JP2024027422A - Information processing device, information processing method, and program - Google Patents

Abstract

[Problem] To create a transportation plan that efficiently reduces CO2 emissions by visualizing the amount of CO2 emissions reduced not only on the logistics side but also on the shipper side. A shipper side information acquisition unit 101 acquires shipper side information. The logistics side information acquisition unit 102 acquires logistics side information. The CO2 emissions prediction unit 103 sets predetermined preconditions including the travel route from the transport source to the transport destination based on at least part of the shipper side information and the logistics side information, and sets the predetermined preconditions including the travel route from the transport source to the transport destination, and uses the predetermined conditions to Predict the carbon dioxide emissions per unit of weight or volume when moving. The planning unit 104 creates one or more transportation plans based on each predicted carbon dioxide emission amount when the preconditions are changed. [Selection diagram] Figure 6

Description

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

Conventionally, there has been technology for managing inventory held in warehouses serving as distribution bases. For example, Patent Document 1 describes a distribution management system in which a store allocates inventory products to an order for a product from a customer and transmits the results of the reservation and delivery date for the order to the store.

Japanese Patent Application Publication No. 9-136704

However, in recent years, there has been a demand to reduce CO2 generated in logistics activities (delivery, storage, work, etc.) on the transportation side, but conventional logistics management systems, including the technology described in Patent Document 1, do not emit CO2. There are limits to how much can be reduced.
This is because the transportation (e.g., logistics company) side creates a transportation plan based on information unilaterally requested by the shipper, so such a transportation plan is not effective in reducing CO2 emissions. This is because it had not become a standard.
In other words, by making the amount of reduction in CO2 emissions visible not only to the logistics side but also to the shipper side, it is possible to formulate a transportation plan that efficiently reduces CO2 emissions, as disclosed in Patent Document 1. Conventional logistics management systems, including the technology described in , do not disclose any information to shippers.

The present invention was made in view of this situation, and aims to efficiently reduce CO2 emissions by making the reduction in CO2 emissions visible not only to the logistics side but also to the shipper. The purpose is to realize the formulation of transportation plans.

In order to achieve the above object, an information processing device that is one embodiment of the present invention includes:
In an information processing device that creates a plan for transporting a shipper's products from a shipping source to a shipping destination using a moving object as a transportation plan,
Shipper side information acquisition means for acquiring, as shipper side information, information on the shipper side that includes at least the weight or volume of the product, the shipping source and the shipping destination;
Logistics-side information acquisition means for acquiring, as logistics-side information, information on the logistics side that manages the transportation of the mobile object and that includes at least a moving object characteristic amount indicating the characteristics of the mobile object;
When predetermined preconditions including a travel route from the transport source to the transport destination are set based on at least part of the shipper side information and the logistics side information, and the mobile object moves under the preconditions. a carbon dioxide emissions prediction means for predicting carbon dioxide emissions per unit amount of weight or volume;
Planning means for creating one or more of the transportation plans based on each of the carbon dioxide emissions predicted when the preconditions are changed;
Equipped with.

According to the present invention, by making the amount of reduction in CO2 emissions visible not only to the logistics side but also to the shipper side, it is possible to formulate a transportation plan that efficiently reduces CO2 emissions. .

FIG. 2 is an image diagram showing an overview of this service that can be realized by various processes executed by a server according to an embodiment of the information processing device of the present invention. 2 is a diagram illustrating an example of a method for calculating CO2 emissions applied to the service shown in FIG. 1. FIG. An example of the change in delivery unit price per package amount is shown. 2 is a diagram showing the configuration of an information processing system including the server of FIG. 1. FIG. 3 is a block diagram showing the hardware configuration of the server in FIG. 2. FIG. 4 is a functional block diagram showing an example of the functional configuration of the server in FIG. 3. FIG. FIG. 3 is a diagram showing an example of CO2 emissions per truck on a predetermined route when the CO2 emissions prediction method of the example in FIG. 2 is adopted. This is an example of a predicted result of CO2 emissions per cargo amount (one pallet and one case) when the predicted result of CO2 emissions per truck in FIG. 7 is adopted. 8 is a diagram showing preconditions in an example of a transportation plan created by this service, which is different from the examples shown in FIGS. 7 and 8. FIG. This is an example of a transportation plan drawn up by this service, and is an example of a predicted result of CO2 emissions per cargo amount (one pallet and one case) in an example different from the examples in FIGS. 7 and 8. 11 is an example of a transportation plan created by this service, and is a diagram showing preconditions for utilizing a transportation company found by a matching site in an example different from the examples of FIGS. 9 and 10. FIG. This is an example of a transportation plan created by this service, and is an example of a predicted result of CO2 emissions per amount of cargo (one pallet and one case) in an example different from the examples in FIGS. 9 and 10. FIG. 2 is a diagram illustrating an example of factors that change fuel efficiency necessary for predicting CO2 emissions. It is a diagram showing an example of a CO2 emission prediction model as an AI model.

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is an image diagram showing an overview of this service that can be realized by various processes executed by a server according to an embodiment of an information processing apparatus of the present invention.

As shown in FIG. 1, in this service, consumers C include companies, retailers and wholesalers, individuals (end users), etc., and place orders for products from shippers S.
In this service, when a consumer C places an order with a shipper S, the contents are managed as "order information."

The shipper S is made up of manufacturers, individuals, companies, etc., and orders the supply of products from the supplier V based on the order information. In this service, when a shipper S places an order to a supplier V, the contents are managed as "order information".

Supplier V consists of manufacturers, makers, etc., and supplies products to logistics company L based on order information. From the perspective of the logistics company L, the product will be received from the supplier V. Furthermore, from the perspective of the shipper S, this is equivalent to requesting the quantity supplier L to procure the product based on the ordering information. Therefore, in this service, when there is a request from shipper S to logistics company L to procure a product (when a product arrives from supplier V to logistics company L), the content of the request is "Procurement information (arrival information)". ”.

Further, in this service, various information held by the logistics company L in the course of business is managed. Specifically, as information (hereinafter referred to as "vehicle information") regarding cargo transport vehicles (hereinafter referred to as "trucks") used for transporting products, the vehicle number, loading capacity, and vehicle class of each cargo transport vehicle are collected. , information regarding the driver (for example, name, age, working hours, overtime hours, etc.) is managed.

In this service, the logistics company L ships the products received (procured) from the supplier V and delivers them to the consumer C based on the order information. From the perspective of the shipper S, this is equivalent to selling the product to the consumer C based on the order information. Therefore, in this service, when a shipper S requests a distribution company L to sell a product (when a distribution company L ships the product), the contents are managed as "sales information (shipping information)".

This service manages the above-mentioned order information, ordering information, procurement information (arrival information), vehicle information, and sales information (shipping information) all at once, and creates flexible transportation plans that take this information into consideration.
In other words, according to this service, information that was previously managed by logistics company L (procurement information (arrival information), vehicle information, and sales information (shipping information)) and information that was previously managed by shipper S (order information) It becomes possible to formulate an effective transportation plan based on the above information (information and ordering information). In other words, it becomes possible to formulate an effective transportation plan based on information from the logistics company and information from the shipper. As a result, efficient transportation without waste can be realized.

Here, in recent years, there has been a demand for reduction of CO2 generated in logistics activities (delivery, storage, work, etc.) on the side of the logistics company L.
Therefore, logistics company L itself has been conducting various activities to reduce CO2 emissions.
However, as described above, the procurement (arrival) of products, which is the basis of logistics activities, is determined in response to orders placed by the shipper S to the supplier V. Furthermore, the sale (shipment) of products, which is the basis of logistics activities, is determined in response to orders from consumers C to shippers S. That is, the logistics activities on the side of the logistics company L are determined by order information, which is a decision between the consumer C and the shipper S, and order information, which is a decision between the shipper S and the supplier V. .
Therefore, there is a limit to how much CO2 can be reduced by logistics company L alone.
Therefore, in this service, we will conduct CO2 reduction activities from the generation stage of order information, which is decision-making between consumer C and shipper S, and order information, which is decision-making between shipper S and supplier V. It is designed to be able to do the following. In other words, in this service, a transportation plan that takes CO2 emissions into account is created as a transportation plan for product procurement (arrival) and sales (shipping), and the CO2 emissions are reported to shipper S and logistics company L. Presented and shared.
In other words, at least some of the shippers S, carriers L, etc. can formulate the optimal transportation plan for themselves while visually checking whether the presented CO2 emissions will reach the reduction target. Become. The remaining portion allows the user to visually check the created transportation plan along with its CO2 emissions.

Below, we will provide an overview of the transportation plan that takes CO2 emissions into consideration, which will be applied to this service.

FIG. 2 is a diagram showing an example of a method for calculating CO2 emissions applied to the service shown in FIG. 1.
As shown in FIG. 2, the amount of CO2 emissions (tCO2) per truck is expressed by the following equation.
CO2 emissions = fuel consumption (kl) x 2.58 (tCO2/kl)

Here, 2.58 (tCO2/Kl) is the CO2 emission coefficient per 1kl of light oil, and is calculated by the following formula.
2.58 (tCO2/kl) = Unit calorific value (GJ/Kl) x Emission factor (tC/GJ) x 22/12 (tCO2/tC)
The unit calorific value is 37.7 according to Ministry of Economy, Trade and Industry Notification No. 66 (March 29, 2006).
Emission factors are provided by the Global Environment Bureau of the Ministry of the Environment, Greenhouse Gas Emissions Calculation Method Guidelines (Draft Version 1.6) from Business Operators, CO2 Emissions Calculation Formula Based on the Fuel Law, Ministry of Economy, Trade and Industry and Japan Logistics Systems Association. According to the "2003 Environmentally Friendly Logistics Promotion Manual", it is 0.0187.

On the other hand, the amount of fuel used (kl) is calculated by the following formula.
Fuel consumption (kl) = Traveling distance (km) ÷ Fuel consumption (km/kl)
Here, it is known that fuel efficiency varies depending on the route such as ordinary roads and expressways, but it does not change much depending on the loading capacity (weight and volume) of the truck, that is, the amount of cargo (the amount of cases and pallets). There is.

In other words, if a truck is traveling on the same route, the fuel efficiency of a fully loaded truck and an empty truck will be the same, and as a result, the amount of CO2 emitted per truck will also be the same. That is, the amount of CO2 emissions per truck does not depend on the amount of cargo loaded on the truck.
In other words, in terms of CO2 emissions not per truck, but per amount of cargo transported by one truck (per unit of case or pallet), the lower the loading efficiency, the higher the CO2 emissions. It will become more and more. For example, if the amount of CO2 emissions per truck is 100, and the amount of cargo is 100 units, the amount of CO2 emissions per unit of amount of cargo is 1. On the other hand, if the amount of luggage is 10 units, the CO2 emissions per unit of luggage will be 10, which is 10 times as much.
Therefore, in this service, a transportation plan is created based on the CO2 emissions per amount of cargo transported by one truck (per unit of case or pallet).
In other words, in this service, we develop a transportation plan that increases transportation efficiency in order to reduce CO2 emissions per unit of cargo transported by one truck (per unit of case or pallet). will be done.

Now, with reference to Figure 3, let's consider from the perspective of transportation efficiency and logistics costs.
FIG. 3 shows an example of changes in delivery unit price per package amount.
In FIG. 3, the basic information fare is the fare (logistics cost) of a chartered flight for a 4-ton vehicle or a 10-ton vehicle, and the so-called ton×km is adopted.
A ton is a unit price determined by the vehicle class of the truck (4 ton vehicle or 10 ton vehicle). In principle, the amount of goods (commodities) that can actually be transported is within the maximum loading capacity for each truck, and only in the case of light items, it is within the volume of the truck's box. In other words, the freight charge is the same no matter how many tons of goods (products) you carry, as long as it is within the maximum loading capacity of the vehicle.
A kilometer is the distance traveled by a truck. However, a flat fare will be applied based on the approximate distance per prefecture (100 km from Yamanashi Prefecture to Tokyo), rather than the exact distance traveled (from Kofu City, Yamanashi Prefecture to Mitaka City, Tokyo).
For example, when a 10-ton vehicle transports luggage from Yamanashi to Tokyo, the amount will be fixed, for example, 50,000 yen, regardless of the amount of luggage.
For example, a 10-ton vehicle can transport up to 1,920 cases of products on a maximum of 16 pallets, and in this case, the transport efficiency (loading ratio in FIG. 3) is 100%. The unit price for a case with 100% transportation efficiency is 26 yen. On the other hand, 480 cases on 4 pallets can be transported by a 4-ton truck, so 600 cases on 5 pallets is the minimum transportation efficiency, which is 31%. The unit price for a case with a transportation efficiency of 31% is 83 yen, which is more than three times as expensive as a case with a transportation efficiency of 100%.

In this way, in terms of logistics costs, it is preferable to use the unit price per amount of cargo transported by one truck (per unit when a case or pallet is taken as one unit), and the transportation efficiency is high. Indeed, the unit price will also be lower.
In summary, this service allows transportation plans to be created from the perspective of transportation efficiency, making it possible to reduce both CO2 emissions and logistics costs.

Next, the configuration of the information processing system including the server 1 that executes various processes for providing this service will be described.
FIG. 4 is a diagram showing the configuration of an information processing system including a server according to an embodiment of the information processing apparatus of the present invention.

The information processing system shown in FIG. ) are connected to each other via a predetermined network N such as the Internet.

Each of the distributor side terminals 2-1 to 2-n in this embodiment is configured with a personal computer, a smartphone, a tablet terminal, or the like. Each of the logistics company side terminals 2-1 to 2-n is operated by a person in charge of each of the n logistics companies L.
Note that, hereinafter, when there is no need to distinguish each of the logistics company side terminals 2-1 to 2-n individually, they will be collectively referred to as the "distribution company side terminal 2."

Each of the shipper side terminals 3-1 to 3-m in this embodiment includes a personal computer, a smartphone, a tablet terminal, or the like. Each of the shipper side terminals 3-1 to 3-m is operated by a person in charge of each shipper S of m.
Hereinafter, if there is no need to distinguish each of the shipper side terminals 3-1 to 3-m individually, they will be collectively referred to as the "shipper side terminal 3."

Next, the hardware configuration of the server 1 that executes various processes for providing this service will be described.
FIG. 5 is a block diagram showing the hardware configuration of the server in FIG. 4.

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

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

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

The input unit 16 is made up of various hardware such as lead, and inputs various information.
The output unit 17 is composed of various liquid crystal displays and the like, and outputs various information.
The storage unit 18 is composed of a DRAM (Dynamic Random Access Memory) or the like, and stores various data.
The communication unit 19 performs communication with other devices (for example, the logistics company terminals 2-1 to 2-n and the shipper terminals 3-1 to 3-m in FIG. 4) via the network N including the Internet. control.

The drive 20 is provided as necessary. A removable medium 30 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately installed in the drive 20. The program read from the removable medium 30 by the drive 20 is installed in the storage unit 18 as necessary. Further, the removable medium 30 can also store various data stored in the storage section 18 in the same manner as the storage section 18.

Although not shown, the logistics company terminal 2 and the shipper terminal 3 also have the hardware configuration shown in FIG. 5.

Next, the functions of the server 1 having such a hardware configuration will be explained with reference to FIG. 6.
FIG. 6 is a functional block diagram showing an example of the functional configuration of the server 1 in FIG. 5. As shown in FIG.

As shown in FIG. 6, in the CPU 11 of the server 1, a shipper side information acquisition unit 101, a logistics side information acquisition unit 102, a CO2 emission prediction unit 103, a planning unit 104, and a presentation unit 105 function. .
One area of the storage unit 18 is provided with a shipper side DB 401, a logistics side DB 402, and a CO2 emissions prediction model 403.

The shipper side information acquisition unit 101 acquires shipper side information including order information and ordering information.
The shipper side information acquired by the shipper side information acquisition unit 101 is stored and managed in the shipper side DB 401.

The logistics side information acquisition unit 102 acquires information necessary for formulating a transportation plan such as vehicle information (for example, vehicle information, information on each base for determining a route, etc.) from among the information managed by the logistics company L. ) is obtained as information on the logistics company side.
The logistics side information acquired by the logistics side information acquisition unit 102 is stored and managed in the logistics side DB 402.

Here, the CO2 emissions prediction model 403 is a model that predicts and outputs the CO2 emissions per baggage amount (pallet/case) when each value of one or more input parameters is input.
The CO2 emission prediction model 403 is provided individually depending on the CO2 emission prediction method. For example, if the model corresponds to the prediction method shown in Figure 2 above and is based on the premise that fuel efficiency differs between expressways and local roads, (Is it a 10-ton vehicle?), route information (route divided into expressways and local roads, the distance of each of which can be specified), and cargo weight are entered as input parameters. Ru.
Note that a specific example of the CO2 emission prediction model 403 will be described later with reference to the drawings from FIG. 7 onwards.

The CO2 emissions prediction unit 103 extracts the respective values of each input parameter from the shipper side information and the logistics side information, substitutes them into the CO2 emissions prediction model 403, and uses the output to predict the CO2 emissions per unit of cargo volume. Output as result.

The planning unit 104 creates a transportation plan for receiving or shipping so that CO2 emissions will be below a predetermined amount, based on shipper side information, logistics side information, and the prediction result of CO2 emissions per package amount. .
For example, when the CO2 emissions prediction method shown in the example of FIG. Develop a transportation plan (to reduce costs).
A specific example of formulating a transportation plan will be described later with reference to FIGS. 7 to 12.

The presentation unit 104 presents the drafted transportation plan to the logistics company L through the logistics company terminal 2 and to the shipper S through the shipper terminal 3.
Here, the CO2 emissions (prediction results) are also presented in the transportation plan. In this way, information on CO2 emissions is presented and shared not only by the logistics company L but also by the shipper S. As a result, not only the logistics company L but also the shipper S can participate in activities to reduce CO2 generated in logistics activities.

To summarize the above, in the CPU 101 of the server 1, the shipper side information acquisition unit 101 and the logistics side information acquisition unit formulate a plan for transporting the goods of the shipper S by truck from the shipping source to the shipping destination as a transportation plan. 102, a CO2 emission prediction unit 103, a planning unit 104, and a presentation unit 105 function.
The shipper side information acquisition unit 101 acquires information on the shipper S side, including at least the weight or volume of the product, and the shipping source and shipping destination, as shipper side information.
The logistics-side information acquisition unit 102 acquires, as logistics-side information, information on the logistics side that manages truck transportation, and that includes at least a truck feature amount indicating characteristics of the truck such as vehicle class.
The CO2 emissions prediction unit 103 sets predetermined preconditions including the travel route from the transport source to the transport destination based on at least part of the shipper side information and the logistics side information, and determines whether the mobile object will move under the preconditions. Predict the CO2 emissions per unit amount (case or pallet) in terms of weight or volume when moving.
The planning unit 104 creates one or more transportation plans based on each CO2 emission amount predicted when the preconditions are changed.
The presentation unit 105 presents one or more of the drafted transportation plans and the predicted value of CO2 emissions per unit amount to each of the logistics company terminal 2 and the shipper terminal 3.

Next, a specific example of a transportation plan created by this service will be described with reference to FIGS. 7 to 12.

FIG. 7 is a diagram showing an example of the amount of CO2 emissions per truck on a predetermined route when the method of predicting the amount of CO2 emissions shown in FIG. 2 is adopted.
In the example of FIG. 7, a 10-ton vehicle (a truck with a maximum loading capacity of 12,000 kg) travels from Hokuto City, Yamanashi Prefecture to Suita City, Osaka Prefecture. Specifically, the route consists of a 12 km long road from Suita City, Yamanashi Prefecture to Kobuchizawa IC, a 373 km expressway from Kobuchizawa IC to Suita IC, and a 15 km long road from Suita IC to Suita City, Osaka Prefecture. This is adopted in the example shown in FIG.
Such travel routes, that is, the mileage for each of the local roads and expressways in the table in Figure 7, can be obtained from the order information or ordering information on the shipper's side information, and the base information on the logistics side information. be.
Here, the fixed values in the table at the bottom of FIG. 7 are used for the fuel consumption, and since it is assumed here that luggage (products) is loaded, the actual fuel consumption of the vehicle is used.
Furthermore, the fact that the truck on the current travel route is a 10-ton vehicle can be obtained from the vehicle information in the logistics information.
That is, the CO2 emissions prediction unit 103 extracts the fact that the vehicle is a 10-ton vehicle and the mileage on ordinary roads and highways as the values of the input parameters from the shipper's information and the logistics side information, and calculates the CO2 emissions. Substitute into the emission prediction model 403. Then, the CO2 emission prediction model 403 outputs the results shown in the table of FIG. That is, the CO2 emissions prediction unit 103 outputs the table shown in FIG. 7 as the prediction result of the CO2 emissions per truck (10 ton vehicle).

FIG. 8 is an example of a predicted result of CO2 emissions per cargo amount (one pallet and one case) when the predicted result of CO2 emissions per truck shown in FIG. 7 is adopted.

In FIG. 8, 1) basic information is based on the preconditions of the example in FIG. 7, and the fare indicates the chartered fare for the 10-ton vehicle described above with reference to FIG.
2) The table for CO2 emissions when delivered based on basic information is the same as the table for the prediction results in FIG.

3) Regarding the difference in CO2 emissions per pallet and per case depending on the distribution volume of goods, the table on the left shows the distribution cost (unit price) per cargo volume (1 pallet and 1 case), and the table on the right shows the distribution cost (unit price) per cargo volume (1 pallet and 1 case). The table below shows the amount of CO2 emitted per cargo volume (one pallet and one case).
Here, the maximum loading capacity of a 10-ton vehicle is 12,000 kg, but the actual articles (commodities) that can be loaded are 16 pallets of 11,920 kg because they are loaded in pallets.

After obtaining the results from the table in FIG. 7 (table 2 in FIG. 8), the CO2 emissions prediction unit 103 further extracts the cargo amount from the shipper's information, etc., and calculates the CO2 emissions prediction. Substitute into model 403. Then, the CO2 emissions prediction model 403 outputs the CO2 emissions per pallet and per case as prediction results according to the table on the right side of 3) in FIG. For example, if there are 16 pallets, the CO2 emissions per pallet are 22.23t-CO2, and the CO2 emissions per case are 0.19t-CO2.
That is, the CO2 emissions prediction unit 103 outputs the prediction result of the CO2 emissions per cargo amount (one pallet and one case).

Here, the statement that the amount of cargo as an input parameter value is extracted from the shipper's information, etc. is basically obtained from the order information or ordering information, but there are cases where logistics information is also used. This is because there is. In other words, when creating a free transportation plan, such as transporting goods mixed with other goods, distributing them to two or more trucks, or loading goods that are in stock at carrier L's base as goods, etc. This is because information on the logistics side is also required.
Specifically, for example, assume that the amount of cargo obtained from the shipper's information is 5 pallets. In this case, the CO2 emissions per pallet are 71.12t-CO2, and the CO2 emissions per case are 0.59t-CO2. In other words, due to poor loading efficiency, CO2 emissions have increased.
In such a case, if it is possible to obtain from the logistics information that there is a truck moving from Yamanashi to Osaka that is scheduled to transport 11 pallets of another item, then the 11 pallets of the other item and the shipper If the input parameter value is 16 pallets including the 5 pallets obtained from the side information, the CO2 emissions per pallet are 22.23t-CO2, and the CO2 emissions per case are 0.19t- It is predicted to be CO2. In other words, the loading efficiency is better than when transporting on five pallets, and the amount of CO2 emissions is lower (the amount of reduction is greater).
In order to have the CO2 emissions prediction unit 103 make predictions under these various conditions, not only information on the shipper side but also information on the logistics side is comprehensively referenced.

In other words, the CO2 emissions prediction unit 103 uses shipper side information and logistics side information to calculate the forecast under various conditions (such as changing routes, changing trucks, and consolidating or distributing cargo). , calculate the predicted result of CO2 emissions per unit of cargo volume.
The planning unit 104 can formulate an optimal transportation plan for receiving or shipping goods based on the respective prediction results of CO2 emissions per package amount under various conditions such as these.

FIG. 9 is an example of a transportation plan created by this service, and is a diagram showing preconditions in an example different from the examples shown in FIGS. 7 and 8.
Note that, in this example as well, the method of predicting CO2 emissions in the example of FIG. 2 is adopted.
Company A (an example of shipper S) receives a request from customer B (an example of consumer C) to deliver goods D (720 cases) to destination Y in Osaka by delivery date: February 10, 2022. Order received. That is, it is assumed that the order information of the shipper's side information has such contents.
Here, it is assumed that the base information of the distribution side information indicates that the base where the D article is shipped (sold) is Koto Ward, Tokyo.
The CO2 emissions prediction unit 103 predicted the CO2 emissions per case, as shown in FIG. 10, based on the information shown in FIG.

FIG. 10 is an example of a transportation plan created by this service, and is an example of a predicted result of CO2 emissions per cargo amount (one pallet and one case) in an example different from the examples shown in FIGS. 7 and 8. It is.

In FIG. 10, 1) Basic information is based on the preconditions of the example in FIG. 9, and the fare indicates the chartered fare for the 10-ton vehicle described above with reference to FIG.
2) The table regarding CO2 emissions in the case of delivery based on basic information shows the predicted results of CO2 emissions per truck (10 ton vehicle).
That is, the CO2 emission prediction unit 103 recognizes that the weight of article D is 4,470 kg as shown in FIG. 9, so it needs to be transported by a 10-ton vehicle. Then, the CO2 emissions prediction unit 103 extracts the fact that the vehicle is a 10-ton vehicle and the travel distance on general roads and expressways as respective values of the input parameters from the information in FIG. 9, and predicts the CO2 emissions. Substitute into model 403. Then, the CO2 emission prediction model 403 outputs the results shown in the table 2) in FIG. That is, the CO2 emissions prediction unit 103 outputs the table 2) in FIG. 10 as the prediction result of the CO2 emissions per truck (10 ton vehicle).

In Figure 10, regarding 3) Differences in CO2 emissions per pallet and per case depending on the distribution volume of goods, the table on the left shows the distribution cost (unit price) per cargo volume (1 pallet and 1 case). The table on the right shows the amount of CO2 emitted per cargo volume (one pallet and one case).
Here, the maximum loading capacity of a 10-ton vehicle is 12,000 kg, but the actual articles (commodities) that can be loaded are 16 pallets of 11,920 kg because they are loaded in pallets.

After obtaining the results in the table 2) in FIG. 10, the CO2 emissions prediction unit 103 further extracts the cargo amount from the shipper's information etc. as an input parameter value, and substitutes it into the CO2 emissions prediction model 403. Then, the CO2 emissions prediction model 403 outputs the CO2 emissions per pallet and per case as prediction results according to the table on the right side of 3) in FIG.
That is, the CO2 emissions prediction unit 103 outputs the prediction result of the CO2 emissions per cargo amount (one pallet and one case).
Specifically, in the example shown in Figure 9, the weight of article D is 4,470 kg, resulting in 6 pallets, or 720 cases, so the CO2 emissions per case are as shown on the right side of 3) in Figure 10. According to the table, it is 0.61 tCO2.
Therefore, the planning unit 104 informs Company A (an example of the shipper S) of the content shown in FIG. presentation.

Company A's annual policy was to reduce CO2 emissions per case to 0.33tCO2 or less between Tokyo and Osaka, so in the transportation plan presented, the predicted CO2 emissions were 0. The delivery plan was found to have a considerable environmental impact, failing to achieve the target of .61tCO2.
Therefore, since Company A had a three-day lead time including the logistics lead time, they decided to use another transportation company instead of the usual transportation company T, in order to search for a transportation company that could further reduce CO2 emissions. The planning department 104 was requested to formulate a transportation plan.

As a result, the planning unit 104 creates a newly drawn up transportation plan based on the content shown in FIG. (prediction result of the route) was presented to Company A (an example of the shipper S) via the shipper side terminal 3.

FIG. 11 is an example of a transportation plan created by this service, and is a diagram showing preconditions for utilizing a transportation company found by a matching site in an example different from the examples of FIGS. 9 and 10.
That is, the planning department 104 utilizes a matching site (a site operated by Company C) that searches for transportation companies, and uses a 10-ton vehicle (maximum load capacity 11,300 kg) from Transportation Company O to deliver X in Shizuoka. A search was made for a truck transporting 5,200 kg of F goods from the destination to the W delivery destination in Osaka.
The planning department 104 determines that since the maximum loading capacity of transport company O's truck is 11,300 kg, the remaining 6,100 kg can be loaded, and that company A's delivery destination Y for goods D is higher than delivery destination W. I also realized that it was right in front of me.
Therefore, the planning unit 104 has set the route of black circle 2 → the route of black circle 3 → the route of black circle 4 as shown in FIG. 11 as a precondition.
The route designated by Kuromaru 2 is from the base in Koto Ward, Tokyo to the destination X in Fuji City, Shizuoka Prefecture, and is a route in which only the D goods are transported using the original 10-ton truck of the T transport company. In the route indicated by black circle 2, the travel distance on ordinary roads is 10 km, and the travel distance on expressways is 138 km.
The route marked by black circle 3 is from delivery destination X in Fuji City, Shizuoka Prefecture to delivery destination Y in Osaka City, Osaka Prefecture, and goods F and D are mixed and transported in a 10-ton vehicle of transport company O. It is the root. In the route indicated by black circle 3, the travel distance on ordinary roads is 3 km, and the travel distance on expressways is 361 km.
The route marked by black circle 4 is from the Y delivery destination in Osaka City, Osaka Prefecture to the W delivery destination in Osaka City, Osaka Prefecture, and is a route in which only the F goods are transported by the 10-ton vehicle of the O transport company. The route marked by black circle 4 has a running distance of 27 km on general roads.

The CO2 emissions prediction unit 103 predicted the CO2 emissions per 10 ton vehicle for each of the routes indicated by black circles 2 to 4, and predicted the CO2 emissions per case based on the prediction results. The prediction results are as shown in FIG.
FIG. 12 is an example of a transportation plan created by this service, and is an example of a predicted result of CO2 emissions per cargo volume (one pallet and one case) in an example different from the examples shown in FIGS. 9 and 10. It is.
In the table in Figure 12, from the left side, the following items are CO2 emissions (per 10-ton vehicle), CO2 emissions per case, freight charges (for 10-ton vehicles), and freight charges per case. Yes, and the results (numeric values) of the routes in black circles 1 to 4 are substituted.
Here, the route marked by black circle 1 is shown for reference and indicates the route of the example in FIG. 9 (the route of the original transportation plan).
Comparing the result of the route indicated by black circle 1 (the original transportation plan in the example of FIGS. 9 and 10) and the total result of the routes indicated by black circles 2 to 4 (the second transportation plan in the example of FIG. 11), CO2 emissions per case will not reach the annual policy of 0.33tCO2 even in the second transportation plan, but with limited vehicle information (search results from matching sites), an improvement of 0.22tCO2 has been achieved. It was seen.
There was also an improvement in freight costs (logistics costs), with the unit price per case increasing from 250 yen to 179 yen.
Therefore, Company A decided to adopt the second transportation plan (transportation plan in the example of FIGS. 11 and 12).
In this way, Company A can compare the CO2 emissions and unit price per case, so it can select an appropriate transportation plan from multiple transportation plans (if no appropriate transportation plan exists, further transportation plans can be drawn up).

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

For example, in the above example, the target of the transportation plan was a truck, but it is not limited to this, and any vehicle that emits CO2 during movement can be used, such as passenger cars, motorcycles, airplanes, and ships. can do.

For example, in the above example, the weight of the cargo was obtained, and the CO2 emissions per pallet and per case were calculated based on the weight, but the present invention is not limited thereto.
That is, the weight or volume of the luggage may be obtained, and the CO2 emissions per arbitrary unit amount converted from the weight or volume may be calculated.

For example, the CO2 emission prediction model 403 is a model corresponding to the prediction method shown in FIG. 2 in the above-described embodiment, but is not particularly limited thereto.

Specifically, for example, in the prediction method shown in FIG. 2, the CO2 emissions per truck are calculated based on fuel efficiency, and the only factors that change the fuel efficiency are local roads and expressways. That is, the only input parameters for varying fuel efficiency were local roads and expressways.
However, as shown in FIG. 13, various elements can be employed as input parameters (elements) for varying fuel efficiency.
FIG. 13 shows an example of factors that change fuel efficiency and are necessary for predicting CO2 emissions.
For example, seasonal factors such as Obon/New Year's and end of the year, time of day factors, driver's habits, weather, etc. may be employed as input parameters (elements) for varying fuel efficiency.

Further, for example, the CO2 emission prediction model 403 may be a model in which a dispatcher's empirical rules are converted into AI, as shown in FIG.
FIG. 14 is a diagram showing an example of a CO2 emission prediction model as an AI model.
That is, although not illustrated, the server 1 or other information processing device may also include a learning section.
The learning department collects information on route decisions and fuel usage, as well as data on actual CO2 emissions, when dispatchers make their own route decisions and actually drive trucks. do.
Here, the data collection tools for route decision-making, fuel usage records, and CO2 emissions are not particularly limited; for example, existing vehicle dispatch systems (transportation planning), digital tachographs (operation status), drive recorders (image Data, etc.), fuel tank meters (fuel efficiency data), terminals carried by dispatchers, etc. can be adopted.
The learning section accumulates data on CO2 emissions by repeating the above process, and accumulates scheduled and actual CO2 emissions (fuel consumption) and data on which errors have been corrected.
The learning unit uses the data accumulated in this way as learning data and performs machine learning to generate or generate an AI model capable of proposing CO2 emissions suppression optimization as a CO2 emissions prediction model 403. Can be updated.
The CO2 emissions prediction unit 103 and the planning unit 104 can create an optimal transportation plan using such an AI model.
In this way, it becomes possible to propose optimization (optimal transportation plans) by applying the dispatcher's empirical rules to AI.

Moreover, each hardware configuration shown in FIG. 5 is merely an example for achieving the object of the present invention, and is not particularly limited.

Further, the functional block diagram shown in FIG. 6 is merely an example and is not particularly limited. In other words, it is sufficient that the information processing system has a function that can execute the series of processes described above as a whole, and the type of functional block used to realize this function is not particularly limited to the example shown in FIG. 6. .

Furthermore, the locations of the functional blocks are not limited to those shown in FIG. 6, and may be arbitrary. For example, at least a part of the functional blocks on the server 1 side may be provided in the logistics company terminal 2, the shipper terminal 3, or an information processing device (not shown), or vice versa.
One functional block may be composed of a single piece of hardware, or may be composed of a single piece of software.

When the processing of each functional block is executed by software, a program constituting the software is installed in a computer or the like from a network or a recording medium.
The computer may be a computer built into dedicated hardware. Further, the computer may be a computer that can execute various functions by installing various programs, such as a server, a general-purpose smartphone, or a personal computer.

Recording media containing such programs are not only comprised of removable media that is distributed separately from the device itself in order to provide the program to each user, but also are pre-installed in the device body and delivered to each user. Consists of provided recording media, etc.

Note that in this specification, the step of writing a program to be recorded on a recording medium is not only a process that is performed chronologically in accordance with the order, but also a process that is not necessarily performed chronologically, but may be performed in parallel or individually. It also includes the processing to be executed.
Furthermore, in this specification, the term system refers to an overall device composed of a plurality of devices, a plurality of means, and the like.

In summary, the information processing apparatus to which the present invention is applied only needs to have the following configuration, and can take various embodiments.
That is, the information processing device (for example, the server 1 in FIG. 4) to which the present invention is applied,
In an information processing device that creates a plan for transporting the goods of a shipper (shipper S in FIG. 1) by a moving body from a shipping source to a shipping destination as a transportation plan,
Acquisition of shipper side information, which is information on the shipper side and includes at least the weight or volume of the product, the shipping source and the shipping destination, as shipper side information (for example, shipper side information in FIG. 1) means (for example, the shipper side information acquisition unit 101 in FIG. 6),
Information on the logistics side that manages the transportation of the mobile object, which includes at least a moving object feature quantity (for example, the vehicle information in FIG. 1) indicating the characteristics of the mobile object, is logistics side information acquisition means (for example, the logistics side information acquisition unit 102 in FIG. 6),
Based on at least part of the shipper side information and the logistics side information, predetermined preconditions (for example, the preconditions shown in FIG. 7) including the travel route from the shipping source to the shipping destination are set, and the preconditions are Carbon dioxide emissions prediction that predicts carbon dioxide emissions per unit amount of weight or volume (for example, CO2 emissions per pallet and per case shown in FIG. 8) when the mobile object moves under the conditions means (for example, the CO2 emission prediction unit 103 in FIG. 6),
Planning means (for example, the planning unit 104 in FIG. 6) that creates one or more of the transportation plans based on each of the carbon dioxide emissions predicted when the preconditions are changed;
Equipped with.

Presentation means (for example, the presentation unit shown in FIG. 6 105)
It is possible to further include the following.

The carbon dioxide emissions prediction means includes:
Calculate the carbon dioxide emissions per moving object based on the travel distance and fuel consumption when the moving object moves under the above preconditions (for example, calculate as shown in FIG. 2, FIG. 7, and 2 in FIG. 8). death),
Calculate the carbon dioxide emissions per unit amount based on the carbon dioxide emissions per moving body and the weight or volume of the product (for example, calculate as shown in 3 in FIG. 8)
be able to.

If there are three or more bases based on the shipping source and the shipping destination (for example, in the case shown in Figure 11),
The carbon dioxide emissions prediction means sets the preconditions for each of two or more travel routes between bases (for example, as shown in FIG. 11),
For each of the two or more travel routes, predict the carbon dioxide emissions per unit amount (for example, predict as shown in FIG. 12)
be able to.

The carbon dioxide emissions prediction means includes:
A model obtained as a result of machine learning based on actual carbon dioxide emissions when the moving body moves under the actual preconditions, the model being at least part of the shipper side information and the logistics side information. When inputting , a model that outputs the carbon dioxide emissions per unit amount (for example, the CO2 emissions prediction model 403 of FIG. 6 that has been converted to AI as shown in FIG. 14) is obtained, and
calculating the carbon dioxide emissions per unit amount using the model;
be able to.

1: Server, 2, 2-1, 2-n: Logistics company terminal, 3, 3-1, 3-m: Shipper terminal, 11: CPU, 12: ROM, 13: RAM, 14: Bus, 15 : input/output interface, 16: output section, 17: input section, 18: storage section, 19: communication section, 20: drive, 30: removable media, 101: shipper side information acquisition section, 102: logistics side information acquisition section, 103: CO2 emissions prediction unit, 104: Planning unit, 105: Presentation unit, 401: Shipper side DB, 402: Logistics side DB, 403: CO2 emissions prediction model, C: Consumer, S: Shipper, V: Supply Person, L: Logistics company

Claims (7)

In an information processing device that creates a plan for transporting a shipper's products from a shipping source to a shipping destination using a moving object as a transportation plan,
Shipper side information acquisition means for acquiring, as shipper side information, information on the shipper side that includes at least the weight or volume of the product, the shipping source and the shipping destination;
Logistics-side information acquisition means for acquiring, as logistics-side information, information on the logistics side that manages the transportation of the mobile object and that includes at least a moving object characteristic amount indicating the characteristics of the mobile object;
When predetermined preconditions including a travel route from the transport source to the transport destination are set based on at least part of the shipper side information and the logistics side information, and the mobile object moves under the preconditions. a carbon dioxide emissions prediction means for predicting carbon dioxide emissions per unit amount of weight or volume;
Planning means for creating one or more of the transportation plans based on each of the carbon dioxide emissions predicted when the preconditions are changed;
An information processing device comprising: 2. The method according to claim 1, further comprising presentation means for presenting one or more of the drafted transportation plans and each predicted value of carbon dioxide emissions per unit amount to respective terminals on the shipper's side and the logistics side. The information processing device described. The carbon dioxide emissions prediction means includes:
Calculating the amount of carbon dioxide emissions per mobile body based on the travel distance and fuel consumption when the mobile body moves under the preconditions,
calculating the amount of carbon dioxide emissions per unit amount based on the amount of carbon dioxide emissions per moving object and the weight or volume of the product;
The information processing device according to claim 1. If there are three or more bases based on the transportation source and the transportation destination,
The carbon dioxide emissions prediction means sets the preconditions for each of two or more travel routes between bases,
The information processing device according to claim 3, wherein the amount of carbon dioxide emissions per unit amount is predicted for each of the two or more travel routes. The carbon dioxide emissions prediction means includes:
A model obtained as a result of machine learning based on actual carbon dioxide emissions when the moving body moves under the actual preconditions, the model being at least part of the shipper side information and the logistics side information. When inputting , a model that outputs the carbon dioxide emissions per unit amount is obtained, and
calculating the carbon dioxide emissions per unit amount using the model;
The information processing device according to claim 1. In an information processing method executed by an information processing device that creates a transportation plan for transporting a shipper's products from a transportation source to a transportation destination using a mobile object,
a shipper-side information acquisition step of acquiring, as shipper-side information, information on the shipper's side that includes at least the weight or volume of the product, the shipping source, and the shipping destination;
a logistics-side information acquisition step of acquiring, as logistics-side information, information on the logistics side that manages the transportation of the mobile object and that includes at least a moving object feature amount indicating the characteristics of the mobile object;
When predetermined preconditions including a travel route from the transport source to the transport destination are set based on at least part of the shipper side information and the logistics side information, and the mobile object moves under the preconditions. a carbon dioxide emissions prediction step of predicting carbon dioxide emissions per unit amount of weight or volume;
a planning step of creating one or more of the transportation plans based on each of the carbon dioxide emissions predicted when the preconditions are changed;
Information processing methods including A computer that creates a transportation plan for transporting the shipper's products from the shipping source to the shipping destination using a moving object.
a shipper-side information acquisition step of acquiring, as shipper-side information, information on the shipper's side that includes at least the weight or volume of the product, the shipping source, and the shipping destination;
a logistics-side information acquisition step of acquiring, as logistics-side information, information on the logistics side that manages the transportation of the mobile object and that includes at least a moving object feature amount indicating the characteristics of the mobile object;
When predetermined preconditions including a travel route from the transport source to the transport destination are set based on at least part of the shipper side information and the logistics side information, and the mobile object moves under the preconditions. a carbon dioxide emissions prediction step of predicting carbon dioxide emissions per unit amount of weight or volume;
a planning step of creating one or more of the transportation plans based on each of the carbon dioxide emissions predicted when the preconditions are changed;
A program that executes control processing including.

Images