Plant factory operation support device, operation support method, and program

Abstract

To provide a plant factory operation support device, an operation support method, and a program capable of suppressing the impact of the number of users at boarding and alighting stations.SOLUTION: The plant factory operation support device, according to one embodiment of the present invention, comprises an acquisition unit, a storage unit, and a sales planning unit. The acquisition unit acquires information about the past number of boarding and alighting at each railway station. The storage unit stores the information. The sales planning unit, based on the information stored in the storage unit, predicts the number of plants produced in the plant factory that will be sold at each station over a predetermined period and generates a sales plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] An embodiment of the present invention relates to a plant factory operation support device, an operation support method, and a program. [Background technology]

[0002] Plant factories can maintain a constant production volume throughout the year, regardless of the season or climate, making it possible to stabilize food supplies and produce according to demand. Furthermore, because they can be set up in cities and densely populated areas, they can reduce the use of farmland and the energy and resource consumption required for transportation. Plants produced in these plant factories are also sold inside train stations and in station stores adjacent to train stations. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-191854 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the number of tickets sold at stations may be affected by the number of passengers at the stations.

[0005] Therefore, the problem that the present invention aims to solve is to provide a plant factory operation support device, operation support method, and program that can reduce the impact of the number of users at boarding and disembarking stations on plant production. [Means for solving the problem]

[0006] A plant factory operation support device according to an embodiment of the present invention includes an acquisition unit, a memory unit, and a sales planning unit. The acquisition unit acquires information regarding the past number of passengers boarding and alighting at each train station. The memory unit stores the information. The sales planning unit predicts the number of plants produced in the plant factory sold at each train station over a predetermined period of time based on the information stored in the memory unit, and generates a sales plan. [Effects of the Invention]

[0007] According to the present invention, the influence of the number of users at the boarding and disembarking stations on plant production can be reduced. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is an overall configuration diagram of a plant factory operation support system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing an example of the configuration of a storage unit. [Figure 3] FIG. 2 is a block diagram showing an example of the configuration of a control processing unit. [Figure 4] FIG. 2 is a block diagram showing an example of the configuration of a sales planning department. [Figure 5] FIG. 10 is a diagram showing the processing flow of the sales planning department. [Figure 6] FIG. 4 is a block diagram showing an example of the configuration of a delivery planning unit. [Figure 7] FIG. 10 is a diagram showing the processing flow of a delivery planning unit. [Figure 8] FIG. 2 is a block diagram showing an example of the configuration of a power procurement planning unit. [Figure 9] FIG. 4 is a diagram showing the processing flow of a power procurement planning unit. [Figure 10] FIG. 2 is a block diagram showing an example of the configuration of a production planning unit. [Figure 11] FIG. 10 is a diagram showing the processing flow of a production planning department. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, a plant factory operation support device, an operation support method, and a program according to an embodiment of the present invention will be described in detail with reference to the drawings. Note that the embodiment described below is an example of an embodiment of the present invention, and the present invention should not be interpreted as being limited to these embodiments. Furthermore, in the drawings referred to in this embodiment, identical parts or parts having similar functions are given the same or similar symbols, and repeated explanations thereof may be omitted. Furthermore, part of the configuration may be omitted from the drawings.

[0010] [Overall configuration of the operation support system] Fig. 1 is an overall configuration diagram of a plant factory operation support system 1 according to this embodiment. As shown in Fig. 1, the operation support system 1 for a plant factory 10 according to this embodiment is a system capable of supporting the operation of a plant factory using, for example, information held by a plant factory operator, and includes a plant factory 10, which is a facility of the plant factory operator, and an operation support device 20 for the plant factory 10. Fig. 1 also illustrates a group of external services 30 run by, for example, a railway operator, as an example of a service provided by the plant factory operator.

[0011] The plant factory 10 is, for example, a sealed facility. This plant factory 10 is a facility for producing plants that is able to directly utilize sunlight, for example. Note that the plant factory 10 is not limited to a facility that is able to directly utilize sunlight, and may be, for example, a facility that produces plants using only artificial light. The plant factory 10 can produce and ship plants according to a plan by adjusting the amount of light and temperature within the facility using an information environment such as a computer network. Furthermore, the plants produced in the plant factory 10 can be transported by rail and sold, for example, at station stores owned by railway operators.

[0012] Station stores refer to stores located within stations that are entered through ticket gates, stores located outside the ticket gates but along passageways through which passengers pass at stations where passengers board and disembark, and stores within a predetermined distance from the ticket gates. The predetermined distance is, for example, 300 meters. This distance can be set according to the range through which passengers pass. In other words, station stores are stores whose purchase volume is affected by the number of passengers boarding and disembarking at stations where passengers board and disembark. These stores are, for example, directly operated stores of railway operators, and are stores that can use railway vehicles to transport shipments from the plant factory 10, for example.

[0013] The operation support device 20 has a CPU (Central Processing Unit) and is, for example, a computer. The operation support device 20 is a device that performs operation support for the plant factory 10 using information from a group of external services 30 run by, for example, a railway operator or a service provider contracted with the railway operator, and includes a communication unit 100, a storage unit 102, a control processing unit 104, a display control unit 106, and an input unit 108. Some or all of these functional units are realized by, for example, a hardware processor such as a CPU executing a program (software) stored in the storage unit 102.

[0014] The program may be downloaded from a device (e.g., an application server) connected via the communication network Nw, or may be stored on a portable storage medium such as an SD card and installed in the operation support device 20. Some or all of the functional units of the operation support device 20 may be realized by hardware such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field Programmable Gate Array), or may be realized by a combination of software and hardware. Details of the operation support device 20 will be described later.

[0015] The external service group 30 is, for example, services provided by a railway operator or a service provider under contract with a railway operator. The external service group 30 is provided by a receipt management system 300, a ticket management system 302, a weather management system 304, a timetable management system 306, a vehicle operation management system 308, and a power supply management system 310.

[0016] The receipt management system 300 is a system that provides a receipt management service for managing receipt records. The receipt management system 300 is a service that digitizes detailed receipts for purchased items, which are usually provided on paper at the time of checkout, and manages and provides them as receipt data. In other words, the receipt data includes past receipt information about electronic receipts that associate the number of plants produced in the plant factory 10 sold, the time of sale, and the boarding and disembarking stations. This receipt information associates the type, quantity, sale date, time of sale, etc. of the items sold.

[0017] Furthermore, tickets managed by the ticket management system 302 include coupons issued by directly managed stores at stations where passengers board or disembark, coupons issued by shopping malls around stations, and the like. Information on these tickets is managed, for example, by a railway operator via the ticket management system 302, and stored as ticket actual data in the database 303. For example, the ticket actual data includes ticket information for each station where passengers board or disembark, correlated with the coupon type, issue date and time, expiration date, and the like, and compiled for each station. Coupons may also include discount coupons and complimentary coupons used for marketing purposes by stores or companies. In this way, the ticket actual data includes coupon information associated with the number of plant coupons distributed at stations and their expiration dates.

[0018] Tickets managed by the ticket management system 302 may include, for example, QR codes and the like. Passengers can pass through the ticket gate by displaying the QR code on, for example, a smartphone and scanning it with a scanning tablet. Alternatively, if a scanning tablet is not available, passengers can pass through the ticket gate by having station attendants scan the QR code ticket with the tablet. This scanned information is managed by, for example, a railway operator via the ticket management system 302, and is associated with boarding and alighting stations, boarding and alighting dates, boarding and alighting times, and the like. This information is then stored in the database 303 as ticket performance data.

[0019] The weather management system 304 is a system that provides a weather forecast service that manages weather forecast data and actually measured weather data. Weather includes information on weather conditions (e.g., sunny / cloudy / rainy) for each region and hour, and outside temperatures (average temperature, maximum temperature, minimum temperature). This weather data conforms to, for example, the weather forecast data and meteorological measurement data of the Japan Meteorological Agency. It is managed, for example, by a railway operator via the weather management system 304 and stored as weather data in database 305. Note that database 305 includes actually measured weather data. In other words, the weather data includes historical weather data for each hour for each area including boarding and alighting stations, and hourly weather forecast data for each area including boarding and alighting stations.

[0020] The timetable management system 306 is a system that provides data related to vehicle operation plans. Data related to these operation plans is managed, for example, by a railway operator via the timetable management system 306 and stored as timetable plan data in a database 307. A timetable is a vehicle operation plan. Furthermore, a train consisting of individual vehicles is identified by a train number. Once the train number is identified, it is possible to determine when the train will arrive at which boarding and alighting station. In other words, the information contained in the timetable plan data is associated with the arrival and departure times at the boarding and alighting station, for example, based on the train number. The timetable plan data is also associated with information on train numbers that can transport luggage by train. Train luggage transport also refers to the transport of luggage by passenger trains other than freight trains. In train luggage transport, not only the car sales preparation room but also the passenger compartment can be used for transportation.

[0021] The vehicle operation management system 308 is a system that provides data related to vehicle operation. This data related to vehicle operation is managed, for example, by a railway operator via the vehicle operation management system 308, and is stored in a database 309 as vehicle operation performance data. The vehicle operation performance data is data that records the operating status of the equipment that constitutes the vehicle. In other words, the information included in the vehicle operation performance data associates the operating status of the equipment that constitutes the vehicle with time. Furthermore, the regenerative power performance of each vehicle is associated with time and the location of generation.

[0022] The power supply management system 310 is a system that provides a power supply management service that manages power supply prediction data to be supplied to businesses and the like, and data on actually supplied power supply. This data on power supply is managed, for example, by a railway business via the power supply management system 310, and is stored as power supply prediction data in a database 311. The database 311 also includes data on actually supplied power supply. That is, the information included in the power supply data associates the power supply prediction data of the power business that can supply power to the area including the plant factory 10, and the actual power supply data of the actually supplied power with time.

[0023] Here, the operation support device 20 will be described in detail. The communication unit 100 communicates with the plant factory 10 and the external service group 30 via the network Nw. This communication unit 100 acquires information regarding the past number of passengers boarding and alighting at each train boarding and alighting station. In other words, the communication unit 100 functions as an interface between the operation support device 20 and the external service group 30. The network Nw is at least one of a wired network and a wireless network, and also includes the Internet.

[0024] The communication unit 100 can convert the acquired data into a format that can be processed by the control processing unit 104 and store the data in the storage unit 102. Note that the communication unit 100 can store data that does not require conversion in the storage unit 102 without converting the data. The communication unit 100 according to this embodiment corresponds to an acquisition unit.

[0025] 2 is a block diagram showing an example configuration of the storage unit 102. The storage unit 102 is configured, for example, with an HDD (hard disk drive) or an SSD (solid state drive). The storage unit 102 stores various data and programs used by the operation support device 20. For example, the storage unit 102 stores data converted or acquired by the communication unit 100 as a receipt record database 114, a ticket record database 116, a weather forecast database 118, a timetable planning database 120, a vehicle operation record database 122, and a power supply database 124.

[0026] As a data management method for the storage unit 102, for example, a relational database can be used for data expressed in tabular relationships. A time-series database can be used for time-series data, and a graph database can be used for data expressed in connections between things. Furthermore, the storage unit 102 may manage data using text files written in formats such as JSON, XML, and CSV. JSON is a data representation format characterized by a text-based, concise, and easy-to-read structure. XML is a markup language for representing and transferring data, established by the World Wide Web Consortium (W3C). CSV stands for Comma-Separated Values ​​and is a text-based format for representing data. In the CSV format, each data item is separated by a comma (,), and each row represents one record. CSV is a simple and easy-to-use format that can be used in spreadsheet software, database software, and the like.

[0027] The receipt record data stored in the receipt record database 114 corresponds to the receipt record data stored in the database 301. In other words, receipt information for each boarding / alighting station is associated with the product sold, price, and time, and is compiled for each boarding / alighting station where the purchase is made. In addition, data for a period of, for example, the past several years is stored.

[0028] The ticket actual data stored in the ticket actual database 116 corresponds to the ticket actual data stored in the database 303. That is, ticket information for each boarding / alighting station is associated with the coupon type, issue date and time, expiration date, etc., and is compiled for each boarding / alighting station where the ticket is sold. Furthermore, the actual usage of the electronic ticket is associated with the time of use, and is compiled for each boarding / alighting station where the ticket is sold.

[0029] The weather data stored in weather forecast database 118 corresponds to the weather data stored in database 305. That is, the weather data includes past actual data for each hour for each district including the boarding and alighting stations that are sales destinations, and forecast data for each hour for each district including the boarding and alighting stations.

[0030] The timetable plan data stored in the timetable plan database 120 corresponds to the timetable plan data stored in the database 307. In other words, the information included in the timetable plan data is associated with the departure and arrival times of the boarding and alighting stations where the goods are sold, for example, based on the train number. The timetable plan data is also associated with information on the train numbers on which train baggage can be transported.

[0031] The vehicle operation record data stored in vehicle operation record database 122 corresponds to the vehicle operation record data stored in database 309. In other words, the information included in the vehicle operation record data associates the operating status of the equipment constituting the vehicle passing through the boarding / alighting station to which the vehicle is sold with time. In addition, the regenerative power record of each vehicle is associated with the time and the location of generation.

[0032] The power supply forecast data stored in the power supply database 124 corresponds to the power supply forecast data stored in the database 311. In other words, the information included in the power supply data includes the power supply forecast data of the power supplier that can supply power to the area including the plant factory 10, and the power supply data that has actually been supplied, which are associated with time.

[0033] As shown in FIG. 1 again, the communication unit 100 is, for example, an API (Application Programming Interface), which allows different software programs to share authentication functions and read and analyze data. Furthermore, if the external service group 30 is provided as a Web (World Wide Web) service via the Internet, the communication unit 100 can use an interface based on GraphQL or REST-API. The API, GraphQL, REST-API, etc. may be provided by the external service group 30. GraphQL is a data query language for WebAPIs, a technology designed to enable clients to obtain only the necessary data from a server. REST-API is an API designed based on the principles of Web architecture (Representational State Transfer), a distributed network architecture.

[0034] Furthermore, if a method for directly accessing a database in the external service group 30 is provided, the communication unit 100 may use a program that accesses this database 301, 303, 305, 307, 309, 311 as part of the interface function. Alternatively, if the data managed by the external service group 30 is provided as printed material, the data may be digitized using OCR technology and then imported, or read by a human system and manually entered. Either method is provided as part of the interface function. OCR is an abbreviation for Optical Character Recognition, a technology in which a machine optically recognizes printed or handwritten text and converts it into digital text data.

[0035] The control processing unit 104 executes a marketing service function, a logistics service function, a facility service function, and an energy management service function using the information stored in the storage unit 102. Details of the control processing unit 104 will be described later.

[0036] The display control unit 106 causes the display unit 110 to display the image generated by the control processing unit 104 . The input unit 108 receives an operation signal input via the operation unit 112 and supplies it to the control processing unit 104, the display control unit 106, and the like.

[0037] The display unit 110 is, for example, a monitor, and displays image data supplied from the display control unit 106.

[0038] The operation unit 112 is configured with input devices such as a keyboard, a mouse, etc. The operation unit 112 inputs a signal to the input unit 108 in response to an operation by an operator.

[0039] Here, the configuration of the control processing unit 104 will be described. Fig. 3 is a block diagram showing an example of the configuration of the control processing unit 104. The control processing unit 104 has a sales planning unit 126, a delivery planning unit 128, a power procurement planning unit 130, and a production planning unit 132. Details of each processing unit will be described later.

[0040] The sales planning unit 126 is a processing unit that executes a marketing service function. This marketing service function is a function that supports the formulation of sales plans. For example, the sales planning unit 126 generates a sales plan for each sales outlet based on demand forecasts at the outlets corresponding to each boarding and alighting station on a railway line. Alternatively, the planning unit 126 aggregates the sales numbers for each sales outlet and generates a sales plan for each boarding and alighting station. In other words, the sales planning unit 126 generates a sales plan based on a sales quantity plan and a sales price plan. The sales quantity plan is a plan regarding "at which boarding and alighting station," "when," and "how much to sell." The sales price plan is a plan regarding "at which boarding and alighting station," "when," and "at what unit price to sell."

[0041] The delivery planning unit 128 is a processing unit that executes a logistics service function. This logistics service function is a function that supports the creation of delivery plans. For example, the delivery planning unit 128 generates a delivery plan for each retailer corresponding to each boarding and disembarking station on a railway line. Alternatively, the planning unit 126 aggregates the number of deliveries for each retailer and generates a delivery plan for each boarding and disembarking station.

[0042] The power procurement planning unit 130 is a processing unit that executes an energy management service function. The power procurement planning unit 130 generates a procurement plan for the supplier of power to be used in the plant factory 10 and the amount of power.

[0043] The production planning unit 132 is a processing unit that executes the facility service function. The production planning unit 132 generates a production plan for the plant factory 10.

[0044] Here, the details of the sales planning unit 126 will be described. Fig. 4 is a block diagram showing an example of the configuration of the sales planning unit 126. Note that, for simplicity of explanation, the following will be explained using an example in which there is one sales store per station, but even if there are multiple stores, it is possible to provide operational support to each sales store in the same way.

[0045] The sales planning unit 126 includes a demand forecasting unit 140 and a sales planning processing unit 150. The demand forecasting unit 140 executes demand forecasting processing. The demand forecasting processing is processing for predicting "at which boarding and alighting station," "when," and "how much sales volume is expected." The demand forecasting unit 140 predicts the number of plants produced in the plant factory sold for each boarding and alighting station over a predetermined period of time, based on information stored in the memory unit 102. The unit includes a forecasting processing unit 141, a receipt analysis unit 142, a ticket analysis unit 143, a weather forecasting processing unit 144, and a passenger count analysis unit 145. Details of the demand forecasting unit 140 will be described later.

[0046] The sales plan processing unit 150 generates a sales plan for the plant factory 10 based on the sales volume predicted for each boarding and alighting station by the demand forecasting unit 140. The sales plan processing unit 150 includes a sales price planning unit 151 and a sales quantity planning unit 152. Details of the sales plan processing unit 150 will be described later.

[0047] [Demand forecast] Here, the demand forecasting process will be explained in detail. The forecasting processing unit 141 predicts the number of plants produced in the plant factory sold for each boarding and alighting station over a predetermined period of time as a demand forecast. This forecasting processing unit 141 executes the demand forecast using the processing results of the receipt analysis unit 142, ticket analysis unit 143, weather forecasting processing unit 144, and passenger number analysis unit 145. As described above, the demand forecasting process is a process of predicting "at which boarding and alighting station," "when," and "how much sales are expected."

[0048] The prediction processing unit 141 according to this embodiment predicts the demand for plants at each station by predicting increases or decreases in demand due to variable factors at each station, using, for example, the sales record of plants at each station throughout the year as basic information from the receipt analysis unit 142. Variable factors include, but are not limited to, the number of coupons distributed, weather, and the number of passengers getting on and off. Furthermore, for station vendors that do not use electronic receipts, the prediction processing unit 141 predicts demand based on the number of passengers getting on and off at stations close to the vendor.

[0049] Furthermore, the prediction processing unit 141 can also perform demand prediction for each period, such as short-term prediction and seasonal prediction. Short-term prediction is a time-series prediction for each hour up to seven days in the future. Seasonal prediction is a prediction for up to three months in the future, for example. These prediction periods can correspond to, for example, the prediction period and prediction data of weather forecasts. Note that the hours, days, periods, data used for prediction, etc. are merely examples and are not limited to these.

[0050] For example, seasonal forecasts can be used for long-term demand forecasts related to plant production planning, whereas short-term forecasts based on the shelf life (perishable period) of plants can be used for demand forecasts related to distribution planning.

[0051] [Receipt analysis] The receipt analysis unit 142 executes a process of analyzing sales quantities using past sales quantities based on the electronic receipt performance data managed by the receipt performance database 114. This receipt performance is, for example, a numerical value of the purchase quantity of each plant. For example, the receipt analysis unit 142 calculates the relationship between the sales volume of plants for each target station and time based on the past sales performance data managed by the receipt performance database 114. More specifically, the receipt analysis unit 142 tally and calculates the plant sales quantity for each store at the target station for sales by hour of each day.

[0052] As a result, for example, the quantity of plant B sold at station A between 9:00 and 10:00 on March 3rd in the past is calculated as 100. In this way, the receipt analysis unit 142 uses the receipt performance information to quantify the sales quantity of the plant being sold at each station for each hour of each day.

[0053] The receipt analysis unit 142 may calculate the sales volume based on the ticket sales record and other data. The ticket sales record is a numerical value obtained by quantifying the number of coupons containing the plants for sale distributed at each station for each validity period.

[0054] [Ticket Analysis] The ticket analysis unit 143 quantifies the number of coupons containing plants for sale distributed at each boarding and alighting station for each validity date based on the data managed by the ticket performance database 116. For example, a sales increase of about 3% is statistically expected based on the number of coupons distributed.

[0055] The ticket sales record database 116 can also calculate the number of tickets sold based on statistical methods using ticket sales records managed by QR tickets, which are electronic tickets. Alternatively, the ticket sales record database 116 can calculate the number of tickets sold based on receipt records or other data.

[0056] More specifically, the ticket analysis unit 143 can use a regression analysis formula in which, for example, the sales volume at the destination station for each hour is used as the objective variable, and the actual value of electronic tickets at the destination station for each hour is used as the explanatory variable. The sales volume here can be the number of sales analyzed by the receipt analysis unit 142. The actual value of electronic tickets is the number of electronic tickets used at the destination station for each hour. Using this regression formula, the ticket analysis unit 143 can convert the actual value of electronic tickets into the sales volume.

[0057] [Weather forecast] The weather forecast processing unit 144 extracts weather forecast data for the area including the target boarding / alighting station from the data managed by the weather forecast database 118. This weather forecast data includes short-term forecasts, seasonal forecasts, etc. The short-term forecast is a time-series weather forecast for each hour, such as 24 hours or up to seven days in advance. The seasonal forecast is a monthly weather forecast for up to three months in advance.

[0058] [Passenger number analysis] The passenger boarding / alighting number analysis unit 145 analyzes the number of passengers boarding / alighting for each hour of each day at the boarding / alighting station that is the destination of the sale, based on data managed by the timetable plan database 120 and the vehicle operation record database 122. This passenger boarding / alighting number analysis unit 145 calculates the number of passengers boarding / alighting according to the weight difference between the vehicles at the boarding / alighting station, based on data in which weight information regarding the weight of the railcars stopping at the boarding / alighting station is associated with time. More specifically, the passenger boarding / alighting number analysis unit 145 calculates the number of passengers boarding / alighting based on the difference in carbody support air spring pressure between boarding / alighting stations, which is part of the past boarding / alighting operation record, based on the timetable plan at the boarding / alighting station that is the destination of the sale, and with the train arrival time as the reference. In other words, an increase in load indicates an increase in the number of passengers, and a decrease in load indicates a decrease in the number of passengers.

[0059] This enables the boarding / alighting passenger number analysis unit 145 to analyze the difference in the number of boarding / alighting passengers at each boarding / alighting station. Furthermore, the boarding / alighting passenger number analysis unit 145 can also calculate the multiplier and alighting number based on the fluctuations in the carbody support air spring pressure, which is part of the past boarding / alighting operation record, with the train arrival time as a reference, based on the timetable plan at the boarding / alighting station to which the train is sold. For example, the load decreases in the first half of the stop period as passengers alight, and increases in the second half as passengers board. This enables the boarding / alighting passenger number analysis unit 145 to calculate the number of boarding / alighting passengers for each car. The boarding / alighting passenger number analysis unit 145 executes this processing to calculate the number of boarding / alighting passengers for each hour of each day at the target boarding / alighting station. For example, the boarding / alighting passenger number analysis unit 145 calculates the number of boarding / alighting passengers for each hour of each day at the target boarding / alighting station for, for example, the past year.

[0060] [Prediction processing] The prediction process has two modes: Mode 1 and Mode 2. Mode 1 uses the sales volume based on receipt performance as the basic predicted value, and the fluctuation factors are at least one of the following: the number of coupons, the number of passengers boarding and alighting in the period immediately prior to the prediction, and weather forecasts. For example, this mode is used in stores that have installed the receipt management system 300.

[0061] Mode 2 is a mode in which the number of passengers at boarding and alighting stations is used as the basic predicted value, and the fluctuation factors are at least one of the following: the number of coupons, the number of boarding and alightings in the period immediately before the prediction, and weather forecast. For example, this mode is used in stores that do not have the receipt management system 300 installed. [Mode 1] The prediction processing unit 141 can also perform demand prediction for each period, such as short-term prediction and seasonal prediction, based on this information. For example, in a short-term time-series prediction of less than one week, the prediction processing unit 141 sets the predicted sales volume based on the sales figures for each hour of receipts on the same day of the week for the past two months as the predicted sales volume. In other words, the prediction processing unit 141 sets the average value of the sales figures for each hour of the same day of the week for the past two months as the reference predicted sales volume for each hour of the same day of the week for seven days.

[0062] Furthermore, when adding the number of coupons to the predicted sales, the increased sales based on the number of coupons expiring on that day is added to obtain the predicted sales. In other words, the number of coupons distributed with expiration dates on that day is divided by a predetermined number (e.g., 3 percent) by the opening hours of the store, and the result is added to the standard predicted sales for each hour on the same day of the week to obtain the new predicted sales. In other words, the prediction processing unit 141 can change the predicted sales depending on the number of coupons with expiration dates on the sale date distributed at the boarding and disembarking stations.

[0063] Furthermore, when a weather forecast is added, the prediction processing unit 141 multiplies the predicted sales volume for each hour by a weather coefficient according to the weather forecast to obtain a new predicted sales volume. For example, the prediction processing unit 141 sets this weather coefficient to 1 if it is sunny, 0.8 if it is cloudy, and 0.5 if it is raining. The prediction processing unit 141 can calculate this weather coefficient from the relationship between sales performance and weather through statistical processing. In other words, the prediction processing unit 141 can change the predicted sales volume according to weather data.

[0064] Furthermore, the prediction processing unit 141 can reflect the number of passengers boarding and alighting at the time of prediction in a short-term time-series prediction for up to one week. For example, if the number of passengers boarding and alighting at the time of prediction is higher than the average number of passengers at the target boarding and alighting station at the time of prediction, the prediction processing unit 141 multiplies the passenger coefficient by 1.2; if it is about the same, it multiplies by 1.0; and if it is lower, it multiplies by 0.8. In other words, the prediction processing unit 141 can change the predicted sales volume according to the number of passengers boarding and alighting at each boarding and alighting station.

[0065] The prediction processing unit 141 can calculate this customer coefficient as, for example, the ratio of the number of passengers boarding and alighting in the hour before the prediction on the same day of the week to the average value for the same hour before the prediction on the same day of the week in the past. Note that the previous hour is an example and is not limited to this. For example, the customer coefficient can be calculated as the ratio of the average value for the same hour before the prediction on the same day of the week in the past to the average value for the same hour before the prediction on the same day of the week in the past. In this way, the time range for calculating the customer coefficient can be changed depending on the purpose.

[0066] In this way, when the prediction processing unit 141 reflects the number of coupons, the number of passengers boarding and alighting, and weather forecasts in the short-term prediction, the prediction processing unit 141 adds, for example, the number of sales by hour on the same day of the week for the past two months to the increased number of sales based on the number of coupons that expire on that day, and multiplies this by a weather coefficient according to the weather forecast and a passenger coefficient according to the number of passengers boarding and alighting. This allows the prediction processing unit 141 to make short-term predictions in a time series for, for example, up to one week.

[0067] [Mode 2] Mode 2 is a prediction process that uses statistical processing with sales volume as the dependent variable and boarding and alighting numbers, number of coupons, and weather forecasts as explanatory variables. For example, it is possible to use the results of an analysis of electronic receipts, the analysis of coupon numbers, the analysis of passenger numbers, and actual weather data. More specifically, a multiple regression analysis is performed with the dependent variable being the sales volume of a retailer per hour, and the explanatory variables being the boarding and alighting numbers per hour at the retailer's boarding and alighting station, the number of associated coupons distributed, and weather data per hour. In this case, for example, actual weather data such as sunny, cloudy, and rainy are used as explanatory variables. In this case, sunny is quantified as 1, cloudy as 0.8, and rainy as 0.2. It is also possible to use average temperature, maximum temperature, and minimum temperature as weather data.

[0068] The prediction processing unit 141 can also perform demand prediction for each period, such as short-term prediction or seasonal prediction, based on this information. For example, the prediction processing unit 141 can calculate the relationship between the number of sales per hour Y, the number of boarding and alighting passengers per hour X1, the number of coupons with expiration dates during the sales time of the number of sales Y X2, and hourly weather data X3 through statistical processing. In other words, the prediction processing unit 141 generates a data set for analysis processing from past data in which the number of sales per hour is used as the objective variable Y and the explanatory variables X1, X2, and X3 per hour are associated, and performs calculations.

[0069] For example, the prediction processing unit 141 generates the multiple regression equation shown in equation (1).

number

[0070] In a short-term time series forecast within one week, as shown in equation (1), the hourly sales volume is used as the dependent variable Y, and the hourly number of passengers X1, the number of coupons with expiration dates X2, and the hourly weather data X3 on the forecast date are used as explanatory variables. The contribution rates of these explanatory variables X1, X2, and X3 to the dependent variable Y exceed a predetermined value. In other words, the hourly number of plant sales Y indicates a high correlation with the hourly number of passengers X1, the number of coupons with expiration dates X2, and the hourly weather data X3 on the forecast date.

[0071] The number of passengers per hour X1 is, for example, the average number of passengers at the target station for the same time period on the same day of the week for the past two months. The number of coupons X2 is the number of coupons distributed at the target station that expire on the predicted date. Furthermore, the weather data X3 is the weather (sunny, cloudy, rainy, etc.) for each hour on the predicted date at the target station.

[0072] The weather management system 304 can acquire weather information (sunny, cloudy, rainy, etc.) for each hour of the week. The prediction processing unit 141 can use the forecast data acquired by the weather management system 304. Through this process, formula (1) is generated using store information held by the receipt management system 300. As a result, formula (1) can be used to predict sales figures for stores that do not have the receipt management system 300, in addition to predicting sales figures for stores that have the receipt management system 300.

[0073] As in mode 1, for example, the prediction processing unit 141 multiplies the passenger coefficient by 1.2 if the number of passengers boarding and alighting at the time of prediction is higher than the average number for the same time period on the same day of the week at the target boarding and alighting station; by 1.0 if the number is about the same; and by 0.8 if the number is lower. The prediction processing unit 141 can calculate this passenger coefficient, for example, as the ratio of the number of passengers boarding and alighting in the hour prior to the prediction on the same day of the week to the average number for the same time period in the previous hour on the same day of the week. Note that the previous hour is an example and is not limiting. For example, it is also possible to calculate the passenger coefficient as the ratio to the average number for the same time period in the previous 24 hours in the previous hour on the same day of the week. In this way, the time range for calculating the passenger coefficient can be changed depending on the purpose.

[0074] In time-series seasonal predictions up to three months, the prediction processing unit 141 uses the sales volume for each hour on the same day of the week for three months of the previous year as the demand forecast volume. In this case, for stores that use the receipt management system 300, the calculation is performed using the actual values ​​on electronic receipts. On the other hand, for stores that do not have the receipt management system 300, the calculation is performed using Y = k1 × X1 in equation (1). In other words, the sales volume is predicted as demand based on the number of passengers boarding and alighting for each hour on the same day of the week for three months of the previous year, for example.

[0075] The prediction processing unit 141 can also multiply the demand forecast quantity by an increase coefficient to reflect fluctuations in sales volume at the time of prediction in the demand. For example, the increase coefficient is the ratio between the cumulative value of sales volume one month prior to the day on which the seasonal prediction is performed and the cumulative value for the same period of the previous year. If there is an increasing trend, the previous year's sales volume is multiplied by an increase coefficient such as 1.2. Conversely, if there is a decreasing trend, the previous year's sales volume is multiplied by an increase coefficient such as 0.8.

[0076] [Sales Plan] The sales price planning unit 151 generates a sales price plan for a predetermined period (e.g., one week). If the total demand forecast for all stores for a certain period (e.g., one day) based on a demand forecast (e.g., a weekly forecast) exceeds the total maximum production capacity plan for the same period, the sales price planning unit 151 sets the sales price higher than the base price according to the percentage of excess. For example, if the total exceeds the maximum production capacity plan, the sales price is set to twice the base price. For example, production capacity plans and maximum production capacity plans are generated based on demand forecasts (e.g., seasonal forecasts). Production capacity plans are plans regarding "when," "how much light to emit," "what temperature to set the air conditioning at," "how much power to receive," and "how much to produce." Maximum production capacity plans are plans regarding "the maximum production volume that can be produced per unit period." Production capacity plans and maximum production capacity plans will be described later.

[0077] Furthermore, if the total demand forecast for a certain period (for example, one day) of all retailers based on a demand forecast (for example, a weekly forecast) exceeds the total production capacity plan for the same period and falls below the total maximum production capacity plan for the same period, or if the total demand forecast for a certain period of all retailers falls below the total production plan for the same period, the sales price planning unit 151 will, for example, leave the sales price plan at the base price.

[0078] The sales quantity planning unit 152 generates a sales quantity plan for a predetermined period (e.g., one week). Based on a demand forecast (e.g., a weekly forecast), the sales quantity planning unit 152 matches the sales quantity plan to the maximum production capacity plan when the total demand forecast for all retailers for a certain period (e.g., one day) exceeds the total maximum production capacity plan for the same period. Furthermore, the sales quantity planning unit 152 matches the sales quantity plan to the demand forecast (e.g., a weekly forecast) when the total demand forecast for all retailers for a certain period (e.g., one day) exceeds the total production capacity plan for the same period and falls below the total maximum production capacity plan for the same period, or when the total demand forecast for all retailers for a certain period falls below the total production plan for the same period. Note that the demand forecast period, the certain period for the retailers, etc. are merely examples and can be freely set depending on the situation.

[0079] Here, the processing flow of the sales planning unit 126 will be described based on Fig. 5. Fig. 5 is a diagram showing the processing flow of the sales planning unit 126. Here, a case where the number of coupons, the number of passengers getting on and off, and weather forecasts are reflected in demand forecasts will be described.

[0080] First, the receipt analysis unit 142 calculates the number of plants sold by each store at each boarding / alighting station for each day and hour based on the data managed by the receipt record database 114. Next, the ticket analysis unit 143 quantifies the number of coupons containing the plants for sale distributed at each boarding / alighting station for each validity date based on the data managed by the ticket record database 116 (step S102).

[0081] Next, the weather forecasting processing 144 extracts weather forecast data for the area including the target boarding / alighting station from the data managed by the weather forecast database 118 (step S104). Subsequently, the passenger number analysis unit 145 analyzes the number of passengers boarding / alighting for each hour of each day at the boarding / alighting station that is the sales destination, based on the data managed by the timetable plan database 120 and the vehicle operation record database 122 (step S106). Then, the prediction processing unit 141 executes demand forecasts for each period, such as short-term forecasts and seasonal forecasts, based on this information (step S108).

[0082] Next, the production planning unit 132 generates a production capacity plan based on seasonal forecasts and the like (step S110), generates a maximum production capacity plan (step S112), and generates a production plan (step S114). Then, the production planning unit 132 stores these data in the storage unit 102. Details of the production planning unit 132 will be described later.

[0083] Next, the sales unit price planning unit 151 of the sales plan processing unit 150 generates a sales unit price plan for a predetermined period (e.g., one week) based on the demand forecast (e.g., weekly forecast) (step S116), and the sales quantity planning unit 152 generates a sales plan (step S120) by generating a sales quantity plan for a predetermined period (e.g., one week) based on the demand forecast (e.g., weekly forecast) (step S118). The sales planning unit 126 stores the finally generated sales plan (sales unit price plan, sales quantity plan) in the storage unit 102 and transmits it to the plant factory 10 via the communication unit 100. As a result, the plan contents are confirmed by the plant factory operator, and if approved, the sales plan is executed.

[0084] In this way, the sales planning unit 126 generates a sales plan in accordance with the demand forecast by the demand forecasting unit 140. The constraints at this time are the production plan generated by the production planning unit 132. In other words, the upper limit of the sales quantity is constrained by the production volume of the plant factory 10.

[0085] Here, a detailed description will be given of the delivery planning unit 128. Fig. 6 is a block diagram showing an example of the configuration of the delivery planning unit 128. Here, an example will be described in which train numbers that are available for train luggage transport are made available.

[0086] The delivery planning unit 128 includes a loading capacity prediction unit 160 and a loading plan processing unit 170. The loading capacity prediction unit 160 executes a loading capacity prediction process. The loading capacity prediction process is a process for predicting the loading capacity of a railway vehicle specified by its train number by day and time. The loading capacity prediction unit 160 includes a loading processing unit 161, an occupancy rate analysis unit 162, and a vehicle failure analysis unit 163.

[0087] The loading plan processing unit 170 generates a delivery plan for the plant factory 10. The loading plan processing unit 170 includes a loading plan unit 171 and a loading / unloading plan unit 172.

[0088] [Loading capacity prediction] Here, the loading capacity prediction process will be described in detail. The loading processing unit 161 uses the processing results of the occupancy rate analysis unit 162 and the vehicle failure analysis unit 163 to predict the loading capacity.

[0089] [Occupancy rate analysis] The passenger occupancy rate analysis unit 162 analyzes the passenger occupancy rate of trains capable of transporting luggage by train. Based on the data managed by the timetable database 120 and the vehicle operation record database 122, the passenger occupancy rate analysis unit 162 analyzes the passenger occupancy rate at each boarding / alighting station for trains capable of transporting luggage by train. More specifically, the passenger boarding / alighting number analysis unit 145 calculates the number of passengers boarding / alighting based on the difference in carbody support air spring pressure, which is part of the past boarding / alighting operation record, between boarding / alighting stations, based on the timetable plan for the boarding / alighting station where the train is sold and the train arrival time. In other words, an increase in load indicates an increase in the number of passengers, and a decrease indicates a decrease in the number of passengers. This enables the passenger occupancy rate analysis unit 162 to analyze the passenger occupancy rate between boarding / alighting stations. The passenger occupancy rate analysis unit 162 performs such analysis on data from, for example, the past year.

[0090] [Failure rate analysis] The vehicle failure analysis unit 163 analyzes the failure rate of train numbers that are capable of transporting luggage by train. The vehicle failure analysis unit 163 analyzes the failure rate of train numbers that are capable of transporting luggage by train, based on the data managed by the timetable database 120 and the vehicle operation record database 122. The vehicle failure analysis unit 163 analyzes the vehicle failure rate based on the timetable and train arrival times, and on past boarding and alighting operation record information. The vehicle failure analysis unit 163 performs such an analysis on data for the past year, for example.

[0091] [Loading capacity prediction processing] Based on this information, the loading processing unit 161 performs, for example, a one-week loading capacity prediction. For example, the loading processing unit 161 calculates the average value of the loading quantity between boarding and alighting stations for the same train number on the same day of the week for the past two months based on the information in the timetable plan database 120, and sets this as the prediction reference value. The loading processing unit 161 sets, for example, the average of the occupancy rates between boarding and alighting stations for the same train number on the same day of the week for the past two months as the predicted occupancy rate. Similarly, the loading processing unit 161 sets, for example, the average of the vehicle failure rates between boarding and alighting stations for the same train number on the same day of the week for the past two months as the predicted vehicle failure rate.

[0092] Then, if the predicted occupancy rate is high, the loading processing unit 161 calculates the loading capacity prediction to be lower than the predicted reference value obtained by the timetable plan, and if the predicted occupancy rate is low, the loading processing unit 161 calculates the loading capacity prediction to be higher than the predicted reference value. Also, if the predicted vehicle failure rate is high, the loading capacity prediction calculates the loading quantity to be lower than the predicted reference value obtained by the timetable plan, and if the predicted vehicle failure rate is low, the loading processing unit 161 calculates the loading quantity to be the same as the predicted reference value. Through this processing, the loading processing unit 161 can predict the loading capacity even in train baggage transportation.

[0093] [Shipping Plan] The loading plan processing unit 170 generates a delivery plan for a predetermined period (for example, one week). The delivery plan includes a loading plan and a loading / unloading plan. The loading plan is a plan regarding "from which boarding / unloading station," "by which train number," and "how much to load." The loading / unloading plan is a plan regarding "at which boarding / unloading station," "by which train number," and "how much to unload." The freshness plan is a plan regarding "the longest period during which quality cannot be maintained." The freshness plan is an upper limit value determined by the variety of plant being produced. This upper limit value is predetermined for each plant and stored in the memory unit 102 as a freshness plan.

[0094] The constraints on the delivery plan are the sales volume plan and the freshness plan. When using train freight transport, the constraints are the sales volume plan, the freshness plan, and the loading capacity forecast. Ideally, the delivery plan would be planned so as to match the sales volume plan, but it is difficult to match the sales volume plan because it is necessary to maintain a certain level of freshness for the produced plants and, when using train freight transport, the amount that can be loaded onto a railcar is limited.

[0095] For this reason, when train luggage transport is used, the loading planning unit 171 of the loading plan processing unit 170 generates a loading plan that matches the predicted loading capacity at the boarding and disembarking stations where loading from the plant factory 10 is possible. When the total of the sales quantity plans for all boarding and disembarking stations for a certain period (for example, one day) exceeds the total of the loading capacity plans for the same period, the loading planning unit 171 generates a loading plan with the total amount of the loading capacity plans as the upper limit. Note that when train luggage transport is not used, the loading planning unit 171 can generate a loading plan excluding the constraints of the loading capacity plans.

[0096] In addition, if the total sales volume plan for all boarding and disembarking stations for a certain period (for example, one day) is less than the total loading capacity plan for the same period and can satisfy the freshness plan, the loading planning unit 171 generates a loading plan in which, for example, the delivery plan matches the sales volume plan.

[0097] The loading and unloading plan unit 172 of the loading plan processing unit 170 generates a loading and unloading plan for each boarding and unloading station. The loading and unloading plan unit 172 generates a loading and unloading plan for each boarding and unloading station based on the loading plan so as to satisfy the sales quantity plan of each retailer. The loading plan processing unit 170 generates the loading plan and the loading and unloading plan as a delivery plan, stores them in the memory unit 102, and transmits the delivery plan to the plant factory operator of the plant factory 10 via the communication unit 100. As a result, the plant factory operator confirms the plan contents, and if approved, the plan is executed.

[0098] Here, the flow of processing by the delivery planning unit 128 will be described based on Fig. 7. Fig. 7 is a diagram showing the flow of processing by the delivery planning unit 128. Here, a case where train luggage transportation is used will be described.

[0099] First, the passenger load factor analysis unit 162 analyzes the passenger load factor at each boarding / alighting station of train numbers that can transport luggage by train, based on the data managed by the timetable planning database 120 and the vehicle operation record database 122 (step S200). Next, the vehicle failure analysis unit 163 analyzes the failure rate of train numbers that can transport luggage by train, based on the data managed by the timetable planning database 120 and the vehicle operation record database 122 (step S202). The loading processing unit 161 performs a loading capacity prediction, for example, for one week, based on this information (step S204).

[0100] Next, the loading plan unit 171 of the loading plan processing unit 170 generates a loading plan based on the sales quantity plan, the freshness plan, and the loading capacity prediction, in accordance with the loading capacity prediction at the boarding and disembarking stations where loading is possible from the plant factory 10 (step S206). Subsequently, the loading and disembarking plan unit 172 of the loading plan processing unit 170 generates a loading and disembarking plan for each boarding and disembarking station (step S208).

[0101] Next, the delivery planning unit 128 stores the finally generated delivery plan (loading plan, unloading plan) in the storage unit 102 and transmits it to the plant factory 10 via the communication unit 100 (step S210). As a result, the plant factory operator checks the plan contents, and if approved, the delivery plan is executed.

[0102] In this way, the delivery planning unit 128 generates a delivery plan in accordance with the sales volume plan and the freshness plan. The constraints at this time are the loading capacity predictions of the loading capacity prediction unit 160.

[0103] Here, a detailed description will be given of the power procurement planning unit 130. Fig. 8 is a block diagram showing an example of the configuration of the power procurement planning unit 130.

[0104] The power procurement planning unit 130 includes a power prediction unit 180 and a power procurement planning processing unit 190. The power prediction unit 180 executes power supplier supply capacity prediction processing and power supplier cost prediction processing. The power prediction unit 180 includes a supply capacity analysis unit 181 and a cost analysis unit 182.

[0105] The power procurement plan processing unit 190 generates a power procurement plan for the plant factory 10. The power procurement plan processing unit 190 includes a power procurement capacity planning unit 191 and a maximum power procurement cost planning unit 192.

[0106] [Power Procurement Plan] The power procurement plan processing unit 190 generates a power procurement plan for a predetermined period (for example, one week). The power procurement capacity plan is a plan regarding "when," "from which power supply source," and "how much can be procured." The maximum power procurement cost plan is a plan regarding "what is the maximum cost that can be spent on power procurement per unit period." The maximum power procurement cost plan is a constant upper limit value determined from the profit and loss perspective by the plant factory operator using this system.

[0107] The constraints on the power procurement capacity plan are the supply capacity and cost of the power supplier. Ideally, the power procurement capacity plan should be made to match the production capacity plan, but depending on the supply capacity and power procurement cost of the power supplier, it can be difficult to match the production capacity plan.

[0108] For this reason, the supply capacity analysis unit 181 of the power prediction unit 180 analyzes, for example, the average value for the same day of the week and the same time period over the past two months as the power supply status based on the data in the power supply database 124. In this way, the supply capacity analysis unit 181 analyzes "which power supplier can supply how much power and when." The supply capacity analysis unit 181 also calculates the average value for the same day of the week and the same time period over the past two months of the regenerative power record, which is part of the vehicle operation record recorded in the power supply database 124. The supply capacity analysis unit 181 sets this average value as the regenerative power prediction value.

[0109] The cost analysis unit 182 of the power prediction unit 180 analyzes the price per unit of power for the same day of the week and the same time period over the past two months as the cost status based on the data in the power supply database 124. In this way, the cost analysis unit 182 analyzes "which power company can supply power, when, and at what price per unit of power".

[0110] Furthermore, the power procurement capacity planning unit 191 of the power procurement plan processing unit 190 breaks down a certain period (for example, one week) specified by the power procurement capacity plan into hourly intervals, and selects the power procurement source with the lowest predicted power procurement cost for each time period as the power procurement capacity plan. In this case, if a predicted regenerative power value is included in each time period, regenerative power is selected. Furthermore, if the predicted power procurement supply capacity for the power procurement source with the lowest predicted cost for the same time period exceeds the amount of power required by the production capacity plan for the same time period, the power procurement capacity planning unit 191 selects the power procurement source with the next lowest predicted power procurement cost, and continues to select power procurement sources until the amount of power required by the predicted production capacity can be secured, thereby generating a power procurement capacity plan.

[0111] If the total power procurement costs required for the power procurement capacity plan specified by the power procurement capacity planning unit 191 are lower than the maximum power procurement cost plan for the same period (e.g., one week), the maximum power procurement cost planning unit 192 of the power procurement plan processing unit 190 generates a maximum power procurement cost plan that matches the power procurement plan with the production capacity plan. On the other hand, if the total power procurement costs required for a certain period (e.g., one week) specified by the power procurement capacity plan exceed the maximum power procurement cost plan for the same period, the maximum power procurement cost planning unit 192 generates a maximum power procurement cost plan that suppresses the amount of power so that the power procurement plan matches the maximum power procurement cost. In other words, the amount of power required for the production plan is suppressed using the power procurement plan as a reference for the maximum power procurement cost.

[0112] Here, the flow of processing by the power procurement planning unit 130 will be described with reference to Fig. 9. Fig. 9 is a diagram showing the flow of processing by the power procurement planning unit 130.

[0113] First, the cost analysis unit 182 and the supply capacity analysis unit 181 analyze, for example, the average value for the same day of the week and the same time period over the past two months as the power supply state based on the data in the power supply database 124 (step S300). Next, the cost analysis unit 182 analyzes, for example, the price per unit of power for the same day of the week and the same time period over the past two months as the cost state based on the data in the power supply database 124 (step S302).

[0114] Next, the power procurement capacity planning unit 191 breaks down the fixed period (e.g., one week) defined by the power procurement capacity plan into hourly intervals, and generates a power procurement capacity plan by selecting the power procurement source that will have the lowest predicted power procurement cost for each time period (step S304). Subsequently, the maximum power procurement cost planning unit 192 generates a power procurement plan in which the total required power procurement cost in the power procurement capacity plan for the fixed period defined by the power procurement capacity planning unit 191 is within a predetermined value (e.g., a production capacity plan value) (step S206).

[0115] Next, the power procurement planning unit 130 stores the finally generated power procurement plan (power procurement capacity plan, maximum power procurement cost plan) in the storage unit 102 and transmits it to the plant factory 10 via the communication unit 100. This allows the plant factory operator to confirm the plan contents, and if approved, the power procurement plan is executed.

[0116] Here, a detailed description will be given of the production planning unit 132. FIG.

[0117] The production planning unit 132 includes a light intensity prediction unit 200 and a production plan processing unit 210. The light intensity prediction unit 200 includes a light intensity analysis unit 201 and a power consumption analysis unit 202. The production plan processing unit 210 includes a production capacity planning unit 211 and a maximum production capacity planning unit 212. The production planning unit 132 executes large production capacity planning processing and production capacity planning processing. As described above, the production capacity plan is a plan regarding "when," "how much light to emit," "what temperature to set the air conditioning," "how much power to receive," and "how much to produce." The maximum production capacity plan is a plan regarding "the maximum production volume that can be produced per unit period." The maximum production capacity plan is an upper limit constant value determined by the light intensity and set temperature specified by the plant factory 10 being operated and the variety of plants to be produced.

[0118] [Production Capacity Planning] The production capacity planning unit 211 generates a production capacity plan so that it matches the sum of the demand forecast values ​​at all stations 40 to 50 days from now generated by the demand forecasting unit 140 of the sales planning unit 126. On the other hand, if the weather forecast also shows that the weather will be unseasonable and the hours of sunshine will be extremely short, or if the outside temperature will be significantly high or low, it will become difficult to match the demand forecast values, for example by limiting the amount of light emitted and air conditioning settings to a range that uses the amount of electricity that can be procured at a cost below the maximum electricity procurement cost plan, which is part of the electricity procurement plan.

[0119] Therefore, the light intensity analysis unit 201 analyzes the hourly "light intensity" and "air conditioning temperature setting" so that they match the production volume predicted for demand at all stations 40 to 50 days from now. The power amount analysis unit 202 analyzes the amount of power required for maintaining the "light intensity" and "air conditioning temperature setting" set by the light intensity analysis unit 201 for each hour. This analysis reflects the light intensity and temperature predicted by the weather forecast data in the weather forecast database 118 obtained via the weather management system 304.

[0120] That is, the production capacity planning unit 211 generates a production capacity plan by adding the required power so that it matches the sum of the demand forecast values ​​at all stations 40 to 50 days from now. In other words, the production capacity planning unit 211 generates a production capacity plan for "when," "how much light to emit," "what temperature to set the air conditioning to," "how much power to receive," and "how much to produce."

[0121] As described above, there is a limit to the production volume of the plant factory 10. Therefore, when the total plant production volume of the production capacity planning unit 211 exceeds the upper limit of the production volume of the plant factory 10, the maximum production capacity planning unit 212 prioritizes the production volume of plants with high unit prices and expected sales volumes, for example, and sets the maximum production volume as a new production capacity plan.

[0122] Here, the flow of processing by the production planning unit 132 will be described with reference to Fig. 11. Fig. 11 is a diagram showing the flow of processing by the production planning unit 132.

[0123] First, the light intensity analysis unit 201 analyzes the hourly "light intensity" and "air conditioning temperature setting" so that they match the production volume predicted for demand at all stations 40 to 50 days from now (step S300). Next, the power amount analysis unit 202 analyzes the amount of power required to maintain the "light intensity" and "air conditioning temperature setting" set by the light intensity analysis unit 201 for each hour (step S302).

[0124] Next, based on this information, the production capacity planning unit 211 generates a production capacity plan for a period of about 40 to 50 days, including "when," "how much light to emit," "what temperature to set the air conditioning at," "how much power to receive," and "how much to produce" (step S404). At this time, the planned values ​​are changed to those in accordance with the maximum power procurement cost plan. Subsequently, the maximum production capacity planning unit 212 modifies the production capacity plan so that the total plant production volume calculated by the production capacity planning unit 211 is within the upper limit of the production volume of the plant factory 10 (step S406).

[0125] As explained in FIG. 9, this production capacity plan is constrained to be within the range of the maximum electricity procurement cost plan. Also, as explained in FIG. 5, the sales volume plan is constrained by the production plan. Furthermore, as explained in FIG. 7, the sales volume plan is constrained by the loading plan. In other words, the sales volume plan is constrained to be within the upper production limit based on the demand forecast, within the range of the maximum electricity procurement cost plan, and, if rail freight transport is used, within the range of the loading plan based on the loading capacity forecast.

[0126] The plant factory 10 is attracting attention for the following reasons: It can stabilize food production. Because a consistent production volume can be maintained throughout the year, regardless of the season or climate, it enables a stable food supply and production in response to demand. It minimizes the impact on the local area. Because it can be installed in urban or densely populated areas, it reduces the energy and resource consumption required for agricultural land use and transportation. It enables pesticide-free cultivation. Since plant factories do not require the use of pesticides to control pests and pathogens, safer food production is expected. It can efficiently use water. It uses a circulating water system, allowing crops to be grown with significantly less water than traditional agriculture. High production efficiency is expected. The use of lighting technology maximizes photosynthesis, improving crop production efficiency. Furthermore, optimizing the cultivation environment shortens the growth cycle, allowing more crops to be grown in a shorter period of time. It can contribute to combating global warming. In addition to reducing carbon dioxide emissions, it also reduces the energy required for transportation, which is effective in combating global warming. The operation support system 1 according to this embodiment can more efficiently support the operation of such a plant factory 10.

[0127] As described above, according to this embodiment, the sales planning unit 126 predicts the number of plants produced in the plant factory sold for each station during a predetermined period based on information about the past number of passengers boarding and alighting at each station. This allows the number of plants sold to be predicted according to the number of passengers boarding and alighting at each station, making it possible to generate a sales plan that minimizes the impact of the number of passengers using the stations. [Explanation of symbols]

[0128] 1: Operation support system, 10: plant factory, 20: operation support device, 100: communication unit (acquisition unit), 102: memory unit, 104: control processing unit, 126: sales planning unit, 128: delivery planning unit, 130: power procurement planning unit, 132: production planning unit.

Claims

1. an acquisition unit that acquires information regarding the past number of passengers boarding and alighting at each train boarding and alighting station; a storage unit that stores the information; a sales planning unit that predicts the number of plants to be produced in the plant factory for each of the boarding and alighting stations for a predetermined period based on the information stored in the storage unit, and generates a sales plan; A plant factory operation support device equipped with the above.

2. the information is past receipt information regarding an electronic receipt that associates the number of plants produced in the plant factory sold, the time of sale, and the boarding and alighting station; The plant factory operation support device according to claim 1 , wherein the sales planning unit predicts the number of sales of the plant for each of the boarding and alighting stations based on past sales numbers at the boarding and alighting stations during the same time period.

3. the information is data relating to weight information of a railway vehicle stopping at the boarding / alighting station, the weight information being associated with time; 3. The plant factory operation support device according to claim 1, wherein the sales planning unit calculates the number of passengers boarding and alighting at the boarding and alighting stations according to a weight difference between the vehicles based on the weight information, and predicts or changes the predicted sales number of the plants for each boarding and alighting station according to the number of passengers boarding and alighting.

4. The information includes weather forecast data; The plant factory operation support device according to claim 3 , wherein the sales planning unit changes the predicted number of sales in accordance with the weather forecast data.

5. The information includes coupon information associated with the number of coupons for the plants distributed at the boarding and alighting stations and expiration dates; The plant factory operation support device according to claim 4 , wherein the sales planning unit changes the predicted number of sales at the boarding and disembarking station depending on the number of coupons having the expiration date on the sales date distributed at the boarding and disembarking station.

6. The plant factory operation support device according to claim 3 , further comprising: a delivery planning unit that generates a delivery plan to the boarding and disembarking station based on the predicted number of sales at the boarding and disembarking station.

7. The information includes data relating to weight information of a train baggage transport vehicle stopping at the boarding / alighting station, the weight information being associated with time; The plant factory operation support device according to claim 6 , wherein the delivery planning unit predicts a load capacity of the train baggage transport vehicle based on the weight information and a difference in weight between stations.

8. The plant factory operation support device according to claim 6 , further comprising: a production planning unit that generates a production plan for the plants based on the predicted number.

9. The plant factory operation support device according to claim 8 , wherein the production plan includes a production number of the plants and an amount of electricity used for each predetermined time period.

10. The plant factory operation support device according to claim 9 , further comprising: a power procurement planning unit that generates the power procurement plan for each of the predetermined time periods.

11. The information includes data relating information on regenerative power of the railway vehicle to time, The plant factory operation support device according to claim 10 , wherein the power procurement planning unit generates the procurement plan including procurement of the regenerative power corresponding to the predetermined time.

12. 12. The plant factory operation support device according to claim 11, wherein the acquisition unit converts the information into a data format that can be processed by at least one of the sales planning unit, the delivery planning unit, the power procurement planning unit, and the production planning unit, and stores the converted information in a storage unit.

13. an acquisition step of acquiring information regarding the past number of passengers boarding and alighting at each train boarding and alighting station; a sales planning process for predicting the number of plants produced in the plant factory to be sold for a predetermined period for each of the boarding and disembarking stations based on the information; A method for supporting the operation of a plant factory.

14. an acquisition step of acquiring information regarding the past number of passengers boarding and alighting at each train boarding and alighting station; a sales planning step of predicting the number of plants produced in the plant factory for sale for a predetermined period at each of the stations based on the information; A plant factory operation support program that runs the following on a computer.

Images