Information processing device, information processing method, and program

Abstract

We provide an information processing device that enables sales role-playing that closely resembles actual sales experiences, assuming a target audience with knowledge of the sales target. [Solution] The information processing device 1 comprises an input receiving unit 121 that receives document identification information to identify sales material information, an operation unit 132 that obtains sales material information corresponding to one or more document identification information from one or more document databases 44 in which sales material information corresponding to one or more document identification information is stored, and provides the sales material information and customer persona prompt to the generating AI, an answer acquisition unit 133 that obtains an answer from the generating AI, and an answer output unit 142 that outputs the answer, and further receives training input which is input to advance role-playing, provides the training input to the generating AI, obtains an answer from the generating AI, and outputs the answer.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus and the like that assist a user in performing a simulated business role-play.

Background Art

[0002] Conventionally, there has been a technology that enables role-play using ChatGPT (generative AI) (see Non-Patent Document 1).

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, it has been impossible to realize a business role-play close to an actual business experience. In particular, in the prior art, it has been impossible to realize a business role-play close to an actual business experience assuming a partner with knowledge of the business target.

Means for Solving the Problems

[0005] The first information processing device of the present invention is an information processing device that supports sales role-playing using a generating AI, and comprises: an input receiving unit that receives input information including document identification information that identifies sales document information which is a document that is the subject of sales; an operation unit that obtains sales document information corresponding to the document identification information from one or more document databases in which sales document information corresponding to one or more document identification information is stored, provides the sales document information to the generating AI, and gives the generating AI a customer persona prompt which is a prompt for the generating AI to become a customer persona which is a persona corresponding to a sales target; an answer acquisition unit that obtains an answer corresponding to the customer persona prompt from the generating AI; and an answer output unit that outputs the answer obtained by the answer acquisition unit, wherein the input receiving unit further receives training input which is input that advances the role-playing after the answer output unit has output an answer, the operation unit provides the training input to the generating AI, the answer acquisition unit obtains an answer corresponding to the training input from the generating AI, and the answer output unit outputs an answer corresponding to the training input obtained by the answer acquisition unit.

[0006] This configuration allows for sales role-playing that closely resembles actual sales experiences, simulating interactions with clients who are already knowledgeable about the target market.

[0007] Furthermore, the information processing device of this second invention, compared to the first invention, is an information processing device comprising: an input receiving unit that receives user identification information to identify a user who performs a sales role-playing with a generating AI, and using the user identification information to acquire document identification information from a document management unit which stores document identification information paired with two or more user identification pieces of information; and an operation unit which comprises a sales document acquisition means that acquires sales document information corresponding to the document identification information acquired by the input receiving unit from a document database, and an AI operation means that provides the sales document information acquired by the sales document acquisition means to the generating AI and provides the generating AI with a previous customer persona prompt.

[0008] This configuration allows for the selection and acquisition of document identification information for target customers, and by using this information, it becomes possible to conduct sales role-playing that closely resembles actual sales experiences, simulating interactions with customers who are knowledgeable about the target customers.

[0009] Furthermore, in the third invention, the information processing device differs from the second invention in that the two or more data databases reside in data management devices separate from the information processing device, and the sales data acquisition means accesses the data management device corresponding to the data identification information acquired by the input reception unit to acquire sales data information.

[0010] This configuration allows for sales role-playing that closely resembles actual sales experiences, assuming the participant has knowledge of the target product.

[0011] Furthermore, the information processing device of the fourth invention is an information processing device that, in addition to the first invention, further comprises an evaluation unit that acquires evaluation results of the user's sales role-playing using training input and sales material information received by an input receiving unit, and an evaluation output unit that outputs the evaluation results acquired by the evaluation unit.

[0012] This configuration allows for the evaluation of a user's role-playing performance using sales materials for the target audience and the content of the user's role-playing.

[0013] Furthermore, the information processing device of the fifth invention, in contrast to the fourth invention, is an information processing device in which the evaluation unit acquires an evaluation result that includes one or more pieces of information from among accuracy evaluation information indicating an evaluation of the accuracy of training input based on sales data information, and result evaluation information relating to the results of sales.

[0014] This configuration allows for the evaluation of the accuracy and results of role-playing by using sales materials for the target audience and the content of the user's role-playing.

[0015] Furthermore, the information processing device of the sixth invention, compared to the first invention, is an information processing device in which the input receiving unit receives input information including counterparty identification information that identifies a business partner, and the operation unit obtains unique information of the business partner based on the counterparty identification information received by the input receiving unit from a business management database that stores counterparty information having unique information associated with two or more counterparty identification pieces of information, provides the unique information to the generating AI, and the generating AI provides the generating AI with a customer persona prompt.

[0016] This configuration allows for the generation of AI that also receives unique customer information acquired from the data management device, enabling sales role-playing that more closely resembles actual sales experiences.

[0017] Furthermore, the information processing device of the seventh invention, compared to the first invention, is an information processing device comprising: an input receiving unit that receives input information including counterparty identification information that identifies a sales partner, which is associated with user identification information of a user who performs a sales role-play with a generating AI; and an operation unit that obtains unique information acquisition means from a sales negotiation management database that stores past sales negotiation information associated with user identification information and one or more counterparty identification pieces, which is associated with the counterparty identification information and user identification information received by the input receiving unit; and an AI operation means that also provides the sales negotiation information obtained by the unique information acquisition means to the generating AI and provides the generating AI with a customer persona prompt.

[0018] This configuration allows for sales role-playing that closely resembles actual sales experiences by providing the AI ​​with negotiation information from past business negotiations with potential clients.

[0019] Furthermore, the information processing device of the eighth invention further comprises an instruction receiving unit that receives a partner selection instruction including user identification information for any one of the first to seventh inventions; a candidate acquisition unit that acquires one or more partner identification pieces of information that are paired with the user identification information in the partner selection instruction received by the instruction receiving unit from a business partner management database which stores one or more partner identification pieces of information that identify business partners in association with one or more user identification pieces of information; and a candidate output unit that outputs one or more partner identification pieces of information acquired by the candidate acquisition unit, wherein the input receiving unit is an information processing device that receives input information including one partner identification piece of information from among one or more partner identification pieces of information.

[0020] This configuration automatically retrieves and presents potential sales targets to the user, allowing the user to easily begin sales role-playing that closely resembles actual sales experience.

[0021] The present invention relates to an information processing device that supports sales role-playing using a generating AI, comprising: an input receiving unit that receives input information including counterparty identification information that identifies a sales partner; an operation unit that obtains unique information of a sales partner based on the counterparty identification information received by the input receiving unit from a sales management database that stores counterparty information having unique information associated with two or more counterparty identification pieces of information, provides the unique information to the generating AI, and provides the generating AI with a customer persona prompt, which is a prompt for the generating AI to become a customer persona, which is a persona corresponding to the sales partner; an answer acquisition unit that obtains an answer from the generating AI corresponding to the customer persona prompt; and an answer output unit that outputs the answer obtained by the answer acquisition unit. The input receiving unit further receives training input, which is input that advances the role-playing after the answer output unit has output an answer, the operation unit provides the training input to the generating AI, the answer acquisition unit obtains an answer from the generating AI corresponding to the training input, and the answer output unit outputs an answer corresponding to the training input obtained by the answer acquisition unit.

[0022] This configuration allows for sales role-playing that closely resembles actual sales experiences by providing the AI ​​with unique customer information acquired from the data management device.

[0023] Further, in the information processing apparatus of the present invention, for the above invention, the input reception unit receives input information having partner identification information for specifying a business partner corresponding to the user identification information of a user who conducts a business role-play with the generation AI, the business management database exists in a data management apparatus other than the information processing apparatus, and stores partner information having unique information associated with one or more pieces of each partner identification information paired with the user identification information, and the operation unit includes unique information acquisition means for acquiring, from the business management database, unique information associated with the partner identification information and the user identification information received by the input reception unit, and AI operation means for providing the unique information acquired by the unique information acquisition means to the generation AI and providing a customer persona prompt to the generation AI.

[0024] With such a configuration, by acquiring unique information of an actual business partner from the business management database existing in the data management apparatus and providing the unique information to the generation AI, a business role-play close to an actual business experience can be realized.

[0025] Further, in the information processing apparatus of the present invention, for the above invention, the unique information acquisition means is an information processing apparatus that acquires, from the business management database, unique information including a URL or a web page associated with the partner identification information received by the input reception unit.

[0026] With such a configuration, by providing information on the web page of the organization to which the business partner belongs to the generation AI, a business role-play close to an actual business experience can be realized.

[0027] Further, in the information processing apparatus of the present invention, for the above invention, the unique information acquisition means is an information processing apparatus that acquires, from the business management database, unique information including one or more pieces of information of the name of the business partner, the name of the partner's organization, the name of the partner's position, and the name of the partner's department associated with the partner identification information received by the input reception unit.

[0028] This configuration allows for sales role-playing that closely resembles actual sales experiences by providing the AI ​​with personal information such as the names of sales targets.

[0029] Furthermore, the information processing device of the present invention, in relation to the above invention, comprises an input receiving unit that receives input information corresponding to user identification information of a user who performs a sales role-play with a generating AI, and an operation unit that acquires unique information including deal information corresponding to the deal information and user identification information received by the input receiving unit from a deal management database that stores past deal information corresponding to user identification information and one or more deal identification pieces, and an AI operation unit that provides the unique information acquired by the unique information acquisition unit to the generating AI and provides the generating AI with a customer persona prompt.

[0030] This configuration allows for sales role-playing that closely resembles actual sales experiences by providing the AI ​​with negotiation information from past business negotiations with potential clients.

[0031] Furthermore, the information processing device of the present invention, in contrast to the above invention, is an information processing device in which the business negotiation information includes conversation information of past business negotiations, or summary information which is a summary of conversation information of past business negotiations.

[0032] This configuration allows for sales role-playing that closely resembles actual sales experiences by providing the AI ​​with conversation information from past business negotiations with potential clients, or summarized information of those conversations.

[0033] Furthermore, the information processing apparatus of the present invention, in relation to the above invention, comprises an input receiving unit that receives input information including document identification information that identifies sales document information which is a document to be sold, and an operation unit that acquires sales document information corresponding to the document identification information received by the input receiving unit from one of the one or more document databases in which sales document information corresponding to one or more document identification pieces is stored, and an AI operation unit that provides the sales document information acquired by the sales document acquisition unit to a generating AI and provides the customer persona prompt to the generating AI.

[0034] This configuration allows for sales role-playing against customer personas that understand the target audience by providing sales materials to a generating AI, resulting in an experience that closely resembles actual sales.

[0035] Furthermore, in contrast to the above invention, the information processing device of the present invention is an information processing device in which the data database resides in a data management device that is not an information processing device, the input receiving unit refers to a data management unit that manages data identification information paired with one or more user identification pieces of information, and acquires data identification information paired with user identification information, and the sales material acquisition means acquires sales material information from the data database that corresponds to the data identification information acquired by the input receiving unit.

[0036] This configuration allows for the acquisition of sales materials for target customers from an external data management device and the feeding of these materials to a generating AI. As a result, it enables sales role-playing with customer personas that understand the target customers, providing an experience closer to actual sales.

[0037] Furthermore, the information processing device of the present invention is an information processing device that, in addition to the above invention, further comprises an evaluation unit that acquires an evaluation result of the user's sales role-playing using training input and sales material information received by an input receiving unit, and an evaluation output unit that outputs the evaluation result acquired by the evaluation unit.

[0038] This configuration allows for the evaluation of a user's role-playing performance using sales materials for the target audience and the content of the user's role-playing.

[0039] Furthermore, the information processing device of the present invention, in relation to the above invention, is an information processing device in which the evaluation unit acquires an evaluation result that includes one or more pieces of information from among sales data information, accuracy evaluation information indicating an evaluation of the accuracy of training input, and result evaluation information relating to the results of sales.

[0040] This configuration allows for the evaluation of a user's role-playing performance using sales materials for the target audience and the content of the user's role-playing.

[0041] Furthermore, the information processing device of the present invention further comprises an instruction receiving unit that receives a partner selection instruction including user identification information, a candidate acquisition unit that acquires one or more partner identification information that is paired with the user identification information in the partner selection instruction received by the instruction receiving unit from a business partner management database which stores one or more partner identification information that identifies business partners in association with one or more user identification information, and a candidate output unit that outputs one or more partner identification information acquired by the candidate acquisition unit, and the input receiving unit is an information processing device that receives input information that includes one partner identification information from among one or more partner identification information.

[0042] This configuration automatically retrieves and presents potential sales targets to the user, allowing the user to easily begin sales role-playing that closely resembles actual sales experience. [Effects of the Invention]

[0043] According to the information processing device of the present invention, it is possible to realize sales role-playing that closely resembles an actual sales experience, assuming a customer who is knowledgeable about the target of sales. [Brief explanation of the drawing]

[0044] [Figure 1] Conceptual diagram of information system A in Embodiment 1 [Figure 2]Block diagram of information system A [Figure 3] Block diagram of the information processing device 1 [Figure 4] A flowchart illustrating an example of the operation of the information processing device 1. [Figure 5] A flowchart illustrating an example of the process for obtaining identification information of the same party. [Figure 6] A flowchart illustrating an example of the same evaluation process. [Figure 7] A flowchart illustrating an example of the accuracy evaluation process. [Figure 8] A flowchart illustrating an example of the fact extraction process. [Figure 9] A flowchart illustrating an example of the same result evaluation process. [Figure 10] Diagram showing the prompt management table. [Figure 11] A diagram showing an example of the sales management database 41. [Figure 12] This diagram shows an example of the same business negotiation management database 42. [Figure 13] A diagram showing an example of a DB management table for the same document. [Figure 14] Figure showing an example of the same screen. [Figure 15] A diagram showing an example of the same customer persona prompt. [Figure 16] Figure showing an example of the same output. [Figure 17] Figure showing an example of the same output. [Figure 18] Figure showing an example of the same output. [Figure 19] Block diagram of the computer system [Modes for carrying out the invention]

[0045] The embodiments of the information processing device, etc., will be described below with reference to the drawings. In the embodiments, components that are denoted by the same reference numerals perform the same operation, and therefore, further explanation may be omitted.

[0046] (Embodiment 1) This embodiment describes an information processing device that enables sales role-playing with a customer persona as the sales partner by providing a generating AI with one or more types of information from the sales partner's unique information and negotiation information. The unique information is, for example, the sales partner's unique information in a sales management DB located on an external device different from the information processing device. The sales partner's unique information in the sales management DB is, for example, the web page information of the organization to which the sales partner belongs, the sales partner's name, job title, and other personal information. The negotiation information is, for example, information on past negotiations with the sales partner in the negotiation management DB.

[0047] This embodiment describes an information processing device that provides sales materials from an external device to a generating AI, thereby enabling sales role-playing with customer personas that understand the target audience.

[0048] In this embodiment, an information processing device that evaluates role-playing using sales materials will be described.

[0049] This embodiment describes an information processing device that automatically acquires one or more potential business partners corresponding to a user and sets the business partner selected by the user as the business partner.

[0050] In this specification, information X being associated with information Y means that information Y can be obtained from information X, or information X can be obtained from information Y, and the method of association is irrelevant. Information X and information Y may be linked, may reside in the same buffer, may information X be contained in information Y, or information Y may be contained in information X, and so on.

[0051] Furthermore, in this specification, selecting or determining information Z means obtaining information Z, obtaining a pointer to information Z, obtaining the ID of information Z, setting a flag on information Z, etc., and it is sufficient to be able to access information Z.

[0052] Figure 1 is a conceptual diagram of information system A in this embodiment. Information system A comprises an information processing device 1, one or more terminal devices 2, one or more generation AI devices 3, and one or more data management devices 4.

[0053] Information Processing Device 1 is a device that enables sales role-playing with the user. Information Processing Device 1 can be, for example, a cloud server or an ASP server, but the type is not specified. Information Processing Device 1 can also be a terminal. If Information Processing Device 1 is a terminal, then Terminal Device 2 is not required in Information System A. If Information Processing Device 1 is a terminal, then it can be considered to also function as Terminal Device 2. If Information Processing Device 1 is a terminal, then Information Processing Device 1 can be, for example, a so-called personal computer, smartphone, or tablet device, but the type is not specified.

[0054] Terminal device 2 is the terminal used by the user. The user is the person who performs sales role-playing. The user is, for example, the person who receives training through role-playing with a generating AI. Terminal device 2 is a device that receives input information from the user and outputs the response described later. Terminal device 2 is, for example, a so-called personal computer, smartphone, or tablet device, but the type is not limited.

[0055] The generation AI device 3 is, for example, a ChatGPT (registered trademark) server or a Gemini (registered trademark) server. The generation AI device 3 is, for example, a cloud server or an ASP server, but the type is not limited. If the information processing device 1 has the function of generation AI, generation AI device 3 is not necessary. The generation AI device 3 will be referred to as generation AI as appropriate. The information processing device 1 may also have the function of generation AI. In this case, generation AI device 3 is not necessary.

[0056] Data management device 4 is a device that has databases such as the sales management database, the deal management database, and the document database, which will be described later. Data management device 4 is, for example, a cloud server or an ASP server, but the type is not limited. It is preferable that data management device 4 is a different device from information processing device 1. Data management device 4 having the sales management database is, for example, a Salesforce® server or a Cybozu® server. Data management device 4 having the deal management database is, for example, an amptalk® server or a zoom® server. Data management device 4 having the document database is a server of the company to which one or more users belong, and is a server that manages the documents of each company. It is preferable that data management device 4 having the sales management database, data management device 4 having the deal management database, and data management device 4 having the document database are each separate devices.

[0057] Figure 2 is a block diagram of information system A in this embodiment. Figure 3 is a block diagram of information processing device 1.

[0058] Information system A comprises an information processing device 1, a terminal device 2, a generation AI device 3, and a data management device 4.

[0059] The information processing device 1 comprises a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 comprises a prompt management unit 111 and a document management unit 112. The reception unit 12 comprises an input reception unit 121 and an instruction reception unit 122. The processing unit 13 comprises a candidate acquisition unit 131, an operation unit 132, an answer acquisition unit 133, and an evaluation unit 134. The operation unit 132 comprises a unique information acquisition means 1321, a sales document acquisition means 1322, a prompt acquisition means 1323, and an AI operation means 1325. The output unit 14 comprises a candidate output unit 141, an answer output unit 142, and an evaluation output unit 143.

[0060] The terminal device 2 includes a terminal storage unit 21, a terminal receiving unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal receiving unit 25, and a terminal output unit 26.

[0061] Each of the one or more data management devices 4 includes one or more databases from among the sales management database 41, the business opportunity management database 42, the business partner management database 43, and the document database 44. Note that two or more of the sales management database 41, the business opportunity management database 42, the business partner management database 43, and the document database 44 may be implemented in a single database. For example, the business partner management database 43 is either the sales management database 41 or the business opportunity management database 42. Here, a database is, for example, a relational database, but it may also be a NoSQL database, object-oriented database, etc. A database may also be a folder or a file. A database can be understood simply as a collection of data.

[0062] The storage unit 11, which constitutes the information processing device 1, stores various types of information. These types of information include, for example, prompt templates (described later) and document identification information (described later).

[0063] The prompt management unit 111 stores one or more prompt templates. A prompt template is information that serves as a template for prompts to be given to the generation AI. A prompt template may also be a prompt given to the generation AI. For example, a prompt template has variables for substituting one or more input pieces of information entered by the user. For example, a prompt template has variables for substituting unique information and sales material information, which will be described later.

[0064] The generated AI is either the generated AI device 3, the program for the generated AI device, or a program within the information processing device 1. In other words, the program for the generated AI may be stored in the storage unit 11. In this case, the generated AI device 3 is not required for information system A. The generated AI is typically the partner in a role-playing scenario.

[0065] The prompts given to the generating AI include, for example, customer persona prompts, factual judgment prompts, and result evaluation prompts.

[0066] A customer persona prompt is a prompt used by the generating AI to create a customer persona that corresponds to a potential sales target.

[0067] A factual judgment prompt is a prompt that requests the user to determine whether or not the information contained in the sales materials described later is factual.

[0068] The results evaluation prompt is a prompt used to obtain the evaluation results of a user's sales role-playing.

[0069] The document management unit 112 stores one or more document identification information. This document identification information is paired with user identification information.

[0070] Document identification information refers to information that identifies sales materials that are the target of sales. Examples of document identification information include a URL that identifies the location where the sales materials are stored, information that identifies the data management device 4 and folder where the sales materials are stored, and an API for retrieving the sales materials.

[0071] It is preferable that the document management unit 112 stores document identification information for each of two or more organizations (usually companies). This document identification information includes information that identifies the data management device 4. In other words, for example, it is preferable that each company has a device (server) for managing its own sales document information.

[0072] Here, user identification information refers to information used to identify a user. User identification information does not necessarily have to be information that identifies a single user. User identification information may be, for example, a user identifier or an organization identifier. A user identifier is information that identifies a single user. A user identifier may be, for example, a user ID, name, email address, telephone number, or the IP address of the user's terminal device 2. An organization identifier is information that identifies an organization. An organization is the organization to which the user belongs. An organization may be, for example, a company, a local government, various organizations, or a department within a company. An organization identifier may be, for example, an organization ID, an organization name, a company name, or a department name.

[0073] Sales materials refer to materials related to sales targets. Sales targets are the objects that users sell to. Examples of sales targets include products and services. Examples of sales materials include manuals, sales presentation materials, and press releases. Sales materials are usually files, but their data structure is not specified.

[0074] The reception unit 12 receives various instructions and information. These instructions and information include, for example, start instructions, input information (described later), training input (described later), and opponent selection instructions (described later).

[0075] The start instruction is an instruction to begin role-playing. The start instruction may also be an instruction to log in to the information processing device 1. The start instruction is usually associated with user identification information.

[0076] Here, "reception" usually refers to the reception of information transmitted via a wired or wireless communication line from terminal device 2, but it may also be a concept that includes the reception of information input from input devices such as keyboards, mice, and touch panels, and the reception of information read from recording media such as optical discs, magnetic discs, and semiconductor memory. Various instructions and information here can be obtained by simply acquiring the instructions or information.

[0077] The input reception unit 121 receives various types of information from the user. These types of information include, for example, input information and training input.

[0078] The input information refers to information about the counterparty in the sales role-playing. The input information includes, for example, counterparty identification information that identifies the sales target. The input information received by the input reception unit 121 corresponds to, for example, user identification information of the user who performs the sales role-playing with the generating AI as the counterparty. The input information includes, for example, document identification information that identifies the sales material information that is the subject of the sales. The input information includes, for example, document identification information that identifies the sales material information that is the subject of the sales.

[0079] The input receiving unit 121 receiving input information including document identification information may also be done by the input receiving unit 121 acquiring the document identification information using user identification information associated with the input information it receives.

[0080] The input receiving unit 121 accepts further training input after the response output unit 142 has output a response. Training input refers to the user's input as they advance the role-playing. Training input also refers to the user's input corresponding to the response from the generating AI.

[0081] The input receiving unit 121 receives input information that includes one of the counterparty identification information from among one or more counterparty identification information.

[0082] The instruction receiving unit 122 receives various types of instructions. These instructions include, for example, start instructions and recipient selection instructions.

[0083] A partner selection instruction is an instruction to select a business partner. This instruction includes the user identification information of the user performing the sales role-playing. Typically, partner identification information is obtained through a partner selection instruction.

[0084] The processing unit 13 performs various processes. These processes include, for example, those performed by the candidate acquisition unit 131, the operation unit 132, the answer acquisition unit 133, and the evaluation unit 134.

[0085] The processing unit 13 performs speech recognition processing on, for example, the voice information input by the user (e.g., training input) and obtains string information (e.g., training input). Note that the processing of converting the voice information input by the user into string information may be performed by the terminal device 2.

[0086] The processing unit 13 converts the string response obtained by the generating AI into an audio response. Note that the terminal device 2 may also perform the process of converting the response obtained by the generating AI into an audio response.

[0087] The candidate acquisition unit 131 acquires one or more counterpart identification information from the business partner management database 43 that corresponds to the user identification information contained in the counterpart selection instruction received by the instruction reception unit 122. The business partner management database 43 may also be, for example, the sales management database 41 or the business opportunity management database 42.

[0088] Counterparty identification information is information that identifies the other party in a business negotiation. For example, counterparty identification information could be the name of the other party. For example, counterparty identification information could be the organization name and individual name of the other party. For example, counterparty identification information could be the ID of the other party. For example, counterparty identification information could be the organization name of the other party. Counterparty identification information does not necessarily have to identify a single person; it could also be information that identifies the organization of the other party.

[0089] The operation unit 132 acquires unique information of the business partner based on the counterparty identification information received by the input reception unit 121. The operation unit 132 then provides this unique information to the generating AI. It also provides the generating AI with a customer persona prompt, which is a prompt for the generating AI to become a customer persona corresponding to the business partner.

[0090] The operation unit 132, for example, uses the counterparty identification information as a key to obtain unique information about the sales partner from the sales management database 41. The operation unit 132 typically obtains customer persona prompts from the prompt management unit 111 and provides them to the generation AI.

[0091] The operation unit 132, for example, substitutes unique information into a template prompt for a customer persona prompt to construct a customer persona prompt, and provides the customer persona prompt to the generating AI.

[0092] Unique information refers to information specific to a business partner. Unique information includes, for example, one or two types of information such as personal information and business negotiation information. Personal information refers to the personal information of a business partner. Personal information includes, for example, the business partner's name, job title, age, gender, email address, telephone number, the name of the organization to which the business partner belongs (for example, a company or local government), the URL of the organization's homepage, and the organization's homepage (which may include web pages of the organization's site). Note that homepage can also be called web pages.

[0093] Sales negotiation information refers to information about past sales negotiations with sales partners. Sales negotiation information may include, for example, information recorded or / or videotaped during sales negotiations conducted via web conference or telephone (overall sales negotiation information), sales negotiation conversation information, or summary information that summarizes the sales negotiation using audio information from the overall sales negotiation information.

[0094] The operation unit 132 provides the training input received by the input reception unit 121 to the generation AI. Note that the training input received by the input reception unit 121 may be voice information, and the training input provided to the generation AI may be text.

[0095] The unique information acquisition means 1321, which constitutes the operating unit 132, acquires unique information. The following describes the cases in which personal information and business negotiation information are acquired from the unique information. (1) When acquiring personal information

[0096] The unique information acquisition means 1321 acquires the counterparty identification information contained in the input information received by the input reception unit 121. The unique information acquisition means 1321 also acquires user identification information associated with the input information received by the input reception unit 121. Next, the unique information acquisition means 1321 acquires personal information associated with the counterparty identification information and the user identification information from the sales management database 41. It is preferable that the sales management database 41 resides in a data management device 4, which is an external device of the information processing device 1.

[0097] The unique information acquisition means 1321 retrieves personal information by, for example, using the counterparty identification information and the user identification information as keys to search the sales management database 41 of the data management device 4 (for example, a Salesforce server). The process of searching the sales management database 41 is, for example, a process of providing the counterparty identification information and the user identification information to an API that searches the sales management database 41 and executing the API.

[0098] The unique information acquisition means 1321 is preferably used to acquire personal information, including URLs or web pages associated with the recipient identification information received by the input reception unit 121, from the sales management database 41.

[0099] The unique information acquisition means 1321, for example, acquires a URL associated with the counterparty identification information received by the input reception unit 121. Next, the unique information acquisition means 1321 uses the URL to acquire the web page of the business partner organization identified by the counterparty identification information.

[0100] The unique information acquisition means 1321 preferably acquires personal information from the sales management database 41 that includes the name of the business partner corresponding to the counterparty identification information received by the input reception unit 121, and one or more pieces of information from the counterparty's organization name, job title, or department name. (2) When obtaining business negotiation information

[0101] The unique information acquisition means 1321 acquires counterparty identification information contained in the input information received by the input reception unit 121. The unique information acquisition means 1321 also acquires user identification information associated with the input information received by the input reception unit 121. Next, it is preferable for the unique information acquisition means 1321 to acquire deal information associated with the counterparty identification information and the user identification information from the deal management database 42. The deal information associated with the counterparty identification information and the user identification information is information about past deals between the business partner specified by the counterparty identification information and the user specified by the user identification information. The business partner specified by the counterparty identification information may be an organization. The user specified by the user identification information may be another user in the organization to which the user belongs.

[0102] Deal information refers to past deal information. Past deal information includes, for example, conversation information from past deals, or summary information which is a summary of past deals.

[0103] The sales material acquisition means 1322 acquires sales material information corresponding to the material identification information received by the input reception unit 121 from one of the material databases 44 located in one or more data management devices 4.

[0104] The sales material acquisition means 1322 preferably acquires sales material information from the material database 44 that corresponds to the material identification information acquired by the input reception unit 121 by referring to the material management unit 112.

[0105] The data databases 44 of each of the two or more data management devices 4 are associated with data identification information.

[0106] The prompt acquisition means 1323 acquires customer persona prompts, which are prompts for the generating AI to become a customer persona, which is a persona corresponding to a sales target. The prompt acquisition means 1323 acquires the customer persona prompt or a prompt template for composing the customer persona prompt from the prompt management unit 111.

[0107] The AI ​​operation means 1325 provides the generating AI with one or more types of information, either unique information or business opportunity information, acquired by the unique information acquisition means 1321. The AI ​​operation means 1325 also provides the generating AI with customer persona prompts. For example, the AI ​​operation means 1325 provides the generating AI with customer persona prompts acquired by the prompt acquisition means 1323.

[0108] The AI ​​operation means 1325 provides the sales material information acquired by the sales material acquisition means 1322 to the generating AI. The AI ​​operation means 1325 also provides customer persona prompts to the generating AI. For example, the AI ​​operation means 1325 provides customer persona prompts acquired by the prompt acquisition means 1323 to the generating AI.

[0109] The AI ​​operating means 1325 preferably provides the generating AI with two or more types of information from among unique information, negotiation information, and sales material information, as well as customer persona prompts.

[0110] The response acquisition unit 133 acquires responses from the generating AI that correspond to prompts given to the generating AI by the AI ​​operating means 1325. The response acquisition unit 133 acquires responses from the generating AI that correspond to training inputs. Prompts given to the generating AI include, for example, customer persona prompts, fact judgment prompts, and result evaluation prompts.

[0111] The evaluation unit 134 uses the training input and sales material information received by the input reception unit 121 to obtain the evaluation results of the user's sales role-playing.

[0112] The evaluation unit 134, for example, provides a result evaluation prompt to the generating AI and obtains the evaluation result from the generating AI.

[0113] The evaluation unit 134 acquires an evaluation result that includes, for example, one or more pieces of information from among accuracy evaluation information and result evaluation information. (1) When obtaining accuracy evaluation information (1-1) When using a generating AI

[0114] The evaluation unit 134 provides the generating AI with a result evaluation prompt that inquires about accuracy evaluation (for example, "Please evaluate the accuracy of the statements made by the user, who is a sales representative, regarding the sales role-playing exercises so far"), and obtains accuracy evaluation information from the generating AI. (1-2) Using natural language processing

[0115] The evaluation unit 134 acquires accuracy evaluation information, for example, by processing using the flowchart shown in Figure 7, which will be described later. (2) When obtaining result evaluation information (2-1) When using a generating AI

[0116] The evaluation unit 134 provides the generating AI with a result evaluation prompt (for example, "Please provide an overall evaluation of the sales role-playing so far") to obtain an evaluation of the results of the sales role-playing, and obtains result evaluation information from the generating AI. (2-2) Using natural language processing

[0117] The evaluation unit 134 determines, for example, whether a next-step term, which indicates that the next step has been taken in sales, exists in the response from the generating AI to the training input. If it exists, it obtains positive result evaluation information "1," and if it does not exist, it obtains negative result evaluation information "0." Examples of next-step terms include "I will buy it," "I will sign the contract," and "Next business negotiation."

[0118] The evaluation unit 134 determines, for example, whether a termination term, which indicates that the contract was not concluded, exists in the response from the generating AI to the training input. If it exists, it obtains negative result evaluation information "0," and if it does not exist, it obtains positive result evaluation information "1." Examples of termination terms are "I will not purchase" and "I will not enter into a contract."

[0119] The output unit 14 outputs various types of information. These types of information include, for example, the other party's identification information, the response, and the evaluation result.

[0120] Here, output usually refers to transmission to terminal device 2, but it is a concept that includes audio output, display on a screen, projection using a projector, printing with a printer, storage on a recording medium, and transfer of processing results to other processing devices or other programs. Here, it is preferable that the output is the transmission of audio information to terminal device 2.

[0121] The candidate output unit 141 outputs one or more counterpart identification information acquired by the candidate acquisition unit 131. Typically, the candidate output unit 141 outputs information in a form in which one or more counterpart identification information can be selected. This information in a form in which one or more counterpart identification information can be selected is, for example, a menu, checkbox, or radio button in which the counterpart identification information can be selected. It is preferable for the candidate output unit 141 to transmit information in a form in which one or more counterpart identification information can be selected, and which can be displayed, to the terminal device 2.

[0122] The response output unit 142 outputs the response acquired by the response acquisition unit 133. The response output unit 142 outputs the response corresponding to the training input passed to the generating AI. It is preferable for the response output unit 142 to transmit the response, which is voice information, to the terminal device 2.

[0123] The evaluation output unit 143 outputs the evaluation results acquired by the evaluation unit 134. This output is typically transmitted to the terminal device 2. The evaluation results include, for example, advice.

[0124] The terminal storage unit 21, which constitutes the terminal device 2, stores various types of information. These types of information include, for example, a user identifier.

[0125] The terminal reception unit 22 receives various types of information and instructions. These types of information and instructions include, for example, input information and user voice information. User voice information includes, for example, training input.

[0126] The means of inputting various information and instructions can be anything, such as a touch panel, keyboard, mouse, menu screen, camera, microphone, etc.

[0127] The terminal processing unit 23 performs various processes. These processes include, for example, converting received information and instructions into information and instructions for transmission. Other processes include, for example, converting received information into information for output.

[0128] It is preferable for the terminal processing unit 23 to perform speech recognition processing on the user's voice information (e.g., training input) received by the terminal reception unit 22 and obtain text (e.g., text training input).

[0129] The terminal transmission unit 24 transmits various information and instructions to the information processing device 1. These various information and instructions include, for example, input information and user voice information.

[0130] The terminal receiving unit 25 receives various types of information. These types of information include, for example, one or more pieces of information identifying the other party, a response, and an evaluation result.

[0131] The terminal output unit 26 receives various types of information. These types of information include, for example, one or more pieces of information identifying the other party, a response, and an evaluation result. The terminal output unit 26 preferably outputs an audio response.

[0132] The sales management database 41 stored in the data management device 4 stores one or more unique pieces of information. Each unique piece of information corresponds to a counterparty identification piece. In addition, one or more counterparty identification pieces are paired with user identification pieces.

[0133] The business opportunity management database 42 stored in the data management device 4 stores information on one or more past business opportunities. Each business opportunity is associated with a counterparty identification information. Additionally, one or more business opportunity entries are paired with user identification information.

[0134] The data database 44 stored in the data management device 4 stores sales material information that corresponds to one or more pieces of material identification information. Sales material information is typically associated with user identification information.

[0135] The storage unit 11, prompt management unit 111, terminal storage unit 21, sales management database 41, negotiation management database 42, and document database 44 are preferably made of non-volatile recording media, but can also be made of volatile recording media.

[0136] The process by which information is stored in the storage unit 11, etc. is not relevant. For example, information may be stored in the storage unit 11, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the storage unit 11, etc., or information input via an input device may be stored in the storage unit 11, etc.

[0137] The reception unit 12, input reception unit 121, and instruction reception unit 122 are preferably implemented by wireless or wired communication means, but may also be implemented by means of receiving broadcasts, device drivers for input means such as touch panels and keyboards, or control software for menu screens.

[0138] The processing unit 13, candidate acquisition unit 131, operation unit 132, response acquisition unit 133, evaluation unit 134, unique information acquisition means 1321, sales material acquisition means 1322, prompt acquisition means 1323, AI operation means 1325, and terminal processing unit 23 can typically be implemented using a processor, memory, etc. The processing procedures of the processing unit 13, etc., are typically implemented in software, and this software is recorded on a recording medium such as ROM. However, it may also be implemented in hardware (dedicated circuitry). The processor can be a CPU, MPU, GPU, etc., and the type is not limited.

[0139] The output unit 14, candidate output unit 141, answer output unit 142, and evaluation output unit 143 are preferably implemented by wireless or wired communication means, but may also be implemented by driver software for an output device such as a display or speaker, or by driver software for an output device and the output device itself.

[0140] The terminal reception unit 22 can be implemented using device drivers for input means such as touch panels and keyboards, or control software for menu screens, etc.

[0141] The terminal transmission unit 24 is usually implemented by wireless or wired communication means, but it may also be implemented by broadcasting means.

[0142] The terminal receiving unit 25 is usually implemented by wireless or wired communication means, but it may also be implemented by means of receiving broadcasts.

[0143] The terminal output unit 26 may or may not be considered to include output devices such as a display or speakers. The terminal output unit 26 can be implemented using driver software for an output device, or driver software for an output device and an output device.

[0144] Next, an example of the operation of the information processing device 1 will be explained using the flowchart in Figure 4.

[0145] (Step S401) The reception unit 12 determines whether or not it has received the start instruction. If it has received the start instruction, it proceeds to step S402; otherwise, it returns to step S401.

[0146] (Step S402) The processing unit 13 obtains user identification information (e.g., user ID, user's name, telephone number, email address) associated with the start instruction. The user identification information consists of one or two pieces of information, such as a user identifier or an organization identifier of the organization to which the user belongs (e.g., company name).

[0147] (Step S403) The processing unit 13 acquires opponent identification information (for example, the opponent's name and company name) to identify the opponent in the sales role-playing. An example of this opponent identification information acquisition process will be explained using the flowchart in Figure 5.

[0148] (Step S404) The unique information acquisition means 1321 uses the counterparty identification information to acquire the counterparty's unique information (for example, name, company name, job title, company homepage URL) from the sales management database 41.

[0149] The unique information acquisition means 1321 searches the sales management database 41 using, for example, user identification information and counterparty identification information as keys, and acquires unique information.

[0150] (Step S405) The unique information acquisition means 1321 uses the URL of the organization contained in the unique information to acquire the web page of the said organization.

[0151] (Step S406) The unique information acquisition means 1321 uses the user identification information and the counterparty identification information to acquire deal information from the deal management database 42.

[0152] The unique information acquisition means 1321 searches the business opportunity management database 42 using, for example, user identification information and counterparty identification information as keys, and acquires one or more business opportunity information.

[0153] (Step S407) The sales data acquisition means 1322 determines the data management device 4 and the data database 44 that correspond to the user identification information.

[0154] (Step S408) The sales material acquisition means 1322 accesses the data management device 4 associated with the user identification information and acquires sales material information from the material database 44 of the data management device 4.

[0155] (Step S409) The prompt acquisition means 1323 acquires customer persona prompts from the prompt management unit 111. The AI ​​operation means 1325 provides the acquired information (unique information, business negotiation information, sales material information) to the generating AI. The AI ​​operation means 1325 also provides the acquired customer persona prompts to the generating AI.

[0156] (Step S410) The response acquisition unit 133 determines whether or not it has acquired a response from the generating AI. If a response has been acquired, it proceeds to step S411; otherwise, it returns to step S410.

[0157] (Step S411) The response output unit 142 outputs all or part of the response obtained in step S410. The response output unit 142 transmits all or part of the response to the terminal device 2. Here, it is preferable for the response output unit 142 to transmit all or part of the response, which has been converted into voice information, to the terminal device 2.

[0158] Furthermore, the response output unit 142 stores all or part of the responses obtained in step S410 in a buffer (not shown).

[0159] (Step S412) The processing unit 13 determines whether the answer satisfies the termination condition. If the termination condition is met, the process proceeds to step S418; otherwise, the process proceeds to step S413.

[0160] The termination condition is, for example, that the response contains a specific term (e.g., "end," "it's finished," "sales role-playing is over").

[0161] (Step S413) The input receiving unit 121 determines whether or not it has received training input from the user. If training input has been received, the process proceeds to step S414; otherwise, it returns to step S413.

[0162] (Step S414) The processing unit 13 determines whether the training input satisfies the termination condition. If the termination condition is met, the process proceeds to step S418; otherwise, the process proceeds to step S415. For example, if the training input is audio information, the processing unit 13 performs speech recognition processing on the audio information to obtain the training input as a string.

[0163] The termination condition is, for example, that a specific term (e.g., "end", "it's over", "sales role-playing is over") is included in the training input.

[0164] (Step S415) The processing unit 13 determines whether the time, etc., satisfies the termination conditions. If the termination conditions are met, the unit proceeds to step S418; otherwise, the unit proceeds to step S416.

[0165] The termination condition here is that the current time is at least a predetermined time (e.g., "30 minutes") elapsed from the start time.

[0166] (Step S416) The AI ​​operating means 1325 provides the training input to the generating AI.

[0167] (Step S417) The output unit 14 stores the training input in a buffer (not shown). Return to step S410.

[0168] (Step S418) The evaluation unit 134 obtains the evaluation result for the user's sales role-playing. An example of such evaluation processing will be explained using the flowchart in Figure 6.

[0169] (Step S419) The evaluation output unit 143 outputs the evaluation result obtained in step S418. The process ends.

[0170] Next, an example of the process for obtaining the counterparty identification information in step S403 will be explained using the flowchart in Figure 5.

[0171] (Step S501) The candidate acquisition unit 131 determines whether the start instruction has counterpart identification information. If the start instruction has counterpart identification information, the unit proceeds to step S507; otherwise, the unit proceeds to step S502.

[0172] (Step S502) The candidate acquisition unit 131 uses the user identification information to acquire one or more counterpart identification information from the counterpart management database 43 (which may also be the sales management database 41 or the deal management database 42).

[0173] (Step S503) The candidate acquisition unit 131 configures a UI (for example, a menu screen) for selecting one counterparty identification information from one or more counterparty identification information.

[0174] (Step S504) The candidate output unit 141 outputs a UI (for example, a menu screen).

[0175] (Step S505) The input receiving unit 121 determines whether it has received input information that includes the selection of one counterparty identification information from one or more counterparty identification information. If such input information has been received, the unit proceeds to step S506; otherwise, it returns to step S505. It should be noted that input information that includes the selection of one counterparty identification information is considered to be input information that includes one counterparty identification information.

[0176] (Step S506) The processing unit 13 obtains a single counterparty identification information corresponding to the selection of a single counterparty identification information. It returns to the higher-level processing unit.

[0177] (Step S507) The processing unit 13 obtains the counterparty identification information contained in the start instruction. It returns to the higher-level processing unit.

[0178] Next, an example of the evaluation process in step S418 will be explained using the flowchart in Figure 6.

[0179] (Step S601) The evaluation unit 134 acquires sales data information.

[0180] (Step S602) The evaluation unit 134 obtains training inputs and responses for the sales role-playing from a buffer (not shown).

[0181] (Step S603) The evaluation unit 134 evaluates the accuracy of the user's statements using sales material information and training input. An example of such accuracy evaluation processing will be explained using the flowchart in Figure 7.

[0182] (Step S604) The evaluation unit 134 evaluates the results of the sales role-playing. An example of this results evaluation process will be explained using the flowchart in Figure 9.

[0183] Next, an example of the accuracy evaluation process in step S603 will be explained using the flowchart in Figure 7.

[0184] (Step S701) The evaluation unit 134 obtains factual information from the sales materials. An example of this fact extraction process will be explained using the flowchart in Figure 8.

[0185] (Step S702) The evaluation unit 134 assigns 1 to counter i.

[0186] (Step S703) The evaluation unit 134 determines whether or not the i-th judgment unit exists in the sales data information. If the i-th judgment unit exists, the unit proceeds to step S704; otherwise, the unit proceeds to step S711.

[0187] The unit of judgment is, for example, a sentence, paragraph, or topic. Techniques for dividing a group of texts into two or more topics are publicly known.

[0188] (Step S704) The evaluation unit 134 obtains the i-th judgment unit from the sales data information. The evaluation unit 134 vectorizes the i-th judgment unit and obtains the i-th judgment unit vector.

[0189] (Step S705) The evaluation unit 134 assigns 1 to counter j.

[0190] (Step S706) The evaluation unit 134 determines whether the j-th fact vector exists. If the j-th fact vector exists, the unit proceeds to step S707; otherwise, the unit proceeds to step S709.

[0191] (Step S707) The evaluation unit 134 obtains the similarity between the i-th judgment unit vector and the j-th fact vector.

[0192] (Step S708) The evaluation unit 134 increments counter j by 1. Return to step S706.

[0193] (Step S709) The evaluation unit 134 obtains the highest similarity of the i-th judgment unit.

[0194] (Step S710) The evaluation unit 134 obtains the class corresponding to the highest similarity, associates it with the i-th judgment unit, and stores it.

[0195] The classes are, for example, "Correct," "Incorrect," and "Irrelevant." The evaluation unit 134, for example, acquires the class "Correct" if the maximum similarity is equal to or greater than the first threshold, the class "Incorrect" if it is less than the first threshold but equal to or greater than the second threshold, and the class "Irrelevant" if it is less than the second threshold but equal to or greater than the third threshold (provided that the first threshold > second threshold > third threshold).

[0196] (Step S711) The evaluation unit 134 increments counter i by 1. Return to step S703.

[0197] (Step S712) The evaluation unit 134 calculates accuracy using the classes of two or more judgment units. It then returns to the higher-level processing.

[0198] The evaluation unit 134 calculates higher accuracy the more judgment units there are in the "correct" class. The evaluation unit 134 calculates lower accuracy the more judgment units there are in the "incorrect" class. The evaluation unit 134 calculates accuracy, for example, using the formula "Accuracy = Number of judgment units in the "correct" class / Total number of judgment units" or "Accuracy = Number of judgment units in the "correct" class / (Number of judgment units in the "correct" class + Number of judgment units in the "incorrect" class)".

[0199] In addition, in the flowchart of Figure 7, the evaluation unit 134 may provide the generating AI with sales material information and training input, and may also provide the generating AI with a prompt asking for accuracy (for example, "Based on the sales role-playing so far, please evaluate the accuracy of the statements made by the user, who is a sales representative"), and obtain the accuracy from the generating AI.

[0200] Next, an example of the fact extraction process in step S701 will be explained using the flowchart in Figure 8.

[0201] (Step S801) The evaluation unit 134 assigns 1 to counter i.

[0202] (Step S802) The evaluation unit 134 determines whether or not the i-th judgment unit exists in the acquired sales data information. If the i-th judgment unit exists, the process proceeds to step S803; otherwise, it returns to the higher-level process.

[0203] A judgment unit is a unit used to determine whether or not information is factual. Examples of judgment units include sentences, paragraphs, information enclosed in specific tags, and topics.

[0204] (Step S803) The evaluation unit 134 obtains the i-th judgment unit from the acquired sales data information.

[0205] (Step S804) The evaluation unit 134 determines whether the i-th judgment unit is information that indicates a fact. If it is information that indicates a fact, the unit proceeds to step S805; otherwise, the unit proceeds to step S806.

[0206] The evaluation unit 134 uses, for example, a machine learning algorithm or generative AI to determine whether the i-th judgment unit is factual information. Each case is described below. (1) In the case of machine learning

[0207] The evaluation unit 134 provides the i-th decision unit and the learning model to a machine learning prediction processing module, executes the module, and obtains a determination result of whether or not the i-th decision unit is information that indicates a fact.

[0208] A learning model is information constructed through the learning process of machine learning, and is used in the prediction process of machine learning. A learning model can also be called a learner, classifier, or classification model. Here, a learning model is information obtained by providing a machine learning module with two or more training data sets, where the explanatory variables are decision units or vectors obtained from decision units, and the dependent variable is the result of a judgment on whether or not the information represents a fact, and then executing that module. The machine learning algorithm can be deep learning, random forest, decision tree, SVM, etc. Furthermore, various machine learning functions and various existing libraries can be used for machine learning, such as the TensorFlow® library, the R language's random forest module, fastText, TinySVM, etc. (2) When generated by AI

[0209] The evaluation unit 134 provides the generating AI with the i-th unit of judgment and a prompt requesting it to determine whether or not the information represents a fact, and obtains the result of the judgment of whether or not the i-th unit of judgment represents a fact from the generating AI. The prompt is, for example, "Is the following information information that represents a fact? Or is it not information that represents a fact? Output '1' if it is information that represents a fact, and output '0' if it is not information that represents a fact. <Information>". In the prompt, the information enclosed in "<" and ">" (in this case, <Information>) is a variable, and in this case, the i-th unit of judgment is assigned to it.

[0210] The evaluation unit 134 may also use other algorithms for clustering information to obtain a determination result on whether or not the i-th judgment unit is factual information.

[0211] (Step S805) The evaluation unit 134 temporarily stores the i-th judgment unit in a buffer (not shown). Here, it is preferable for the evaluation unit 134 to vectorize the i-th judgment unit, obtain a fact vector, and temporarily store the fact vector in a buffer (not shown).

[0212] (Step S806) The evaluation unit 134 increments counter i by 1. The process returns to step S802.

[0213] Next, an example of the result evaluation process in step S604 will be explained using the flowchart in Figure 9.

[0214] (Step S901) The evaluation unit 134 obtains a result evaluation prompt from the prompt management unit 111.

[0215] (Step S902) The evaluation unit 134 passes the result evaluation prompt to the generating AI.

[0216] (Step S903) The evaluation unit 134 determines whether or not an answer has been obtained from the generating AI. If an answer has been obtained, the unit proceeds to step S904; otherwise, the unit proceeds to step S903.

[0217] (Step S904) The evaluation unit 134 obtains the result evaluation included in the response. It returns to the higher-level processing.

[0218] The following describes a specific example of the operation of information system A in this embodiment.

[0219] Currently, the prompt management unit 111 of the information processing device 1 stores the prompt management table shown in Figure 10. The prompt management table manages one or more records that have an "ID", "prompt identifier", "phase", and "prompt template". "ID" is information that identifies the record. "Prompt identifier" is the name of the prompt. "Phase" indicates one of the phases in a series of phases in a sales role-play where the prompt is used. "Prompt template" is the prompt template. As mentioned above, the prompt template can be considered to contain the prompt. The strings enclosed in "<" and ">" in the prompt template are variables. The series of phases in a sales role-play are the "persona setting" phase, the "role-playing" phase, and the "evaluation" phase.

[0220] Furthermore, Figure 11 shows the sales management database 41 of the first data management device 4. The sales management DB 41 manages one or more records that have "ID", "Contact Person Information", and "Customer Information". "Contact Person Information" has "Contact Person ID", "Name", "Company", and "Department". "Customer Information" has "Contact Person", "Position", "Company", "Department", "Gender", "Age", "Department", "Gender", "URL", "Responsible Person", and "Meeting Date". In "Customer Information", "Contact Person" is the name of the contact person of the sales partner. "URL" is the URL of the homepage of the company to which the contact person belongs. "Responsible Person" is the name of the responsible person of the organization to which the contact person belongs. "Meeting Date" is the date on which the sales representative identified by "Contact Person ID" and the customer corresponding to the customer information conducted a meeting. One or more dates are stored in "Meeting Date". Furthermore, the first data management device 4 in this case is a Salesforce server.

[0221] Figure 12 shows the business opportunity management database 42 of the second data management device 4. The business opportunity management DB 42 manages one or more records that have "ID", "person in charge information", and "business partner information". "Person in charge information" has "person in charge ID", "name", "company", and "department". "Business partner information" has "partner ID", "name", "position", "company", and "business opportunity information". "Business opportunity information" has "business opportunity date and time", "full information", and "summary". "Business opportunity date and time" is the time period during which the business opportunity took place or the start time of the business opportunity. "Full information" is the text of all the audio from both the person in charge and the business partner in the business opportunity conducted via web conference. "Summary" is the text that summarizes the full information. Note that "summary" is information obtained from the generating AI by, for example, providing the generating AI with all the information and a prompt obtained from the prompt template "Please summarize the following business opportunity: [Business Opportunity]<Full Information>". The second data management device 4 is, in this context, a server (for example, an amptalk server) where deal information is recorded by amptalk's service, "amptalk assist" (see URL "https: / / amptalk.co.jp / product / assist").

[0222] Furthermore, the business partner management database 43 of the data management device 4 is assumed to be the same as the sales management database 41 of the first data management device 4.

[0223] Furthermore, the document management unit 112 of the information processing device 1 stores the document database management table shown in Figure 13. The document database management table is a table that manages information for accessing the document databases 44 of one or more data management devices 4. The document database management table can be said to be, for example, a table that manages the location of sales materials for each company. The document database management table manages one or more records that have "ID," "user identification information," and "document identification information." The "user identification information" has "company name" and "person in charge." The "person in charge" is the name of the person in charge. The "document identification information" in this case is the URL for accessing the sales material information. The destination of this URL may be a single piece of sales material information, or it may be a folder containing two or more pieces of sales material information.

[0224] In the above situation, let's assume that user "Tanaka A" (hereinafter referred to as "User A") entered a start command from terminal device 2.

[0225] Next, terminal device 2 receives the start command and transmits the start command, including the user identifier (person in charge ID) "P01", to information processing device 1.

[0226] The receiving unit 12 of the information processing device 1 receives a start instruction from user A's terminal device 2. Next, the processing unit 13 obtains the user identifier "P01" included in the start instruction. Then, the processing unit 13 determines that the start instruction does not contain any recipient identification information.

[0227] Next, the processing unit 13 uses the user identification information (here, "P01") to retrieve four counterparty identification pieces that correspond to "P01" from the Salesforce server (data management device 4) which has a counterparty management database 43 (here, the sales management database 41 in Figure 11). Here, the counterparty identification piece is the "person in charge," but the processing unit 13 also retrieves the "company" and "department" in addition to the "person in charge" from the sales management database 41. Next, the processing unit 13 configures a screen for selecting one counterparty identification piece from the four counterparty identification pieces. Next, the candidate output unit 141 transmits this screen to user A's terminal device 2.

[0228] Next, User A's terminal device 2 receives and outputs the screen. An example of such a screen is shown in Figure 14. User A then selects "M11" from the four potential business partners. In other words, User A turns ON the toggle 1301 on the screen in Figure 14. Next, User A presses the "Send" button 1302. Terminal device 2 then receives the instruction for the "Send" button 1302. Next, the terminal processing unit 23 of terminal device 2 acquires the information 1301 "<Name>M11 <Company>C Company <Department>Purchasing Department" corresponding to the instruction. Next, the terminal processing unit 23 constructs the input information "<Name>M11 <Company>C Company <Department>Purchasing Department". Next, the terminal transmission unit 24 transmits the input information to the information processing device 1. Note that the input information includes the counterparty identification information "<Name>M11 <Company>C Company <Department>Purchasing Department".

[0229] Next, the unique information acquisition means 1321 of the information processing device 1 uses the counterparty identification information to obtain the counterparty's unique information from the sales management database 41 (Figure 11) "<Name> M11 <Company> Company C <Department> Purchasing Department <Gender> Male <Age> 41 <url>Retrieve URL11 <Responsible Person>M13.

[0230] Next, the unique information acquisition means 1321 uses the URL "URL11" of the homepage of the organization "Company C" to which the unique information belongs, to perform a web search and acquire the web page of Company C.

[0231] Next, the unique information acquisition means 1321 acquires business opportunity information that pairs user identification information "P01" with counterparty identification information "<Name>M11 <Company>C Company" from the business opportunity management database 42 (Figure 12). Here, the unique information acquisition means 1321 acquires the full information "file11" and summary "file12" of the record "ID=1" in Figure 12.

[0232] Next, the sales material acquisition means 1322 refers to the material DB management table in Figure 13 and determines the data management device 4 and material database 44 that correspond to the user identification information "<Person in Charge ID>P01 <Name>A. Tanaka <Company>X Company". In other words, the sales material acquisition means 1322 refers to the material DB management table in Figure 13 and obtains the material DB access information "URL_D1" that is paired with the company name "X Company". Then, the sales material acquisition means 1322 uses the URL "URL_D1" to access the folder indicated by "URL_D1" in the data management device 4 where X Company's sales materials are stored and obtains one or more sales materials.

[0233] Next, the prompt acquisition means 1323 acquires a prompt template from the prompt management table (Figure 10) that corresponds to the prompt identifier "Customer Persona Prompt" in the persona setting phase. Next, the prompt acquisition means 1323 acquires the variables of the prompt template (the prompt template with "ID=1" in Figure 10) <Company><Name><Position><Gender><Age> <url>The acquired information is substituted into the <Deal Information> and <Sales Material Information> sections, respectively, to construct the customer persona prompt. This customer persona prompt is shown in Figure 15. In Figure 15, each underlined section is a variable in the prompt template, and represents the acquired unique information, deal information, or sales material information.

[0234] Next, the AI ​​operation means 1325 provides the generating AI with a customer persona prompt (Figure 15) for setting the persona.

[0235] Next, the response acquisition unit 133 acquires the response from the generating AI. Then, the response output unit 142 transmits the response to user A's terminal device 2.

[0236] Next, terminal device 2 receives and outputs the response. An example of such output is shown in Figure 16. From this point onward, Tanaka A can engage in sales role-playing with a customer persona generated by an AI that embodies the role of M11 from company C.

[0237] Then, user A voice-inputs the following into terminal device 2: "M11, thank you very much for your help the other day. And thank you very much for taking the time to meet with me today." This input is a training input.

[0238] Next, terminal device 2 receives the training input and transmits it to information processing device 1.

[0239] Next, the input receiving unit 121 of the information processing device 1 receives training input from user A from the terminal device 2. Next, the processing unit 13 performs speech recognition processing on the training input of voice information and obtains training input in the form of a string. The training input from user A is 1701 in Figure 17. Next, the processing unit 13 determines that the termination condition is not met.

[0240] Next, the AI ​​operating means 1325 provides training input to the generating AI. Next, the answer acquisition unit 133 acquires a string response from the generating AI. Next, the processing unit 13 converts the acquired response into voice information. The answer output unit 142 transmits the voice information of the response to user A's terminal device 2.

[0241] Next, terminal device 2 receives the corresponding voice information and outputs it as voice. The outputted response is 1702 in Figure 17. Note that the information marked with "〇" (1702, 1704, 1706) is the response from the generating AI. Also, the information (1701, 1703, 1705) is the training input from user A.

[0242] Subsequently, the sales role-playing between User A and the generated AI proceeds through the same process as described above, and the processing unit 13 of the information processing device 1 determines that the sales role-playing has met the termination conditions.

[0243] Next, the evaluation unit 134 of the information processing device 1 obtains the result evaluation prompt "ID=3" (the prompt template "ID=3") shown in Figure 10. Next, the evaluation unit 134 provides the result evaluation prompt to the generating AI. Next, the evaluation unit 134 obtains the evaluation result from the generating AI. Next, the evaluation output unit 143 transmits the evaluation result to user A's terminal device 2.

[0244] Next, user A's terminal device 2 receives and outputs the evaluation results. An example of such output is shown in Figure 18. In Figure 18, accuracy evaluation information (contents of 1.) and result evaluation information (contents of 2.) are output.

[0245] As described above, according to this embodiment, by providing the AI ​​with unique information about the sales partner, it is possible to realize a sales role-playing experience that closely resembles an actual sales experience.

[0246] Furthermore, according to this embodiment, by obtaining unique information of actual sales clients from the sales management database 41 located in the data management device 4 and providing this unique information to the generating AI, it is possible to realize a sales role-playing experience that closely resembles an actual sales experience.

[0247] Furthermore, according to this embodiment, by providing the generating AI with information from the web page of the organization to which the sales target belongs, it is possible to realize a sales role-playing experience that closely resembles an actual sales experience.

[0248] Furthermore, according to this embodiment, by providing the AI ​​with personal information such as the names of sales targets, it is possible to realize sales role-playing that closely resembles actual sales experiences.

[0249] Furthermore, according to this embodiment, by providing the AI ​​with negotiation information from past business negotiations with sales partners, it is possible to realize sales role-playing that is very close to actual sales experience.

[0250] Furthermore, according to this embodiment, by providing the AI ​​with conversation information from past business negotiations with sales partners or summarized information of those conversations, it is possible to realize a sales role-playing experience that is very close to an actual sales experience.

[0251] Furthermore, according to this embodiment, by acquiring sales materials for target customers from an external data management device 4 and providing these sales materials to the generating AI, it becomes possible to perform sales role-playing with customer personas that understand the target customers, resulting in an experience that is closer to actual sales.

[0252] Furthermore, according to this embodiment, the user's role-playing can be evaluated using sales materials for the target of sales and the content of the user's role-playing.

[0253] The processing in this embodiment may be implemented in software. This software may be distributed via software download or the like. Alternatively, this software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments described herein. The software that implements the information processing device 1 in this embodiment is the following program. In other words, this program is a program that causes the computer to function as follows: an input receiving unit that receives input information including document identification information that identifies sales material information which is the material to be sold; an operation unit that retrieves sales material information corresponding to one or more document identification pieces from one or more document databases in which sales material information corresponding to one or more document identification pieces is stored, provides the sales material information to the generating AI, and gives the generating AI a customer persona prompt which is a prompt for the generating AI to become a customer persona which is the persona corresponding to the sales target; an answer acquisition unit that retrieves an answer corresponding to the customer persona prompt from the generating AI; and an answer output unit that outputs the answer obtained by the answer acquisition unit. The input receiving unit further receives training input which is input to advance the role-playing after the answer output unit has output an answer, the operation unit provides the training input to the generating AI, the answer acquisition unit retrieves an answer corresponding to the training input from the generating AI, and the answer output unit outputs the answer corresponding to the training input obtained by the answer acquisition unit.

[0254] Figure 19 is a block diagram of a computer system 300 that executes the program described herein to realize the various embodiments of the information processing device 1 described above.

[0255] In Figure 19, the computer system 300 includes a computer 301 with a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0256] In Figure 19, the computer 301 includes, in addition to the CD-ROM drive 3012, an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012, a ROM 3015 for storing programs such as boot-up programs, a RAM 3016 connected to the MPU 3013 for temporarily storing application program instructions and providing temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Although not shown here, the computer 301 may further include a network card for providing connectivity to a LAN.

[0257] The program that causes the computer system 300 to execute the functions of the information processing device 1, etc., as described above, may be stored on the CD-ROM 3101, inserted into the CD-ROM drive 3012, and then transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into the RAM 3016 during execution. The program may also be loaded directly from the CD-ROM 3101 or the network.

[0258] The program does not necessarily have to include an operating system (OS) or third-party program that causes the computer 301 to execute the functions of the information processing device 1, etc., as described above. The program only needs to include the instruction portion that calls the appropriate function (module) in a controlled manner and obtains the desired result. How the computer system 300 operates is well known, so a detailed explanation is omitted.

[0259] In the above program, steps such as sending information and receiving information do not include hardware-based processing, such as processing performed by a modem or interface card in the transmission step (processing that can only be performed by hardware).

[0260] Furthermore, the computer running the above program may be a single computer or multiple computers. In other words, it may perform centralized processing or distributed processing.

[0261] Furthermore, it goes without saying that in each of the above embodiments, two or more communication means present in a single device may be physically implemented in a single medium.

[0262] Furthermore, in each of the above embodiments, each process may be implemented by centralized processing by a single device, or by distributed processing by multiple devices.

[0263] It goes without saying that the present invention is not limited to the embodiments described above, and various modifications are possible, all of which are also included within the scope of the present invention. [Industrial applicability]

[0264] As described above, the information processing device 1 according to the present invention has the effect of realizing sales role-playing that closely resembles actual sales experience, assuming a customer with knowledge of the target of sales, and is useful as a server for training sales personnel. [Explanation of Symbols]

[0265] A Information Systems 1. Information Processing Device 2 Terminal devices 3 Generation AI device 4. Data Management Device 11 Storage Unit 12 Reception Department 13 Processing Unit 14 Output section 21 Terminal storage section 22 Terminal Reception Section 23 Terminal Processing Unit 24 Terminal transmission unit 25 Receiving part of the terminal 26 Terminal output section 41 Sales Management Database 41 Sales Management Database 42 Business Negotiation Management Database 42 Business Negotiation Management DB 43 Business Negotiation Partner Management Database 44 Document Database 111 Prompt Management Department 112 Document Management Department 121 Input Reception Department 122 Instruction Reception Department 131 Candidate Acquisition Department 132 Operation Department 133 Answer Acquisition Department 134 Evaluation Department 141 Candidate Output Department 142 Answer Output Department 143 Evaluation Output Department 1321 Unique Information Acquisition Means 1322 Sales Document Acquisition Means 1323 Prompt Acquisition Means 1325 AI Operation Means< / url> < / url>

Claims

1. An information processing device that uses generational AI to support sales role-playing, An input receiving unit that receives input information including document identification information that identifies sales materials that are the target of sales, An operation unit that retrieves sales material information corresponding to one or more document identification pieces from one or more document databases in which sales material information corresponding to one or more document identification pieces is stored, provides the sales material information to the generating AI, and provides the generating AI with a customer persona prompt, which is a prompt for the generating AI to become a customer persona that corresponds to a sales target, A response acquisition unit that acquires a response corresponding to the customer persona prompt from the generated AI, The system comprises a response output unit that outputs the response acquired by the response acquisition unit, The aforementioned input receiving unit is After the response output unit outputs a response, it further accepts training input, which is input to advance the role-playing, The aforementioned operating unit is The training input is provided to the generating AI. The aforementioned response acquisition unit, The AI ​​generates the response corresponding to the training input, The aforementioned response output unit is: An information processing device that outputs the response corresponding to the training input acquired by the response acquisition unit.

2. The aforementioned input receiving unit is The system receives user identification information that identifies a user who performs a sales role-playing exercise with the aforementioned AI, and uses this user identification information to retrieve document identification information from a document management unit that stores document identification information paired with two or more user identification pieces. The aforementioned operating unit is A sales material acquisition means that acquires the sales material information corresponding to the document identification information acquired by the input receiving unit from the document database, The information processing apparatus according to claim 1, further comprising: an AI operation means for providing the sales material information acquired by the sales material acquisition means to the generating AI, and an AI operation means for providing the generating AI with a previous customer persona prompt.

3. Each of the two or more data databases mentioned above resides in a data management device different from the information processing device. The aforementioned means of obtaining sales materials is, The information processing device according to claim 2, which accesses the data management device corresponding to the document identification information acquired by the input receiving unit and acquires the sales document information.

4. An evaluation unit obtains the evaluation results of the user's sales role-playing using the training input and sales material information received by the input reception unit, The information processing apparatus according to claim 1, further comprising: an evaluation output unit that outputs the evaluation results acquired by the evaluation unit.

5. The evaluation unit, The information processing device according to claim 4, which acquires the evaluation result including one or more pieces of information from among the sales data information, accuracy evaluation information indicating an evaluation of the accuracy of the training input, and result evaluation information relating to the results of sales.

6. The aforementioned input receiving unit is We accept input information that includes contact identification information to identify sales partners. The aforementioned operating unit is The information processing apparatus according to claim 1, wherein the input receiving unit obtains unique information of the business partner based on the counterparty identification information received from a business management database that stores counterparty information having unique information corresponding to two or more counterparty identification information, provides said unique information to the generating AI, and the generating AI provides the customer persona prompt to the generating AI.

7. The aforementioned input receiving unit is The system receives the input information, which includes the user identification information of a user who performs a sales role-playing exercise with the generated AI, and the counterparty identification information that identifies the sales target. The aforementioned operating unit is Unique information acquisition means that acquires the business negotiation information corresponding to the counterparty identification information and user identification information received by the input receiving unit from a business negotiation management database which stores past business negotiation information corresponding to user identification information and one or more counterparty identification information, The information processing apparatus according to claim 1, further comprising: an AI operation means that provides the business negotiation information acquired by the unique information acquisition means to the generating AI, and an AI operation means that provides the customer persona prompt to the generating AI.

8. An instruction receiving unit that receives instructions for selecting a recipient, including user identification information, A candidate acquisition unit acquires one or more counterparty identification pieces from a business partner management database, which stores one or more counterparty identification pieces that identify business partners in association with one or more user identification pieces, that are paired with the user identification pieces in the counterparty selection instruction received by the instruction receiving unit. The system further comprises a candidate output unit that outputs the one or more opponent identification pieces acquired by the candidate acquisition unit, The aforementioned input receiving unit is An information processing apparatus according to any one of claims 1 to 7, which receives input information including one of the aforementioned counterparty identification information from among the one or more counterparty identification information.

9. An information processing method comprising all the steps performed by the information processing device described in any one of claims 1 to 8.

10. Computers, A program for causing an information processing device to function as described in any one of claims 1 to 8.

Images