Behavior prediction device

The behavior prediction device predicts purchasing actions in destination areas by analyzing population and weather data, enabling effective inventory management and customer attraction, thus reducing waste and increasing sales.

JP7587053B2Active Publication Date: 2024-11-19NTT DOCOMO INC
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2023550455
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2021-09-30
Filing Date
2022-08-22
Publication Date
2024-11-19
Estimated Expiration
2042-08-22

AI Technical Summary

Technical Problem

Existing retail store management systems cannot predict the number of people who will purchase products in a destination area, limiting the ability to effectively manage inventory and customer attraction.

Method used

A behavior prediction device that calculates action and movement probabilities using population distribution data, weather data, and historical purchase data to predict the number of people likely to engage in purchasing actions in specific destination areas, and guides customer referrals based on these predictions.

Benefits of technology

Enhances inventory management by reducing food waste and increasing sales volume through targeted customer referrals, thereby improving store efficiency and profitability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007587053000001
    Figure 0007587053000001
  • Figure 0007587053000002
    Figure 0007587053000002
  • Figure 0007587053000003
    Figure 0007587053000003
Patent Text Reader

Abstract

The present invention addresses the problem of predicting the population involved in behaviors at a destination area. This purchase prediction device 1 comprises: a storage unit 10 for storing a prediction coefficient representing the probability that people present in a prescribed area will be involved in purchases, and an average moving population percentage representing the probability that people present in the prescribed area will move to a destination area that is a destination for movement; an acquisition unit 11 for acquiring population distribution data relating to per-area population; and a prediction unit 13 for predicting the population involved in purchases in each destination area on the basis of population distribution data acquired by the acquisition unit 11 and the prediction coefficient and average moving population percentage stored by the storage unit 10. The prediction coefficient represents the probability that people present in a prescribed area at a prescribed time will be involved in purchases, and the average moving population percentage represents the probability that people present in the prescribed area at the prescribed time will move to the destination area. The population distribution data can furthermore relate to per-time population.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] One aspect of the present disclosure relates to a behavior prediction device that predicts a population involved in a behavior. [Background technology]

[0002] The following Patent Document 1 discloses a retail store management system that predicts sales volume for each product from a prediction of the number of customers based on causal information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2002-24350 A Summary of the Invention [Problem to be solved by the invention]

[0004] The retail store management system described above cannot predict the number of people who will purchase products among those in a destination area, which is the area to which people will move. Therefore, it is desirable to predict the population involved in actions (e.g., purchasing products) in the destination area. [Means for solving the problem]

[0005] A behavior prediction device according to one aspect of the present disclosure includes a storage unit that stores a behavior probability, which is the probability that a person in a specified area will engage in a behavior, and a movement probability, which is the probability that a person in the specified area will move to a destination area, which is a destination area; an acquisition unit that acquires population distribution data regarding the population for each area; and a prediction unit that predicts the population involved in the behavior for each destination area based on the population distribution data acquired by the acquisition unit and the behavior probability and movement probability stored by the storage unit.

[0006] In this aspect, the population involved in the behavior for each destination area is predicted based on the population distribution data, the behavior probability, and the movement probability. That is, the population involved in the behavior in the destination area can be predicted. Effect of the Invention

[0007] According to one aspect of the present disclosure, it is possible to predict the population involved in activities in a destination area. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram illustrating a usage image of a purchase prediction device according to an embodiment. [Diagram 2] FIG. 1 is a schematic diagram illustrating an example of an effect of a purchase prediction device according to an embodiment. [Diagram 3] 1 is a diagram illustrating an example of a system configuration of a purchase prediction system including a purchase prediction device according to an embodiment. [Figure 4] FIG. 13 is a diagram illustrating an example of a table of population distribution data. [Diagram 5] FIG. 13 is a diagram illustrating an example of a table of moving population data. [Figure 6] FIG. 13 is a diagram illustrating an example of a table of weather data. [Figure 7] FIG. 13 is a diagram illustrating an example of a table of purchase quantity data. [Figure 8] FIG. 2 is a diagram illustrating an example of a functional configuration of a purchase prediction device according to an embodiment. [Figure 9] FIG. 13 is a diagram illustrating an example of learning data. [Figure 10] FIG. 13 is a diagram showing an example (part 1) of a table of population distribution data including prediction coefficients. [Figure 11] FIG. 13 is a diagram showing an example (part 2) of a table of population distribution data including prediction coefficients. [Figure 12] FIG. 13 is a diagram illustrating an example of a prediction of the number of purchases using a prediction model. [Figure 13] FIG. 13 is a diagram showing an example of a table of migrant population data including an average migrant population and an average migrant population ratio. [Figure 14]FIG. 13 is a diagram showing an example of a table of population distribution data used to calculate a purchase probability. [Figure 15] FIG. 13 is a diagram illustrating an example of a table of purchasing population data. [Figure 16] FIG. 13 is a diagram showing an example of a table of purchasing population data including purchase probability. [Figure 17] FIG. 13 is a diagram showing an example of customer referral. [Figure 18] 1 is a flowchart (part 1) illustrating an example of a process executed by the purchase prediction system. [Figure 19] 11 is a flowchart (part 2) illustrating an example of the process executed by the purchase prediction system. [Figure 20] 11 is a flowchart illustrating an example of a process executed by the purchase prediction device according to the embodiment. [Figure 21] FIG. 2 is a diagram illustrating an example of a hardware configuration of a computer used in the purchase prediction device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the embodiments of the present disclosure will be described in detail with reference to the drawings. In the description of the drawings, the same elements are given the same reference numerals, and duplicated descriptions will be omitted. In addition, the embodiments of the present disclosure in the following description are specific examples of the present invention, and the present invention is not limited to these embodiments unless otherwise specified to limit the present invention.

[0010] 1 is a schematic diagram (part 1) showing a usage image of a purchase prediction device 1 (behavior prediction device) according to an embodiment. The purchase prediction device 1 is a server device that predicts the number of purchases of products (e.g., food) or services of a store (retailer) by customers, extracts segments (gender, age, place of residence) with a high purchase probability from among customers, and encourages customers to visit the store and purchase products or services based on the predicted number of purchases and the extracted customer segments.

[0011] Hereinafter, in this embodiment, "products or services" will be collectively referred to as "products." Also, in this embodiment, for convenience of explanation, processing related to a specific (already determined) store (simply referred to as "store" in this embodiment) will be explained, rather than an arbitrary store. For example, by appropriately using a store ID, which is identification information of the store, during processing, it is possible to extend the processing to any store.

[0012] As shown in FIG. 1, the purchase prediction device 1 predicts the number of purchases of customers based on the population distribution of the day, the weather of the day, and population movement statistics, which are statistics on the movement of people. Next, the purchase prediction device 1 extracts a layer with a high probability of purchase. More specifically, the purchase prediction device 1 extracts (picks up) meshes (areas) and segments that are highly correlated with the future purchase numbers used for the prediction. For example, assume that "16:00, mesh number XX, female, 40s" is extracted. Next, the purchase prediction device 1 judges whether or not to send customers based on the predicted number of purchases. More specifically, it automatically judges whether or not to send customers based on the customer sending conditions set in advance by the store manager (responsible person). If it is judged that customers should be sent, a geofence is set (stretched) around the meshes and segments with high correlation. When a customer checks in to the set geofence, the purchase prediction device 1 distributes information to the customer and sends the customer to the store. For example, a coupon is distributed to a female in her 40s who enters the area of ​​mesh number XX at 16:00, encouraging her to visit and make a purchase.

[0013] FIG. 2 is a schematic diagram showing an example of the effect of the purchase prediction device 1 according to the embodiment. The left side of FIG. 2 is a graph showing the purchase amount of customers and the (amount of) inventory in the store as of 13:00. The upper right side of FIG. 2 is a graph showing the purchase amount and inventory as of 20:00 (on the same day) when the purchase prediction device 1 sends customers. As shown in the graph, the purchase amount increases due to the customer sending effect of the purchase prediction device 1, and the inventory decreases. If the product is food, food waste can be reduced by the amount of inventory decreased. On the other hand, the lower right side of FIG. 2 is a graph showing the purchase amount and inventory as of 20:00 (on the same day) when the purchase prediction device 1 does not send customers. As shown in the graph, since there is no customer sending effect, the purchase amount does not increase and inventory (food waste) occurs.

[0014] In general, the amount of food waste from domestic businesses (restaurants, supermarkets, etc.) is about 3.52 million tons, which is an opportunity loss. Because discarded food is incinerated at waste disposal plants, a large amount of food waste leads to an increase in carbon dioxide emissions, which is an issue. For example, the purchase prediction device 1 can reduce food waste by sending customers to stores on days when the probability of food waste is high.

[0015] Fig. 3 is a diagram showing an example of a system configuration of a purchase prediction system 8 including a purchase prediction device 1 according to an embodiment. As shown in Fig. 1, the purchase prediction system 8 includes the purchase prediction device 1, a population distribution data acquisition device 2, a moving population data acquisition device 3, an external data acquisition device 4, a purchase inventory management device 5, a store manager device 6, and a customer smartphone 7. The purchase prediction device 1, the population distribution data acquisition device 2, the moving population data acquisition device 3, the external data acquisition device 4, the purchase inventory management device 5, the store manager device 6, and the customer smartphone 7 are each communicatively connected to one another via a network such as the Internet, and can transmit and receive information to and from one another.

[0016] The population distribution data acquiring device 2 is a server device that acquires population distribution data on the population distribution around a store (nearby, surrounding, nearby, surrounding, nearby, around, within a predetermined distance) and transmits it to the purchase prediction device 1. Information about the store may be stored in advance in the population distribution data acquiring device 2, or may be acquired by being transmitted in advance from the purchase prediction device 1. Information about the target store in this embodiment may be stored in advance in various devices, not limited to the population distribution data acquiring device 2, or may be acquired by being transmitted in advance from the purchase prediction device 1, etc.

[0017] Fig. 4 is a diagram showing an example of a table of population distribution data. As shown in Fig. 4, in the population distribution data, a date and time, a mesh indicating a position, range or area, a person's gender, a person's age, a person's place of residence, and a population, which is the number of people of that gender, age and place of residence present in that mesh on that date and time, are associated with each other. The population distribution data shown in Fig. 4 shows, for example, population distribution data around a store. In this case, the store is located around mesh X and mesh Y shown in Fig. 4 (including within mesh X or mesh Y).

[0018] The population distribution data acquiring device 2 may acquire population distribution data based on terminal information collected from a mobile terminal that is carried by each person and capable of mobile communication and capable of measuring its own position using a Global Positioning System (GPS). In collecting the terminal information, an existing technology such as Mobile Spatial Statistics (registered trademark) provided by NTT Docomo, Inc. may be used. The population distribution data acquiring device 2 may acquire population distribution data in real time and transmit it to the purchase prediction device 1.

[0019] The movement population data acquisition device 3 is a server device that acquires movement population data related to movement population statistics and transmits it to the purchase prediction device 1. The movement population data acquisition device 3 may acquire the movement population data based on the population distribution data acquired by the population distribution data acquisition device 2, for example. Although details will be described later, the movement population data includes a source mesh (sometimes simply referred to as a "mesh") that is a mesh from which a person moves, and a destination mesh (sometimes referred to as a "movement mesh") that is a mesh to which a person moves. The movement population data acquisition device 3 acquires movement population data in which the source mesh is the vicinity of a store, and transmits it to the purchase prediction device 1. The purchase prediction device 1 may acquire the movement population data once a month and transmit it to the purchase prediction device 1.

[0020] FIG. 5 is a diagram showing an example of a table of moving population data. As shown in FIG. 5, in the moving population data, the date when a person started moving, the time when the person started moving, the mesh from which the person moved, the moving time when the person reached the moving mesh which is the moving destination mesh, the moving mesh, the gender of the person, the age of the person, the place of residence of the person, and the moving population which is the number of people of the gender, age and place of residence who started moving from the mesh on the date and time and arrived at the moving mesh at the moving time are associated with each other. The moving population data shown in FIG. 5 shows, for example, moving population data around a store. In this case, the store is located around mesh X and mesh Y shown in FIG. 5 (including within mesh X or mesh Y). The moving population data is used from the viewpoint of which mesh a person will go to, with the mesh (within a predetermined range around the store) to be included in the prediction as the moving source.

[0021] The external data acquisition device 4 is a server device that acquires external data, which is data acquired from an external device, etc., and transmits the data to the purchase prediction device 1. The external data includes weather data related to the weather around the store. The external data acquisition device 4 may acquire each piece of external data from various other devices via a network, for example. The external data acquisition device 4 may acquire the external data in real time and transmit the data to the purchase prediction device 1.

[0022] Fig. 6 is a diagram showing an example of a weather data table. As shown in Fig. 6, in the weather data, a date and time correspond to (information indicating) the weather at that date and time. The weather data shown in Fig. 6 indicates, for example, weather data for the vicinity of a store. When the weather data is data regarding future weather, the weather forecast (predicted weather) is used as the weather, rather than the actual weather.

[0023] The purchase inventory management device 5 is a server device that acquires purchase quantity data regarding the number of products purchased by customers in the store and inventory quantity data regarding the number of products in stock in the store, and transmits them to the purchase prediction device 1. The purchase inventory management device 5 is, for example, a Point of Sale (POS) system. The purchase inventory management device 5 may acquire purchase quantity data in real time and transmit it to the purchase prediction device 1, or may acquire inventory quantity data in real time and transmit it to the purchase prediction device 1.

[0024] Fig. 7 is a diagram showing an example table of purchase quantity data. As shown in Fig. 7, in the purchase quantity data, a date and time, a product ID which is identification information of a product, and the number of products sold at the date and time indicated by the product ID are associated with each other. The purchase quantity data shown in Fig. 7 indicates, for example, purchase quantity data of a store.

[0025] Although not shown, the stock quantity data corresponds, for example, to a time, a product ID, the expiration date of a product (e.g., food) indicated by the product ID, and the stock quantity of the product indicated by the product ID at that time.

[0026] The store manager device 6 is a server device that acquires customer sending condition data related to customer sending conditions, which are conditions for sending customers, and distribution information, which is information to be distributed to customers, and transmits them to the purchase prediction device 1. The store manager device 6 is a device operated by a store manager. The store manager inputs the customer sending condition data and the distribution information to the purchase prediction device 1. The store manager device 6 may be realized as a Web application.

[0027] Although not shown in the figure, the customer sending condition data corresponds, for example, to a time, a product ID, an inventory quantity, a predicted purchase quantity which is a purchase quantity predicted (by the prediction unit 13 described below), and the expiration date of the product indicated by the product ID.

[0028] Although not shown, the distribution information includes, for example, a product ID and information (such as an advertisement) about the product indicated by the product ID, which are associated with each other.

[0029] A customer smartphone 7 is a smartphone carried by (one or more) customers of a store. In this embodiment, multiple customers are collectively referred to as customers, and multiple customer smartphones 7 are collectively referred to as customer smartphones 7. The customer smartphone 7 is equipped with a GPS and can measure the position of its own terminal. In order to determine check-in to a geofence, the customer smartphone 7 transmits position attribute information including the position information of its own terminal and customer attribute information to the purchase prediction device 1. The customer smartphone 7 receives distribution information transmitted from the purchase prediction device 1 to direct customers, and displays it on the customer smartphone 7.

[0030] Although the location attribute information is not shown in the figure, for example, a customer ID, which is the customer's identification information, a time, the position of the customer smartphone 7 at that time (latitude and longitude, etc.), the gender of the customer indicated by the customer ID, the age of the customer indicated by the customer ID, and the place of residence of the customer indicated by the customer ID correspond to each other.

[0031] In the above explanation, it is assumed that the data required for the processing of the purchase prediction device 1 is prepared in advance on each of the devices, the population distribution data acquisition device 2, the population movement data acquisition device 3, the external data acquisition device 4, the purchase inventory management device 5, the store manager device 6, and the customer smartphone 7, but this is not limited to the above. For example, each of the devices, the population distribution data acquisition device 2, the population movement data acquisition device 3, the external data acquisition device 4, the purchase inventory management device 5, the store manager device 6, and the customer smartphone 7, may prepare the data required for the processing of the purchase prediction device 1 by, for example, transmitting raw data of all stores, rather than data related to a specific store, to the purchase prediction device 1, and extracting data related to the store from the raw data on the purchase prediction device 1 side.

[0032] Fig. 8 is a diagram showing an example of a functional configuration of the purchase prediction device 1 according to the embodiment. As shown in Fig. 8, the purchase prediction device 1 includes a storage unit 10 (storage unit), an acquisition unit 11 (acquisition unit), a learning unit 12, a prediction unit 13 (prediction unit), a customer sending unit 14 (guiding unit), a determination unit 15 (guiding unit), and a distribution unit 16 (guiding unit).

[0033] Each functional block of the purchase prediction device 1 is assumed to function within the purchase prediction device 1, but is not limited to this. For example, some of the functional blocks of the purchase prediction device 1 may function in a computer device different from the purchase prediction device 1 and connected to the purchase prediction device 1 through a network, while appropriately transmitting and receiving information to and from the purchase prediction device 1. For example, the customer sending unit 14 may be realized by a customer sending determination device, which is a different device. The determination unit 15 may be realized by a check-in determination device, which is a different device. The distribution unit 16 may be realized by an information distribution device, which is a different device. In addition, some functional blocks of the purchase prediction device 1 may be omitted, multiple functional blocks may be integrated into one functional block, or one functional block may be decomposed into multiple functional blocks.

[0034] Hereinafter, each function of the purchase prediction device 1 shown in FIG. 8 will be described.

[0035] The storage unit 10 stores any information used in calculations in the purchase prediction device 1 and the results of calculations in the purchase prediction device 1. The information stored by the storage unit 10 may be referred to by each function of the purchase prediction device 1 as appropriate.

[0036] The storage unit 10 stores a prediction coefficient (behavior probability) which is the probability that a person in a specific mesh (area) will make a purchase (behavior), and an average moving population ratio (movement probability) which is the probability that a person in a specific mesh will move to a moving mesh (destination area) which is a destination mesh. The behavior may be the purchase of a product or service at a store. In this embodiment, a purchase is assumed as an example of a behavior, but the present invention is not limited to this. The prediction coefficient and the average moving population ratio will be described in detail later.

[0037] The acquisition unit 11 acquires information from another device via a network or from its own device (the purchase prediction device 1). The acquisition unit 11 may cause the acquired information to be stored in the storage unit 10, or may output the information to another functional block.

[0038] The acquisition unit 11 acquires population distribution data on the population for each mesh (area) from the population distribution data acquisition device 2 or the like. The population in the population distribution data may further be for each time. That is, the acquisition unit 11 acquires population distribution data on the population for each time and mesh. The population in the population distribution data may further be for each person's attribute. That is, the acquisition unit 11 may acquire population distribution data on the population for each mesh and person's attribute, or may acquire population distribution data on the population for each time, mesh, and person's attribute.

[0039] The acquisition unit 11 may acquire moving population data from a moving population data acquisition device 3 or the like. The acquisition unit 11 may acquire weather data from an external data acquisition device 4 or the like. The acquisition unit 11 may acquire purchase quantity data and inventory quantity data from a purchase and inventory management device 5 or the like. The acquisition unit 11 may acquire customer sending condition data and distribution information from a store manager device 6 or the like. The acquisition unit 11 may acquire location attribute information from a customer smartphone 7 or the like.

[0040] The learning unit 12 generates a prediction model that predicts future purchase numbers based on the past data (demographic distribution data, purchase number data, external data) stored (accumulated) by the storage unit 10. The learning unit 12 causes the storage unit 10 to store the generated prediction model.

[0041] A prediction model is a combination of a computer program and parameters. A prediction model is also a combination of a neural network structure and parameters (weighting coefficients) that are the strength of the connections between the neurons of the neural network. A prediction model is also a set of instructions for a computer that are combined to obtain a certain result (to execute a certain process), that is, a computer program that causes a computer to function.

[0042] The learning unit 12 may generate a prediction model by performing learning based on learning data consisting of pairs including input data and correct answer data. For example, the learning unit 12 performs learning based on learning data consisting of pairs including population distribution data (related to population distribution around the store) in the morning of an arbitrary past day, weather data (around the store) in the afternoon of the day (including input data), and purchase number data (of the store) in the afternoon of the day (including correct answer data), to generate a prediction model. FIG. 9 is a diagram showing an example of learning data. The learning data shown in FIG. 9 shows pairs of population distribution data in the morning of January 1st, weather data in the afternoon of the same day (January 1st), and correct answer data in the afternoon of the same day (January 1st) (actually, the learning data is composed of a plurality of pairs, such as those for January 2nd, January 3rd, etc.).

[0043] The learning unit 12 performs learning based on the learning data shown in Fig. 9 to learn the relationship between the number of purchases (or purchase number data) (at a store) in the afternoon of an arbitrary day from, for example, population distribution data (related to the population distribution around the store) in the morning of that day and weather data (around the store) in the afternoon of that day. The learning unit 12 performs learning based on the learning data shown in Fig. 9 to generate a prediction model that outputs the number of purchases (or purchase number data) (at a store) in the afternoon of that day from, for example, population distribution data (related to the population distribution around the store) in the morning of that day and weather data (around the store) in the afternoon of that day. In other words, the generated prediction model predicts future purchase numbers.

[0044] The following describes the prediction coefficients generated by the learning of the learning unit 12. For example, the relationship between the population distribution in the morning, the weather in the afternoon, and the number of purchases in the afternoon is learned by the learning of the learning unit 12, and the prediction coefficients are optimized for each product, time, and weather. The number of purchases is expressed, for example, by the following formula. Number of purchases = Σ(Population 日時,メッシュ,性別,年代,居住地 × Prediction coefficient 日時,メッシュ,性別,年代,居住地 )

[0045] Prediction coefficients are an existing technique in machine learning. For example, see the following URL, which explains Elastic-Net in the open source machine learning library scikit-learn. https: / / www.tutorialspoint.com / scikit_learn / scikit_learn_elastic_net.htm

[0046] Decision tree algorithms (such as random forest and XGBoost) can also calculate the contribution of each feature to the prediction, so they can be used in the same way as prediction coefficients. However, prediction coefficients are not limited to the content of these specific existing technologies.

[0047] Fig. 10 is a diagram showing an example table (part 1) of population distribution data including prediction coefficients. The prediction coefficients in the example table shown in Fig. 10 indicate the probability (degree) of people (population distribution) contributing to the purchase of product "Product A" at time "13:00" when the weather is "sunny". For example, the first record in the example table in Fig. 10 indicates that the probability that a person with gender "male", age group "20s", and place of residence "Tokyo" who is located in mesh "Mesh X" at time "9:00" will purchase product "Product A" at time "13:00" (on the same day) when the weather is "sunny" is "0.05" (5%).

[0048] Fig. 11 is a diagram showing an example (part 2) of a table of population distribution data including prediction coefficients. The difference from the example table shown in Fig. 10 is that the weather is "cloudy" instead of "sunny", and the prediction coefficients are different accordingly.

[0049] The learning unit 12 causes the storage unit 10 to store the prediction coefficients (or the population distribution data including the prediction coefficients) generated by learning.

[0050] The prediction unit 13 predicts the (future) number of purchases at the store based on the prediction model stored by the storage unit 10. More specifically, the prediction unit 13 applies population distribution data (related to the population distribution around the store) for the morning of an arbitrary day (for example, today) and weather data (around the store) for the afternoon of that day to the prediction model, thereby obtaining the number of purchases (or purchase number data) for that afternoon (at the store) output by the prediction model, and sets this as a prediction result. The prediction unit 13 causes the storage unit 10 to store the predicted number of purchases (or purchase number data).

[0051] Fig. 12 is a diagram showing an example of a purchase volume forecast using a prediction model. Fig. 12 shows a scene in which purchase volume data (at a store) for the afternoon of the current day (April 1) is predicted by applying population distribution data (related to the population distribution around the store) for the morning of the current day (April 1) and weather data (forecast) for the afternoon of the same day (around the store) to a prediction model.

[0052] The prediction unit 13 calculates the purchase probability (for each afternoon time, mesh, gender, age group, and place of residence) based on the prediction coefficient stored by the storage unit 10 and the moving population data acquired by the acquisition unit 11. A specific calculation method will be described below.

[0053] The prediction unit 13 calculates an average migrant population ratio based on the migrant population data acquired by the acquisition unit 11. The average migrant population ratio is a ratio (probability) indicating where the probability of migrating from each mesh is typically high. The prediction unit 13 may calculate an average population movement from an arbitrary mesh in the morning to an arbitrary mesh in the afternoon based on the migrant population data. The prediction unit 13 calculates data obtained by adding up the migrant population data (date, time, mesh, moving time, moving mesh, sex, age, place of residence, migrant population) for each time as the average migrant population, and calculates an average migrant population ratio as a value obtained by dividing the average migrant population of each record (row) by the total number of the average migrant population at the corresponding time ("1000" in the table example shown in FIG. 13 described later). FIG. 13 is a diagram showing an example of a table of migrant population data including the average migrant population and the average migrant population ratio. The prediction unit 13 causes the storage unit 10 to store the calculated migrant population ratio.

[0054] The prediction unit 13 predicts the population involved in purchases (behavior) for each destination mesh based on the population distribution data acquired by the acquisition unit 11 and the prediction coefficients (behavior probability) and average moving population ratio (movement probability) stored by the storage unit 10.

[0055] The prediction coefficient may be the probability that a person in a specific mesh at a specific time will make a purchase (behavior). The average moving population ratio may be the probability that a person in a specific mesh at a specific time will move to a destination mesh.

[0056] The prediction coefficient may be a probability for each person's attribute. The average moving population ratio may be a probability for each person's attribute. The prediction unit 13 may predict the population related to purchases (behavior) for each destination mesh and person's attribute.

[0057] The prediction coefficient may be a probability for each weather. The prediction unit 13 may make a prediction further based on the weather data acquired by the acquisition unit 11.

[0058] The prediction unit 13 may further predict the probability that a person will be involved in a purchase (behavior) based on the predicted population involved in the purchase (behavior).

[0059] Hereinafter, details will be described with reference to FIGS. 14, 15 and 16 in addition to the above-mentioned FIGS.

[0060] Fig. 14 is a diagram showing an example of a table of population distribution data used to calculate a purchase probability. The example table shown in Fig. 14 is a table that incorporates the weather (forecast) for the afternoon of the same day into the morning (real-time) population distribution data.

[0061] The prediction unit 13 associates the model of the example table shown in FIG. 10 that matches the morning time and afternoon weather of the table example shown in FIG. 14, and calculates the purchasing population for each morning time and attribute by multiplying the population at each morning time, mesh, and attribute of the table example shown in FIG. 14 by the prediction coefficient at each morning time, mesh, and attribute of the table example shown in FIG. 10. Next, the prediction unit 13 multiplies the calculated purchasing population for each morning time, mesh, and attribute by the average moving population ratio of the example table shown in FIG. 13 that has the corresponding morning time (time before moving), source mesh, and attribute, and calculates the afternoon purchasing population by adding up each afternoon time (time after moving), destination mesh, and attribute. The prediction unit 13 causes the storage unit 10 to store the calculated purchasing population.

[0062] Fig. 15 is a diagram showing an example of a table of purchasing population data. As shown in Fig. 15, in the purchasing population data, the movement time, the movement mesh, the gender of the person who moved, the age of the person who moved, the residence of the person who moved, and the predicted purchasing population, which is the purchasing population calculated by the prediction unit 13, are associated with each other.

[0063] The prediction unit 13 calculates the purchase probability by dividing the calculated purchasing population for each afternoon time, destination mesh, and attribute by the total purchasing population for each time. In other words, the prediction unit 13 converts the purchasing population into a ratio and obtains the purchase probability for each travel time, destination mesh, gender, age, and place of residence. The prediction unit 13 causes the storage unit 10 to store the calculated purchase probability.

[0064] 16 is a diagram showing an example of a table of purchasing population data including purchase probabilities. As shown in FIG. 16, predicted purchase probabilities, which are purchase probabilities calculated by the prediction unit 13, are further associated.

[0065] The customer redirection unit 14 uses the purchase quantity prediction value and the stock quantity for each product and time to determine whether to redirect customers based on customer redirection conditions registered in advance. For example, the customer redirection unit 14 may determine whether to redirect customers based on (at least one of) the stock quantity data acquired from the purchase and inventory management device 5, the customer redirection condition data acquired from the store manager device 6, the purchase quantity prediction value (where time, product ID, and purchase quantity correspond to each other), and the purchase probability prediction value (where time, product ID, gender, age group, place of residence, location, and purchase probability correspond to each other). For example, the customer redirection unit 14 determines to redirect customers when the difference between the stock quantity and the predicted purchase quantity of product A, whose expiration date is the same day, at "18:00" is "100".

[0066] When it is determined that a customer should be sent, the customer sending unit 14 selects targets (gender, age, place of residence, location, etc.) with a high purchase probability for each time and product using the purchase probability prediction value. The customer sending unit 14 outputs the selection result to the determination unit 15 as customer sending target information. In the customer sending target information, for example, the time, product ID, target gender, target age, target place of residence, and target location are associated with each other.

[0067] The determination unit 15 registers a geofence and determines check-in based on the customer referral target information input from the customer referral unit 14. When registering a geofence, the determination unit 15 transmits geofence registration information to the customer smartphone 7. In the geofence registration information, for example, the time, the period for which the geofence is set, the gender of the target, the age group of the target, the place of residence of the target, the position of the target, and the range of the geofence are associated with each other.

[0068] After registering the geofence, the determination unit 15 acquires location attribute information from the customer smartphone 7 based on the geofence registration information, and performs check-in determination as to whether or not the customer has checked in to the geofence based on the acquired location attribute information. The determination unit 15 outputs the check-in determination result to the distribution unit 16 as check-in determination information. In the check-in determination information, for example, a customer ID, which is identification information of the checked-in customer, and a product ID included in the customer transfer target information are associated with each other.

[0069] The distribution unit 16 transmits customer distribution information to the customer smartphone 7 based on the check-in determination information input from the determination unit 15 and the distribution information acquired from the store manager device 6. In the customer distribution information, for example, a customer ID included in the check-in determination information and product information (such as advertisements) included in the distribution information are associated with each other.

[0070] The customer browses the product information acquired and displayed by the customer's smartphone 7, and if they like the product, they head to the corresponding store.

[0071] Fig. 17 is a diagram showing an example of customer transfer. Fig. 17 assumes that the third record in the example table of purchasing population data shown in Fig. 16 has been selected as a target by the customer transfer unit 14. In Fig. 17, the determination unit 15 has registered a geofence (a geofence of a concentric circle (radius 250 m) centered on mesh C) for customers with a travel time of "13:00" (or a time period of "13:00 to 13:59"), gender of "female", age group of "40s", and place of residence of "Kanagawa Prefecture" in the travel mesh "mesh C" (destination area).

[0072] As described above, the customer redirection unit 14, the determination unit 15, and the distribution unit 16 guide people based on the prediction results by the prediction unit 13. More specifically, the customer redirection unit 14, the determination unit 15, and the distribution unit 16 set geofences targeting segments with high purchase probabilities for each time period, and encourage customers to visit by information distribution. The customer redirection unit 14, the determination unit 15, and the distribution unit 16 may guide people in the destination mesh. The guidance may be to send customers to a store.

[0073] An example of processing executed by the purchase prediction system 8 will be described with reference to Figs. 18 and 19. Fig. 18 is a flowchart (part 1) showing an example of processing executed by the purchase prediction system 8. Fig. 19 is a flowchart (part 2) showing an example of processing executed by the purchase prediction system 8. The flowcharts in Figs. 18 and 19 may be consecutive. That is, the last processing (S10) in Fig. 18 may be followed by the first processing (S11) in Fig. 19.

[0074] In FIG. 18, first, the population distribution data acquisition device 2 transmits population distribution data to the purchase prediction device 1 (step S1). Next, the storage unit 10 of the purchase prediction device 1 stores the population distribution data transmitted in S1 (step S2). Next, the moving population data acquisition device 3 transmits the moving population data to the purchase prediction device 1 (step S3). Next, the storage unit 10 of the purchase prediction device 1 stores the moving population data transmitted in S3 (step S4). Next, the external data acquisition device 4 transmits external data to the purchase prediction device 1 (step S5). Next, the storage unit 10 of the purchase prediction device 1 stores the external data transmitted in S5 (step S6). Next, the purchase inventory management device 5 transmits purchase quantity data to the purchase prediction device 1 (step S7). Next, the learning unit 12 of the purchase prediction device 1 generates a prediction model (step S8). Next, the prediction unit 13 of the purchase prediction device 1 predicts the purchase quantity (step S9). Next, the prediction unit 13 of the purchase prediction device 1 calculates a purchase probability (step S10).

[0075] 18, the order of S1, S3, S5, and S7 may be arbitrary, each may be executed multiple times, or each may be executed repeatedly periodically. S2 may be executed at any time after S1 and before S8. S4 may be executed at any time after S3 and before S10. S6 may be executed at any time after S5 and before S8. The order of S9 and S10 may be reversed.

[0076] In FIG. 19, the store manager device 6 transmits a transmission condition to the purchase prediction device 1 (step S11). Next, the purchase inventory management device 5 transmits inventory information to the purchase prediction device 1 (step S12). Next, the customer sending unit 14 of the purchase prediction device 1 judges whether to send a customer (step S13). Assume that it is judged to send a customer in S13. Next, the customer sending unit 14 of the purchase prediction device 1 selects a target with a high purchase probability (step S14). Next, the determination unit 15 of the purchase prediction device 1 performs a field registration for the customer smartphone 7 (step S15). Next, the customer smartphone 7 transmits location attribute information to the purchase prediction device 1 (step S16). Next, the determination unit 15 of the purchase prediction device 1 performs a check-in judgment (step S17). Next, the store manager device 6 transmits distribution information to the purchase prediction device 1 (step S18). Next, the distribution unit 16 of the purchase prediction device 1 transmits the customer distribution information to the customer smartphone 7 (step S19).

[0077] 19, the order of S11 and S12 may be reversed, and S18 may be executed at any time before S19.

[0078] An example of processing executed by the purchase prediction device 1 will be described with reference to Fig. 20. Fig. 20 is a flowchart showing an example of processing executed by the purchase prediction device 1 according to the embodiment.

[0079] First, the storage unit 10 stores the prediction coefficients and the average moving population ratio (step S30, storage step). Next, the acquisition unit 11 acquires population distribution data (step S31, acquisition step). Next, the prediction unit 13 predicts the purchasing population for each movement mesh based on the population distribution data acquired in S31 and the prediction coefficients and the average moving population ratio stored in S30 (step S32).

[0080] Next, the effects of the purchase prediction device 1 according to the embodiment will be described.

[0081] According to the purchase prediction device 1, the storage unit 10 stores a prediction coefficient (behavior probability) which is the probability that a person in a specific mesh (area) will make a purchase (behavior) and an average moving population ratio (movement probability) which is the probability that a person in a specific mesh will move to a destination mesh which is a destination mesh, the acquisition unit 11 acquires population distribution data on the population for each mesh, and the prediction unit 13 predicts the population involved in purchases for each destination mesh based on the population distribution data acquired by the acquisition unit 11 and the prediction coefficient and average moving population ratio stored by the storage unit 10. With this configuration, the population involved in behavior for each destination mesh is predicted based on the population distribution data, behavior probability, and movement probability. That is, the population involved in behavior in the destination mesh can be predicted.

[0082] In addition, in the purchase prediction device 1, the prediction coefficient is the probability that a person in a specific mesh at a specific time will make a purchase, the average moving population ratio is the probability that a person in a specific mesh at a specific time will move to a destination mesh, and the population of the population distribution data may further be for each time. With this configuration, it is possible to predict the population involved in behavior for each time and destination mesh. In other words, more accurate predictions can be made, and the usefulness of the prediction results is increased.

[0083] In addition, in the purchase prediction device 1, the prediction coefficient is a probability for each person's attribute, the average moving population ratio is a probability for each person's attribute, and the population of the population distribution data is further for each person's attribute, and the prediction unit 13 may predict the population involved in purchases for each destination mesh and person's attribute. With this configuration, it is possible to predict the population involved in purchases for each destination mesh and person's attribute. In other words, more accurate predictions can be made, and the usefulness of the prediction results is increased.

[0084] Furthermore, in the purchase prediction device 1, the prediction coefficient is a probability for each weather, the acquisition unit 11 further acquires weather data related to the weather, and the prediction unit 13 may make a prediction further based on the weather data acquired by the acquisition unit 11. With this configuration, it is possible to reflect the weather data in the prediction. This allows a more accurate prediction to be made, and the usefulness of the prediction result is increased.

[0085] In addition, in the purchase prediction device 1, the prediction unit 13 may further predict the probability that a person will be involved in a purchase based on the predicted population involved in the purchase. With this configuration, it is possible to predict the probability that a person will be involved in a purchase, and the usefulness of the prediction result is increased.

[0086] The purchase prediction device 1 may further include a customer directing unit 14, a determining unit 15, and a distribution unit 16 that guide people based on the prediction result by the prediction unit 13. With this configuration, people can be appropriately guided based on the prediction result.

[0087] In addition, in the purchase prediction device 1, the customer sending unit 14, the determination unit 15, and the distribution unit 16 may guide people in the destination mesh. With this configuration, people can be guided to the destination mesh, so that people can be guided more reliably.

[0088] In addition, in the purchase prediction device 1, a purchase may be a purchase of a product or service at a store, and a guide may be sending customers to the store. With this configuration, for example, food waste can be reduced by sending customers to a store that has a large amount of food inventory that is close to its expiration date.

[0089] As described above, the purchase prediction device 1 can automatically send customers to a store.

[0090] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. The method of realizing each functional block is not particularly limited. That is, each functional block may be realized by using one device that is physically or logically combined, or may be realized by using two or more devices that are physically or logically separated and directly or indirectly connected (for example, by wire, wirelessly, etc.). The functional blocks may be realized by combining the one device or the multiple devices with software.

[0091] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocation, mapping, assignment, etc. For example, a functional block (component) that performs the function of transmission is called a transmitting unit or a transmitter. In either case, as described above, there is no particular limitation on the method of realization.

[0092] For example, the purchase prediction device 1 according to an embodiment of the present disclosure may function as a computer that performs processing of the purchase prediction method according to the present disclosure. Fig. 21 is a diagram showing an example of a hardware configuration of the purchase prediction device 1 according to an embodiment of the present disclosure. The above-mentioned purchase prediction device 1 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0093] In the following description, the term "apparatus" may be replaced with a circuit, a device, a unit, etc. The hardware configuration of the purchase prediction device 1 may be configured to include one or more of the devices shown in the drawings, or may be configured to exclude some of the devices.

[0094] Each function of the purchase prediction device 1 is realized by loading a specific software (program) onto hardware such as a processor 1001 and a memory 1002, causing the processor 1001 to perform calculations, control communication via a communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and the storage 1003.

[0095] The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned acquisition unit 11, learning unit 12, prediction unit 13, customer sending unit 14, determination unit 15, and distribution unit 16 may be realized by the processor 1001.

[0096] Moreover, the processor 1001 reads out a program (program code), a software module, data, etc. from at least one of the storage 1003 and the communication device 1004 to the memory 1002, and executes various processes according to the read out programs. As the program, a program that causes a computer to execute at least a part of the operations described in the above-mentioned embodiment is used. For example, the acquisition unit 11, the learning unit 12, the prediction unit 13, the customer sending unit 14, the determination unit 15, and the distribution unit 16 may be realized by a control program stored in the memory 1002 and operated in the processor 1001, and other functional blocks may be realized in a similar manner. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed by two or more processors 1001 simultaneously or sequentially. The processor 1001 may be implemented by one or more chips. The program may be transmitted from a network via a telecommunication line.

[0097] The memory 1002 is a computer-readable recording medium, and may be configured by at least one of, for example, a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a Random Access Memory (RAM), etc. The memory 1002 may be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store a program (program code), software modules, etc. that are executable to implement a wireless communication method according to an embodiment of the present disclosure.

[0098] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, 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 disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, and the like. Storage 1003 may be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0099] The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc., in order to realize at least one of, for example, Frequency Division Duplex (FDD) and Time Division Duplex (TDD). For example, the above-mentioned acquisition unit 11, learning unit 12, prediction unit 13, customer transfer unit 14, determination unit 15, and distribution unit 16 may be realized by the communication device 1004.

[0100] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0101] In addition, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0102] Furthermore, the purchase prediction device 1 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0103] Notification of information is not limited to the aspects / embodiments described in this disclosure and may be performed using other methods.

[0104] Each aspect / embodiment described in the present disclosure may be applied to at least one of systems using 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 (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth (registered trademark), and other suitable systems, and next-generation systems extended based on these. In addition, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A and 5G, etc.) may be applied.

[0105] The order of the steps, sequences, flow charts, etc. of each aspect / embodiment described in this disclosure may be changed unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0106] Information, etc. may be output from a higher layer (or a lower layer) to a lower layer (or a higher layer). Information may be input / output via multiple network nodes.

[0107] The input and output information may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added to. The output information may be deleted. The input information may be transmitted to another device.

[0108] The determination may be based on a value represented by a single bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0109] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched according to execution. In addition, notification of specific information (e.g., notification that "X is the case") is not limited to being done explicitly, but may be done implicitly (e.g., not notifying the specific information).

[0110] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described in the present disclosure. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0111] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0112] Additionally, software, instructions, information, etc. may be transmitted or received over a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired and / or wireless technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave, etc.), then these wired and / or wireless technologies are included within the definition of transmission media.

[0113] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0114] In addition, terms explained in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings.

[0115] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0116] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0117] The names used for the above parameters are not limiting in any way, and furthermore, the formulas etc. using these parameters may differ from those explicitly disclosed in this disclosure.

[0118] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, search, inquiry (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in a memory), and the like. In addition, "judgment" and "decision" can include considering resolving, selecting, choosing, establishing, comparing, etc., to be a "judgment" or "decision." In other words, "judgment" and "decision" can include considering some action to be a "judgment" or "decision." In addition, "judgment" can be interpreted as "assuming," "expecting," "considering," etc.

[0119] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0120] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0121] Any reference to an element using a designation such as "first," "second," etc., 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 method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must precede the second element in some way.

[0122] The "means" in the configuration of each of the above devices may be replaced with "part," "circuit," "device," etc.

[0123] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Further, when used in this disclosure, the term "or" is not intended to be an exclusive or.

[0124] In this disclosure, where articles have been added due to translation, such as, for example, a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0125] In the present 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 "coupled" may also be interpreted in the same way as "different." [Explanation of symbols]

[0126] 1...purchase prediction device, 2...population distribution data acquisition device, 3...mobile population data acquisition device, 4...external data acquisition device, 5...purchase inventory management device, 6...store manager device, 7...customer smartphone, 8...purchase prediction system, 10...storage unit, 11...acquisition unit, 12...learning unit, 13...prediction unit, 14...customer redirection unit, 15...determination unit, 16...distribution unit, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. A storage unit that stores a behavior probability, which is the probability that a person in a predetermined area will purchase a product or service, and a movement probability, which is the probability that a person in the predetermined area will move to a destination area, which is a destination area; An acquisition unit that acquires population distribution data regarding the population of each area and population movement data regarding the movement of people; a prediction unit that calculates a movement probability based on the moving population data acquired by the acquisition unit, stores the calculated movement probability in the storage unit, and predicts a population that will purchase a product or service for each destination area based on the population distribution data acquired by the acquisition unit and the behavior probability and movement probability stored in the storage unit; A behavior prediction device comprising:

2. The behavior probability is the probability that a person in a given area at a given time will purchase a product or service. The movement probability is the probability that a person in a given area at a given time moves to a destination area, The population distribution data is further divided by time. The behavior prediction device according to claim 1 .

3. The probability of an action is the probability for each person's attributes, The probability of movement is the probability for each person's attributes, The population distribution data is further divided by human attributes, The prediction unit predicts a population that will purchase a product or service for each destination area and each person attribute. The behavior prediction device according to claim 1 .

4. The probability of action is the probability for each weather condition, The acquisition unit further acquires weather data relating to weather, The prediction unit makes a prediction further based on the weather data acquired by the acquisition unit. The behavior prediction device according to claim 1 .

5. The prediction unit further predicts a probability that a person will purchase a product or service based on the predicted population that will purchase the product or service. The behavior prediction device according to claim 1 .

6. Further comprising a guidance unit that guides a person based on a prediction result by the prediction unit. The behavior prediction device according to claim 1 .

7. The guiding unit guides people in a destination area. The behavior prediction device according to claim 6.

8. The action is the purchase of a product or service at a store; Guidance is sending customers to the store. The behavior prediction device according to claim 6.

9. A storage unit for storing an action probability, which is the probability that a person in a predetermined area will engage in an action, and a movement probability, which is the probability that a person in the predetermined area will move to a destination area, which is a destination area; An acquisition unit that acquires population distribution data regarding the population of each area; a prediction unit that predicts a population involved in a behavior for each destination area based on the population distribution data acquired by the acquisition unit and the behavior probability and the movement probability stored by the storage unit; Equipped with The probability of a behavior is the probability that a person in a given area at a given time will engage in a behavior. The movement probability is the probability that a person in a given area at a given time moves to a destination area, The population distribution data is further divided by time. Behavioral prediction device.

10. A storage unit for storing an action probability, which is the probability that a person in a predetermined area will engage in an action, and a movement probability, which is the probability that a person in the predetermined area will move to a destination area, which is a movement destination area; An acquisition unit that acquires population distribution data regarding the population of each area; a prediction unit that predicts a population involved in a behavior for each destination area based on the population distribution data acquired by the acquisition unit and the behavior probability and the movement probability stored by the storage unit; Equipped with The probability of an action is the probability for each person's attributes, The probability of movement is the probability for each person's attributes, The population distribution data is further divided by human attributes, The prediction unit predicts a population related to a destination area and a behavior of each person for each attribute of the person. Behavioral prediction device.

Citation Information

Patent Citations

  • Retail store managing system

    JP2002024350A

  • Customer inducing method

    JP2008204370A

  • Information processing apparatus, information processing method, and program

    JP2015055934A

  • Targeted information content delivery using a combination of environmental and demographic information

    WO2004036476A1

  • Simulation device, simulation system, and simulation method

    WO2018008203A1