Proposal creation support device, proposal creation support system, proposal creation support method, and program

Abstract

Reduce the time required to create proposals that reflect the client's latent needs. [Solution] The proposal creation support device 1 includes a customer information acquisition unit 11 that acquires at least one of negotiation history information showing past negotiations with a customer, or order history information showing order history from a customer; a prompt creation unit 13 that creates a customer reproduction prompt to reproduce a customer and inputs it to a customer generation AI 21, creates a hearing prompt including questions including a proposal to the customer generation AI 21, inputs the hearing prompt to the customer generation AI 21, and obtains a response from the customer generation AI 21; and an information output unit 15 that outputs information including the content of the response from the customer generation AI 21.

Description

Technical Field

[0005] , , ,

[0001] The present disclosure relates to a proposal creation support device, a proposal creation support system, a proposal creation support method, and a program.

Background Art

[0002] As one of the means for sales to increase the order rate of the company's products or services, there is the creation of proposals that reflect the potential needs of customers. To create proposals that reflect the potential needs of customers, it is necessary to check the past negotiation results and order winning / losing results of the target customers, and there is also a limit to the time available for conversation with customers. In addition, in order to grasp the potential needs of customers, it is also necessary to conduct operations such as investigating the past negotiation results and order winning / losing results of customers with the same attributes as the customers, which requires a huge amount of time.

[0003] Patent Document 1 discloses a proposal recommendation device that records a plurality of sales records each including a negotiation history text in which negotiation contents and proposal contents are expressed in natural language and a negotiation status associated with the negotiation history text, and presents one or more sales records as recommended records according to an evaluation score corresponding to the degree of conformity to the negotiation history text included in the newly input sales record.

Prior Art Documents

Patent Documents

[0006] This disclosure is made to address the problems described above and aims to reduce the time required to create proposals that reflect the potential needs of our clients. [Means for solving the problem]

[0007] To achieve the above objective, the proposal creation support device relating to this disclosure comprises a customer information acquisition unit, a prompt creation unit, and an information output unit. The customer information acquisition unit acquires at least one of the following: negotiation history information showing past negotiations with a customer, or order performance information showing order performance from a customer. The prompt creation unit creates a customer reproduction prompt that reproduces the customer based on at least one of the negotiation history information or order performance information, inputs it to the first artificial intelligence unit, creates a hearing prompt that includes questions including a proposal to the first artificial intelligence unit, inputs the hearing prompt to the first artificial intelligence unit, and obtains a response from the first artificial intelligence unit. The information output unit outputs information including the content of the response from the first artificial intelligence unit. [Effects of the Invention]

[0008] According to this disclosure, by asking questions to an artificial intelligence unit that has learned about customer attributes and circumstances, past business negotiations with customers, and past order records from customers, and obtaining answers, it becomes possible to shorten the time required to create proposals that reflect the customer's latent needs. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example configuration of the proposal creation support system according to Embodiment 1. [Figure 2] A diagram showing an example of a hearing prompt according to Embodiment 1. [Figure 3] Flowchart showing the proposal creation support process according to Embodiment 1 [Figure 4] This figure shows an example configuration of the proposal creation support system according to Embodiment 2. [Figure 5] A diagram showing an example of a prompt template according to Embodiment 2. [Figure 6]Flowchart showing the proposal creation support process according to Embodiment 2 [Figure 7] A diagram showing an example of the hardware configuration of the proposal creation support device according to Embodiments 1 and 2. [Modes for carrying out the invention]

[0010] The proposal creation support device, proposal creation support system, proposal creation support method, and program according to this embodiment will be described in detail below with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals. In the following description, the proposal creation support device uses generation AI (Artificial Intelligence) to support the creation of proposals that reflect the latent needs of customers. The user of the proposal creation support device is a salesperson who proposes their company's products or services to customers and concludes contracts.

[0011] (Embodiment 1) The configuration of the proposal creation support system 100 according to Embodiment 1, and the functional configuration of the proposal creation support device 1 and the server device 2 that operates the generation AI will be explained with reference to Figure 1. The customer generation AI 21 operating on the server device 2 is a text generation AI that learns the customer's attributes and situation, past business negotiations with the customer, past order records from the customer, and interactions with sales, and reproduces the customer. The customer generation AI 21 is an example of the first artificial intelligence unit.

[0012] As shown in Figure 1, the proposal creation support device 1 includes a customer information acquisition unit 11 that acquires customer basic information indicating the attributes and status of the customer, negotiation history information indicating past negotiations with the customer, and order performance information indicating the order performance from the customer; a question information acquisition unit 12 that acquires question information indicating questions including proposals to the customer generation AI 21; a prompt creation unit 13 that creates prompts to be input to the customer generation AI 21 based on the customer basic information, negotiation history information, order performance information, and question information, and inputs them to the customer generation AI 21 operating on the server device 2; a speech history storage unit 14 that stores prompts including interactions with the customer generation AI 21; and an information output unit 15 that outputs response information indicating the response from the customer generation AI 21.

[0013] The customer information acquisition unit 11 acquires customer basic information, negotiation history information, and order performance information. The customer information acquisition unit 11 may acquire customer basic information, negotiation history information, and order performance information from an external device or system, or sales personnel or other personnel may input customer basic information, negotiation history information, and order performance information into the customer information acquisition unit 11. Customer basic information includes, for example, if the customer is a building management company, information such as building name, building attributes, year of construction, floor height, distance to the station, current power consumption, number of tenants, tenant type, number of people flowing in, floor area by floor height, floor height by floor height, number of rooms, sunlight information, installed equipment information, equipment maintenance information, and the business status of the customer company. Negotiation history information includes, for example, daily negotiation reports, audio recordings, video recordings, email history, and chat history. Order performance information includes, for example, if the company's product is air conditioning equipment, the model name of the air conditioning equipment, the date and time of order, and the number of units ordered. The customer information acquisition unit 11 sends the acquired customer basic information, negotiation history information, and order performance information to the prompt creation unit 13.

[0014] The question information acquisition unit 12 acquires question information that includes questions, including proposals for the customer-generated AI 21. The question information acquisition unit 12 may accept question information input from sales or receive question information from terminals used by sales. For example, if the company's products are air conditioning equipment, the question information may include questions to elicit customer needs for air conditioning equipment, or proposals for introducing new models of air conditioning equipment.

[0015] The prompt creation unit 13 first creates a customer reproduction prompt that reproduces the customer based on customer basic information, negotiation history information, and order performance information, and stores it in the speech history storage unit 14. When it receives question information from the question information acquisition unit 12, the prompt creation unit 13 adds the content of the question indicated by the question information to the customer reproduction prompt to create a hearing prompt and inputs it to the customer generation AI 21 of the server device 2. At this time, the prompt creation unit 13 stores the hearing prompt in the speech history storage unit 14. When it receives a response from the customer generation AI 21 of the server device 2, the prompt creation unit 13 generates a prompt with the response added to the hearing prompt and stores it in the speech history storage unit 14. The prompt creation unit 13 saves the input content to the customer generation AI 21 and the response content from the customer generation AI 21 in the speech history storage unit 14 one by one. Hereinafter, the input content to the generation AI and the response content from the generation AI will be referred to as the speech history. The prompts stored in the speech history memory unit 14 are updated as speech history is added.

[0016] When the prompt creation unit 13 receives question information and creates a hearing prompt, it adds the content of the question indicated by the question information to the prompt stored in the utterance history storage unit 14 to create the hearing prompt. For hearing prompts created after the initial one, the utterance history is added sequentially. By sequentially adding the utterance history to the hearing prompt, it becomes possible to interact with the customer-generated AI 21 as if having a continuous conversation with the customer. If the interaction with the customer-generated AI 21 becomes long and exceeds the number of input tokens for the customer-generated AI 21, a separate generation AI is used to summarize the content of the utterance.

[0017] Here, the hearing prompt will be described with reference to FIG. 2. The customer to be reproduced by the customer reproduction prompt included in the hearing prompt shown in FIG. 2 is a person in charge of replacing air-conditioning equipment at a major general construction company. In the example shown in FIG. 2, the hearing prompt has headings such as Introduction, Office Building Features, Question, etc. Question is the content of the question indicated by the question information. Although not described in the example of FIG. 2, the hearing prompt may describe, for example, the past negotiation history with the customer under the heading of Negotiation History. When the negotiation history data is generated as table data, it is advisable to describe it in Markdown format.

[0018] Returning to FIG. 1, when the answer content from the customer generation AI 21 is saved in the speech history storage unit 14, The information output unit 15 generates and outputs answer information indicating the answer from the customer generation AI 21. The output method of the answer information is, for example, when configured to receive input of question information from sales, the answer information is displayed on the screen, and when configured to receive question information from the terminal used by sales, the answer information is transmitted to the terminal used by sales.

[0019] The information output unit 15 may be configured to generate a negotiation screen for communicating with the customer generation AI 21. In this case, the information output unit 15 may display the negotiation screen on the screen or transmit it to the terminal used by sales. The negotiation screen enables input of questions from sales, and the question information acquisition unit 12 acquires the question information indicating the questions input from sales. The information output unit 15 displays the answer content from the customer generation AI 21 to the questions input from sales on the negotiation screen.

[0020] By having sales ask questions to the customer generation AI 21 that reproduces a pseudo-customer personality for the text generation AI in the above procedure, it becomes possible to obtain a pseudo-answer from the customer and shorten the time required to create a proposal that reflects the potential needs of the customer.

[0021] Next, the flow of the proposal creation support process executed by the proposal creation support device 1 will be explained using Figure 3. The proposal creation support process shown in Figure 3 starts, for example, when the proposal creation support device 1 is started. The prompt creation unit 13 of the proposal creation support device 1 creates a customer reproduction prompt that reproduces the customer based on customer basic information, negotiation history information, and order performance information (step S11), and stores it in the speech history storage unit 14. If the question information acquisition unit 12 does not acquire question information (step S12; NO), the process moves to step S18.

[0022] When the question information acquisition unit 12 acquires question information (step S12; YES), the prompt creation unit 13 adds the content of the question indicated by the question information to the prompt stored in the utterance history storage unit 14 to create a hearing prompt (step S13), and inputs it to the customer-generated AI 21 of the server device 2 (step S14). At this time, the prompt creation unit 13 stores the hearing prompt in the utterance history storage unit 14. When it receives a response from the customer-generated AI 21 of the server device 2 (step S15), the prompt creation unit 13 generates a prompt with the response added to the hearing prompt (step S16), and stores it in the utterance history storage unit 14.

[0023] The information output unit 15 generates and outputs response information indicating the response from the customer-generated AI 21 (step S17). If the power is not turned off (step S18; NO), the process returns to step S12 and steps S12 to S18 are repeated. If the power is turned off (step S18; YES), the process ends.

[0024] According to the proposal creation support device 1 of Embodiment 1, by asking questions to the customer generation AI 21, which has learned the customer's attributes and situation, past business negotiations with the customer, and past order records from the customer, and obtaining answers, it becomes possible to shorten the time required to create a proposal that reflects the customer's latent needs.

[0025] (Embodiment 2) In Embodiment 1, the salesperson inputted questions into a customer-generating AI that replicated a customer, and received answers. In Embodiment 2, however, the salesperson is also replicated by a generation AI, and the sales-generating AI that replicates the salesperson and the customer-generating AI that replicates a customer conduct business negotiations. The following description will mainly explain the differences from Embodiment 1.

[0026] The configuration of the proposal creation support system 100 according to Embodiment 2 and the functional configuration of the proposal creation support device 1 and the server device 2 that operates the generation AI will be explained with reference to Figure 4. The customer generation AI 21 that operates on the server device 2 is the same as in Embodiment 1. The sales generation AI 22 that operates on the server device 2 is a text generation AI that replicates a salesperson asking questions to a customer. The sales generation AI 22 is an example of the second artificial intelligence unit. As shown in Figure 4, the proposal creation support device 1 includes a customer information acquisition unit 11, a prompt creation unit 13, a speech history storage unit 14, and an information output unit 15, as well as a document storage unit 16 that stores data on materials related to the company's products or services, such as the company's own catalog, other companies' catalogs, technical documents, and specification sheets.

[0027] The prompt creation unit 13 first creates a customer reproduction prompt that replicates the customer based on the customer's basic information, negotiation history information, and order performance information, and stores it in the speech history storage unit 14. The prompt creation unit 13 also creates a sales reproduction prompt that shows the role of a salesperson asking questions, including proposals, to the customer, and stores it in the speech history storage unit 14. A general prompt is used for the sales reproduction prompt. In the following processes, the prompt creation unit 13 saves the speech history in the speech history storage unit 14 one by one.

[0028] The prompt creation unit 13 creates a prompt for creating interview content, which asks questions about the content of the interview with the customer, based on the sales reproduction prompt. The prompt creation unit 13 inputs the prompt for creating interview content into the sales generation AI 22 and obtains the output of the interview content. At this time, the interview content is not just a sentence, but is a table data in which the sentences of the interview content are listed for each item.

[0029] The prompt creation unit 13 adds the interview content obtained from the sales generation AI 22 to the customer reproduction prompt to create an interview prompt. The prompt creation unit 13 inputs the interview prompt to the customer generation AI 21 on the server device 2 and receives a response from the customer generation AI 21 on the server device 2. At this time, the response from the customer generation AI 21 is also formatted as tabular data, with the text of the response content written for each item, similar to the interview content.

[0030] The prompt generation unit 13 searches the data storage unit 16 for relevant materials in order to propose the company's products or services that match the answers to each item. First, the prompt generation unit 13 creates a search query to search for relevant materials for each item of the answer. The search query is, for example, a sentence that combines the interview content and the answer content. Using the search query, the prompt generation unit 13 searches the data storage unit 16 for relevant materials from the company's catalogs, competitor catalogs, technical documents, specification sheets, etc. that it stores. At this time, it is assumed that the company's catalogs, competitor catalogs, technical documents, specification sheets, etc. are database-organized in units such as chapters, sections, and pages.

[0031] The search process performed by the prompt generation unit 13 may involve picking out important words from the search query using morphological analysis and TF-IDF (term frequency - inverse document frequency), and then searching for sections containing the most important words. Alternatively, the database may be pre-embedded using natural language processing techniques such as BERT (Bidirectional Encoder Representations from Transformers), and the search query may be compared with the embedded results to find sections with high similarity. The search results will extract the top N items.

[0032] The prompt creation unit 13 extracts relevant materials for all responses and then creates a proposal creation prompt that asks about the proposal content based on the sales reproduction prompt and the extracted materials. The prompt creation unit 13 inputs the proposal creation prompt into the sales generation AI 22 and obtains the output of the proposal content. The proposal content not only proposes the company's products or services but also includes the reasons for proposing those products or services (e.g., selling points derived from the responses = created from the search results of the materials).

[0033] The prompt creation unit 13 creates a prompt for hearing based on the proposed content. The prompt creation unit 13 inputs the customer feedback creation prompt into the customer generation AI 21 and receives the customer's opinion on the proposal, i.e., the evaluation result. The evaluation result includes an evaluation of the merits of the proposal and the reasons for it.

[0034] The prompt generation unit 13 determines whether a deal has been concluded based on the validity of the proposal indicated by the evaluation result. When the prompt generation unit 13 determines that the evaluation is positive (deal concluded), the information output unit 15 outputs a summary of the proposal content, which includes the proposal content and evaluation result, and shows the history of statements made by the sales generation AI 22 and the customer generation AI 21 up to that point. The output of the summary of the proposal content may simply be a list of each sentence in a single file, or it may be summarized using the generation AI.

[0035] If the evaluation is negative (meaning the deal was not closed), the prompt creation unit 13 generates a "brush-up point extraction" prompt that asks for improvement suggestions indicating which elements should be customized to be evaluated favorably by the customer-generating AI 21, using the reason for the deal's failure. The prompt creation unit 13 inputs the "brush-up point extraction" prompt into the sales-generating AI 22 and obtains an answer indicating improvement suggestions indicating which elements should be customized to be evaluated favorably by the customer-generating AI 21. Hereinafter, improvement suggestions indicating which elements should be customized to be evaluated favorably by the customer-generating AI 21 are referred to as "brush-up points." The brush-up points are output in a table format that lists what was wrong with each specification of the company's product or service based on the customer's evaluation. Subsequently, the prompt creation unit 13 creates a "hearing content creation" prompt that incorporates the brush-up points obtained from the sales-generating AI 22. The prompt creation unit 13 inputs the "hearing content creation" prompt into the sales-generating AI 22 and obtains the output of the hearing content. At this time, the interview content will be presented as a table data containing written interview content for each item, used to confirm with the customer-generated AI21 what kind of requests there are for each specification.

[0036] The various prompts created by the prompt creation unit 13 in each of the processes described above are each provided with a template as shown in Figure 5, and are completed by pasting the necessary content into that template.

[0037] Next, the flow of the proposal creation support process executed by the proposal creation support device 1 will be explained using Figure 6. The proposal creation support process shown in Figure 6 starts, for example, when the proposal creation support device 1 is started. The prompt creation unit 13 of the proposal creation support device 1 creates a customer reproduction prompt that reproduces the customer based on the customer's basic information, negotiation history information, and order performance information (step S21), and stores it in the speech history storage unit 14. The prompt creation unit 13 also creates a sales reproduction prompt that indicates the role of the salesperson asking questions to the customer (step S22), and stores it in the speech history storage unit 14. A general prompt is used for the sales reproduction prompt. In the following processes, the prompt creation unit 13 saves the speech history in the speech history storage unit 14 one by one.

[0038] The prompt creation unit 13 creates a prompt for creating interview content, which asks questions about the content of the interview with the customer, based on the sales reproduction prompt (step S23). The prompt creation unit 13 inputs the prompt for creating interview content into the sales generation AI 22 (step S24) and obtains the output of the interview content (step S25). At this time, the interview content is not just a sentence, but is table data in which the sentences of the interview content are written for each item.

[0039] The prompt creation unit 13 adds the interview content obtained from the sales generation AI 22 to the customer reproduction prompt to create an interview prompt (step S26). The prompt creation unit 13 inputs the interview prompt to the customer generation AI 21 on the server device 2 (step S27) and receives a response from the customer generation AI 21 on the server device 2 (step S28). At this time, the response from the customer generation AI 21 is also formatted as tabular data, with the text of the response content written for each item, similar to the interview content.

[0040] The prompt generation unit 13 creates a search query to search for relevant materials for each item of the response content (step S29). The search query is, for example, a sentence that combines the interview content and the response content. The prompt generation unit 13 uses the search query to search for relevant materials from the materials stored in the material storage unit 16, such as the company's catalog, other companies' catalogs, technical documents, and specification sheets (step S30). At this time, it is assumed that the materials such as the company's catalog, other companies' catalogs, technical documents, and specification sheets are database-organized in units such as chapters, sections, and pages.

[0041] If relevant materials have not been extracted for all the answers (Step S31; NO), the process returns to Step S29, and Steps S29 and S31 are repeated. If relevant materials have been extracted for all the answers (Step S31; YES), the prompt creation unit 13 creates a proposal creation prompt that asks for the proposal content (Step S32). The prompt creation unit 13 inputs the proposal creation prompt to the sales generation AI 22 (Step S33) and obtains the output of the proposal content (Step S34). The proposal content not only proposes the company's products or services, but also includes the reasons for proposing those products or services.

[0042] The prompt creation unit 13 creates a customer feedback creation prompt based on the proposed content (step S35). The prompt creation unit 13 inputs the customer feedback creation prompt into the customer generation AI 21 (step S36) and receives a response with the evaluation result for the proposal (step S37). The evaluation result includes whether the proposal is good or bad and the reasons for that evaluation.

[0043] The prompt creation unit 13 determines whether the deal was concluded based on the evaluation results indicating the validity of the proposal (step S38). If the evaluation is determined to be negative (no), the prompt creation unit 13 generates a prompt for extracting refinement points using the reason why the deal was not concluded (step S39). The prompt creation unit 13 inputs the prompt for extracting refinement points into the sales generation AI 22 (step S40) and obtains the output of refinement points (step S41). The refinement points are output in a table format that describes what was wrong with each specification of the company's product or service based on the customer's evaluation. The process returns to step S24, and steps S24 to S38 are repeated. At this time, in step 24, the prompt creation unit 13 creates a prompt for creating hearing content with added refinement points.

[0044] On the other hand, if the evaluation is determined to be positive = the deal is closed (Step S38; YES), the information output unit 15 outputs a summary of the proposal content, which includes the proposal content and evaluation results, and summarizes the history of statements made by the sales generation AI 22 and the customer generation AI 21 up to that point (Step S42). This process can simply involve listing each sentence in a single file, or it can be summarized using the generation AI. If the power is not turned off (Step S43; NO), the process returns to Step S21 and repeats Steps S21 to S43. If the power is turned off (Step S43; YES), the process terminates.

[0045] According to the proposal creation support device 1 of Embodiment 2, by learning the customer's attributes and situation, past business negotiations with the customer, past order records from the customer, and interactions with sales, and having a customer-generating AI 21 that replicates the customer and a sales-generating AI 22 that replicates the salesperson conduct business negotiations, it becomes possible to further reduce the time required to create proposals that reflect the customer's latent needs.

[0046] The hardware configuration of the proposal creation support device 1 will be explained using Figure 7. As shown in Figure 7, the proposal creation support device 1 includes a temporary storage unit 301, a storage unit 302, a calculation unit 303, an input unit 304, a transmitting / receiving unit 305, and a display unit 306. The temporary storage unit 301, storage unit 302, input unit 304, transmitting / receiving unit 305, and display unit 306 are all connected to the calculation unit 303 via a BUS.

[0047] The calculation unit 303 is, for example, a CPU (Central Processing Unit). The calculation unit 303 executes the processing of the prompt creation unit 13 and the information output unit 15 according to the control program stored in the storage unit 302.

[0048] The temporary storage unit 301 is, for example, RAM (Random-Access Memory). The temporary storage unit 301 loads the control program stored in the storage unit 302 and uses it as a work area for the calculation unit 303.

[0049] The memory unit 302 is a non-volatile memory such as flash memory, hard disk, DVD-RAM (Digital Versatile Disc - Random Access Memory), or DVD-RW (Digital Versatile Disc - ReWritable). The memory unit 302 pre-stores a program for causing the calculation unit 303 to perform processing of the proposal creation support device 1, and also supplies the information stored by this program to the calculation unit 303 according to the instructions of the calculation unit 303, and stores the information supplied from the calculation unit 303. The speech history storage unit 14 and the data storage unit 16 are configured in the memory unit 302.

[0050] The input unit 304 is an interface device that connects input devices such as keyboards, pointing devices, and voice input devices to the BUS. Information entered by the user is supplied to the calculation unit 303 via the input unit 304. The input unit 304 functions as a customer information acquisition unit 11.

[0051] The transmitting / receiving unit 305 is a network termination device or wireless communication device connected to a network, and a serial interface or LAN (Local Area Network) interface connected to them. The transmitting / receiving unit 305 functions as a customer information acquisition unit 11 and an information output unit 15.

[0052] The display unit 306 is a display device such as an LCD (Liquid Crystal Display) or an organic EL (electroluminescence) display. The display unit 306 functions as an information output unit 15.

[0053] The processing of the customer information acquisition unit 11, question information acquisition unit 12, prompt creation unit 13, speech history storage unit 14, information output unit 15, and data storage unit 16 of the proposal creation support device 1 shown in Figures 1 and 4 is performed by a control program that uses resources such as the temporary storage unit 301, calculation unit 303, storage unit 302, input unit 304, transmission / reception unit 305, and display unit 306 for processing.

[0054] Furthermore, the aforementioned hardware configuration and flowchart are examples only and can be changed and modified as needed.

[0055] The core components of the proposal creation support device 1, such as the calculation unit 303, temporary storage unit 301, storage unit 302, input unit 304, transmission / reception unit 305, and display unit 306, can be implemented using a standard computer system, rather than a dedicated system. For example, the proposal creation support device 1 can be configured by distributing a computer-readable recording medium such as a flexible disk, CD-ROM (Compact Disc - Read Only Memory), or DVD-ROM (Digital Versatile Disc - Read Only Memory) containing a computer program for performing the aforementioned operations, and then installing the computer program on a computer. Alternatively, the computer program can be stored in a storage device on a server device on a communication network such as the Internet, and the proposal creation support device 1 can be configured by downloading it from a standard computer system.

[0056] Furthermore, if the functions of the proposal creation support device 1 are realized through a division of labor between the OS (Operating System) and the application program, or through collaboration between the OS and the application program, then only the application program portion may be stored on the recording medium or storage device.

[0057] Furthermore, it is possible to superimpose a computer program onto the carrier wave and provide it via a communication network. For example, the computer program may be posted on a bulletin board system (BBS) on the communication network and provided via the communication network. The system may then be configured to execute the aforementioned processing by starting this computer program and running it under the control of the OS, just like other application programs.

[0058] In the above embodiment 2, general prompts were used when creating the sales generation AI 22, but this is not limited to that. For example, the generation AI may be trained on the attributes of the salesperson, past business negotiations with customers, and past order records from customers to create a sales generation AI 22 that replicates a salesperson.

[0059] In embodiments 1 and 2 described above, the speech history storage unit 14 sequentially stored prompts created by the prompt creation unit 13, but it is not limited to this. The speech history storage unit 14 may store the speech history with customer-generated AI 21 and the speech history with sales-generated AI 22, and the prompt creation unit 13 may store customer-reproduced prompts and sales-reproduced prompts, and create prompts by sequentially adding the speech history stored in the speech history storage unit 14.

[0060] In embodiments 1 and 2 described above, the server device 2 is equipped with customer-generating AI 21 and sales-generating AI 22, but the proposal creation support device 1 may be equipped with these generating AIs.

[0061] In embodiments 1 and 2 described above, a question prompt was created by adding the content of the question to the customer reproduction prompt. However, the system is not limited to this configuration; it is also possible to input the customer reproduction prompt into the customer generation AI 21, then create the question prompt and input it into the customer generation AI 21. Similarly, a question prompt for creating question content based on the sales reproduction prompt was created to ask questions about the content of the question asked to the customer. However, the system is not limited to this configuration; it is also possible to input the sales reproduction prompt into the sales generation AI 22, then create the question prompt for creating question content and input it into the sales generation AI 22.

[0062] In embodiments 1 and 2 described above, the message history is sequentially added to prompts created after the initial prompt. However, the invention is not limited to this, and prompts that do not add the message history may be created.

[0063] In the above embodiment 2, the customer generation AI 21 that replicates a customer and the sales generation AI 22 that replicates a salesperson were described separately, but they may also be implemented using the same generation AI.

[0064] Although preferred embodiments have been described in detail above, the invention is not limited to the embodiments described above, and various modifications and substitutions can be made to Embodiment 1 described above without departing from the scope of the claims.

[0065] The various aspects of this disclosure are summarized below as an appendix.

[0066] (Note 1) A customer information acquisition unit that acquires at least one of the following: negotiation history information showing past business negotiations with the customer, or order history information showing the order history from the customer. A prompt creation unit creates a customer reproduction prompt that reproduces a customer based on at least one of the sales negotiation history information or the order performance information, inputs it to the first artificial intelligence unit, creates a hearing prompt that includes questions including suggestions to the first artificial intelligence unit, inputs the hearing prompt to the first artificial intelligence unit, and obtains a response from the first artificial intelligence unit. An information output unit that outputs information including the response content from the first artificial intelligence unit, Equipped with, A proposal creation support device. (Note 2) The aforementioned customer information acquisition unit, The system acquires customer basic information indicating the customer's attributes and status, the sales negotiation history information, and the order performance information. The prompt generation unit, Based on the customer basic information, the negotiation history information, and the order performance information, a customer reproduction prompt is created to reproduce the customer; a question including a proposal to the first artificial intelligence unit is added to the customer reproduction prompt to create a hearing prompt; the hearing prompt is input to the first artificial intelligence unit, and a response is obtained from the first artificial intelligence unit. The proposal creation support device described in Appendix 1. (Note 3) The system further includes a speech history storage unit that stores a speech history including the input content to the first artificial intelligence unit and the response content from the first artificial intelligence unit, The prompt generation unit, The aforementioned statement history is added sequentially to create the hearing prompt. A proposal creation support device as described in Appendix 1 or 2. (Note 4) The system further includes a question information acquisition unit that acquires question information indicating a question that includes a proposal to the first artificial intelligence unit, The prompt generation unit, Create the hearing prompt which includes questions that include suggestions indicated by the aforementioned question information. A proposal creation support device as described in any of the appendices 1 to 3. (Note 5) The prompt generation unit, A sales simulation prompt is created to simulate a sales transaction and input into a second artificial intelligence unit; a prompt for creating interview content is created to ask questions about the content of the interview with the customer and input into the second artificial intelligence unit; the answer to the interview content is obtained from the second artificial intelligence unit, and the interview prompt is created that includes the interview content obtained from the second artificial intelligence unit. A proposal creation support device as described in any of the appendices 1 to 4. (Note 6) It further includes a data storage unit for storing data related to the company's products or services, The prompt generation unit, The aforementioned hearing prompt is input to the first artificial intelligence unit, a response is obtained from the first artificial intelligence unit, documents related to the response from the first artificial intelligence unit are searched from the document storage unit, a proposal creation prompt asking about the proposal content is created based on the data of the searched documents and input to the second artificial intelligence unit, a response regarding the company's products or services is obtained from the second artificial intelligence unit, a customer feedback creation prompt including the proposal content obtained from the second artificial intelligence unit is created, the customer feedback creation prompt is input to the first artificial intelligence unit, and a response regarding the proposal content is obtained from the first artificial intelligence unit. The proposal creation support device described in Appendix 5. (Note 7) The system further includes a speech history storage unit that stores a speech history including the input content to the first artificial intelligence unit and the response content from the first artificial intelligence unit, and the input content to the second artificial intelligence unit and the response content from the second artificial intelligence unit. The aforementioned information output unit is Outputs a summary of the proposal, including the aforementioned statement history. A proposal creation support device as described in Appendix 5 or 6. (Note 8) The response to the proposal from the first artificial intelligence department is an evaluation result of the proposal, including whether the proposal is valid and the reasons for that evaluation. The prompt generation unit, Based on the evaluation results of the aforementioned proposal, it is determined whether the deal will be concluded or not. If it is determined that the deal will not be concluded, a prompt for extracting refinement points is generated, which asks for refinement points that indicate which elements should be customized to be evaluated favorably by the first artificial intelligence unit, using the reason why the deal was concluded. This prompt is then input to the second artificial intelligence unit, and the response regarding the refinement points is obtained from the second artificial intelligence unit. A prompt for creating the hearing content is then created, incorporating the refinement points obtained from the second artificial intelligence unit. A proposal creation support device as described in any of the appendices 5 to 7. (Note 9) A proposal creation support device described in any of Appendix 1 to 8, A server device having at least the first artificial intelligence unit, A proposal creation support system equipped with the following features. (Note 10) The proposal creation support device performs the following actions: A step of creating a customer reproduction prompt that reproduces a customer based on at least one of the following: negotiation history information showing past business negotiations with the customer, or order history information showing the customer's order history. Steps include creating a hearing prompt that includes questions, including suggestions for the first artificial intelligence department, The steps include inputting the customer reproduction prompt and the hearing prompt to the first artificial intelligence unit, or inputting the customer reproduction prompt to the first artificial intelligence unit and then inputting the hearing prompt to the first artificial intelligence unit, The steps include outputting information including the response content from the first artificial intelligence unit, Equipped with, Methods for supporting proposal creation. (Note 11) Computers, A prompt creation unit creates a customer reproduction prompt that reproduces a customer based on at least one of the following: negotiation history information showing past negotiations with a customer, or order history information showing the customer's order history; inputs this prompt to the first artificial intelligence unit; creates a hearing prompt that includes questions including suggestions to the first artificial intelligence unit; inputs the hearing prompt to the first artificial intelligence unit; and obtains a response from the first artificial intelligence unit. An information output unit that outputs information including the response content from the first artificial intelligence unit. To make it function as program. [Explanation of Symbols]

[0067] 1 Proposal creation support device, 2 Server device, 11 Customer information acquisition unit, 12 Question information acquisition unit, 13 Prompt creation unit, 14 Speech history storage unit, 15 Information output unit, 16 Document storage unit, 21 Customer generation AI, 22 Sales generation AI, 100 Proposal creation support system, 301 Temporary storage unit, 302 Storage unit, 303 Calculation unit, 304 Input unit, 305 Transmission / reception unit, 306 Display unit.

Claims

1. A customer information acquisition unit that acquires at least one of the following: negotiation history information showing past business negotiations with the customer, or order history information showing the order history from the customer. A prompt creation unit creates a customer reproduction prompt that reproduces a customer based on at least one of the sales negotiation history information or the order performance information, inputs it to the first artificial intelligence unit, creates a hearing prompt that includes questions including suggestions to the first artificial intelligence unit, inputs the hearing prompt to the first artificial intelligence unit, and obtains a response from the first artificial intelligence unit. An information output unit that outputs information including the response content from the first artificial intelligence unit, Equipped with, A proposal creation support device.

2. The aforementioned customer information acquisition unit, The system acquires customer basic information indicating the customer's attributes and status, the sales negotiation history information, and the order performance information. The prompt generation unit, Based on the customer basic information, the negotiation history information, and the order performance information, a customer reproduction prompt is created to reproduce the customer; a question including a proposal to the first artificial intelligence unit is added to the customer reproduction prompt to create a hearing prompt; the hearing prompt is input to the first artificial intelligence unit, and a response is obtained from the first artificial intelligence unit. The proposal creation support device according to claim 1.

3. The system further includes a speech history storage unit that stores a speech history including the content of input to the first artificial intelligence unit and the content of the response from the first artificial intelligence unit, The prompt generation unit, The aforementioned statement history is added sequentially to create the hearing prompt. A proposal creation support device according to claim 1 or 2.

4. The system further includes a question information acquisition unit that acquires question information indicating a question that includes a proposal to the first artificial intelligence unit, The prompt generation unit, Create the hearing prompt which includes questions that include suggestions indicated by the aforementioned question information. A proposal creation support device according to claim 1 or 2.

5. The prompt generation unit, A sales simulation prompt is created to simulate a sales transaction and input into the second artificial intelligence unit; a prompt for creating interview content is created to ask questions about the content of the interview with the customer and input into the second artificial intelligence unit; the answer to the interview content is obtained from the second artificial intelligence unit, and the interview prompt is created that includes the interview content obtained from the second artificial intelligence unit. A proposal creation support device according to claim 1 or 2.

6. It further includes a data storage unit for storing data related to the company's products or services, The prompt generation unit, The aforementioned hearing prompt is input to the first artificial intelligence unit, a response is obtained from the first artificial intelligence unit, documents related to the response from the first artificial intelligence unit are searched from the document storage unit, a proposal creation prompt asking about the proposal content is created based on the data of the searched documents and input to the second artificial intelligence unit, a response regarding the company's products or services is obtained from the second artificial intelligence unit, a customer feedback creation prompt including the proposal content obtained from the second artificial intelligence unit is created, the customer feedback creation prompt is input to the first artificial intelligence unit, and a response regarding the proposal content is obtained from the first artificial intelligence unit. The proposal creation support device according to claim 5.

7. The system further includes a speech history storage unit that stores a speech history including the input content to the first artificial intelligence unit and the response content from the first artificial intelligence unit, and the input content to the second artificial intelligence unit and the response content from the second artificial intelligence unit. The aforementioned information output unit is Outputs a summary of the proposal, including the aforementioned statement history. The proposal creation support device according to claim 5.

8. The response to the proposal from the first artificial intelligence department is an evaluation result of the proposal, including whether the proposal is valid and the reasons for that evaluation. The prompt generation unit, Based on the evaluation results of the aforementioned proposal, it is determined whether the deal is concluded or not. If it is determined that the deal is concluded or not, a prompt for extracting refinement points is generated, which asks for refinement points that indicate which elements should be customized to be evaluated favorably by the first artificial intelligence unit, using the reason why the deal was concluded. This prompt is then input to the second artificial intelligence unit, and after obtaining the refinement points from the second artificial intelligence unit, a prompt for creating the hearing content is created, incorporating the refinement points obtained from the second artificial intelligence unit. The proposal creation support device according to claim 5.

9. A proposal creation support device according to claim 1 or 2, A server device having at least the first artificial intelligence unit, A proposal creation support system equipped with the following features.

10. The proposal creation support device performs the following actions: A step of creating a customer reproduction prompt that reproduces a customer based on at least one of the following: negotiation history information showing past business negotiations with the customer, or order history information showing the customer's order history. The first step is to create a hearing prompt that includes questions, including suggestions for the artificial intelligence department, The steps include inputting the customer reproduction prompt and the hearing prompt to the first artificial intelligence unit, or inputting the customer reproduction prompt to the first artificial intelligence unit and then inputting the hearing prompt to the first artificial intelligence unit, The steps include outputting information including the response content from the first artificial intelligence unit, Equipped with, Methods for supporting proposal creation.

11. Computers, A prompt creation unit creates a customer reproduction prompt that reproduces a customer based on at least one of the following: negotiation history information showing past negotiations with a customer, or order history information showing the customer's order history; inputs this prompt to the first artificial intelligence unit; creates a hearing prompt that includes questions including suggestions to the first artificial intelligence unit; inputs the hearing prompt to the first artificial intelligence unit; and obtains a response from the first artificial intelligence unit. An information output unit that outputs information including the response content from the first artificial intelligence unit. To make it function as program.

Images