JP7755269B2 - Information processing system, information processing method and program - Google Patents

Description

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

Emissions of carbon dioxide and other substances have been calculated (see Patent Document 1).

Japanese Patent Application Laid-Open No. 2007-164754

However, calculating indirect emissions downstream in the supply chain is difficult.

The present invention was made in light of this background, and aims to determine indirect emissions downstream of the supply chain.

The main invention of the present invention, which aims to solve the above problem, is an information processing system characterized by comprising: a consumption estimation unit that uses a large-scale language model to estimate the amount of energy consumed during product use; and an emissions calculation unit that multiplies the amount of energy consumed by the energy emission coefficient to calculate the amount of greenhouse gases emitted during product use.

Other problems and solutions disclosed in this application will be made clear in the detailed description of the invention and drawings.

This invention makes it possible to determine indirect emissions downstream in the supply chain.

FIG. 1 is a diagram illustrating an example of the overall configuration of an information processing system. FIG. 2 illustrates an example of a hardware configuration of a management server 2. FIG. 2 illustrates an example of the software configuration of a management server 2. FIG. 1 is a diagram illustrating the calculation process of emissions related to Category 11 of Scope 3.

<System Overview>
An information processing system according to one embodiment of the present invention will be described below. The information processing system of this embodiment is a system for calculating greenhouse gas emissions, and in particular, attempts to calculate indirect emissions (emissions related to the use of sold products) related to Scope 3 Category 11 of the GHG Protocol. Emissions related to Category 11 are difficult to calculate precisely, so estimation is necessary. Therefore, the information processing system of this embodiment uses a large-scale language model to estimate energy consumption during product use, and calculates emissions based on the estimated energy consumption.

Figure 1 is a diagram showing an example of the overall configuration of an information processing system. The information processing system of this embodiment includes a management server 2. The management server 2 is communicatively connected to a user terminal 1 and an API server 3 via a communications network. The communications network is, for example, the Internet, and is constructed using a public telephone network, a mobile phone network, a wireless communication path, Ethernet (registered trademark), or the like.

The user terminal 1 is a computer operated by a user. The user terminal 1 can be, for example, a smartphone, a tablet computer, or a personal computer.

The management server 2 may be a general-purpose computer such as a workstation or personal computer, or may be logically realized using cloud computing.

The API server 3 is a computer that generates data using a large-scale language model. The API server 3 provides an API (Application Programming Interface) and can perform generation processing using a large-scale language model in response to a request. The API server 3 can be, for example, a ChatGPT server.

<Management Server>
FIG. 2 is a diagram illustrating an example of the hardware configuration of the management server 2. Note that the illustrated configuration is an example, and other configurations may also be used. The management server 2 includes a CPU 201, memory 202, storage device 203, communication interface 204, input device 205, and output device 206. The storage device 203 stores various data and programs, and is, for example, a hard disk drive, solid state drive, or flash memory. The communication interface 204 is an interface for connecting to a communication network, and is, for example, an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone network, a wireless communication device for wireless communication, a USB (Universal Serial Bus) connector or an RS232C connector for serial communication, etc. The input device 205 is used to input data, and is, for example, a keyboard, mouse, touch panel, button, microphone, etc. The output device 206 is used to output data, and is, for example, a display, printer, speaker, etc. Each functional unit of the management server 2 described below is realized by the CPU 201 reading a program stored in the storage device 203 into the memory 202 and executing it, and each storage unit of the management server 2 is realized as part of the storage area provided by the memory 202 and the storage device 203.

Figure 3 shows an example of the software configuration of the management server 2. The management server 2 includes an emission coefficient memory unit 231, a sales information memory unit 232, an emission amount memory unit 233, a consumption amount estimation unit 211, an emission amount calculation unit 212, a sales number acquisition unit 213, a count acquisition unit 214, an energy usage designation unit 215, and an emission amount output unit 216.

<Storage section>
The emission coefficient storage unit 231 stores an emission coefficient for each type of activity amount. At least, it stores an emission coefficient for each type of energy. The types of energy are, for example, electricity, gas, fuel, etc. The emission coefficient may be secondary data provided by, for example, the Ministry of the Environment. The emission coefficient storage unit 231 may store emission coefficients in association with sales regions and types of energy.

The sales information storage unit 232 stores information related to product sales (hereinafter referred to as sales information). Sales information can include information identifying the product (product identification information), time information (for example, year, fiscal year, month, date, etc.), and sales quantity. Sales information may also include sales region. Sales information can include information related to the product (product information). For example, sales information can include the standard number of uses of the product. For consumables, the number of uses can be calculated by dividing the content volume by the standard amount used per use. For equipment, the number of uses can be calculated by multiplying the standard useful life until disposal by the standard number of times the equipment is used per year. Sales information can include a description of how the product is used (this embodiment assumes text data, but image data or audio data may also be used). The description of how the product is used may, but does not have to, include a description of the type of energy used during use.

The emission amount storage unit 233 stores information about emission amounts (hereinafter referred to as emission amount information). The emission amount information may include, for example, time information (e.g., year, fiscal year, year/month, date, etc.), scope, category, type of activity amount, and emission amount.
<Functional department>
The consumption estimation unit 211 estimates the consumption of energy used (consumed) when the product is used. The consumption estimation unit 211 can estimate the consumption using a large-scale language model. The consumption estimation unit 211 can obtain an estimate of the energy consumption by providing a prompt to the large-scale language model instructing it to estimate the energy consumption. The consumption estimation unit 211 may provide a prompt to the large-scale language model that includes an explanation of how the product is used and an instruction to estimate the consumption related to the use.

In this embodiment, it is assumed that the large-scale language model is used by sending a prompt to the API server 3 and receiving a response from the API server 3, but the management server 2 may also be equipped with a model storage unit that stores the large-scale language model and an inference processing unit that performs processing related to inference using the model.

The emission calculation unit 212 calculates the amount of greenhouse gas emissions. The emission calculation unit 212 can calculate the amount of emissions by multiplying the amount of activity by an emission coefficient. For indirect emissions related to Scope 3 Category 11, the emission calculation unit 212 can calculate the amount of emissions by having the consumption estimation unit 211 estimate the amount of energy consumption and multiplying the estimated consumption by the emission coefficient corresponding to the type of energy.

The sales number acquisition unit 213 acquires the sales number of the product. The sales number acquisition unit 213 can acquire the sales number corresponding to the product from the sales information storage unit 232. The sales number acquisition unit 213 can also receive the sales number of the product from the user terminal 1, for example, and set the received sales number in the sales information registered in the sales information storage unit 232.

The count acquisition unit 214 acquires the number of times the product is used. The count acquisition unit 214 can acquire the number of times the product is used from the sales information storage unit 232. The count acquisition unit 214 can also receive the number of times the product is used from the user terminal 1, for example, and set the received number in the sales information registered in the sales information storage unit 232.

The energy use specification unit (energy consumption specification unit) 215 can accept specification of the type of energy used (consumed) when using the product. The energy use specification unit (energy consumption specification unit) 215 determines whether the product information included in the sales information includes the type of energy used (consumed) when using the product, and if the type of energy used when using the product is not included, may accept specification of the type of energy from the user terminal 1.

The consumption estimation unit 211 may estimate the type of energy used (consumed) when the product is in use. For example, the consumption estimation unit 211 can estimate the type of energy by providing a prompt (first prompt) to the large-scale language model that includes an instruction to estimate the type of energy used (consumed) when the product is in use. The consumption estimation unit 211 can then provide a prompt (second prompt) to the large-scale language model that includes the estimated type and an instruction to estimate the energy consumption for each type, thereby estimating the consumption for each type.

The emissions calculation unit 212 can calculate the total amount of indirect emissions related to Scope 3 Category 11 by the seller of a product for that product by multiplying the amount of energy consumed by the emission factor and the number of sales. The emissions calculation unit 212 can calculate the amount of emissions by multiplying the amount of energy consumed by the emission factor and the number of times the product is used. The number of times the product is used can be obtained from the sales information storage unit 232. The emissions calculation unit 212 can calculate the amount of emissions by aggregating the values obtained by multiplying the consumption amount for each type by the emission factor corresponding to that type. The emission factor corresponding to the type of energy can be obtained from the emission factor storage unit 231.

The emission amount output unit 216 outputs the emission amount. The emission amount output unit 216 can output the emission amount in the form of a report, for example. The emission amount output unit 216 can aggregate and output the emission amount by time information (year, fiscal year, year/month, etc.), scope, and category. The emission amount output unit 216 can output the aggregated emission amount as a number or a graph. The emission amount output unit 216 can create screen information for displaying the emission amount and send it to the user terminal 1.

<Operation>
FIG. 4 is a diagram for explaining the calculation process of emissions related to Category 11 of Scope 3.

The management server 2 sends a prompt to the API server 3 inquiring about the amount of energy consumed when the product is in use (S301), obtains a response from the large-scale language model (LLM) returned by the API server 3 (S302), and calculates the amount of emissions by multiplying the consumption amount included in the response by the energy emission coefficient and the number of times the product is used (S303).

In this way, the information processing system of this embodiment can estimate and calculate emissions downstream in the supply chain (Scope 3, Category 11).

The present embodiment has been described above, but the above embodiment is intended to facilitate understanding of the present invention and is not intended to limit the present invention. The present invention may be modified or improved without departing from its spirit, and equivalents thereof are also included within the present invention.

<Disclosures>
The present disclosure also includes the following configurations.
[Item 1]
a consumption estimation unit that estimates the amount of energy consumed when the product is in use using a large-scale language model;
an emission calculation unit that calculates the amount of greenhouse gas emitted during use of the product by multiplying the consumption amount by the energy emission coefficient;
An information processing system comprising:
[Item 2]
Item 1, an information processing system according to item 1,
the consumption estimation unit provides a prompt to the large-scale language model, the prompt including a description of a usage of the product and an instruction to estimate the consumption related to the usage;
An information processing system characterized by:
[Item 3]
Item 1, an information processing system according to item 1,
a sales number acquisition unit that acquires the sales number of the product;
the emission calculation unit calculates the indirect emissions by the seller of the product by multiplying the consumption amount by the emission coefficient and the number of sales;
An information processing system characterized by:
[Item 4]
Item 1, an information processing system according to item 1,
a number acquisition unit that acquires the number of times the product is used,
the emission calculation unit calculates the emission amount by multiplying the consumption amount by the emission coefficient and the number of times;
An information processing system characterized by:
[Item 5]
Item 1, an information processing system according to item 1,
an energy use specification unit that accepts specification of the type of energy used when using the product;
the consumption amount estimation unit estimates the types of energy by providing a first prompt to the large-scale language model, the first prompt including an instruction to estimate the types of energy used when the product is used, and estimates the consumption amounts of the energy for each of the types by providing a second prompt to the large-scale language model, the second prompt including an instruction to estimate the estimated types and the energy consumption amounts for each of the types;
the emission calculation unit calculates the emission amount by aggregating values obtained by multiplying the consumption amount for each of the types by the emission coefficient corresponding to the type;
An information processing system characterized by:
[Item 6]
estimating the consumption of energy used during use of the product using a large-scale language model;
calculating the amount of greenhouse gases emitted during use of the product by multiplying the consumption amount by the energy emission factor;
An information processing method characterized by being executed by a computer.
[Item 7]
estimating the consumption of energy used during use of the product using a large-scale language model;
calculating the amount of greenhouse gases emitted during use of the product by multiplying the consumption amount by the energy emission factor;
A program that causes a computer to execute the following.

1 User terminal 2 Management server

Claims (7)

a sales information storage unit that stores information about the sales of the product, including at least an explanation of how the product is used;
a consumption estimation unit that estimates the consumption by providing a prompt to a large-scale language model, the prompt including a description of the usage mode of the product, which is composed of text data, and an instruction to estimate the consumption of energy used when the product is used;
an emission calculation unit that calculates the amount of greenhouse gas emitted during use of the product by multiplying the consumption amount by the energy emission coefficient;
An information processing system comprising: 2. The information processing system according to claim 1,
the consumption estimation unit provides the large-scale language model with a prompt including a description of the usage of the product, which is formed from image data , and an instruction to estimate the consumption ;
An information processing system characterized by: 2. The information processing system according to claim 1,
a sales number acquisition unit that acquires the sales number of the product;
the emission calculation unit calculates the indirect emissions by the seller of the product by multiplying the consumption amount by the emission coefficient and the number of sales;
An information processing system characterized by: 2. The information processing system according to claim 1,
a number acquisition unit that acquires the number of times the product is used,
the emission calculation unit calculates the emission amount by multiplying the consumption amount by the emission coefficient and the number of times;
An information processing system characterized by: 2. The information processing system according to claim 1,
an energy use specification unit that accepts specification of the type of energy used when using the product;
the consumption amount estimation unit estimates the types of energy by providing a first prompt to the large-scale language model, the first prompt including an instruction to estimate the types of energy used when the product is used, and estimates the consumption amounts of the energy for each of the types by providing a second prompt to the large-scale language model, the second prompt including an instruction to estimate the estimated types and the energy consumption amounts for each of the types;
the emission calculation unit calculates the emission amount by aggregating values obtained by multiplying the consumption amount for each of the types by the emission coefficient corresponding to the type;
An information processing system characterized by: a sales information storage unit that stores information about the sales of the product, including at least an explanation of how the product is used;
providing a prompt, the prompt including a description of the usage of the product, which is made up of text data, and an instruction to estimate the energy consumption when using the product , to a large-scale language model to estimate the consumption;
calculating the amount of greenhouse gases emitted during use of the product by multiplying the consumption amount by the energy emission factor;
An information processing method characterized by being executed by a computer. a sales information storage unit that stores information about the sales of the product, including at least an explanation of how the product is used;
providing a prompt, the prompt including a description of the usage of the product, which is made up of text data, and an instruction to estimate the energy consumption when using the product , to a large-scale language model to estimate the consumption;
calculating the amount of greenhouse gases emitted during use of the product by multiplying the consumption amount by the energy emission factor;
A program that causes a computer to execute the following.