FIG. 6 and the like.

Each data stored in the marketing DB 71 has a plurality of items, and when it has an item with the same content as other data, it is associated with the other data by the item with the same content. ing. Here, items having the same content do not necessarily mean complete matching, but mean that the content is the same to the extent that correspondence is possible. For example, if the first item in one of the data is Prefecture A and the second item in the other data is City B, and City B is included in Prefecture A, then the first item and the second item You may employ|adopt two items as an item of the same content.
For example, in the example of FIG. 7, the people flow data DJ and the store purchase history data DR are associated with each other by the item "datetime" indicating the date and time. Note that the store purchase history data DR of all stores and the people flow data DJ are not associated with each other, but based on the item "long latitude" indicating latitude and longitude, data with overlapping geographical ranges are associated with each other. It is
For example, in the example of FIG. 7, the store purchase history data DR and the net purchase history data DN are associated with each other by the item "order id" indicating the transaction ID.
For example, in the example of FIG. 7, census data is used as the official statistical data DC, and the store purchase history data DR and the official statistical data DC are associated with each other by items indicating addresses.

FIG. 8 shows a structural example of store purchase history data stored in the marketing DB shown in FIG. 6 and the like.
In the example of FIG. 8, the store purchase history data DR includes "sales detail: detailed purchase information", "sales: purchase information", "discount: discount information", "tender: payment information", "customer: customer information", It consists of various kinds of small information such as "item: product", "item category: product category", and "store: store information".
That is, in the marketing DB 71, the store purchase history data DR is formed by linking these small pieces of information with other information in the same content items.
For example, "sales detail: detailed purchase information" and "item: product" both have the item "item_cd: product code", so they are associated with each other.
As described above, with reference to FIG. 7, the people flow data DJ and the store purchase history data DR are associated with each other by the item "datetime" indicating the date and time. More precisely, the people flow data DJ and the store purchase history data DR are associated with each other by associating the people flow data DJ and "sales detail" with the item "datetime" indicating the date and time. It is
For example, "item: product" and "item category: product category" both have the item "item_category_id: product category ID", so they are associated by this item.
Since both "sales detail: purchase detailed information" and "sales: purchase information" have the item "tran_id: transaction ID", they are associated with each other. Similarly, "sales: purchase information", "discount: discount information", "tender: payment information", and "customer: customer information" each have the item "tran_id: transaction ID". Therefore, they are associated with each other by the corresponding item.
As described above, with reference to FIG. 7, the store purchase history data DR and the net purchase history data DN are associated with each other by the item "order id" indicating the transaction ID. More precisely, the online purchase history data DN and "customer: customer information" are associated by the item "order id" indicating the transaction ID, so that the store purchase history data DR and the online purchase history data DN are associated with each other. are associated.
Since both "sales: purchase information" and "store: store information" have the item "store id: store ID", they are associated with each other.
Note that, referring to FIG. 7, census data is adopted as the official statistical data DC, and the store purchase history data DR and the official statistical data DC are associated with each other by items indicating addresses. , said above. More precisely, the store purchase history data DR and the public statistical data DC are associated with each other by the address grasped by the item of "store place: store location" in "store id: store ID".

FIG. 9 shows an example of data structure when a national census is adopted as official statistical data stored in the marketing DB shown in FIG. 6 and the like.
FIG. 10 shows an example structure of research data stored in the marketing DB shown in FIG. 6 and the like.
FIG. 11 shows a structural example of net purchase history data stored in the marketing DB shown in FIG. 6 and the like.
FIG. 12 shows an example of the structure of people flow data stored in the marketing DB shown in FIG. 6 and the like.

Specific examples of data stored in the marketing DB 71 shown in FIG. 6 and the like have been described with reference to FIGS. 7 to 12 .
Next, with reference to FIGS. 13 to 18, specific examples of visualization information indicating results of analysis using data stored in the marketing DB 71 shown in FIG. 6 and the like will be described.

FIG. 13 shows a specific example of visualization information indicating the results of analysis using the data stored in the marketing DB of FIG. 6 and the like.
In the example of FIG. 13, among the data stored in the marketing DB 71 such as FIG. It is an example showing the results of analysis based on online behavior data (search trends).
In the example of FIG. 13, an interface is built in the user terminal 3 that makes it easy for users who are not good at data utilization to visually grasp information and make the next move, such as when data utilization is a list of numbers and you need to interpret it yourself. .
That is, the user terminal 3 functions as something like a fish finder. By visually recognizing the user terminal 3 that functions as a fish finder, the user can take an action (e.g., a campaign or other measures) to drop a string because there are many fish (that is, there are many people in the trade area around the store). can do.
In this way, this service can link necessary information linked to execution with the user terminal 3, which is a digital device. As a result, the user terminal 3 can display only the information required by the user on the dashboard.

FIG. 14 shows a specific example of visualization information indicating the result of analysis using the data stored in the marketing DB such as FIG. 6, which is different from FIG.
FIG. 15 shows a screen example of visualization information displayed on the user terminal for the specific example of FIG.

In the examples of FIGS. 14 and 15, the user is a person belonging to a predetermined store (store manager or salesclerk).
As shown in FIG. 14, in this example, the user has the following problem.
In other words, users have the problem that they want to hold a bargain time sale, but do not know what to do because it is often affected by external factors that cannot be controlled by the company (user side) such as weather, day of the week, and time.
In this service, various data stored in the marketing DB 71 shown in FIG. is displayed on the user terminal 3 .
For example, as shown in FIG. 14, based on the crowd flow data DJ, the user terminal 3 displays visualization information alerting that there are 150% or more of the usual crowd within a 500 m radius from the store (predetermined store). . Specifically, for example, as shown in FIG. 15, data indicating the flow of people (circles displayed in colors indicating the number of people) is displayed on a map including a range of a radius of 500 m centered on the shop (predetermined shop). The user terminal 3 receives visualization information superimposed with data marked with a mark and visualization information of an alert that ``Caution is required. Is displayed.
Further, specifically, as shown in FIG. 15, specific measures such as "utilization of digital sales promotion", "utilization of over-the-counter sales", and "plan for changing shelf display" are given as implementation measures (countermeasures). countermeasures are displayed as visualization information. Here, "utilization of digital sales promotion" means, for example, sending a sales promotion push notification through LINE (registered trademark), a predetermined application, or the like.
Furthermore, regarding the sales of the predetermined store (own store), the current performance and the sales forecast (including the forecast of increase when countermeasures are taken) are displayed as bar graphs for each time period (such visualization information ) is displayed.
By visually recognizing such visualized information, the user can consider appropriate execution measures (countermeasures).
In other words, since there are situations in the field that cannot be deciphered from data, users can choose from specific countermeasures such as "utilization of digital sales promotions", "utilization of over-the-counter sales", and "plans for changes in shelf display". can take whatever action it deems best. The reason why specific countermeasures are displayed as visualization information in this way is that they are more likely to be executed when there are options than when there are no plans (examples of countermeasures).
Here, for example, it is assumed that the user has decided to take a countermeasure of "utilization of store sales promotion". Then, for example, as shown in FIG. 14 (although not shown in FIG. 15), as a result of linking and analyzing the store purchase history data DR and the research data DL, it is possible to sell easily in the same environment in the past. , the X product is automatically picked up as a product with high price elasticity, and visualization information including the optimum price for attracting customers is displayed on the user terminal 3 together with the X product.
By visually recognizing such visualization information, the user can take action measures (countermeasures) of "utilization of store sales promotions" and take special time sale (at the optimum price) of the target product (x product) at the storefront of the specified store. sales) can be implemented to promote store visits. In addition, the user can appropriately view the visualization information indicating the flow of people within a radius of 500 m, and end the bargain time sale when the flow of people decreases according to the data.

FIG. 16 shows a specific example of visualization information indicating the result of analysis using the data stored in the marketing DB of FIG. 6, etc., and shows an example different from FIGS.
FIG. 17 shows a screen example of visualization information displayed on the user terminal for the specific example of FIG.

In the examples of FIGS. 16 and 17, the user is a person involved in the management level of the head office that supervises a plurality of stores.
As shown in FIG. 16, in this example, the user has the following problems.
That is, conventionally, it takes time for the management level to grasp the opportunity loss that occurs at the site (for example, multiple stores including a predetermined store (A store) in the examples of FIGS. 14 and 15). There were cases where the correct information about what was happening was not conveyed. The reason for this is that reporting to management is subject to various filters, such as those in the field and middle management, and it takes time.
That is, we want to obtain accurate information in a short time for the management team to grasp the opportunity loss occurring at the site (for example, multiple stores including a predetermined store (A store) in the example of FIGS. 14 and 15). The user has such a problem.
In this service, various data stored in the marketing DB 71 shown in FIG. is displayed on the user terminal 3 .
For example, as shown in FIG. 16, as a result of linking and analyzing the people flow data DJ and the store purchase history data DR of the previous day, the user terminal 3 can display visualization information that enables the user to grasp the poorly performing stores and the performing stores of the previous day. Is displayed. Furthermore, if there is a large difference between poor performance and good performance among similar stores, visualization information indicating an alert is displayed on the user terminal 3 . That is, an alert is generated from the user terminal 3 . The reason why an alert is generated in this way is that there is a possibility that correct countermeasures have not been taken.
Specifically, for example, as shown in FIG. 17, data indicating the flow of people (number of people) is displayed on a map of a range including four similar stores, that is, stores A, B, C, and D. Visualized information superimposed with circle data displayed in the indicated color) and "Attention required: Opportunity loss of XX million yen due to similar stores on the previous day. Target stores A, C, and D" The alert visualization information is displayed on the user terminal 3 .
Further, specifically, for example, as shown in FIG. 17, as execution measures (countermeasures), concrete measures such as "instructions to countermeasures to applicable stores", "instructions to area managers", and "instructions to sales promotion department" are displayed. countermeasures are displayed as visualization information. Here, the "instruction to the sales promotion department" means, for example, an instruction to the target stores (stores A, C, and D in this case) to immediately implement sales promotion through specific media.
In addition, regarding the amount of opportunity loss, the current performance of similar stores (A store, B store, C store, D store) and the sales forecast (loss calculated from the performance of strong stores when countermeasures were not taken) (including amount) is displayed (as such visualization information) as a bar graph for each time period.
By visually recognizing such visualized information, the user can consider appropriate execution measures (countermeasures).
In other words, since there are situations in the field that cannot be deciphered from data, from among specific countermeasures such as "instructions to the relevant store", "instructions to the area manager", and "instructions to the sales promotion department", The user (management team) can implement the countermeasure that they think is the best. In other words, the user (management team) can select the most appropriate target person from among the relevant store (store manager and salesclerk), area manager, and sales promotion department. Here, it is assumed that "instructions to countermeasures to applicable store", "instructions to area manager", "instructions to sales promotion department", etc. are software buttons. That is, when the user presses a software button indicating the best countermeasure (target person considered optimal), the user can issue an instruction to the terminal of the pressed target person.
In this way, as shown in FIG. 16, the user can give instructions to the site (the target person who is considered to be the most suitable among the relevant store, area manager, and sales promotion department) along with the evidence using the people flow data. Become.

FIG. 18 shows a specific example of visualization information showing the results of analysis using the data stored in the marketing DB such as FIG. 6, and shows an example different from FIGS.

In the example of FIG. 18, the user is a person belonging to a predetermined store (store manager or salesclerk).
The screen in the example of FIG. 18 is displayed on the user terminal 3 as a summary page of the predetermined store.
In the rectangular area in FIG. 18, the area marked "target" indicates the predicted value analyzed by this service, and the area marked "this week" or "this month" is analyzed by this service. The results (predicted values) are shown. In the example of FIG. 18, the descriptive text is displayed for convenience of description, but the numerical summary is actually displayed within the rectangular area. This rectangular area also serves as a software button, and when pressed (tapped), it jumps to another page (not shown) and displays detailed numerical values, graphs, and the like.
The circle area in FIG. 18 is a software button, and when pressed (tapped), it jumps to another page showing the details of the information in the circle area.
The three circle areas on the upper left, that is, the circle areas with "new product information", "sales priority items", and "campaign content" are the entire company (own company) that supervises multiple stores including predetermined stores. A software button that jumps to another page showing information about
When the circular area labeled "Movement of people around the store" is pressed (tapped), data indicating the flow of people (in colors indicating the number of people) is displayed on the map including the store (predetermined store) This is a software button for jumping to another page that displays the visualization information (see the example in FIG. 15) superimposed with the displayed circle data). By visually recognizing the visualized information, the user can grasp more detailed movements of people around the predetermined store (own store).

Although not shown in FIG. 18, if the user is an area manager, the summary page will have the same layout as in FIG. It becomes a level, the numerical value is the sum of the stores in charge, and the one that allows you to see the individual summary of each store in charge is adopted. Similarly, higher-level VPs and executives are presented with a condensed summary page.
In this case, the analysis is performed by classifying the stores into excellent stores, acceptable stores, stores that still have to work a little harder, unprofitable stores, etc., and the analysis results are also displayed on the summary page or the like. Furthermore, if there is data, it may be combined with a tableau or the like, and may include visualization information for later analysis.

Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the range that can achieve the object of the present invention are included in the present invention. is.

For example, in the above example, the data stored in the marketing DB 71 are shown in FIG. 1, but are not particularly limited to the above embodiment as long as at least the people flow data DJ and store purchase history data DR are included. For example, although not shown in FIG. 1, the online behavior data (search trends) in FIG. 2 may be stored in the marketing DB 71. FIG.

Also, the configuration of the information processing system shown in FIG. 3 is merely an example for achieving the object of the present invention, and is not particularly limited.
For example, in the above-described embodiment, two servers, the data server 1 and the analysis server 2, are used, but the present invention is not particularly limited to this. May be distributed across servers.

Also, each hardware configuration shown in FIG. 4 is merely an example for achieving the object of the present invention, and is not particularly limited.

Also, the functional block diagrams shown in FIGS. 5 and 6 are merely examples and are not particularly limited. That is, it is sufficient if the information processing system is provided with a function capable of executing the above-described series of processes as a whole, and what kind of functional blocks are used to realize this function is not particularly limited to the example of FIG. .

Also, the locations of the functional blocks are not limited to those shown in FIGS. 5 and 6, and may be arbitrary. For example, at least part of the functional blocks on the data server 1 side may be provided in the analysis server 2 or other information processing device, or vice versa.
One functional block may be composed of hardware alone, or may be composed of a combination of software alone.

When the processing of each functional block is to be executed by software, a program that constitutes the software is installed in a computer or the like from a network or recording medium.
The computer may be a computer built into dedicated hardware. Also, the computer may be a computer capable of executing various functions by installing various programs, such as a server, a general-purpose smart phone, or a personal computer.

A recording medium containing such a program not only consists of a removable medium that is distributed separately from the device main body in order to provide each user with the program, but is also preinstalled in the device main body and distributed to each user. It consists of a provided recording medium, etc.

In this specification, the steps of writing a program recorded on a recording medium are not only processes performed chronologically in that order, but also processes performed in parallel or individually. It also includes the processing to be executed.
Further, in this specification, the term "system" means an overall device composed of a plurality of devices, a plurality of means, or the like.

To summarize the above, the information processing system to which the present invention is applied is sufficient if it has the following configuration, and can take various embodiments.
That is, an information processing system to which the present invention is applied (for example, an information processing system including the data server 1 and the analysis server 2 in FIG. 3) is
People flow data acquisition means (for example, FIG. 6) that acquires one or more data groups indicating people staying and moving within a predetermined range in the real world on a predetermined date and time as people flow data (for example, people flow data DJ in FIGS. 1, 2, and 12). people flow data acquisition unit 151),
A store that acquires, as store purchase history data (for example, store purchase history data DR in FIGS. 1, 2, and 8), one or more data groups indicating that a person has purchased a predetermined product on a predetermined date and time at a predetermined store in the real world. purchase history acquisition means (for example, store purchase history acquisition unit 132 in FIG. 6);
Data management means (for example, FIG. 5 and FIG. 6) stores and manages the people flow data and the store purchase history data (for example, see FIG. 7) in a predetermined database (for example, marketing DB 71 in FIGS. 1 and 6) in association with each other. a data management unit 32);
Analysis means (for example, FIGS. 5 and 6) for executing a predetermined analysis using the flow of people within a certain range including the store, based on the people flow data and the store purchase history data stored in the predetermined database. analysis unit 41),
Visualization information generating means (for example, the visualization information generating unit 441 in FIG. 6) for generating visualization information (for example, the visualization information in FIGS. 13 to 18) including the analysis result by the analysis means;
Prepare.

Net purchase history acquisition means (for example, net purchase history data DN in FIGS. 1, 2, and 11) for acquiring one or more data groups indicating that a person has purchased a predetermined product at an Internet store as net purchase history data (for example, net purchase history data DN in FIGS. For example, the network purchase history acquisition unit 153) of FIG. 6 is further provided,
The data management means manages the online purchase history data in association with the people flow data and the store purchase history data,
The analysis means executes the predetermined analysis based on the online purchase history data in addition to the people flow data and the store purchase history data.
be able to.

Official statistics obtained as official statistical data (for example, official statistical data DC in Figures 1, 2, and 9) that indicate the results of statistics provided by a predetermined organization of the national or local government itself. Data acquisition means (for example, the official statistical data acquisition unit 154 in FIG. 6) is further provided,
The data management means manages the public statistical data in association with the people flow data and the shop purchase history data,
The analysis means executes the predetermined analysis based on the public statistical index clustering data in addition to the people flow data and the store purchase history data.
be able to.

Research data acquisition means (for example, the research in FIG. 6) that acquires data indicating the results of research on a predetermined target provided by a predetermined research organization as research data (for example, research data DL in FIGS. 1, 2, and 10). A data acquisition unit 155) is further provided,
The data management means manages the research data in association with the people flow data and the shop purchase history data,
The analysis means executes the predetermined analysis based on the public statistical index clustering data in addition to the people flow data and the store purchase history data.
be able to.

1: data server, 2: analysis server, 3, 3-1, 3-n: user terminal, 11, 11D, 11K: CPU, 12: ROM, 13: RAM, 14: bus, 15: input/output interface, 16 : Input unit, 17: Output unit, 18, 18D: Storage unit, 19, 19D, 19K: Communication unit, 20: Drive, 21: Removable media, 31: API Gateway, 32: Data management unit, 33: Data I/ F API, 41: data analysis unit, 42: data extraction unit, 43: API gateway, 44: application unit, 71: marketing DB, 72: user DB, 151: people flow data acquisition unit, 152: store purchase history acquisition unit, 153: Internet purchase history acquisition unit 154: Public statistical data acquisition unit 155: Research data acquisition unit DJ: People flow data DR: Store purchase history data DN: Internet purchase history data DC: Official statistical data DL: research data

Claims

People flow data acquisition means for acquiring, as people flow data, one or more data groups indicating people staying and moving within a predetermined range in the real world on a predetermined date and time;
store purchase history acquisition means for acquiring, as store purchase history data, one or more data groups indicating that a person purchased a predetermined product on a predetermined date and time at a predetermined store in the real world;
data management means for storing and managing the people flow data and the shop purchase history data in association with each other in a predetermined database;
analysis means for executing a predetermined analysis using the flow of people within a certain range including the store, based on the people flow data and the store purchase history data stored in the predetermined database;
Visualization information generating means for generating visualization information including analysis results by the analysis means;
An information processing system comprising
further comprising an internet purchase history acquiring means for acquiring, as internet purchase history data, one or more data groups indicating that a person has purchased a predetermined product at an internet store;
The data management means manages the online purchase history data in association with the people flow data and the store purchase history data,
The analysis means executes the predetermined analysis based on the online purchase history data in addition to the people flow data and the store purchase history data.
The information processing system according to claim 1.
Further comprising an official statistical data acquisition means for acquiring, as official statistical data, data indicating statistical results for a predetermined target provided by a predetermined institution of the national or local government,
The data management means manages the public statistical data in association with the people flow data and the shop purchase history data,
The analysis means executes the predetermined analysis based on the public statistical index clustering data in addition to the people flow data and the store purchase history data.
The information processing system according to claim 1.
further comprising research data acquisition means for acquiring, as research data, data indicating the results of research on a predetermined target provided by a predetermined research organization;
The data management means manages the research data in association with the people flow data and the shop purchase history data,
The analysis means executes the predetermined analysis based on the public statistical index clustering data in addition to the people flow data and the store purchase history data.
The information processing system according to claim 1.
In the information processing method executed by the information processing system,
a people flow data obtaining step of obtaining, as people flow data, one or more data groups indicating people staying and moving within a predetermined range in the real world on a predetermined date and time;
a store purchase history acquisition step of acquiring, as store purchase history data, one or more data groups indicating that a person purchased a predetermined product on a predetermined date and time at a predetermined store in the real world;
a data management step of correlating said people flow data with said shop purchase history data and storing and managing them in a predetermined database;
an analysis step of performing a predetermined analysis using the flow of people within a certain range including the store, based on the people flow data and the store purchase history data stored in the predetermined database;
a visualization information generating step of generating visualization information including the analysis result by the analysis means;
Information processing method including.
to the computer,
a people flow data obtaining step of obtaining, as people flow data, one or more data groups indicating people staying and moving within a predetermined range in the real world on a predetermined date and time;
a store purchase history acquisition step of acquiring, as store purchase history data, one or more data groups indicating that a person purchased a predetermined product on a predetermined date and time at a predetermined store in the real world;
a data management step of correlating said people flow data with said shop purchase history data and storing and managing them in a predetermined database;
an analysis step of performing a predetermined analysis using the flow of people within a certain range including the store, based on the people flow data and the store purchase history data stored in the predetermined database;
a visualization information generating step of generating visualization information including the analysis result by the analysis means;
A program that executes control processing including