JP2019145006A - Selection device, selection method and selection program - Google Patents

Abstract

To enable a predetermined business operator to take an appropriate behavior.SOLUTION: A selection device comprises an acquisition unit, a prediction unit and a selection unit. The acquisition unit acquires a planned value of an index relating to a business of one business operator and corresponding to a predetermined point of time and acquires history information at the predetermined point of time and before. The prediction unit predicts a prediction value of an index relating to a business of one business operator and corresponding to a predetermined point of time on the basis of the history information acquired by the acquisition unit. The selection unit selects a coping behavior which is a behavior for coping with deviation if deviation between the prediction value predicted by the prediction unit and the planned value meets a predetermined condition.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a selection device, a selection method, and a selection program.

  2. Description of the Related Art Conventionally, various technologies related to business in business operators (stores and the like) have been provided. For example, a technique for managing sales by predicting sales of products in a store is provided. In such a technique, for example, alarm information is output when the predicted sales of a product are not within a predetermined deviation allowable range from the sales target value.

JP 2004-127017 A

  However, with the above-described conventional technology, it is not always possible to perform appropriate behavior for a predetermined business operator. For example, if the predicted sales of a product are not within a predetermined deviation allowable range from the sales target value, the behavior of the side (for example, the store) that received the output of the alarm information will be handled only by outputting the alarm information. It may be difficult to make appropriate actions for a given business operator because it is necessary to determine whether or not to do so.

  The present application has been made in view of the above, and an object thereof is to provide a selection device, a selection method, and a selection program that enable an appropriate action for a predetermined operator.

  The selection device according to the present application is a plan value of an index related to the business of one business operator, and obtains a plan value corresponding to a predetermined time point and history information before the predetermined time point, Based on the history information acquired by the acquisition unit, a prediction unit that predicts a prediction value of the index related to the business of the one operator and corresponding to the predetermined time point, and the prediction And a selection unit that selects a coping action that is an action for coping with the divergence when the divergence between the predicted value predicted by the unit and the planned value satisfies a predetermined condition. .

  According to one aspect of the embodiment, there is an effect that an appropriate action can be made possible for a predetermined business operator.

FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 2 is a diagram illustrating an example of the selection process according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the selection system according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of the selection device according to the embodiment. FIG. 5 is a diagram illustrating an example of a learning data storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the model information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of the store information storage unit according to the embodiment. FIG. 8 is a diagram illustrating an example of the index information storage unit according to the embodiment. FIG. 9 is a diagram illustrating an example of a coping behavior information storage unit according to the embodiment. FIG. 10 is a flowchart illustrating an example of the generation process according to the embodiment. FIG. 11 is a flowchart illustrating an example of the selection process according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the selection device.

  Hereinafter, a selection device, a selection method, and a mode for implementing a selection program (hereinafter referred to as “embodiment”) according to the present application will be described in detail with reference to the drawings. In addition, the selection apparatus, the selection method, and the selection program which concern on this application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1. Generation process)
First, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. In FIG. 1, the selection device 100 generates a model for predicting a predicted value of an index related to a business of one operator, using history information related to each of a plurality of businesses including the one business operator. Show the case. Note that the selection device 100 may generate a model using not only history information related to each of a plurality of business operators but also history information related to one business operator. Further, any information may be included in the history information. For example, the history information may include any information as long as it can be acquired before the prediction time point. For example, the history information is not limited to the above as long as it is information that can be used as model input information. Details of the history information will be described later. FIG. 1 shows a case where each business operator has one store, that is, a case where the business operator and the store have a one-to-one relationship. For example, the case where the selection apparatus 100 generates a model for predicting the sales of the store A with the store A as the target store is shown. In the example of FIG. 1, as an example of a store KPI (Key Performance Indicator), the store sales are predicted. However, the selection device 100 may be an index related to the store performance. For example, a model for predicting any index may be generated. In addition, the selection device 100 may target a case where a single company has a plurality of stores such as a chain store. That is, the selection apparatus 100 may generate a model that predicts a predicted value of an index related to the business of one business using the history information related to the business of one business having a plurality of stores. In this case, the selection apparatus 100 may predict an index related to the performance of one business operator having a plurality of stores using a model. For example, the selection device 100 generates a model (model MX) using only history information of stores located in a predetermined area (area X or the like) among stores of a single company having a plurality of stores. May be. In this case, the selection apparatus 100 may predict an index related to the performance of the area XX of one operator using the model MX. As described above, the business targeted by the selection device 100 is not limited to a business having a single store, and may be various businesses such as a business having a plurality of stores. In the following, in order to simplify the explanation, the business operator is described as a store in order to explain based on the case where one business operator has one store. That is, below, a store may be read as an operator.

  In FIG. 1, the selection device 100 inputs various information such as history information (hereinafter also referred to as “store history information”), weather information, and user behavior information of a plurality of stores such as A store and B store. The case where it is used as (input data) is shown. Hereinafter, the history information associated with the correct answer information is also referred to as “learning data”. In addition, when described as date and time below, it may be a predetermined period including the date and time (for example, 10 minutes, 1 hour, 1 day, etc.).

  In FIG. 2, the selection apparatus 100 uses the generated model to store store history information such as A store and B store at a certain date and time (period), user behavior information at a certain date and time (period), and A store information. Based on the history information including weather information corresponding to the area, the sales of the store A at a predetermined date (period) after that date are predicted. Hereinafter, the predicted sales value is also referred to as a sales predicted value. In FIG. 2, the selection device 100 performs the coping action based on the difference between the sales forecast value of the store A at a predetermined date and time and the sales value planned by the store A (hereinafter also referred to as “sales planned value”). Indicates the case of selection.

[Configuration of selected system]
Prior to the description of FIGS. 1 and 2, the configuration of the selection system 1 will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the selection system according to the embodiment. As illustrated in FIG. 3, the selection system 1 includes a terminal device 10, a store terminal 20, a service providing device 50, and a selection device 100. The terminal device 10, the store terminal 20, the service providing device 50, and the selection device 100 are connected via a predetermined network N so as to be communicable by wire or wirelessly. The selection system 1 shown in FIG. 3 may include a plurality of terminal devices 10, a plurality of store terminals 20, a plurality of service providing devices 50, and a plurality of selection devices 100. .

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. FIG. 1 shows a case where the terminal device 10 is a smartphone. The terminal device 10 has a function such as a GPS (Global Positioning System) sensor, and can detect and acquire the position of the user. Further, the terminal device 10 transmits various information and the like to the selection device 100 and the service providing device 50. For example, the terminal device 10 transmits position information about the user to the selection device 100 and the service providing device 50. In addition, the terminal device 10 receives information from the selection device 100 and the service providing device 50. For example, the terminal device 10 receives information from the selection device 100 and the service providing device 50. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10.

  The terminal device 10 may collect user information such as user behavior information and transmit it to the selection device 100 and the service providing device 50. Moreover, the terminal device 10 may detect various sensor information not only with a GPS sensor etc. but with various sensors. For example, the terminal device 10 may predict and acquire the position information of the user using the position information of the base station with which communication is performed or the radio wave of WiFi (registered trademark) (Wireless Fidelity). Moreover, the terminal device 10 has a function of an acceleration sensor, and may detect and acquire acceleration information (sensor information) in the movement of the user. Further, the terminal device 10 may have various functions such as a temperature sensor and an atmospheric pressure sensor, and may be able to detect and acquire environmental information where the user is placed such as temperature and atmospheric pressure. Moreover, the terminal device 10 may have various functions such as a heart rate sensor, and may be able to detect and acquire a user's biological information. For example, a user using the terminal device 10 may acquire a user's own context information by the terminal device 10 by wearing a wearable device that can communicate with the terminal device 10. For example, a user who uses the terminal device 10 wears a wristband type wearable device that can communicate with the terminal device 10, and the terminal device 10 acquires information on the user's own heartbeat (pulse) by the terminal device 10. It may be possible.

  The store terminal 20 is an information processing device used by each store. For example, the store terminal 20 is used by the manager of each store. The store terminal 20 transmits and receives information to and from the terminal device 10, the selection device 100, and the service providing device 50. For example, the manager of the store A uses the store terminal 20 to transmit / receive information to / from the terminal device 10, the selection device 100, and the service providing device 50.

  Further, the store terminal 20 transmits various information and the like to the selection device 100 and the service providing device 50. For example, the store terminal 20 transmits information related to the store to the selection device 100 and the service providing device 50. Further, the store terminal 20 receives information from the selection device 100 and the service providing device 50. For example, the store terminal 20 receives information from the selection device 100 and the service providing device 50. For example, the store terminal 20 is realized by a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. Hereinafter, the store terminal 20 may be referred to as a store. That is, below, a store can be read as the store terminal 20.

  The service providing device 50 is an information processing device used by a service provider. For example, the service providing device 50 is used by a service provider who distributes content to a user. The service providing device 50 transmits and receives information to and from the terminal device 10, the store terminal 20, and the selection device 100. Further, the service providing apparatus 50 transmits various information and the like to the terminal device 10, the store terminal 20, and the selection device 100. For example, the service providing device 50 transmits information related to the provided service to the terminal device 10, the store terminal 20, and the selection device 100. The service providing device 50 receives information from the terminal device 10, the store terminal 20, and the selection device 100. For example, the service providing device 50 receives information from the terminal device 10, the store terminal 20, and the selection device 100.

  The service providing device 50 provides various information to the selection device 100. For example, the service providing apparatus 50 provides collected weather information and information about the user to the selection apparatus 100. For example, the service providing apparatus 50 provides weather information indicating the weather in the area A to the selection apparatus 100. For example, the service providing apparatus 50 transmits user position information and user number information indicating the number of users located in the area A to the selection apparatus 100. For example, the service providing apparatus 50 provides the selection apparatus 100 with information related to various user actions such as user search, purchase, and content browsing. For example, the service providing apparatus 50 may provide the selection apparatus 100 with information on a model such as the model M1.

  An information processing apparatus that selects a coping action that is an action for dealing with a divergence when a divergence between a predicted value and a plan value satisfies a predetermined condition for an index related to the business of one store. It is. The selection apparatus 100 predicts a predicted value of an index corresponding to a predetermined time point based on history information related to each of the plurality of stores before the predetermined time point. Further, when selecting the coping action, the selection device 100 executes processing corresponding to the selected coping action. For example, when selecting the coping behavior, the selection device 100 provides services such as information provision to the terminal device 10, the store terminal 20, and the service providing device 50 based on the selected coping behavior. For example, the selection device 100 transmits information to the terminal device 10, the store terminal 20, and the service providing device 50. For example, the selection device 100 transmits information based on the coping behavior to the terminal device 10, the store terminal 20, and the service providing device 50.

  First, the case where the selection device 100 generates the model M1 used for predicting the sales of the store A will be described with reference to FIG. In the example of FIG. 1, it is assumed that information indicating the sales plan of the store A (hereinafter also referred to as “sales plan information”) has been acquired in advance. For example, the selection apparatus 100 acquires sales plan information including sales plan values CV10 to CV16 corresponding to the dates and times DA10 to DA16 as shown in the index information storage unit 124 (see FIG. 8). For example, the selection device 100 acquires the sales plan information from the store terminal 20 (see FIG. 3) of the store A and stores it in the index information storage unit 124 (see FIG. 8). Further, in the example of FIG. 1, as illustrated in the map information MP1, a case where an A store located in the area A is targeted will be described as an example.

  In addition, “* (* is an arbitrary numerical value)” following “DA” in each date and time “DA *” shown in the example of FIG. 1 or FIG. 2 indicates that the date (period) is larger as the value of “*” is larger. It shall be new. For example, since the date and time “DA11” has a smaller numerical value following “DA” than the date and time “DA12”, the date and time “DA11” indicates the date and time (period) corresponding to the past than the date and time “DA12”. . For example, each date and time “DA *” may be a predetermined period such as one hour.

  The selection device 100 acquires history information of each store from a plurality of stores. The selection device 100 acquires history information regarding the KPI of the store at each date and time (period). For example, the selection device 100 acquires history information related to the sales of the store A, the number of visitors, the number of inquiries, etc. at each date and time (period).

  Selection device 100 acquires history information of A store from A store (Step S11-1). The selection apparatus 100 acquires the history information of the store A from the store terminal 20 of the store SH11 (store A) in the map information MP1 of FIG. For example, the selection device 100 acquires store history information LG11 including the number of visitors corresponding to each date and time from the A store. In the example of FIG. 1, the selection apparatus 100 acquires store history information LG11-0 to LG11-3 corresponding to the dates DA10 to DA13 from the store A. As described above, the date and time here may be a predetermined period including the date and time. For example, the date and time may be a predetermined period before the date and time (for example, within 24 hours from the date and time). For example, the date and time DA11 and the date and time DA12 may include overlapping periods.

  Moreover, the selection apparatus 100 acquires the historical information of B store from B store (step S11-2). The selection apparatus 100 acquires the history information of the B store from the store terminal 20 of the store SH12 (B store) in the map information MP1 of FIG. For example, the selection device 100 acquires store history information LG12 including the number of visitors corresponding to each date and time from the store A. In the example of FIG. 1, the selection device 100 acquires store history information LG12-0 to LG12-3 corresponding to the dates DA10 to DA13 from the B store.

  Hereinafter, when it demonstrates without distinguishing step S11-1, S11-2, it is named step S11 generically. Moreover, not only step S11-1 and S11-2 but information acquisition from each store may be performed in multiple times. Note that FIG. 1 shows a case where information of only two stores, that is, the A store and the B store is used for the sake of simplicity, but the selection device 100 uses the B for stores other than the A store to be predicted. Not only stores but also information on a large number of stores (for example, 100 stores and 1000 stores) may be used.

  Moreover, the selection apparatus 100 acquires correct answer information from A store (step S12). The selection apparatus 100 acquires correct information from the store terminal 20 of the A store. For example, the selection apparatus 100 acquires correct answer information RDT1 indicating the actual sales value (hereinafter also referred to as “actually measured value”) corresponding to each date and time from the A store. In the example of FIG. 1, the selection device 100 acquires correct answer information RDT1-1 to RDT1-4 corresponding to the dates and times DA11 to DA14 from the store A.

  Further, the selection device 100 acquires history information including weather information and information on user behavior (hereinafter also referred to as “user-related information”) from the service providing device 50 (step S13). For example, the selection device 100 acquires the history information LG21 corresponding to each date and time from the service providing device 50. In the example of FIG. 1, the selection device 100 acquires the history information LG21 including weather information and user related information corresponding to the dates DA10 to DA13 from the service providing device 50.

  For example, the selection apparatus 100 acquires weather information related to the position of the store A as weather information. For example, the selection device 100 acquires the weather information of the area A corresponding to each date and time as the weather information related to the position of the store A.

  For example, the selection apparatus 100 acquires a user's action history on the Internet as the user related information. For example, the selection apparatus 100 acquires information such as search information indicating user search and purchase information indicating user purchase as user-related information. Note that the purchase information may be purchase information related to a product sold by the A store or a related product of the product. Further, for example, the selection device 100 acquires information related to a user's schedule and schedule such as calendar information as user-related information. Moreover, the selection apparatus 100 acquires the number-of-users information which shows the number of users located in the area A where A shop is located as user related information. In the example of FIG. 1, only search information is shown as user-related information, but the history information LG21 includes purchase information corresponding to each date and time, information related to the user's schedule, and the number of users. . Further, steps S11 to S13 may be performed at any timing as long as they are before step S14. For example, step S13 may be performed before step S11 or step S12.

  And the selection apparatus 100 adds the data which combined the information acquired by step S11-S13 as learning data (step S14). In the example of FIG. 1, the selection device 100 generates learning data in which the actual sales values (sales actual sales values) such as the respective dates and times DA11 to DA14 included in the correct information RDT1 are correct information RDT1-1 to RDT1-4. . Specifically, the selection device 100 adds learning data to the learning data storage unit 121.

  For example, the selection device 100 generates, as learning data, data DT1-1 including correct information RDT1-1 indicating the sales actual value of the store A at the date DA11. Moreover, the selection apparatus 100 produces | generates data DT1-1 including the store history information of A store and B store before the date DA11 as learning data. In the example of FIG. 1, the selection apparatus 100 generates data DT1-1 including store history information LG11-0 of store A and store history information LG12-0 of store B corresponding to the date and time DA10 as learning data. In addition, the selection device 100 generates data DT1-1 including weather information and user-related information before the date and time DA11 as learning data. In the example of FIG. 1, the selection device 100 generates, as learning data, data DT <b> 1-1 including weather information WDT <b> 10 and search information SDT <b> 10 as history information in the history date LG <b> 21 in the past date and time DA <b> 11.

  For example, the search information SDT10 includes information indicating the number of searches using a query related to the product provided by the store A at the date and time DA10. For example, the search information SDT10 includes information indicating the number of searches using the name of the product provided by the A store at the date and time DA10. The weather information WDT10 includes information indicating whether the area (area A) related to the store A at the date and time DA10 was clear, cloudy, rainy, or the like. The data DT1-1 includes user purchase information at the date and time DA10 and user number information in the area A as user related information. The weather information WDT10 may be information predicted when data is added (for example, at the time of step S14). The weather information WDT10 may be, for example, weather information indicating a prediction of whether the weather at the date and time DA11 is sunny, cloudy, rainy, or the like.

  As described above, when “data DT * (* is an arbitrary numerical value)” is described, it indicates that the data is data identified by the data ID “DT *”. For example, when “data DT1-1” is described, the data is data identified by the data ID “DT1-1”.

  In addition, for example, the selection device 100 generates data DT1-2 including correct information RDT1-2 indicating the sales actual value of the store A at the date and time DA12 as learning data. Moreover, the selection apparatus 100 produces | generates data DT1-2 including the store history information of A store and B store before the date DA12 as learning data. In the example of FIG. 1, the selection apparatus 100 generates data DT1-2 including the store history information LG11-1 of the A store corresponding to the date and time DA11 and the store history information LG12-1 of the B store as learning data. In addition, the selection device 100 generates data DT1-2 including weather information and user-related information before the date and time DA12 as learning data. In the example of FIG. 1, the selection apparatus 100 generates, as learning data, data DT1-2 including, as history information, weather information WDT11 and search information SDT11 at a date and time DA11 that is earlier than the date and time DA12 in the history information LG21.

  For example, the search information SDT11 includes information indicating the number of searches using a query related to a product provided by the store A at the date and time DA11. For example, the search information SDT11 includes information indicating the number of searches using the name of the product provided by the store A at the date and time DA11. Further, the weather information WDT11 includes information indicating whether the area (area A) related to the store A at the date and time DA11 was clear, cloudy, rainy, or the like. The data DT1-2 includes user purchase information at the date and time DA11 and user number information in the area A as user related information. The weather information WDT11 may be information predicted when data is added (for example, at the time of step S14). The weather information WDT11 may be, for example, weather information indicating a prediction of whether the weather at the date and time DA12 is sunny, cloudy, rainy, or the like.

  In addition, the correct information RDT1-1 to RDT1-4 is not limited to the actual sales value but may be various information based on the actual sales value. For example, it may be information indicating to which level the measured value of sales in a predetermined period (for example, one day) of the store A corresponds. For example, the correct information RDT1-1 to RDT1-4 may be in 10 levels of 0 to 1 when the maximum daily sales of the store A is 100,000 yen. For example, the correct answer information RDT1-1 to RDT1-4 is level “0” when the actual measurement value is less than 10,000 yen, and the level “0 .0” when the actual measurement value is 10,000 yen or more and less than 20,000 yen. 1 ". In addition, the correct information RDT1-1 to RDT1-4 has a level “0.9” when the actual measurement value is 90,000 yen or more and less than 100,000 yen, and when the actual measurement value is 100,000 yen or more, the level “ 1 ". As described above, the correct answer information RDT1-1 to RDT1-4 may be information that indicates which level corresponds to a plurality of levels, that is, information that indicates sales in stages. For example, the correct information RDT1-1 may be “0.7” when the actual sales value at the date and time DA11 is 70,000 yen.

  In this case, the selection apparatus 100 may store a correspondence table indicating correspondence between each level and sales in the storage unit 120 (see FIG. 4). The model M1 may be a model that outputs a score indicating a level. The selection apparatus 100 may predict the predicted value of sales using the score output by the model M1 and the level correspondence table. For example, when the model M1 to which history information is input outputs a score “0.9”, the selection device 100 may predict the sales as the predicted value “90,000 yen” using the level correspondence table. . Hereinafter, in order to simplify the description, a case where the selection device 100 generates the model M1 that outputs a value of 0 to 1 as described above will be described as an example.

  The selection device 100 generates a model based on the learning data (step S15). As described above, the selection device 100 generates a model by using store history information, weather information, and user related information at a date before the date corresponding to each correct answer information as history information. Thereby, the selection apparatus 100 can generate a model for predicting future sales of the store A by inputting the current information.

  For example, the selection device 100 generates a model by performing learning using the data DT1-1 to DT1-4 in the learning data storage unit 121 as learning data (teacher data). For example, the selection device 100 generates a model using a feature amount related to store history information. For example, the selection device 100 generates a model using the feature amount related to the KPI of the store. Further, for example, the selection device 100 generates a model using a feature amount related to weather information. For example, the selection device 100 generates a model using feature quantities related to the weather, temperature, humidity, and the like of an area related to the store. In addition, for example, the selection device 100 generates a model using a feature amount related to search information related to a store. For example, the selection device 100 generates a model using a feature amount related to the number of searches using a query related to a product provided by a store. As described above, the selection device 100 learns the characteristics included in the history information and generates a model for predicting the sales of the store. In the example of FIG. 1, the selection device 100 learns characteristics related to information included in the history information and generates a model for predicting store sales. The features included in the history information learned by the selection device 100 may be input to the selection device 100 by a person such as an administrator of the selection device 100, or may be automatically learned (extracted) by the selection device 100. Also good.

  For example, the selection device 100 generates a model M1 using learning data as shown in the learning data storage unit 121. For example, when the correct information RDT1-1 is “1” indicating that the sales were 100,000 yen or more, the selection device 100 receives the history information included in the data DT1-1 in the model M1. The learning process is performed so that the score output by the model M1 approaches “1”. For example, when the store history information LG11-0, the store history information LG12-0, the weather information WDT10, and the search information SDT10 of the data DT1-1 are input to the model M1, the selection device 100 has a score output by the model M1. The learning process is performed so as to approach “1”.

  For example, when the selection information 100 is “0.5” indicating that the sales were 50,000 yen as the correct answer information RDT1-2, the history information included in the data DT1-2 is input to the model M1. Learning process is performed so that the score output by the model M1 approaches “0.5”. For example, when the store history information LG11-1, the store history information LG12-1, the weather information WDT11, and the search information SDT11 of the data DT1-2 are input to the model M1, the selection device 100 has a score output by the model M1. The learning process is performed so as to approach “0.5”.

  Note that the model learning technique is not limited to the technique described above, and any known technique can be applied. Each model may be generated using various conventional techniques relating to machine learning as appropriate. For example, the model generation may be performed using a technique related to machine learning of supervised learning such as SVM (Support Vector Machine). Further, for example, the model generation may be performed using a technique related to machine learning of unsupervised learning. For example, the generation of the model may be performed using a deep learning technique. For example, the model generation may be performed by appropriately using various deep learning techniques such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network). The description relating to the generation of the model is merely an example, and the generation of the model may be performed by a learning method appropriately selected according to information that can be acquired. That is, when the history information included in the learning data is input, the selection device 100 can generate the model M1 by any method as long as the model M1 can be learned so as to output a score corresponding to the correct answer information. May be performed.

  With the above processing, in the example of FIG. 1, the selection device 100 generates a model (model M1) identified by the model ID “M1” as shown in the model information storage unit 122. As described above, when “model M * (* is an arbitrary numerical value)” is described, it indicates that the model is a model identified by the model ID “M *”. For example, when “model M1” is described, the model is a model identified by the model ID “M1”. Further, as shown in the model information storage unit 122 in FIG. 1, the model M1 is a use “sales forecast (A store)”, that is, a model used for forecasting sales of the A store. Indicates “model data MDT1”. For example, the selection apparatus 100 inputs the history information corresponding to the date and time in the model M1, and thereby the model M1 has a score indicating the sales of the A store ahead (future) ahead of the date and time corresponding to the input history information. The sales of store A are predicted based on the score output by model M1.

  As described above, the selection device 100 makes it possible to appropriately predict the predicted value of the index related to the business of one store by learning using learning data in which history information and correct answer information are associated with each other. A model can be generated. Therefore, the selection apparatus 100 can make it possible to accurately predict the predicted value of the index related to the business of one store, for example, by using the model generated as described above. In the example described above, the correct information RDT1-1 of the data DT1-1 is information indicating the sales of the store A at the date and time DA11. Further, the data DT1-1 uses the store history information LG11-0, the store history information LG12-0, the weather information WDT10, and the search information SDT10 at the past date and time DA10 corresponding to the correct information RDT1-1 as history information. Including. As described above, the selection device 100 generates a model using information before the date and time corresponding to the correct answer information RDT1-1 as input information. Thereby, the selection apparatus 100 can generate a model that predicts a predicted value of an index related to the business of one store by inputting the current situation.

[2. (Selection process)
An example of the selection process according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of the selection process according to the embodiment. In FIG. 2, the selection device 100 illustrates a case where the coping action is selected based on the predicted sales forecast value at the date and time DA16 and the sales plan value at the date and time DA16. The description of the same points as in FIG. 1 will be omitted as appropriate. The category of the store A is “food” as shown in the store information storage unit 123 in FIG.

  The selection device 100 acquires history information of each store from a plurality of stores. The selection device 100 acquires history information regarding the KPI of the store at the date and time DA15. For example, the selection device 100 acquires history information related to the sales of the store A, the number of visitors, the number of inquiries, etc. at the date DA15.

  Selection device 100 acquires history information of A store from A store (Step S21-1). The selection apparatus 100 acquires the history information of the store A from the store terminal 20 of the store SH11 (store A) in the map information MP1 of FIG. For example, the selection device 100 acquires store history information LG11 including the number of visitors corresponding to each date and time from the A store. In the example of FIG. 2, the selection apparatus 100 acquires store history information LG11-5 corresponding to the date and time DA15 from the A store.

  Moreover, the selection apparatus 100 acquires the historical information of B store from B store (step S21-2). The selection apparatus 100 acquires the history information of the B store from the store terminal 20 of the store SH12 (B store) in the map information MP1 of FIG. For example, the selection device 100 acquires store history information LG12 including the number of visitors corresponding to each date and time from the store A. In the example of FIG. 2, the selection apparatus 100 acquires store history information LG12-5 corresponding to the date and time DA15 from the B store.

  Hereinafter, when it demonstrates without distinguishing step S21-1 and S21-2, it will be named step S21 generically. Moreover, not only step S21-1 and S21-2 but information acquisition from each store may be performed in multiple times. Note that the selection device 100 may use information of a large number of stores (for example, 100 stores, 1000 stores, etc.) as well as the B store for stores other than the A store to be predicted.

  Further, the selection device 100 acquires history information including weather information and user related information from the service providing device 50 (step S22). For example, the selection device 100 acquires the history information LG25 including the weather information WDT15 and the search information SDT15 corresponding to the date and time DA15 from the service providing device 50. For example, the selection apparatus 100 acquires weather information related to the position of the store A as weather information. For example, the selection device 100 acquires the weather information of the area A corresponding to each date and time as the weather information related to the position of the store A. Weather information WDT15 and search information SDT15 are acquired.

  For example, the selection apparatus 100 acquires information such as search information indicating user search and purchase information indicating user purchase as user-related information. Moreover, the selection apparatus 100 acquires the number-of-users information which shows the number of users located in the area A where A shop is located as user related information. Note that steps S21 and S22 may be performed at any timing as long as they are before step S23. For example, step S22 may be performed before step S21.

  And the selection apparatus 100 produces | generates the input data which combined the information acquired by step S21, S22 (step S23). In the example of FIG. 2, as shown in the input data list IPD21, the selection device 100 inputs data DT21 including store history information LG11-5 of the A store and store history information LG12-5 of the B store corresponding to the date and time DA15. Generate as data. Further, the selection device 100 generates data DT21 including weather information and user related information before the date and time DA16 as input data. In the example of FIG. 2, as illustrated in the input data list IPD21, the selection device 100 generates data DT1-1 including weather information WDT15 and search information SDT15 as history information as learning data.

  Then, the selection device 100 inputs the data DT21 into the model. In the example of FIG. 2, the selection device 100 calculates a score indicating the sales of the store A at the date and time DA <b> 16 by processing as shown in the processing group PS <b> 21. The selection device 100 inputs the data DT21 to the model M1 (Step S24). Specifically, the selection device 100 inputs history information including store history information LG11-5, LG12-5, weather information WDT15, search information SDT15, and the like to the model M1. The model M1 to which the data DT21 is input outputs a score (step S25). In the example of FIG. 2, the model M1 to which the data DT21 is input outputs the score SC16. For example, the score SC16 may be a value indicating a sales level such as “0.2” or “0.3”. The score SC16 may be a sales value such as “20000” or “30000”.

  Then, the selection device 100 predicts the sales forecast value for the date and time DA16 based on the score indicating the sales of the store A at the date and time DA16 (step S26). For example, the selection device 100 predicts the sales forecast value for the date and time DA16 by using a correspondence table indicating the correspondence between each level and sales. In the example of FIG. 2, the selection device 100 predicts the sales forecast value PV16 of the date and time DA16 using a correspondence table indicating the correspondence between each level and sales, as shown in the forecast list PL11. For example, when the score SC16 is “0.2”, the selection device 100 uses the correspondence table indicating the correspondence between each level and the sales, and the sales of the store A predicted for the date and time DA16 is 20,000 yen (for example, Forecast sales value PV16). Note that the above is an example, and the selection apparatus 100 may predict (calculate) the sales forecast value PV16 using various information as appropriate.

  Then, the selection device 100 calculates the difference between the sales plan value and the sales prediction value for the date and time DA16 (step S27). In the example of FIG. 2, as shown in the plan list CL <b> 11, the selection device 100 determines from the index information storage unit 124 (see FIG. 8) that the sales plan value at the date and time DA <b> 16 of store A is the sales plan value CV <b> 16. Get the information shown. Then, as illustrated in the deviation list DL11, the selection device 100 calculates that the difference between the sales plan value CV16 and the sales forecast value PV16 is the difference DF11. For example, the selection device 100 calculates the difference by comparing the sales plan value with the sales forecast value. For example, the selection device 100 calculates the difference DF11 by subtracting the sales forecast value PV16 from the sales plan value CV16. In this case, when the sales forecast value is smaller than the sales plan value, the difference is a positive value, and when the sales forecast value is larger than the sales plan value, the difference is a negative value. For example, if the difference is a positive value, the selection device 100 can determine that there is a high possibility that future sales will not reach the planned level. In the example of FIG. 2, it is assumed that the sales forecast value PV16 is smaller than the sales plan value CV16. For example, the sales forecast value PV16 may be 20,000 yen, and the sales plan value CV16 may be 50,000 yen.

  Then, the selection device 100 determines whether or not the difference DF11 indicating the deviation between the sales plan value CV16 and the sales forecast value PV16 satisfies the condition (step S28). For example, the selection device 100 uses the condition corresponding to the category “food” and the index “sales” of the store A among the information stored in the coping behavior storage unit 125 in FIG. Determine whether or not. For example, the selection device 100 determines which divergence condition among the divergences in the target “food” and the index “sales” stored in the coping behavior storage unit 125 in FIG. For example, in the coping behavior storage unit 125 in FIG. 1, the coping behavior (coping behavior AT1) identified by the coping behavior ID “AT1” indicates “advertisement delivery”. The coping behavior AT1 may be various behaviors that increase the bid amount of the advertisement, increase the number of times the advertisement is distributed, or increase the exposure of the advertisement at the store A.

  In the example of FIG. 2, the selection apparatus 100 determines that the difference DF11 is larger than the condition value SP2 and smaller than the condition value SP3 by comparing the difference DF11 with the condition values SP1 to SP3 and the like. In this case, the selection device 100 determines that the divergence between the planned value and the predicted value of the sales of the store A satisfies the divergence condition of the condition value SP2.

  Then, the selection device 100 selects a coping action based on the difference between the planned value and the predicted value (step S29). The selection device 100 selects one measure as a coping action from among a plurality of measures related to the improvement in sales of the store A according to the degree of deviation between the planned value and the predicted value. For example, the selection device 100 selects one coping behavior among the coping behaviors AT1 to AT3 related to the sales improvement of the store A according to the degree of deviation between the planned value and the predicted value. In the example of FIG. 2, the selection device 100 selects the coping action AT2 corresponding to the condition value SP2 because the difference between the planned value and the predicted value of the sales of the store A satisfies the condition of the difference of the condition value SP2.

  Then, the selection device 100 executes the selected coping action (Step S30). In the example of FIG. 2, the selection device 100 requests the service providing device 50 to execute coupon distribution to a user located in the area A where the A store is located.

  And the service provision apparatus 50 requested | required to perform the coupon delivery to the user located in the area A from the selection apparatus 100 delivers the coupon of A store to the user's terminal device 10 according to each user's position. (Step S31). In the example of FIG. 2, the service providing device 50 distributes the coupon of the store A to the terminal device 10 of the user U1 located in the area A. Thereby, the selection system 1 can give the user U1 the motivation to purchase a product at the store A, and can eliminate the sales divergence at the store A.

  As described above, the selection device 100 predicts the sales of the store A on the date and time of the prediction based on the history information before the date and time of the prediction. In the example of FIG. 2, the selection apparatus 100 causes the model M1 to output a score related to the sales of the store A by inputting the history information into the model M1. And the selection apparatus 100 estimates the sales of A store based on the score which the model M1 outputs. Then, the selection device 100 selects a coping action based on the difference between the predicted sales forecast value and the sales plan value. Thereby, the selection apparatus 100 can enable an appropriate action for a predetermined business operator. Moreover, since the selection apparatus 100 determines whether or not a deviation occurs based on the predicted information, it is possible to eliminate a time lag until an actual measurement value is determined. In other words, the selection device 100 determines which action (the coping action) at the stage where it is predicted that a divergence may occur based on the planned value and the predicted value before the actual divergence based on the planned value and the actually measured value is calculated. ) Can be selected. Therefore, the selection device 100 can select which action (coping action) to take without waiting for the confirmation of the actual measurement value. Therefore, the selection apparatus 100 can reduce the time lag and can act on a predetermined store at an appropriate timing. When the predicted value exceeds the planned value, the selection device 100 selects a coping action that suppresses the improvement of the index value, such as reducing the bid amount of the advertisement or reducing the number of advertisements to be delivered. By doing so, you may select the coping action that a prediction value corresponds as much as possible with a plan value.

[2-1. (Execution subject)
In the above example, the selection device 100 requests the service providing device 50 based on the selected coping behavior, and the service providing device 50 performs the coping behavior. However, the selection device 100 performs the coping behavior. You may go. In the example of FIG. 2, the selection device 100 may distribute a coupon to a user located in the area A. The selection device 100 may transmit the coupon of the store A to the terminal device 10 of the user U1 located in the area A. In this way, the coping action selected by the selection device 100 may be performed by the selection device 100 itself, or may be performed by a device other than the selection device 100 such as the service providing device 50.

[2-2. (Use of information between stores)
For example, the selection device 100 may perform the selection process based on the predicted sales value only for stores that are permitted to provide information on other stores. For example, the selection device 100 may acquire information indicating whether or not each store is permitted to use information on its own store (information provision) for predicting an index of another store from each store. For example, the selection apparatus 100 may acquire information indicating whether or not the A store is permitted to use the information of the A store for prediction of an index of another store such as the B store or the C store from the A store. . In this case, the selection apparatus 100 may perform the selection process only on a store (permitted store) permitted to provide information to other stores. For example, the selection device 100 uses the information of one authorized store and the information of another authorized store for one authorized store that has permitted the provision of information to another store, and the predicted value of the index of the one authorized store And the selection process may be performed. Thereby, the selection apparatus 100 promotes that each store provides information, enables information collection from a large number of authorized stores, and improves the prediction accuracy by using the information. Therefore, the selection apparatus 100 can improve the quality of the provided service.

  In the example of FIG. 1, in the prediction for the A store located in the area A, the store information of the B store located in the area A, the weather information of the area A, and the like are used as the history information. However, the history information is not limited to the information of area A, and information of various areas may be used. For example, the selection device 100 may predict the predicted value of the store A located in the area A using the weather information of other areas other than the area A and the store information of stores located in other areas. For example, the selection device 100 may predict the predicted value of the A store located in the area A using the weather information of the area adjacent to the area A (adjacent area) or the store information of the store located in the adjacent area. . For example, when the prediction device 100 predicts a predicted value of a store that sells medicine (pharmacy PHA), the selection device 100 is located in an area adjacent to the area where the pharmacy PH is located, and the other stores (pharmacy PHB) that sell the medicine Store information may be used. For example, when predicting sales of a cold medicine at a store (pharmacy PHA) that sells medicines, the selection apparatus 100 may use the sales information of the cold medicine of the pharmacy PHB located in an area adjacent to the area of the pharmacy PH. Thereby, for example, if the cold medicine is sold in the adjacent area (neighboring town) of the area where the store to be predicted is located, the selection device 100 may be sold in the store to be predicted. However, it can be predicted appropriately. Note that the above is an example, and the selection device 100 may perform prediction using information of various areas.

[2-3. About selection of coping behavior (action)
In the example of FIG. 1, in order to simplify the explanation, the selection device 100 takes measures based on a comparison between a deviation (difference) between the planned value and the predicted value and a deviation (reference) associated with each coping action. The case of selecting an action is shown. However, the selection device 100 may select the coping action by various processes using information on the difference (difference) between the planned value and the predicted value. For example, the selection device 100 may select the coping action using a model that receives information on the difference (difference) between the planned value and the predicted value. For example, the selection device 100 may select the coping action using a model that receives information on the deviation (difference) between the planned value and the predicted value, and weather information related to the weather and information related to other elements. For example, when the information on the difference (difference) between the planned value and the predicted value, and the weather information related to the weather and information related to other elements are input, the selection device 100 takes a coping action (action) corresponding to the input information. ) May be used to select a coping action.

  Moreover, the selection apparatus 100 outputs the score corresponding to the input information, when the information on the deviation (difference) between the planned value and the predicted value, and the weather information related to the weather and information related to other elements are input. The model may be used to select a coping action. For example, the selection device 100 may select a coping action using a list that associates a score (reference value) with a coping action (action). For example, the selection device 100 may select a coping action by comparing a score output from a model in which weather information related to weather or information related to other elements is input with a score (reference value) of a list. For example, the selection device 100 may select a coping action associated with a score (reference value) corresponding to the score output by the model from the list. Further, the selection device 100 may update (generate) the model through reinforcement learning based on the coping action selected and executed and the subsequent change in the index value. In this way, the selection device 100 may select a coping action (action) that maximizes the effect by referring to other factors such as weather in addition to the degree of divergence, or may present it to the operator. Note that the above is an example, and the selection apparatus 100 may select a coping action (action) using various models and other information.

[3. Configuration of selection device)
Next, the configuration of the selection apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram illustrating a configuration example of the selection device according to the embodiment. As illustrated in FIG. 4, the selection device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The selection device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the selection device 100, and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network N in a wired or wireless manner, and transmits and receives information to and from external devices such as the terminal device 10, the store terminal 20, and the service providing device 50.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 4, the storage unit 120 according to the embodiment includes a learning data storage unit 121, a model information storage unit 122, a store information storage unit 123, an index information storage unit 124, and a coping behavior information storage unit 125. And have.

(Learning data storage unit 121)
The learning data storage unit 121 according to the embodiment stores various types of information related to learning data. FIG. 5 is a diagram illustrating an example of a learning data storage unit according to the embodiment. For example, the learning data storage unit 121 stores teacher data used for generating a model. The learning data storage unit 121 illustrated in FIG. 5 includes items such as “data ID”, “correct information”, and “history information”. The “history information” includes items such as “A store”, “B store”, “weather information”, and “search information”.

  “Data ID” indicates identification information for identifying data. For example, the data identified by the data ID “DT1-1” corresponds to the data DT1-1 shown in the example of FIG.

  “Correct answer information” indicates correct information corresponding to data identified by the data ID. For example, “correct information” indicates an actual index value corresponding to the data identified by the data ID. For example, “correct answer information” indicates an actual sales value corresponding to the data identified by the data ID. FIG. 5 shows an example in which conceptual information such as “RDT1-1” is stored in “correct answer information”. Actually, sales are actually measured at a predetermined date and time (period) of A store, which is one store. Information indicating a value or a file path name indicating the storage location is stored. For example, the “correct answer information” may be information indicating the level of the actual value of sales.

  The “correct answer information” is not limited to the actual sales value, but may be various information based on the actual sales value. For example, it may be information indicating to which level the measured value of sales in a predetermined period (for example, one day) of the store A corresponds. For example, the “correct information” may be a 10-level level from 0 to 1 when the maximum daily sales of the store A is 100,000 yen. For example, the “correct answer information” is level “0” when the measured value is less than 10,000 yen, and level “0.1” when the measured value is between 10,000 yen and less than 20,000 yen. Also good. The “correct information” is level “0.9” when the measured value is 90,000 yen or more and less than 100,000 yen, and is “1” when the measured value is 100,000 yen or more. Also good. As described above, the “correct information” may be information indicating which level of the plurality of levels corresponds, that is, information indicating sales in stages. In this case, the selection device 100 may store a correspondence table indicating correspondence between each level and sales in the storage unit 120. The model M1 may be a model that outputs a score indicating a level. The selection apparatus 100 may predict the predicted value of sales using the score output by the model M1 and the level correspondence table. For example, when the model M1 to which history information is input outputs a score “0.9”, the selection device 100 may predict the sales as the predicted value “90,000 yen” using the level correspondence table. .

  “A store” in “history information” includes various history information related to the A store at a predetermined date and time (period). For example, “A store” in “history information” includes information related to the business of the A store at a predetermined date and time (period). For example, “A store” in “history information” includes information about the A store at a predetermined date and time (period). For example, “A store” in “history information” includes information such as the sales of A store, the number of visitors, the number of inquiries, etc., at a predetermined date and time (period). FIG. 5 shows an example in which conceptual information such as “LG11-0” is stored in “A store”. Actually, however, history information related to the A store at a predetermined date and time (period) or its Stores the file path name indicating the storage location.

  “B store” in “history information” includes various history information related to the B store at a predetermined date and time (period). For example, “B store” in “history information” includes information related to the business of the B store at a predetermined date and time (period). For example, “B store” in “history information” includes information related to the KPI of the B store at a predetermined date and time (period). For example, “B store” in “history information” includes information such as the sales of B store, the number of visitors, the number of inquiries, etc., at a predetermined date and time (period). FIG. 5 shows an example in which conceptual information such as “LG12-0” is stored in “B store”. Actually, however, history information related to the B store at a predetermined date and time (period), or Stores the file path name indicating the storage location.

  “Meteorological information” in the “history information” indicates weather information of an area related to the position of the store A at a predetermined date and time (period). For example, “meteorological information” in “history information” indicates whether the weather in the area A where the store A is located at a predetermined date and time (period) was “sunny”, “cloudy”, “rainy”, or the like. It may be information. FIG. 5 shows an example in which conceptual information such as “WDT10” is stored in “weather information”, but in reality, address and latitude / longitude information indicating a specific location of the operator, or the storage location thereof The file path name indicating

  “Search information” in “history information” indicates search information included in the history information. For example, the “search information” in the “history information” may be information indicating the number of searches using a query related to the product provided by the store A at the date and time (period). FIG. 5 shows an example in which conceptual information such as “SDT10” is stored in “search information”, but in practice, various information such as the number of searches related to the store A at a predetermined date and time (period), or The file path name indicating the storage location is stored.

  For example, in the example shown in FIG. 5, the data (data DT1-1) identified by the data ID “DT1-1” is store history information LG11-0 of store A or store history information LG12 of store B as history information. -0, weather information WDT10, search information SDT10, etc. are included. Further, the data DT1-1 indicates that the correct answer information RDT1-1 is included. For example, the correct information RDT1-1 of the data DT1-1 is information indicating the actual sales value of the store A at the date and time DA11. The data DT1-1 includes store history information LG11-0, store history information LG12-0 of the store B, weather information WDT10, and search information SDT10 at a date and time DA10 that is earlier than the date and time DA11 corresponding to the correct answer information RDT1-1. Include as history information. As described above, the selection device 100 generates a model using the store history information, the weather information, and the search information on the date and time earlier than the date and time corresponding to the correct answer information RDT1-1 as the history information. Thereby, the selection apparatus 100 can generate a model for predicting future demand by inputting the current store KPI-related status and search status. As for weather information, a weather forecast on the same date and time as the correct answer information may be used. For example, the selection device 100 may use the weather information of the date DA11 as an input when the information indicating the measured value of the sales of the store A at the date DA11 is the correct information. In this case, regarding the weather information, the selection device 100 may use the forecasted weather information of the prediction target date and time as an input based on information such as weather forecast.

  Note that the learning data storage unit 121 is not limited to the above, and may store various information according to the purpose. For example, the learning data storage unit 121 may store information such as number-of-users information indicating the number of users located in the area A where the A store is located and purchase information indicating purchase of the users. For example, the learning data storage unit 121 may store information related to the date and time when learning data was added. Further, for example, the learning data storage unit 121 may store information indicating what kind of determination processing each learning data has been added. For example, the learning data storage unit 121 may store information indicating whether each learning data has been determined by an administrator's selection.

(Model information storage unit 122)
The model information storage unit 122 according to the embodiment stores information related to the model. For example, the model information storage unit 122 stores model information (model data) generated by the generation process. FIG. 6 is a diagram illustrating an example of the model information storage unit according to the embodiment. The model information storage unit 122 illustrated in FIG. 6 includes items such as “model ID”, “use”, and “model data”. In FIG. 6, only the model M1 is illustrated, but a lot of model information such as M2, M3, M4, and M5 may be stored depending on each application (target of prediction).

  Further, each model may be assumed to be used as a program module that is a part of the artificial intelligence software. For example, the model M1 may be assumed to be used as a program module for the usage “sales forecast (A store)”. For example, the model M1 may be assumed to be used as a program module that predicts the sales of the store A. For example, the model data MDT1 may be data used as a program module for the usage “sales forecast (A store)”. For example, the model M1 causes the computer to output a value obtained by quantifying the predicted sales corresponding to the predetermined time point of the store A based on the history information related to each of the plurality of stores before the predetermined time point. .

  “Model ID” indicates identification information for identifying a model. For example, the model identified by the model ID “M1” corresponds to the model M1 illustrated in the example of FIG. “Use” indicates the use of the corresponding model. “Model data” indicates data of a corresponding model associated with the model data. For example, “model data” includes information including nodes in each layer, functions adopted by the nodes, connection relationships between the nodes, and connection coefficients set for connections between the nodes.

  For example, in the example illustrated in FIG. 6, the model (model M1) identified by the model ID “M1” indicates that the usage is “sales prediction (A store)” and is used for the sales prediction of the A store. The model data of the model M1 is model data MDT1.

  The model M1 (model data MDT1) is an input layer to which history information related to each of a plurality of stores before a predetermined time is input, an output layer, or any layer from the input layer to the output layer. A first element belonging to a layer other than the output layer, and a second element whose value is calculated based on the first element and the weight of the first element, and outputs the history information input to the input layer By using each element belonging to each layer other than the layer as the first element and performing a calculation based on the first element and the weight of the first element, the score used for predicting the sales (indicator) at a predetermined time of the store A It is a model for making a computer function so that values are output from an output layer.

  Here, it is assumed that the model M1 or the like is realized by a regression model represented by “y = a1 * x1 + a2 * x2 +... + Ai * xi”. In this case, for example, the first element included in the model M1 corresponds to input data (xi) such as x1 or x2. The weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element can correspond to any node of the input layer, and the second element can be regarded as a node of the output layer.

  Further, it is assumed that the model M1 or the like is realized by a neural network having one or more intermediate layers such as DNN. In this case, for example, the first element included in the model M1 corresponds to any node of the input layer or the intermediate layer. The second element corresponds to the next node, which is a node to which a value is transmitted from the node corresponding to the first element. The weight of the first element corresponds to a connection coefficient that is a weight considered for a value transmitted from a node corresponding to the first element to a node corresponding to the second element.

  The model information storage unit 122 is not limited to the above, and may store various model information according to the purpose.

(Store information storage unit 123)
The store information storage unit 123 according to the embodiment stores various types of information regarding stores (businesses). FIG. 7 is a diagram illustrating an example of the store information storage unit according to the embodiment. For example, the store information storage unit 123 stores information related to various stores. The store information storage unit 123 illustrated in FIG. 7 includes items such as “store ID”, “store name”, “category”, and “location”.

  “Store ID” indicates identification information for identifying a store. “Store name” indicates a specific store name of the store. For example, an abstract name such as “A store” is shown, but “store name” is a specific name such as a combination of a store name such as “XX Cafe X Machi store” and information indicating the location of the store. May be stored. “Category” indicates the category to which the store belongs. “Location” indicates a location where the store is located. Note that “location” is information indicating an abstract code or range such as “area A”, but is information indicating latitude and longitude or information indicating an address such as “Y city Z town” in “X prefecture”. There may be.

  For example, in the example of FIG. 7, the store identified by the store ID “SH11” is the store name “A store” and indicates that the store belongs to the category “food”. Further, for example, in the example of FIG. 7, the store A (store SH11) is located in the area A.

  The store information storage unit 123 is not limited to the above, and may store various information according to the purpose. For example, when the business has a plurality of stores, the store information storage unit 123 may store the stores in association with each business. For example, when the business has a store for each of a plurality of areas, the store information storage unit 123 may store the business in association with the store for each area. For example, when the index of one area is predicted for one business operator, the selection device 100 may use store information associated with one area in the store information storage unit 123. For example, the selection device 100 may generate a model using history information about a store associated with one area. For example, the selection device 100 may perform index prediction using history information regarding a store associated with one area. For example, the store information storage unit 123 may store information indicating whether or not each store permits use of information on its own store (information provision) for prediction of an index of another store. For example, the store information storage unit 123 may store information indicating whether or not the A store is permitted to use the information of the A store for prediction of an index of another store such as the B store or the C store. In this case, the selection apparatus 100 may perform the selection process only on a store (permitted store) permitted to provide information to other stores. For example, the selection device 100 uses the information of one authorized store and the information of another authorized store for one authorized store that has permitted the provision of information to another store, and the predicted value of the index of the one authorized store And the selection process may be performed. Thereby, the selection apparatus 100 promotes that each store provides information, enables information collection from a large number of authorized stores, and improves the prediction accuracy by using the information. Therefore, the selection apparatus 100 can improve the quality of the provided service.

(Indicator information storage unit 124)
The index information storage unit 124 according to the embodiment stores various types of information related to the index. FIG. 8 is a diagram illustrating an example of the index information storage unit according to the embodiment. For example, the index information storage unit 124 stores information related to an index that is a KPI of a store. The index information storage unit 124 illustrated in FIG. 8 includes items such as “store”, “index”, “date / time”, “plan value”, “actual value”, and “predicted value”.

  “Store” indicates a target store. “Indicator” indicates an index that is a target of business planning, information collection, and prediction. “Date and time” indicates the time (date and time) for which information is collected and predicted. “Planned value” indicates the planned value of the index scheduled (planned) for the corresponding day. “Actual measurement value” indicates an actual measurement value of an index actually collected (measured) on the corresponding day. “Predicted value” indicates a predicted value of an index that has been predicted for a corresponding day.

  For example, in the example illustrated in FIG. 8, the index for the A store (store SH11) is “sales”. For the date and time DA10, the planned sales value is the planned sales value CV10, and the actual sales value is the actual sales value MV10. Further, for the date and time DA10, the predicted value is “-”, indicating that the predicted value of sales at the date and time DA10 of the A store is not predicted. For the date and time DA12, the sales plan value is the sales plan value CV12, the sales actual value is the sales actual value MV12, and the sales forecast value is the sales forecast value PV12.

  The index information storage unit 124 is not limited to the above, and may store various information according to the purpose. In the example of FIG. 8, the case where information about an index is stored for each store is shown, but store information may be stored for each index.

(Coping behavior information storage unit 125)
The coping behavior information storage unit 125 according to the embodiment stores various types of information regarding coping behavior. FIG. 9 is a diagram illustrating an example of a coping behavior information storage unit according to the embodiment. For example, the coping behavior information storage unit 125 stores various information such as information indicating the target behavior and determination conditions for the target behavior. The coping action information storage unit 125 illustrated in FIG. 9 includes items such as “target”, “index”, “deviation”, “coping action ID”, and “content”.

  “Target” indicates the category of the target store. “Indicator” indicates an index used for determining whether to select a coping action. “Deviation” indicates a condition (condition value) that is a criterion for determining whether or not to select a target action. “Coping action ID” indicates information for identifying the coping action. “Content” indicates the specific content of the coping action identified by the corresponding coping action.

  For example, in the example illustrated in FIG. 9, the category of the target store is “food” and the index is “sales”. The condition (condition value) for determining the deviation indicates the condition values SP1 to SP3. Further, the condition value SP2 is greater than the condition value SP1, and the condition value SP3 is greater than the condition value SP2.

  When the condition value SP3 is satisfied, that is, when the deviation is equal to or greater than the condition value SP3, the coping action is the target action (target action AT3) identified by the target action ID “AT3”. Further, the target action AT3 indicates that “X% discount” (X is a predetermined numerical value such as 10 or 30), that is, a sale such as X% discount for the price of a product sold in a store.

  In addition, when the condition value SP2 is satisfied, that is, when the deviation is equal to or greater than the condition value SP2, the coping action is the target action (target action AT2) identified by the target action ID “AT2”. Further, the target action AT2 indicates that coupon distribution is performed. Specifically, the target action AT2 indicates that the coupon is distributed to users located in an area corresponding to the store. In addition, when the condition value SP1 is satisfied, that is, when the deviation is equal to or greater than the condition value SP1, the coping action is the target action (target action AT1) identified by the target action ID “AT1”. The target action AT1 indicates that the advertisement is related to the store.

  The coping action information storage unit 125 is not limited to the above, and may store various information according to the purpose. In the example of FIG. 9, the case where information related to an index is stored for each store is shown, but store information may be stored for each index.

(Control unit 130)
Returning to the description of FIG. 4, the control unit 130 is a controller and is stored in a storage device inside the selection device 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of a selection program) are implemented by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The control unit 130 includes an input layer in which history information related to each of a plurality of stores before a predetermined time point is input by an information process according to the model M1 stored in the model information storage unit 122, and an output layer A first element belonging to any layer from the input layer to the output layer and other than the output layer; a second element whose value is calculated based on the first element and the weight of the first element; , And for the history information input to the input layer, each element belonging to each layer other than the output layer is set as the first element, and the calculation based on the first element and the weight of the first element is performed. The score value used for predicting sales at a predetermined time is output from the output layer.

  As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, a generation unit 132, a prediction unit 133, a selection unit 134, and a provision unit 135, and functions and functions of information processing described below. Realize or execute. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 4, and may be another configuration as long as the information processing described below is performed. The control unit 130, by information processing according to the model M1 (model data MDT1) stored in the storage unit 120, a second element whose value is calculated based on the first element and the weight of the first element, And the history information input to the input layer is calculated based on the first element and the weight of the first element, with each element belonging to each layer other than the output layer as the first element. A score value used for forecasting sales at a predetermined time is output from the output layer.

(Acquisition part 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various types of information from the learning data storage unit 121, the model information storage unit 122, the store information storage unit 123, the index information storage unit 124, the coping behavior information storage unit 125, and the like. The acquisition unit 131 may acquire various types of information from an external information processing apparatus. Moreover, the acquisition part 131 may acquire various information from the store terminal 20 grade | etc.,.

  The acquisition unit 131 acquires learning data as shown in the learning data storage unit 121. For example, the acquisition unit 131 acquires learning data including the data DT1-1 to DT1 to 4 from the learning data storage unit 121.

  The acquisition unit 131 acquires a planned value of an index related to the business of one business operator and corresponding to a predetermined time point. The acquisition unit 131 acquires history information related to one operator. The acquisition unit 131 acquires a plan value of an index related to the business of one operator, the plan value corresponding to a predetermined time point, and history information related to the one business operator before the predetermined time point. . The acquisition unit 131 acquires a plan value of an index related to the business of one store, the plan value corresponding to a predetermined time point, and history information related to each of a plurality of stores before the predetermined time point. . The acquisition unit 131 acquires a model that outputs a score indicating a predicted value of one operator at a predetermined time point in response to input of history information. The acquisition unit 131 acquires a model that outputs a score indicating a predicted value of one store at a predetermined time in response to input of history information.

  The acquisition unit 131 acquires history information of a plurality of business operators including one business operator. The acquisition unit 131 acquires history information of a plurality of stores including one store. The acquisition unit 131 acquires history information including a user's behavior history before a predetermined time point. The acquisition unit 131 acquires history information including user behavior history on the Internet. The acquisition unit 131 acquires history information including a search history by the user. The acquisition unit 131 acquires history information including a purchase history by the user. The acquisition unit 131 acquires history information including information related to the number of users in an area corresponding to one provider based on the user location information. The acquisition unit 131 acquires history information including information related to the number of users in an area corresponding to one store based on the user location information. The acquisition unit 131 acquires history information including weather information of an area corresponding to one operator. The acquisition unit 131 acquires history information including weather information of an area corresponding to one store.

  For example, the acquisition unit 131 acquires sales plan information including sales plan values CV10 to CV16 corresponding to the dates and times DA10 to DA16 as shown in the index information storage unit 124 (see FIG. 8). For example, the acquisition unit 131 acquires the sales plan information from the store terminal 20 (see FIG. 3) of the store A and stores it in the index information storage unit 124 (see FIG. 8).

  The acquisition unit 131 acquires history information of each store from a plurality of stores. The acquisition unit 131 acquires history information regarding the KPI of the store at each date and time (period). For example, the acquisition unit 131 acquires history information relating to sales at the A store, the number of visitors, the number of inquiries, and the like at each date and time (period).

  In the example of FIG. 1, the acquisition unit 131 acquires history information of A store from A store. The acquisition unit 131 acquires the history information of the A store from the store terminal 20 of the A store. For example, the acquisition unit 131 acquires store history information LG11 including the number of visitors corresponding to each date and time from the A store. In the example of FIG. 1, the acquisition unit 131 acquires store history information LG11-0 to LG11-3 corresponding to the dates DA10 to DA13 from the A store.

  Moreover, the acquisition part 131 acquires the historical information of B store from B store. The acquisition unit 131 acquires the history information of the B store from the store terminal 20 of the B store. For example, the acquisition unit 131 acquires store history information LG12 including the number of visitors corresponding to each date and time from the A store. In the example of FIG. 1, the acquisition unit 131 acquires store history information LG12-0 to LG12-3 corresponding to the dates DA10 to DA13 from the B store.

  Moreover, the acquisition part 131 acquires correct information from A store. The acquisition unit 131 acquires correct information from the store terminal 20 of the A store. For example, the acquisition unit 131 acquires correct information RDT1 indicating actual measurement values corresponding to each date and time from the A store. In the example of FIG. 1, the acquisition unit 131 acquires correct information RDT1-1 to RDT1-4 corresponding to the dates and times DA11 to DA14 from the store A.

  Further, the acquisition unit 131 acquires history information including weather information and information on user behavior (hereinafter also referred to as “user related information”) from the service providing apparatus 50. For example, the acquisition unit 131 acquires history information LG21 corresponding to each date and time from the service providing apparatus 50. In the example of FIG. 1, the acquisition unit 131 acquires history information LG21 including weather information and user-related information corresponding to the dates DA10 to DA13 from the service providing apparatus 50.

  For example, the acquisition unit 131 acquires weather information related to the position of the store A as weather information. For example, the acquisition unit 131 acquires the weather information of the area A corresponding to each date and time as the weather information related to the position of the store A.

  For example, the acquisition unit 131 acquires information such as search information indicating user search and purchase information indicating user purchase as user-related information. Note that the purchase information may be purchase information related to a product sold by the A store or a related product of the product. Moreover, the acquisition part 131 acquires the number-of-users information which shows the number of users located in the area A where A shop is located as user related information.

  In the example of FIG. 2, the acquisition unit 131 acquires history information of each store from a plurality of stores. The acquisition unit 131 acquires history information regarding the KPI of the store at the date and time DA15. For example, the acquisition unit 131 acquires history information regarding the sales of the A store, the number of visitors, the number of inquiries, and the like at the date DA15.

  The acquisition unit 131 acquires the history information of the A store from the A store. The acquisition unit 131 acquires the history information of the A store from the store terminal 20 of the A store. For example, the acquisition unit 131 acquires store history information LG11 including the number of visitors corresponding to each date and time from the A store. In the example of FIG. 2, the acquisition unit 131 acquires store history information LG11-5 corresponding to the date and time DA15 from the A store.

  Moreover, the acquisition part 131 acquires the historical information of B store from B store. The acquisition unit 131 acquires the history information of the B store from the store terminal 20 of the B store. For example, the acquisition unit 131 acquires store history information LG12 including the number of visitors corresponding to each date and time from the A store. In the example of FIG. 2, the acquisition unit 131 acquires store history information LG12-5 corresponding to the date and time DA15 from the B store.

  Further, the acquisition unit 131 acquires history information including weather information and user-related information from the service providing device 50. For example, the acquisition unit 131 acquires the history information LG25 including the weather information WDT15 and the search information SDT15 corresponding to the date and time DA15 from the service providing apparatus 50. For example, the acquisition unit 131 acquires weather information related to the position of the store A as weather information. For example, the acquisition unit 131 acquires the weather information of the area A corresponding to each date and time as the weather information related to the position of the store A. Weather information WDT15 and search information SDT15 are acquired.

  For example, the acquisition unit 131 acquires information such as search information indicating user search and purchase information indicating user purchase as user-related information. Moreover, the acquisition part 131 acquires the number-of-users information which shows the number of users located in the area A where A shop is located as user related information. Further, as shown in the plan list CL11, the acquisition unit 131 acquires information indicating that the planned value of sales at the date and time DA16 of the store A is the sales planned value CV16 from the index information storage unit 124 (see FIG. 8). To do.

(Generator 132)
The generation unit 132 generates various types of information. For example, the generation unit 132 generates a model as shown in the model information storage unit 122 using the learning data stored in the learning data storage unit 121. For example, the generation unit 132 generates a model used for prediction of demand related to a business object of a predetermined operator based on various information acquired by the acquisition unit 131. For example, the generation unit 132 generates a model used for prediction of demand related to a business object of a predetermined operator based on the learning data acquired by the acquisition unit 131. For example, the generation unit 132 uses the learning data including history information before a predetermined time point and correct information indicating the sales performance value of one store at the predetermined time point (actual sales actual value). A model used for prediction of sales (index) corresponding to a predetermined point in time of the store is generated.

  For example, the generation unit 132 generates a model M1 and the like, and stores the generated model M1 and the like in the model information storage unit 122. Note that the generation unit 132 may generate the model M1 or the like using any learning algorithm. For example, the generation unit 132 generates a model M1 and the like using a learning algorithm such as a neural network, a support vector machine (SVM), clustering, and reinforcement learning. As an example, when the generation unit 132 generates a model M1 or the like using a neural network, the model M1 or the like includes an input layer including one or more neurons, an intermediate layer including one or more neurons, and one or more neurons. Including an output layer.

  The generation unit 132 generates a model and stores the generated model in the model information storage unit 122. Specifically, the generation unit 132 is an input layer to which history information related to each of a plurality of stores before a predetermined time is input, an output layer, or any layer from the input layer to the output layer. A first element belonging to a layer other than the output layer, and a second element whose value is calculated based on the first element and the weight of the first element, and for history information input to the input layer, By using each element belonging to each layer other than the output layer as the first element and performing a calculation based on the first element and the weight of the first element, the score value used for predicting the sales at a predetermined point in time at the store A Generate a model to be output from the output layer.

  In the example of FIG. 1, the generation unit 132 generates learning data in which the actual sales values (sales actual sales values) such as the respective dates and times DA11 to DA14 included in the correct information RDT1 are correct information RDT1-1 to RDT1-4. . For example, the generation unit 132 adds learning data to the learning data storage unit 121.

  The generation unit 132 generates data DT1-1 including the correct answer information RDT1-1 indicating the sales actual value of the store A at the date and time DA11 as learning data. Moreover, the production | generation part 132 produces | generates data DT1-1 including the store history information of A store and B store before the date DA11 as learning data. In the example of FIG. 1, the generation unit 132 generates data DT1-1 including the store history information LG11-0 of the A store corresponding to the date and time DA10 and the store history information LG12-0 of the B store as learning data. Moreover, the production | generation part 132 produces | generates data DT1-1 including the weather information and user relevant information before the date DA11 as learning data. In the example of FIG. 1, the generation unit 132 generates, as learning data, data DT <b> 1-1 including the weather information WDT <b> 10 and the search information SDT <b> 10 at the date and time DA10 that is earlier than the date and time DA <b> 11 as history information.

  Further, for example, the generation unit 132 generates data DT1-2 including the correct information RDT1-2 indicating the sales actual value of the store A at the date and time DA12 as learning data. Moreover, the production | generation part 132 produces | generates data DT1-2 including the store history information of A store and B store before the date DA12 as learning data. In the example of FIG. 1, the generation unit 132 generates data DT1-2 including the store history information LG11-1 of the A store corresponding to the date and time DA11 and the store history information LG12-1 of the B store as learning data. In addition, the generation unit 132 generates data DT1-2 including weather information and user-related information before the date and time DA12 as learning data. In the example of FIG. 1, the generation unit 132 generates, as learning data, data DT1-2 including, as history information, weather information WDT11 and search information SDT11 at a date and time DA11 earlier than the date and time DA12 in the history information LG21.

  In the example of FIG. 1, the generation unit 132 generates a model based on the learning data. For example, the generation unit 132 generates a model based on the learning data. For example, the generation unit 132 generates a model by performing learning using the data DT1-1 to DT1-4 in the learning data storage unit 121 as learning data (teacher data). The generation unit 132 generates a model by using store history information, weather information, and user-related information at a date before the date corresponding to each correct answer information as history information.

  The generation unit 132 generates a model M1 using learning data as shown in the learning data storage unit 121. For example, when the correct information RDT1-1 is “1” indicating that the sales were 100,000 yen or more, the generation unit 132 receives the history information included in the data DT1-1 in the model M1. The learning process is performed so that the score output by the model M1 approaches “1”. For example, when the store history information LG11-0, the store history information LG12-0, the weather information WDT10, and the search information SDT10 of the data DT1-1 are input to the model M1, the generation unit 132 generates a score output by the model M1. The learning process is performed so as to approach “1”.

  In addition, when the correct information RDT1-2 is “0.5” indicating that the sales were 50,000 yen, the generation unit 132 receives the history information included in the data DT1-2 as the model M1. In addition, the learning process is performed so that the score output from the model M1 approaches “0.5”. For example, when the store history information LG11-1, the store history information LG12-1, the weather information WDT11, and the search information SDT11 of the data DT1-2 are input to the model M1, the generation unit 132 generates a score output by the model M1. The learning process is performed so as to approach “0.5”.

  The generation unit 132 generates input data obtained by combining the information acquired by the acquisition unit 131. In the example of FIG. 2, the generation unit 132 inputs the data DT21 including the store history information LG11-5 of the A store and the store history information LG12-5 of the B store corresponding to the date DA15 as shown in the input data list IPD21. Generate as data. Further, the generation unit 132 generates data DT21 including weather information and user-related information before the date and time DA16 as input data. As shown in the input data list IPD21, the generation unit 132 generates data DT1-1 including the weather information WDT15 and the search information SDT15 as history information as learning data.

(Prediction unit 133)
The prediction unit 133 predicts various types of information. The prediction unit 133 uses various information stored in the learning data storage unit 121, the model information storage unit 122, the store information storage unit 123, the index information storage unit 124, the coping action information storage unit 125, and the like. Predict information. For example, the prediction unit 133 predicts various types of information based on various types of information acquired by the acquisition unit 131.

  Based on the history information acquired by the acquisition unit 131, the prediction unit 133 predicts a prediction value of an index related to the business of one operator and corresponding to a predetermined time point. Based on the history information acquired by the acquisition unit 131, the prediction unit 133 predicts a prediction value of an index related to the business of one store and corresponding to a predetermined time point. The prediction unit 133 inputs history information to the model, and predicts a predicted value of one operator at a predetermined time based on the score output by the model. The prediction unit 133 inputs history information to the model, and predicts a predicted value of one store at a predetermined time based on the score output by the model.

  The prediction unit 133 predicts a predicted value of one store at a predetermined time using history information of a plurality of stores including the one store. The prediction unit 133 predicts a predicted value of one store at a predetermined time using history information including a user's action history before the predetermined time. The prediction unit 133 predicts a predicted value of one store at a predetermined point in time using history information including a user's action history on the Internet. The prediction unit 133 predicts a predicted value of one store at a predetermined point in time using history information including a search history by the user. The prediction unit 133 predicts a predicted value of one store at a predetermined time using history information including a purchase history by the user. The prediction unit 133 predicts a predicted value of one store at a predetermined point in time using history information including information on the number of users in an area corresponding to one store based on the user location information. The prediction unit 133 predicts a predicted value of one store at a predetermined time using history information including weather information of an area corresponding to one store.

  In the example of FIG. 2, the prediction unit 133 inputs data DT21 into the model. The prediction unit 133 calculates a score indicating the sales of the store A at the date and time DA16 by the process as shown in the process group PS21. The prediction unit 133 inputs the data DT21 to the model M1. The prediction unit 133 inputs history information including store history information LG11-5, LG12-5, weather information WDT15, search information SDT15, and the like to the model M1. The model M1 to which the data DT21 is input outputs a score. The prediction unit 133 predicts the sales forecast value for the date DA16 based on the score indicating the sales of the store A at the date DA16. The predicting unit 133 predicts the sales forecast value for the date and time DA16 using a correspondence table indicating the correspondence between each level and sales. In the example of FIG. 2, as shown in the prediction list PL11, the sales forecast value PV16 of the date and time DA16 is predicted using a correspondence table showing the correspondence between each level and sales. For example, when the score SC16 is “0.2”, the selection device 100 uses the correspondence table indicating the correspondence between each level and the sales, and the sales of the store A predicted for the date and time DA16 is 20,000 yen (for example, Forecast sales value PV16).

  For example, the prediction unit 133 calculates a score using a model having an arbitrary structure such as the above-described regression model or neural network. Specifically, the model M1 predicts a predetermined target when history information related to each of a plurality of stores before a predetermined point in time (that is, each element used for calculating the score described above) is input. The coefficient is set so as to output a value obtained by quantifying (that is, a score suggesting how much sales at a predetermined time point of the store A are). The prediction unit 133 uses such a model M1 to calculate a score relating to the predicted value of sales at a predetermined point in the store A.

  In the above example, when the history information related to each of the plurality of stores before the predetermined time point is input, the model M1 is a value obtained by quantifying the prediction of sales at the predetermined time point of the A store (predicted value). ) Is shown as an example model. However, the model (model X) according to the embodiment may be a model generated based on a result obtained by repeatedly inputting / outputting data to / from the model M1. For example, the model X may be a model (model Y) learned to receive history information related to each of a plurality of stores before a predetermined point in time and output a score output from the model M1. Alternatively, the model M1 may be a model learned so that history information related to each of a plurality of stores before a predetermined point in time is input and the output value of the model Y is output. When the prediction unit 133 performs a prediction process using GAN (Generative Adversarial Networks), the model M1 may be a model that constitutes a part of the GAN.

(Selection unit 134)
The selection unit 134 selects various information. The selection unit 134 uses various information stored in the learning data storage unit 121, the model information storage unit 122, the store information storage unit 123, the index information storage unit 124, the coping action information storage unit 125, and the like. Select information. For example, the selection unit 134 can select various information from information stored in the learning data storage unit 121, the model information storage unit 122, the store information storage unit 123, the index information storage unit 124, the coping action information storage unit 125, and the like. Select the information.

  When the deviation between the predicted value predicted by the prediction unit 133 and the planned value satisfies a predetermined condition, the selection unit 134 selects a coping action that is an action for dealing with the deviation. The selection unit 134 determines whether the deviation satisfies a predetermined condition by comparing the planned value and the predicted value, and selects a coping action when it is determined that the predetermined condition is satisfied. The selection unit 134 selects a coping action when the difference between the planned value and the predicted value is equal to or greater than a predetermined threshold value. The selection unit 134 selects one coping behavior among a plurality of coping behaviors related to the improvement of one operator's index according to the degree of deviation between the planned value and the predicted value. The selection unit 134 selects one coping action among a plurality of coping actions related to the improvement of the index of one store according to the degree of deviation between the planned value and the predicted value.

  In the example of FIG. 2, the selection unit 134 calculates the difference between the sales plan value and the sales prediction value for the date and time DA16. As shown in the deviation list DL11, the selection unit 134 calculates that the difference between the sales plan value CV16 and the sales forecast value PV16 is the difference DF11. For example, the selection unit 134 calculates the difference DF11 by subtracting the sales forecast value PV16 from the sales plan value CV16.

  The selection unit 134 determines whether or not the difference DF11 indicating the deviation between the sales plan value CV16 and the sales forecast value PV16 satisfies the condition. For example, the selection unit 134 uses the condition corresponding to the category “food” and the index “sales” of the store A among the information stored in the coping behavior storage unit 125 in FIG. Determine whether or not. For example, the selection unit 134 determines which divergence condition among the divergences in the target “food” and the index “sales” stored in the coping behavior storage unit 125 in FIG.

  The selection unit 134 selects one coping action among a plurality of coping actions according to the degree of deviation between the planned value and the predicted value. The selection unit 134 selects one measure as a coping action among a plurality of measures related to the improvement of the index of one store according to the degree of deviation between the planned value and the predicted value. For example, the selection unit 134 selects one measure from the coping behaviors AT1 to AT3 as the coping behavior according to the difference between the plan value and the predicted value. For example, when the difference between the planned value and the predicted value is equal to or greater than the condition value SP3, the selection unit 134 selects the X% discount (the coping action AT3) that is one of the coping actions AT1 to AT3. For example, when the difference between the planned value and the predicted value is smaller than the condition value SP3 and greater than or equal to the condition value SP2, the selection unit 134 distributes a coupon distribution (coping action AT2), which is one of the coping actions AT1 to AT3. select. For example, when the difference between the planned value and the predicted value is smaller than the condition value SP2 and greater than or equal to the condition value SP1, the selection unit 134 performs advertisement distribution (handling action AT1) as one of the countermeasure actions AT1 to AT3. select.

  In the example of FIG. 2, the selection unit 134 determines that the difference DF11 is greater than the condition value SP2 and smaller than the condition value SP3 by comparing the difference DF11 with the condition values SP1 to SP3 and the like. In this case, the selection unit 134 determines that the divergence between the planned value and the predicted value of the sales of the store A satisfies the divergence condition of the condition value SP2. Then, the selection unit 134 selects a coping action based on the difference between the planned value and the predicted value. In the example of FIG. 2, the selection unit 134 selects the coping action AT2 corresponding to the condition value SP2 because the difference between the planned value and the predicted value of the sales of the store A satisfies the condition of the difference of the condition value SP2.

(Providing unit 135)
The providing unit 135 provides various services. For example, the providing unit 135 provides various types of information. For example, the providing unit 135 transmits various types of information to the user terminal device 10. For example, the providing unit 135 transmits various information to the store terminal 20. For example, the providing unit 135 transmits various types of information to the service providing apparatus 50.

  For example, the providing unit 135 provides various services based on the coping behavior selected by the selecting unit 134. For example, when the coping action selected by the selection unit 134 is provision of information to the user's terminal device 10, the provision unit 135 provides an information provision service to the terminal device 10. For example, the providing unit 135 distributes (transmits) an advertisement to the terminal device 10 when the coping action selected by the selection unit 134 is an advertisement distribution to the user's terminal device 10. For example, the providing unit 135 distributes (transmits) a coupon such as a discount to the terminal device 10 when the coping action selected by the selection unit 134 is coupon distribution such as a discount to the user's terminal device 10. For example, the providing unit 135 provides an information providing service to the store terminal 20 when the coping action selected by the selecting unit 134 is providing information to the store terminal 20 of the store. For example, when the coping action selected by the selection unit 134 is a sale execution such as a discount, the providing unit 135 distributes (transmits) information requesting the sale to be executed to the store terminal 20.

  In addition, when the service providing device 50 provides information to the terminal device 10 or the store terminal 20, the providing unit 135 provides information indicating the coping behavior selected by the selecting unit 134 to the service providing device 50. For example, when the coping action selected by the selection unit 134 is information provision to the user terminal device 10, the provision unit 135 requests the service provision device 50 to perform an information provision service to the terminal device 10. For example, when the coping action selected by the selection unit 134 is an advertisement distribution to the user's terminal device 10, the providing unit 135 provides information that requests the terminal device 10 to distribute (send) the advertisement to the service unit. Transmit to device 50. For example, when the coping action selected by the selection unit 134 is distribution of a coupon such as a discount to the user's terminal device 10, the providing unit 135 requests that the coupon such as a discount be distributed (transmitted) to the terminal device 10. Information to be transmitted to the service providing apparatus 50. For example, the providing unit 135 requests the service providing apparatus 50 to perform an information providing service to the store terminal 20 when the coping action selected by the selecting unit 134 is providing information to the store terminal 20 of the store. To do. For example, when the coping action selected by the selection unit 134 is a sale execution such as a discount, the providing unit 135 requests the store terminal 20 to distribute (transmit) information requesting the sale to be executed. Information is transmitted to the service providing apparatus 50.

  In the example of FIG. 2, the providing unit 135 executes the coping action selected by the selecting unit 134. In the example of FIG. 2, the providing unit 135 requests the service providing apparatus 50 to execute coupon distribution to a user located in the area A where the A store is located. The providing unit 135 transmits request information for requesting the service providing apparatus 50 to the service providing apparatus 50 so as to execute coupon distribution to a user located in the area A where the A store is located.

[4. Generation process flow)
Next, the procedure of the generation process by the selection system 1 according to the embodiment will be described using FIG. FIG. 10 is a flowchart illustrating an example of the generation process according to the embodiment.

  As illustrated in FIG. 10, the selection device 100 acquires learning data (step S101). For example, the selection device 100 acquires learning data from the learning data storage unit 121.

  Thereafter, the selection device 100 generates a model based on the learning data (step S102). In the example of FIG. 1, the selection device 100 generates a model M <b> 1 using learning data from the learning data storage unit 121.

[5. (Selection process flow)
Next, a generation process procedure performed by the selection system 1 according to the embodiment will be described with reference to FIG. FIG. 11 is a flowchart illustrating an example of the selection process according to the embodiment.

  As illustrated in FIG. 11, the selection device 100 acquires history information (step S201). In the example of FIG. 2, the selection device 100 acquires the history information LG11-5 at the date and time DA15 from the store A. In the example of FIG. 2, the selection device 100 acquires store history information LG12-5 at the date and time DA15 from the B store. In the example of FIG. 2, the selection device 100 acquires the history information LG25 at the date and time DA15 from the service providing device 50.

  Further, the selection device 100 predicts the predicted value of the index using the history information and the model (Step S202). Using the history information and the model M1, the selection device 100 predicts a predicted sales value as an index for the A store. In the example of FIG. 2, the selection device 100 uses the data DT21 including the history information LG11-5, LG12-5, LG25, etc. of the date and time DA15 and the model M1 to calculate the predicted value of the sales of the store A at the date and time DA16. Predicted value PV16.

  Further, the selection device 100 acquires the planned value of the index (Step S203). In the example of FIG. 2, the selection device 100 acquires information indicating that the planned sales value at the date DA16 of the A store is the sales planned value CV16. For example, the selection device 100 acquires information indicating that the planned sales value of the store A at the date and time DA16 is the sales planned value CV16 from the index information storage unit 124 (see FIG. 8).

  Note that step S203 may be performed at any stage as long as it is before step S204. For example, step S203 may be performed before step S202 or at the same timing.

  Then, the selection device 100 determines whether or not the deviation between the planned value and the predicted value satisfies a predetermined condition (step S204). In the example of FIG. 2, the selection device 100 calculates the difference between the sales plan value CV16 and the sales forecast value PV16. In this case, the selection device 100 calculates that the difference between the sales plan value CV16 and the sales forecast value PV16 is the difference DF11. Then, the selection device 100 determines which condition corresponds to the difference DF11 indicating the deviation between the sales plan value CV16 and the sales forecast value PV16. For example, the selection device 100 determines which divergence condition among the divergences in the target “food” and the index “sales” stored in the coping behavior storage unit 125 (see FIG. 9).

  In the example of FIG. 2, the selection apparatus 100 determines that the difference DF11 is larger than the condition value SP2 and smaller than the condition value SP3 by comparing the difference DF11 with the condition values SP1 to SP3 and the like. In this case, the selection device 100 determines that the divergence between the planned value and the predicted value of the sales of the store A satisfies the divergence condition of the condition value SP2.

  When it is determined that the deviation between the planned value and the predicted value satisfies the predetermined condition (step S204: Yes), the selection device 100 selects a coping action based on the deviation between the planned value and the predicted value (step S205). ). In the example of FIG. 2, the selection device 100 selects the coping action AT2 corresponding to the condition value SP2 because the difference between the planned value and the predicted value of the sales of the store A satisfies the condition of the difference of the condition value SP2.

  The selection device 100 executes the selected coping action (step S206). For example, when the coping behavior AT2 is coupon distribution (distribution) to the users in the area, the selection device 100 executes coupon distribution to the users located in the area A where the A store is located. In the example of FIG. 2, the selection device 100 requests the service providing device 50 to execute coupon distribution to a user located in the area A where the A store is located.

  On the other hand, the selection apparatus 100 complete | finishes a process, when it determines with the deviation of a plan value and a predicted value not satisfy | filling a predetermined condition (step S204: No). For example, if the difference between the planned value and the predicted value of the sales of store A is less than the condition value SP1, the selection device 100 ends the process without selecting any coping action, assuming that no condition is satisfied.

[6. effect〕
As described above, the selection device 100 according to the embodiment includes the acquisition unit 131, the prediction unit 133, and the selection unit 134. The acquisition unit 131 acquires a plan value of an index related to the business of one operator, the plan value corresponding to a predetermined time point, and history information related to the one business operator before the predetermined time point. . Based on the history information acquired by the acquisition unit 131, the prediction unit 133 predicts a prediction value of an index related to the business of one operator and corresponding to a predetermined time point. When the deviation between the predicted value predicted by the prediction unit 133 and the planned value satisfies a predetermined condition, the selection unit 134 selects a coping action that is an action for dealing with the deviation.

  As described above, when the deviation between the predicted value and the plan value satisfies a predetermined condition, the selection device 100 according to the embodiment selects a predetermined action by selecting a coping action that is an action for dealing with the deviation. It is possible to take appropriate actions on the person.

  Moreover, in the selection apparatus 100 according to the embodiment, the acquisition unit 131 acquires history information related to one business operator.

  As described above, the selection device 100 according to the embodiment predicts a predicted value of one operator at a predetermined time using history information related to one operator, and takes a coping action based on the predicted value predicted. By selecting, it is possible to enable appropriate behavior for a predetermined business operator.

  Further, in the selection device 100 according to the embodiment, the acquisition unit 131 acquires a model that outputs a score indicating a predicted value of one business operator at a predetermined time in response to input of history information. The prediction unit 133 inputs history information to the model, and predicts a predicted value of one operator at a predetermined time based on the score output by the model.

  As described above, the selection device 100 according to the embodiment uses a model to predict a predicted value of one operator at a predetermined time point based on the score output from the model, and copes with the predicted value based on the predicted value. By selecting an action, it is possible to enable an appropriate action for a predetermined business operator.

  In the selection device 100 according to the embodiment, the selection unit 134 determines whether the deviation satisfies a predetermined condition by comparing the plan value and the predicted value, and determines that the predetermined condition is satisfied. Then, select the coping action.

  As described above, the selection device 100 according to the embodiment determines whether the deviation satisfies the predetermined condition by comparing the plan value and the predicted value, and copes with it when it is determined that the predetermined condition is satisfied. By selecting an action, it is possible to enable an appropriate action for a predetermined business operator.

  In the selection device 100 according to the embodiment, the selection unit 134 selects a coping action when the difference between the plan value and the predicted value is equal to or greater than a predetermined threshold.

  As described above, when the difference between the plan value and the predicted value is equal to or greater than the predetermined threshold, the selection device 100 according to the embodiment enables appropriate behavior for the predetermined business operator by selecting the coping behavior. be able to.

  In the selection device 100 according to the embodiment, the acquisition unit 131 acquires history information of a plurality of business operators including one business operator.

  As described above, the selection device 100 according to the embodiment can improve the prediction accuracy of the predicted value by predicting the predicted value using the history information of a plurality of business operators including one business operator. Appropriate behavior can be made possible for a given operator.

  In the selection device 100 according to the embodiment, the acquisition unit 131 acquires history information including a user's action history before a predetermined time point.

  As described above, the selection device 100 according to the embodiment can improve the prediction accuracy of the prediction value by predicting the prediction value using the history information including the user's behavior history before the predetermined time point. Appropriate behavior can be made possible for a given operator.

  Moreover, in the selection device 100 according to the embodiment, the acquisition unit 131 acquires history information including a user's behavior history on the Internet.

  Thus, since the selection apparatus 100 according to the embodiment can improve the prediction accuracy of the predicted value by predicting the predicted value using the history information including the user's behavior history on the Internet, the predetermined device It is possible to take appropriate actions on the person.

  In the selection device 100 according to the embodiment, the acquisition unit 131 acquires history information including a search history by the user.

  As described above, the selection device 100 according to the embodiment can improve the prediction accuracy of the predicted value by predicting the predicted value using the history information including the search history by the user. Appropriate action can be made possible.

  In the selection device 100 according to the embodiment, the acquisition unit 131 acquires history information including a purchase history by the user.

  As described above, the selection device 100 according to the embodiment can improve the prediction accuracy of the prediction value by predicting the prediction value using the history information including the purchase history by the user. Appropriate action can be made possible.

  Moreover, in the selection device 100 according to the embodiment, the acquisition unit 131 acquires history information including information regarding the number of users in an area corresponding to one store based on the user location information.

  Thus, the selection apparatus 100 according to the embodiment predicts a predicted value by predicting a predicted value using history information including information on the number of users in an area corresponding to one store based on the position information of the user. Since the accuracy can be improved, it is possible to enable appropriate behavior for a predetermined business operator.

  Moreover, in the selection device 100 according to the embodiment, the acquisition unit 131 acquires history information including weather information of an area corresponding to one store.

  As described above, the selection device 100 according to the embodiment can improve the prediction accuracy of the prediction value by predicting the prediction value using the history information including the weather information of the area corresponding to one store. It is possible to make appropriate actions for a given business operator.

  In the selection device 100 according to the embodiment, the selection unit 134 selects one coping action among a plurality of coping actions according to the degree of deviation between the planned value and the predicted value.

  As described above, the selection device 100 according to the embodiment selects an appropriate coping behavior among a plurality of coping behaviors according to the degree of deviation between the planned value and the predicted value, so that it is appropriate for a predetermined operator. Can make it possible.

[7. Hardware configuration)
The selection apparatus 100 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in FIG. 12, for example. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the selection device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. In addition, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the selection device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes control by executing a program or data (for example, model M1 (model data MDT1)) loaded on the RAM 1200. The function of the unit 130 is realized. The CPU 1100 of the computer 1000 reads and executes these programs or data (for example, model M1 (model data MDT1)) from the recording medium 1800. As another example, these programs or data are transmitted from other devices via the network N. May be obtained.

  As described above, some of the embodiments and modifications of the present application have been described in detail with reference to the drawings. It is possible to carry out the present invention in other forms that have been modified and improved.

[8. Others]
In addition, among the processes described in the above-described embodiments and modifications, all or a part of the processes described as being automatically performed can be manually performed, or are described as being performed manually. All or part of the processing can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the above-described embodiments and modifications can be combined as appropriate within a range that does not contradict processing contents.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Selection system 100 Selection apparatus 121 Learning data storage part 122 Model information storage part 123 Store information storage part 124 Index information storage part 125 Coping action information storage part 130 Control part 131 Acquisition part 132 Generation part 133 Prediction part 134 Selection part 135 Provision part 10 terminal device 20 store terminal 50 service providing device N network

Claims (15)

An acquisition unit that acquires a plan value of an index related to the business of one operator, the plan value corresponding to a predetermined time point, and history information before the predetermined time point;
Based on the history information acquired by the acquisition unit, a prediction unit that predicts a prediction value corresponding to the predetermined time point, which is a predicted value of the index related to the business of the one operator,
A selection unit that selects a coping action that is an action for coping with the divergence when the divergence between the predicted value predicted by the prediction unit and the plan value satisfies a predetermined condition;
A selection device comprising: The acquisition unit
The selection apparatus according to claim 1, wherein the history information related to one business operator is acquired. The acquisition unit
In response to the input of the history information, obtain a model that outputs a score indicating the predicted value of the one operator at the predetermined time point,
The prediction unit
The history value is input to the model, and the predicted value of the one operator at the predetermined time point is predicted based on a score output by the model. The selection device described. The selection unit includes:
By comparing the plan value and the predicted value, it is determined whether the deviation satisfies a predetermined condition, and when it is determined that the predetermined condition is satisfied, the coping action is selected. The selection device according to any one of claims 1 to 3. The selection unit includes:
The selection device according to any one of claims 1 to 4, wherein the coping action is selected when a difference between the planned value and the predicted value is greater than or equal to a predetermined threshold value. The acquisition unit
The selection apparatus according to any one of claims 1 to 5, wherein the history information of a plurality of business operators including the one business operator is acquired. The acquisition unit
The selection apparatus according to claim 1, wherein the history information including a user's action history before the predetermined time point is acquired. The acquisition unit
The selection apparatus according to claim 7, wherein the history information including an action history of a user on the Internet is acquired. The acquisition unit
The selection device according to claim 7 or 8, wherein the history information including a search history by the user is acquired. The acquisition unit
The selection apparatus according to claim 7, wherein the history information including a purchase history by the user is acquired. The acquisition unit
The selection device according to any one of claims 7 to 10, wherein the history information including information related to the number of users in an area corresponding to the one business operator based on the user location information is acquired. The acquisition unit
The selection device according to claim 1, wherein the history information including weather information of an area corresponding to the one business operator is acquired. The selection unit includes:
The one coping action is selected from a plurality of coping actions concerning the improvement of the indicator of the one operator according to the degree of deviation between the planned value and the predicted value. 13. The selection device according to any one of items 12. A selection method performed by a computer,
An acquisition step of acquiring a plan value of an index related to a business of one operator, the plan value corresponding to a predetermined time, and history information related to the one business before the predetermined time; ,
A prediction step of predicting a prediction value corresponding to the predetermined time point, which is a prediction value of the index related to the business of the one operator, based on the history information acquired by the acquisition step;
A selection step of selecting a coping action that is an action for coping with the divergence when the divergence between the predicted value predicted by the prediction step and the planned value satisfies a predetermined condition;
The selection method characterized by including. An acquisition procedure for obtaining a plan value of an index related to a business of one operator, the plan value corresponding to a predetermined time, and history information related to the one business before the predetermined time; ,
Based on the history information acquired by the acquisition procedure, a prediction procedure for predicting a prediction value of the index related to the business of the one operator and corresponding to the predetermined time point;
A selection procedure for selecting a coping action that is an action for coping with the divergence when a divergence between the predicted value predicted by the prediction procedure and the plan value satisfies a predetermined condition;
A selection program characterized by causing a computer to execute.

Images