Product shipment prediction apparatus, system, method and program

Abstract

To provide a product shipment prediction apparatus, and the like, which can contribute to providing useful information to producers while taking into account future demand and supply of products.SOLUTION: A product shipment prediction apparatus includes: a data acquisition unit configured to acquire data at introduction, data at cultivation, data at shipment representing characteristics of animals and plans at the time of introduction, cultivation and shipment, respectively, and demand-supply influence data that affects demand and supply of products related to the animals and plants; and a shipment prediction unit configured to predict shipment of the products, based on the data at introduction and the data at cultivation with a request for a result of predicting shipment, using the data at introduction, the data at cultivation, the data at shipment, and the demand-supply influence data.SELECTED DRAWING: Figure 15

Description

[Technical field]

[0001] The present invention relates to a product shipment forecasting device, system, method, and program. [Background technology]

[0002] In recent years, information processing devices and systems have been proposed that collect various information on livestock animals from their birth to their shipment and use machine learning to create a learning model, and then use the learning model to predict or estimate the breeding methods for other livestock animals, as well as the quality, quantity, and trading status of livestock products (meat, skin, hair, bones, etc.) obtained from livestock animals at the time of future shipment (see, for example, Patent Documents 1 to 3).

[0003] Patent Document 1 discloses an information processing system that acquires, as teaching information, breeding information related to the breeding of an animal and meat information related to the meat of the animal, learns correspondence information that represents the correspondence between the breeding information and the meat information, acquires new meat information after learning, and uses the correspondence information to output breeding information that corresponds to the newly acquired meat information.

[0004] Patent Document 2 also discloses an information processing device that acquires physical information about individual livestock, feed information about the feed given to the livestock, environmental information about the environment in which the livestock are raised, and quality information about the quality of livestock slaughtered after shipping, and uses machine learning to generate a predictive model that predicts meat quality; it also acquires new information from among the physical information, feed information, environmental information, and quality information, and uses the generated predictive model to predict meat quality corresponding to the newly acquired information.

[0005] Furthermore, Patent Document 3 discloses a meat trading status estimation system that acquires procurement conditions, including a desired procurement time for the meat to be procured, from a consumer who procures meat, and estimates future shipping status of the livestock using farmed livestock information, including information on the farming status of the livestock corresponding to the meat, and past livestock information, including information on the farming status of the livestock that have been farmed in the past, acquires market information including meat trading information, including information on the meat supply volume of the livestock in the wholesale market for the livestock, and estimates future meat trading status including the future meat supply volume at the desired procurement time using the future shipping status and the market information, and notifies the consumer of the estimated future meat trading status. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent Publication No. 2020-161043 [Patent Document 2] Patent Publication No. 2021-140512 [Patent Document 3] Patent Publication No. 2021-96606 Summary of the Invention [Problem to be solved by the invention]

[0007] The following analysis is provided by the present inventors.

[0008] In recent years, meat consumption has been increasing worldwide, and the productivity of livestock products has been improved by administering growth agents to livestock animals. Increasing productivity can lead to poor growth of livestock animals and a decrease in the production of high-quality livestock products. For this reason, it is desirable to provide livestock farmers (producers) with useful information about livestock animals so that they can supply high-quality livestock products with an eye to the future demand and supply of livestock products. The same can be said for products obtained from plants and animals other than livestock animals, such as agricultural crops and farmed products. In this regard, Patent Documents 1 to 3 do not provide livestock farmers with information about livestock animals with an eye to the future demand and supply of livestock products.

[0009] The main objective of the present invention is to provide a product shipment forecasting device, system, method, and program that can contribute to providing useful information to producers in anticipation of future demand and supply of products. [Means for solving the problem]

[0010] The product shipment prediction device according to a first aspect includes a data acquisition unit configured to acquire introduction time data, cultivation time data, and shipping time data representing characteristics of animals and plants at the time of introduction, cultivation, and shipment, as well as supply and demand impact data that affects the supply and demand of products related to the animals and plants, and a shipment prediction unit configured to predict the shipment of the product based on the introduction time data or the cultivation time data accompanied by a request for a predicted shipping result, using the introduction time data, cultivation time data, shipping time data, and supply and demand impact data.

[0011] A product shipment forecasting system according to a second aspect comprises the product shipment forecasting device according to the first aspect, an animal and plant management device configured to manage information relating to the animals and plants grown on-site and to transmit the introduction data, cultivation data, and shipping data of the animals and plants to the product shipment forecasting device, and an information providing device configured to transmit the supply and demand impact data to the product shipment forecasting device.

[0012] A product shipment forecasting method according to a third aspect is a product shipment forecasting method for predicting shipment of a product related to an animal or plant using hardware resources, the method including the steps of: the hardware resources acquiring introduction time data, cultivation time data, and shipping time data representing characteristics of the animal or plant at the time of introduction, cultivation, and shipping, as well as supply and demand impact data that influences supply and demand of the product; and the hardware resources using the introduction time data, cultivation time data, shipping time data, and supply and demand impact data to predict shipment of the product based on the introduction time data or the cultivation time data accompanied by a request for a predicted shipping result.

[0013] A program relating to a fourth aspect is a program that causes hardware resources to execute a process of predicting shipment of an animal or plant product, wherein the hardware resources execute a process of acquiring introduction time data, cultivation time data, and shipping time data that represent characteristics of the animal or plant at the time of introduction, cultivation, and shipping, as well as supply and demand impact data that affects the supply and demand of the product, and a process of predicting shipment of the product based on the introduction time data or the cultivation time data accompanied by a request for a predicted shipping result, using the introduction time data, cultivation time data, shipping time data, and supply and demand impact data.

[0014] The program can be recorded in a computer-readable storage medium. The storage medium can be a non-transient medium such as a semiconductor memory, a hard disk, a magnetic recording medium, or an optical recording medium. In addition, the present disclosure can be embodied as a computer program product. The program is input to the computer device from an input device or an external device via a communication interface, stored in a storage device, drives the processor according to a predetermined step or process, and can display the processing result, including an intermediate state as necessary, at each stage via a display device, or can communicate with the outside via the communication interface. For example, a computer device for this purpose typically includes a processor, a storage device, an input device, a communication interface, and a display device as necessary, which are connectable to each other via a bus. Effect of the Invention

[0015] The first to fourth aspects can contribute to providing producers with useful information in anticipation of future demand and supply of products. [Brief description of the drawings]

[0016] [Figure 1] 1 is a block diagram illustrating a schematic configuration of a product shipment forecasting system according to a first embodiment. [Diagram 2]4 is a table illustrating an example of introduction time data used in the product shipment forecasting system according to the first embodiment. [Diagram 3] 3 is a table illustrating an example of growing-time data used in the product shipment prediction system according to the first embodiment. [Figure 4] 3 is a table that illustrates an example of shipping data used in the product shipping prediction system according to the first embodiment. [Diagram 5] 1 is a graph showing a schematic example of a learning model for predicting a possible shipping time used in the product shipment forecasting system according to the first embodiment. [Figure 6] 1 is a graph showing a schematic example of a learning model for predicting meat weight at the time of shipment, which is used in the product shipment prediction system according to the first embodiment. [Figure 7] 1 is a graph showing a schematic example of a learning model for predicting the unit price of meat at the time of shipment, which is used in the product shipment prediction system according to the first embodiment. [Figure 8] 1 is a graph showing a schematic diagram of upper and lower limits of the unit price of meat at the time of possible shipment predicted by the product shipment prediction system according to the first embodiment. [Figure 9] 4 is a table that illustrates a forecast shipping result generated by the product shipping forecast system according to the first embodiment. [Figure 10] 4 is a flowchart illustrating an example of an operation of the product shipment forecasting device of the product shipment forecasting system according to the first embodiment when generating a learning model. [Figure 11] 1 is a flowchart illustrating an example of an operation of the product shipment forecasting device of the product shipment forecasting system according to the first embodiment when estimating a supply and demand impact degree number. [Figure 12] 4 is a flowchart illustrating an example of an operation of the product shipment prediction device of the product shipment prediction system according to the first embodiment when generating a predicted shipping result. [Figure 13] FIG. 11 is a block diagram illustrating a configuration of a product shipment forecasting system according to a second embodiment. [Figure 14]FIG. 11 is a block diagram illustrating a configuration of a product shipment forecasting system according to a third embodiment. [Figure 15] FIG. 11 is a block diagram illustrating a configuration of a product shipment prediction device according to a fourth embodiment. [Figure 16] FIG. 2 is a block diagram illustrating a schematic configuration of hardware resources. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] Hereinafter, the embodiments will be described with reference to the drawings. In addition, when drawing reference symbols are used in this application, they are intended to aid understanding only and are not intended to limit the present invention to the illustrated embodiment. In addition, the following embodiments are merely examples and do not limit the present invention. In addition, the connection lines between blocks in the drawings and the like referred to in the following description include both bidirectional and unidirectional. A unidirectional arrow is a schematic representation of the flow of a main signal (data) and does not exclude bidirectionality. Furthermore, although not explicitly shown in the circuit diagrams, block diagrams, internal configuration diagrams, connection diagrams, and the like shown in the present disclosure, an input port and an output port exist at the input end and output end of each connection line. The same is true for input / output interfaces. A program is executed via a computer device, which includes, for example, a processor, a storage device, an input device, a communication interface, and a display device as necessary, and which is configured to be able to communicate with an internal or external device (including a computer) via the communication interface, regardless of whether it is wired or wireless.

[0018] [Embodiment 1] The product shipment prediction system according to the first embodiment will be described with reference to the drawings. FIG. 1 is a block diagram showing a schematic configuration of the product shipment prediction system according to the first embodiment. FIG. 2 is a table showing a schematic example of data at the time of introduction used in the product shipment prediction system according to the first embodiment. FIG. 3 is a table showing a schematic example of data at the time of rearing used in the product shipment prediction system according to the first embodiment. FIG. 4 is a table showing a schematic example of data at the time of shipping used in the product shipment prediction system according to the first embodiment. FIG. 5 is a graph showing a schematic example of a learning model for predicting a possible shipping time used in the product shipment prediction system according to the first embodiment. FIG. 6 is a graph showing a schematic example of a learning model for predicting a meat weight at the time of shipping used in the product shipment prediction system according to the first embodiment. FIG. 7 is a graph showing a schematic example of a learning model for predicting a meat unit price at the time of shipping used in the product shipment prediction system according to the first embodiment. FIG. 8 is a graph showing a schematic example of an upper limit and a lower limit of a meat unit price at the possible shipping time predicted by the product shipment prediction system according to the first embodiment. FIG. 9 is a table that illustrates the predicted shipping results generated by the product shipping prediction system according to the first embodiment.

[0019] The product shipment prediction system 1 is a system for predicting the shipment of products (livestock products in the first embodiment) obtained from animals and plants (livestock animals in the first embodiment) (see FIG. 1). Examples of the animals and plants include livestock animals, agricultural crops, and farmed products, and the first embodiment will be described using livestock animals as an example. Examples of the products include livestock products (e.g., meat, bones, skin, hair, etc.), agricultural products, and aquatic products, and the first embodiment will be described using livestock animals as an example. Examples of the predicted shipment include the shipping time, shipping volume, shipping price, and shipping unit price of the product. The product shipment prediction system 1 has a function of generating a learning model for predicting shipment. The product shipment prediction system 1 has a function of predicting shipment in view of future demand and supply of the product. The product shipment prediction system 1 includes a product shipment prediction device 10, livestock management systems 20A to 20N, information provision devices 30A to 30M, and a network 40.

[0020] The product shipment prediction device 10 is a device that predicts the shipment of a product (in the first embodiment, livestock products) obtained from an animal or plant based on data of the animal or plant (in the first embodiment, livestock animals) at the time of introduction or cultivation (see FIG. 1). As the product shipment prediction device 10, for example, a physical server equipped with a computer function or a virtual server virtually realized on the cloud can be used. The product shipment prediction device 10 is communicably connected to the livestock management systems 20A to 20N and the information providing devices 30A to 30M via a network 40. The product shipment prediction device 10 can be virtually configured to include a data acquisition unit 11, a learning model generation unit 12, a supply and demand influence degree estimation unit 13, a storage unit 14, a shipment prediction unit 15, and a data output unit 16 by executing a predetermined program stored therein.

[0021] The data acquisition unit 11 is a functional unit that acquires data from the livestock management systems 20A-20N and the information providing devices 30A-30M (see FIG. 1). The data acquisition unit 11 acquires data at the time of introduction, data at the time of rearing, and data at the time of shipping of livestock from the livestock management systems 20A-20N (data acquisition devices 21, livestock management devices 22, manager terminal 23). The data acquisition unit 11 acquires supply and demand impact data on livestock products related to livestock from the information providing devices 30A-30M. The data acquisition unit 11 may acquire data from external terminals or devices other than the livestock management systems 20A-20N and the information providing devices 30A-30M.

[0022] Here, the data at the time of introduction is data that represents the characteristics of the livestock animals at the time of introduction (see, for example, FIG. 2). The data at the time of introduction can include, for example, the date of introduction of the livestock animals, the identification information of the livestock animals, the weight of the livestock animals, and the basic specifications of the livestock animals at the time of introduction (for example, age in months, species, breed, pedigree, appearance characteristics, images, Animal Welfare (AW) compliance level, etc.). The data at the time of introduction is used to generate a learning model. The data at the time of introduction is used to predict the shipment of the product (livestock product) when a predicted shipping result is required. The AW compliance level refers to a numerical representation of the degree of compliance with animal welfare, and can be, for example, a numerical representation of the degree of compliance with standards set by the country, prefecture, or municipality. The standards for the AW compliance level may be not only Japanese standards but also standards set by countries or organizations around the world. The AW compliance level may indicate not only the level for livestock breeders but also the level for individual livestock animals.

[0023] The rearing data is data that represents the characteristics of livestock animals during rearing, obtained periodically or at any time during the rearing period from introduction to shipping (see, for example, FIG. 3). The rearing data can include, for example, the date of rearing of the livestock animal, the identification information of the livestock animal, the weight of the livestock animal, and the basic specifications of the livestock animal during rearing (for example, age in months, appearance characteristics, images, amount of feed fed, amount of water drunk, season, weather, AW response level, administration of growth agents, etc.). The rearing data is used to generate a learning model. The rearing data is used to predict the shipment of the product (livestock product) when a predicted shipping result is required.

[0024] The shipping data is data that represents the characteristics of livestock animals (livestock products) at the time of shipping (slaughter) (see, for example, FIG. 4). The shipping data can include, for example, the date of shipping of the livestock animals (livestock products), identification information of the livestock animals (livestock products), the weight of the livestock animals, and the weight and unit price of various livestock products (meat, bones, skin, hair, etc.). The shipping data is used to generate a learning model.

[0025] The supply and demand impact data is data that affects the supply and demand of products related to animals and plants. Examples of the supply and demand impact data include information on the consumption of products during events (e.g., the Olympics, the World Expo, meat festivals, etc.), information on the consumption of products due to weather and seasons, information on the number of stores and restaurants that handle animal welfare ingredients and the consumption of products, information on the number of posts on social networking services (SNS) about animal welfare and products, information on the number of news articles about animal welfare and products, information on the number of stores that handle products registered on gourmet sites, information on nutrients for livestock animals, information on world population trends, information on preferred products by country and their quality, a survey of system users regarding the shipping time and shipping volume of products, information on the planned shipping time and shipping volume of products by system users, information on the shipping time, shipping volume, animal welfare level, and quality of products shipped by system users in the past, and information on the consumption of products due to past and current trends (e.g., inflation, deflation, etc.). In addition, data at the time of introduction, data at the time of cultivation, and data at the time of shipment may be used as the supply and demand impact data.

[0026] The learning model generation unit 12 is a functional unit that performs machine learning based on the data at the time of introduction, the data at the time of rearing, and the data at the time of shipping to generate a learning model (see, for example, Figs. 5 to 7) for predicting the shipment of a product (livestock product) (see Fig. 1). The learning model generation unit 12 may perform machine learning based on the age in months and weight of the livestock animal breed A in the data at the time of introduction, the data at the time of rearing, and the data at the time of shipping to generate a learning model for predicting the possible shipping time (see Fig. 5). The learning model generation unit 12 may also perform machine learning based on the weight and meat weight of the livestock animal breed A in the data at the time of shipping to generate a learning model for predicting the meat weight at the time of shipping (see Fig. 6). Furthermore, the learning model generation unit 12 may perform machine learning based on the shipping date (calendar), meat unit price, and AW correspondence level of the livestock animal breed A in the data at the time of shipping to generate a learning model for predicting the meat unit price at the time of shipping (see Fig. 7). Note that the learning models in Figures 5 to 7 are merely examples, and a learning model may be generated by systematically selecting data from the data at the time of introduction, the data at the time of cultivation, and the data at the time of shipment so as to predict specific parameters and features of a product at the time of shipment.

[0027] The supply and demand impact degree estimation unit 13 is a functional unit that estimates a supply and demand impact degree indicating the degree of change in shipment of a product (for example, change in unit price (predicted unit price) at the time of shipment) predicted based on a learning model based on the supply and demand impact data (see FIG. 1). The supply and demand impact degree is used to predict changes in shipment of a product in anticipation of future demand and supply of the product. The supply and demand impact degree can be set to 1 when the demand amount and the supply amount are estimated to be the same, a value greater than 1 when the demand amount is estimated to be greater than the supply amount, and a value less than 1 when the demand amount is estimated to be less than the supply amount. In other words, the supply and demand impact degree can be set to 1 when it is estimated that there will be no change with respect to the predicted unit price, a value greater than 1 when it is estimated to increase, and a value less than 1 when it is estimated to decrease. When the supply and demand impact degree is used as the degree of change in the unit price, the unit price becomes cheaper as the supply and demand impact degree becomes smaller when it is smaller than 1, and the unit price becomes higher as it is larger when it is larger than 1. The supply and demand impact degree may be estimated based on the magnitude of a quantified predetermined parameter (e.g., the number of posts, the number of articles, the number of stores, the world population, etc.) or feature amount (e.g., consumption amount, shipping amount, etc.) included in the supply and demand impact data, the number of data items of the same type of supply and demand impact data, etc. The supply and demand impact degree may be estimated for each supply and demand impact data.

[0028] The memory unit 14 is a functional unit that stores various data (see FIG. 1). The memory unit 14 includes an acquired data memory unit 14a, a learning model memory unit 14b, and a supply and demand impact degree memory unit 14c. The acquired data memory unit 14a stores data acquired by the data acquisition unit 11 (introduction time data, development time data, shipping time data, and supply and demand impact data). The learning model memory unit 14b stores the learning model generated by the learning model generation unit 12. The supply and demand impact degree memory unit 14c stores the supply and demand impact degree estimated by the supply and demand impact degree estimation unit 13.

[0029] The shipment prediction unit 15 is a functional unit that predicts the shipment of a product (livestock product) based on the data at the time of introduction or the data at the time of rearing accompanied by a request for a predicted shipping result using a learning model and a supply and demand influence degree (see FIG. 1). The shipment prediction unit 15 may predict the possible shipping time and weight based on the age and weight of the livestock animal breed A in the data at the time of introduction or the data at the time of rearing, for example, using a learning model for predicting the possible shipping time (see FIG. 5). The shipment prediction unit 15 may also predict the weight of various livestock products (meat, bones, skin, hair, etc.) based on the predicted weight, for example, using a learning model for predicting the weight of livestock products at the time of shipping (see FIG. 6). Furthermore, the shipment prediction unit 15 may predict the unit price of livestock products in the calendar corresponding to the predicted possible shipping time, for example, using a learning model for predicting the unit price of livestock products at the time of shipping (for example, for predicting the unit price of meat) (see FIG. 7). The calendar corresponding to the possible shipping time can be specified based on the introduction date, the age in months at the time of introduction, and the age in months at the possible shipping time. The shipment prediction unit 15 uses the supply and demand impact degree to predict the predicted changes in shipment of livestock products (for example, the fluctuation range (upper limit, lower limit) of the unit price of edible meat) (see Figure 8). The shipment prediction unit 15 predicts the timing when the upper limit of the change in shipment during the shipping period (for example, the fluctuation range of the unit price of edible meat) is maximized as the shipping period (see Figure 8). The shipment prediction unit 15 may predict the transaction price based on the predicted livestock product weight and unit price of livestock products. The shipment prediction unit 15 generates a predicted shipping result (see Figure 9) based on data related to the predicted shipment.

[0030] The data output unit 16 is a functional unit that outputs data (see FIG. 1). For example, the data output unit 16 outputs the predicted shipping results generated by the shipping prediction unit 15 to the manager terminal 23 of the livestock management systems 20A to 20N.

[0031] The livestock management systems 20A to 20N are systems for managing livestock raised on-site (see FIG. 1). The livestock management systems 20A to 20N each include a data acquisition device 21, a livestock management device 22, and an administrator terminal .

[0032] The data acquisition device 21 is a device that acquires characteristic data of livestock animals (e.g., weight, identification information, images, etc.) (see FIG. 1). A plurality of data acquisition devices 21 may be provided in one livestock animal management system 20A to 20N. As the data acquisition device 21, for example, a weight measurement device, an identification information acquisition device, an imaging device, an image processing device, etc. may be used. When measuring the weight of a livestock animal using the data acquisition device 21, the data acquisition device 21 may be installed in the aisle to measure the weight of the livestock animal. In the case of cattle, the weight may be estimated based on the measured scale using data corresponding to the scale (length, dimensions, area, etc.) and weight, the weight of the livestock animal may be estimated based on the size of the livestock animal in the image, the weight of the livestock animal may be estimated from a part captured in the image (for example, the outline shape), the weight of the livestock animal may be estimated by identifying the posture of the livestock animal's body, or it may be estimated from information measured by hand. In the case of livestock animals with a lot of hair (sheep, alpaca, llama, etc.), the weight may be measured before shearing, and the weight and hair weight may be measured after shearing. For livestock animals that change between rearing and shipping, the weight may be measured before and after the change.

[0033] The livestock management device 22 is a device that manages data on livestock raised on site (see FIG. 1). For example, a physical server equipped with a computer function or a virtual server virtually realized on the cloud can be used as the livestock management device 22. The livestock management device 22 is communicatively connected to the data acquisition device 21 and the manager terminal 23. The livestock management device 22 is communicatively connected to the product shipment prediction device 10 via a network 40. The livestock management device 22 stores data acquired by the data acquisition device 21 and data input by the manager terminal 23.

[0034] The manager terminal 23 is an information terminal used by a manager (which may be an operator) (see FIG. 1). There may be a plurality of manager terminals 23 in each livestock management system 20A-20N. The manager terminal 23 transmits data input by operation of the manager to the livestock management device 22. The manager terminal 23 can transmit data at the time of introduction, data at the time of rearing, or data at the time of shipping of livestock stored in the livestock management device 22 to the product shipment prediction device 10 by operation of the manager.

[0035] The information providing devices 30A to 30M are devices that provide supply and demand impact data (see FIG. 1). The information providing devices 30A to 30M are communicably connected to the product shipment forecasting device 10 via a network 40. The information providing devices 30A to 30M transmit the supply and demand impact data to the product shipment forecasting device 10 in response to access from the product shipment forecasting device 10.

[0036] The network 40 is an information and communication network that communicatively connects the product shipment prediction device 10, the livestock management systems 20A to 20N, and the information providing devices 30A to 30M among each other. As the network 40, for example, a communication network such as a personal area network (PAN), a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), or a global area network (GAN) can be used.

[0037] Next, the operation of the product shipment forecasting device of the product shipment forecasting system according to the first embodiment will be described.

[0038] The operation of the product shipment forecasting device of the product shipment forecasting system according to the embodiment 1 when generating a learning model will be described with reference to the drawings. Fig. 10 is a flow chart that illustrates the operation of the product shipment forecasting device of the product shipment forecasting system according to the embodiment 1 when generating a learning model. Please refer to Fig. 1 for the configuration of the product shipment forecasting system.

[0039] First, the data acquisition unit 11 of the product shipment prediction device 10 collects (acquires) introduction data of livestock animals (e.g., see Figure 2) from the livestock management systems 20A to 20N, and stores the collected introduction data in the acquired data memory unit 14a of the memory unit 14 (step A1).

[0040] Next, the data acquisition unit 11 collects (acquires) livestock rearing data (eg, see FIG. 3) from the livestock management systems 20A to 20N, and stores the collected rearing data in the acquired data storage unit 14a of the storage unit 14 (step A2).

[0041] Next, the data acquisition unit 11 collects (acquires) livestock shipping data (eg, see FIG. 4) from the livestock management systems 20A to 20N, and stores the collected shipping data in the acquired data storage unit 14a of the storage unit 14 (step A3).

[0042] Next, the learning model generation unit 12 of the product shipment prediction device 10 performs machine learning based on the collected data at the time of introduction, data at the time of rearing, and data at the time of shipping to generate a learning model (for example, see Figs. 5 to 7) for product (livestock product) shipment prediction, stores the generated learning model in the learning model storage unit 14b of the storage unit 14 (step A4), and then terminates. Note that the generation of the learning model can be performed periodically or at any time.

[0043] The operation of the product shipment forecasting device of the product shipment forecasting system according to the embodiment 1 when estimating the supply and demand impact degree will be described with reference to the drawings. Fig. 11 is a flow chart showing a schematic operation of the product shipment forecasting device of the product shipment forecasting system according to the embodiment 1 when estimating the supply and demand impact degree. Please refer to Fig. 1 for the configuration of the product shipment forecasting system.

[0044] First, the data acquisition unit 11 of the product shipment prediction device 10 collects (acquires) supply and demand impact data from the information provision devices 30A to 30M, and stores the collected supply and demand impact data in the supply and demand impact degree storage unit 14c of the storage unit 14 (step B1). The supply and demand impact data can be collected periodically or at any time.

[0045] Next, the supply and demand impact degree estimation unit 13 of the product shipment prediction device 10 estimates a supply and demand impact degree indicating the degree of change in product shipment (for example, change in unit price (predicted unit price) at the time of shipment) predicted based on the learning model based on the supply and demand impact data, stores the estimated supply and demand impact degree in the supply and demand impact degree storage unit 14c of the storage unit 14 (step B2), and then terminates. Note that the supply and demand impact degree can be estimated periodically or at any time.

[0046] The operation of the product shipment forecast device of the product shipment forecast system according to the first embodiment when generating a forecast shipping result will be described with reference to the drawings. Fig. 12 is a flow chart showing a schematic operation of the product shipment forecast device of the product shipment forecast system according to the first embodiment when generating a forecast shipping result. Please refer to Fig. 1 for the configuration of the product shipment forecast system.

[0047] First, the data acquisition unit 11 of the product shipment prediction device 10 acquires the introduction data (e.g., see FIG. 2) or the rearing data (e.g., see FIG. 3) accompanied by a request for a predicted shipping result from the manager terminal 23 (which may be the data acquisition device 21 or the livestock management device 22) of any of the livestock management systems 20A to 20N (step C1). The introduction data or the rearing data acquired in step C1 may be stored in the acquired data storage unit 14a of the storage unit 14 and used to generate a learning model.

[0048] Next, the shipment prediction unit 15 of the product shipment prediction device 10 predicts the shipment of the product (livestock product) (e.g., the available shipping time, weight of livestock animals, weight of livestock products, unit price of livestock products, etc.) based on the data at the time of introduction or the data at the time of rearing accompanied by a request for predicted shipping results, using a learning model (e.g., a learning model for predicting the available shipping time (see Figure 5), a learning model for predicting the weight of livestock products at the time of shipping (see Figure 6), a learning model for predicting the unit price of livestock products at the time of shipping (e.g., for predicting the unit price of meat) (see Figure 7)) (step C2). In step C2, the shipping time, etc. are predicted based on the learning model without using the supply and demand impact degree number. Note that when data collection is insufficient and there is no learning model, a statistical model created in advance using a statistical method may be utilized.

[0049] Next, the shipment prediction unit 15 predicts the predicted change in shipment of livestock products (for example, fluctuation range of unit price (upper limit, lower limit)) using the supply and demand impact degree (step C3). When the supply and demand impact degree is not available due to insufficient data collection, the supply and demand impact degree may be set to 1.

[0050] Next, the shipment prediction unit 15 predicts the timing at which the upper limit of the change in shipment (e.g., fluctuation range of unit price) during the possible shipment period predicted in step C2 is maximized as the shipment period (e.g., see FIG. 8) (step C4).

[0051] Next, the shipment prediction unit 15 generates a predicted shipping result (for example, see FIG. 9) including the results predicted in steps C2 to C4, and outputs the generated predicted shipping result via the data output unit 16 to the manager terminal 23 (or the livestock management device 22) of any of the livestock management systems 20A to 20N that requested the predicted shipping result (step C5), and then ends. This allows the manager terminal 23 to display the presented information, and the manager can check the presented information and decide when to ship.

[0052] According to embodiment 1, the learning model and the supply and demand influence factor are used to predict the shipment of products based on data at the time of introduction or data at the time of cultivation, which can contribute to providing producers with useful information (information on the shipment time of products, weight of animals and plants, products (livestock products, unit price, trading price, etc.)) in anticipation of future demand and supply of products.

[0053] Furthermore, according to the first embodiment, by utilizing the provided information, it becomes possible to increase high-quality products and meet demand.

[0054] Furthermore, according to the first embodiment, by utilizing the provided information, products can be shipped at a time when their commercial value is high.

[0055] In addition, as interest in livestock products that consider animal welfare is growing worldwide, according to embodiment 1, animal welfare-compliant livestock products will be produced in Japan as well, and production in response to demand for livestock products raised using specific feeding methods, such as animal welfare-compliant foods, can contribute to increasing the value of livestock products.

[0056] Furthermore, according to embodiment 1, even for sheep that are shipped as livestock products separated into meat, wool, bones, skin, etc., the weight at the time of shipping can be known, and the weight of the meat included in the weight, as well as the weight of non-meat items such as wool, bones, skin, etc. can also be known, allowing producers to determine the appropriate shipping amount.

[0057] [Embodiment 2] The product shipment forecasting system according to the second embodiment will be described with reference to the drawings. Fig. 13 is a block diagram showing a schematic configuration of the product shipment forecasting system according to the second embodiment.

[0058] The second embodiment is a modification of the first embodiment, and includes a rearing plan generating unit 17 so that a rearing plan for the corresponding animal or plant can be provided when the growth period (age, month, day, week, day, etc.) of the animal or plant at the predicted shipping time is earlier or later than the appropriate growth period. When the growth period of the animal or plant at the shipping time predicted by the shipping prediction unit 15 is earlier or later than the appropriate growth period set in advance, the rearing plan generating unit 17 generates a rearing plan based on information on growth (e.g., feeding amount, drinking water amount, administration of growth agent, etc.) included in the data (introduction time data, rearing time data, shipping time data) stored in the acquired data storage unit 14a of the storage unit 14, and outputs the generated rearing plan through the data output unit 16 to the manager terminal 23 (or the livestock management device 22) of any of the livestock management systems 20A to 20N that have requested the predicted shipping result. The other configurations and operations are the same as those of the first embodiment.

[0059] According to the second embodiment, as in the first embodiment, it is possible to contribute to providing useful information to producers in anticipation of future demand and supply of products, and since a growth plan is generated based on the growth period of plants and animals at the predicted shipping time, by utilizing the generated growth plan, it is possible to meet demand while suppressing deterioration in the quality of products whose shipment is brought forward or delayed.

[0060] [Embodiment 3] A product shipment forecasting system according to the third embodiment will be described with reference to the drawings. Fig. 14 is a block diagram showing a schematic configuration of the product shipment forecasting system according to the third embodiment.

[0061] The third embodiment is a modified example of the first embodiment, and includes an introduction plan generating unit 18 that uses a learning model to back-calculate and propose an introduction time (including the addition of a rearing period such as age in months or days) using a shipping time when demand is high as a reference point. When the introduction plan generating unit 18 receives a request for an introduction plan from the manager terminal 23 of any of the livestock management systems 20A to 20N, the introduction plan generating unit 18 extracts a shipping time in which the degree of change in product shipment (for example, change in unit price (predicted unit price)) (the supply and demand impact degree estimated by the supply and demand impact degree estimation unit 13) is higher than a preset threshold value. The introduction plan generating unit 18 uses the extracted shipping time as a reference point and back-calculates the introduction time using a learning model. The introduction plan generating unit 18 generates an introduction plan including the back-calculated introduction time, and outputs the generated introduction plan to the manager terminal 23 that has requested the introduction plan through the data output unit 16. Other configurations and operations are the same as those of the first embodiment. The third embodiment may be applied to the second embodiment.

[0062] According to the third embodiment, as in the first embodiment, it is possible to contribute to providing useful information to producers in anticipation of future demand and supply of products, and since an implementation plan is generated according to the shipping period when demand is high, by utilizing the generated implementation plan, it is possible to contribute to optimizing the business plans of producers while optimizing the quality of animals and plants at the time of shipping.

[0063] [Embodiment 4] A product shipment prediction device according to the fourth embodiment will be described with reference to the drawings. Fig. 15 is a block diagram showing a schematic configuration of the product shipment prediction device according to the fourth embodiment.

[0064] The product shipment prediction device 10 is a device that predicts the shipment of products obtained from animals or plants based on data of the animals or plants at the time of introduction or cultivation (see FIG. 15). The product shipment prediction device 10 includes a data acquisition unit 11 and a shipment prediction unit 15.

[0065] The data acquisition unit 11 is configured to acquire introduction data, cultivation data, and shipping data representing characteristics of animals and plants at the time of introduction, cultivation, and shipping, and supply and demand impact data that affects the supply and demand of products related to the animals and plants. The shipment prediction unit 15 is configured to predict the shipment of the product based on the introduction data or the cultivation data accompanied by a request for a predicted shipment result, using the introduction data, cultivation data, shipping data, and supply and demand impact data.

[0066] According to the fourth embodiment, the data at the time of introduction, the data at the time of cultivation, the data at the time of shipment, and the supply and demand impact data are used to predict the shipment of the product based on the data at the time of introduction or the data at the time of cultivation accompanied by a request for a predicted shipment result, which can contribute to providing useful information to producers in anticipation of future demand and supply of the product.

[0067] The product shipment prediction device according to the first to fourth embodiments can be configured by so-called hardware resources (information processing device, computer), and can use a device having the configuration shown in Fig. 16. For example, the hardware resource 100 includes a processor 101, a memory 102, a network interface 103, and the like, which are connected to each other by an internal bus 104.

[0068] 16 is not intended to limit the hardware configuration of the hardware resource 100. The hardware resource 100 may include hardware (e.g., an input / output interface) that is not shown. Furthermore, the number of units such as the processor 101 included in the device is not intended to be limited to the example shown in FIG. 16, and for example, multiple processors 101 may be included in the hardware resource 100. For example, a CPU (Central Processing Unit), an MPU (Micro Processor Unit), a GPU (Graphics Processing Unit), etc. may be used as the processor 101.

[0069] The memory 102 may be, for example, a random access memory (RAM), a read only memory (ROM), a hard disk drive (HDD), or a solid state drive (SSD).

[0070] The network interface 103 may be, for example, a LAN (Local Area Network) card, a network adapter, a network interface card, or the like.

[0071] The functions of the hardware resource 100 are realized by the above-mentioned processing module. The processing module is realized, for example, by the processor 101 executing a program stored in the memory 102. The program can be updated by downloading it via a network or by using a storage medium storing the program. Furthermore, the processing module may be realized by a semiconductor chip. That is, it is sufficient that the functions performed by the processing module are realized by executing software on some kind of hardware.

[0072] A part or all of the above-described embodiments may be described as, but is not limited to, the following supplementary notes.

[0073] [Appendix 1] a data acquisition unit configured to acquire introduction data, cultivation data, and shipping data representing characteristics of the animals and plants at the time of introduction, cultivation, and shipping, as well as supply and demand impact data that influences the supply and demand of products related to the animals and plants; a shipment forecasting unit configured to forecast shipment of the product based on the introduction data or the cultivation data accompanied by a request for a forecast shipment result, using the introduction data, the cultivation data, the shipping data, and the supply and demand impact data; A product shipment forecasting device comprising: [Appendix 2] a learning model generation unit configured to perform machine learning based on the introduction data, the cultivation data, and the shipping data to generate a learning model for predicting shipment of the product; The shipment forecasting unit is configured to forecast shipment of the product based on the introduction time data or the cultivation time data accompanied by the request for the predicted shipment result, using the learning model and the supply and demand impact data. 2. The product shipment forecasting device according to claim 1. [Appendix 3] a supply and demand impact degree estimation unit configured to estimate a supply and demand impact degree indicating a degree of change in shipment of the product predicted based on the learning model, based on the supply and demand impact data; The shipment forecasting unit is configured to forecast shipment of the product based on the introduction time data or the cultivation time data accompanied by the request for the predicted shipment result, using the learning model and the supply and demand influence degree number. 3. The product shipment forecasting device according to claim 2. [Appendix 4] The product shipment prediction device described in Appendix 2 or 3, wherein the learning model generation unit is configured to systematically select or organize data from the introduction data, the development data, and the shipment data, and generate the learning model for predicting specified parameters or features of the product at the time of shipment. [Appendix 5] The learning model generation unit is generating the learning model for predicting the shipping time by performing machine learning based on the growth period and weight of the predetermined variety of the animal or plant in the data at the time of introduction, the data at the time of cultivation, and the data at the time of shipping; generating the learning model for predicting the product weight at the time of shipment by machine learning based on the body weight and the product weight of the predetermined variety of the animal or plant in the shipping data; generating a learning model for predicting the unit price of a product at the time of shipment by performing machine learning based on the shipping date, the unit price of the product, and the animal welfare compliance level of the predetermined variety of the animal or plant in the shipping data; 5. The product shipment forecasting device of claim 4, configured as follows: [Appendix 6] The shipment forecasting unit is predicting a shipping possible time and a weight based on the growth period and the weight of the predetermined variety of the animal or plant in the introduction data or the cultivation data using the learning model for predicting the shipping possible time; Using the learning model for predicting the livestock product weight at the time of shipment, predicting the weight of the product based on the predicted body weight; predicting a unit price of the product in a calendar corresponding to the predicted possible shipping time using the learning model for predicting a unit price of the product at the time of shipment; Using the supply and demand impact degree number, a fluctuation range of the predicted unit price of the product is predicted; predicting, as a shipping time, a timing at which an upper limit of a fluctuation range of the unit price of the product during the shipping possible time period is maximized; It is configured as follows: 6. The product shipment forecasting device according to claim 5. [Appendix 7] 5. The product shipment prediction device according to claim 4, wherein the shipment prediction unit is configured to predict a transaction price based on the predicted product weight and the product unit price. [Appendix 8] 8. The product shipment forecasting device according to claim 6 or 7, wherein the supply and demand impact degree indicates the degree of change in unit price at the shipping time of the product. [Appendix 9] 9. The product shipment forecasting device according to any one of Appendix 3 to 8, wherein the supply and demand impact degree number is estimated based on the magnitude of a predetermined quantified parameter or feature value included in the supply and demand impact data, or the number of data items in the supply and demand impact data of the same type. [Appendix 10] a data output section configured to output data; The shipping forecasting unit is configured to generate a forecast shipping result based on data related to forecasted shipping; The data output unit is configured to output the predicted shipping result. 10. A product shipment prediction device according to any one of claims 1 to 9. [Appendix 11] The product shipment prediction device according to any one of Appendices 2 to 10, wherein the shipment prediction unit is configured to, when the learning model is not present, predict the shipment of the product based on the introduction time data or the cultivation time data accompanied by a request for the predicted shipment result, using a statistical model created in advance by a statistical method. [Appendix 12] 12. The product shipment forecasting device according to any one of appendix 3 to 11, wherein the shipment forecasting unit is configured to predict the shipment of the product by setting the supply and demand impact degree number to 1 when the supply and demand impact degree number does not exist. [Appendix 13] and a cultivation plan generating unit configured to generate a cultivation plan based on the introduction data, the cultivation data, and information on the cultivation included in the shipping data when the growth period of the plant or animal at the shipping time predicted by the shipping prediction unit is earlier or later than a previously set appropriate growth period. 8. The product shipment forecasting device according to claim 6 or 7. [Appendix 14] an introduction plan generating unit configured to extract a shipping time when the supply and demand impact degree estimated by the supply and demand impact degree estimation unit is higher than a preset threshold value, to use the extracted shipping time as a reference point to back-calculate an introduction time using the learning model, and to generate an introduction plan including the back-calculated introduction time; 14. The product shipment prediction device according to any one of appendix 6, 7, and 13. [Appendix 15] A product shipment forecasting device according to any one of appendix 1 to 14, an animal / plant management device configured to manage information related to the animals and plants being cultivated on-site and to transmit the introduction data, the cultivation data, and the shipping data of the animals and plants to the product shipment prediction device; an information providing device configured to transmit the supply and demand impact data to the product shipment forecasting device; A product shipment forecasting system comprising: [Appendix 16] A product shipment forecasting method for forecasting shipment of a product related to an animal or plant using hardware resources, comprising: The hardware resource acquires introduction data, cultivation data, and shipping data representing characteristics of the animals and plants at the time of introduction, cultivation, and shipping, and supply and demand impact data that affects the supply and demand of the product; a step in which the hardware resource uses the installation data, the cultivation data, the shipping data, and the supply and demand influence data to predict shipment of the product based on the installation data or the cultivation data accompanied by a request for a predicted shipping result; A method for forecasting production shipments, comprising: [Appendix 17] A program for causing hardware resources to execute a process for predicting shipment of products related to animals and plants, a process in which the hardware resource acquires introduction data, cultivation data, and shipping data representing characteristics of the animals and plants at the time of introduction, cultivation, and shipping, and supply and demand impact data that influences the supply and demand of the product; a process in which the hardware resource uses the installation data, the cultivation data, the shipping data, and the supply and demand impact data to predict shipment of the product based on the installation data or the cultivation data accompanied by a request for a predicted shipping result; A program for causing the hardware resource to execute the above.

[0074] The disclosures of the above patent documents are incorporated herein by reference and may be used as the basis or part of the present invention as necessary. Within the framework of the entire disclosure of the present invention (including the claims and drawings), and further based on the basic technical idea, modifications and adjustments of the embodiments and examples are possible. Furthermore, within the framework of the entire disclosure of the present invention, various combinations or selections (or non-selection as necessary) of various disclosed elements (including each element of each claim, each element of each embodiment or example, each element of each drawing, etc.) are possible. In other words, the present invention naturally includes various modifications and corrections that a person skilled in the art would be able to make according to the entire disclosure, including the claims and drawings, and the technical idea. Furthermore, with regard to the numerical values ​​and numerical ranges described in this application, any intermediate value, lower numerical value, and small range are deemed to be described even if not specified. Furthermore, the disclosures of the above cited documents may be used in part or in whole in combination with the descriptions in this document as part of the disclosure of the present invention as necessary, in accordance with the spirit of the present invention, and are deemed to be included (belong) in the disclosures of this application. [Explanation of symbols]

[0075] 1. Product shipment forecasting system 3 Domestic animals 10 Product shipment forecasting device 11 Data Acquisition Section 12 Learning model generation unit 13. Supply and Demand Impact Estimation Department 14 Storage section 14a Acquired data storage unit 14b Learning model memory section 14c Supply and demand impact memory section 15 Shipping Forecast Department 16 Data output section 17 Development Plan Creation Department 18 Implementation Plan Creation Department 20A~20N Livestock Management Systems 21 Data acquisition device 22 Livestock animal management equipment 23 Administrator terminal 30A~30M Information providing device 40 Network 100 Hardware Resources 101 Processor 102 Memory 103 Network Interface 104 Internal Bus

Claims

1. a data acquisition unit configured to acquire introduction data, cultivation data, and shipping data representing characteristics of the plants and animals at the time of introduction, cultivation, and shipping, as well as supply and demand impact data that influences the supply and demand of products related to the plants and animals; a shipment forecasting unit configured to forecast shipment of the product based on the introduction data or the growth data accompanied by a request for a predicted shipment result, using the introduction data, the growth data, the shipping data, and the supply and demand impact data; A product shipment forecasting device comprising:

2. a learning model generation unit configured to perform machine learning based on the introduction data, the cultivation data, and the shipping data to generate a learning model for shipping prediction of the product; the shipment forecasting unit is configured to use the learning model and the supply and demand impact data to forecast shipment of the product based on the introduction data or the cultivation data accompanied by a request for the predicted shipment result. The product shipment forecasting device according to claim 1.

3. a supply and demand impact degree estimation unit configured to estimate a supply and demand impact degree indicating a degree of change in shipment of the product predicted based on the learning model, based on the supply and demand impact data; the shipment forecasting unit is configured to forecast shipment of the product based on the introduction data or the cultivation data accompanied by a request for the predicted shipment result, using the learning model and the supply and demand influence degree.

3. The product shipment forecasting device according to claim 2.

4. The product shipment prediction device of claim 3, wherein the learning model generation unit is configured to systematically select or organize data from the introduction data, the development data, and the shipping data to generate the learning model for predicting specified parameters or features at the time of shipment of the product.

5. The learning model generation unit generating the learning model for predicting the shipping date by performing machine learning based on the growth period and weight of the predetermined variety of the animal or plant in the data at the time of introduction, the data at the time of cultivation, and the data at the time of shipping; generating the learning model for predicting the product weight at the time of shipment by performing machine learning based on the body weight and product weight of the predetermined variety of the animal or plant in the shipping data; generating a learning model for predicting the unit price of a product at the time of shipment by performing machine learning based on the shipping date, unit price of the product, and animal welfare compliance level of the predetermined variety of the animal or plant in the shipping data; 5. The product shipment forecasting device according to claim 4, wherein the product shipment forecasting device is configured as follows:

6. The shipment forecasting unit predicting a shipping date and a weight based on the growth period and the weight of the predetermined variety of the animal or plant in the data at the time of introduction or the data at the time of rearing using the learning model for predicting the shipping date; Using the learning model for predicting the livestock product weight at the time of shipping, predict the weight of the product based on the predicted body weight; predicting a unit price of the product in a calendar corresponding to the predicted possible shipping time using the learning model for predicting the unit price of the product at the time of shipping; Using the supply and demand impact degree number, predict a fluctuation range of the predicted unit price of the product; predicting, as a shipping time, a timing at which an upper limit of a fluctuation range of the unit price of the product during the shipping possible time is maximized; It is configured as follows:

6. The product shipment forecasting device according to claim 5.

7. The product shipment forecasting device according to claim 6 , wherein the shipment forecasting unit is configured to forecast a transaction price based on the forecasted product weight and the forecasted product unit price.

8. 7. The product shipment forecasting device according to claim 6, wherein the supply and demand influence degree indicates a degree of change in unit price of the product at the time of shipment.

9. 4. The product shipment forecasting device according to claim 3, wherein the supply and demand impact degree is estimated based on the magnitude of a predetermined quantified parameter or feature contained in the supply and demand impact data, or the number of data items of the same type of supply and demand impact data.

10. a data output unit configured to output data; the shipping forecasting unit is configured to generate a forecast shipping result based on data related to forecasted shipping; The data output unit is configured to output the predicted shipping result. The product shipment forecasting device according to claim 1.

11. 3. The product shipment forecasting device of claim 2, wherein the shipment forecasting unit is configured to, when the learning model is not available, use a statistical model created in advance using a statistical method to predict the shipment of the product based on the introduction data or the cultivation data accompanied by a request for the predicted shipment result.

12. 4. The product shipment forecasting device according to claim 3, wherein the shipment forecasting unit is configured to predict the shipment of the product by setting the supply and demand influence degree number to 1 when the supply and demand influence degree number does not exist.

13. and a cultivation plan generation unit configured to generate a cultivation plan based on information on the growth included in the data at the time of introduction, the data at the time of cultivation, and the data at the time of shipping when the growth period of the plant or animal at the time of shipping predicted by the shipping prediction unit is earlier or later than a previously established appropriate growth period.

7. The product shipment forecasting device according to claim 6.

14. an introduction plan generation unit configured to extract a shipping time when the supply and demand impact degree estimated by the supply and demand impact degree estimation unit is higher than a preset threshold, to use the extracted shipping time as a reference point to back-calculate an introduction time using the learning model, and to generate an introduction plan including the back-calculated introduction time; 7. The product shipment forecasting device according to claim 6.

15. The product shipment forecasting device according to any one of claims 1 to 14; an animal and plant management device configured to manage information related to the animals and plants being cultivated on-site and to transmit the data at the time of introduction, the data at the time of cultivation, and the data at the time of shipping of the animals and plants to the product shipment prediction device; an information providing device configured to transmit the supply and demand impact data to the product shipment forecasting device; A product shipment forecasting system comprising:

16. A product shipment forecasting method for forecasting shipment of a product related to an animal or plant using hardware resources, comprising: a step in which the hardware resource acquires introduction data, cultivation data, and shipping data representing characteristics of the plants and animals at the time of introduction, cultivation, and shipping, as well as supply and demand impact data that affects the supply and demand of the product; a step in which the hardware resource uses the installation data, the cultivation data, the shipping data, and the supply and demand impact data to predict shipment of the product based on the installation data or the cultivation data accompanied by a request for a predicted shipping result; A method for forecasting production shipments, including:

17. A program that causes hardware resources to execute a process for predicting shipment of products related to plants and animals, a process in which the hardware resource acquires introduction data, cultivation data, and shipping data representing characteristics of the plants and animals at the time of introduction, cultivation, and shipping, as well as supply and demand impact data that influences the supply and demand of the product; a process in which the hardware resource uses the installation data, the development data, the shipping data, and the supply and demand impact data to predict shipment of the product based on the installation data or the development data accompanied by a request for a predicted shipping result; A program that causes the hardware resource to execute the above.

Images