Information processing device, information processing method, and program

Abstract

To provide an information processing device that realizes a sales role play similar to an actual sales experience assuming a sales target who has knowledge. [Solution] The information processing device 1 is equipped with an input receiving unit 121 that receives material identification information that identifies sales material information, an operation unit 132 that acquires sales material information for the material identification information from one or more material databases 44 in which sales material information corresponding to each of one or more material identification information is stored, and provides the sales material information and a customer persona prompt to the generation AI, an answer acquisition unit 133 that acquires an answer from the generation AI, and an answer output unit 142 that outputs the answer, and further accepts training input that is input to advance the role-play, provides the training input to the generation AI, acquires an answer from the generation AI, and outputs the answer.

Description

[Technical field]

[0001] The present invention relates to an information processing device or the like that supports a user in performing a simulated sales role-play. [Background technology]

[0002] Previously, there was technology that allowed role-playing using ChatGPT (generative AI) (see Non-Patent Document 1). [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Magical conversation script generation, ChatGPT prompt that turns a reluctant partner into one who wants to try, Gathering Customers Research Institute [online], October 10, 2023, URL:<https: / / www.active-note.jp / chatgptprompt / will / > ,[Retrieval date: December 16, 2020] Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, it has not been possible to realize a sales role-play that is close to a real sales experience. In particular, in the conventional technology, it has not been possible to realize a sales role-play that is close to a real sales experience that assumes a sales target with knowledge. [Means for solving the problem]

[0005] The information processing device of the first invention is an information processing device that supports sales role-playing using a generation AI, and is equipped with an input accepting unit that accepts input information including material identification information that identifies sales material information, which is material for sales, and an operation unit that acquires sales material information corresponding to the material identification information from one or more material databases in which sales material information corresponding to each of one or more material identification information is stored, provides the sales material information to the generation AI, and provides the generation AI with a customer persona prompt, which is a prompt for the generation AI to become a customer persona, which is a persona corresponding to the sales partner, an answer acquisition unit that acquires an answer corresponding to the customer persona prompt from the generation AI, and an answer output unit that outputs the answer acquired by the answer acquisition unit, and the input accepting unit further accepts training input, which is input to advance the role-playing after the answer output unit outputs the answer, and the operation unit provides the training input to the generation AI, the answer acquisition unit acquires an answer corresponding to the training input from the generation AI, and the answer output unit outputs the answer corresponding to the training input acquired by the answer acquisition unit.

[0006] With this configuration, a sales role-play that is close to a real sales experience, assuming a sales target that has knowledge, can be realized.

[0007] In addition, the information processing device of the second invention is an information processing device in which, compared to the first invention, the input receiving unit receives user identification information identifying a user who performs a sales role-play with the generation AI, and uses the user identification information to obtain material identification information from a material management unit in which material identification information paired with two or more user identification information is stored, and the operation unit is an information processing device that includes a sales material acquisition means for acquiring sales material information corresponding to the material identification information acquired by the input receiving unit from a material database, and an AI operation means for providing the sales material information acquired by the sales material acquisition means to the generation AI, and providing a previous customer persona prompt to the generation AI.

[0008] With this configuration, it is possible to select and obtain material identification information about a sales target, and by using the material identification information, it is possible to realize a sales role-play that is close to an actual sales experience, assuming that the sales target is someone who has knowledge of the sales target.

[0009] In addition, in the information processing device of the third invention, compared to the second invention, each of the two or more material databases exists in a data management device different from the information processing device, and the sales material acquisition means is an information processing device that accesses the data management device corresponding to the material identification information acquired by the input receiving unit and acquires the sales material information.

[0010] With this configuration, a sales role-play that is close to a real sales experience, assuming a customer who has knowledge about the sales target, can be realized.

[0011] In addition, the information processing device of the fourth invention is an information processing device that, compared to the first invention, further includes an evaluation unit that obtains an evaluation result of the user's sales role-play using the training input and sales material information received by the input receiving unit, and an evaluation output unit that outputs the evaluation result obtained by the evaluation unit.

[0012] With this configuration, the user's role-playing can be evaluated using the sales materials of the sales target and the content of the user's role-playing.

[0013] In addition, the information processing device of the fifth invention is an information processing device in which the evaluation unit obtains evaluation results including one or more of the following information: accuracy evaluation information indicating an evaluation regarding the accuracy of training input based on sales material information, and result evaluation information regarding sales results.

[0014] With this configuration, the accuracy and results of the role-play can be evaluated using the sales materials of the sales target and the content of the user's role-play.

[0015] In addition, the information processing device of the sixth invention is an information processing device in which, compared to the first invention, an input receiving unit receives input information including party identification information that identifies a sales partner, and an operating unit obtains unique information of the sales partner based on the party identification information received by the input receiving unit from a sales management database that stores party information having unique information corresponding to each of two or more party identification information, provides the unique information to the generation AI, and the generation AI provides a customer persona prompt to the generation AI.

[0016] With this configuration, by providing the generation AI with the unique information of the sales partner obtained from the data management device, it is possible to realize a sales role-play that is closer to a real sales experience.

[0017] In addition, the information processing device of the seventh invention is an information processing device in which, compared to the first invention, the input receiving unit receives the input information including partner identification information that identifies a sales partner and corresponds to user identification information of a user who role-plays a sales situation with the generation AI, and the operation unit is equipped with a unique information acquisition means for acquiring negotiation information corresponding to the partner identification information and user identification information accepted by the input receiving unit from a negotiation management database that stores past negotiation information corresponding to the user identification information and one or more partner identification information, and AI operation means for providing the negotiation information acquired by the unique information acquisition means to the generation AI and providing a customer persona prompt to the generation AI.

[0018] With this configuration, by providing the generation AI with sales negotiation information from past sales negotiations with sales partners, it is possible to realize a sales role-play that is very close to an actual sales experience.

[0019] In addition, the information processing device of the eighth invention, relative to any one of the first to seventh inventions, 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 pairs with the user identification information held by the partner selection instruction accepted by the instruction receiving unit from a negotiation partner management database in which one or more partner identification information that identifies a sales partner is stored in correspondence with each of the one or more user identification information, and a candidate output unit that outputs the one or more partner identification information acquired by the candidate acquisition unit, and the input receiving unit is an information processing device that accepts input information including one partner identification information from the one or more partner identification information.

[0020] With this configuration, potential sales partners are automatically acquired and presented to the user, allowing the user to easily begin a sales role-play that is close to an actual sales experience.

[0021] The information processing device of the present invention is an information processing device that supports sales role-playing using a generation AI, and is equipped with an input receiving unit that receives input information including party identification information that identifies a sales party, an operation unit that acquires unique information of the sales party based on the party identification information received by the input receiving unit from a sales management database that stores party information having unique information corresponding to each of two or more party identification information, provides the unique information to the generation AI, and provides the generation AI with a customer persona prompt that is a prompt for the generation AI to become a customer persona, which is a persona corresponding to the sales party, an answer acquisition unit that acquires an answer corresponding to the customer persona prompt from the generation AI, and an answer output unit that outputs the answer acquired by the answer acquisition unit, and the input receiving unit further accepts training input, which is input that advances the role-playing after the answer output unit outputs the answer, and the operation unit provides the training input to the generation AI, the answer acquisition unit acquires an answer corresponding to the training input from the generation AI, and the answer output unit outputs the answer corresponding to the training input acquired by the answer acquisition unit.

[0022] With this configuration, by providing the generation AI with unique information about the sales partner obtained from the data management device, a sales role-play that is close to an actual sales experience can be realized.

[0023] In addition, in the information processing device of the present invention, compared to the above invention, the input receiving unit receives input information having partner identification information that corresponds to user identification information of a user who role-plays a sales role with the generation AI as the partner, the sales management database exists in a data management device that is not an information processing device, and stores partner information having unique information that corresponds to one or more partner identification information that pairs with the user identification information, and the operation unit is an information processing device that includes a unique information acquisition means for acquiring from the sales management database the unique information that corresponds to the partner identification information and user identification information accepted by the input receiving unit, and an 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 this configuration, it is possible to realize a sales role-play that is close to an actual sales experience by obtaining unique information of actual sales counterparties from a sales management database stored in a data management device and providing the unique information to the generation AI.

[0025] Further, in the information processing device of the present invention, in addition to the above-mentioned invention, the unique information acquisition means acquires unique information including a URL or a web page corresponding to the party identification information accepted by the input acceptance unit from a sales management database.

[0026] With this configuration, by providing the generation AI with information about the web page of the organization to which the sales partner belongs, a sales role-play that is close to an actual sales experience can be realized.

[0027] In addition, in the information processing device of the present invention, compared to the above-mentioned invention, the unique information acquisition means is an information processing device that acquires unique information from a sales management database, the unique information including one or more pieces of information among the sales partner's name, the partner's organization name, the partner's job title, and the partner's department name, which correspond to the partner identification information accepted by the input acceptance unit.

[0028] With this configuration, by providing personal information such as the name of the sales partner to the generation AI, a sales role-play that is close to an actual sales experience can be realized.

[0029] In addition, in the information processing device of the present invention, in comparison with the above invention, an input receiving unit receives input information corresponding to user identification information of a user who role-plays a sales role with the generation AI as a partner, and the operation unit is an information processing device that includes a unique information acquisition means for acquiring unique information including negotiation information corresponding to the partner identification information and user identification information accepted by the input receiving unit from a negotiation management database that stores past negotiation information corresponding to the user identification information and one or more partner identification information, and an 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.

[0030] With this configuration, by providing the generation AI with sales negotiation information from past sales negotiations with sales partners, it is possible to realize a sales role-play that is very close to an actual sales experience.

[0031] Furthermore, in accordance with the above-described information processing device of the present invention, the business negotiation information includes conversation information of a business negotiation that has been held in the past, or summary information that is a summary of the conversation information of a business negotiation that has been held in the past.

[0032] With this configuration, by providing the generation AI with conversation information from past business negotiations with a sales partner or summary information summarizing the conversation, it is possible to realize a sales role-play that is very close to an actual sales experience.

[0033] In addition, in the information processing device of the present invention, in comparison with the above invention, an input receiving unit receives input information including material identification information that identifies sales material information, which is material for sales, and an operation unit is an information processing device that includes: a sales material acquisition means for acquiring sales material information corresponding to the material identification information accepted by the input receiving unit from one or more material databases in which sales material information corresponding to one or more material identification information is stored; and an AI operation means for providing the sales material information acquired by the sales material acquisition means to a generation AI and providing the customer persona prompt to the generation AI.

[0034] With this configuration, by providing the sales materials of the sales target to the generation AI, it is possible to realize sales role-playing for a customer persona that understands the sales target, resulting in an experience that is close to actual sales.

[0035] In addition, in the information processing device of the present invention, compared to the above invention, the material database is present in a data management device which is not an information processing device, the input accepting unit refers to a material management unit in which material identification information paired with one or more user identification information is managed, and acquires the material identification information paired with the user identification information, and the sales material acquisition means is an information processing device which acquires sales material information corresponding to the material identification information acquired by the input accepting unit from the material database.

[0036] With this configuration, sales materials for the sales target can be obtained from an external data management device and the sales materials can be provided to the generation AI, enabling a sales role-play for a customer persona that understands the sales target, resulting in an experience that is closer to actual sales.

[0037] In addition, the information processing device of the present invention is an information processing device that, in addition to the above-mentioned invention, further includes an evaluation unit that obtains an evaluation result of the user's sales role-play using the training input and sales material information received by the input receiving unit, and an evaluation output unit that outputs the evaluation result obtained by the evaluation unit.

[0038] With this configuration, the user's role-playing can be evaluated using the sales materials of the sales target and the content of the user's role-playing.

[0039] In addition, with respect to the above-mentioned invention, the information processing device of the present invention is an information processing device in which the evaluation unit obtains evaluation results including one or more of the following information: accuracy evaluation information indicating an evaluation regarding the accuracy of training input based on sales material information, and result evaluation information regarding sales results.

[0040] With this configuration, the user's role-playing can be evaluated using the sales materials of the sales target and the content of the user's role-playing.

[0041] In addition, in accordance with the above-mentioned invention, the information processing device of the present invention further includes 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 pairs with the user identification information held by the partner selection instruction accepted by the instruction receiving unit from a negotiation partner management database in which one or more partner identification information that identifies a sales partner is stored in correspondence with each of one or more user identification information, and a candidate output unit that outputs the one or more partner identification information acquired by the candidate acquisition unit, and the input receiving unit is an information processing device that accepts input information including one partner identification information from the one or more partner identification information.

[0042] With this configuration, potential sales partners are automatically acquired and presented to the user, allowing the user to easily begin a sales role-play that is close to an actual sales experience. Effect of the Invention

[0043] According to the information processing device of the present invention, it is possible to realize a sales role-play that is close to an actual sales experience, assuming that the sales target is a knowledgeable person. [Brief description of the drawings]

[0044] [Figure 1] Conceptual diagram of information system A in embodiment 1. [Diagram 2]Block diagram of Information System A [Diagram 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. [Diagram 5] A flowchart for explaining an example of a party identification information acquisition process [Figure 6] A flowchart illustrating an example of the evaluation process [Figure 7] A flowchart for explaining an example of the accuracy evaluation process [Figure 8] A flowchart for explaining an example of the fact extraction process [Figure 9] A flowchart illustrating an example of the result evaluation process. [Figure 10] A diagram showing the prompt management table [Figure 11] A diagram showing an example of the sales management database 41. [Figure 12] A diagram showing an example of the business negotiation management database 42. [Figure 13] An example of the database management table for the same document is shown below. [Figure 14] A diagram showing an example of the screen [Figure 15] Example customer persona prompts [Figure 16] A diagram showing an example of the output [Figure 17] A diagram showing an example of the output [Figure 18] A diagram showing an example of the output [Figure 19] Block diagram of the computer system DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0045] Hereinafter, an embodiment of an information processing device and the like will be described with reference to the drawings. Note that, in the embodiments, components with the same reference numerals perform similar operations, and therefore repeated description may be omitted.

[0046] (Embodiment 1) In this embodiment, an information processing device is described that realizes a sales role-play in which a customer persona is used as the sales partner by providing one or more types of information of the sales partner's unique information and business negotiation information to a generation AI. Note that the unique information is, for example, unique information of the sales partner in a sales management DB that exists in an external device different from the information processing device. The unique information of the sales partner in the sales management DB is, for example, web page information of the organization to which the sales partner belongs, and personal information such as the sales partner's name and job title. The business negotiation information is, for example, information of past business negotiations with the sales partner in the business negotiation management DB.

[0047] In this embodiment, an information processing device is described that realizes a sales role-play in which sales materials stored in an external device are provided to a generating AI and a customer persona who understands the sales target is used as the sales partner.

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

[0049] In this embodiment, an information processing device that automatically acquires one or more negotiation partner candidates corresponding to a user and sets the negotiation partner to the negotiation partner selected by the user will be described.

[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 not important. Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, or information Y may be included in information X, etc.

[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 for information Z, etc., and is sufficient as long as information Z can be accessed.

[0052] 1 is a conceptual diagram of an information system A according to the present embodiment. The information system A includes 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] The information processing device 1 is a device that realizes a sales role-play with a user. The information processing device 1 is, for example, a cloud server or an ASP server, but the type is not important. The information processing device 1 may be a terminal. If the information processing device 1 is a terminal, the information system A does not require a terminal device 2. If the information processing device 1 is a terminal, it can be considered that the information processing device 1 also functions as the terminal device 2. If the information processing device 1 is a terminal, the information processing device 1 is, for example, a so-called personal computer, smartphone, or tablet terminal, but the type is not important.

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

[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 important. If the information processing device 1 has the generation AI function, the generation AI device 3 is not necessary. Note that the generation AI device 3 is appropriately referred to as the generation AI. Furthermore, the information processing device 1 may have the generation AI function. In such a case, the generation AI device 3 is not necessary.

[0056] The data management device 4 is a device having databases such as a sales management database, a negotiation management database, and a document database, which will be described later. The data management device 4 is, for example, a cloud server or an ASP server, but the type does not matter. It is preferable that the data management device 4 is a device different from the information processing device 1. The data management device 4 having the sales management database is, for example, a Salesforce (registered trademark) server or a Cybozu (registered trademark) server. The data management device 4 having the negotiation management database is, for example, an amptalk (registered trademark) server or a zoom (registered trademark) server. The data management device 4 having the document database is a server of a company to which one or more users belong, and is a server that manages the company's own documents. It is preferable that the data management device 4 having the sales management database, the data management device 4 having the negotiation management database, and the data management device 4 having the document database are each separate devices.

[0057] Fig. 2 is a block diagram of an information system A according to the present embodiment, and Fig. 3 is a block diagram of an information processing device 1.

[0058] The information system A includes an information processing device 1, a terminal device 2, a generating AI device 3, and a data management device 4.

[0059] The information processing device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 includes a prompt management unit 111, and a material management unit 112. The reception unit 12 includes an input reception unit 121, and an instruction reception unit 122. The processing unit 13 includes a candidate acquisition unit 131, an operation unit 132, an answer acquisition unit 133, and an evaluation unit 134. The operation unit 132 includes unique information acquisition means 1321, sales material acquisition means 1322, prompt acquisition means 1323, and AI operation means 1325. The output unit 14 includes 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 reception unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal reception unit 25, and a terminal output unit .

[0061] Each of the one or more data management devices 4 includes one or more databases selected from a sales management database 41, a negotiation management database 42, a negotiation partner management database 43, and a material database 44. Two or more databases selected from the sales management database 41, the negotiation management database 42, the negotiation partner management database 43, and the material database 44 may be implemented as a single database. The negotiation partner management database 43 is, for example, the sales management database 41 or the negotiation management database 42. Here, the database is, for example, a relational database, but may also be a NoSQL database, an object-oriented database, or the like. The database may also be a folder or a file. The database may also be understood to mean something like a collection of data.

[0062] Various types of information are stored in the storage unit 11 constituting the information processing device 1. The various types of information are, for example, a prompt template (to be described later) and material identification information (to be 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 a prompt to be given to a generation AI. A prompt template may be a prompt to be given to a generation AI. A prompt template has, for example, variables for substituting one or more pieces of input information entered by a user. A prompt template has, for example, variables for substituting specific information (described later) and sales document information (described later).

[0064] The generated AI is the generated AI device 3, or a program of the generated AI device, or a program in the information processing device 1. In other words, the program of the generated AI may be stored in the storage unit 11. In such a case, the generated AI device 3 is not required for the information system A. The generated AI is usually the other party in the role-play.

[0065] The prompts given to the generation AI include, for example, customer persona prompts, fact-judgment prompts, and outcome evaluation prompts.

[0066] A customer persona prompt is a prompt that enables the generation AI to create a customer persona that corresponds to the sales partner.

[0067] The fact determination prompt is a prompt that requests a user to determine whether or not information contained in sales literature information, which will be described later, is factual.

[0068] The result evaluation prompt is a prompt for obtaining the evaluation result of the user's sales role-play.

[0069] One or more pieces of material identification information are stored in the material management unit 112. The material identification information here is paired with the user identification information.

[0070] The material identification information is information that identifies the sales material information that is the material for the sales target. The material identification information is, for example, a URL that identifies the location where the sales material information is stored, information that identifies the data management device 4 and the folder in which the sales material information is stored, and an API for acquiring the sales material information.

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

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

[0073] Sales document information is materials for sales targets. Sales targets are targets to which a user is making sales. Sales targets are, for example, products and services. Sales document information is, for example, manuals, sales presentation materials, and news releases. Sales document information is usually a file, but the data structure is not important.

[0074] The reception unit 12 receives various instructions and information, such as a start instruction, input information (to be described later), training input (to be described later), and a partner selection instruction (to be described later).

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

[0076] Here, acceptance usually means receiving from the terminal device 2 information transmitted via a wired or wireless communication line, but may also be a concept including acceptance of information input from an input device such as a keyboard, mouse, or touch panel, acceptance of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory, etc. The various instructions and information here may be acquired as long as they are received.

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

[0078] The input information is information about the other party in the sales role-play. The input information includes, for example, party identification information that identifies the sales partner. The input information accepted by the input accepting unit 121 corresponds, for example, to user identification information of a user who performs a sales role-play with the generating AI as the other party. The input information includes, for example, material identification information that identifies sales literature information, which is a material for the sales target. The input information includes, for example, material identification information that identifies sales literature information, which is a material for the sales target.

[0079] The input receiving unit 121 may receive input information including the material identification information by acquiring the material identification information using user identification information associated with the input information received by the input receiving unit 121.

[0080] The input receiving unit 121 further receives a training input after the answer output unit 142 outputs an answer. The training input is an input from a user who advances the role play. The training input is an input from a user that corresponds to an answer from the generation AI.

[0081] The input receiving unit 121 receives input information including one piece of party identification information from one or more pieces of party identification information.

[0082] The instruction receiving unit 122 receives various instructions, such as a start instruction and a partner selection instruction.

[0083] The partner selection instruction is an instruction to select a negotiation partner. The partner selection instruction includes user identification information of the user who will perform the sales role-play. The partner selection instruction usually results in the acquisition of partner identification information.

[0084] The processing unit 13 performs various types of processing. The various types of processing are, for example, processing performed by a candidate acquisition unit 131, an operation unit 132, an answer acquisition unit 133, and an evaluation unit .

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

[0086] The processing unit 13 converts, for example, a response that is a character string acquired by the generation AI into a response of voice information. Note that the process of converting the response acquired by the generation AI into a voice response may be performed by the terminal device 2.

[0087] The candidate acquisition unit 131 acquires one or more pieces of partner identification information that are paired with the user identification information included in the partner selection instruction accepted by the instruction acceptance unit 122 from the negotiation partner management database 43. Note that the negotiation partner management database 43 may also be the sales management database 41 or the negotiation management database 42, for example.

[0088] The other party identification information is information that identifies the other party in a business negotiation. The other party identification information is, for example, the name of the other party in a business negotiation. The other party identification information is, for example, the organization name and name of the other party in a business negotiation. The other party identification information is, for example, the ID of the other party in a business negotiation. The other party identification information is, for example, the organization name of the other party in a business negotiation. The other party identification information does not have to be information that identifies a single other party (person), but may also be information that identifies the organization of the other party in a business negotiation.

[0089] The operation unit 132 acquires unique information of the sales partner based on the partner identification information accepted by the input acceptance unit 121. Then, the operation unit 132 provides the unique information to the generation AI. The operation unit 132 also provides the generation AI with a customer persona prompt, which is a prompt for the generation AI to become a customer persona, which is a persona corresponding to the sales partner.

[0090] The operation unit 132, for example, uses the counterpart identification information as a key to obtain unique information of the sales counterpart from the sales management database 41. The operation unit 132 normally obtains a customer persona prompt from the prompt management unit 111 and provides it to the generation AI.

[0091] The operation unit 132, for example, substitutes the specific information into a template prompt of a customer persona prompt, constructs a customer persona prompt, and provides the customer persona prompt to the generation AI.

[0092] Unique information is information unique to a sales partner. Unique information is, for example, one or two of the following types of information: personal information and business negotiation information. Personal information is personal information about a sales partner. Personal information is, for example, the sales partner's name, job title, age, gender, email address, telephone number, the name of the organization to which the sales partner belongs (e.g., a company, local government), the URL of the organization's homepage, and the organization's homepage (which may include a web page of the organization's site). Note that a homepage may also be called a web page.

[0093] The business negotiation information is information about past business negotiations with a sales partner. The business negotiation information is, for example, information recorded or / and filmed during a business negotiation held in a web conference or over the phone (overall business negotiation information), business negotiation conversation information, or summary information that summarizes the business negotiation using the audio information of the overall business negotiation information.

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

[0095] Unique information acquisition means 1321 constituting operation unit 132 acquires unique information. The following describes the cases where personal information, which is part of the unique information, and business negotiation information are acquired. (1) When acquiring personal information

[0096] The unique information acquiring means 1321 acquires the other party identification information included in the input information accepted by the input accepting unit 121. The unique information acquiring means 1321 also acquires the user identification information corresponding to the input information accepted by the input accepting unit 121. Next, the unique information acquiring means 1321 acquires personal information corresponding to the other party identification information and the user identification information from the sales management database 41. It is preferable that the sales management database 41 exists in the data management device 4 which is an external device of the information processing device 1.

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

[0098] It is preferable that the unique information acquisition means 1321 acquires from the sales management database 41 personal information including a URL or a web page corresponding to the other party identification information accepted by the input acceptance unit 121 .

[0099] The unique information acquiring means 1321 acquires, for example, a URL corresponding to the counterpart identification information accepted by the input accepting unit 121. Next, the unique information acquiring means 1321 acquires, for example, a web page of the organization of the sales counterpart identified by the counterpart identification information, using the URL.

[0100] It is preferable that the unique information acquisition means 1321 acquires personal information from the sales management database 41, including the name of the sales partner corresponding to the partner identification information accepted by the input acceptance unit 121, and one or more pieces of information including the name of the partner's organization, the partner's job title, or the name of the partner's department. (2) When acquiring business negotiation information

[0101] The unique information acquisition means 1321 acquires counterpart identification information included in the input information accepted by the input acceptance unit 121. The unique information acquisition means 1321 also acquires user identification information corresponding to the input information accepted by the input acceptance unit 121. Next, it is preferable for the unique information acquisition means 1321 to acquire negotiation information corresponding to the counterpart identification information and the user identification information from the negotiation management database 42. The negotiation information corresponding to the counterpart identification information and the user identification information is information on past negotiations between a sales partner identified by the counterpart identification information and a user identified by the user identification information. The sales partner identified by the counterpart identification information may be an organization. The user identified by the user identification information may be another user in the organization to which the user belongs.

[0102] The business negotiation information is information about past business negotiations. The past business negotiation information includes, for example, conversation information about a business negotiation that was conducted in the past, or summary information that is a summary of a business negotiation that was conducted in the past.

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

[0104] It is preferable that the sales material acquisition means 1322 acquires, from the material database 44 , sales material information that corresponds to the material identification information acquired by the input reception unit 121 with reference to the material management unit 112 .

[0105] The material database 44 of each of the two or more data management devices 4 corresponds to the material identification information.

[0106] The prompt acquisition means 1323 acquires a customer persona prompt, which is a prompt for the generation AI to become a customer persona, which is a persona corresponding to a sales partner. The prompt acquisition means 1323 acquires the customer persona prompt or a prompt template for configuring the customer persona prompt from the prompt management unit 111.

[0107] The AI ​​operation means 1325 provides the generation AI with one or more types of information among the unique information and the business negotiation information acquired by the unique information acquisition means 1321. The AI ​​operation means 1325 also provides the generation AI with a customer persona prompt. For example, the AI ​​operation means 1325 provides the generation AI with a customer persona prompt acquired by the prompt acquisition means 1323.

[0108] The AI ​​operation means 1325 provides the generation AI with the sales material information acquired by the sales material acquisition means 1322. The AI ​​operation means 1325 also provides the generation AI with a customer persona prompt. Note that the AI ​​operation means 1325 provides the generation AI with, for example, a customer persona prompt acquired by the prompt acquisition means 1323.

[0109] It is preferable that the AI ​​operation means 1325 provides the generation AI with two or more types of information among the unique information, the business negotiation information, and the sales document information, as well as a customer persona prompt.

[0110] The answer acquisition unit 133 acquires an answer corresponding to a prompt given to the generation AI by the AI ​​operation means 1325 from the generation AI. The answer acquisition unit 133 acquires an answer corresponding to a training input from the generation AI. The prompt given to the generation AI is, for example, a customer persona prompt, a fact judgment prompt, or a result evaluation prompt.

[0111] The evaluation unit 134 uses the training input and sales material information received by the input receiving unit 121 to obtain an evaluation result of the user's sales role-play.

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

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

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

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

[0116] The evaluation unit 134, for example, provides the generation AI with a result evaluation prompt (for example, "Regarding the sales role-play so far, please evaluate the sales role-play as a whole") to obtain an evaluation of the results of the sales role-play, and obtains result evaluation information from the generation AI. (2-2) Using natural language processing

[0117] The evaluation unit 134 judges whether or not a next step term, which is a term indicating that the next step has been reached in sales, is present in the response from the generation AI to the training input, and if it is present, obtains positive result evaluation information "1," and if it is not present, obtains negative result evaluation information "0." Examples of next step terms are "purchase," "contract," and "next business meeting."

[0118] The evaluation unit 134 judges whether or not a termination term, which is a term indicating that the contract was not concluded, exists in the response from the generation AI to the training input, and if it exists, obtains negative result evaluation information "0", and if it does not exist, obtains positive result evaluation information "1". The termination term is, for example, "I will not purchase" or "I will not sign the contract".

[0119] The output unit 14 outputs various types of information, such as the other party identification information, the response, and the evaluation result.

[0120] Here, output is usually transmission to the terminal device 2, but it is a concept that includes audio output, display on a display, projection using a projector, printing on a printer, storage on a recording medium, delivery of processing results to other processing devices, other programs, etc. Here, output is preferably transmission of audio information to the terminal device 2.

[0121] The candidate output unit 141 outputs one or more pieces of partner identification information acquired by the candidate acquisition unit 131. The candidate output unit 141 usually outputs information in a form in which one or more pieces of partner identification information are selectable. The information in a form in which one or more pieces of partner identification information are selectable is, for example, a menu, a check box, or a radio button in which the partner identification information can be selected. It is preferable that the candidate output unit 141 transmits to the terminal device 2 information in a form in which one or more pieces of partner identification information are selectable and can be displayed.

[0122] The answer output unit 142 outputs the answer acquired by the answer acquisition unit 133. The answer output unit 142 outputs an answer corresponding to the training input passed to the generation AI. It is preferable that the answer output unit 142 transmits the answer, which is voice information, to the terminal device 2.

[0123] The evaluation output unit 143 outputs the evaluation result acquired by the evaluation unit 134. The output here is usually a transmission to the terminal device 2. The evaluation result includes, for example, advice.

[0124] Various types of information are stored in the terminal storage unit 21 constituting the terminal device 2. The various types of information are, for example, a user identifier.

[0125] The terminal reception unit 22 receives various types of information, instructions, etc. The various types of information, instructions, etc. are, for example, input information and user voice information. The user voice information is, for example, training input.

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

[0127] The terminal processing unit 23 performs various types of processing. For example, the various types of processing are processing for converting received information, instructions, etc. into information or instructions with a structure to be transmitted. For example, the various types of processing are processing for converting received information into information with a structure to be output.

[0128] It is preferable that the device processing unit 23 performs a voice recognition process on the user's voice information (for example, training input) accepted by the terminal accepting unit 22, and acquires text (for example, training input of text).

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

[0130] The terminal receiving unit 25 receives various types of information, such as one or more pieces of party identification information, a response, and an evaluation result.

[0131] The terminal output unit 26 receives various types of information. The various types of information include, for example, one or more pieces of partner identification information, a response, and an evaluation result. It is preferable that the terminal output unit 26 outputs a voice response.

[0132] One or more pieces of unique information are stored in the business management database 41 stored in the data management device 4. The unique information corresponds to the other party identification information. Furthermore, the one or more pieces of unique information are paired with the user identification information.

[0133] The business negotiation management database 42 stored in the data management device 4 stores information on one or more past business negotiations. The business negotiation information corresponds to the partner identification information. In addition, one or more pieces of business negotiation information are paired with user identification information.

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

[0135] The storage unit 11, the prompt management unit 111, the terminal storage unit 21, the sales management database 41, the negotiation management database 42, and the material database 44 are preferably non-volatile recording media, but may also be realized as volatile recording media.

[0136] There is no restriction on the process by which information is stored in the storage unit 11, etc. 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 inputted via an input device may be stored in the storage unit 11, etc.

[0137] It is preferable that the reception unit 12, the input reception unit 121, and the instruction reception unit 122 are realized by wireless or wired communication means, but they may also be realized by a means for receiving broadcasts, a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen.

[0138] The processing unit 13, the candidate acquisition unit 131, the operation unit 132, the answer acquisition unit 133, the evaluation unit 134, the unique information acquisition means 1321, the sales material acquisition means 1322, the prompt acquisition means 1323, the AI ​​operation means 1325, and the terminal processing unit 23 can usually be realized by a processor, a memory, etc. The processing procedure of the processing unit 13, etc. is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit). The processor is a CPU, an MPU, a GPU, etc., and the type is not important.

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

[0140] The terminal reception unit 22 can be realized by a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen.

[0141] The terminal transmitting unit 24 is usually realized by a wireless or wired communication means, but may also be realized by a broadcasting means.

[0142] The terminal receiving unit 25 is usually realized by a wireless or wired communication means, but may be realized by a means for receiving a broadcast.

[0143] The terminal output unit 26 may be considered to include, or may not include, an output device such as a display, a speaker, etc. The terminal output unit 26 may be realized by driver software for an output device, or a combination of driver software for an output device and an output device, etc.

[0144] Next, an example of the operation of the information processing device 1 will be described with reference to the flowchart of FIG.

[0145] (Step S401) The reception unit 12 judges whether or not a start instruction has been received. If a start instruction has been received, the process proceeds to step S402, and if not, the process returns to step S401.

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

[0147] (Step S403) The processing unit 13 acquires other party identification information (for example, the other party's name, company name) that identifies the other party in the sales role-play. An example of such other party identification information acquisition processing will be described with reference to the flowchart of FIG.

[0148] (Step S404) The unique information acquiring means 1321 acquires unique information of the other party (for example, name, company name, job title, and URL of the company's homepage) from the sales management database 41 using the other party identification information.

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

[0150] (Step S405) The unique information acquiring means 1321 acquires the web page of the organization using the URL of the organization contained in the unique information.

[0151] (Step S406) The unique information acquiring unit 1321 acquires negotiation information from the negotiation management database 42 using the user identification information and the other party identification information.

[0152] The unique information acquisition means 1321 searches the negotiation management database 42 using, for example, the user identification information and the other party identification information as keys, and acquires one or more pieces of negotiation information.

[0153] (Step S407) The sales material obtaining means 1322 determines the data management device 4 and the material database 44 associated with 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 a customer persona prompt from the prompt management unit 111. The AI ​​operation means 1325 provides the acquired information (unique information, business negotiation information, and sales material information) to the generation AI. The AI ​​operation means 1325 also provides the acquired customer persona prompt to the generation AI.

[0156] (Step S410) The answer acquisition unit 133 judges whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S411, and if not, the process returns to step S410.

[0157] (Step S411) The answer output unit 142 outputs all or part of the answer acquired in step S410. For example, the answer output unit 142 transmits all or part of the answer to the terminal device 2. Here, it is preferable that the answer output unit 142 transmits all or part of the answer that has become voice information to the terminal device 2, for example.

[0158] Furthermore, the answer output unit 142 accumulates all or part of the answer acquired in step S410 in a buffer (not shown).

[0159] (Step S412) The processing unit 13 judges whether or not the answer satisfies the end condition. If the answer satisfies the end condition, the process proceeds to step S418, and if the answer does not satisfy the end condition, the process proceeds to step S413.

[0160] The end condition is, for example, that a specific term (for example, "end," "it's over," "the sales role-play is over") is included in the answer.

[0161] (Step S413) The input receiving unit 121 judges whether or not a training input from the user has been received. If a training input has been received, the process proceeds to step S414, and if not, the process returns to step S413.

[0162] (Step S414) The processing unit 13 judges whether the training input satisfies the end condition. If the end condition is satisfied, the process proceeds to step S418, and if the end condition is not satisfied, the process proceeds to step S415. Note that, for example, if the training input is voice information, the processing unit 13 performs voice recognition processing on the voice information to obtain the training input of the character string.

[0163] The end condition is, for example, that the training input contains a specific term (for example, "end," "it's over," "the sales role-play is over").

[0164] (Step S415) The processing unit 13 judges whether or not the time etc. satisfy the end condition. If the end condition is satisfied, the process proceeds to step S418, and if the end condition is not satisfied, the process proceeds to step S416.

[0165] The end condition here is that the current time is a time that has elapsed a predetermined time (for example, "30 minutes") or more from the start time.

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

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

[0168] (Step S418) The evaluation unit 134 acquires the evaluation result of the user for the sales role-play. An example of such evaluation processing will be described with reference to the flowchart of FIG.

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

[0170] Next, an example of the other party identification information acquisition process in step S403 will be described with reference to the flowchart in FIG.

[0171] (Step S501) The candidate acquisition unit 131 judges whether or not the start instruction has the other party identification information. If the start instruction has the other party identification information, the process proceeds to step S507, and if not, the process proceeds to step S502.

[0172] (Step S502) The candidate acquiring unit 131 acquires one or more pieces of partner identification information from the negotiation partner management database 43 (which may also serve as the sales management database 41 or the negotiation management database 42) using the user identification information.

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

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

[0175] (Step S505) Input reception unit 121 judges whether input information including a selection of one of one or more pieces of party identification information has been received. If such input information has been received, the process proceeds to step S506, and if not, the process returns to step S505. Note that input information including a selection of one party identification information can be said to be input information including one party identification information.

[0176] (Step S506) The processing unit 13 acquires one piece of party identification information corresponding to the selection of one piece of party identification information, and returns to the upper processing.

[0177] (Step S507) The processing unit 13 acquires the other party identification information contained in the start instruction, and returns to the upper processing.

[0178] Next, an example of the evaluation process in step S418 will be described with reference to the flowchart in FIG.

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

[0180] (Step S602) The evaluation unit 134 acquires training inputs and answers in the sales role-play from a buffer (not shown).

[0181] (Step S603) The evaluation unit 134 evaluates the accuracy of the user's statement using the sales document information and the training input. An example of such accuracy evaluation processing will be described with reference to the flowchart of FIG.

[0182] (Step S604) The evaluation unit 134 evaluates the result of the sales role-play. An example of such result evaluation processing will be described with reference to the flowchart of FIG.

[0183] Next, an example of the accuracy evaluation process in step S603 will be described with reference to the flowchart in FIG.

[0184] (Step S701) The evaluation unit 134 acquires information indicating facts from the sales document information. An example of such fact extraction processing will be described with reference to the flowchart of FIG.

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

[0186] (Step S703) The evaluation unit 134 judges whether or not the i-th judgment unit exists in the sales document information. If the i-th judgment unit exists, the process proceeds to step S704, and if not, the process proceeds to step S711.

[0187] The judgment unit is, for example, a sentence, a paragraph, or a topic. However, the technique of dividing a group of sentences into two or more topics is a well-known technique.

[0188] (Step S704) The evaluation unit 134 acquires the i-th judgment unit from the sales document information. The evaluation unit 134 converts the i-th judgment unit into a vector and acquires the i-th judgment unit vector.

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

[0190] (Step S706) The evaluation unit 134 judges whether or not the j-th fact vector exists. If the j-th fact vector exists, the process proceeds to step S707, and if not, the process proceeds to step S709.

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

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

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

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

[0195] The classes are, for example, "correct," "incorrect," and "irrelevant." For example, the evaluation unit 134 acquires the class "correct" if the maximum similarity is equal to or greater than a first threshold, acquires the class "incorrect" if it is less than the first threshold and equal to or greater than a second threshold, and acquires the class "irrelevant" if it is less than the second threshold and equal to or greater than a third threshold (wherein the first threshold>second threshold>third threshold).

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

[0197] (Step S712) The evaluation unit 134 calculates the accuracy by using the class of each of the two or more judgment units, and returns to the upper process.

[0198] The evaluation unit 134 calculates a higher accuracy as the number of judgment units of the class "correct" increases. The evaluation unit 134 calculates a lower accuracy as the number of judgment units of the class "incorrect" increases. The evaluation unit 134 calculates accuracy, for example, using the formula "accuracy = number of judgment units of class "correct" / total number of judgment units" or "accuracy = number of judgment units of class "correct" / (number of judgment units of class "correct" + number of judgment units of class "incorrect")".

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

[0200] Next, an example of the fact extraction process in step S701 will be described with reference to the flowchart in FIG.

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

[0202] (Step S802) The evaluation unit 134 judges whether the i-th judgment unit exists in the acquired sales document information. If the i-th judgment unit exists, the process proceeds to step S803, and if not, the process returns to the upper process.

[0203] A judgment unit is a unit for judging whether or not information describes a fact. Examples of judgment units include a sentence, a paragraph, information surrounded by a specific tag, and a topic.

[0204] (Step S803) The evaluation unit 134 acquires the ith judgment unit from the acquired sales document information.

[0205] (Step S804) The evaluation unit 134 judges whether the i-th judgment unit is information indicating a fact. If it is information indicating a fact, the process proceeds to step S805, and if it is not information indicating a fact, the process proceeds to step S806.

[0206] The evaluation unit 134 uses, for example, a machine learning algorithm or a generating AI to determine whether or not the i-th determination unit is information indicating a fact. Each case will be described below. (1) Machine learning

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

[0208] The learning model is information configured by the learning process of machine learning, and is information used in the prediction process of machine learning. The learning model may be called a learning device, a classifier, a classification model, or the like. The learning model here is information obtained by providing two or more pieces of teacher data, in which a judgment unit or a vector acquired from the judgment unit is an explanatory variable, and a judgment result of whether the information indicates a fact is an objective variable, to a module that performs a learning process of machine learning, and executing the module. The algorithm of machine learning may be deep learning, random forest, decision tree, SVM, or the like. In addition, for machine learning, for example, various machine learning functions such as the TensorFlow (registered trademark) library, the random forest module of the R language, fastText, TinySVM, and various existing libraries can be used. (2) When using generation AI

[0209] The evaluation unit 134 provides the generation AI with the i-th judgment unit and a prompt requesting it to judge whether the information indicates a fact, and obtains from the generation AI a judgment result as to whether the i-th judgment unit indicates a fact. The prompt is, for example, "Is the following information information indicating a fact? Or is it not information indicating a fact? If it is information indicating a fact, output "1", and if it is not information indicating a fact, output "0". <information>". In the prompt, information enclosed in "<" and ">" (here, <information>) is a variable, and here, the i-th judgment unit is substituted.

[0210] The evaluation unit 134 may obtain a determination result as to whether or not the i-th determination unit is information indicating a fact by using another algorithm for clustering information.

[0211] (Step S805) The evaluation unit 134 temporarily stores the i-th decision unit in a buffer (not shown). Here, it is preferable that the evaluation unit 134 vectorizes the i-th decision unit, obtains a fact vector, and temporarily stores the fact vector in a buffer (not shown).

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

[0213] Next, an example of the result evaluation process in step S604 will be described with reference to the flowchart in FIG.

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

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

[0216] (Step S903) The evaluation unit 134 judges whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S904, and if an answer has not been acquired, the process proceeds to step S903.

[0217] (Step S904) The evaluation unit 134 acquires the result evaluation included in the response, and returns to the upper level process.

[0218] A specific example of the operation of the information system A in this embodiment will be described below.

[0219] Currently, the prompt management table shown in FIG. 10 is stored in the prompt management unit 111 of the information processing device 1. The prompt management table manages one or more records having an "ID", "prompt identifier", "phase", and "prompt template". "ID" is information that identifies a record. "Prompt identifier" is the name of the prompt. "Phase" indicates one of a series of phases in a sales role-play in which a prompt is used. "Prompt template" is a prompt template. As described above, a prompt template can be considered to include a prompt. A character string enclosed in "<" and ">" in a prompt template is a variable. The series of phases in a sales role-play are the "persona setting" phase, the "role-play" phase, and the "evaluation" phase.

[0220] FIG. 11 shows the sales management database 41 of the first data management device 4. The sales management DB 41 manages one or more records having "ID", "person in charge information", and "client information". The "person in charge information" has "person in charge ID", "name", "company", and "department". The "client information" has "person in charge", "position", "company", "department", "gender", "age", "department", "gender", "URL", "responsible person", and "business negotiation date". The "person in charge" in the "client information" is the name of the person in charge of the sales partner. The "URL" is the URL of the homepage of the company to which the person in charge belongs. The "responsible person" is the name of the responsible person of the organization to which the person in charge belongs. The "business negotiation date" is the date on which the sales person identified by the "person in charge ID" and the client corresponding to the client information conducted a business negotiation. The "business negotiation date" stores one or more dates. Here, the first data management device 4 is a Salesforce server.

[0221] FIG. 12 shows the business negotiation management database 42 of the second data management device 4. The business negotiation management DB 42 manages one or more records having "ID", "person in charge information", and "business partner information". The "person in charge information" has "person in charge ID", "name", "company", and "department". The "business partner information" has "partner ID", "name", "job title", "company", and "business negotiation information". The "business negotiation information" has "business negotiation date and time", "all information", and "summary". The "business negotiation date and time" is the time period during which the business negotiation took place or the start time of the business negotiation. The "all information" is a text obtained by converting all the voices of both the person in charge and the business partner in the business negotiation held in a web conference into text. The "summary" is a text summarizing all the information. The "summary" is information obtained from the generation AI by, for example, providing the generation AI with all the information and giving a prompt obtained from a prompt template such as "Please summarize the business negotiation below. [business negotiation] <all information>". In this case, the second data management device 4 is a server (for example, an amptalk server) in which business negotiation information is recorded by "amptalk assist" (see URL "https: / / amptalk.co.jp / product / assist"), which is a service of amptalk.

[0222] Also, it is assumed here that the negotiating partner management database 43 of the data management device 4 also serves as the sales management database 41 of the first data management device 4 .

[0223] Furthermore, the material management unit 112 of the information processing device 1 stores a material DB management table shown in FIG. 13. The material DB management table is a table that manages information for accessing the material database 44 of one or more data management devices 4. The material DB management table can be said to be a table that manages the location of sales materials for each company, for example. The material DB management table manages one or more records having an "ID," "user identification information," and "material identification information." The "user identification information" has a "company name" and a "person in charge." The "person in charge" is the name of the person in charge. The "material identification information" here is a URL for accessing the sales material information. The destination indicated by this URL may be one piece of sales material information, or a folder in which two or more pieces of sales material information are stored.

[0224] In the above situation, it is assumed that the user “Tanaka A-san” (hereinafter, “user A”) inputs a start instruction from the terminal device 2.

[0225] Next, the terminal device 2 accepts the start instruction and transmits the start instruction including the user identifier (person in charge ID) “P01” to the information processing device 1.

[0226] The reception unit 12 of the information processing device 1 receives the start instruction from the terminal device 2 of the user A. Next, the processing unit 13 acquires the user identifier "P01" included in the start instruction. Next, the processing unit 13 determines that the start instruction does not include the other party identification information.

[0227] Next, the processing unit 13 uses the user identification information (here, "P01") to acquire four pieces of partner identification information that are paired with "P01" from a Salesforce server (data management device 4) that includes a negotiation partner management database 43 (here, the sales management database 41 in FIG. 11). Here, the partner identification information is "person in charge", but the processing unit 13 acquires "company" and "department" in addition to "person in charge" from the sales management database 41. Next, the processing unit 13 configures a screen for selecting one piece of partner identification information, etc. from the four pieces of partner identification information, etc. Next, the candidate output unit 141 transmits the screen to the terminal device 2 of user A.

[0228] Next, the terminal device 2 of the user A receives and outputs the screen. An example of such a screen is shown in FIG. 14. Then, the user A selects "M11" from among four candidates for business partners. That is, the user A toggles on 1301 on the screen of FIG. 14. Next, the user A instructs the "Send" button 1302. Then, the terminal device 2 accepts the instruction for the "Send" button 1302. Next, the device processing unit 23 of the terminal device 2 acquires the information "<Name>M11 <Company>Company C <Department>Purchase Department" of 1301 corresponding to the instruction. Next, the device processing unit 23 configures the input information "<Name>M11 <Company>Company C <Department>Purchase Department". Next, the terminal transmission unit 24 transmits the input information to the information processing device 1. Note that the input information includes the other party identification information "<Name>M11 <Company>Company C <Department>Purchase Department".

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

[0230] Next, the unique information acquiring means 1321 performs a web search using the URL "URL11" of the home page of the organization "C company" contained in the unique information, and acquires the web page of C company.

[0231] Next, the unique information acquisition means 1321 acquires the negotiation information paired with the user identification information "P01" and the other party identification information "<Name>M11 <Company>Company C" from the negotiation management database 42 (FIG. 12). Here, the unique information acquisition means 1321 acquires all the information "file11" and the summary "file12" of the record with "ID=1" in FIG. 12.

[0232] Next, the sales material acquisition means 1322 refers to the material DB management table in Fig. 13 and determines the data management device 4 and material database 44 corresponding to the user identification information "<Person in Charge ID> P01 <Name> Tanaka A <Company> Company X". In other words, the sales material acquisition means 1322 refers to the material DB management table in Fig. 13 and acquires the material DB access information "URL_D1" that is paired with the company name "Company X". 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 in which the sales materials of Company X are stored, and acquires one or more sales materials.

[0233] Next, the prompt acquisition unit 1323 acquires a prompt template that is paired with the prompt identifier "customer persona prompt" of the persona setting phase from the prompt management table (FIG. 10). Next, the prompt acquisition unit 1323 acquires the variables <company><name><position><gender><age> of the prompt template (prompt template with "ID=1" in FIG. 10). <url>The above acquired information is substituted into <business negotiation information> and <sales document information> to construct a customer persona prompt. Such a customer persona prompt is shown in Figure 15. In Figure 15, each underlined part is a variable in the prompt template, and is the acquired specific information, business negotiation information, or sales document information.

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

[0235] Next, the answer acquisition unit 133 acquires the answer from the generation AI. Then, the answer output unit 142 transmits the answer to the terminal device 2 of the user A.

[0236] Next, the terminal device 2 receives and outputs the answer. An example of such an output is shown in Fig. 16. After that, Mr. Tanaka A can perform a sales role-play with the customer persona of the generated AI, who is pretending to be M11 of Company C.

[0237] It is assumed that user A then makes a speech input to the terminal device 2, saying, "M11, thank you very much for the other day. Also, thank you very much for giving me your time today." Such an input is a training input.

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

[0239] Next, the input receiving unit 121 of the information processing device 1 receives a training input from the user A from the terminal device 2. Next, the processing unit 13 performs a voice recognition process on the training input of the voice information to obtain a training input of a character string. The training input from the user A is 1701 in Fig. 17. Next, the processing unit 13 determines that the end condition is not satisfied.

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

[0241] Next, the terminal device 2 receives the answer in the form of voice information and outputs it as voice. The output answer is 1702 in FIG. 17. Note that information marked with a circle (1702, 1704, 1706) is the answer from the generating AI. Also, information (1701, 1703, 1705) is the training input from user A.

[0242] Thereafter, the sales role-play between user A and the generated AI proceeds through the same process as above, and the processing unit 13 of the information processing device 1 determines that the sales role-play has satisfied the end condition.

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

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

[0245] As described above, according to this embodiment, by providing the generation AI with unique information about a sales partner, a sales role-play that is close to an actual sales experience can be realized.

[0246] Furthermore, according to this embodiment, by obtaining unique information of actual sales counterparties from the sales management database 41 present in the data management device 4 and providing the unique information to the generation AI, a sales role-play that is close to an actual sales experience can be realized.

[0247] Furthermore, according to this embodiment, by providing the generation AI with information about the web page of the organization to which the sales partner belongs, a sales role-play that is close to an actual sales experience can be realized.

[0248] Furthermore, according to this embodiment, by providing personal information such as the name of a sales partner to the generation AI, a sales role-play that is close to an actual sales experience can be realized.

[0249] Furthermore, according to this embodiment, by providing the generation AI with sales negotiation information from past sales negotiations with a sales partner, a sales role-play that is very close to an actual sales experience can be realized.

[0250] In addition, according to this embodiment, by providing the generation AI with conversation information from past business negotiations with a sales partner or summary information summarizing the conversation, it is possible to realize a sales role-play that is very close to an actual sales experience.

[0251] Furthermore, according to this embodiment, by acquiring sales materials for the sales target from an external data management device 4 and providing the sales materials to the generation AI, it is possible to realize a sales role-play for a customer persona that understands the sales target, 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 the sales materials of the sales target and the content of the user's role-playing.

[0253] The processing in this embodiment may be realized by software. This software may be distributed by software download or the like. This software may also be recorded on a recording medium such as a CD-ROM and distributed. This also applies to the other embodiments in this specification. The software that realizes the information processing device 1 in this embodiment is a program such as the following. In other words, this program causes the computer to function as an input accepting unit that accepts input information including material identification information that identifies sales material information, which is a material for sales, an operation unit that acquires sales material information corresponding to the material identification information from one or more material databases in which sales material information corresponding to each of one or more material identification information is stored, provides the sales material information to the generation AI, and provides the generation AI with a customer persona prompt, which is a prompt for the generation AI to become a customer persona, which is a persona corresponding to the sales partner, an answer acquisition unit that acquires an answer corresponding to the customer persona prompt from the generation AI, and an answer output unit that outputs the answer acquired by the answer acquisition unit, and the input accepting unit further accepts training input, which is an input for progressing the role-play after the answer output unit outputs the answer, the operation unit provides the training input to the generation AI, the answer acquisition unit acquires an answer corresponding to the training input from the generation AI, and the answer output unit outputs the answer corresponding to the training input acquired by the answer acquisition unit.

[0254] FIG. 19 is a block diagram of a computer system 300 that executes the programs described in this specification to realize the information processing device 1 and the like according to the various embodiments described above.

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

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

[0257] A program for causing computer system 300 to execute the functions of information processing device 1 and the like of the above-mentioned embodiment may be stored on CD-ROM 3101, inserted into CD-ROM drive 3012, and further transferred to hard disk 3017. Alternatively, the program may be transmitted to computer 301 via a network (not shown) and stored on hard disk 3017. The program is loaded into RAM 3016 at the time of execution. The program may be loaded directly from CD-ROM 3101 or the network.

[0258] The program does not necessarily include an operating system (OS) or a third party program that causes the computer 301 to execute the functions of the information processing device 1 of the above-mentioned embodiment. The program only needs to include an instruction portion that calls appropriate functions (modules) in a controlled manner to obtain a desired result. How the computer system 300 operates is well known, and a detailed description will be omitted.

[0259] In addition, in the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmitting step (processing that is performed only by hardware).

[0260] The program may be executed by a single computer or a plurality of computers. That is, the program may be executed by a centralized processing or a distributed processing.

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

[0262] In each of the above embodiments, each process may be realized by centralized processing in a single device, or may be realized by distributed processing in a plurality of devices.

[0263] The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention. [Industrial Applicability]

[0264] As described above, the information processing device 1 of the present invention has the effect of enabling sales role-playing that is close to actual sales experience, assuming a sales target that is knowledgeable, and is useful as a server for educating sales personnel, etc. [Explanation of symbols]

[0265] A. Information Systems 1. Information processing device 2 Terminal Equipment 3 Generation AI device 4 Data management device 11 Storage area 12 Reception 13 Processing section 14 Output section 21 Terminal storage section 22 Terminal Reception 23 Terminal Processing Section 24 Terminal transmitter 25 Terminal receiving section 26 Terminal Output Section 41 Sales Management DB 41 Sales Management Database 42 Business negotiation management database 42 Business negotiation management DB 43 Business Partner Management Database 44 Document Database 111 Prompt Management Department 112 Materials Management Department 121 Input reception section 122 Instruction Reception Department 131 Candidate acquisition section 132 Operating Part 133 Answer acquisition part 134 Evaluation Department 141 Candidate Output Unit 142 Answer output section 143 Evaluation output unit 1321 Unique information acquisition means 1322 Means of obtaining business information 1323 Prompt Acquisition Method 1325 AI operation means< / url> < / url>

Claims

1. An information processing device that supports sales role-playing using generation AI, an input receiving unit that receives input information including material identification information that identifies sales material information that is a sales target material; an operating unit that acquires sales material information corresponding to one or more material identification information from one of one or more material databases in which sales material information corresponding to each of the one or more material identification information is stored, provides the sales material information to the generation AI, and provides a customer persona prompt to the generation AI, which is a prompt for the generation AI to become a customer persona that is a persona corresponding to a sales partner; an answer acquisition unit that acquires an answer corresponding to the customer persona prompt from the generating AI; a response output unit that outputs the response acquired by the response acquisition unit, The input receiving unit is After the answer output unit outputs the answer, a training input is further received, which is an input for proceeding with the role play; The operation unit includes: providing said training inputs to said generation AI; The answer acquisition unit, Obtaining an answer corresponding to the training input from the generation AI; The answer output unit, An information processing device that outputs the answer corresponding to the training input acquired by the answer acquisition unit.

2. The input receiving unit is Accepting user identification information for identifying a user who will perform a sales role-play with the generating AI, and using the user identification information, acquiring the material identification information from a material management unit in which material identification information paired with each of two or more user identification information is stored; The operation unit includes: a sales material acquisition means for acquiring, from the material database, the sales material information corresponding to the material identification information acquired by the input receiving unit; 2. The information processing apparatus according to claim 1, further comprising: AI operation means for providing the sales material information acquired by the sales material acquisition means to the generation AI, and for providing a previous customer persona prompt to the generation AI.

3. each of the two or more material databases exists in a data management device different from the information processing device; The sales information acquisition means includes:

3. The information processing apparatus according to claim 2, wherein the input receiving unit accesses the data management device corresponding to the material identification information acquired, and acquires the sales material information.

4. an evaluation unit that acquires an evaluation result of the user's sales role-play using the training input and the sales material information received by the input receiving unit; The information processing apparatus according to claim 1 , further comprising an evaluation output unit that outputs the evaluation result acquired by the evaluation unit.

5. The evaluation unit is An information processing device as described in claim 4, which acquires the evaluation result including one or more of the following information: accuracy evaluation information indicating an evaluation regarding the accuracy of the training input based on the sales material information, and result evaluation information regarding the sales results.

6. The input receiving unit is Accepting input information including party identification information that identifies a business partner; The operation unit includes: An information processing device as described in claim 1, wherein the unique information of the sales partner based on the partner identification information accepted by the input accepting unit is obtained from a sales management database which stores partner information having unique information corresponding to each of two or more partner identification information, the unique information is also provided to a generation AI, and the generation AI provides the customer persona prompt to the generation AI.

7. The input receiving unit is Accept the input information including counterparty identification information that identifies a sales counterparty in correspondence with user identification information of a user who will perform a sales role-play with the generated AI; The operation unit includes: a unique information acquisition means for acquiring the negotiation information corresponding to the counterpart identification information and the user identification information received by the input receiving unit from a negotiation management database storing past negotiation information corresponding to the user identification information and one or more counterpart identification information; 2. An information processing apparatus according to claim 1, further comprising: AI operation means for providing the business negotiation information acquired by the specific information acquisition means to the generation AI, and for providing the customer persona prompt to the generation AI.

8. An instruction receiving unit that receives a partner selection instruction including user identification information; a candidate acquisition unit that acquires one or more pieces of partner identification information that are paired with the user identification information included in the partner selection instruction received by the instruction reception unit from a negotiation partner management database in which one or more pieces of partner identification information that identify a sales partner are stored in association with each of one or more pieces of user identification information; a candidate output unit that outputs the one or more pieces of partner identification information acquired by the candidate acquisition unit, The input receiving unit is The information processing apparatus according to claim 1 , further comprising: receiving input information including one of said one or more pieces of party identification information;

9. 9. An information processing method comprising all steps performed by the information processing device according to claim 1.

10. Computer, A program for causing an information processing device to function as the information processing device according to any one of claims 1 to 8.

Images