JP7631768B2 - Information processing device and information processing method - Google Patents

Description

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

Technology is known to assist in estimating expected costs when procuring new parts from suppliers. For example, Patent Literature 1 discloses an invention that determines whether an estimated manufacturing cost for a machine part is within an expected range.

JP 2020-021462 A

By the way, purchasing personnel may acquire empirical knowledge about effective purchasing conditions for reducing costs (e.g., items to be ordered, payment terms, delivery dates, relationships with suppliers, etc.) based on past purchasing records.

However, the technology disclosed in Patent Document 1 does not take past purchasing records into account, so effective purchasing conditions based on past purchasing records are not reflected in the manufacturing cost estimate. Therefore, even if such a technology is used, there is a possibility that opportunities to reduce manufacturing costs will be missed.

The object of the present invention is to provide an information processing device that can reduce costs when purchasing products, etc.

One of the present inventions for achieving the above object is an information processing device that includes an acquisition unit that acquires a plurality of pieces of order data including first information indicating a budget for an order target, second information indicating an actual cost for the order target, third information indicating a time when the order target was ordered, fourth information indicating a delivery date for the order target, and amount information indicating a relationship between the budget for the order target and the actual cost for the order target, and a model generation unit that generates a tree-structured learning model using the first to fourth pieces of information of the plurality of order data as independent variables and the amount information as a dependent variable.

With this configuration, it is possible to reduce ordering costs by using past purchase records for the item being ordered.

Another aspect of the present invention is the information processing device described above, in which the order data further includes fifth information indicating a monetary payment method when ordering the order target, and the model generation unit generates the learning model using the first to fifth information as independent variables.

In this configuration, the same payment method used when placing an order for a past order item is used, making it possible to reduce ordering costs more effectively.

Another aspect of the present invention is the information processing device described above, in which the order data further includes sixth information indicating an estimated price for the order object, and the model generation unit generates the learning model using the first to sixth information as independent variables.

In this configuration, the estimated price used when the order item was purchased in the past is used, making it possible to reduce ordering costs more effectively.

Another aspect of the present invention is the information processing device described above, in which the order data further includes seventh information indicating the contract method for the order target, and the model generation unit generates the learning model using the first to seventh information as independent variables.

In this configuration, the contract method used for past orders is used, making it possible to reduce ordering costs more effectively.

Another aspect of the present invention is the information processing device described above, in which the order data further includes eighth information indicating a bidding method for ordering the order target, and the model generation unit generates the learning model using the first to eighth information as independent variables.

In this configuration, the bidding method used when placing orders for past order items is used, making it possible to reduce ordering costs more effectively.

Another aspect of the present invention is the information processing device, in which the order data further includes ninth information indicating the contracting party of the order target, and the model generation unit generates the learning model using the first to ninth information as independent variables.

In this configuration, since the contracting party to which the order is placed is used, it is possible to reduce ordering costs more effectively.

Another aspect of the present invention is the information processing device described above, in which the order data further includes tenth information indicating a transaction period with the contracting party, and the model generation unit generates the learning model using the first to tenth information as independent variables.

In this configuration, the transaction period with the contracting party is used, making it possible to reduce ordering costs more effectively.

Another aspect of the present invention is the information processing device described above, in which the order data further includes eleventh information regarding sales by the contracting party to the ordering party of the order target, and the model generation unit generates the learning model using the first to eleventh information as independent variables.

In this configuration, information about the contracting party's sales to the ordering party of the order target is used, making it possible to reduce ordering costs more effectively.

Another aspect of the present invention is an information processing device that includes a storage unit that stores a tree-structured learning model for each of a plurality of order objects, the tree-structured learning model being generated using a plurality of order data including, as independent variables, first information indicating the budget of an order object, second information indicating the actual cost of the order object, third information indicating the time when the order object was ordered, and fourth information indicating the delivery date of the order object, and, as dependent variables, amount information indicating the relationship between the budget of the order object and the actual cost of the order object, and an output unit that outputs an analysis result of the learning model corresponding to the input order object from among the plurality of the learning models.

With this configuration, it is possible to reduce ordering costs by using past purchase records for the desired order item.

The present invention provides an information processing device that can reduce costs when purchasing products, etc.

FIG. 1 is a diagram showing a configuration of an information processing system 1. FIG. 2 is a diagram illustrating an example of hardware of an information processing device 2. FIG. 11 is a diagram showing an example of a plurality of order data. FIG. 2 is a diagram showing functional blocks of the information processing device 2. 11 is a flowchart illustrating the process flow up to generating a learning model. FIG. 4 is a diagram illustrating an example of a decision tree generated by a model generation unit. FIG. 2 is a diagram showing decision trees for each of a plurality of order targets stored in a storage unit. 13 is a flowchart illustrating a process flow up to displaying an analysis result. FIG. 13 is a diagram illustrating an example of an input screen. FIG. 13 is a diagram showing an example of an output screen.

==Embodiment==
<Information Processing System>
1 is a diagram showing a configuration of an information processing system 1 according to the present embodiment. The information processing system 1 includes an information processing device 2 and a user terminal 4. The information processing device 2 and the user terminal 4 are communicatively connected via a network NW. The network NW is, for example, a public line such as the Internet, or a dedicated line such as a Wide Area Network (WAN) or a Local Area Network (LAN).

The user terminal 4 is a general personal computer, a tablet terminal, etc. The user terminal 4 is a terminal operated by a user of the information processing system 1 (hereinafter referred to as the "user").

[Hardware configuration of information processing device]
2 is a diagram showing an example of hardware of the information processing device 2. The illustrated information processing device 2 includes a processor 20, a main storage device 21, an auxiliary storage device 22, an input device 23, an output device 24, and a communication device 25. The illustrated information processing device 2 may be realized, in whole or in part, using virtual information processing resources provided using virtualization technology, process space separation technology, or the like, such as a virtual server provided by a cloud system. In addition, all or in part of the functions provided by the information processing device 2 may be realized by a service provided by the cloud system via an API (Application Programming Interface), for example. The information processing system 1 may be configured using a plurality of information processing devices 2 connected to each other so as to be able to communicate with each other.

In the figure, the processor 20 is configured using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), an AI (Artificial Intelligence) chip, etc.

The main memory device 21 is a device that stores programs and data, and is, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), or a non-volatile memory (NVRAM (Non Volatile RAM)).

The auxiliary storage device 22 is, for example, an SSD (Solid State Drive), a hard disk drive, an optical storage device (CD (Compact Disc), DVD (Digital Versatile Disc), etc.), a storage system, an IC card, a read/write device for a recording medium such as an SD card or an optical recording medium, a storage area of a cloud server, etc. Programs and data can be read into the auxiliary storage device 22 via a recording medium reader or a communication device 25. The programs and data stored (memorized) in the auxiliary storage device 22 are read into the main storage device 21 as needed.

The input device 23 is an interface that accepts input from the outside, and is, for example, a keyboard, a mouse, a touch panel, a card reader, a pen-input tablet, a voice input device, etc.

The output device 24 is an interface that outputs various information such as the progress of processing and the results of processing. The output device 24 is, for example, a display device (liquid crystal monitor, LCD (Liquid Crystal Display), graphic card, etc.) that visualizes the various information described above, a device that converts the various information described above into audio (audio output device (speaker, etc.)), or a device that converts the various information described above into text (printer, etc.).

The input device 23 and the output device 24 constitute a user interface that accepts information from the user and presents information.

The communication device 25 is a device that realizes communication with other devices. The communication device 25 is a wired or wireless communication interface that realizes communication with other devices via a communication network such as the Internet, and is, for example, a NIC (Network Interface Card), a wireless communication module, a USB module, etc. The information processing device 2 is configured to input and output information to and from the user terminal 4 via the communication device 25.

The information processing device 2 may be equipped with, for example, an operating system, a file system, a DBMS (DataBase Management System) (relational database, NoSQL, etc.), a KVS (Key-Value Store), etc.

The above-mentioned functions of the information processing system 1 are realized by the processor 20 of the information processing device 2 reading and executing a program stored in the main memory device 21, or by the hardware (FPGA, ASIC, AI chip, etc.) that constitutes the information processing system 1. The information processing system 1 stores the above-mentioned various information (data), for example, as a database table or a file managed by a file system.

[Order data]
Fig. 3 is a diagram illustrating multiple order data in this embodiment stored in the auxiliary storage device 22 described above. Here, "order data" refers to data on one past order item for one order target, and is purchase history. Also, "multiple order data" refers to data on multiple past order items for one order target. Each of the multiple rows shown in Fig. 3 indicates data on one past order item for one order target. Each of the multiple columns shown in Fig. 3 indicates information (described below) related to the order target.

The "order subject" is the object that the purchaser places an order with the contractor, and includes, for example, products such as equipment and parts, construction work including installation work, dismantling work, and civil engineering work for equipment, and services such as maintenance of equipment. Note that the order subject also includes a combination of products and services, such as the purchase of equipment and the installation work for the purchased equipment. Hereinafter, products, services, or combinations of products and services will be referred to as "products, etc.".

The "product code" shown in the lower left of FIG. 3 is a code for identifying the order target. The product code is set by the administrator of the information processing device 2. In this embodiment, a "denitrification device" will be used as an example of an order target identified by the product code "0000001".

The "information regarding the order subject" is classified into items 50, 51, 52, and 53 shown in Figure 3.

Item 50 is information regarding the amount of the order. In FIG. 3, item 50 is written as "Amount." Item 50 includes information 50a, information 50b, and information 50c.

Information 50a indicates the budget for the order item, and is written as "Budget (yen)." Information 50a is the amount (budget) planned by the orderer to purchase the order item. Information 50a corresponds to "first information."

Information 50b indicates the actual cost of the item being ordered, and is expressed as "cost (yen)." The "actual cost" is the amount paid to the supplier when a contract is concluded with the supplier. Information 50b corresponds to the "second information."

Information 50c is information indicating the estimated price of the ordered item, and is written as "Estimate (yen)." The "estimated price of the ordered item" is the price of the ordered item quoted by the party to whom the estimate is requested after the order is placed. The party to whom the estimate is requested may be the same company as the ordering party, or it may be another company. Information 50c corresponds to "sixth information."

Note that the above information is merely an example, and item 50 may further include other information. The other information may include, for example, the consumption tax rate applied at the time of payment. Furthermore, if the actual payment of the cost is in a foreign currency, the other information may include the exchange rate applied at the time of payment.

Item 51 is information about the purchasing method of the ordered item. In FIG. 3, item 51 is written as "purchase method." Item 51 includes information 51a, information 51b, information 51c, information 51d, and information 51e.

Information 51a indicates the time when the order was placed, and is written as "order date." In this embodiment, information 51a is the date on which the order was placed (order date). Information 51a corresponds to "third information."

Information 51b indicates the delivery date of the ordered item, and is written as "delivery date." In this embodiment, information 51b is the delivery deadline date (delivery deadline). Information 51b corresponds to the "fourth information."

Information 51c indicates the payment method when ordering the order object, and is indicated as "payment method." In this embodiment, information 51c is a lump sum payment (lump sum) or installment payment (splits). In the case of installment payment, the number of installments may be taken into consideration as the payment method. Information 51c corresponds to "fifth information."

Information 51d indicates the contract method for the order target, and is written as "contract method." In this embodiment, information 51d is individual purchase (individual) or lump-sum purchase (lump-sum). The contract method may also include contract methods such as the VE (Value Engineering) method and the TP (Target Price) method. Information 51d corresponds to the "seventh information."

Information 51e indicates the bidding method when placing an order for the order target, and is written as "bidding method." In this embodiment, information 51e is special bidding (special bidding) or competitive bidding (competition). Information 51e corresponds to "8th information."

Note that the above information is merely an example, and item 51 may further include other information. Examples of other information include the date of quotation request, delivery destination, etc.

Item 52 is information about the contracting party to which the order is to be placed. In FIG. 3, item 52 is written as "contracting party." Item 52 includes information 52a, information 52b, and information 52c.

Information 52a indicates the contracting party of the order target, and is written as "contracting party." In this embodiment, information 52a is the name of the contracting company. "Contracting party" is the party to whom the order target is ordered when a contract is concluded. Information 52a corresponds to "ninth information."

Information 52b indicates the transaction period with the contracting party, and is written as "transaction years." In this embodiment, information 52b is the transaction period (transaction years) in years. The transaction years here are the number of years of transaction with the supplier at the time of ordering. Information 52b corresponds to the "tenth information."

Information 52c is information regarding sales of the order target to the client, and is expressed as "sales ratio." In this embodiment, information 52c is the ratio of sales to the client out of the total sales of the client. Information 52c corresponds to "11th information."

The above information is merely an example, and item 52 may further include other information. Examples of other information include the name of the contracting officer at the client, the classification of the client's contractor (e.g., large company, small or medium-sized enterprise, micro-enterprise, etc.), the age of the contracting officer at the client, the gender of the contracting officer at the client, etc.

Item 53 is amount information that indicates the relationship between the budget for the order and the actual cost for the order. In FIG. 3, item 53 is written as "discount." Item 53 includes information 53a and information 53b.

Information 53a indicates the discount rate for the order, and is written as "discount rate." In this embodiment, the discount rate is defined as "discount rate = 1 - cost/budget" using the budget (information 50a) and the cost (information 50b).

Information 53b indicates the step-by-step evaluation of the discount rate of the order target, and is indicated as "evaluation." In this embodiment, the discount rate (information 53a) is evaluated on a five-level scale, A to E, with A indicating "discount rate < -0.15," B indicating "-0.15 ≦ discount rate < -0.05," C indicating "-0.05 ≦ discount rate < 0.05," D indicating "0.05 ≦ discount rate < 0.15," and E indicating "0.15 ≦ discount rate."

In other words, A and B are cases where the purchase was made at a higher cost than the budget, C is a case where the purchase was made at a cost almost equal to the budget, and D and E are cases where the purchase was made at a lower cost than the budget.

[Functional blocks of information processing device]
4 is a diagram showing functional blocks of the information processing device 2 of this embodiment. In the information processing device 2 of this embodiment, an acquisition unit 30, a model generation unit 31, a storage unit 32, an input reception unit 33, and an output unit 34 are realized by the processor 20 executing a predetermined program.

When the model generation unit 31 generates a learning model, the acquisition unit 30 acquires multiple pieces of order data that are stored in advance in the auxiliary storage device 22.

The model generation unit 31 generates a learning model based on a tree-structured learning model, using the information 50a to 50c, 51a to 51e, and 52a to 51c (first to eleventh pieces of information) in FIG. 3 as independent variables and item 53 (discount) as a dependent variable. A "tree-structured learning model" is, for example, a decision tree or a random forest. Decision trees include classification trees and regression trees. In this embodiment, an aspect using a classification tree will be described.

The storage unit 32 uses multiple pieces of order data to store the generated decision tree for each of the multiple order targets.

The input reception unit 33 receives input from outside via a user interface such as an input screen displayed on the output device 24 or the user terminal 4.

The output unit 34 outputs the analysis results of the learning model corresponding to the order item input by the user from among the multiple learning models.

[Processing up to generating a learning model]
5 is a flowchart illustrating the flow of processing up to generation of a learning model by the information processing device 2. The processing up to generation of a learning model includes steps S11 and S12.

First, in step S11, the acquisition unit 30 of the information processing device 2 acquires a plurality of pieces of order data for a specified order target from among the plurality of pieces of order data stored in the auxiliary storage device 22. The plurality of pieces of order data shown in FIG. 3 are an example of the plurality of pieces of order data acquired by the acquisition unit 30 in step S11.

Next, in step S12, the model generation unit 31 of the information processing device 2 generates a learning model based on a decision tree using the multiple order data shown in FIG. 3. At this time, a learning model based on a decision tree is generated using the information 50a to 50c, 51a to 51e, and 52a to 51c in FIG. 3 as independent variables and the evaluation (information 53b), which is a discrete value, as a dependent variable.

Specifically, in this embodiment, the dependent variable is the evaluation (information 53b), which is a discrete value, so a learning model is generated using a classification tree. Note that there are no particular limitations on the algorithm for generating a learning model using a decision tree.

Figure 6 shows a decision tree 6a generated by the model generation unit 31 in step S12 using the multiple order data shown in Figure 3. In this example, multiple order data are classified according to the order timing, delivery method, and delivery date.

In this example, the number of classifications and the tree depth are limited to avoid overfitting. Furthermore, in this example, a decision is made as to whether or not to further classify a node based on the evaluation function at the node and a predefined threshold.

The evaluation function for a node can be, for example, the product of the information gain at the node and the number of data items at the node. The information gain at a node (parent node) is the difference between the impurity of the parent node and the impurity of multiple nodes (child nodes) after classifying the parent node. The impurity of multiple child nodes is the sum of the impurity of each child node weighted by the number of data items at that child node for all of the multiple child nodes. Gini impurity, entropy, etc. can be used as the impurity.

In Figure 6, first, all of the multiple order data are classified by the time of order (node n1). As a result, for order data with an order date in March, the evaluation function is smaller than a predetermined threshold, so division is terminated. Such conditions are then classified as evaluation E. On the other hand, order data with an order date other than March is further classified.

Next, all order data that was placed in a month other than March is classified by payment method (node n2). As a result, the order data that is paid in a lump sum and the order data that is paid in installments are further classified.

Next, all order data that was ordered in a month other than March and that has a lump-sum payment method is classified by delivery date (node n3). As a result, for order data with delivery dates of 10 months or more, the evaluation function is smaller than the specified threshold, so classification is terminated. Such conditions are then classified as evaluation E. On the other hand, order data with delivery dates of less than 10 months is further classified.

In Figure 6, the dashed lines at the ends of the branches indicate that further classification conditions are not shown.

The above-described process completes the process for generating the learning model. A similar process is used to generate learning models for other order targets. The learning models based on the decision trees generated for each of the multiple order targets are linked to the product code and stored in the memory unit 32. Figure 7 shows the decision trees for each of the multiple order targets stored in the memory unit 32.

[Processing up to displaying analysis results]
8 is a flowchart explaining the flow of processing up to when the information processing system 1 displays the analysis results. The processing up to when the analysis results are displayed includes steps S21 to S26. In this example, a user operates the user terminal 4. The user does not necessarily have much experience in purchasing. It is also assumed that the user has taken on the role of purchasing a denitration device and is considering placing an order for the denitration device.

First, in step S21, the user inputs a product code that identifies the desired order item via the input screen 40 displayed on the user terminal 4. Figure 9 shows an example of the input screen 40 at this time.

The input screen 40 displays a product code input window 40a, a major category selection window 40b, a medium category selection window 40c, and a minor category selection window 40d. The user can input the product code that identifies the denitrification device that is the desired item to be ordered into the product code input window 40a.

The user can also input a product code that identifies the denitrification device by selecting an item corresponding to the desired order item from each of the major category selection window 40b, the medium category selection window 40c, and the minor category selection window 40c.

At this time, the user places the mouse cursor over the major category selection window 40b and clicks. This displays a drop-down list, from which the user can select the major category (thermal power plant construction) to which the denitrification equipment belongs.

In the same way, the user selects the medium category (boiler-related) to which the denitration equipment belongs from the medium category selection window 40c. Next, in the same way, the user selects the denitration equipment from the small category selection window 40d. In response, the product code identifying the denitration equipment is automatically entered into the product code input window 40a. After entering the product code using one of the above procedures, the user clicks the OK button.

In step S22, the input reception unit 33 of the information processing device 2 receives the product code entered into the user terminal 4.

In step S23, the input reception unit 33 identifies a decision tree for the received product code. Specifically, the input reception unit 33 searches the memory unit 32 for the received product code, and identifies a decision tree associated with the searched product code.

In step S24, the acquisition unit 30 acquires a learning model based on the identified decision tree from the storage unit 32. That is, the acquisition unit 30 acquires the tree structure of the identified decision tree, the classification conditions at each node, the evaluation at each endpoint, etc.

In step S25, the output unit 34 outputs the analysis results based on the learning model acquired by the acquisition unit to the user terminal 4.

The "analysis results" are information based on the classification conditions of the ratings (information 53b), which are the dependent variables. The information based on the classification conditions of the ratings (information 53b) may be, for example, the classification conditions or comments based on the classification conditions.

In step S26, the user terminal 4 displays the analysis results received from the information processing device 2 on the output screen 41. FIG. 10 shows an example of the output screen 41 at this time.

The output screen 41 displays the product code 41a entered by the user, the product code decision tree 6a, and the analysis results 41b based on the decision tree. The decision tree displayed in FIG. 10 is the decision tree shown in FIG. 6.

In this example, a comment based on the classification criteria of rating E is displayed as the analysis result 41b. The analysis result 41b displayed on the output screen 41 describes the classification corresponding to the end points t1 and t2 of the decision tree shown in FIG. 6. End point t1 is a classification in which the order subject is placed in March. End point t2 is a classification in which the order subject is placed in a month other than March, the payment method is lump sum, and the delivery date is less than 10 months. End points t1 and t2 are classified as rating E on a five-point scale. A comment explaining this result is displayed in the analysis result 41b.

The user can further display the details of the classification of other endpoints by clicking "Next" shown in the analysis result 41b (not shown). The user can refer to such analysis results when ordering a denitrification device.

The above embodiments are intended to facilitate understanding of the present invention, and are not intended to limit the scope of the present invention. Furthermore, the present invention may be modified or improved without departing from the spirit of the present invention, and it goes without saying that the present invention includes equivalents.

For example, in this embodiment, the product (denitrification device) was used, but it may also be construction work, thermal power plant construction, nuclear power construction, etc. Even in such cases, the information processing device 2 can appropriately reduce costs when purchasing products, etc.

1: Information processing system 2: Information processing device 20: Processor 21: Main memory device 22: Auxiliary memory device 23: Input device 24: Output device 25: Communication device 30: Acquisition unit 31: Model generation unit 32: Memory unit 33: Input reception unit 34: Output unit 4: User terminal

Claims (11)

an acquisition unit that acquires a plurality of pieces of order data including first information indicating a budget for an order target, second information indicating an actual cost for the order target, third information indicating a time when the order target was ordered, fourth information indicating a delivery date for the order target, and amount information indicating a relationship between the budget for the order target and the actual cost for the order target;
a model generation unit that generates a tree-structured learning model using the first to fourth information of the plurality of pieces of order data as independent variables and the amount information as a dependent variable;
An information processing device comprising: The order data further includes fifth information indicating a payment method for ordering the order target,
The model generation unit generates the learning model using the first to fifth pieces of information as independent variables.
The information processing device according to claim 1 . The order data further includes sixth information indicating an estimated price of the order object,
The model generation unit generates the learning model using the first to sixth pieces of information as independent variables.
The information processing device according to claim 2 . The order data further includes seventh information indicating a contract type of the order target,
The model generation unit generates the learning model using the first to seventh information as independent variables.
The information processing device according to claim 3 . The order data further includes eighth information indicating a bidding method for ordering the order target,
The model generation unit generates the learning model using the first to eighth pieces of information as independent variables.
The information processing device according to claim 4. The order data further includes ninth information indicating a contracting party of the order target,
The model generation unit generates the learning model using the first to ninth pieces of information as independent variables.
The information processing device according to claim 5 . The order data further includes tenth information indicating a transaction period with the contracting party,
The model generation unit generates the learning model using the first to tenth pieces of information as independent variables.
The information processing device according to claim 6. The order data further includes eleventh information regarding sales of the contracting party to an ordering party of the order target,
The model generation unit generates the learning model using the first to eleventh pieces of information as independent variables.
The information processing device according to claim 7. a storage unit that stores, for each of a plurality of order targets, a tree-structured learning model generated using a plurality of order data including, as independent variables, first information indicating a budget for the order target, second information indicating an actual cost for the order target, third information indicating a time when the order target was ordered, and fourth information indicating a delivery date for the order target, and, as a dependent variable, amount information indicating a relationship between the budget for the order target and the actual cost for the order target;
An output unit that outputs an analysis result of the learning model corresponding to the input order target among the plurality of learning models;
An information processing device comprising: An information processing method by an information processing device,
acquiring a plurality of pieces of order data including first information indicating a budget for an order target, second information indicating an actual cost for the order target, third information indicating a time when the order target was ordered, fourth information indicating a delivery date for the order target, and amount information indicating a relationship between the budget for the order target and the actual cost for the order target;
generating a tree-structured learning model using the first to fourth information of the plurality of pieces of order data as independent variables and the amount information as a dependent variable;
An information processing method comprising: An information processing method by an information processing device,
A step of acquiring a learning model for a desired order target from a tree-structured learning model generated in advance for each of a plurality of order targets using a plurality of order data including, as independent variables, first information indicating a budget for the order target, second information indicating an actual cost for the order target, third information indicating a time when the order target was ordered, and fourth information indicating a delivery date for the order target, and, as a dependent variable, amount information indicating a relationship between the budget for the order target and the actual cost for the order target;
outputting an analysis result of the learning model for the desired order target;
An information processing method comprising:

Images