Purchase support device, purchase support method, and purchase support program

Abstract

To enable efficient purchase application.SOLUTION: A purchase support device 100 disclosed herein is configured to input a prompt based on a natural language text received from a user into a generative model provided with information regarding purchase application for articles in an organization so as to generate information regarding purchase application for an article indicated by the text. The purchase support device 100 outputs the information regarding the purchase application for the article indicated by the text to the user.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a purchasing assistance device, a purchasing assistance method, and a purchasing assistance program. [Background technology]

[0002] For business management and accounting purposes, certain procedures may be required when purchasing goods within an organization. For example, when an employee of an organization purchases goods for business use, the employee may be required to compile information about the goods, such as the name, purchase price, and details, as well as information about the purpose of the purchase and account code, as application information, and submit a purchase application according to a predetermined procedure for each organization.

[0003] When making the above-mentioned purchase application, there is known a technology that executes a series of processes, such as accepting application information and approving the purchase application. For example, as a conventional technology, there is known a workflow system that enables a series of operations to be carried out smoothly and quickly by allowing the applicant, the verifier, the approver, and the contractor to grasp in advance the progress status of work related to the application data (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-250611 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the conventional technology has the problem that it is difficult to efficiently process purchase applications. For example, the conventional technology allows approvers and contractors to grasp the progress status of work related to the application data in advance, allowing a series of tasks to be carried out smoothly and quickly. On the other hand, the conventional technology has the problem that applicants must create and input application data, which requires applicants to spend time on each purchase application. [Means for solving the problem]

[0006] Therefore, in order to solve the above-mentioned problems and achieve the objectives, the purchasing assistance device of the present invention is characterized by having a generation unit that inputs a prompt based on natural language text received from a user to a generation model provided with information regarding an application to purchase an item in an organization, and generates information regarding the application to purchase the item indicated in the text, and an output unit that outputs information regarding the application to purchase the item indicated in the text. [Effects of the Invention]

[0007] The present invention has the effect of enabling purchase applications to be made efficiently. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an overall process of the purchase assistance device according to this embodiment. [Figure 2] FIG. 2 is a diagram showing the configuration of the purchase assistance device according to the first embodiment. [Figure 3] FIG. 3 is a table diagram illustrating an example of employee information according to the first embodiment. [Figure 4] FIG. 4 is a table diagram illustrating an example of text information according to the first embodiment. [Figure 5] FIG. 5 is a table diagram illustrating an example of application regulation information according to the first embodiment. [Figure 6] FIG. 6 is a table diagram illustrating an example of purchase application information according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of the purchase assistance process according to the first embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of the purchase assistance process according to the first embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of the purchase assistance process according to the first embodiment. [Figure 10] FIG. 10 is a diagram showing a flowchart of the purchase assistance process according to the first embodiment. [Figure 11] FIG. 11 is a diagram showing a flowchart of the purchase assistance process according to the first embodiment. [Figure 12] FIG. 12 is a diagram showing a flowchart of the purchase assistance process according to the first embodiment. [Figure 13] FIG. 13 is a diagram showing the configuration of a purchase assistance device according to the second embodiment. [Figure 14] FIG. 14 is a table illustrating an example of an account code according to the second embodiment. [Figure 15] FIG. 15 is a diagram illustrating an example of a purchase assistance process according to the second embodiment. [Figure 16] FIG. 16 is a diagram illustrating an example of a purchase assistance process according to the second embodiment. [Figure 17] FIG. 17 is a diagram illustrating an example of a purchase assistance process according to the second embodiment. [Figure 18] FIG. 18 is a diagram showing a flowchart of the purchase assistance process according to the second embodiment. [Figure 19] FIG. 19 is a diagram showing a flowchart of the purchase assistance process according to the second embodiment. [Figure 20] FIG. 20 is a diagram showing a flowchart of the purchase assistance process according to the second embodiment. [Figure 21] FIG. 21 is a diagram illustrating tsuzumi. [Figure 22] FIG. 22 is a diagram illustrating tsuzumi. [Figure 23] FIG. 23 is a diagram illustrating tsuzumi. [Figure 24] FIG. 24 is a diagram illustrating IOWN. [Figure 25] FIG. 25 is a diagram illustrating an example of a computer that executes the purchase assistance process according to this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention (hereinafter referred to as "embodiments") will be described with reference to the drawings. Note that the embodiments are not limited to the following description.

[0010] <Overview> Fig. 1 is a diagram illustrating an overall view of the processing of a purchasing support device 100 according to this embodiment. The purchasing support device 100 shown in Fig. 1 is an example of a computer that provides technology to assist employees of a specific organization in processes such as creating application forms (application information) and identifying account codes when submitting purchase applications.

[0011] In the following sections, an "employee" is a person who belongs to a specific organization and performs tasks assigned to that organization. A "user" is an employee who uses the purchase support device 100 according to this embodiment, or an administrator who manages the purchase support device 100, in the above-mentioned specific organization.

[0012] (background) When purchasing business-related goods or services (hereinafter referred to simply as "purchasing"), specific application procedures established by each organization may be required for the purposes of business management and accounting control. In other words, users cannot, in principle, purchase goods or services on their own, but must make purchases based on specific procedures such as a purchase application, submission of a request for approval, and approval.

[0013] (Reference technologies and issues) Conventionally, the above-mentioned procedures for purchasing have been carried out by printing out application information on paper, requesting its circulation to a person with approval authority, and obtaining approval. However, because circulation using paper is inefficient, in recent years, reference technologies such as workflow systems have become known that allow applicants, verifiers, approvers, and contractors to grasp the progress of work related to the application data in advance, thereby enabling a series of tasks to be carried out smoothly and quickly.

[0014] However, the reference technology has issues with efficiently processing purchase applications. For example, the reference technology is a technology that enables smooth and rapid processing of applications and approvals by visualizing the progress of work related to application data to approvers and contractors. However, the reference technology has issues such as the applicant having to create and input application data to achieve this visualization, which creates a burden for the applicant every time they submit a purchase application.

[0015] (Processing by purchase assistance device 100) Therefore, in order to solve the above-mentioned problems related to purchase applications, the purchase assistance device 100 according to this embodiment generates information related to the application for the purchase of goods (hereinafter, sometimes referred to as "purchase application information") using natural language text related to the business input by the user (hereinafter, sometimes simply referred to as "text information").The purchase assistance device 100 then outputs the generated purchase application information to the user.

[0016] Returning to FIG. 1, the purchase assistance process performed by purchase assistance device 100 will now be described. First, purchase assistance device 100 accepts text information entered by the user. Next, purchase assistance device 100 converts the text information ((1) in FIG. 1). Specifically, purchase assistance device 100 converts the accepted text information into a prompt for input into a generative model ((1-1) and (1-2) in FIG. 1).

[0017] The purchasing assistance device 100 executes the process of generating purchasing requisition information ((2) in FIG. 1). Specifically, the purchasing assistance device 100 inputs the converted prompt ((2-1) in FIG. 1) into a predetermined generation model 10 ((2-2) in FIG. 1) that has been provided with the purchasing requisition information of the target organization as prior knowledge, and generates the purchasing requisition information ((2-3) in FIG. 1).

[0018] The purchase assistance device 100 outputs the purchase request information generated based on a predetermined generation model to the terminal device 200 operated by the user ((3) in FIG. 1). The terminal device 200 then displays the purchase request information, such as the purchase request form, approval information, and account code, output by the purchase assistance device 100 to the user ((3-1) in FIG. 1).

[0019] As described above, the purchase assistance device 100 according to this embodiment can output purchase request information generated using text information entered by a user who wishes to make a purchase. Therefore, the purchase assistance device 100 eliminates the need for the user to create the purchase request information used to make a purchase request, thereby enabling efficient purchase requests.

[0020] First Embodiment Next, a first embodiment realized by the purchase assistance device 100 according to the present embodiment will be described. As described above, in the conventional reference technology, when a user wishes to purchase an item, the user must input information related to the purchase request, making it difficult to make an efficient purchase.

[0021] Therefore, in the first embodiment, the purchase assistance device 100 (generation unit) inputs a prompt based on text information received from a user to a generation model provided with purchase application information in an organization, and generates purchase application information indicated in the text information. Then, the purchase assistance device 100 (output unit) outputs the purchase application information indicated in the text information.

[0022] (Purchasing aid device 100) Next, the configuration of the purchase support device 100 according to the first embodiment will be described. FIG. 2 is a diagram showing the configuration of the purchase support device 100 according to the first embodiment. As shown in FIG. 2, the purchase support device 100 has a communication unit 110, a memory unit 120, and a control unit 130. Although not shown in FIG. 2, the purchase support device 100 may also have an input unit such as a keyboard or mouse for accepting input such as operations by an administrator or the like. The purchase support device 100 may also have a display unit such as a display for displaying input text information, prompts set for the generative model, generated purchase request information, etc. to an administrator or the like.

[0023] (Communication unit 110) The communication unit 110 performs data communication related to the input of text information input via the terminal device 200 operated by the user. The communication unit 110 also performs data communication related to the output of generated purchase application information.

[0024] The communication unit 110 is realized by a NIC (Network Interface Card) or the like, and controls communication via an electric communication line such as a LAN (Local Area Network), the Internet, etc. The communication unit 110 is connected to the network by wire or wirelessly as necessary, and can transmit and receive information bidirectionally with the generative model 10, the terminal device 200, the server 300, etc.

[0025] (Storage unit 120) The storage unit 120 stores data and programs used for various processes by the control unit 130, as well as various data acquired by the operation of the control unit 130. The storage unit 120 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2, the storage unit 120 has an employee information DB 121, a text information DB 122, an application specification information DB 123, and a purchase application information DB 124.

[0026] (Employee Information DB121) Employee information DB121 is a database that stores employee information including identification information and attribute information of employees who belong to a predetermined organization. Specifically, employee information DB121 stores information such as employee identification information based on a combination of predetermined characters, numbers, symbols, etc. that identify employees, and organizational attribute information, which is attribute information of employees within the organization.

[0027] Here, a description will be given using a table diagram of an example of employee information stored in the employee information DB 121. Fig. 3 is a table diagram showing an example of employee information according to the first embodiment.

[0028] 3, employee information DB121 stores employee identification information and organization attribute information in association with "No.", which is information identifying individual employee information. For example, employee information DB121 stores employee identification information "A" and organization attribute information "B," which are identified by No. "1."

[0029] The above-mentioned employee identification information may include information for identifying an employee, such as the employee's name, nickname, handle name, identification number, identification symbol, identification character string, etc.

[0030] Organizational attribute information may include gender, seniority, department, position, job rank, career history, talent, skills, areas of expertise, qualifications, acquaintances, communication tendencies and preferences, communication data, personality, chat data, self-introduction data (self-promotion), career sheet, keywords, and other information used in offer matching.

[0031] (Text information DB122) The text information DB 122 is a database that stores text information, which is information on business-related conversations and utterances input by employees. An example of the text information stored in the text information DB 122 will now be described using a table. Fig. 4 is a table showing an example of text information according to the first embodiment.

[0032] 4, the text information DB 122 stores employee identification information and text in association with "No.", which is information that identifies individual text information. For example, the text information DB 122 stores employee identification information "A" and text "C," which are identified by No. "1."

[0033] The above-mentioned employee identification information "A" is information that identifies an employee, and is the same information as the employee identification information stored in employee information DB 121. That is, this means that the employee information stored in employee information DB 121 and the text information stored in text information DB 122 correspond to each other.

[0034] Text "C" is information about a dialogue or speech based on natural language input via the terminal device 200 operated by a user or employee. Specifically, the text includes business-related text such as text about purchasing, text about systems used in business, text about business schedules, text about business and sales activities, text about employee skills and evaluations, and text including general business-related conversations between employees.

[0035] (Application regulation information DB123) The application rule information DB123 is a database that stores application rule information, which is information related to the rules for purchasing each item predetermined within the organization. Specifically, the application rule information DB123 stores information such as the classification of items and services related to purchase, whether approval is required, whether automatic purchase is possible, etc.

[0036] Here, an example of the application specification information stored in the application specification information DB 123 will be described using a table diagram. Fig. 5 is a table diagram showing an example of the application specification information according to the first embodiment. As shown in Fig. 5, the application specification information DB 123 stores a classification, a purchase rule, whether approval is required, and whether automatic purchase is possible, in association with "No.", which is information that identifies individual application specification information.

[0037] The above-mentioned "classification" is information indicating the classification of the goods or services to be purchased, and includes, for example, classifications determined based on predetermined account items such as consumables and fixtures. Furthermore, "purchasing rules" are information regarding the procedures and rules for purchasing predetermined goods, including, for example, the information to be entered when making an application and the application route. Furthermore, "approval requirement" is information indicating whether a purchase approval request is required within the organization, which is determined for each classification of goods or services to be purchased. Furthermore, "automatic purchase availability" is information indicating whether the purchase can be performed automatically, which is determined for each classification of goods or services to be purchased.

[0038] For example, as shown in Fig. 5, the application regulation information DB 123 stores the classification "consumables," a purchasing rule "D," whether approval is required "not required," and whether automatic purchase is possible "(under 10,000 yen)," all of which are identified by No. "1." The above information means that for purchases classified as "consumables," the purchasing rule is "D," and in principle, approval is "not required," and automatic purchase is permitted for purchases "under 10,000 yen." For example, the purchasing rule "D" may include information such as "enter the item name, price, and supplier information and submit to your department's supervisor."

[0039] 5, the application regulation information DB 123 stores, for example, a classification "fixtures," a purchasing rule "E," whether approval is required "Yes," and whether automatic purchase is possible "No," all of which are identified by the number "2." The above information means that, for a purchase classified as "fixtures," the purchasing rule is "E," approval is required "Yes," and automatic purchase is prohibited regardless of price. For example, the purchasing rule "E" may include information such as, "Enter the item name, price, supplier information, and purpose of purchase, and submit to a supervisor in the management department."

[0040] (Purchase requisition information DB124) The purchase request information DB 124 is a database that stores purchase request information, which is information related to purchase requests for goods in an organization. Specifically, the purchase request information DB 124 stores information that identifies the goods or services that are the subject of the purchase request, information used to request the purchase of each item (hereinafter, sometimes simply referred to as "purchase information"), purchase history information, the presence or absence of approval information, the presence or absence of automatic purchase, etc.

[0041] Here, an example of purchase application information stored in the purchase application information DB 124 will be described with reference to a table diagram. Fig. 6 is a table diagram showing an example of purchase application information according to the first embodiment.

[0042] As shown in Figure 6, the purchase application information DB124 stores, in association with "No," which is information identifying individual purchase application information, purchase identification information, which is information identifying the goods or services to be purchased, purchase information, which is information used to apply for the purchase, information regarding the purchase history of the goods (purchase history), whether or not there is approval information, which is information indicating whether or not there is approval information, and whether or not there is automatic purchase, which is information indicating whether or not there is automatic purchase.

[0043] The above-mentioned purchase information includes, for example, the name of the purchase object (product name, etc.), price, URL (Uniform Resource Locator), purchase purpose, etc. The purchase history also includes the date and time when the purchase request was made, the contents of the purchase request, etc.

[0044] For example, as shown in Fig. 6, the purchase request information DB 124 stores purchase identification information "business card", purchase information "F", purchase history "G", whether approval information is available "no", and whether automatic purchase is available "yes", all identified by No. "1". The above information means that the purchase information for "business card" is "F", the purchase history is "G", an automatic purchase has been made (whether automatic purchase is available "yes"), and no approval request has been made (whether approval information is available "no").

[0045] The purchase information "F" identified by the above-mentioned No. "1" includes, for example, information about the business card supplier, price, specifications, account code, etc. Furthermore, the purchase history "G" identified by the above-mentioned No. "1" includes, for example, information about the date the business card purchase request was made, the date of purchase, and the contents of the actual purchased item.

[0046] 6, the purchase request information DB 124 stores purchase identification information "PC", purchase information "H", purchase history "I", whether approval information is available "Yes", and whether automatic purchase is available "No", all of which are identified by No. "2". The above information means that the purchase information for "PC" is "H", the purchase history is "I", automatic purchase has not been made (whether automatic purchase is available "No"), and an approval request has been made (whether approval information is available "Yes").

[0047] The purchasing information "H" identified by the above-mentioned No. "2" includes, for example, information about the computer's supplier, price, specifications, account code, etc. The purchasing history "I" identified by the above-mentioned No. "2" includes, for example, information about the date the computer purchase request was made, the date of purchase, and the contents of the actual purchased item.

[0048] (control unit 130) Now, returning to Figure 2, the explanation will continue. Control unit 130 has an internal memory for temporarily storing programs that define various processing procedures of purchase assistance device 100 and processing data, and is realized by electronic circuits such as a CPU (Central Processing Unit) or MPU (Micro Processing Unit), or integrated circuits such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array). As shown in Figure 2, control unit 130 has a reception unit 131, a generation unit 132, a storage unit 133, an output unit 134, and a purchase execution unit 135.

[0049] (Reception Department 131) The receiving unit 131 receives text information input by the user via the terminal device 200 via the communication unit 110 described above.

[0050] (Generation unit 132) The generation unit 132 provides predetermined prior knowledge, such as purchase request information including purchasing information and approval information for the target organization, to the generative model to be used. Then, the generation unit 132 inputs prompts based on text information received from the user to the generative model to which the predetermined prior knowledge has been provided, thereby generating purchase request information for the item to be purchased. Note that the provision of the above-mentioned prior knowledge may be achieved by prompt engineering, adapter tuning, or the like, which will be described later.

[0051] Specifically, the generation unit 132 inputs a prompt including an instruction to generate purchasing information for each item included in the text information to a generation model that has been provided with purchasing information for each item and application specification information, and generates purchasing information for each item shown in the text information.

[0052] For example, the generation unit 132 converts text information input by the user into a prompt. Next, the generation unit 132 inputs the prompt converted from information such as the "classification" of consumables, fixtures, etc. stored in the application specification information DB 123, and the "purchase rules" that define the rules for purchase applications in the target organization, into a generative model provided in advance. Then, the generation unit 132 generates purchase information related to the item indicated in the text information input by the user.

[0053] In addition, the generation unit 132 inputs a prompt including an instruction to generate purchasing information for each item included in the text information to a generation model provided with the purchasing history of items in the organization, and generates purchasing information for each item shown in the text information.

[0054] For example, the generation unit 132 converts text information input by the user into a prompt. Next, the generation unit 132 inputs a prompt obtained by converting information such as "classification" and "purchase rules" stored in the application specification information DB 123, as well as "purchase history" which is historical information on purchase applications for items stored in the purchase application information DB 124, into a pre-provided generation model. Then, the generation unit 132 generates purchase information to be used for making purchase suggestions to the user.

[0055] Furthermore, the generation unit 132 determines whether or not approval information required at the time of applying for the purchase of an item is to be generated. If it is determined that approval information is to be generated, the generation unit 132 inputs a prompt including an instruction to generate approval information required at the time of applying for the purchase of an item included in the text information to a generation model to which the approval information in the target organization has been provided, and generates approval information related to the item indicated in the text information.

[0056] For example, the generation unit 132 determines whether or not it is necessary to generate approval information for an "item" included in the purchase requisition information generated by the above-described process, based on the "classification," "approval information," etc. stored in the application specification information DB 123. As a specific example, the generation unit 132 determines that "approval information is not necessary" when the item included in the purchase requisition information is a "consumable item," and determines that "approval information is necessary" when the item included in the purchase requisition information is a "fixture."

[0057] Next, the generation unit 132 inputs a prompt that converts information such as "approval information" stored in the application specification information DB 123 into a pre-provided generation model, and generates approval information related to the item to be purchased.

[0058] The generation unit 132 can automatically generate purchasing requisition information using text information input on a daily basis by employees, etc. Specifically, the generation unit 132 converts text information related to employees' daily conversations and work into a prompt containing an instruction to generate purchasing requisition information. Next, the generation unit 132 inputs the converted prompt into a generative model to which the purchasing requisition information has been provided, thereby generating purchasing requisition information. The generated purchasing requisition information is then stored in the memory unit 120 by the storage unit 133, which will be described later.

[0059] The generation unit 132 can use at least one of a large-scale language model having general-purpose knowledge and tsuzumi as a generative model. Furthermore, the generation unit 132 can use a generative model that communicates via a communication network related to IOWN (Innovative Optical and Wireless Network). Details of tsuzumi and IOWN will be explained later in the section on modified examples.

[0060] (storage section 133) The storage unit 133 stores the generated purchase application information in the memory unit 120. Specifically, the storage unit 133 stores the purchase application information, including the purchase information and approval information, generated by the generation unit 132, in the purchase application information DB 124. An example of the storage process by the storage unit 133 will be described in detail in the sections describing the first and second examples below.

[0061] (output unit 134) The output unit 134 outputs purchase application information for the product indicated in the text information to the user. An example of the output process by the output unit 134 will be described in detail in the sections describing the first and second examples below.

[0062] In addition, the output unit 134 can output purchase information for each item indicated in the text information generated based on the purchase history information as suggested information to the user. For example, the output unit 134 can use the purchase information generated based on the purchase history stored in the purchase request information DB 124 to output suggested information for suggesting to the user the purchase of consumables such as business cards, stationery, and water from a water dispenser.

[0063] (Purchasing Execution Department 135) The purchase execution unit 135 executes a purchase process for the product or the like to be purchased based on the purchase request information generated by the generation unit 132. Specifically, the purchase execution unit 135 executes the purchase of the product when at least one of the price and type of the product satisfies a predetermined condition.

[0064] For example, the purchase execution unit 135 can execute the purchase of a target item when the price of the item satisfies the condition of a reference price included in the "automatic purchase availability" stored in the application specification information DB 123. Furthermore, the purchase execution unit 135 can execute the purchase of a target item when the classification (type) of the item matches the "classification" stored in the application specification information DB 123. Furthermore, the purchase execution unit 135 can execute a purchase request for an item even when a purchase instruction from a user is received.

[0065] (Generative Model 10) Generative model 10 is a generative model such as a large-scale language model, and generates output information in response to input generation instructions in natural language. Specifically, generative model 10 generates purchase requisition information in response to text information input by purchase assistance device 100, based on a large-scale language model or the like in which a prompt is set to generate purchase requisition information.

[0066] The generative model 10 according to this embodiment may be realized by an information processing device such as a server. The generative model 10 can generate an answer in response to a prompt based on prior knowledge that has been provided, input, learned, added, etc.

[0067] (Terminal device 200) Terminal device 200 is an information processing terminal device operated by a user. Specifically, terminal device 200 receives text information from a user, transmits the received text information to purchase assistance device 100, and receives and displays purchase application information and the like from purchase assistance device 100.

[0068] The type of the terminal device 200 is not particularly limited, and may be, for example, a smartphone, a tablet, a PDA (Personal Digital Assistant), a PC (Personal Computer), a notebook PC, or the like.

[0069] (Server 300) Server 300 is an information processing device that executes purchasing processes for goods and the like in a specific organization. Specifically, server 300 executes the purchase of goods and the like based on a purchase execution instruction received from purchase assistance device 100. Note that the type of server 300 referred to here is not particularly limited, and may be, for example, an on-premise information processing device, a cloud server, or the like.

[0070] (Example of processing) An example of the purchase support process by the purchase support device 100 according to the first embodiment will now be described with reference to Fig. 7 to Fig. 9. Fig. 7 to Fig. 9 are diagrams showing an example of the purchase support process according to the first embodiment.

[0071] Note that Fig. 7 shows an example of "purchase information generation processing and purchase execution processing" as a first example. Fig. 8 shows an example of "purchase information and approval information generation processing" as a second example. Fig. 9 shows an example of "purchase request information generation processing and storage processing" as a third example.

[0072] (First example) The first example of "purchase information generation processing and purchase execution processing" will be described with reference to FIG. 7. The first example is an example of generating purchase information to be used in a purchase request for an item by inputting a prompt based on text information entered by a user into a generative model provided with prior knowledge. The first example is also an example of processing in which, if the item to be purchased satisfies predetermined conditions, the generated purchase information is used to automatically execute the purchase of the item.

[0073] Figure 7 shows a purchase assistance device 100 that generates purchase information, a terminal device 200 operated by a user who wishes to make a purchase, a generation model 10a used by the purchase assistance device 100, and a server 300 that has the functionality to make the purchase.

[0074] First, terminal device 200 receives text information from the user, such as "I don't have enough business cards, so I need to buy some soon." Then, terminal device 200 transmits the text information received from the user to purchase assistance device 100 ((1-1) in FIG. 7).

[0075] The purchase assistance device 100 converts the text information ((1-1) in FIG. 7) received from the terminal device 200 into a prompt ((1-2) in FIG. 7). For example, the purchase assistance device 100 converts text information such as "I don't have enough business cards, so I need to buy some soon" into a prompt to be input to a generation model, such as "Please generate purchasing information to be used to purchase user XX's business card."

[0076] The purchase assistance device 100 executes the process of generating purchasing information ((2) in FIG. 7). Specifically, the purchase assistance device 100 inputs the converted prompt to the generation model 10a, which has been provided with prior knowledge for generating purchasing request information ((2-1) in FIG. 7), and generates "purchase information" as purchasing request information ((2-2) in FIG. 7).

[0077] If the purchase price of the product or service included in the purchase information is higher than a preset reference price (Yes in (3) of FIG. 7), the purchase assistance device 100 executes a process to output the purchase information to the user ((4) of FIG. 7). The purchase assistance device 100 then transmits the purchase information to be used in applying for the purchase, including information such as the name, price, URL, and purpose of the product, to the terminal device 200 operated by the user. The terminal device 200 then displays the received purchase information to the user ((4-1) of FIG. 7).

[0078] On the other hand, if the purchase price of the goods or services included in the purchase information is lower than the preset reference price (No in (3) of Figure 7), the purchase assistance device 100 executes the purchase process based on the purchase information ((5) of Figure 7).

[0079] For example, the purchase assistance device 100 uses purchase information including "information such as the name, price, URL, and purpose of purchase of the item to be purchased" to send an instruction to the server 300 that manages purchase processing within the organization to execute the purchase. Then, upon receiving the instruction, the server 300 executes the purchase processing ((6) in FIG. 7).

[0080] As described above, purchase assistance device 100 can automatically generate purchase request information corresponding to the item to be purchased from text information entered by the user. Furthermore, purchase assistance device 100 can automatically execute the purchase process for the item desired by the user using the generated purchase request information. As a result, purchase assistance device 100 can reduce the amount of work required for the user to submit a purchase request.

[0081] (Second example) The second example, "Purchase information and approval request information generation processing," will be explained using Fig. 8. The second example is an example of processing for generating purchase information to be used in a purchase application for an item based on text information input by a user, similar to the first example, and also generating approval request information when the request for purchase of the target item requires such information.

[0082] Figure 8 shows a purchasing assistance device 100 that generates purchasing information and approval information, a terminal device 200 operated by a user who wishes to make a purchase, and generation models 10a and 10b used by the purchasing assistance device 100.

[0083] First, terminal device 200 receives text information from the user, such as "My PC is about to break down, so I need to buy something." Then, terminal device 200 transmits the received text information to purchase assistance device 100 ((1-1) in FIG. 8).

[0084] The purchase assistance device 100 converts the text information ((1-1) in FIG. 8) received from the terminal device 200 into a prompt ((1-2) in FIG. 8). For example, the purchase assistance device 100 converts text information such as "My computer is about to break down, so I need to buy one" into a prompt to be input into a generation model, such as "Please generate purchase request information to be used to purchase a computer for user XX."

[0085] Next, the purchase assistance device 100 generates purchase information in the same manner as in the first example ((2) in FIG. 8). Here, if the organization's regulations do not stipulate that a request for approval be submitted for the goods or services included in the purchase information (No in (3) in FIG. 8), the purchase assistance device 100 executes a process to output the purchase information to the user ((4) in FIG. 8). Next, the purchase assistance device 100 transmits the purchase information, including information such as the name, price, URL, and purpose of the purchase item, to the terminal device 200 operated by the user. The terminal device 200 then displays the received purchase information to the user ((4-1) in FIG. 8).

[0086] On the other hand, if the organization's regulations stipulate that a request for approval be submitted for the goods or services included in the purchasing information (Yes in (3) of FIG. 8), the purchasing support device 100 executes a process to generate the approval information based on the purchasing information ((5) of FIG. 8). Specifically, the purchasing support device 100 inputs the generated purchasing information into the generative model 10b, which has been provided with prior knowledge for generating the approval information ((5-1) of FIG. 8), and generates "approval information" as purchasing application information ((5-2) of FIG. 8).

[0087] The purchase assistance device 100 then executes a process to output the purchase information and approval information to the user ((6) in FIG. 8). The purchase assistance device 100 transmits the purchase information, such as the name, price, URL, and purpose of the purchase item, and the purchase request information, including the generated approval information, to the terminal device 200 operated by the user. The terminal device 200 then displays the received purchase information to the user ((6-1) in FIG. 8).

[0088] As described above, purchase assistance device 100 can automatically generate purchase information and approval information corresponding to the item to be purchased from text information entered by the user. Therefore, purchase assistance device 100 can reduce the amount of work required for the user to submit a purchase application, even when approval information is required when submitting a purchase application for an item.

[0089] (Third example) As a third example, a "processing for generating and storing purchase request information" will be described with reference to Fig. 9. The third example is an example of a process for generating purchase request information to be used for a purchase request for an item based on text information input by a user, as in the first example, and storing the information in storage unit 120, even when no instructions are given by the user or the like.

[0090] FIG. 9 shows a purchase assistance device 100 that generates purchase request information, a terminal device 200 operated by an employee, and a generation model 10 used by the purchase assistance device 100.

[0091] First, terminal device 200 receives text information such as "I'm running low on business cards, so I need to buy some soon," or "My computer is about to break down, so I need to buy some," as a business conversation between an employee. Terminal device 200 then transmits the text information received from the user to purchase assistance device 100 ((1-1) in FIG. 9).

[0092] As in the first example, purchase assistance device 100 converts the text information ((1-1) in FIG. 9) received from terminal device 200 into a prompt ((1-2) in FIG. 9). Next, purchase assistance device 100 generates purchase application information ((2) in FIG. 9) as in the first example.

[0093] The purchase assistance device 100 stores the generated purchase request information in the purchase request information DB 124 ((3) in FIG. 9). Specifically, the purchase assistance device 100 associates the purchase identification information "business card" ((3-1) in FIG. 9), purchase information "F" ((3-2) in FIG. 9), purchase history "G" ((3-3) in FIG. 9), the presence or absence of approval information "no" ((3-4) in FIG. 9), and the presence or absence of automatic purchase "yes" ((3-5) in FIG. 9) in the purchase request information DB 124. In addition, the purchase assistance device 100 associates the purchase identification information "PC" ((3-6) in Figure 9), purchase information "H" ((3-7) in Figure 9), purchase history "I" ((3-8) in Figure 9), whether or not there is approval information "Yes" ((3-9) in Figure 9), and whether or not there is automatic purchase "No" ((3-10) in Figure 9) and stores them in the purchase request information DB 124.

[0094] As described above, purchase assistance device 100 can automatically generate purchase request information for items included in text information entered by a user, even without user instructions, etc. Purchase assistance device 100 can then accumulate the automatically generated purchase request information to improve the generation of purchase request information and recommend items for purchase to users.

[0095] (Procedure for purchasing assistance processing) Next, the procedure of the purchase assistance process implemented by the purchase assistance device 100 according to the first embodiment will be described with reference to Figures 10 to 12. Figures 10 to 12 are diagrams showing flowcharts of the purchase assistance process according to the first embodiment.

[0096] Fig. 10 shows an example of the processing procedure for "purchase information generation processing and purchase execution processing." Fig. 11 shows an example of the processing procedure for "purchase information and approval information generation processing." Fig. 12 shows an example of the processing procedure for "purchase request information generation processing and storage processing."

[0097] First, an example of the processing procedure for the "purchase information generation processing and purchase execution processing" will be described using Figure 10. The generation unit 132 provides prior knowledge to the generative model (S101). Specifically, the generation unit 132 inputs purchase application information such as "classification" and "purchase information" stored in the application specification information DB 123 and a prompt including an instruction to store the purchase application information to the generative model to be used. Through the above-mentioned processing, the generation unit 132 causes the generative model to generate purchase application information for the target organization.

[0098] If the user does not issue an instruction to start the generation process, the purchase assistance device 100 waits for the process (No in S102). On the other hand, if the user issues an instruction to start the generation process (Yes in S102), the purchase assistance device 100 starts the process in S103.

[0099] The receiving unit 131 receives text information from a user (S103). Next, the generating unit 132 converts the text information into a prompt (S104). Next, the generating unit 132 inputs the converted prompt into a generation model to generate purchase request information (S105).

[0100] If the purchase price included in the generated purchase request information is higher than the reference price (Yes in S106), the output unit 134 outputs the generated purchase request information to the user (S107). Then, the purchase assistance device 100 ends the process.

[0101] On the other hand, if the purchase price included in the generated purchase request information is lower than the reference price (No in S106), the purchase execution unit 135 executes the purchase process based on the purchase request information (S108).Then, the purchase assistance device 100 ends the process.

[0102] Next, an example of a processing procedure for "generating purchasing information and approval information" will be described using Figure 11. The generation unit 132 provides prior knowledge to the generative model (S201). Specifically, the generation unit 132 inputs purchasing application information such as "classification," "purchase information," and "approval information" stored in the application specification information DB 123, and a prompt including an instruction to store the purchasing application information, to the generative model to be used. Through the above-described processing, the generation unit 132 causes the generative model to generate purchasing application information for the target organization.

[0103] If the user does not issue an instruction to start the generation process, the purchase assistance device 100 waits for the process (No in S202). On the other hand, if the user issues an instruction to start the generation process (Yes in S202), the purchase assistance device 100 starts the process in S203.

[0104] The receiving unit 131 receives text information from a user (S203). Next, the generating unit 132 converts the text information into a prompt (S204). Next, the generating unit 132 inputs the converted prompt into a generation model to generate purchase information (S205).

[0105] If a purchase item included in the generated purchasing information requires a request for approval (Yes in S206), the generation unit 132 converts the text information into a prompt including an instruction to generate the request for approval (S207). The generation unit 132 then inputs the converted prompt into a generation model to generate the request for approval (S208). The output unit 134 then outputs the generated purchase request information and request for approval information to the user (S209). The purchase assistance device 100 then terminates the process.

[0106] On the other hand, if the purchase object included in the generated purchase request information does not require approval (No in S206), the output unit 134 outputs the generated purchase information to the user (S210). Then, the purchase assistance device 100 ends the process.

[0107] Next, an example of the processing procedure for the "processing for generating and storing purchase requisition information" will be described with reference to FIG. 12. As in the processing described with reference to FIG. 10, the generation unit 132 provides prior knowledge to the generative model (S301). Next, the reception unit 131 receives text information from an employee (S302). Next, the generation unit 132 converts the text information into a prompt (S303). Next, the generation unit 132 inputs the converted prompt into the generative model to generate purchase requisition information (S304).

[0108] The storage unit 133 stores the generated purchase application information in the purchase application information DB 124 (memory unit 120) (S305). Then, the purchase assistance device 100 ends the process.

[0109] (effect) Next, we will explain the effects of the purchasing assistance device 100 according to this embodiment. Conventionally, techniques such as workflow visualization have been proposed to improve the efficiency of purchasing application procedures within an organization. However, in order to realize such visualization, applicants must create and input application data, which results in a burden on applicants each time they submit a purchase application.

[0110] Therefore, generation unit 132 of purchase assistance device 100 inputs a prompt based on the text information received from the user to the generation model provided with the organization's purchase application information, and generates the purchase application information indicated in the text information. Then, output unit 134 of purchase assistance device 100 outputs the purchase application information indicated in the text information.

[0111] Through the above-described processing, the purchase assistance device 100 according to the first embodiment can automatically generate purchase request information to be used for submitting a purchase request, using purchase-related text information contained in text information of business-related exchanges between the user and other employees during work, etc. As a result, the purchase assistance device 100 according to the first embodiment can automatically generate purchase request information that was previously created manually by the user, thereby enabling efficient submission of purchase requests.

[0112] Furthermore, the purchase support device 100 according to the first embodiment performs the processes described below to achieve the respective predetermined effects.

[0113] The generation unit 132 inputs a prompt including an instruction to generate purchasing information for each item included in the text information to a generation model that has been provided with purchasing information for each item and application specification information, and generates purchasing information for each item shown in the text information.

[0114] Through the above-described process, purchase assistance device 100 can automatically generate purchase information based on text information, such as speech, entered by the user, instead of the purchase information that users previously created manually. Therefore, purchase assistance device 100 eliminates the need for users to manually create purchase information, thereby improving the efficiency of tasks such as applying for the purchase of goods.

[0115] The generation unit 132 inputs a prompt including an instruction to generate purchasing information for each item included in the text information to the generation model provided with the purchasing history of items in the organization, and generates purchasing information for each item included in the text information. The output unit 134 then outputs the purchasing information for each item included in the text information generated based on the purchasing history information as suggested information to the user.

[0116] Through the above process, purchase assistance device 100 can automatically generate purchase information for items that a user is considering or hoping to purchase, based on text information such as utterances input by the user and past purchase history. Therefore, purchase assistance device 100 has the effect of eliminating the need for users to manually create purchase information, thereby making it possible to streamline tasks such as applying for the purchase of items by users.

[0117] The generation unit 132 determines whether or not approval information required at the time of applying for a purchase of an item is to be generated. If it is determined that approval information is to be generated, the generation unit 132 inputs a prompt including an instruction to generate approval information required at the time of applying for a purchase of an item included in the text information to a generation model to which the approval information in the target organization has been provided, and generates approval information related to the item indicated in the text information.

[0118] Through the above-described process, purchase assistance device 100 can automatically generate approval request information, which conventionally has been created manually by users, based on text information such as speech input by the user. Therefore, purchase assistance device 100 has the effect of eliminating the need for users to manually create approval request information, thereby making it possible to streamline tasks such as applying for the purchase of goods.

[0119] The generation unit 132 converts natural language text information related to the employee's work into a prompt including an instruction to generate purchase requisition information. Next, the generation unit 132 inputs the converted prompt into the generation model to which the purchase requisition information was provided, thereby generating the purchase requisition information. The storage unit 133 then stores the generated purchase requisition information in the memory unit 120.

[0120] Through the above-described process, purchase assistance device 100 can generate purchase request information using text information related to employee conversations and store it in storage unit 120, even when there is no instruction from a user to perform the generation process. In other words, purchase assistance device 100 can automatically generate and store purchase request information related to items included in daily business conversations. As a result, purchase assistance device 100 can use the stored purchase request information to improve the accuracy of the generation process of purchase request information instructed by the user and to make product purchase proposals to users, thereby achieving the effect of making it possible to streamline tasks such as applying for the purchase of items.

[0121] The purchase execution unit 135 executes the purchase of an item when at least one of the price and type of the item meets a predetermined condition. Through the above-described process, the purchase assistance device 100 can automatically execute the purchase of items that meet the conditions without the user having to submit a purchase application. Therefore, even if an organization's regulations require a purchase application, the purchase assistance device 100 achieves the effect of streamlining the process of purchasing items by eliminating the need for the user to create application information and execute a purchase when submitting a purchase application for daily necessities, etc.

[0122] <Second embodiment> Next, we will explain the second embodiment realized by the purchase assistance device 100 according to this embodiment. As explained in the first embodiment, in the past, when a user purchased an item, the user had to input information related to the purchase request themselves. Here, the information related to the purchase request may include, for example, an "account code" for each item to be purchased.

[0123] The above-mentioned account codes are codes assigned to account items that make up financial statements, and are information used by organizations and the like when performing accounting procedures and business management. In other words, since account codes are information assigned to each item to be purchased, when, for example, purchasing a new item, it may be necessary to submit an application that associates the code with information about the item to be purchased. However, users who are not knowledgeable may find it difficult to associate the item to be purchased with the account code.

[0124] Therefore, the second embodiment is an embodiment that aims to solve the above-mentioned problems regarding account codes. Specifically, a purchase assistance device 100 (generation unit) according to the second embodiment inputs a prompt based on text information in a natural language received from a user to a generation model provided with an account code related to a request to purchase an item in an organization, and generates an account code related to the request to purchase the item indicated in the text information. Then, the purchase assistance device 100 (output unit) outputs the account code related to the request to purchase the item indicated in the text information to the user.

[0125] (Purchasing aid device 100) Next, the configuration of the purchase support device 100 according to the second embodiment will be described. FIG. 13 is a diagram showing the configuration of the purchase support device 100 according to the second embodiment. As shown in FIG. 13, the purchase support device 100 has a communication unit 110, a storage unit 120, and a control unit 130. The purchase support device 100 according to the second embodiment may have the same functions and configuration as the purchase support device 100 according to the first embodiment. In the following sections, explanations of parts of the functions and configuration common to the first and second embodiments will be omitted.

[0126] (Storage unit 120) As shown in FIG. 13, the storage unit 120 according to the second embodiment includes an employee information DB 121, a text information DB 122, an application specification information DB 123, a purchase application information DB 124, and an account code DB 125.

[0127] (Account code DB125) The account code DB 125 is a database that stores information (account codes) related to account codes for identifying account items that make up financial statements. An example of an account code stored in the account code DB 125 will now be described using a table diagram. Fig. 14 is a table diagram showing an example of an account code according to the second embodiment.

[0128] As shown in FIG. 14, the account code DB 125 stores "No.", which is information for identifying an individual account code, a purchase target, which is information for identifying the item, etc. to be purchased, and an account code associated with the item, etc. to be purchased.

[0129] For example, the account code DB 125 stores a purchase object "business card" identified by No. "1" and an account code "J." The account code DB 125 also stores a purchase object "personal computer" identified by No. "2" and an account code "K." The above information means that the account code for "business card" is "J" and the account code for "personal computer" is "K." Note that in FIG. 14, the account code for "business card" is represented as "J" and the account code for "personal computer" is represented as "K," but the information may be represented by a predetermined combination of text, symbols, numbers, etc.

[0130] (control unit 130) Here, the explanation will be continued by returning to Fig. 13. As shown in Fig. 13, the control unit 130 according to the second embodiment includes a receiving unit 131, a generating unit 132, a storage unit 133, an output unit 134, a purchase execution unit 135, and a question creation unit 136.

[0131] (Reception Department 131) The receiving unit 131 receives text information or question creation instructions input by the user via the terminal device 200 via the communication unit 110 described above.

[0132] (Generation unit 132) The generation unit 132 provides predetermined prior knowledge, such as purchase requisition information including account codes in the target organization, to the generative model to be used. Then, the generation unit 132 inputs a prompt based on text information received from the user to the generative model to which the predetermined prior knowledge has been provided, and generates an account code for the item to be purchased.

[0133] Specifically, the generation unit 132 inputs a prompt including an instruction to generate an account code to be used for a purchase request for each item to a generation model that has been provided with information regarding the account code to be used for a purchase request for each item, and generates an account code to be used for a purchase request for each item indicated in the text information.

[0134] For example, the generation unit 132 inputs a prompt including an instruction to generate an account code to be used for applying for a purchase of each item to a generation model that has been provided with at least one of the correspondence information between a pre-set account code and an item, and generates an account code to be used for applying for a purchase of each item indicated in the text information.

[0135] As an example, the generation unit 132 converts text information input by the user into a prompt. Next, the generation unit 132 inputs the prompt, which is obtained by converting information such as "purchased item" and "account code" stored in the account code DB 125, into a pre-provided generation model, and generates an account code related to the item indicated in the text information input by the user.

[0136] The generation unit 132 can also automatically generate an account code to be used in a purchase request using text information input by an employee or the like. Specifically, the generation unit 132 converts text information related to the employee's daily conversations or work into a prompt that includes an instruction to generate an account code to be used in a purchase request for each item. Next, the generation unit 132 inputs the converted prompt into a generative model that has been provided with the account code to be used in a purchase request for each item, thereby generating an account code. The generated account code is then stored in the memory unit 120 by the storage unit 133, which will be described later.

[0137] (storage section 133) The storage unit 133 stores the generated account code in the memory unit 120. Specifically, the storage unit 133 stores the account code generated by the generation unit 132 in the account code DB 125. For example, when an account code "J" related to a "business card" is generated by a user, the storage unit 133 associates the "business card" with "J" and stores them in the account code DB 125.

[0138] (Purchasing Execution Department 135) When the purchase execution unit 135 receives a question creation instruction and if at least one of the price and type of the item satisfies a predetermined condition, the purchase execution unit 135 executes the purchase of the item using the generated account code (purchase request information). Note that the processing of the purchase execution unit 135 according to the second embodiment is the same as that of the first embodiment, and therefore a detailed description thereof will be omitted.

[0139] (Question Creation Section 136) The question creation unit 136 creates association information between information identifying an item and an account code. Then, the question creation unit 136 creates a question from the created association information in which at least one of the information identifying an item and the account code has been deleted. Note that the question creation process by the question creation unit 136 will be explained in the section on an example of processing below.

[0140] (Generative Model 10) The generative model 10 according to the second embodiment generates an account code as purchase requisition information in accordance with text information input by the purchase assistance device 100, based on a generative model to which purchase requisition information for generating an account code is provided. Note that the generative model 10 according to the second embodiment may be a generative model in which purchase requisition information for generating an account code is further provided to the generative model 10 according to the first embodiment.

[0141] (Example of processing) An example of the purchase support process by the purchase support device 100 according to the second embodiment will now be described with reference to Fig. 15 to Fig. 17. Fig. 15 to Fig. 17 are diagrams showing an example of the purchase support process according to the second embodiment.

[0142] FIG. 15 shows an example of "account code generation processing" as a fourth example. FIG. 16 shows an example of "account code question creation processing" as a fifth example. FIG. 17 shows an example of "account code generation processing and storage processing" as a sixth example.

[0143] (Example 4) The fourth example, "account code generation processing," will now be described. Fig. 15 shows purchase assistance device 100 that generates an account code, terminal device 200 operated by a user who wishes to generate an account code, and generation model 10c used by purchase assistance device 100.

[0144] First, terminal device 200 receives text information from the user, such as "I would like to purchase a business card, so please tell me your account code." Then, terminal device 200 transmits the text information received from the user to purchase assistance device 100 ((1-1) in FIG. 15).

[0145] The purchasing assistance device 100 converts the text information ((1-1) in FIG. 15) received from the terminal device 200 into a prompt ((1-2) in FIG. 15). For example, the purchasing assistance device 100 converts text information such as "I would like to purchase a business card, so please tell me your account code" into a prompt to be input to a generation model, such as "Please generate an account code to be used to purchase user XX's business card."

[0146] The purchasing assistance device 100 executes the process of generating an account code ((2) in FIG. 15). Specifically, the purchasing assistance device 100 inputs the converted prompt to the generation model 10c, which has been provided with prior knowledge for generating an account code ((2-1) in FIG. 15), and generates an "account code" as purchase request information ((2-2) in FIG. 15).

[0147] The purchase assistance device 100 transmits (outputs) the generated account code to the terminal device 200 operated by the user ((3) in FIG. 15). The terminal device 200 then displays the received account code to the user ((3-1) in FIG. 15).

[0148] As described above, purchase assistance device 100 can automatically generate an account code corresponding to the item to be purchased from the text information entered by the user. Therefore, purchase assistance device 100 can reduce the amount of work required for the user to submit a purchase request.

[0149] (Fifth Example) The fifth example, "Question Creation Process for Account Codes," will now be described. Fig. 16 shows purchase assistance device 100, which generates account codes and creates questions related to account codes, terminal device 200 operated by a user, and generation model 10c used by purchase assistance device 100.

[0150] First, terminal device 200 receives text information from the user, including an instruction to generate a question about an account code, such as "Please create a question about the account code used to purchase a business card." Then, terminal device 200 transmits the text information received from the user to purchase assistance device 100 ((1-1) in FIG. 16).

[0151] The purchasing assistance device 100 converts the text information ((1-1) in FIG. 16) received from the terminal device 200 into a prompt ((1-2) in FIG. 16). For example, the purchasing assistance device 100 converts text information such as "Please create a question about the account code to be used to purchase business cards" into a prompt to be input to a generation model such as "Please generate an account code to be used to purchase business cards."

[0152] The purchasing support device 100 executes the process of generating an account code in the same manner as in the fourth example ((2) in FIG. 16). Next, the purchasing support device 100 creates a question related to the generated account code ((3) in FIG. 16). For example, the purchasing support device 100 creates an account code question in which the item and the corresponding account code are left blank.

[0153] The purchase assistance device 100 transmits the created question about the account code to the terminal device 200 operated by the user ((4) in FIG. 16). Then, the terminal device 200 displays the accepted question about the account code (account code question) to the user ((4-1) in FIG. 16).

[0154] As described above, purchase assistance device 100 can automatically generate questions about the account code corresponding to the item to be purchased from text information entered by the user. Therefore, purchase assistance device 100 can effectively enhance the user's understanding of account codes by presenting the created questions to the user and having the user solve the questions.

[0155] (Example 6) Next, the sixth example of "account code generation processing and storage processing" will be described with reference to Fig. 17. The sixth example is an example of processing in which, similar to the fourth example, an account code to be used in a purchase application for an item is generated based on text information input by the user, and stored in the storage unit 120, even when no instructions are given by the user or the like.

[0156] FIG. 17 shows a purchase assistance device 100 that generates an account code, a terminal device 200 operated by an employee, and a generative model 10 used by the purchase assistance device 100.

[0157] First, terminal device 200 receives text information such as "I'm running low on business cards, so I need to buy some soon," or "My computer is about to break down, so I need to buy some," as a business conversation between an employee. Terminal device 200 then transmits the text information received from the user to purchase assistance device 100 ((1-1) in FIG. 17).

[0158] As in the fourth example, purchase assistance device 100 converts the text information ((1-1) in FIG. 17) received from terminal device 200 into a prompt ((1-2) in FIG. 17). Next, purchase assistance device 100 generates an account code ((2) in FIG. 17) as in the fourth example.

[0159] The purchase assistance device 100 stores the generated account code in the account code DB 125 ((3) in FIG. 17). Specifically, the purchase assistance device 100 associates the purchase object "business card" ((3-1) in FIG. 17) with the account code "J" ((3-2) in FIG. 17) and stores them in the account code DB 125. The purchase assistance device 100 also associates the purchase object "computer" ((3-3) in FIG. 17) with the account code "K" ((3-4) in FIG. 17) and stores them in the account code DB 125.

[0160] As described above, the purchase assistance device 100 can automatically generate account codes for items included in text information entered by employees, even without user instructions, etc. The purchase assistance device 100 can then store the automatically generated account codes to improve the accuracy of generating account codes and present them together with product purchase recommendations to the user.

[0161] (Procedure for purchasing assistance processing) Next, the procedure of the purchase assistance process implemented by the purchase assistance device 100 according to the second embodiment will be described with reference to Figures 18 to 20. Figures 18 to 20 are diagrams showing flowcharts of the purchase assistance process according to the second embodiment.

[0162] Fig. 18 shows an example of the procedure for "account code generation processing", Fig. 19 shows an example of the procedure for "account code question creation processing", and Fig. 20 shows an example of the processing procedure for "account code generation processing and storage processing".

[0163] First, an example of the procedure for the "account code generation process" will be described using Figure 18. The generation unit 132 provides prior knowledge to the generative model (S401). Specifically, the generation unit 132 inputs account codes such as "purchase object" and "account code" stored in the account code DB 125 and a prompt including an instruction to store the account code to the generative model to be used. Through the above-mentioned process, the generation unit 132 causes the generative model to generate an account code for the target organization.

[0164] If the user does not issue an instruction to start the generation process, the purchase assistance device 100 waits for the process (No in S402). On the other hand, if the user issues an instruction to start the generation process (Yes in S402), the purchase assistance device 100 starts the process in S403.

[0165] The receiving unit 131 receives text information from the user (S403). Next, the generating unit 132 converts the text information into a prompt (S404). Next, the generating unit 132 inputs the converted prompt into a generation model to generate an account code (S405). Next, the output unit 134 outputs the generated account code to the user (S406). Then, the purchasing assistance device 100 ends the process.

[0166] Next, an example of the processing procedure for the "question creation process for account codes" will be described with reference to FIG. 19. The generation unit 132 provides prior knowledge to the generative model (S501). Specifically, the generation unit 132 inputs account codes such as "purchase object" and "account code" stored in the account code DB 125 and a prompt including an instruction to store the account code to the generative model to be used. Through the above-described processing, the generation unit 132 causes the generative model to generate account codes for the target organization.

[0167] If the user does not issue an instruction to start the generation process, the purchase assistance device 100 waits for the process (No in S502). On the other hand, if the user issues an instruction to start the generation process (Yes in S502), the purchase assistance device 100 starts the process in S503.

[0168] The accepting unit 131 accepts text information from a user (S503). Next, the accepting unit 131 converts the text information into a prompt (S504). Next, the generating unit 132 inputs the converted prompt into a generative model and generates an account code (S505).

[0169] The question creation unit 136 creates a question for the generated account code (S506). Next, the output unit 134 outputs the question for the generated account code to the user (S507). Then, the purchase assistance device 100 ends the process.

[0170] Next, an example of the processing procedure for the "account code generation processing and storage processing" will be described with reference to Figure 20. Similar to the processing described with reference to Figure 18, the generation unit 132 provides prior knowledge to the generative model (S601). Next, the reception unit 131 receives text information from an employee (S602). Next, the generation unit 132 converts the text information into a prompt (S603). Next, the generation unit 132 inputs the converted prompt into the generative model to generate an account code (S604).

[0171] The storage unit 133 stores the generated account code in the account code DB 125 (memory unit 120) (S605). Then, the purchase assistance device 100 ends the process.

[0172] (effect) Next, we will explain the effects of the purchase assistance device 100 according to the second embodiment. Conventionally, when submitting a purchase request, it is sometimes necessary to associate the goods to be purchased with an account code. However, for users who do not have the necessary knowledge, associating goods with account codes can be difficult.

[0173] Therefore, the generation unit 132 of the purchase assistance device 100 according to the second embodiment inputs a prompt based on text information in natural language received from the user to a generation model provided with an account code related to a request to purchase an item in an organization, and generates an account code related to the request to purchase the item indicated in the text information. The output unit 134 of the purchase assistance device 100 then outputs the account code related to the request to purchase the item indicated in the text information to the user.

[0174] Through the above-described process, the purchase assistance device 100 according to the second embodiment can generate an account code to be used for making a purchase request, using purchase-related text information contained in text information such as business-related exchanges between the user and other employees during work hours. As a result, the purchase assistance device 100 according to the second embodiment automatically generates an account code that users previously had to specify by themselves, thereby enabling efficient purchase requests.

[0175] Furthermore, the purchase assistance device 100 according to the second embodiment performs the following processes to achieve the respective predetermined effects.

[0176] The generation unit 132 inputs a prompt including an instruction to generate an account code to be used for a purchase request for each item, and an account code to be used for a purchase request for each item, to the generation model to which the account code to be used for a purchase request for each item is provided, and generates an account code to be used for a purchase request for each item indicated in the text information.

[0177] Specifically, the generation unit 132 inputs a prompt including an instruction to generate an account code to be used for requesting purchases for each item into a generation model that has been provided with at least one of the pre-set correspondence information between an account code and an item, and generates an account code to be used for requesting purchases for each item indicated in the text information.

[0178] Through the above-described process, purchase assistance device 100 can automatically generate an account code, which previously had to be specified by the user, based on text information such as speech entered by the user. Therefore, by eliminating the need for the user to specify an account code, purchase assistance device 100 has the effect of making it possible to streamline tasks such as applying for the purchase of goods.

[0179] The purchase execution unit 135 executes the purchase of an item using the generated account code if at least one of the price and type of the item meets a predetermined condition. Through the above-described process, the purchase assistance device 100 can automatically execute purchases of items that meet the conditions without the user having to submit a purchase application. Therefore, even if an organization's regulations require a purchase application, the purchase assistance device 100 eliminates the need for the user to create application information or execute a purchase for purchase applications related to daily necessities, thereby achieving the effect of streamlining the process of purchasing items.

[0180] The generation unit 132 converts text information related to employees' daily conversations and work into a prompt including an instruction to generate an account code to be used in a purchase request for each item. Next, the generation unit 132 inputs the converted prompt into a generation model to which the account code to be used in a purchase request for each item has been provided, thereby generating an account code. The storage unit 133 then stores the generated account code in the memory unit 120.

[0181] Through the above-described process, purchase assistance device 100 can generate account codes using text information related to employee conversations and store them in storage unit 120, even when there are no instructions for the generation process from a user or the like. In other words, purchase assistance device 100 can automatically generate and store account codes for items included in daily business conversations and the like. As a result, purchase assistance device 100 can use the stored purchase request information to improve the accuracy of the process for generating account codes instructed by users and to present account codes when proposing purchases of items to users, thereby achieving the effect of streamlining tasks such as applying for the purchase of items.

[0182] When the question creation unit 136 receives a question creation instruction, it creates association information between the information identifying the item and the account code. Then, the question creation unit 136 creates a question from the created association information in which at least one of the information identifying the item and the account code has been deleted.

[0183] As described above, purchase assistance device 100 can create questions that associate items with account codes to check the user's understanding of account codes. Therefore, purchase assistance device 100 has the effect of improving the user's understanding of account codes, thereby enabling them to make purchase requests more efficiently.

[0184] <Modification> The following describes modified examples realized by the purchase assistance device 100 according to this embodiment.

[0185] (Data, etc.) The text information, prompts, purchase application information, purchasing information, approval information, account codes, names of functional parts of the purchasing assistance device 100, steps, processes, names of steps or processes, etc. used in the description of the above embodiments are merely examples and can be changed as desired.

[0186] For example, the employee information DB 121 stores employee identification information and organization attribute information in association with "No," which is information identifying individual employee information, but is not limited to this. The text information DB 122 stores employee identification information and text information in association with "No," which is information identifying individual text information, but is not limited to this. The application specification information DB 123 stores classification, whether approval is required, and whether automatic purchase is possible in association with "No," which is information identifying individual application specification information, but is not limited to this. The purchase requisition information DB 124 stores purchase identification information, purchase history, whether approval information is available, and whether automatic purchase is possible in association with "No," which is information identifying individual purchase requisition information, but is not limited to this. The account code DB 125 stores, but is not limited to, "No," which is information identifying individual account codes, purchase targets, and account codes.

[0187] (Combination of processing examples, etc.) The first to third examples according to the first embodiment and the fourth to sixth examples according to the second embodiment described above are merely examples and are not limited to the contents described.

[0188] The first and second embodiments may be combined in any manner. That is, the purchase assistance device 100 according to this embodiment may output to the user any combination of the generated "application information" and "request information" and the generated "account code."

[0189] (An example of a generative model) The purchasing assistance device 100 of this embodiment can use large-scale language models such as ChatGPT (registered trademark) (see, for example, Reference 1) or large-scale language models such as tsuzumi (registered trademark) (see, for example, Reference 2) as generation models.

[0190] (Reference 1):ChatGPT(OpenAI),<URL:https: / / openai.com / chatgpt> ,<Searched on March 29, 2020> (Reference 2): NTT's large-scale language model "tsuzumi",<URL:https: / / www.rd.ntt / research / LLM_tsuzumi.html> ,<Searched on March 29, 2020>

[0191] From here, tsuzumi will be described as an example of a generation model used by the purchase assistance device 100 according to this embodiment. Figures 21 to 23 are diagrams for explaining tsuzumi.

[0192] First, the concept of tsuzumi will be explained using Figure 21. tsuzumi is a small, energy-efficient large-scale language model that achieves the same level of accuracy as ChatGPT, a huge single large-scale language model that consumes a lot of power.

[0193] Tsuzumi is a large-scale language model that is compact by focusing on a high-quality corpus and supporting only English and Japanese, rather than on the amount of training data. Furthermore, for domain specialization, Tsuzumi can be fine-tuned and can integrate with external data by combining search and generative AI (Artificial Intelligence).

[0194] As mentioned above, tsuzumi is a compact generative model, making it possible to create and operate multiple large-scale language models with specific specialized fields and diverse personalities. Furthermore, by linking compact large-scale language models for each specialized field, such as "medical care," "retail," "construction," "local government," "technology," "travel," "culture," "religion," "art," "education," "finance," "legal affairs," and "banking" based on a specified network, tsuzumi achieves the formation of generative models that are high-performance, efficient, fault-tolerant, and democratic compared to conventional single huge large-scale language models.

[0195] Furthermore, tsuzumi allows flexible tuning such as the fine tuning mentioned above. Specifically, tsuzumi allows tuning by "prompt engineering" as shown in Figure 22, "full fine tuning," and "adapter tuning."

[0196] For example, "prompt engineering" shown in Figure 22 (1) is a tuning method that uses prompts with information about a specific field added when setting prompts for the base model. In tuning using prompt engineering, the base model itself is not changed and only the prompts that are set are changed, so the learning cost can be reduced compared to other methods.

[0197] For example, "full fine-tuning" shown in Figure 22 (2) is a tuning method in which the base model is additionally trained or retrained using training data related to a specific field. In full fine-tuning, a tuning model specialized for a target field can be constructed by training the base model using training data for the target field. Therefore, full fine-tuning can improve the accuracy of inference and generation compared to other methods.

[0198] For example, "adapter tuning" shown in Figure 22 (3) is a tuning method that adds a submodule related to a specific field to the base model. Adapter tuning can improve the accuracy of inference and generation by fine-tuning the base model using a submodule related to the target field. Furthermore, because adapter tuning does not require retraining the base model, it can improve accuracy while reducing training costs compared to full fine tuning.

[0199] Furthermore, tsuzumi can construct a model based on a “multi-adapter.” Here, a multi-adapter will be explained using FIG.

[0200] As explained using (3) in Figure 22, tsuzumi allows fine-tuning of the model by adding adapters (sub-modules) to the base model. tsuzumi can also add a combination of one or more adapters to the base model.

[0201] For example, as shown in Fig. 23, tsuzumi fine-tunes the basic model using an adapter specialized for organization A, an adapter specialized for organization B, and an adapter specialized for organization C. As a result, even when data with different characteristics, such as data from organization A, organization B, and organization C, is input, tsuzumi can accurately perform inference and generation processing based on the model fine-tuned by the adapters specialized for each organization.

[0202] For example, organization A could be the "research laboratory," organization B could be the "sales department," and organization C could be the "entire company." In other words, even if the characteristics and granularity of the organizations differ, tsuzumi can make fine adjustments using an adapter appropriate for the organization.

[0203] As mentioned above, tsuzumi is small and energy-efficient, and by combining small, large-scale language models specialized for specific fields, and by implementing flexible tuning, it is possible to achieve both accuracy and cost when performing inference and generation processing compared to conventional huge, large-scale language models.

[0204] In other words, tsuzumi can be used as an appropriate generation model for executing specific processing, such as purchasing assistance processing by the purchasing assistance device 100 of this embodiment, corresponding to the use, purpose, and target field of the processing.

[0205] (IOWN technology) The generative model used by the purchase assistance device 100 according to the present embodiment described above may be realized using technology related to the Innovative Optical and Wireless Network (IOWN) technology.

[0206] Here, we will explain the IOWN technology. Figure 24 is a diagram explaining IOWN. As shown in Figure 24, the IOWN technology consists of three main technology fields: "All-Photonics Network (APN)," "Digital Twin Computing (DTC)," and "Cognitive Foundation (CF) (registered trademark)."

[0207] (All Photonics Network) The APN related to IOWN technology is a technology that enables the construction of high-speed networks by processing all network transfer functions in the optical domain. Specifically, the APN related to IOWN technology is a technology that realizes low-power, high-quality, large-capacity, and low-latency communications based on optical-based (photonics-based) technologies such as "photonics-electronic convergence technology," "large-capacity optical transmission system and device technology," "optical Ising machine," and "optical lattice clock network."

[0208] (Digital Twin Computing) DTC, which is related to IOWN technology, is a technology that maps individual objects in the real world onto a virtual space using the vast amount of data collected by devices connected to the APN described above.

[0209] Conventional digital twin frameworks are used by mapping individual objects, such as automobiles and robots, into a virtual space, performing analysis and predictions on them, and then mapping the results of the analysis and predictions back onto the real world.

[0210] On the other hand, DTC related to IOWN technology expands on the conventional concept of digital twins, freely combining digital twins of various industries, objects, and people to perform calculations, thereby reproducing with high accuracy the combination of multiple objects, such as people and automobiles in a city. Furthermore, DTC related to IOWN technology enables not only the expression of a person's external appearance, but also the digital expression of their internal state, such as consciousness and thoughts, by combining technologies that enable "speech recognition," "speech synthesis," "understanding of emotions and intentions," etc. to collect information and build a digital twin environment.

[0211] In this way, DTC related to IOWN technology is a technology that enables the creation of digital twins that do not exist in the real world by combining multiple entities that are single in the real world and replicating them as digital twins in a virtual space, or by exchanging or merging some of the components between multiple digital twins.

[0212] (Cognitive Foundation) CF related to IOWN technology is a technology that centrally performs the deployment, configuration, linkage, management, and operation of ICT (Information and Communication Technology) resources at different layers, from the cloud to edge computers, network services, user equipment, etc. Specifically, CF related to IOWN technology treats various targets as a group of virtualized ICT resources, and optimally integrates multiple resources at different layers using multi-orchestration functions as a hub.

[0213] Furthermore, as shown in FIG. 24, the IOWN technology provides high-value-added services by linking the above-mentioned APN, DTC, and network services provided by operators.

[0214] For example, as shown in (1) of Figure 24, IOWN technology provides a technology for transmitting information collected via APN to other terminal devices at high speed and with low latency. Also, as shown in (2) of Figure 24, IOWN technology provides a technology for collecting large amounts of information from terminal devices and outputting information such as analysis results from the service provided by the operator at high speed and with low latency in services such as information analysis. Also, as shown in (3) of Figure 24, IOWN technology provides a technology for transmitting large amounts of information at high speed and with low latency, using information obtained from surveillance cameras, automobile sensors, etc. to build a digital twin environment, make future predictions, and output the prediction results to the user.

[0215] The purchase assistance device 100 according to this embodiment can efficiently realize purchase assistance processing based on the generative model of tsuzumi and the like, which is configured based on the IOWN technology that transmits data at high speed and with low latency as described above.

[0216] For example, the purchasing assistance device 100 can generate purchase requisition information with higher accuracy than conventional methods based on tsuzumi, which is trained using text information related to one's own organization or other organizations that is collected in large quantities at high speed and with low latency via a network built based on IOWN.

[0217] (Regarding business-related natural language text) In this embodiment, it has been explained that the purchase assistance device 100 uses "business-related natural language text." The "business-related natural language text" does not mean to include only business-related text, but also broadly includes, for example, natural language conversations between employees, such as daily conversations and business-related meeting details.

[0218] (Flowcharts, etc.) The steps in the flowcharts may be interchanged as long as there is no contradiction, and some steps may not be performed. In addition, conjunctions such as "next," "continue," "further," "at this time," and "on this occasion" used in the explanation of the flowcharts do not limit the order or timing of the execution of the processes in the flowcharts.

[0219] <Hardware configuration> The components of each device shown in the figure are conceptual functional units and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of each device can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0220] Furthermore, among the processes described in this embodiment, all or part of the processes described as being performed automatically can also be performed manually using known methods. In addition, the information including the processing procedures, control procedures, specific names, various data, and parameters shown in the drawings can be changed as desired unless otherwise specified.

[0221] <Program> In one embodiment, the various devices that make up the purchase assistance device 100 can be implemented by installing a purchase assistance program as package software or online software on a desired computer. For example, by running the above-mentioned purchase assistance program on an information processing device, the various devices that make up the purchase assistance device 100 can function. The information processing device referred to here includes desktop and notebook personal computers. Other information processing devices that fall within this category include mobile communication terminals such as smartphones and mobile phones, and even slate terminals such as PDAs (Personal Digital Assistants).

[0222] 25 is a diagram showing an example of a computer that executes the purchase assistance process according to this embodiment. The computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0223] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120. The video adapter 1060 is connected to, for example, a display 1130.

[0224] Hard disk drive 1090 stores, for example, an OS (Operating System) 1091, application programs 1092, program modules 1093, and program data 1094. In other words, the programs that define the processes of the various devices that make up purchase assistance device 100 are implemented as program modules 1093 in which computer-executable code is written. Program modules 1093 are stored, for example, on hard disk drive 1090. For example, program modules 1093 for executing processes similar to the functional configurations of the various devices that make up purchase assistance device 100 are stored on hard disk drive 1090. Note that hard disk drive 1090 may be replaced with an SSD (Solid State Drive).

[0225] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.

[0226] The program module 1093 and program data 1094 are not limited to being stored in the hard disk drive 1090, but may also be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 may be stored in another computer connected via a network (such as a LAN or a WAN (Wide Area Network)). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070.

[0227] <Other> Although the present embodiment has been described above, the present embodiment is not limited by the descriptions and drawings that form part of the disclosure. In other words, other embodiments, examples, operational techniques, etc. that are made by those skilled in the art based on the present embodiment are all included in the scope of the present embodiment. [Explanation of symbols]

[0228] 10 Generative Model 100 Purchasing aid device 110 Communications Department 120 Storage section 121 Employee Information DB 122 Text Information DB 123 Application regulation information DB 124 Purchase requisition information DB 125 Account Code DB 130 Control Unit 131 Reception 132 Generation part 133 Storage area 134 Output section 135 Purchasing Department 136 Question Creation Department 200 Terminal Device 300 servers

Claims

1. a generation unit that inputs a prompt based on a natural language text received from a user to a generation model provided with information about an application for the purchase of an item in an organization, and generates information about the application for the purchase of the item indicated in the text; an output unit that outputs information regarding a purchase application for the item indicated in the text; A purchasing assistance device comprising:

2. The generation unit inputting the prompt including an instruction for generating the information to be used for the purchase request for each item included in the text to a generative model provided with information on the information to be used for the purchase request for each item and information on regulations related to the purchase request for each item, thereby generating the information to be used for the purchase request for each item included in the text; 2. The purchasing assistance device according to claim 1.

3. The generation unit inputting the prompt including an instruction to generate information to be used in a purchase request for each item included in the text to a generative model provided with information about the purchasing history of items in the organization, thereby generating information to be used in a purchase request for each item included in the text; The output unit outputting information to be used for applying for the purchase of each item indicated in the generated text as suggested information to the user; 3. The purchasing assistance device according to claim 2.

4. The generation unit The presence or absence of approval information required at the time of applying for the purchase of goods is determined, and when it is determined that the approval information is generated, inputting the prompt including an instruction for generating approval information required at the time of applying for a purchase of the item included in the text into a generative model provided with approval information for the target organization, thereby generating approval information related to the item shown in the text; 3. The purchasing assistance device according to claim 2.

5. The generation unit converting natural language text related to the employee's work into prompts containing instructions for generating information related to a request for the purchase of an item; inputting the converted prompt into a generative model provided with information relating to a request to purchase an item to generate information relating to the request to purchase an item; The method further comprises a storage unit that stores information about the generated application for purchasing the product in a storage unit.

2. The purchasing assistance device according to claim 1.

6. a purchase execution unit that executes the purchase of the item when at least one of the price and type of the item satisfies a predetermined condition; 5. The purchasing assistance device according to claim 1, wherein the purchasing assistance device is a device for purchasing a product.

7. The generation unit As the generative model, at least one of a large-scale language model having general knowledge and Tsuzumi is used.

6. The purchasing assistance device according to claim 1, wherein:

8. The generation unit Using the generative model to communicate over a communication network related to an Innovative Optical and Wireless Network (IOWN), 8. The purchasing assistance device according to claim 7.

9. A purchasing assistance method executed by a purchasing assistance device, a generation step of inputting a prompt based on natural language text received from a user to a generation model provided with information about an application for the purchase of an item in an organization, and generating information about the application for the purchase of the item indicated in the text; an output step of outputting information relating to an application for the purchase of the item indicated in the text; A purchasing assistance method comprising:

10. a generation step of inputting a prompt based on natural language text received from a user to a generation model provided with information about an application for the purchase of an item in an organization, and generating information about the application for the purchase of the item indicated in the text; an output step of outputting information regarding a request to purchase the item indicated in the text; A purchasing assistance program that causes a computer to execute the above.

Images